From eaf99c749d43ae74ac7ffece5512f3c73f01dfd2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 6 Aug 2014 10:08:32 +0200
Subject: drm: Perform cmdline mode parsing during connector initialisation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

i915.ko has a custom fbdev initialisation routine that aims to preserve
the current mode set by the BIOS, unless overruled by the user. The
user's wishes are determined by what, if any, mode is specified on the
command line (via the video= parameter). However, that command line mode
is first parsed by drm_fb_helper_initial_config() which is called after
i915.ko's custom initial_config() as a fallback method. So in order for
us to honour it, we need to move the cmdline parser earlier. If we
perform the connector cmdline parsing as soon as we initialise the
connector, that cmdline mode and forced status is then available even if
the fbdev helper is not compiled in or never called.

We also then expose the cmdline user mode in the connector mode lists.

v2: Rebase after connector->name upheaval.

v3: Adapt mga200 to look for the cmdline mode in the new place. Nicely
simplifies things while at that.

v4: Fix checkpatch.

v5: Select FB_CMDLINE to adapt to the changed fbdev patch.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=73154
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> (v2)
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org> (v2)
Cc: dri-devel@lists.freedesktop.org
Cc: Julia Lemire <jlemire@matrox.com>
Cc: Dave Airlie <airlied@redhat.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_crtc.h      | 1 +
 include/drm/drm_fb_helper.h | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index f1105d0da059..c530b4920a09 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -548,6 +548,7 @@ struct drm_connector {
 	void *helper_private;
 
 	/* forced on connector */
+	struct drm_cmdline_mode cmdline_mode;
 	enum drm_connector_force force;
 	bool override_edid;
 	uint32_t encoder_ids[DRM_CONNECTOR_MAX_ENCODER];
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index bfd329d613c4..f4ad254e3488 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -77,7 +77,6 @@ struct drm_fb_helper_funcs {
 
 struct drm_fb_helper_connector {
 	struct drm_connector *connector;
-	struct drm_cmdline_mode cmdline_mode;
 };
 
 struct drm_fb_helper {
-- 
cgit v1.2.3


From 4ed0ce3d0bccd74416ba6beb33a8a79d1617e97b Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 6 Aug 2014 14:49:53 +0300
Subject: drm: Disable vblank interrupt immediately when drm_vblank_offdelay<0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make drm_vblank_put() disable the vblank interrupt immediately when the
refcount drops to zero and drm_vblank_offdelay<0.

v2: Preserve the current drm_vblank_offdelay==0 'never disable' behaviur

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 Documentation/DocBook/drm.tmpl |  1 +
 drivers/gpu/drm/drm_drv.c      |  4 ++--
 drivers/gpu/drm/drm_irq.c      | 11 +++++++----
 include/drm/drmP.h             |  2 +-
 4 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 1d3756d3176c..55923d00bd52 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -3386,6 +3386,7 @@ void (*disable_vblank) (struct drm_device *dev, int crtc);</synopsis>
       by scheduling a timer. The delay is accessible through the vblankoffdelay
       module parameter or the <varname>drm_vblank_offdelay</varname> global
       variable and expressed in milliseconds. Its default value is 5000 ms.
+      Zero means never disable, and a negative value means disable immediately.
     </para>
     <para>
       When a vertical blanking interrupt occurs drivers only need to call the
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 92bc6b1d9646..db03e16ca817 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -39,7 +39,7 @@
 unsigned int drm_debug = 0;	/* 1 to enable debug output */
 EXPORT_SYMBOL(drm_debug);
 
-unsigned int drm_vblank_offdelay = 5000;    /* Default to 5000 msecs. */
+int drm_vblank_offdelay = 5000;    /* Default to 5000 msecs. */
 
 unsigned int drm_timestamp_precision = 20;  /* Default to 20 usecs. */
 
@@ -53,7 +53,7 @@ MODULE_AUTHOR(CORE_AUTHOR);
 MODULE_DESCRIPTION(CORE_DESC);
 MODULE_LICENSE("GPL and additional rights");
 MODULE_PARM_DESC(debug, "Enable debug output");
-MODULE_PARM_DESC(vblankoffdelay, "Delay until vblank irq auto-disable [msecs]");
+MODULE_PARM_DESC(vblankoffdelay, "Delay until vblank irq auto-disable [msecs] (0: never disable, <0: disable immediately)");
 MODULE_PARM_DESC(timestamp_precision_usec, "Max. error on timestamps [usecs]");
 MODULE_PARM_DESC(timestamp_monotonic, "Use monotonic timestamps");
 
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index b2428cb0c64d..99145c4d536b 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -993,10 +993,13 @@ void drm_vblank_put(struct drm_device *dev, int crtc)
 	BUG_ON(atomic_read(&vblank->refcount) == 0);
 
 	/* Last user schedules interrupt disable */
-	if (atomic_dec_and_test(&vblank->refcount) &&
-	    (drm_vblank_offdelay > 0))
-		mod_timer(&vblank->disable_timer,
-			  jiffies + ((drm_vblank_offdelay * HZ)/1000));
+	if (atomic_dec_and_test(&vblank->refcount)) {
+		if (drm_vblank_offdelay < 0)
+			vblank_disable_fn((unsigned long)vblank);
+		else if (drm_vblank_offdelay > 0)
+			mod_timer(&vblank->disable_timer,
+				  jiffies + ((drm_vblank_offdelay * HZ)/1000));
+	}
 }
 EXPORT_SYMBOL(drm_vblank_put);
 
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index a57646382086..24b32d453c60 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1345,7 +1345,7 @@ extern void drm_put_dev(struct drm_device *dev);
 extern void drm_unplug_dev(struct drm_device *dev);
 extern unsigned int drm_debug;
 
-extern unsigned int drm_vblank_offdelay;
+extern int drm_vblank_offdelay;
 extern unsigned int drm_timestamp_precision;
 extern unsigned int drm_timestamp_monotonic;
 
-- 
cgit v1.2.3


From 00185e667009dda907887a4f84fbd02c6e651a49 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 6 Aug 2014 14:49:54 +0300
Subject: drm: Add dev->vblank_disable_immediate flag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a flag to drm_device which will cause the vblank code to bypass the
disable timer and always disable the vblank interrupt immediately when
the last reference is dropped.

v2: Add some notes about the flag to the kernel doc

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 Documentation/DocBook/drm.tmpl |  6 ++++++
 drivers/gpu/drm/drm_irq.c      |  2 +-
 include/drm/drmP.h             | 10 ++++++++++
 3 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 55923d00bd52..583edbffff1a 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -3387,6 +3387,12 @@ void (*disable_vblank) (struct drm_device *dev, int crtc);</synopsis>
       module parameter or the <varname>drm_vblank_offdelay</varname> global
       variable and expressed in milliseconds. Its default value is 5000 ms.
       Zero means never disable, and a negative value means disable immediately.
+      Drivers may override the behaviour by setting the
+      <structname>drm_device</structname>
+      <structfield>vblank_disable_immediate</structfield> flag, which when set
+      causes vblank interrupts to be disabled immediately regardless of the
+      drm_vblank_offdelay value. The flag should only be set if there's a
+      properly working hardware vblank counter present.
     </para>
     <para>
       When a vertical blanking interrupt occurs drivers only need to call the
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 99145c4d536b..8dbcc3f892d5 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -994,7 +994,7 @@ void drm_vblank_put(struct drm_device *dev, int crtc)
 
 	/* Last user schedules interrupt disable */
 	if (atomic_dec_and_test(&vblank->refcount)) {
-		if (drm_vblank_offdelay < 0)
+		if (dev->vblank_disable_immediate || drm_vblank_offdelay < 0)
 			vblank_disable_fn((unsigned long)vblank);
 		else if (drm_vblank_offdelay > 0)
 			mod_timer(&vblank->disable_timer,
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 24b32d453c60..17a5c10474bd 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1074,6 +1074,16 @@ struct drm_device {
 	 */
 	bool vblank_disable_allowed;
 
+	/*
+	 * If true, vblank interrupt will be disabled immediately when the
+	 * refcount drops to zero, as opposed to via the vblank disable
+	 * timer.
+	 * This can be set to true it the hardware has a working vblank
+	 * counter and the driver uses drm_vblank_on() and drm_vblank_off()
+	 * appropriately.
+	 */
+	bool vblank_disable_immediate;
+
 	/* array of size num_crtcs */
 	struct drm_vblank_crtc *vblank;
 
-- 
cgit v1.2.3


From 020178a1bcadf20b9d057988984f374c905d542e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 22 May 2014 19:36:03 +0300
Subject: drm: Add drm_crtc_vblank_waitqueue()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a small static inline helper to grab the vblank wait queue based on
the drm_crtc.

This is useful for drivers to do internal vblank waits using
wait_event() & co.

v2: Pimp commit message (Daniel)
    Add kernel doc (Daniel)

Suggested-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 Documentation/DocBook/drm.tmpl |  1 +
 include/drm/drmP.h             | 11 +++++++++++
 2 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 1d3756d3176c..972759489376 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -3400,6 +3400,7 @@ void (*disable_vblank) (struct drm_device *dev, int crtc);</synopsis>
     <sect2>
       <title>Vertical Blanking and Interrupt Handling Functions Reference</title>
 !Edrivers/gpu/drm/drm_irq.c
+!Iinclude/drm/drmP.h drm_crtc_vblank_waitqueue
     </sect2>
   </sect1>
 
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index d3d9be6b83ef..bb44c1ee557d 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1344,6 +1344,17 @@ extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,
 extern void drm_calc_timestamping_constants(struct drm_crtc *crtc,
 					    const struct drm_display_mode *mode);
 
+/**
+ * drm_crtc_vblank_waitqueue - get vblank waitqueue for the CRTC
+ * @crtc: which CRTC's vblank waitqueue to retrieve
+ *
+ * This function returns a pointer to the vblank waitqueue for the CRTC.
+ * Drivers can use this to implement vblank waits using wait_event() & co.
+ */
+static inline wait_queue_head_t *drm_crtc_vblank_waitqueue(struct drm_crtc *crtc)
+{
+	return &crtc->dev->vblank[drm_crtc_index(crtc)].queue;
+}
 
 /* Modesetting support */
 extern void drm_vblank_pre_modeset(struct drm_device *dev, int crtc);
-- 
cgit v1.2.3


From 2a297cce2e775812e9d6ca84c3ab92cee5c38e25 Mon Sep 17 00:00:00 2001
From: Sonika Jindal <sonika.jindal@intel.com>
Date: Tue, 5 Aug 2014 11:26:54 +0530
Subject: drm: Add rotation_property to mode_config
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Sonika Jindal <sonika.jindal@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_crtc.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index f1105d0da059..62f73bdbcc47 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -821,6 +821,7 @@ struct drm_mode_config {
 	struct drm_property *dpms_property;
 	struct drm_property *path_property;
 	struct drm_property *plane_type_property;
+	struct drm_property *rotation_property;
 
 	/* DVI-I properties */
 	struct drm_property *dvi_i_subconnector_property;
-- 
cgit v1.2.3


From 10f637bf292ba501f9b9e9df6dfe21d8fa521fbd Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 29 Jul 2014 13:47:11 +0200
Subject: drm: Add drm_plane/connector_index

In the atomic state we'll have an array of states for crtcs, planes
and connectors and need to be able to at them by their index. We
already have a drm_crtc_index function so add the missing ones for
planes and connectors.

If it later on turns out that the list walking is too expensive we can
add the index to the relevant modeset objects.

Rob Clark doesn't like the loops too much, but we can always add an
obj->idx parameter later on. And for now reiterating is actually safer
since nowadays we have hotpluggable connectors (thanks to DP MST).

v2: Fix embarrassing copypasta fail in kerneldoc and header
declarations, spotted by Matt Roper.

Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_crtc.h     |  2 ++
 2 files changed, 48 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 66d3bfb8d264..f3ef461deeb8 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1021,6 +1021,29 @@ void drm_connector_cleanup(struct drm_connector *connector)
 }
 EXPORT_SYMBOL(drm_connector_cleanup);
 
+/**
+ * drm_connector_index - find the index of a registered connector
+ * @connector: connector to find index for
+ *
+ * Given a registered connector, return the index of that connector within a DRM
+ * device's list of connectors.
+ */
+unsigned int drm_connector_index(struct drm_connector *connector)
+{
+	unsigned int index = 0;
+	struct drm_connector *tmp;
+
+	list_for_each_entry(tmp, &connector->dev->mode_config.connector_list, head) {
+		if (tmp == connector)
+			return index;
+
+		index++;
+	}
+
+	BUG();
+}
+EXPORT_SYMBOL(drm_connector_index);
+
 /**
  * drm_connector_register - register a connector
  * @connector: the connector to register
@@ -1325,6 +1348,29 @@ void drm_plane_cleanup(struct drm_plane *plane)
 }
 EXPORT_SYMBOL(drm_plane_cleanup);
 
+/**
+ * drm_plane_index - find the index of a registered plane
+ * @plane: plane to find index for
+ *
+ * Given a registered plane, return the index of that CRTC within a DRM
+ * device's list of planes.
+ */
+unsigned int drm_plane_index(struct drm_plane *plane)
+{
+	unsigned int index = 0;
+	struct drm_plane *tmp;
+
+	list_for_each_entry(tmp, &plane->dev->mode_config.plane_list, head) {
+		if (tmp == plane)
+			return index;
+
+		index++;
+	}
+
+	BUG();
+}
+EXPORT_SYMBOL(drm_plane_index);
+
 /**
  * drm_plane_force_disable - Forcibly disable a plane
  * @plane: plane to disable
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index c530b4920a09..9f18e7022ab3 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -904,6 +904,7 @@ int drm_connector_register(struct drm_connector *connector);
 void drm_connector_unregister(struct drm_connector *connector);
 
 extern void drm_connector_cleanup(struct drm_connector *connector);
+extern unsigned int drm_connector_index(struct drm_connector *connector);
 /* helper to unplug all connectors from sysfs for device */
 extern void drm_connector_unplug_all(struct drm_device *dev);
 
@@ -943,6 +944,7 @@ extern int drm_plane_init(struct drm_device *dev,
 			  const uint32_t *formats, uint32_t format_count,
 			  bool is_primary);
 extern void drm_plane_cleanup(struct drm_plane *plane);
+extern unsigned int drm_plane_index(struct drm_plane *plane);
 extern void drm_plane_force_disable(struct drm_plane *plane);
 extern int drm_crtc_check_viewport(const struct drm_crtc *crtc,
 				   int x, int y,
-- 
cgit v1.2.3


From a6a8bb848d5ca40bc0eb708ddeb23df2b0eca1fb Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 25 Jul 2014 17:47:18 +0200
Subject: drm: Move modeset_lock_all helpers to drm_modeset_lock.[hc]

Somehow we've forgotten about this little bit of OCD.

Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c         | 95 --------------------------------------
 drivers/gpu/drm/drm_modeset_lock.c | 95 ++++++++++++++++++++++++++++++++++++++
 include/drm/drm_crtc.h             |  4 --
 include/drm/drm_modeset_lock.h     |  5 ++
 4 files changed, 100 insertions(+), 99 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index f3ef461deeb8..caaa01f3b353 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -45,101 +45,6 @@ static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
 							struct drm_mode_fb_cmd2 *r,
 							struct drm_file *file_priv);
 
-/**
- * drm_modeset_lock_all - take all modeset locks
- * @dev: drm device
- *
- * This function takes all modeset locks, suitable where a more fine-grained
- * scheme isn't (yet) implemented. Locks must be dropped with
- * drm_modeset_unlock_all.
- */
-void drm_modeset_lock_all(struct drm_device *dev)
-{
-	struct drm_mode_config *config = &dev->mode_config;
-	struct drm_modeset_acquire_ctx *ctx;
-	int ret;
-
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-	if (WARN_ON(!ctx))
-		return;
-
-	mutex_lock(&config->mutex);
-
-	drm_modeset_acquire_init(ctx, 0);
-
-retry:
-	ret = drm_modeset_lock(&config->connection_mutex, ctx);
-	if (ret)
-		goto fail;
-	ret = drm_modeset_lock_all_crtcs(dev, ctx);
-	if (ret)
-		goto fail;
-
-	WARN_ON(config->acquire_ctx);
-
-	/* now we hold the locks, so now that it is safe, stash the
-	 * ctx for drm_modeset_unlock_all():
-	 */
-	config->acquire_ctx = ctx;
-
-	drm_warn_on_modeset_not_all_locked(dev);
-
-	return;
-
-fail:
-	if (ret == -EDEADLK) {
-		drm_modeset_backoff(ctx);
-		goto retry;
-	}
-}
-EXPORT_SYMBOL(drm_modeset_lock_all);
-
-/**
- * drm_modeset_unlock_all - drop all modeset locks
- * @dev: device
- *
- * This function drop all modeset locks taken by drm_modeset_lock_all.
- */
-void drm_modeset_unlock_all(struct drm_device *dev)
-{
-	struct drm_mode_config *config = &dev->mode_config;
-	struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx;
-
-	if (WARN_ON(!ctx))
-		return;
-
-	config->acquire_ctx = NULL;
-	drm_modeset_drop_locks(ctx);
-	drm_modeset_acquire_fini(ctx);
-
-	kfree(ctx);
-
-	mutex_unlock(&dev->mode_config.mutex);
-}
-EXPORT_SYMBOL(drm_modeset_unlock_all);
-
-/**
- * drm_warn_on_modeset_not_all_locked - check that all modeset locks are locked
- * @dev: device
- *
- * Useful as a debug assert.
- */
-void drm_warn_on_modeset_not_all_locked(struct drm_device *dev)
-{
-	struct drm_crtc *crtc;
-
-	/* Locking is currently fubar in the panic handler. */
-	if (oops_in_progress)
-		return;
-
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
-		WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
-
-	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
-	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
-}
-EXPORT_SYMBOL(drm_warn_on_modeset_not_all_locked);
-
 /* Avoid boilerplate.  I'm tired of typing. */
 #define DRM_ENUM_NAME_FN(fnname, list)				\
 	const char *fnname(int val)				\
diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
index 0dc57d5ecd10..73e6534fd0aa 100644
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -56,6 +56,101 @@
  */
 
 
+/**
+ * drm_modeset_lock_all - take all modeset locks
+ * @dev: drm device
+ *
+ * This function takes all modeset locks, suitable where a more fine-grained
+ * scheme isn't (yet) implemented. Locks must be dropped with
+ * drm_modeset_unlock_all.
+ */
+void drm_modeset_lock_all(struct drm_device *dev)
+{
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_modeset_acquire_ctx *ctx;
+	int ret;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (WARN_ON(!ctx))
+		return;
+
+	mutex_lock(&config->mutex);
+
+	drm_modeset_acquire_init(ctx, 0);
+
+retry:
+	ret = drm_modeset_lock(&config->connection_mutex, ctx);
+	if (ret)
+		goto fail;
+	ret = drm_modeset_lock_all_crtcs(dev, ctx);
+	if (ret)
+		goto fail;
+
+	WARN_ON(config->acquire_ctx);
+
+	/* now we hold the locks, so now that it is safe, stash the
+	 * ctx for drm_modeset_unlock_all():
+	 */
+	config->acquire_ctx = ctx;
+
+	drm_warn_on_modeset_not_all_locked(dev);
+
+	return;
+
+fail:
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(ctx);
+		goto retry;
+	}
+}
+EXPORT_SYMBOL(drm_modeset_lock_all);
+
+/**
+ * drm_modeset_unlock_all - drop all modeset locks
+ * @dev: device
+ *
+ * This function drop all modeset locks taken by drm_modeset_lock_all.
+ */
+void drm_modeset_unlock_all(struct drm_device *dev)
+{
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx;
+
+	if (WARN_ON(!ctx))
+		return;
+
+	config->acquire_ctx = NULL;
+	drm_modeset_drop_locks(ctx);
+	drm_modeset_acquire_fini(ctx);
+
+	kfree(ctx);
+
+	mutex_unlock(&dev->mode_config.mutex);
+}
+EXPORT_SYMBOL(drm_modeset_unlock_all);
+
+/**
+ * drm_warn_on_modeset_not_all_locked - check that all modeset locks are locked
+ * @dev: device
+ *
+ * Useful as a debug assert.
+ */
+void drm_warn_on_modeset_not_all_locked(struct drm_device *dev)
+{
+	struct drm_crtc *crtc;
+
+	/* Locking is currently fubar in the panic handler. */
+	if (oops_in_progress)
+		return;
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
+		WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
+
+	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
+}
+EXPORT_SYMBOL(drm_warn_on_modeset_not_all_locked);
+
 /**
  * drm_modeset_acquire_init - initialize acquire context
  * @ctx: the acquire context
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 9f18e7022ab3..a11d73422e7f 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -218,10 +218,6 @@ struct drm_property {
 	struct list_head enum_blob_list;
 };
 
-void drm_modeset_lock_all(struct drm_device *dev);
-void drm_modeset_unlock_all(struct drm_device *dev);
-void drm_warn_on_modeset_not_all_locked(struct drm_device *dev);
-
 struct drm_crtc;
 struct drm_connector;
 struct drm_encoder;
diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h
index 402aa7a6a058..cf61e857bc06 100644
--- a/include/drm/drm_modeset_lock.h
+++ b/include/drm/drm_modeset_lock.h
@@ -120,6 +120,11 @@ int drm_modeset_lock_interruptible(struct drm_modeset_lock *lock,
 void drm_modeset_unlock(struct drm_modeset_lock *lock);
 
 struct drm_device;
+
+void drm_modeset_lock_all(struct drm_device *dev);
+void drm_modeset_unlock_all(struct drm_device *dev);
+void drm_warn_on_modeset_not_all_locked(struct drm_device *dev);
+
 int drm_modeset_lock_all_crtcs(struct drm_device *dev,
 		struct drm_modeset_acquire_ctx *ctx);
 
-- 
cgit v1.2.3


From d059f652e73c35678d28d4cd09ab2cec89696af9 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 25 Jul 2014 18:07:40 +0200
Subject: drm: Handle legacy per-crtc locking with full acquire ctx

So drivers using the atomic interfaces expect that they can acquire
additional locks internal to the driver as-needed. Examples would be
locks to protect shared state like shared display PLLs.

Unfortunately the legacy ioctls assume that all locking is fully done
by the drm core. Now for those paths which grab all locks we already
have to keep around an acquire context in dev->mode_config. Helper
functions that implement legacy interfaces in terms of atomic support
can therefore grab this acquire contexts and reuse it.

The only interfaces left are the cursor and pageflip ioctls. So add
functions to grab the crtc lock these need using an acquire context
and preserve it for atomic drivers to reuse.

v2:
- Fixup comments&kerneldoc.
- Drop the WARNING from modeset_lock_all_crtcs since that can be used
  in legacy paths with crtc locking.

v3: Fix a type on the kerneldoc Dave spotted.

Cc: Dave Airlie <airlied@redhat.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c         |  8 ++--
 drivers/gpu/drm/drm_modeset_lock.c | 84 ++++++++++++++++++++++++++++++++++++++
 include/drm/drm_crtc.h             |  6 +++
 include/drm/drm_modeset_lock.h     |  5 +++
 4 files changed, 99 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index caaa01f3b353..ab121b6d980c 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -2801,7 +2801,7 @@ static int drm_mode_cursor_common(struct drm_device *dev,
 	if (crtc->cursor)
 		return drm_mode_cursor_universal(crtc, req, file_priv);
 
-	drm_modeset_lock(&crtc->mutex, NULL);
+	drm_modeset_lock_crtc(crtc);
 	if (req->flags & DRM_MODE_CURSOR_BO) {
 		if (!crtc->funcs->cursor_set && !crtc->funcs->cursor_set2) {
 			ret = -ENXIO;
@@ -2825,7 +2825,7 @@ static int drm_mode_cursor_common(struct drm_device *dev,
 		}
 	}
 out:
-	drm_modeset_unlock(&crtc->mutex);
+	drm_modeset_unlock_crtc(crtc);
 
 	return ret;
 
@@ -4561,7 +4561,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 	if (!crtc)
 		return -ENOENT;
 
-	drm_modeset_lock(&crtc->mutex, NULL);
+	drm_modeset_lock_crtc(crtc);
 	if (crtc->primary->fb == NULL) {
 		/* The framebuffer is currently unbound, presumably
 		 * due to a hotplug event, that userspace has not
@@ -4645,7 +4645,7 @@ out:
 		drm_framebuffer_unreference(fb);
 	if (old_fb)
 		drm_framebuffer_unreference(old_fb);
-	drm_modeset_unlock(&crtc->mutex);
+	drm_modeset_unlock_crtc(crtc);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
index 73e6534fd0aa..4753c8bd5ab5 100644
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -129,6 +129,90 @@ void drm_modeset_unlock_all(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_modeset_unlock_all);
 
+/**
+ * drm_modeset_lock_crtc - lock crtc with hidden acquire ctx
+ * @crtc: drm crtc
+ *
+ * This function locks the given crtc using a hidden acquire context. This is
+ * necessary so that drivers internally using the atomic interfaces can grab
+ * further locks with the lock acquire context.
+ */
+void drm_modeset_lock_crtc(struct drm_crtc *crtc)
+{
+	struct drm_modeset_acquire_ctx *ctx;
+	int ret;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (WARN_ON(!ctx))
+		return;
+
+	drm_modeset_acquire_init(ctx, 0);
+
+retry:
+	ret = drm_modeset_lock(&crtc->mutex, ctx);
+	if (ret)
+		goto fail;
+
+	WARN_ON(crtc->acquire_ctx);
+
+	/* now we hold the locks, so now that it is safe, stash the
+	 * ctx for drm_modeset_unlock_crtc():
+	 */
+	crtc->acquire_ctx = ctx;
+
+	return;
+
+fail:
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(ctx);
+		goto retry;
+	}
+}
+EXPORT_SYMBOL(drm_modeset_lock_crtc);
+
+/**
+ * drm_modeset_legacy_acquire_ctx - find acquire ctx for legacy ioctls
+ * crtc: drm crtc
+ *
+ * Legacy ioctl operations like cursor updates or page flips only have per-crtc
+ * locking, and store the acquire ctx in the corresponding crtc. All other
+ * legacy operations take all locks and use a global acquire context. This
+ * function grabs the right one.
+ */
+struct drm_modeset_acquire_ctx *
+drm_modeset_legacy_acquire_ctx(struct drm_crtc *crtc)
+{
+	if (crtc->acquire_ctx)
+		return crtc->acquire_ctx;
+
+	WARN_ON(!crtc->dev->mode_config.acquire_ctx);
+
+	return crtc->dev->mode_config.acquire_ctx;
+}
+EXPORT_SYMBOL(drm_modeset_legacy_acquire_ctx);
+
+/**
+ * drm_modeset_unlock_crtc - drop crtc lock
+ * @crtc: drm crtc
+ *
+ * This drops the crtc lock acquire with drm_modeset_lock_crtc() and all other
+ * locks acquired through the hidden context.
+ */
+void drm_modeset_unlock_crtc(struct drm_crtc *crtc)
+{
+	struct drm_modeset_acquire_ctx *ctx = crtc->acquire_ctx;
+
+	if (WARN_ON(!ctx))
+		return;
+
+	crtc->acquire_ctx = NULL;
+	drm_modeset_drop_locks(ctx);
+	drm_modeset_acquire_fini(ctx);
+
+	kfree(ctx);
+}
+EXPORT_SYMBOL(drm_modeset_unlock_crtc);
+
 /**
  * drm_warn_on_modeset_not_all_locked - check that all modeset locks are locked
  * @dev: device
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index a11d73422e7f..508817bae538 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -371,6 +371,12 @@ struct drm_crtc {
 	void *helper_private;
 
 	struct drm_object_properties properties;
+
+	/*
+	 * For legacy crtc ioctls so that atomic drivers can get at the locking
+	 * acquire context.
+	 */
+	struct drm_modeset_acquire_ctx *acquire_ctx;
 };
 
 
diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h
index cf61e857bc06..d38e1508f11a 100644
--- a/include/drm/drm_modeset_lock.h
+++ b/include/drm/drm_modeset_lock.h
@@ -120,10 +120,15 @@ int drm_modeset_lock_interruptible(struct drm_modeset_lock *lock,
 void drm_modeset_unlock(struct drm_modeset_lock *lock);
 
 struct drm_device;
+struct drm_crtc;
 
 void drm_modeset_lock_all(struct drm_device *dev);
 void drm_modeset_unlock_all(struct drm_device *dev);
+void drm_modeset_lock_crtc(struct drm_crtc *crtc);
+void drm_modeset_unlock_crtc(struct drm_crtc *crtc);
 void drm_warn_on_modeset_not_all_locked(struct drm_device *dev);
+struct drm_modeset_acquire_ctx *
+drm_modeset_legacy_acquire_ctx(struct drm_crtc *crtc);
 
 int drm_modeset_lock_all_crtcs(struct drm_device *dev,
 		struct drm_modeset_acquire_ctx *ctx);
-- 
cgit v1.2.3


From 3d30a59bfcb7c96d4aacdb053c2ccc49394b2311 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Sun, 27 Jul 2014 13:42:42 +0200
Subject: drm: Move ->old_fb from crtc to plane

Atomic implemenations for legacy ioctls must be able to drop locks.
Which doesn't cause havoc since we only do that while constructing
the new state, so no driver or hardware state change has happened.

The only troubling bit is the fb refcounting the core does - if
someone else has snuck in then it might potentially unref an
outdated framebuffer. To fix that move the old_fb temporary storage
into struct drm_plane for all ioctls, so that the atomic helpers can
update it.

v2: Fix up the error case handling as suggested by Matt Roper and just
grab locks uncoditionally - there's no point in optimizing the locking
for when userspace gets it wrong.

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Dave Airlie <airlied@redhat.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c | 46 ++++++++++++++++++++++++----------------------
 include/drm/drm_crtc.h     |  8 ++++----
 2 files changed, 28 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index ab121b6d980c..cacb460a7145 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1287,19 +1287,21 @@ EXPORT_SYMBOL(drm_plane_index);
  */
 void drm_plane_force_disable(struct drm_plane *plane)
 {
-	struct drm_framebuffer *old_fb = plane->fb;
 	int ret;
 
-	if (!old_fb)
+	if (!plane->fb)
 		return;
 
+	plane->old_fb = plane->fb;
 	ret = plane->funcs->disable_plane(plane);
 	if (ret) {
 		DRM_ERROR("failed to disable plane with busy fb\n");
+		plane->old_fb = NULL;
 		return;
 	}
 	/* disconnect the plane from the fb and crtc: */
-	__drm_framebuffer_unreference(old_fb);
+	__drm_framebuffer_unreference(plane->old_fb);
+	plane->old_fb = NULL;
 	plane->fb = NULL;
 	plane->crtc = NULL;
 }
@@ -2275,23 +2277,21 @@ static int setplane_internal(struct drm_plane *plane,
 			     uint32_t src_w, uint32_t src_h)
 {
 	struct drm_device *dev = plane->dev;
-	struct drm_framebuffer *old_fb = NULL;
 	int ret = 0;
 	unsigned int fb_width, fb_height;
 	int i;
 
+	drm_modeset_lock_all(dev);
 	/* No fb means shut it down */
 	if (!fb) {
-		drm_modeset_lock_all(dev);
-		old_fb = plane->fb;
+		plane->old_fb = plane->fb;
 		ret = plane->funcs->disable_plane(plane);
 		if (!ret) {
 			plane->crtc = NULL;
 			plane->fb = NULL;
 		} else {
-			old_fb = NULL;
+			plane->old_fb = NULL;
 		}
-		drm_modeset_unlock_all(dev);
 		goto out;
 	}
 
@@ -2331,8 +2331,7 @@ static int setplane_internal(struct drm_plane *plane,
 		goto out;
 	}
 
-	drm_modeset_lock_all(dev);
-	old_fb = plane->fb;
+	plane->old_fb = plane->fb;
 	ret = plane->funcs->update_plane(plane, crtc, fb,
 					 crtc_x, crtc_y, crtc_w, crtc_h,
 					 src_x, src_y, src_w, src_h);
@@ -2341,15 +2340,16 @@ static int setplane_internal(struct drm_plane *plane,
 		plane->fb = fb;
 		fb = NULL;
 	} else {
-		old_fb = NULL;
+		plane->old_fb = NULL;
 	}
-	drm_modeset_unlock_all(dev);
 
 out:
 	if (fb)
 		drm_framebuffer_unreference(fb);
-	if (old_fb)
-		drm_framebuffer_unreference(old_fb);
+	if (plane->old_fb)
+		drm_framebuffer_unreference(plane->old_fb);
+	plane->old_fb = NULL;
+	drm_modeset_unlock_all(dev);
 
 	return ret;
 
@@ -2456,7 +2456,7 @@ int drm_mode_set_config_internal(struct drm_mode_set *set)
 	 * crtcs. Atomic modeset will have saner semantics ...
 	 */
 	list_for_each_entry(tmp, &crtc->dev->mode_config.crtc_list, head)
-		tmp->old_fb = tmp->primary->fb;
+		tmp->primary->old_fb = tmp->primary->fb;
 
 	fb = set->fb;
 
@@ -2469,8 +2469,9 @@ int drm_mode_set_config_internal(struct drm_mode_set *set)
 	list_for_each_entry(tmp, &crtc->dev->mode_config.crtc_list, head) {
 		if (tmp->primary->fb)
 			drm_framebuffer_reference(tmp->primary->fb);
-		if (tmp->old_fb)
-			drm_framebuffer_unreference(tmp->old_fb);
+		if (tmp->primary->old_fb)
+			drm_framebuffer_unreference(tmp->primary->old_fb);
+		tmp->primary->old_fb = NULL;
 	}
 
 	return ret;
@@ -4545,7 +4546,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 {
 	struct drm_mode_crtc_page_flip *page_flip = data;
 	struct drm_crtc *crtc;
-	struct drm_framebuffer *fb = NULL, *old_fb = NULL;
+	struct drm_framebuffer *fb = NULL;
 	struct drm_pending_vblank_event *e = NULL;
 	unsigned long flags;
 	int ret = -EINVAL;
@@ -4617,7 +4618,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 			(void (*) (struct drm_pending_event *)) kfree;
 	}
 
-	old_fb = crtc->primary->fb;
+	crtc->primary->old_fb = crtc->primary->fb;
 	ret = crtc->funcs->page_flip(crtc, fb, e, page_flip->flags);
 	if (ret) {
 		if (page_flip->flags & DRM_MODE_PAGE_FLIP_EVENT) {
@@ -4627,7 +4628,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 			kfree(e);
 		}
 		/* Keep the old fb, don't unref it. */
-		old_fb = NULL;
+		crtc->primary->old_fb = NULL;
 	} else {
 		/*
 		 * Warn if the driver hasn't properly updated the crtc->fb
@@ -4643,8 +4644,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 out:
 	if (fb)
 		drm_framebuffer_unreference(fb);
-	if (old_fb)
-		drm_framebuffer_unreference(old_fb);
+	if (crtc->primary->old_fb)
+		drm_framebuffer_unreference(crtc->primary->old_fb);
+	crtc->primary->old_fb = NULL;
 	drm_modeset_unlock_crtc(crtc);
 
 	return ret;
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 508817bae538..279565aa0c33 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -341,10 +341,6 @@ struct drm_crtc {
 	int cursor_x;
 	int cursor_y;
 
-	/* Temporary tracking of the old fb while a modeset is ongoing. Used
-	 * by drm_mode_set_config_internal to implement correct refcounting. */
-	struct drm_framebuffer *old_fb;
-
 	bool enabled;
 
 	/* Requested mode from modesetting. */
@@ -623,6 +619,10 @@ struct drm_plane {
 	struct drm_crtc *crtc;
 	struct drm_framebuffer *fb;
 
+	/* Temporary tracking of the old fb while a modeset is ongoing. Used
+	 * by drm_mode_set_config_internal to implement correct refcounting. */
+	struct drm_framebuffer *old_fb;
+
 	const struct drm_plane_funcs *funcs;
 
 	struct drm_object_properties properties;
-- 
cgit v1.2.3


From cb597bb3a2fbfc871cc1c703fb330d247bd21394 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Sun, 27 Jul 2014 19:09:33 +0200
Subject: drm: trylock modest locking for fbdev panics

In the fbdev code we want to do trylocks only to avoid deadlocks and
other ugly issues. Thus far we've only grabbed the overall modeset
lock, but that already failed to exclude a pile of potential
concurrent operations. With proper atomic support this will be worse.

So add a trylock mode to the modeset locking code which attempts all
locks only with trylocks, if possible. We need to track this in the
locking functions themselves and can't restrict this to drivers since
driver-private w/w mutexes must be treated the same way.

There's still the issue that other driver private locks aren't handled
here at all, but well can't have everything. With this we will at
least not regress, even once atomic allows lots of concurrent kms
activity.

Aside: We should move the acquire context to stack-based allocation in
the callers to get rid of that awful WARN_ON(kmalloc_failed) control
flow which just blows up when memory is short. But that's material for
separate patches.

v2:
- Fix logic inversion fumble in the fb helper.
- Add proper kerneldoc.

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_fb_helper.c    | 10 +++----
 drivers/gpu/drm/drm_modeset_lock.c | 56 ++++++++++++++++++++++++++++++--------
 include/drm/drm_modeset_lock.h     |  6 ++++
 3 files changed, 55 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 3a6b6635e3f5..7b7b9565188f 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -365,11 +365,11 @@ static bool drm_fb_helper_force_kernel_mode(void)
 		if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 			continue;
 
-		/* NOTE: we use lockless flag below to avoid grabbing other
-		 * modeset locks.  So just trylock the underlying mutex
-		 * directly:
+		/*
+		 * NOTE: Use trylock mode to avoid deadlocks and sleeping in
+		 * panic context.
 		 */
-		if (!mutex_trylock(&dev->mode_config.mutex)) {
+		if (__drm_modeset_lock_all(dev, true) != 0) {
 			error = true;
 			continue;
 		}
@@ -378,7 +378,7 @@ static bool drm_fb_helper_force_kernel_mode(void)
 		if (ret)
 			error = true;
 
-		mutex_unlock(&dev->mode_config.mutex);
+		drm_modeset_unlock_all(dev);
 	}
 	return error;
 }
diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
index 4753c8bd5ab5..5280b64a0230 100644
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -57,26 +57,37 @@
 
 
 /**
- * drm_modeset_lock_all - take all modeset locks
- * @dev: drm device
+ * __drm_modeset_lock_all - internal helper to grab all modeset locks
+ * @dev: DRM device
+ * @trylock: trylock mode for atomic contexts
  *
- * This function takes all modeset locks, suitable where a more fine-grained
- * scheme isn't (yet) implemented. Locks must be dropped with
- * drm_modeset_unlock_all.
+ * This is a special version of drm_modeset_lock_all() which can also be used in
+ * atomic contexts. Then @trylock must be set to true.
+ *
+ * Returns:
+ * 0 on success or negative error code on failure.
  */
-void drm_modeset_lock_all(struct drm_device *dev)
+int __drm_modeset_lock_all(struct drm_device *dev,
+			   bool trylock)
 {
 	struct drm_mode_config *config = &dev->mode_config;
 	struct drm_modeset_acquire_ctx *ctx;
 	int ret;
 
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-	if (WARN_ON(!ctx))
-		return;
+	ctx = kzalloc(sizeof(*ctx),
+		      trylock ? GFP_ATOMIC : GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
 
-	mutex_lock(&config->mutex);
+	if (trylock) {
+		if (!mutex_trylock(&config->mutex))
+			return -EBUSY;
+	} else {
+		mutex_lock(&config->mutex);
+	}
 
 	drm_modeset_acquire_init(ctx, 0);
+	ctx->trylock_only = trylock;
 
 retry:
 	ret = drm_modeset_lock(&config->connection_mutex, ctx);
@@ -95,13 +106,29 @@ retry:
 
 	drm_warn_on_modeset_not_all_locked(dev);
 
-	return;
+	return 0;
 
 fail:
 	if (ret == -EDEADLK) {
 		drm_modeset_backoff(ctx);
 		goto retry;
 	}
+
+	return ret;
+}
+EXPORT_SYMBOL(__drm_modeset_lock_all);
+
+/**
+ * drm_modeset_lock_all - take all modeset locks
+ * @dev: drm device
+ *
+ * This function takes all modeset locks, suitable where a more fine-grained
+ * scheme isn't (yet) implemented. Locks must be dropped with
+ * drm_modeset_unlock_all.
+ */
+void drm_modeset_lock_all(struct drm_device *dev)
+{
+	WARN_ON(__drm_modeset_lock_all(dev, false) != 0);
 }
 EXPORT_SYMBOL(drm_modeset_lock_all);
 
@@ -287,7 +314,12 @@ static inline int modeset_lock(struct drm_modeset_lock *lock,
 
 	WARN_ON(ctx->contended);
 
-	if (interruptible && slow) {
+	if (ctx->trylock_only) {
+		if (!ww_mutex_trylock(&lock->mutex))
+			return -EBUSY;
+		else
+			return 0;
+	} else if (interruptible && slow) {
 		ret = ww_mutex_lock_slow_interruptible(&lock->mutex, &ctx->ww_ctx);
 	} else if (interruptible) {
 		ret = ww_mutex_lock_interruptible(&lock->mutex, &ctx->ww_ctx);
diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h
index d38e1508f11a..a3f736d24382 100644
--- a/include/drm/drm_modeset_lock.h
+++ b/include/drm/drm_modeset_lock.h
@@ -53,6 +53,11 @@ struct drm_modeset_acquire_ctx {
 	 * list of held locks (drm_modeset_lock)
 	 */
 	struct list_head locked;
+
+	/**
+	 * Trylock mode, use only for panic handlers!
+	 */
+	bool trylock_only;
 };
 
 /**
@@ -123,6 +128,7 @@ struct drm_device;
 struct drm_crtc;
 
 void drm_modeset_lock_all(struct drm_device *dev);
+int __drm_modeset_lock_all(struct drm_device *dev, bool trylock);
 void drm_modeset_unlock_all(struct drm_device *dev);
 void drm_modeset_lock_crtc(struct drm_crtc *crtc);
 void drm_modeset_unlock_crtc(struct drm_crtc *crtc);
-- 
cgit v1.2.3


From fd3cbdc0d1b5254a2e8793df58c409b469899a3f Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sun, 10 Aug 2014 08:53:39 +0200
Subject: jump_label: Fix small typos in the documentation

Was reading through the documentation of this code and noticed
a few typos, missing commas, etc.

Cc: Jason Baron <jbaron@akamai.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Mel Gorman <mgorman@suse.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/jump_label.h | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 784304b222b3..98f923b6a0ea 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -8,28 +8,28 @@
  * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
  *
  * Jump labels provide an interface to generate dynamic branches using
- * self-modifying code. Assuming toolchain and architecture support the result
- * of a "if (static_key_false(&key))" statement is a unconditional branch (which
+ * self-modifying code. Assuming toolchain and architecture support, the result
+ * of a "if (static_key_false(&key))" statement is an unconditional branch (which
  * defaults to false - and the true block is placed out of line).
  *
  * However at runtime we can change the branch target using
  * static_key_slow_{inc,dec}(). These function as a 'reference' count on the key
- * object and for as long as there are references all branches referring to
+ * object, and for as long as there are references all branches referring to
  * that particular key will point to the (out of line) true block.
  *
- * Since this relies on modifying code the static_key_slow_{inc,dec}() functions
+ * Since this relies on modifying code, the static_key_slow_{inc,dec}() functions
  * must be considered absolute slow paths (machine wide synchronization etc.).
- * OTOH, since the affected branches are unconditional their runtime overhead
+ * OTOH, since the affected branches are unconditional, their runtime overhead
  * will be absolutely minimal, esp. in the default (off) case where the total
  * effect is a single NOP of appropriate size. The on case will patch in a jump
  * to the out-of-line block.
  *
- * When the control is directly exposed to userspace it is prudent to delay the
+ * When the control is directly exposed to userspace, it is prudent to delay the
  * decrement to avoid high frequency code modifications which can (and do)
  * cause significant performance degradation. Struct static_key_deferred and
  * static_key_slow_dec_deferred() provide for this.
  *
- * Lacking toolchain and or architecture support, it falls back to a simple
+ * Lacking toolchain and or architecture support, jump labels fall back to a simple
  * conditional branch.
  *
  * struct static_key my_key = STATIC_KEY_INIT_TRUE;
@@ -43,8 +43,7 @@
  *
  * Not initializing the key (static data is initialized to 0s anyway) is the
  * same as using STATIC_KEY_INIT_FALSE.
- *
-*/
+ */
 
 #include <linux/types.h>
 #include <linux/compiler.h>
-- 
cgit v1.2.3


From 2a0d7cfd9482ca4c10a4d8794791760a6a7ce40c Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 29 Jul 2014 15:32:37 +0200
Subject: drm: Add a plane->reset hook

In general having this can't hurt, and the atomic helpers will need
it to be able to reset the state objects properly. The overall idea
is to reset in the order pixels flow, so planes -> crtcs ->
encoders -> connectors.

v2: Squash in fixup from Ville to correctly deference struct drm_plane
instead of drm_crtc when walking the plane list. Fixes an oops in
driver init and resume.

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c | 5 +++++
 include/drm/drm_crtc.h     | 1 +
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index cacb460a7145..285e62a134b2 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -4663,9 +4663,14 @@ out:
 void drm_mode_config_reset(struct drm_device *dev)
 {
 	struct drm_crtc *crtc;
+	struct drm_plane *plane;
 	struct drm_encoder *encoder;
 	struct drm_connector *connector;
 
+	list_for_each_entry(plane, &dev->mode_config.plane_list, head)
+		if (plane->funcs->reset)
+			plane->funcs->reset(plane);
+
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
 		if (crtc->funcs->reset)
 			crtc->funcs->reset(crtc);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 279565aa0c33..2c1f58d6957a 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -581,6 +581,7 @@ struct drm_plane_funcs {
 			    uint32_t src_w, uint32_t src_h);
 	int (*disable_plane)(struct drm_plane *plane);
 	void (*destroy)(struct drm_plane *plane);
+	void (*reset)(struct drm_plane *plane);
 
 	int (*set_property)(struct drm_plane *plane,
 			    struct drm_property *property, uint64_t val);
-- 
cgit v1.2.3


From e8450f51a4b39cfe0878b4aee339820b2bfff240 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 25 Jul 2014 23:34:03 +0200
Subject: drm/irq: Implement a generic vblank_wait function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As usual in both a crtc index and a struct drm_crtc * version.

The function assumes that no one drivers their display below 10Hz, and
it will complain if the vblank wait takes longer than that.

v2: Also check dev->max_vblank_counter since some drivers register a
fake get_vblank_counter function.

v3: Use drm_vblank_count instead of calling the low-level
->get_vblank_counter callback. That way we'll get the sw-cooked
counter for platforms without proper vblank support and so can ditch
the max_vblank_counter check again.

v4: Review from Michel Dänzer:
- Restore lost notes about v3:
- Spelling in kerneldoc.
- Inline wait_event condition.
- s/vblank_wait/wait_one_vblank/

Cc: Michel Dänzer <michel@daenzer.net>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_irq.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 include/drm/drmP.h        |  2 ++
 2 files changed, 46 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 6f16a104d6d0..e64d24951fc2 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -1009,6 +1009,50 @@ void drm_crtc_vblank_put(struct drm_crtc *crtc)
 }
 EXPORT_SYMBOL(drm_crtc_vblank_put);
 
+/**
+ * drm_wait_one_vblank - wait for one vblank
+ * @dev: DRM device
+ * @crtc: crtc index
+ *
+ * This waits for one vblank to pass on @crtc, using the irq driver interfaces.
+ * It is a failure to call this when the vblank irq for @crtc is disabled, e.g.
+ * due to lack of driver support or because the crtc is off.
+ */
+void drm_wait_one_vblank(struct drm_device *dev, int crtc)
+{
+	int ret;
+	u32 last;
+
+	ret = drm_vblank_get(dev, crtc);
+	if (WARN_ON(ret))
+		return;
+
+	last = drm_vblank_count(dev, crtc);
+
+	ret = wait_event_timeout(dev->vblank[crtc].queue,
+				 last != drm_vblank_count(dev, crtc),
+				 msecs_to_jiffies(100));
+
+	WARN_ON(ret == 0);
+
+	drm_vblank_put(dev, crtc);
+}
+EXPORT_SYMBOL(drm_wait_one_vblank);
+
+/**
+ * drm_crtc_wait_one_vblank - wait for one vblank
+ * @crtc: DRM crtc
+ *
+ * This waits for one vblank to pass on @crtc, using the irq driver interfaces.
+ * It is a failure to call this when the vblank irq for @crtc is disabled, e.g.
+ * due to lack of driver support or because the crtc is off.
+ */
+void drm_crtc_wait_one_vblank(struct drm_crtc *crtc)
+{
+	drm_wait_one_vblank(crtc->dev, drm_crtc_index(crtc));
+}
+EXPORT_SYMBOL(drm_crtc_wait_one_vblank);
+
 /**
  * drm_vblank_off - disable vblank events on a CRTC
  * @dev: DRM device
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index d3d9be6b83ef..c2209178981f 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1327,6 +1327,8 @@ extern int drm_vblank_get(struct drm_device *dev, int crtc);
 extern void drm_vblank_put(struct drm_device *dev, int crtc);
 extern int drm_crtc_vblank_get(struct drm_crtc *crtc);
 extern void drm_crtc_vblank_put(struct drm_crtc *crtc);
+extern void drm_wait_one_vblank(struct drm_device *dev, int crtc);
+extern void drm_crtc_wait_one_vblank(struct drm_crtc *crtc);
 extern void drm_vblank_off(struct drm_device *dev, int crtc);
 extern void drm_vblank_on(struct drm_device *dev, int crtc);
 extern void drm_crtc_vblank_off(struct drm_crtc *crtc);
-- 
cgit v1.2.3


From f72a113a71ab08c4df8a5f80ab2f8a140feb81f6 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 7 Aug 2014 09:36:00 +0200
Subject: drm/radeon: add userptr support v8
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds an IOCTL for turning a pointer supplied by
userspace into a buffer object.

It imposes several restrictions upon the memory being mapped:

1. It must be page aligned (both start/end addresses, i.e ptr and size).

2. It must be normal system memory, not a pointer into another map of IO
space (e.g. it must not be a GTT mmapping of another object).

3. The BO is mapped into GTT, so the maximum amount of memory mapped at
all times is still the GTT limit.

4. The BO is only mapped readonly for now, so no write support.

5. List of backing pages is only acquired once, so they represent a
snapshot of the first use.

Exporting and sharing as well as mapping of buffer objects created by
this function is forbidden and results in an -EPERM.

v2: squash all previous changes into first public version
v3: fix tabs, map readonly, don't use MM callback any more
v4: set TTM_PAGE_FLAG_SG so that TTM never messes with the pages,
    pin/unpin pages on bind/unbind instead of populate/unpopulate
v5: rebased on 3.17-wip, IOCTL renamed to userptr, reject any unknown
    flags, better handle READONLY flag, improve permission check
v6: fix ptr cast warning, use set_page_dirty/mark_page_accessed on unpin
v7: add warning about it's availability in the API definition
v8: drop access_ok check, fix VM mapping bits

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> (v4)
Reviewed-by: Jérôme Glisse <jglisse@redhat.com> (v4)
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon.h        |   6 ++
 drivers/gpu/drm/radeon/radeon_cs.c     |  25 +++++-
 drivers/gpu/drm/radeon/radeon_drv.c    |   5 +-
 drivers/gpu/drm/radeon/radeon_gem.c    |  68 ++++++++++++++++
 drivers/gpu/drm/radeon/radeon_kms.c    |   1 +
 drivers/gpu/drm/radeon/radeon_object.c |   3 +
 drivers/gpu/drm/radeon/radeon_prime.c  |  10 +++
 drivers/gpu/drm/radeon/radeon_ttm.c    | 145 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/radeon/radeon_vm.c     |   3 +
 include/uapi/drm/radeon_drm.h          |  16 ++++
 10 files changed, 279 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 9e1732eb402c..6f38a23a5810 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2138,6 +2138,8 @@ int radeon_gem_info_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp);
 int radeon_gem_create_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *filp);
+int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *filp);
 int radeon_gem_pin_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 int radeon_gem_unpin_ioctl(struct drm_device *dev, void *data,
@@ -2871,6 +2873,10 @@ extern void radeon_legacy_set_clock_gating(struct radeon_device *rdev, int enabl
 extern void radeon_atom_set_clock_gating(struct radeon_device *rdev, int enable);
 extern void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain);
 extern bool radeon_ttm_bo_is_radeon_bo(struct ttm_buffer_object *bo);
+extern int radeon_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
+				     uint32_t flags);
+extern bool radeon_ttm_tt_has_userptr(struct ttm_tt *ttm);
+extern bool radeon_ttm_tt_is_readonly(struct ttm_tt *ttm);
 extern void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 base);
 extern void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
 extern int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index ee712c199b25..1321491cf499 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -78,7 +78,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 	struct radeon_cs_chunk *chunk;
 	struct radeon_cs_buckets buckets;
 	unsigned i, j;
-	bool duplicate;
+	bool duplicate, need_mmap_lock = false;
+	int r;
 
 	if (p->chunk_relocs_idx == -1) {
 		return 0;
@@ -164,6 +165,19 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 			p->relocs[i].allowed_domains = domain;
 		}
 
+		if (radeon_ttm_tt_has_userptr(p->relocs[i].robj->tbo.ttm)) {
+			uint32_t domain = p->relocs[i].prefered_domains;
+			if (!(domain & RADEON_GEM_DOMAIN_GTT)) {
+				DRM_ERROR("Only RADEON_GEM_DOMAIN_GTT is "
+					  "allowed for userptr BOs\n");
+				return -EINVAL;
+			}
+			need_mmap_lock = true;
+			domain = RADEON_GEM_DOMAIN_GTT;
+			p->relocs[i].prefered_domains = domain;
+			p->relocs[i].allowed_domains = domain;
+		}
+
 		p->relocs[i].tv.bo = &p->relocs[i].robj->tbo;
 		p->relocs[i].handle = r->handle;
 
@@ -176,8 +190,15 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 	if (p->cs_flags & RADEON_CS_USE_VM)
 		p->vm_bos = radeon_vm_get_bos(p->rdev, p->ib.vm,
 					      &p->validated);
+	if (need_mmap_lock)
+		down_read(&current->mm->mmap_sem);
+
+	r = radeon_bo_list_validate(p->rdev, &p->ticket, &p->validated, p->ring);
 
-	return radeon_bo_list_validate(p->rdev, &p->ticket, &p->validated, p->ring);
+	if (need_mmap_lock)
+		up_read(&current->mm->mmap_sem);
+
+	return r;
 }
 
 static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority)
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index a773830c6c40..5b18af926527 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -114,6 +114,9 @@ int radeon_gem_object_open(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
 void radeon_gem_object_close(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
+struct dma_buf *radeon_gem_prime_export(struct drm_device *dev,
+					struct drm_gem_object *gobj,
+					int flags);
 extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc,
 				      unsigned int flags,
 				      int *vpos, int *hpos, ktime_t *stime,
@@ -568,7 +571,7 @@ static struct drm_driver kms_driver = {
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
-	.gem_prime_export = drm_gem_prime_export,
+	.gem_prime_export = radeon_gem_prime_export,
 	.gem_prime_import = drm_gem_prime_import,
 	.gem_prime_pin = radeon_gem_prime_pin,
 	.gem_prime_unpin = radeon_gem_prime_unpin,
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index bfd7e1b0ff3f..993ab223b503 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -272,6 +272,65 @@ int radeon_gem_create_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
+int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *filp)
+{
+	struct radeon_device *rdev = dev->dev_private;
+	struct drm_radeon_gem_userptr *args = data;
+	struct drm_gem_object *gobj;
+	struct radeon_bo *bo;
+	uint32_t handle;
+	int r;
+
+	if (offset_in_page(args->addr | args->size))
+		return -EINVAL;
+
+	/* we only support read only mappings for now */
+	if (!(args->flags & RADEON_GEM_USERPTR_READONLY))
+		return -EACCES;
+
+	/* reject unknown flag values */
+	if (args->flags & ~RADEON_GEM_USERPTR_READONLY)
+		return -EINVAL;
+
+	/* readonly pages not tested on older hardware */
+	if (rdev->family < CHIP_R600)
+		return -EINVAL;
+
+	down_read(&rdev->exclusive_lock);
+
+	/* create a gem object to contain this object in */
+	r = radeon_gem_object_create(rdev, args->size, 0,
+				     RADEON_GEM_DOMAIN_CPU, 0,
+				     false, &gobj);
+	if (r)
+		goto handle_lockup;
+
+	bo = gem_to_radeon_bo(gobj);
+	r = radeon_ttm_tt_set_userptr(bo->tbo.ttm, args->addr, args->flags);
+	if (r)
+		goto release_object;
+
+	r = drm_gem_handle_create(filp, gobj, &handle);
+	/* drop reference from allocate - handle holds it now */
+	drm_gem_object_unreference_unlocked(gobj);
+	if (r)
+		goto handle_lockup;
+
+	args->handle = handle;
+	up_read(&rdev->exclusive_lock);
+	return 0;
+
+release_object:
+	drm_gem_object_unreference_unlocked(gobj);
+
+handle_lockup:
+	up_read(&rdev->exclusive_lock);
+	r = radeon_gem_handle_lockup(rdev, r);
+
+	return r;
+}
+
 int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp)
 {
@@ -315,6 +374,10 @@ int radeon_mode_dumb_mmap(struct drm_file *filp,
 		return -ENOENT;
 	}
 	robj = gem_to_radeon_bo(gobj);
+	if (radeon_ttm_tt_has_userptr(robj->tbo.ttm)) {
+		drm_gem_object_unreference_unlocked(gobj);
+		return -EPERM;
+	}
 	*offset_p = radeon_bo_mmap_offset(robj);
 	drm_gem_object_unreference_unlocked(gobj);
 	return 0;
@@ -532,6 +595,11 @@ int radeon_gem_op_ioctl(struct drm_device *dev, void *data,
 		return -ENOENT;
 	}
 	robj = gem_to_radeon_bo(gobj);
+
+	r = -EPERM;
+	if (radeon_ttm_tt_has_userptr(robj->tbo.ttm))
+		goto out;
+
 	r = radeon_bo_reserve(robj, false);
 	if (unlikely(r))
 		goto out;
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index eb7164d07985..8309b11e674d 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -885,5 +885,6 @@ const struct drm_ioctl_desc radeon_ioctls_kms[] = {
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_BUSY, radeon_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_VA, radeon_gem_va_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_OP, radeon_gem_op_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_USERPTR, radeon_gem_userptr_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 };
 int radeon_max_kms_ioctl = ARRAY_SIZE(radeon_ioctls_kms);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 480c87d8edc5..c73c1e320585 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -264,6 +264,9 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 {
 	int r, i;
 
+	if (radeon_ttm_tt_has_userptr(bo->tbo.ttm))
+		return -EPERM;
+
 	if (bo->pin_count) {
 		bo->pin_count++;
 		if (gpu_addr)
diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c
index f7e48d329db3..bb18bc74b7d7 100644
--- a/drivers/gpu/drm/radeon/radeon_prime.c
+++ b/drivers/gpu/drm/radeon/radeon_prime.c
@@ -103,3 +103,13 @@ void radeon_gem_prime_unpin(struct drm_gem_object *obj)
 	radeon_bo_unpin(bo);
 	radeon_bo_unreserve(bo);
 }
+
+struct dma_buf *radeon_gem_prime_export(struct drm_device *dev,
+					struct drm_gem_object *gobj,
+					int flags)
+{
+	struct radeon_bo *bo = gem_to_radeon_bo(gobj);
+	if (radeon_ttm_tt_has_userptr(bo->tbo.ttm))
+		return ERR_PTR(-EPERM);
+	return drm_gem_prime_export(dev, gobj, flags);
+}
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 72afe82a95c9..b20933fa35c6 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -39,6 +39,8 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/swiotlb.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
 #include <linux/debugfs.h>
 #include "radeon_reg.h"
 #include "radeon.h"
@@ -515,8 +517,92 @@ struct radeon_ttm_tt {
 	struct ttm_dma_tt		ttm;
 	struct radeon_device		*rdev;
 	u64				offset;
+
+	uint64_t			userptr;
+	struct mm_struct		*usermm;
+	uint32_t			userflags;
 };
 
+/* prepare the sg table with the user pages */
+static int radeon_ttm_tt_pin_userptr(struct ttm_tt *ttm)
+{
+	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+	unsigned pinned = 0, nents;
+	int r;
+
+	int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
+	enum dma_data_direction direction = write ?
+		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
+
+	if (current->mm != gtt->usermm)
+		return -EPERM;
+
+	do {
+		unsigned num_pages = ttm->num_pages - pinned;
+		uint64_t userptr = gtt->userptr + pinned * PAGE_SIZE;
+		struct page **pages = ttm->pages + pinned;
+
+		r = get_user_pages(current, current->mm, userptr, num_pages,
+				   write, 0, pages, NULL);
+		if (r < 0)
+			goto release_pages;
+
+		pinned += r;
+
+	} while (pinned < ttm->num_pages);
+
+	r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0,
+				      ttm->num_pages << PAGE_SHIFT,
+				      GFP_KERNEL);
+	if (r)
+		goto release_sg;
+
+	r = -ENOMEM;
+	nents = dma_map_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
+	if (nents != ttm->sg->nents)
+		goto release_sg;
+
+	drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
+					 gtt->ttm.dma_address, ttm->num_pages);
+
+	return 0;
+
+release_sg:
+	kfree(ttm->sg);
+
+release_pages:
+	release_pages(ttm->pages, pinned, 0);
+	return r;
+}
+
+static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
+{
+	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+	struct scatterlist *sg;
+	int i;
+
+	int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
+	enum dma_data_direction direction = write ?
+		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
+
+	/* free the sg table and pages again */
+	dma_unmap_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
+
+	for_each_sg(ttm->sg->sgl, sg, ttm->sg->nents, i) {
+		struct page *page = sg_page(sg);
+
+		if (!(gtt->userflags & RADEON_GEM_USERPTR_READONLY))
+			set_page_dirty(page);
+
+		mark_page_accessed(page);
+		page_cache_release(page);
+	}
+
+	sg_free_table(ttm->sg);
+}
+
 static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
 				   struct ttm_mem_reg *bo_mem)
 {
@@ -525,6 +611,11 @@ static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
 		RADEON_GART_PAGE_WRITE;
 	int r;
 
+	if (gtt->userptr) {
+		radeon_ttm_tt_pin_userptr(ttm);
+		flags &= ~RADEON_GART_PAGE_WRITE;
+	}
+
 	gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
 	if (!ttm->num_pages) {
 		WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
@@ -547,6 +638,10 @@ static int radeon_ttm_backend_unbind(struct ttm_tt *ttm)
 	struct radeon_ttm_tt *gtt = (void *)ttm;
 
 	radeon_gart_unbind(gtt->rdev, gtt->offset, ttm->num_pages);
+
+	if (gtt->userptr)
+		radeon_ttm_tt_unpin_userptr(ttm);
+
 	return 0;
 }
 
@@ -603,6 +698,16 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
 	if (ttm->state != tt_unpopulated)
 		return 0;
 
+	if (gtt->userptr) {
+		ttm->sg = kcalloc(1, sizeof(struct sg_table), GFP_KERNEL);
+		if (!ttm->sg)
+			return -ENOMEM;
+
+		ttm->page_flags |= TTM_PAGE_FLAG_SG;
+		ttm->state = tt_unbound;
+		return 0;
+	}
+
 	if (slave && ttm->sg) {
 		drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
 						 gtt->ttm.dma_address, ttm->num_pages);
@@ -652,6 +757,12 @@ static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	unsigned i;
 	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
 
+	if (gtt->userptr) {
+		kfree(ttm->sg);
+		ttm->page_flags &= ~TTM_PAGE_FLAG_SG;
+		return;
+	}
+
 	if (slave)
 		return;
 
@@ -680,6 +791,40 @@ static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	ttm_pool_unpopulate(ttm);
 }
 
+int radeon_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
+			      uint32_t flags)
+{
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+
+	if (gtt == NULL)
+		return -EINVAL;
+
+	gtt->userptr = addr;
+	gtt->usermm = current->mm;
+	gtt->userflags = flags;
+	return 0;
+}
+
+bool radeon_ttm_tt_has_userptr(struct ttm_tt *ttm)
+{
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+
+	if (gtt == NULL)
+		return false;
+
+	return !!gtt->userptr;
+}
+
+bool radeon_ttm_tt_is_readonly(struct ttm_tt *ttm)
+{
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+
+	if (gtt == NULL)
+		return false;
+
+	return !!(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
+}
+
 static struct ttm_bo_driver radeon_bo_driver = {
 	.ttm_tt_create = &radeon_ttm_tt_create,
 	.ttm_tt_populate = &radeon_ttm_tt_populate,
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index ccae4d9dc3de..0e107c5650bf 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -888,6 +888,9 @@ int radeon_vm_bo_update(struct radeon_device *rdev,
 	bo_va->flags &= ~RADEON_VM_PAGE_VALID;
 	bo_va->flags &= ~RADEON_VM_PAGE_SYSTEM;
 	bo_va->flags &= ~RADEON_VM_PAGE_SNOOPED;
+	if (bo_va->bo && radeon_ttm_tt_is_readonly(bo_va->bo->tbo.ttm))
+		bo_va->flags &= ~RADEON_VM_PAGE_WRITEABLE;
+
 	if (mem) {
 		addr = mem->start << PAGE_SHIFT;
 		if (mem->mem_type != TTM_PL_SYSTEM) {
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 509b2d7a41b7..3a9f20930372 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -511,6 +511,7 @@ typedef struct {
 #define DRM_RADEON_GEM_BUSY		0x2a
 #define DRM_RADEON_GEM_VA		0x2b
 #define DRM_RADEON_GEM_OP		0x2c
+#define DRM_RADEON_GEM_USERPTR		0x2d
 
 #define DRM_IOCTL_RADEON_CP_INIT    DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_CP_INIT, drm_radeon_init_t)
 #define DRM_IOCTL_RADEON_CP_START   DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_CP_START)
@@ -554,6 +555,7 @@ typedef struct {
 #define DRM_IOCTL_RADEON_GEM_BUSY	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_BUSY, struct drm_radeon_gem_busy)
 #define DRM_IOCTL_RADEON_GEM_VA		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_VA, struct drm_radeon_gem_va)
 #define DRM_IOCTL_RADEON_GEM_OP		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_OP, struct drm_radeon_gem_op)
+#define DRM_IOCTL_RADEON_GEM_USERPTR	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_USERPTR, struct drm_radeon_gem_userptr)
 
 typedef struct drm_radeon_init {
 	enum {
@@ -808,6 +810,20 @@ struct drm_radeon_gem_create {
 	uint32_t	flags;
 };
 
+/*
+ * This is not a reliable API and you should expect it to fail for any
+ * number of reasons and have fallback path that do not use userptr to
+ * perform any operation.
+ */
+#define RADEON_GEM_USERPTR_READONLY	(1 << 0)
+
+struct drm_radeon_gem_userptr {
+	uint64_t		addr;
+	uint64_t		size;
+	uint32_t		flags;
+	uint32_t		handle;
+};
+
 #define RADEON_TILING_MACRO				0x1
 #define RADEON_TILING_MICRO				0x2
 #define RADEON_TILING_SWAP_16BIT			0x4
-- 
cgit v1.2.3


From ddd00e33e17a62c5f44377ab42e7562ccfae7bd1 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 7 Aug 2014 09:36:01 +0200
Subject: drm/radeon: add userptr flag to limit it to anonymous memory v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Avoid problems with writeback by limiting userptr to anonymous memory.

v2: add commit and code comments

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_gem.c |  3 ++-
 drivers/gpu/drm/radeon/radeon_ttm.c | 10 ++++++++++
 include/uapi/drm/radeon_drm.h       |  1 +
 3 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 993ab223b503..032736b429bf 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -290,7 +290,8 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
 		return -EACCES;
 
 	/* reject unknown flag values */
-	if (args->flags & ~RADEON_GEM_USERPTR_READONLY)
+	if (args->flags & ~(RADEON_GEM_USERPTR_READONLY |
+	    RADEON_GEM_USERPTR_ANONONLY))
 		return -EINVAL;
 
 	/* readonly pages not tested on older hardware */
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index b20933fa35c6..12e37b1ddc40 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -538,6 +538,16 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_tt *ttm)
 	if (current->mm != gtt->usermm)
 		return -EPERM;
 
+	if (gtt->userflags & RADEON_GEM_USERPTR_ANONONLY) {
+		/* check that we only pin down anonymous memory
+		   to prevent problems with writeback */
+		unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE;
+		struct vm_area_struct *vma;
+		vma = find_vma(gtt->usermm, gtt->userptr);
+		if (!vma || vma->vm_file || vma->vm_end < end)
+			return -EPERM;
+	}
+
 	do {
 		unsigned num_pages = ttm->num_pages - pinned;
 		uint64_t userptr = gtt->userptr + pinned * PAGE_SIZE;
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 3a9f20930372..9720e1a36848 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -816,6 +816,7 @@ struct drm_radeon_gem_create {
  * perform any operation.
  */
 #define RADEON_GEM_USERPTR_READONLY	(1 << 0)
+#define RADEON_GEM_USERPTR_ANONONLY	(1 << 1)
 
 struct drm_radeon_gem_userptr {
 	uint64_t		addr;
-- 
cgit v1.2.3


From 2a84a4476d6e13de72472f6ca4338aed0a8269b8 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 7 Aug 2014 09:36:02 +0200
Subject: drm/radeon: add userptr flag to directly validate the BO to GTT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This way we test userptr availability at BO creation time instead of first use.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_gem.c | 18 +++++++++++++++++-
 include/uapi/drm/radeon_drm.h       |  1 +
 2 files changed, 18 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 032736b429bf..450656027aba 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -291,7 +291,7 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
 
 	/* reject unknown flag values */
 	if (args->flags & ~(RADEON_GEM_USERPTR_READONLY |
-	    RADEON_GEM_USERPTR_ANONONLY))
+	    RADEON_GEM_USERPTR_ANONONLY | RADEON_GEM_USERPTR_VALIDATE))
 		return -EINVAL;
 
 	/* readonly pages not tested on older hardware */
@@ -312,6 +312,22 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
 	if (r)
 		goto release_object;
 
+	if (args->flags & RADEON_GEM_USERPTR_VALIDATE) {
+		down_read(&current->mm->mmap_sem);
+		r = radeon_bo_reserve(bo, true);
+		if (r) {
+			up_read(&current->mm->mmap_sem);
+			goto release_object;
+		}
+
+		radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_GTT);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
+		radeon_bo_unreserve(bo);
+		up_read(&current->mm->mmap_sem);
+		if (r)
+			goto release_object;
+	}
+
 	r = drm_gem_handle_create(filp, gobj, &handle);
 	/* drop reference from allocate - handle holds it now */
 	drm_gem_object_unreference_unlocked(gobj);
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 9720e1a36848..5dc61c2d4c73 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -817,6 +817,7 @@ struct drm_radeon_gem_create {
  */
 #define RADEON_GEM_USERPTR_READONLY	(1 << 0)
 #define RADEON_GEM_USERPTR_ANONONLY	(1 << 1)
+#define RADEON_GEM_USERPTR_VALIDATE	(1 << 2)
 
 struct drm_radeon_gem_userptr {
 	uint64_t		addr;
-- 
cgit v1.2.3


From 341cb9e426fac32523427c80c67543a16be46605 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 7 Aug 2014 09:36:03 +0200
Subject: drm/radeon: add userptr flag to register MMU notifier v3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Whenever userspace mapping related to our userptr change
we wait for it to become idle and unmap it from GTT.

v2: rebased, fix mutex unlock in error path
v3: improve commit message

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/Kconfig                |   1 +
 drivers/gpu/drm/radeon/Makefile        |   2 +-
 drivers/gpu/drm/radeon/radeon.h        |  12 ++
 drivers/gpu/drm/radeon/radeon_device.c |   2 +
 drivers/gpu/drm/radeon/radeon_gem.c    |   9 +-
 drivers/gpu/drm/radeon/radeon_mn.c     | 272 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/radeon/radeon_object.c |   1 +
 include/uapi/drm/radeon_drm.h          |   1 +
 8 files changed, 298 insertions(+), 2 deletions(-)
 create mode 100644 drivers/gpu/drm/radeon/radeon_mn.c

(limited to 'include')

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index b066bb3ca01a..358b6e8697e9 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -115,6 +115,7 @@ config DRM_RADEON
 	select HWMON
 	select BACKLIGHT_CLASS_DEVICE
 	select INTERVAL_TREE
+	select MMU_NOTIFIER
 	help
 	  Choose this option if you have an ATI Radeon graphics card.  There
 	  are both PCI and AGP versions.  You don't need to choose this to
diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index 0013ad0db9ef..c7fa1aeb8c3f 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -80,7 +80,7 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
 	r600_dpm.o rs780_dpm.o rv6xx_dpm.o rv770_dpm.o rv730_dpm.o rv740_dpm.o \
 	rv770_smc.o cypress_dpm.o btc_dpm.o sumo_dpm.o sumo_smc.o trinity_dpm.o \
 	trinity_smc.o ni_dpm.o si_smc.o si_dpm.o kv_smc.o kv_dpm.o ci_smc.o \
-	ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o
+	ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o
 
 # add async DMA block
 radeon-y += \
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 6f38a23a5810..542da8208674 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -65,6 +65,7 @@
 #include <linux/list.h>
 #include <linux/kref.h>
 #include <linux/interval_tree.h>
+#include <linux/hashtable.h>
 
 #include <ttm/ttm_bo_api.h>
 #include <ttm/ttm_bo_driver.h>
@@ -487,6 +488,9 @@ struct radeon_bo {
 
 	struct ttm_bo_kmap_obj		dma_buf_vmap;
 	pid_t				pid;
+
+	struct radeon_mn		*mn;
+	struct interval_tree_node	mn_it;
 };
 #define gem_to_radeon_bo(gobj) container_of((gobj), struct radeon_bo, gem_base)
 
@@ -1725,6 +1729,11 @@ void radeon_test_ring_sync(struct radeon_device *rdev,
 			   struct radeon_ring *cpB);
 void radeon_test_syncing(struct radeon_device *rdev);
 
+/*
+ * MMU Notifier
+ */
+int radeon_mn_register(struct radeon_bo *bo, unsigned long addr);
+void radeon_mn_unregister(struct radeon_bo *bo);
 
 /*
  * Debugfs
@@ -2372,6 +2381,9 @@ struct radeon_device {
 	/* tracking pinned memory */
 	u64 vram_pin_size;
 	u64 gart_pin_size;
+
+	struct mutex	mn_lock;
+	DECLARE_HASHTABLE(mn_hash, 7);
 };
 
 bool radeon_is_px(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index c8ea050c8fa4..c58f84f3c6a5 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1270,6 +1270,8 @@ int radeon_device_init(struct radeon_device *rdev,
 	init_rwsem(&rdev->pm.mclk_lock);
 	init_rwsem(&rdev->exclusive_lock);
 	init_waitqueue_head(&rdev->irq.vblank_queue);
+	mutex_init(&rdev->mn_lock);
+	hash_init(rdev->mn_hash);
 	r = radeon_gem_init(rdev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 450656027aba..2a6fbf101cf0 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -291,7 +291,8 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
 
 	/* reject unknown flag values */
 	if (args->flags & ~(RADEON_GEM_USERPTR_READONLY |
-	    RADEON_GEM_USERPTR_ANONONLY | RADEON_GEM_USERPTR_VALIDATE))
+	    RADEON_GEM_USERPTR_ANONONLY | RADEON_GEM_USERPTR_VALIDATE |
+	    RADEON_GEM_USERPTR_REGISTER))
 		return -EINVAL;
 
 	/* readonly pages not tested on older hardware */
@@ -312,6 +313,12 @@ int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
 	if (r)
 		goto release_object;
 
+	if (args->flags & RADEON_GEM_USERPTR_REGISTER) {
+		r = radeon_mn_register(bo, args->addr);
+		if (r)
+			goto release_object;
+	}
+
 	if (args->flags & RADEON_GEM_USERPTR_VALIDATE) {
 		down_read(&current->mm->mmap_sem);
 		r = radeon_bo_reserve(bo, true);
diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c
new file mode 100644
index 000000000000..0157bc2f11f8
--- /dev/null
+++ b/drivers/gpu/drm/radeon/radeon_mn.c
@@ -0,0 +1,272 @@
+/*
+ * Copyright 2014 Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ */
+/*
+ * Authors:
+ *    Christian König <christian.koenig@amd.com>
+ */
+
+#include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/mmu_notifier.h>
+#include <drm/drmP.h>
+#include <drm/drm.h>
+
+#include "radeon.h"
+
+struct radeon_mn {
+	/* constant after initialisation */
+	struct radeon_device	*rdev;
+	struct mm_struct	*mm;
+	struct mmu_notifier	mn;
+
+	/* only used on destruction */
+	struct work_struct	work;
+
+	/* protected by rdev->mn_lock */
+	struct hlist_node	node;
+
+	/* objects protected by lock */
+	struct mutex		lock;
+	struct rb_root		objects;
+};
+
+/**
+ * radeon_mn_destroy - destroy the rmn
+ *
+ * @work: previously sheduled work item
+ *
+ * Lazy destroys the notifier from a work item
+ */
+static void radeon_mn_destroy(struct work_struct *work)
+{
+	struct radeon_mn *rmn = container_of(work, struct radeon_mn, work);
+	struct radeon_device *rdev = rmn->rdev;
+	struct radeon_bo *bo, *next;
+
+	mutex_lock(&rdev->mn_lock);
+	mutex_lock(&rmn->lock);
+	hash_del(&rmn->node);
+	rbtree_postorder_for_each_entry_safe(bo, next, &rmn->objects, mn_it.rb) {
+		interval_tree_remove(&bo->mn_it, &rmn->objects);
+		bo->mn = NULL;
+	}
+	mutex_unlock(&rmn->lock);
+	mutex_unlock(&rdev->mn_lock);
+	mmu_notifier_unregister(&rmn->mn, rmn->mm);
+	kfree(rmn);
+}
+
+/**
+ * radeon_mn_release - callback to notify about mm destruction
+ *
+ * @mn: our notifier
+ * @mn: the mm this callback is about
+ *
+ * Shedule a work item to lazy destroy our notifier.
+ */
+static void radeon_mn_release(struct mmu_notifier *mn,
+			      struct mm_struct *mm)
+{
+	struct radeon_mn *rmn = container_of(mn, struct radeon_mn, mn);
+	INIT_WORK(&rmn->work, radeon_mn_destroy);
+	schedule_work(&rmn->work);
+}
+
+/**
+ * radeon_mn_invalidate_range_start - callback to notify about mm change
+ *
+ * @mn: our notifier
+ * @mn: the mm this callback is about
+ * @start: start of updated range
+ * @end: end of updated range
+ *
+ * We block for all BOs between start and end to be idle and
+ * unmap them by move them into system domain again.
+ */
+static void radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
+					     struct mm_struct *mm,
+					     unsigned long start,
+					     unsigned long end)
+{
+	struct radeon_mn *rmn = container_of(mn, struct radeon_mn, mn);
+	struct interval_tree_node *it;
+
+	/* notification is exclusive, but interval is inclusive */
+	end -= 1;
+
+	mutex_lock(&rmn->lock);
+
+	it = interval_tree_iter_first(&rmn->objects, start, end);
+	while (it) {
+		struct radeon_bo *bo;
+		int r;
+
+		bo = container_of(it, struct radeon_bo, mn_it);
+		it = interval_tree_iter_next(it, start, end);
+
+		r = radeon_bo_reserve(bo, true);
+		if (r) {
+			DRM_ERROR("(%d) failed to reserve user bo\n", r);
+			continue;
+		}
+
+		if (bo->tbo.sync_obj) {
+			r = radeon_fence_wait(bo->tbo.sync_obj, false);
+			if (r)
+				DRM_ERROR("(%d) failed to wait for user bo\n", r);
+		}
+
+		radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_CPU);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+		if (r)
+			DRM_ERROR("(%d) failed to validate user bo\n", r);
+
+		radeon_bo_unreserve(bo);
+	}
+	
+	mutex_unlock(&rmn->lock);
+}
+
+static const struct mmu_notifier_ops radeon_mn_ops = {
+	.release = radeon_mn_release,
+	.invalidate_range_start = radeon_mn_invalidate_range_start,
+};
+
+/**
+ * radeon_mn_get - create notifier context
+ *
+ * @rdev: radeon device pointer
+ *
+ * Creates a notifier context for current->mm.
+ */
+static struct radeon_mn *radeon_mn_get(struct radeon_device *rdev)
+{
+	struct mm_struct *mm = current->mm;
+	struct radeon_mn *rmn;
+	int r;
+
+	down_write(&mm->mmap_sem);
+	mutex_lock(&rdev->mn_lock);
+
+	hash_for_each_possible(rdev->mn_hash, rmn, node, (unsigned long)mm)
+		if (rmn->mm == mm)
+			goto release_locks;
+
+	rmn = kzalloc(sizeof(*rmn), GFP_KERNEL);
+	if (!rmn) {
+		rmn = ERR_PTR(-ENOMEM);
+		goto release_locks;
+	}
+
+	rmn->rdev = rdev;
+	rmn->mm = mm;
+	rmn->mn.ops = &radeon_mn_ops;
+	mutex_init(&rmn->lock);
+	rmn->objects = RB_ROOT;
+	
+	r = __mmu_notifier_register(&rmn->mn, mm);
+	if (r)
+		goto free_rmn;
+
+	hash_add(rdev->mn_hash, &rmn->node, (unsigned long)mm);
+
+release_locks:
+	mutex_unlock(&rdev->mn_lock);
+	up_write(&mm->mmap_sem);
+
+	return rmn;
+
+free_rmn:
+	mutex_unlock(&rdev->mn_lock);
+	up_write(&mm->mmap_sem);
+	kfree(rmn);
+
+	return ERR_PTR(r);
+}
+
+/**
+ * radeon_mn_register - register a BO for notifier updates
+ *
+ * @bo: radeon buffer object
+ * @addr: userptr addr we should monitor
+ *
+ * Registers an MMU notifier for the given BO at the specified address.
+ * Returns 0 on success, -ERRNO if anything goes wrong.
+ */
+int radeon_mn_register(struct radeon_bo *bo, unsigned long addr)
+{
+	unsigned long end = addr + radeon_bo_size(bo) - 1;
+	struct radeon_device *rdev = bo->rdev;
+	struct radeon_mn *rmn;
+	struct interval_tree_node *it;
+
+	rmn = radeon_mn_get(rdev);
+	if (IS_ERR(rmn))
+		return PTR_ERR(rmn);
+
+	mutex_lock(&rmn->lock);
+
+	it = interval_tree_iter_first(&rmn->objects, addr, end);
+	if (it) {
+		mutex_unlock(&rmn->lock);
+		return -EEXIST;
+	}
+
+	bo->mn = rmn;
+	bo->mn_it.start = addr;
+	bo->mn_it.last = end;
+	interval_tree_insert(&bo->mn_it, &rmn->objects);
+
+	mutex_unlock(&rmn->lock);
+
+	return 0;
+}
+
+/**
+ * radeon_mn_unregister - unregister a BO for notifier updates
+ *
+ * @bo: radeon buffer object
+ *
+ * Remove any registration of MMU notifier updates from the buffer object.
+ */
+void radeon_mn_unregister(struct radeon_bo *bo)
+{
+	struct radeon_device *rdev = bo->rdev;
+	struct radeon_mn *rmn;
+
+	mutex_lock(&rdev->mn_lock);
+	rmn = bo->mn;
+	if (rmn == NULL) {
+		mutex_unlock(&rdev->mn_lock);
+		return;
+	}
+
+	mutex_lock(&rmn->lock);
+	interval_tree_remove(&bo->mn_it, &rmn->objects);
+	bo->mn = NULL;
+	mutex_unlock(&rmn->lock);
+	mutex_unlock(&rdev->mn_lock);
+}
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index c73c1e320585..287523807989 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -75,6 +75,7 @@ static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	bo = container_of(tbo, struct radeon_bo, tbo);
 
 	radeon_update_memory_usage(bo, bo->tbo.mem.mem_type, -1);
+	radeon_mn_unregister(bo);
 
 	mutex_lock(&bo->rdev->gem.mutex);
 	list_del_init(&bo->list);
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 5dc61c2d4c73..c77495ffc44f 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -818,6 +818,7 @@ struct drm_radeon_gem_create {
 #define RADEON_GEM_USERPTR_READONLY	(1 << 0)
 #define RADEON_GEM_USERPTR_ANONONLY	(1 << 1)
 #define RADEON_GEM_USERPTR_VALIDATE	(1 << 2)
+#define RADEON_GEM_USERPTR_REGISTER	(1 << 3)
 
 struct drm_radeon_gem_userptr {
 	uint64_t		addr;
-- 
cgit v1.2.3


From fadfe7be6e50de7f03913833b33c56cd8fb66bac Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 1 Aug 2014 14:33:02 +0200
Subject: perf: Add queued work to remove orphaned child events

In cases when the  owner task exits before the workload and the
workload made some forks, all the events stay in until the last
workload process exits. Thats' because each child event holds
parent reference.

We want to release all children events once the parent is gone,
because at that time there's no process to read them anyway, so
they're just eating resources.

This removal  races with process exit, which removes all events
and fork, which clone events.  To be clear of those two, adding
work queue to remove orphaned child for context in case such
event is detected.

Using delayed work queue (with delay == 1), because we queue this
work under perf scheduler callbacks. Normal work queue tries to wake
up the queue process, which deadlocks on rq->lock in this place.

Also preventing clones from abandoned parent event.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1406896382-18404-4-git-send-email-jolsa@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/perf_event.h |  4 +++
 kernel/events/core.c       | 87 +++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 90 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 707617a8c0f6..ef5b62bdb103 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -52,6 +52,7 @@ struct perf_guest_info_callbacks {
 #include <linux/atomic.h>
 #include <linux/sysfs.h>
 #include <linux/perf_regs.h>
+#include <linux/workqueue.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -507,6 +508,9 @@ struct perf_event_context {
 	int				nr_cgroups;	 /* cgroup evts */
 	int				nr_branch_stack; /* branch_stack evt */
 	struct rcu_head			rcu_head;
+
+	struct delayed_work		orphans_remove;
+	bool				orphans_remove_sched;
 };
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bbb3ca22f07c..a25460559b4f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -46,6 +46,8 @@
 
 #include <asm/irq_regs.h>
 
+static struct workqueue_struct *perf_wq;
+
 struct remote_function_call {
 	struct task_struct	*p;
 	int			(*func)(void *info);
@@ -1381,6 +1383,45 @@ out:
 		perf_event__header_size(tmp);
 }
 
+/*
+ * User event without the task.
+ */
+static bool is_orphaned_event(struct perf_event *event)
+{
+	return event && !is_kernel_event(event) && !event->owner;
+}
+
+/*
+ * Event has a parent but parent's task finished and it's
+ * alive only because of children holding refference.
+ */
+static bool is_orphaned_child(struct perf_event *event)
+{
+	return is_orphaned_event(event->parent);
+}
+
+static void orphans_remove_work(struct work_struct *work);
+
+static void schedule_orphans_remove(struct perf_event_context *ctx)
+{
+	if (!ctx->task || ctx->orphans_remove_sched || !perf_wq)
+		return;
+
+	if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) {
+		get_ctx(ctx);
+		ctx->orphans_remove_sched = true;
+	}
+}
+
+static int __init perf_workqueue_init(void)
+{
+	perf_wq = create_singlethread_workqueue("perf");
+	WARN(!perf_wq, "failed to create perf workqueue\n");
+	return perf_wq ? 0 : -1;
+}
+
+core_initcall(perf_workqueue_init);
+
 static inline int
 event_filter_match(struct perf_event *event)
 {
@@ -1430,6 +1471,9 @@ event_sched_out(struct perf_event *event,
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
 
+	if (is_orphaned_child(event))
+		schedule_orphans_remove(ctx);
+
 	perf_pmu_enable(event->pmu);
 }
 
@@ -1732,6 +1776,9 @@ event_sched_in(struct perf_event *event,
 	if (event->attr.exclusive)
 		cpuctx->exclusive = 1;
 
+	if (is_orphaned_child(event))
+		schedule_orphans_remove(ctx);
+
 out:
 	perf_pmu_enable(event->pmu);
 
@@ -3074,6 +3121,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx)
 	INIT_LIST_HEAD(&ctx->flexible_groups);
 	INIT_LIST_HEAD(&ctx->event_list);
 	atomic_set(&ctx->refcount, 1);
+	INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work);
 }
 
 static struct perf_event_context *
@@ -3405,6 +3453,42 @@ static int perf_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+/*
+ * Remove all orphanes events from the context.
+ */
+static void orphans_remove_work(struct work_struct *work)
+{
+	struct perf_event_context *ctx;
+	struct perf_event *event, *tmp;
+
+	ctx = container_of(work, struct perf_event_context,
+			   orphans_remove.work);
+
+	mutex_lock(&ctx->mutex);
+	list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) {
+		struct perf_event *parent_event = event->parent;
+
+		if (!is_orphaned_child(event))
+			continue;
+
+		perf_remove_from_context(event, true);
+
+		mutex_lock(&parent_event->child_mutex);
+		list_del_init(&event->child_list);
+		mutex_unlock(&parent_event->child_mutex);
+
+		free_event(event);
+		put_event(parent_event);
+	}
+
+	raw_spin_lock_irq(&ctx->lock);
+	ctx->orphans_remove_sched = false;
+	raw_spin_unlock_irq(&ctx->lock);
+	mutex_unlock(&ctx->mutex);
+
+	put_ctx(ctx);
+}
+
 u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
 {
 	struct perf_event *child;
@@ -7709,7 +7793,8 @@ inherit_event(struct perf_event *parent_event,
 	if (IS_ERR(child_event))
 		return child_event;
 
-	if (!atomic_long_inc_not_zero(&parent_event->refcount)) {
+	if (is_orphaned_event(parent_event) ||
+	    !atomic_long_inc_not_zero(&parent_event->refcount)) {
 		free_event(child_event);
 		return NULL;
 	}
-- 
cgit v1.2.3


From 770eee1fd38c70a009b321f5dbe64358f42511fd Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Mon, 11 Aug 2014 21:27:12 +0200
Subject: perf/x86: Fix data source encoding issues for load latency/precise
 store

This patch fixes issues introuduce by Andi's previous patch 'Revamp PEBS'
series.

This patch fixes the following:

 - precise_store_data_hsw() encode the mem op type whenever we can
 - precise_store_data_hsw set the default data source correctly

 - 0 is not a valid init value for data source. Define PERF_MEM_NA as the
   default value

This bug was actually introduced by

    commit 722e76e60f2775c21b087ff12c5e678cf0ebcaaf
    Author: Stephane Eranian <eranian@google.com>
    Date:   Thu May 15 17:56:44 2014 +0200

        fix Haswell precise store data source encoding

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1407785233-32193-4-git-send-email-eranian@google.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: ak@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event_intel_ds.c | 11 +++++++----
 include/linux/perf_event.h                |  9 ++++++++-
 2 files changed, 15 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index a9b60f32064f..67919ce0f76a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -113,9 +113,12 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
 	union perf_mem_data_src dse;
 	u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK;
 
-	dse.val = 0;
-	dse.mem_op = PERF_MEM_OP_NA;
-	dse.mem_lvl = PERF_MEM_LVL_NA;
+	dse.val = PERF_MEM_NA;
+
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
+		dse.mem_op = PERF_MEM_OP_STORE;
+	else if (event->hw.flags & PERF_X86_EVENT_PEBS_LD_HSW)
+		dse.mem_op = PERF_MEM_OP_LOAD;
 
 	/*
 	 * L1 info only valid for following events:
@@ -126,7 +129,7 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
 	 * MEM_UOPS_RETIRED.ALL_STORES
 	 */
 	if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0)
-		return dse.mem_lvl;
+		return dse.val;
 
 	if (status & 1)
 		dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ef5b62bdb103..f0a1036b1911 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -608,6 +608,13 @@ struct perf_sample_data {
 	u64				txn;
 };
 
+/* default value for data source */
+#define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
+		    PERF_MEM_S(LVL, NA)   |\
+		    PERF_MEM_S(SNOOP, NA) |\
+		    PERF_MEM_S(LOCK, NA)  |\
+		    PERF_MEM_S(TLB, NA))
+
 static inline void perf_sample_data_init(struct perf_sample_data *data,
 					 u64 addr, u64 period)
 {
@@ -620,7 +627,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->regs_user.regs = NULL;
 	data->stack_user_size = 0;
 	data->weight = 0;
-	data->data_src.val = 0;
+	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
 }
 
-- 
cgit v1.2.3


From 2e39465abc4b7856a0ea6fcf4f6b4668bb5db877 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Aug 2014 12:07:15 +0200
Subject: locking: Remove deprecated smp_mb__() barriers

Its been a while and there are no in-tree users left, so remove the
deprecated barriers.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Chen, Gong <gong.chen@linux.intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Joe Perches <joe@perches.com>
Cc: John Sullivan <jsrhbz@kanargh.force9.co.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/atomic.h | 36 ------------------------------------
 include/linux/bitops.h | 20 --------------------
 kernel/sched/core.c    | 16 ----------------
 3 files changed, 72 deletions(-)

(limited to 'include')

diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index fef3a809e7cf..5b08a8540ecf 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -3,42 +3,6 @@
 #define _LINUX_ATOMIC_H
 #include <asm/atomic.h>
 
-/*
- * Provide __deprecated wrappers for the new interface, avoid flag day changes.
- * We need the ugly external functions to break header recursion hell.
- */
-#ifndef smp_mb__before_atomic_inc
-static inline void __deprecated smp_mb__before_atomic_inc(void)
-{
-	extern void __smp_mb__before_atomic(void);
-	__smp_mb__before_atomic();
-}
-#endif
-
-#ifndef smp_mb__after_atomic_inc
-static inline void __deprecated smp_mb__after_atomic_inc(void)
-{
-	extern void __smp_mb__after_atomic(void);
-	__smp_mb__after_atomic();
-}
-#endif
-
-#ifndef smp_mb__before_atomic_dec
-static inline void __deprecated smp_mb__before_atomic_dec(void)
-{
-	extern void __smp_mb__before_atomic(void);
-	__smp_mb__before_atomic();
-}
-#endif
-
-#ifndef smp_mb__after_atomic_dec
-static inline void __deprecated smp_mb__after_atomic_dec(void)
-{
-	extern void __smp_mb__after_atomic(void);
-	__smp_mb__after_atomic();
-}
-#endif
-
 /**
  * atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cbc5833fb221..be5fd38bd5a0 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -32,26 +32,6 @@ extern unsigned long __sw_hweight64(__u64 w);
  */
 #include <asm/bitops.h>
 
-/*
- * Provide __deprecated wrappers for the new interface, avoid flag day changes.
- * We need the ugly external functions to break header recursion hell.
- */
-#ifndef smp_mb__before_clear_bit
-static inline void __deprecated smp_mb__before_clear_bit(void)
-{
-	extern void __smp_mb__before_atomic(void);
-	__smp_mb__before_atomic();
-}
-#endif
-
-#ifndef smp_mb__after_clear_bit
-static inline void __deprecated smp_mb__after_clear_bit(void)
-{
-	extern void __smp_mb__after_atomic(void);
-	__smp_mb__after_atomic();
-}
-#endif
-
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\
 	     (bit) < (size);					\
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1211575a2208..76c518c9b3a7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -90,22 +90,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
-#ifdef smp_mb__before_atomic
-void __smp_mb__before_atomic(void)
-{
-	smp_mb__before_atomic();
-}
-EXPORT_SYMBOL(__smp_mb__before_atomic);
-#endif
-
-#ifdef smp_mb__after_atomic
-void __smp_mb__after_atomic(void)
-{
-	smp_mb__after_atomic();
-}
-EXPORT_SYMBOL(__smp_mb__after_atomic);
-#endif
-
 void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
 {
 	unsigned long delta;
-- 
cgit v1.2.3


From 7608a43d8f2e02f8b532f8e11481d7ecf8b5d3f9 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <davidlohr@hp.com>
Date: Wed, 30 Jul 2014 13:41:54 -0700
Subject: locking/mutexes: Use MUTEX_SPIN_ON_OWNER when appropriate

4badad35 ("locking/mutex: Disable optimistic spinning on some
architectures") added a ARCH_SUPPORTS_ATOMIC_RMW flag to
disable the mutex optimistic feature on specific archs.

Because CONFIG_MUTEX_SPIN_ON_OWNER only depended on DEBUG and
SMP, it was ok to have the ->owner field conditional a bit
flexible. However by adding a new variable to the matter,
we can waste space with the unused field, ie: CONFIG_SMP &&
(!CONFIG_MUTEX_SPIN_ON_OWNER && !CONFIG_DEBUG_MUTEX).

Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Acked-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: aswin@hp.com
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Link: http://lkml.kernel.org/r/1406752916-3341-5-git-send-email-davidlohr@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mutex.h  | 2 +-
 kernel/locking/mutex.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 8d5535c58cc2..e4c29418f407 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -52,7 +52,7 @@ struct mutex {
 	atomic_t		count;
 	spinlock_t		wait_lock;
 	struct list_head	wait_list;
-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP)
+#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
 	struct task_struct	*owner;
 #endif
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 4115fbf83b12..5cda397607f2 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -16,7 +16,7 @@
 #define mutex_remove_waiter(lock, waiter, ti) \
 		__list_del((waiter)->list.prev, (waiter)->list.next)
 
-#ifdef CONFIG_SMP
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 static inline void mutex_set_owner(struct mutex *lock)
 {
 	lock->owner = current;
-- 
cgit v1.2.3


From 214e0aed639ef40987bf6159fad303171a6de31e Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <davidlohr@hp.com>
Date: Wed, 30 Jul 2014 13:41:55 -0700
Subject: locking/Documentation: Move locking related docs into
 Documentation/locking/

Specifically:
  Documentation/locking/lockdep-design.txt
  Documentation/locking/lockstat.txt
  Documentation/locking/mutex-design.txt
  Documentation/locking/rt-mutex-design.txt
  Documentation/locking/rt-mutex.txt
  Documentation/locking/spinlocks.txt
  Documentation/locking/ww-mutex-design.txt

Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: jason.low2@hp.com
Cc: aswin@hp.com
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Chris Mason <clm@fb.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: David Airlie <airlied@linux.ie>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Josef Bacik <jbacik@fusionio.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lubomir Rintel <lkundrak@v3.sk>
Cc: Masanari Iida <standby24x7@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: fengguang.wu@intel.com
Link: http://lkml.kernel.org/r/1406752916-3341-6-git-send-email-davidlohr@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/00-INDEX                    |   2 +
 Documentation/DocBook/kernel-locking.tmpl |   2 +-
 Documentation/lockdep-design.txt          | 286 -----------
 Documentation/locking/lockdep-design.txt  | 286 +++++++++++
 Documentation/locking/lockstat.txt        | 178 +++++++
 Documentation/locking/mutex-design.txt    | 157 ++++++
 Documentation/locking/rt-mutex-design.txt | 781 ++++++++++++++++++++++++++++++
 Documentation/locking/rt-mutex.txt        |  79 +++
 Documentation/locking/spinlocks.txt       | 167 +++++++
 Documentation/locking/ww-mutex-design.txt | 344 +++++++++++++
 Documentation/lockstat.txt                | 178 -------
 Documentation/mutex-design.txt            | 157 ------
 Documentation/rt-mutex-design.txt         | 781 ------------------------------
 Documentation/rt-mutex.txt                |  79 ---
 Documentation/spinlocks.txt               | 167 -------
 Documentation/ww-mutex-design.txt         | 344 -------------
 MAINTAINERS                               |   4 +-
 drivers/gpu/drm/drm_modeset_lock.c        |   2 +-
 include/linux/lockdep.h                   |   2 +-
 include/linux/mutex.h                     |   2 +-
 include/linux/rwsem.h                     |   2 +-
 kernel/locking/mutex.c                    |   2 +-
 kernel/locking/rtmutex.c                  |   2 +-
 lib/Kconfig.debug                         |   4 +-
 24 files changed, 2005 insertions(+), 2003 deletions(-)
 delete mode 100644 Documentation/lockdep-design.txt
 create mode 100644 Documentation/locking/lockdep-design.txt
 create mode 100644 Documentation/locking/lockstat.txt
 create mode 100644 Documentation/locking/mutex-design.txt
 create mode 100644 Documentation/locking/rt-mutex-design.txt
 create mode 100644 Documentation/locking/rt-mutex.txt
 create mode 100644 Documentation/locking/spinlocks.txt
 create mode 100644 Documentation/locking/ww-mutex-design.txt
 delete mode 100644 Documentation/lockstat.txt
 delete mode 100644 Documentation/mutex-design.txt
 delete mode 100644 Documentation/rt-mutex-design.txt
 delete mode 100644 Documentation/rt-mutex.txt
 delete mode 100644 Documentation/spinlocks.txt
 delete mode 100644 Documentation/ww-mutex-design.txt

(limited to 'include')

diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 27e67a98b7be..1750fcef1ab4 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -287,6 +287,8 @@ local_ops.txt
 	- semantics and behavior of local atomic operations.
 lockdep-design.txt
 	- documentation on the runtime locking correctness validator.
+locking/
+	- directory with info about kernel locking primitives
 lockstat.txt
 	- info on collecting statistics on locks (and contention).
 lockup-watchdogs.txt
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index e584ee12a1e7..7c9cc4846cb6 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -1972,7 +1972,7 @@ machines due to caching.
    <itemizedlist>
     <listitem>
      <para>
-       <filename>Documentation/spinlocks.txt</filename>: 
+       <filename>Documentation/locking/spinlocks.txt</filename>:
        Linus Torvalds' spinlocking tutorial in the kernel sources.
      </para>
     </listitem>
diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt
deleted file mode 100644
index 5dbc99c04f6e..000000000000
--- a/Documentation/lockdep-design.txt
+++ /dev/null
@@ -1,286 +0,0 @@
-Runtime locking correctness validator
-=====================================
-
-started by Ingo Molnar <mingo@redhat.com>
-additions by Arjan van de Ven <arjan@linux.intel.com>
-
-Lock-class
-----------
-
-The basic object the validator operates upon is a 'class' of locks.
-
-A class of locks is a group of locks that are logically the same with
-respect to locking rules, even if the locks may have multiple (possibly
-tens of thousands of) instantiations. For example a lock in the inode
-struct is one class, while each inode has its own instantiation of that
-lock class.
-
-The validator tracks the 'state' of lock-classes, and it tracks
-dependencies between different lock-classes. The validator maintains a
-rolling proof that the state and the dependencies are correct.
-
-Unlike an lock instantiation, the lock-class itself never goes away: when
-a lock-class is used for the first time after bootup it gets registered,
-and all subsequent uses of that lock-class will be attached to this
-lock-class.
-
-State
------
-
-The validator tracks lock-class usage history into 4n + 1 separate state bits:
-
-- 'ever held in STATE context'
-- 'ever held as readlock in STATE context'
-- 'ever held with STATE enabled'
-- 'ever held as readlock with STATE enabled'
-
-Where STATE can be either one of (kernel/lockdep_states.h)
- - hardirq
- - softirq
- - reclaim_fs
-
-- 'ever used'                                       [ == !unused        ]
-
-When locking rules are violated, these state bits are presented in the
-locking error messages, inside curlies. A contrived example:
-
-   modprobe/2287 is trying to acquire lock:
-    (&sio_locks[i].lock){-.-...}, at: [<c02867fd>] mutex_lock+0x21/0x24
-
-   but task is already holding lock:
-    (&sio_locks[i].lock){-.-...}, at: [<c02867fd>] mutex_lock+0x21/0x24
-
-
-The bit position indicates STATE, STATE-read, for each of the states listed
-above, and the character displayed in each indicates:
-
-   '.'  acquired while irqs disabled and not in irq context
-   '-'  acquired in irq context
-   '+'  acquired with irqs enabled
-   '?'  acquired in irq context with irqs enabled.
-
-Unused mutexes cannot be part of the cause of an error.
-
-
-Single-lock state rules:
-------------------------
-
-A softirq-unsafe lock-class is automatically hardirq-unsafe as well. The
-following states are exclusive, and only one of them is allowed to be
-set for any lock-class:
-
- <hardirq-safe> and <hardirq-unsafe>
- <softirq-safe> and <softirq-unsafe>
-
-The validator detects and reports lock usage that violate these
-single-lock state rules.
-
-Multi-lock dependency rules:
-----------------------------
-
-The same lock-class must not be acquired twice, because this could lead
-to lock recursion deadlocks.
-
-Furthermore, two locks may not be taken in different order:
-
- <L1> -> <L2>
- <L2> -> <L1>
-
-because this could lead to lock inversion deadlocks. (The validator
-finds such dependencies in arbitrary complexity, i.e. there can be any
-other locking sequence between the acquire-lock operations, the
-validator will still track all dependencies between locks.)
-
-Furthermore, the following usage based lock dependencies are not allowed
-between any two lock-classes:
-
-   <hardirq-safe>   ->  <hardirq-unsafe>
-   <softirq-safe>   ->  <softirq-unsafe>
-
-The first rule comes from the fact the a hardirq-safe lock could be
-taken by a hardirq context, interrupting a hardirq-unsafe lock - and
-thus could result in a lock inversion deadlock. Likewise, a softirq-safe
-lock could be taken by an softirq context, interrupting a softirq-unsafe
-lock.
-
-The above rules are enforced for any locking sequence that occurs in the
-kernel: when acquiring a new lock, the validator checks whether there is
-any rule violation between the new lock and any of the held locks.
-
-When a lock-class changes its state, the following aspects of the above
-dependency rules are enforced:
-
-- if a new hardirq-safe lock is discovered, we check whether it
-  took any hardirq-unsafe lock in the past.
-
-- if a new softirq-safe lock is discovered, we check whether it took
-  any softirq-unsafe lock in the past.
-
-- if a new hardirq-unsafe lock is discovered, we check whether any
-  hardirq-safe lock took it in the past.
-
-- if a new softirq-unsafe lock is discovered, we check whether any
-  softirq-safe lock took it in the past.
-
-(Again, we do these checks too on the basis that an interrupt context
-could interrupt _any_ of the irq-unsafe or hardirq-unsafe locks, which
-could lead to a lock inversion deadlock - even if that lock scenario did
-not trigger in practice yet.)
-
-Exception: Nested data dependencies leading to nested locking
--------------------------------------------------------------
-
-There are a few cases where the Linux kernel acquires more than one
-instance of the same lock-class. Such cases typically happen when there
-is some sort of hierarchy within objects of the same type. In these
-cases there is an inherent "natural" ordering between the two objects
-(defined by the properties of the hierarchy), and the kernel grabs the
-locks in this fixed order on each of the objects.
-
-An example of such an object hierarchy that results in "nested locking"
-is that of a "whole disk" block-dev object and a "partition" block-dev
-object; the partition is "part of" the whole device and as long as one
-always takes the whole disk lock as a higher lock than the partition
-lock, the lock ordering is fully correct. The validator does not
-automatically detect this natural ordering, as the locking rule behind
-the ordering is not static.
-
-In order to teach the validator about this correct usage model, new
-versions of the various locking primitives were added that allow you to
-specify a "nesting level". An example call, for the block device mutex,
-looks like this:
-
-enum bdev_bd_mutex_lock_class
-{
-       BD_MUTEX_NORMAL,
-       BD_MUTEX_WHOLE,
-       BD_MUTEX_PARTITION
-};
-
- mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
-
-In this case the locking is done on a bdev object that is known to be a
-partition.
-
-The validator treats a lock that is taken in such a nested fashion as a
-separate (sub)class for the purposes of validation.
-
-Note: When changing code to use the _nested() primitives, be careful and
-check really thoroughly that the hierarchy is correctly mapped; otherwise
-you can get false positives or false negatives.
-
-Proof of 100% correctness:
---------------------------
-
-The validator achieves perfect, mathematical 'closure' (proof of locking
-correctness) in the sense that for every simple, standalone single-task
-locking sequence that occurred at least once during the lifetime of the
-kernel, the validator proves it with a 100% certainty that no
-combination and timing of these locking sequences can cause any class of
-lock related deadlock. [*]
-
-I.e. complex multi-CPU and multi-task locking scenarios do not have to
-occur in practice to prove a deadlock: only the simple 'component'
-locking chains have to occur at least once (anytime, in any
-task/context) for the validator to be able to prove correctness. (For
-example, complex deadlocks that would normally need more than 3 CPUs and
-a very unlikely constellation of tasks, irq-contexts and timings to
-occur, can be detected on a plain, lightly loaded single-CPU system as
-well!)
-
-This radically decreases the complexity of locking related QA of the
-kernel: what has to be done during QA is to trigger as many "simple"
-single-task locking dependencies in the kernel as possible, at least
-once, to prove locking correctness - instead of having to trigger every
-possible combination of locking interaction between CPUs, combined with
-every possible hardirq and softirq nesting scenario (which is impossible
-to do in practice).
-
-[*] assuming that the validator itself is 100% correct, and no other
-    part of the system corrupts the state of the validator in any way.
-    We also assume that all NMI/SMM paths [which could interrupt
-    even hardirq-disabled codepaths] are correct and do not interfere
-    with the validator. We also assume that the 64-bit 'chain hash'
-    value is unique for every lock-chain in the system. Also, lock
-    recursion must not be higher than 20.
-
-Performance:
-------------
-
-The above rules require _massive_ amounts of runtime checking. If we did
-that for every lock taken and for every irqs-enable event, it would
-render the system practically unusably slow. The complexity of checking
-is O(N^2), so even with just a few hundred lock-classes we'd have to do
-tens of thousands of checks for every event.
-
-This problem is solved by checking any given 'locking scenario' (unique
-sequence of locks taken after each other) only once. A simple stack of
-held locks is maintained, and a lightweight 64-bit hash value is
-calculated, which hash is unique for every lock chain. The hash value,
-when the chain is validated for the first time, is then put into a hash
-table, which hash-table can be checked in a lockfree manner. If the
-locking chain occurs again later on, the hash table tells us that we
-dont have to validate the chain again.
-
-Troubleshooting:
-----------------
-
-The validator tracks a maximum of MAX_LOCKDEP_KEYS number of lock classes.
-Exceeding this number will trigger the following lockdep warning:
-
-	(DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
-
-By default, MAX_LOCKDEP_KEYS is currently set to 8191, and typical
-desktop systems have less than 1,000 lock classes, so this warning
-normally results from lock-class leakage or failure to properly
-initialize locks.  These two problems are illustrated below:
-
-1.	Repeated module loading and unloading while running the validator
-	will result in lock-class leakage.  The issue here is that each
-	load of the module will create a new set of lock classes for
-	that module's locks, but module unloading does not remove old
-	classes (see below discussion of reuse of lock classes for why).
-	Therefore, if that module is loaded and unloaded repeatedly,
-	the number of lock classes will eventually reach the maximum.
-
-2.	Using structures such as arrays that have large numbers of
-	locks that are not explicitly initialized.  For example,
-	a hash table with 8192 buckets where each bucket has its own
-	spinlock_t will consume 8192 lock classes -unless- each spinlock
-	is explicitly initialized at runtime, for example, using the
-	run-time spin_lock_init() as opposed to compile-time initializers
-	such as __SPIN_LOCK_UNLOCKED().  Failure to properly initialize
-	the per-bucket spinlocks would guarantee lock-class overflow.
-	In contrast, a loop that called spin_lock_init() on each lock
-	would place all 8192 locks into a single lock class.
-
-	The moral of this story is that you should always explicitly
-	initialize your locks.
-
-One might argue that the validator should be modified to allow
-lock classes to be reused.  However, if you are tempted to make this
-argument, first review the code and think through the changes that would
-be required, keeping in mind that the lock classes to be removed are
-likely to be linked into the lock-dependency graph.  This turns out to
-be harder to do than to say.
-
-Of course, if you do run out of lock classes, the next thing to do is
-to find the offending lock classes.  First, the following command gives
-you the number of lock classes currently in use along with the maximum:
-
-	grep "lock-classes" /proc/lockdep_stats
-
-This command produces the following output on a modest system:
-
-	 lock-classes:                          748 [max: 8191]
-
-If the number allocated (748 above) increases continually over time,
-then there is likely a leak.  The following command can be used to
-identify the leaking lock classes:
-
-	grep "BD" /proc/lockdep
-
-Run the command and save the output, then compare against the output from
-a later run of this command to identify the leakers.  This same output
-can also help you find situations where runtime lock initialization has
-been omitted.
diff --git a/Documentation/locking/lockdep-design.txt b/Documentation/locking/lockdep-design.txt
new file mode 100644
index 000000000000..5dbc99c04f6e
--- /dev/null
+++ b/Documentation/locking/lockdep-design.txt
@@ -0,0 +1,286 @@
+Runtime locking correctness validator
+=====================================
+
+started by Ingo Molnar <mingo@redhat.com>
+additions by Arjan van de Ven <arjan@linux.intel.com>
+
+Lock-class
+----------
+
+The basic object the validator operates upon is a 'class' of locks.
+
+A class of locks is a group of locks that are logically the same with
+respect to locking rules, even if the locks may have multiple (possibly
+tens of thousands of) instantiations. For example a lock in the inode
+struct is one class, while each inode has its own instantiation of that
+lock class.
+
+The validator tracks the 'state' of lock-classes, and it tracks
+dependencies between different lock-classes. The validator maintains a
+rolling proof that the state and the dependencies are correct.
+
+Unlike an lock instantiation, the lock-class itself never goes away: when
+a lock-class is used for the first time after bootup it gets registered,
+and all subsequent uses of that lock-class will be attached to this
+lock-class.
+
+State
+-----
+
+The validator tracks lock-class usage history into 4n + 1 separate state bits:
+
+- 'ever held in STATE context'
+- 'ever held as readlock in STATE context'
+- 'ever held with STATE enabled'
+- 'ever held as readlock with STATE enabled'
+
+Where STATE can be either one of (kernel/lockdep_states.h)
+ - hardirq
+ - softirq
+ - reclaim_fs
+
+- 'ever used'                                       [ == !unused        ]
+
+When locking rules are violated, these state bits are presented in the
+locking error messages, inside curlies. A contrived example:
+
+   modprobe/2287 is trying to acquire lock:
+    (&sio_locks[i].lock){-.-...}, at: [<c02867fd>] mutex_lock+0x21/0x24
+
+   but task is already holding lock:
+    (&sio_locks[i].lock){-.-...}, at: [<c02867fd>] mutex_lock+0x21/0x24
+
+
+The bit position indicates STATE, STATE-read, for each of the states listed
+above, and the character displayed in each indicates:
+
+   '.'  acquired while irqs disabled and not in irq context
+   '-'  acquired in irq context
+   '+'  acquired with irqs enabled
+   '?'  acquired in irq context with irqs enabled.
+
+Unused mutexes cannot be part of the cause of an error.
+
+
+Single-lock state rules:
+------------------------
+
+A softirq-unsafe lock-class is automatically hardirq-unsafe as well. The
+following states are exclusive, and only one of them is allowed to be
+set for any lock-class:
+
+ <hardirq-safe> and <hardirq-unsafe>
+ <softirq-safe> and <softirq-unsafe>
+
+The validator detects and reports lock usage that violate these
+single-lock state rules.
+
+Multi-lock dependency rules:
+----------------------------
+
+The same lock-class must not be acquired twice, because this could lead
+to lock recursion deadlocks.
+
+Furthermore, two locks may not be taken in different order:
+
+ <L1> -> <L2>
+ <L2> -> <L1>
+
+because this could lead to lock inversion deadlocks. (The validator
+finds such dependencies in arbitrary complexity, i.e. there can be any
+other locking sequence between the acquire-lock operations, the
+validator will still track all dependencies between locks.)
+
+Furthermore, the following usage based lock dependencies are not allowed
+between any two lock-classes:
+
+   <hardirq-safe>   ->  <hardirq-unsafe>
+   <softirq-safe>   ->  <softirq-unsafe>
+
+The first rule comes from the fact the a hardirq-safe lock could be
+taken by a hardirq context, interrupting a hardirq-unsafe lock - and
+thus could result in a lock inversion deadlock. Likewise, a softirq-safe
+lock could be taken by an softirq context, interrupting a softirq-unsafe
+lock.
+
+The above rules are enforced for any locking sequence that occurs in the
+kernel: when acquiring a new lock, the validator checks whether there is
+any rule violation between the new lock and any of the held locks.
+
+When a lock-class changes its state, the following aspects of the above
+dependency rules are enforced:
+
+- if a new hardirq-safe lock is discovered, we check whether it
+  took any hardirq-unsafe lock in the past.
+
+- if a new softirq-safe lock is discovered, we check whether it took
+  any softirq-unsafe lock in the past.
+
+- if a new hardirq-unsafe lock is discovered, we check whether any
+  hardirq-safe lock took it in the past.
+
+- if a new softirq-unsafe lock is discovered, we check whether any
+  softirq-safe lock took it in the past.
+
+(Again, we do these checks too on the basis that an interrupt context
+could interrupt _any_ of the irq-unsafe or hardirq-unsafe locks, which
+could lead to a lock inversion deadlock - even if that lock scenario did
+not trigger in practice yet.)
+
+Exception: Nested data dependencies leading to nested locking
+-------------------------------------------------------------
+
+There are a few cases where the Linux kernel acquires more than one
+instance of the same lock-class. Such cases typically happen when there
+is some sort of hierarchy within objects of the same type. In these
+cases there is an inherent "natural" ordering between the two objects
+(defined by the properties of the hierarchy), and the kernel grabs the
+locks in this fixed order on each of the objects.
+
+An example of such an object hierarchy that results in "nested locking"
+is that of a "whole disk" block-dev object and a "partition" block-dev
+object; the partition is "part of" the whole device and as long as one
+always takes the whole disk lock as a higher lock than the partition
+lock, the lock ordering is fully correct. The validator does not
+automatically detect this natural ordering, as the locking rule behind
+the ordering is not static.
+
+In order to teach the validator about this correct usage model, new
+versions of the various locking primitives were added that allow you to
+specify a "nesting level". An example call, for the block device mutex,
+looks like this:
+
+enum bdev_bd_mutex_lock_class
+{
+       BD_MUTEX_NORMAL,
+       BD_MUTEX_WHOLE,
+       BD_MUTEX_PARTITION
+};
+
+ mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
+
+In this case the locking is done on a bdev object that is known to be a
+partition.
+
+The validator treats a lock that is taken in such a nested fashion as a
+separate (sub)class for the purposes of validation.
+
+Note: When changing code to use the _nested() primitives, be careful and
+check really thoroughly that the hierarchy is correctly mapped; otherwise
+you can get false positives or false negatives.
+
+Proof of 100% correctness:
+--------------------------
+
+The validator achieves perfect, mathematical 'closure' (proof of locking
+correctness) in the sense that for every simple, standalone single-task
+locking sequence that occurred at least once during the lifetime of the
+kernel, the validator proves it with a 100% certainty that no
+combination and timing of these locking sequences can cause any class of
+lock related deadlock. [*]
+
+I.e. complex multi-CPU and multi-task locking scenarios do not have to
+occur in practice to prove a deadlock: only the simple 'component'
+locking chains have to occur at least once (anytime, in any
+task/context) for the validator to be able to prove correctness. (For
+example, complex deadlocks that would normally need more than 3 CPUs and
+a very unlikely constellation of tasks, irq-contexts and timings to
+occur, can be detected on a plain, lightly loaded single-CPU system as
+well!)
+
+This radically decreases the complexity of locking related QA of the
+kernel: what has to be done during QA is to trigger as many "simple"
+single-task locking dependencies in the kernel as possible, at least
+once, to prove locking correctness - instead of having to trigger every
+possible combination of locking interaction between CPUs, combined with
+every possible hardirq and softirq nesting scenario (which is impossible
+to do in practice).
+
+[*] assuming that the validator itself is 100% correct, and no other
+    part of the system corrupts the state of the validator in any way.
+    We also assume that all NMI/SMM paths [which could interrupt
+    even hardirq-disabled codepaths] are correct and do not interfere
+    with the validator. We also assume that the 64-bit 'chain hash'
+    value is unique for every lock-chain in the system. Also, lock
+    recursion must not be higher than 20.
+
+Performance:
+------------
+
+The above rules require _massive_ amounts of runtime checking. If we did
+that for every lock taken and for every irqs-enable event, it would
+render the system practically unusably slow. The complexity of checking
+is O(N^2), so even with just a few hundred lock-classes we'd have to do
+tens of thousands of checks for every event.
+
+This problem is solved by checking any given 'locking scenario' (unique
+sequence of locks taken after each other) only once. A simple stack of
+held locks is maintained, and a lightweight 64-bit hash value is
+calculated, which hash is unique for every lock chain. The hash value,
+when the chain is validated for the first time, is then put into a hash
+table, which hash-table can be checked in a lockfree manner. If the
+locking chain occurs again later on, the hash table tells us that we
+dont have to validate the chain again.
+
+Troubleshooting:
+----------------
+
+The validator tracks a maximum of MAX_LOCKDEP_KEYS number of lock classes.
+Exceeding this number will trigger the following lockdep warning:
+
+	(DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
+
+By default, MAX_LOCKDEP_KEYS is currently set to 8191, and typical
+desktop systems have less than 1,000 lock classes, so this warning
+normally results from lock-class leakage or failure to properly
+initialize locks.  These two problems are illustrated below:
+
+1.	Repeated module loading and unloading while running the validator
+	will result in lock-class leakage.  The issue here is that each
+	load of the module will create a new set of lock classes for
+	that module's locks, but module unloading does not remove old
+	classes (see below discussion of reuse of lock classes for why).
+	Therefore, if that module is loaded and unloaded repeatedly,
+	the number of lock classes will eventually reach the maximum.
+
+2.	Using structures such as arrays that have large numbers of
+	locks that are not explicitly initialized.  For example,
+	a hash table with 8192 buckets where each bucket has its own
+	spinlock_t will consume 8192 lock classes -unless- each spinlock
+	is explicitly initialized at runtime, for example, using the
+	run-time spin_lock_init() as opposed to compile-time initializers
+	such as __SPIN_LOCK_UNLOCKED().  Failure to properly initialize
+	the per-bucket spinlocks would guarantee lock-class overflow.
+	In contrast, a loop that called spin_lock_init() on each lock
+	would place all 8192 locks into a single lock class.
+
+	The moral of this story is that you should always explicitly
+	initialize your locks.
+
+One might argue that the validator should be modified to allow
+lock classes to be reused.  However, if you are tempted to make this
+argument, first review the code and think through the changes that would
+be required, keeping in mind that the lock classes to be removed are
+likely to be linked into the lock-dependency graph.  This turns out to
+be harder to do than to say.
+
+Of course, if you do run out of lock classes, the next thing to do is
+to find the offending lock classes.  First, the following command gives
+you the number of lock classes currently in use along with the maximum:
+
+	grep "lock-classes" /proc/lockdep_stats
+
+This command produces the following output on a modest system:
+
+	 lock-classes:                          748 [max: 8191]
+
+If the number allocated (748 above) increases continually over time,
+then there is likely a leak.  The following command can be used to
+identify the leaking lock classes:
+
+	grep "BD" /proc/lockdep
+
+Run the command and save the output, then compare against the output from
+a later run of this command to identify the leakers.  This same output
+can also help you find situations where runtime lock initialization has
+been omitted.
diff --git a/Documentation/locking/lockstat.txt b/Documentation/locking/lockstat.txt
new file mode 100644
index 000000000000..7428773a1e69
--- /dev/null
+++ b/Documentation/locking/lockstat.txt
@@ -0,0 +1,178 @@
+
+LOCK STATISTICS
+
+- WHAT
+
+As the name suggests, it provides statistics on locks.
+
+- WHY
+
+Because things like lock contention can severely impact performance.
+
+- HOW
+
+Lockdep already has hooks in the lock functions and maps lock instances to
+lock classes. We build on that (see Documentation/lokcing/lockdep-design.txt).
+The graph below shows the relation between the lock functions and the various
+hooks therein.
+
+        __acquire
+            |
+           lock _____
+            |        \
+            |    __contended
+            |         |
+            |       <wait>
+            | _______/
+            |/
+            |
+       __acquired
+            |
+            .
+          <hold>
+            .
+            |
+       __release
+            |
+         unlock
+
+lock, unlock	- the regular lock functions
+__*		- the hooks
+<> 		- states
+
+With these hooks we provide the following statistics:
+
+ con-bounces       - number of lock contention that involved x-cpu data
+ contentions       - number of lock acquisitions that had to wait
+ wait time min     - shortest (non-0) time we ever had to wait for a lock
+           max     - longest time we ever had to wait for a lock
+	   total   - total time we spend waiting on this lock
+	   avg     - average time spent waiting on this lock
+ acq-bounces       - number of lock acquisitions that involved x-cpu data
+ acquisitions      - number of times we took the lock
+ hold time min     - shortest (non-0) time we ever held the lock
+	   max     - longest time we ever held the lock
+	   total   - total time this lock was held
+	   avg     - average time this lock was held
+
+These numbers are gathered per lock class, per read/write state (when
+applicable).
+
+It also tracks 4 contention points per class. A contention point is a call site
+that had to wait on lock acquisition.
+
+ - CONFIGURATION
+
+Lock statistics are enabled via CONFIG_LOCK_STAT.
+
+ - USAGE
+
+Enable collection of statistics:
+
+# echo 1 >/proc/sys/kernel/lock_stat
+
+Disable collection of statistics:
+
+# echo 0 >/proc/sys/kernel/lock_stat
+
+Look at the current lock statistics:
+
+( line numbers not part of actual output, done for clarity in the explanation
+  below )
+
+# less /proc/lock_stat
+
+01 lock_stat version 0.4
+02-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+03                              class name    con-bounces    contentions   waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg
+04-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+05
+06                         &mm->mmap_sem-W:            46             84           0.26         939.10       16371.53         194.90          47291        2922365           0.16     2220301.69 17464026916.32        5975.99
+07                         &mm->mmap_sem-R:            37            100           1.31      299502.61      325629.52        3256.30         212344       34316685           0.10        7744.91    95016910.20           2.77
+08                         ---------------
+09                           &mm->mmap_sem              1          [<ffffffff811502a7>] khugepaged_scan_mm_slot+0x57/0x280
+19                           &mm->mmap_sem             96          [<ffffffff815351c4>] __do_page_fault+0x1d4/0x510
+11                           &mm->mmap_sem             34          [<ffffffff81113d77>] vm_mmap_pgoff+0x87/0xd0
+12                           &mm->mmap_sem             17          [<ffffffff81127e71>] vm_munmap+0x41/0x80
+13                         ---------------
+14                           &mm->mmap_sem              1          [<ffffffff81046fda>] dup_mmap+0x2a/0x3f0
+15                           &mm->mmap_sem             60          [<ffffffff81129e29>] SyS_mprotect+0xe9/0x250
+16                           &mm->mmap_sem             41          [<ffffffff815351c4>] __do_page_fault+0x1d4/0x510
+17                           &mm->mmap_sem             68          [<ffffffff81113d77>] vm_mmap_pgoff+0x87/0xd0
+18
+19.............................................................................................................................................................................................................................
+20
+21                         unix_table_lock:           110            112           0.21          49.24         163.91           1.46          21094          66312           0.12         624.42       31589.81           0.48
+22                         ---------------
+23                         unix_table_lock             45          [<ffffffff8150ad8e>] unix_create1+0x16e/0x1b0
+24                         unix_table_lock             47          [<ffffffff8150b111>] unix_release_sock+0x31/0x250
+25                         unix_table_lock             15          [<ffffffff8150ca37>] unix_find_other+0x117/0x230
+26                         unix_table_lock              5          [<ffffffff8150a09f>] unix_autobind+0x11f/0x1b0
+27                         ---------------
+28                         unix_table_lock             39          [<ffffffff8150b111>] unix_release_sock+0x31/0x250
+29                         unix_table_lock             49          [<ffffffff8150ad8e>] unix_create1+0x16e/0x1b0
+30                         unix_table_lock             20          [<ffffffff8150ca37>] unix_find_other+0x117/0x230
+31                         unix_table_lock              4          [<ffffffff8150a09f>] unix_autobind+0x11f/0x1b0
+
+
+This excerpt shows the first two lock class statistics. Line 01 shows the
+output version - each time the format changes this will be updated. Line 02-04
+show the header with column descriptions. Lines 05-18 and 20-31 show the actual
+statistics. These statistics come in two parts; the actual stats separated by a
+short separator (line 08, 13) from the contention points.
+
+The first lock (05-18) is a read/write lock, and shows two lines above the
+short separator. The contention points don't match the column descriptors,
+they have two: contentions and [<IP>] symbol. The second set of contention
+points are the points we're contending with.
+
+The integer part of the time values is in us.
+
+Dealing with nested locks, subclasses may appear:
+
+32...........................................................................................................................................................................................................................
+33
+34                               &rq->lock:       13128          13128           0.43         190.53      103881.26           7.91          97454        3453404           0.00         401.11    13224683.11           3.82
+35                               ---------
+36                               &rq->lock          645          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
+37                               &rq->lock          297          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+38                               &rq->lock          360          [<ffffffff8103c4c5>] select_task_rq_fair+0x1f0/0x74a
+39                               &rq->lock          428          [<ffffffff81045f98>] scheduler_tick+0x46/0x1fb
+40                               ---------
+41                               &rq->lock           77          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
+42                               &rq->lock          174          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+43                               &rq->lock         4715          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
+44                               &rq->lock          893          [<ffffffff81340524>] schedule+0x157/0x7b8
+45
+46...........................................................................................................................................................................................................................
+47
+48                             &rq->lock/1:        1526          11488           0.33         388.73      136294.31          11.86          21461          38404           0.00          37.93      109388.53           2.84
+49                             -----------
+50                             &rq->lock/1        11526          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
+51                             -----------
+52                             &rq->lock/1         5645          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
+53                             &rq->lock/1         1224          [<ffffffff81340524>] schedule+0x157/0x7b8
+54                             &rq->lock/1         4336          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
+55                             &rq->lock/1          181          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+
+Line 48 shows statistics for the second subclass (/1) of &rq->lock class
+(subclass starts from 0), since in this case, as line 50 suggests,
+double_rq_lock actually acquires a nested lock of two spinlocks.
+
+View the top contending locks:
+
+# grep : /proc/lock_stat | head
+			clockevents_lock:       2926159        2947636           0.15       46882.81  1784540466.34         605.41        3381345        3879161           0.00        2260.97    53178395.68          13.71
+		     tick_broadcast_lock:        346460         346717           0.18        2257.43    39364622.71         113.54        3642919        4242696           0.00        2263.79    49173646.60          11.59
+		  &mapping->i_mmap_mutex:        203896         203899           3.36      645530.05 31767507988.39      155800.21        3361776        8893984           0.17        2254.15    14110121.02           1.59
+			       &rq->lock:        135014         136909           0.18         606.09      842160.68           6.15        1540728       10436146           0.00         728.72    17606683.41           1.69
+	       &(&zone->lru_lock)->rlock:         93000          94934           0.16          59.18      188253.78           1.98        1199912        3809894           0.15         391.40     3559518.81           0.93
+			 tasklist_lock-W:         40667          41130           0.23        1189.42      428980.51          10.43         270278         510106           0.16         653.51     3939674.91           7.72
+			 tasklist_lock-R:         21298          21305           0.20        1310.05      215511.12          10.12         186204         241258           0.14        1162.33     1179779.23           4.89
+			      rcu_node_1:         47656          49022           0.16         635.41      193616.41           3.95         844888        1865423           0.00         764.26     1656226.96           0.89
+       &(&dentry->d_lockref.lock)->rlock:         39791          40179           0.15        1302.08       88851.96           2.21        2790851       12527025           0.10        1910.75     3379714.27           0.27
+			      rcu_node_0:         29203          30064           0.16         786.55     1555573.00          51.74          88963         244254           0.00         398.87      428872.51           1.76
+
+Clear the statistics:
+
+# echo 0 > /proc/lock_stat
diff --git a/Documentation/locking/mutex-design.txt b/Documentation/locking/mutex-design.txt
new file mode 100644
index 000000000000..ee231ed09ec6
--- /dev/null
+++ b/Documentation/locking/mutex-design.txt
@@ -0,0 +1,157 @@
+Generic Mutex Subsystem
+
+started by Ingo Molnar <mingo@redhat.com>
+updated by Davidlohr Bueso <davidlohr@hp.com>
+
+What are mutexes?
+-----------------
+
+In the Linux kernel, mutexes refer to a particular locking primitive
+that enforces serialization on shared memory systems, and not only to
+the generic term referring to 'mutual exclusion' found in academia
+or similar theoretical text books. Mutexes are sleeping locks which
+behave similarly to binary semaphores, and were introduced in 2006[1]
+as an alternative to these. This new data structure provided a number
+of advantages, including simpler interfaces, and at that time smaller
+code (see Disadvantages).
+
+[1] http://lwn.net/Articles/164802/
+
+Implementation
+--------------
+
+Mutexes are represented by 'struct mutex', defined in include/linux/mutex.h
+and implemented in kernel/locking/mutex.c. These locks use a three
+state atomic counter (->count) to represent the different possible
+transitions that can occur during the lifetime of a lock:
+
+	  1: unlocked
+	  0: locked, no waiters
+   negative: locked, with potential waiters
+
+In its most basic form it also includes a wait-queue and a spinlock
+that serializes access to it. CONFIG_SMP systems can also include
+a pointer to the lock task owner (->owner) as well as a spinner MCS
+lock (->osq), both described below in (ii).
+
+When acquiring a mutex, there are three possible paths that can be
+taken, depending on the state of the lock:
+
+(i) fastpath: tries to atomically acquire the lock by decrementing the
+    counter. If it was already taken by another task it goes to the next
+    possible path. This logic is architecture specific. On x86-64, the
+    locking fastpath is 2 instructions:
+
+    0000000000000e10 <mutex_lock>:
+    e21:   f0 ff 0b                lock decl (%rbx)
+    e24:   79 08                   jns    e2e <mutex_lock+0x1e>
+
+   the unlocking fastpath is equally tight:
+
+    0000000000000bc0 <mutex_unlock>:
+    bc8:   f0 ff 07                lock incl (%rdi)
+    bcb:   7f 0a                   jg     bd7 <mutex_unlock+0x17>
+
+
+(ii) midpath: aka optimistic spinning, tries to spin for acquisition
+     while the lock owner is running and there are no other tasks ready
+     to run that have higher priority (need_resched). The rationale is
+     that if the lock owner is running, it is likely to release the lock
+     soon. The mutex spinners are queued up using MCS lock so that only
+     one spinner can compete for the mutex.
+
+     The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spinlock
+     with the desirable properties of being fair and with each cpu trying
+     to acquire the lock spinning on a local variable. It avoids expensive
+     cacheline bouncing that common test-and-set spinlock implementations
+     incur. An MCS-like lock is specially tailored for optimistic spinning
+     for sleeping lock implementation. An important feature of the customized
+     MCS lock is that it has the extra property that spinners are able to exit
+     the MCS spinlock queue when they need to reschedule. This further helps
+     avoid situations where MCS spinners that need to reschedule would continue
+     waiting to spin on mutex owner, only to go directly to slowpath upon
+     obtaining the MCS lock.
+
+
+(iii) slowpath: last resort, if the lock is still unable to be acquired,
+      the task is added to the wait-queue and sleeps until woken up by the
+      unlock path. Under normal circumstances it blocks as TASK_UNINTERRUPTIBLE.
+
+While formally kernel mutexes are sleepable locks, it is path (ii) that
+makes them more practically a hybrid type. By simply not interrupting a
+task and busy-waiting for a few cycles instead of immediately sleeping,
+the performance of this lock has been seen to significantly improve a
+number of workloads. Note that this technique is also used for rw-semaphores.
+
+Semantics
+---------
+
+The mutex subsystem checks and enforces the following rules:
+
+    - Only one task can hold the mutex at a time.
+    - Only the owner can unlock the mutex.
+    - Multiple unlocks are not permitted.
+    - Recursive locking/unlocking is not permitted.
+    - A mutex must only be initialized via the API (see below).
+    - A task may not exit with a mutex held.
+    - Memory areas where held locks reside must not be freed.
+    - Held mutexes must not be reinitialized.
+    - Mutexes may not be used in hardware or software interrupt
+      contexts such as tasklets and timers.
+
+These semantics are fully enforced when CONFIG DEBUG_MUTEXES is enabled.
+In addition, the mutex debugging code also implements a number of other
+features that make lock debugging easier and faster:
+
+    - Uses symbolic names of mutexes, whenever they are printed
+      in debug output.
+    - Point-of-acquire tracking, symbolic lookup of function names,
+      list of all locks held in the system, printout of them.
+    - Owner tracking.
+    - Detects self-recursing locks and prints out all relevant info.
+    - Detects multi-task circular deadlocks and prints out all affected
+      locks and tasks (and only those tasks).
+
+
+Interfaces
+----------
+Statically define the mutex:
+   DEFINE_MUTEX(name);
+
+Dynamically initialize the mutex:
+   mutex_init(mutex);
+
+Acquire the mutex, uninterruptible:
+   void mutex_lock(struct mutex *lock);
+   void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
+   int  mutex_trylock(struct mutex *lock);
+
+Acquire the mutex, interruptible:
+   int mutex_lock_interruptible_nested(struct mutex *lock,
+				       unsigned int subclass);
+   int mutex_lock_interruptible(struct mutex *lock);
+
+Acquire the mutex, interruptible, if dec to 0:
+   int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
+
+Unlock the mutex:
+   void mutex_unlock(struct mutex *lock);
+
+Test if the mutex is taken:
+   int mutex_is_locked(struct mutex *lock);
+
+Disadvantages
+-------------
+
+Unlike its original design and purpose, 'struct mutex' is larger than
+most locks in the kernel. E.g: on x86-64 it is 40 bytes, almost twice
+as large as 'struct semaphore' (24 bytes) and 8 bytes shy of the
+'struct rw_semaphore' variant. Larger structure sizes mean more CPU
+cache and memory footprint.
+
+When to use mutexes
+-------------------
+
+Unless the strict semantics of mutexes are unsuitable and/or the critical
+region prevents the lock from being shared, always prefer them to any other
+locking primitive.
diff --git a/Documentation/locking/rt-mutex-design.txt b/Documentation/locking/rt-mutex-design.txt
new file mode 100644
index 000000000000..8666070d3189
--- /dev/null
+++ b/Documentation/locking/rt-mutex-design.txt
@@ -0,0 +1,781 @@
+#
+# Copyright (c) 2006 Steven Rostedt
+# Licensed under the GNU Free Documentation License, Version 1.2
+#
+
+RT-mutex implementation design
+------------------------------
+
+This document tries to describe the design of the rtmutex.c implementation.
+It doesn't describe the reasons why rtmutex.c exists. For that please see
+Documentation/rt-mutex.txt.  Although this document does explain problems
+that happen without this code, but that is in the concept to understand
+what the code actually is doing.
+
+The goal of this document is to help others understand the priority
+inheritance (PI) algorithm that is used, as well as reasons for the
+decisions that were made to implement PI in the manner that was done.
+
+
+Unbounded Priority Inversion
+----------------------------
+
+Priority inversion is when a lower priority process executes while a higher
+priority process wants to run.  This happens for several reasons, and
+most of the time it can't be helped.  Anytime a high priority process wants
+to use a resource that a lower priority process has (a mutex for example),
+the high priority process must wait until the lower priority process is done
+with the resource.  This is a priority inversion.  What we want to prevent
+is something called unbounded priority inversion.  That is when the high
+priority process is prevented from running by a lower priority process for
+an undetermined amount of time.
+
+The classic example of unbounded priority inversion is where you have three
+processes, let's call them processes A, B, and C, where A is the highest
+priority process, C is the lowest, and B is in between. A tries to grab a lock
+that C owns and must wait and lets C run to release the lock. But in the
+meantime, B executes, and since B is of a higher priority than C, it preempts C,
+but by doing so, it is in fact preempting A which is a higher priority process.
+Now there's no way of knowing how long A will be sleeping waiting for C
+to release the lock, because for all we know, B is a CPU hog and will
+never give C a chance to release the lock.  This is called unbounded priority
+inversion.
+
+Here's a little ASCII art to show the problem.
+
+   grab lock L1 (owned by C)
+     |
+A ---+
+        C preempted by B
+          |
+C    +----+
+
+B         +-------->
+                B now keeps A from running.
+
+
+Priority Inheritance (PI)
+-------------------------
+
+There are several ways to solve this issue, but other ways are out of scope
+for this document.  Here we only discuss PI.
+
+PI is where a process inherits the priority of another process if the other
+process blocks on a lock owned by the current process.  To make this easier
+to understand, let's use the previous example, with processes A, B, and C again.
+
+This time, when A blocks on the lock owned by C, C would inherit the priority
+of A.  So now if B becomes runnable, it would not preempt C, since C now has
+the high priority of A.  As soon as C releases the lock, it loses its
+inherited priority, and A then can continue with the resource that C had.
+
+Terminology
+-----------
+
+Here I explain some terminology that is used in this document to help describe
+the design that is used to implement PI.
+
+PI chain - The PI chain is an ordered series of locks and processes that cause
+           processes to inherit priorities from a previous process that is
+           blocked on one of its locks.  This is described in more detail
+           later in this document.
+
+mutex    - In this document, to differentiate from locks that implement
+           PI and spin locks that are used in the PI code, from now on
+           the PI locks will be called a mutex.
+
+lock     - In this document from now on, I will use the term lock when
+           referring to spin locks that are used to protect parts of the PI
+           algorithm.  These locks disable preemption for UP (when
+           CONFIG_PREEMPT is enabled) and on SMP prevents multiple CPUs from
+           entering critical sections simultaneously.
+
+spin lock - Same as lock above.
+
+waiter   - A waiter is a struct that is stored on the stack of a blocked
+           process.  Since the scope of the waiter is within the code for
+           a process being blocked on the mutex, it is fine to allocate
+           the waiter on the process's stack (local variable).  This
+           structure holds a pointer to the task, as well as the mutex that
+           the task is blocked on.  It also has the plist node structures to
+           place the task in the waiter_list of a mutex as well as the
+           pi_list of a mutex owner task (described below).
+
+           waiter is sometimes used in reference to the task that is waiting
+           on a mutex. This is the same as waiter->task.
+
+waiters  - A list of processes that are blocked on a mutex.
+
+top waiter - The highest priority process waiting on a specific mutex.
+
+top pi waiter - The highest priority process waiting on one of the mutexes
+                that a specific process owns.
+
+Note:  task and process are used interchangeably in this document, mostly to
+       differentiate between two processes that are being described together.
+
+
+PI chain
+--------
+
+The PI chain is a list of processes and mutexes that may cause priority
+inheritance to take place.  Multiple chains may converge, but a chain
+would never diverge, since a process can't be blocked on more than one
+mutex at a time.
+
+Example:
+
+   Process:  A, B, C, D, E
+   Mutexes:  L1, L2, L3, L4
+
+   A owns: L1
+           B blocked on L1
+           B owns L2
+                  C blocked on L2
+                  C owns L3
+                         D blocked on L3
+                         D owns L4
+                                E blocked on L4
+
+The chain would be:
+
+   E->L4->D->L3->C->L2->B->L1->A
+
+To show where two chains merge, we could add another process F and
+another mutex L5 where B owns L5 and F is blocked on mutex L5.
+
+The chain for F would be:
+
+   F->L5->B->L1->A
+
+Since a process may own more than one mutex, but never be blocked on more than
+one, the chains merge.
+
+Here we show both chains:
+
+   E->L4->D->L3->C->L2-+
+                       |
+                       +->B->L1->A
+                       |
+                 F->L5-+
+
+For PI to work, the processes at the right end of these chains (or we may
+also call it the Top of the chain) must be equal to or higher in priority
+than the processes to the left or below in the chain.
+
+Also since a mutex may have more than one process blocked on it, we can
+have multiple chains merge at mutexes.  If we add another process G that is
+blocked on mutex L2:
+
+  G->L2->B->L1->A
+
+And once again, to show how this can grow I will show the merging chains
+again.
+
+   E->L4->D->L3->C-+
+                   +->L2-+
+                   |     |
+                 G-+     +->B->L1->A
+                         |
+                   F->L5-+
+
+
+Plist
+-----
+
+Before I go further and talk about how the PI chain is stored through lists
+on both mutexes and processes, I'll explain the plist.  This is similar to
+the struct list_head functionality that is already in the kernel.
+The implementation of plist is out of scope for this document, but it is
+very important to understand what it does.
+
+There are a few differences between plist and list, the most important one
+being that plist is a priority sorted linked list.  This means that the
+priorities of the plist are sorted, such that it takes O(1) to retrieve the
+highest priority item in the list.  Obviously this is useful to store processes
+based on their priorities.
+
+Another difference, which is important for implementation, is that, unlike
+list, the head of the list is a different element than the nodes of a list.
+So the head of the list is declared as struct plist_head and nodes that will
+be added to the list are declared as struct plist_node.
+
+
+Mutex Waiter List
+-----------------
+
+Every mutex keeps track of all the waiters that are blocked on itself. The mutex
+has a plist to store these waiters by priority.  This list is protected by
+a spin lock that is located in the struct of the mutex. This lock is called
+wait_lock.  Since the modification of the waiter list is never done in
+interrupt context, the wait_lock can be taken without disabling interrupts.
+
+
+Task PI List
+------------
+
+To keep track of the PI chains, each process has its own PI list.  This is
+a list of all top waiters of the mutexes that are owned by the process.
+Note that this list only holds the top waiters and not all waiters that are
+blocked on mutexes owned by the process.
+
+The top of the task's PI list is always the highest priority task that
+is waiting on a mutex that is owned by the task.  So if the task has
+inherited a priority, it will always be the priority of the task that is
+at the top of this list.
+
+This list is stored in the task structure of a process as a plist called
+pi_list.  This list is protected by a spin lock also in the task structure,
+called pi_lock.  This lock may also be taken in interrupt context, so when
+locking the pi_lock, interrupts must be disabled.
+
+
+Depth of the PI Chain
+---------------------
+
+The maximum depth of the PI chain is not dynamic, and could actually be
+defined.  But is very complex to figure it out, since it depends on all
+the nesting of mutexes.  Let's look at the example where we have 3 mutexes,
+L1, L2, and L3, and four separate functions func1, func2, func3 and func4.
+The following shows a locking order of L1->L2->L3, but may not actually
+be directly nested that way.
+
+void func1(void)
+{
+	mutex_lock(L1);
+
+	/* do anything */
+
+	mutex_unlock(L1);
+}
+
+void func2(void)
+{
+	mutex_lock(L1);
+	mutex_lock(L2);
+
+	/* do something */
+
+	mutex_unlock(L2);
+	mutex_unlock(L1);
+}
+
+void func3(void)
+{
+	mutex_lock(L2);
+	mutex_lock(L3);
+
+	/* do something else */
+
+	mutex_unlock(L3);
+	mutex_unlock(L2);
+}
+
+void func4(void)
+{
+	mutex_lock(L3);
+
+	/* do something again */
+
+	mutex_unlock(L3);
+}
+
+Now we add 4 processes that run each of these functions separately.
+Processes A, B, C, and D which run functions func1, func2, func3 and func4
+respectively, and such that D runs first and A last.  With D being preempted
+in func4 in the "do something again" area, we have a locking that follows:
+
+D owns L3
+       C blocked on L3
+       C owns L2
+              B blocked on L2
+              B owns L1
+                     A blocked on L1
+
+And thus we have the chain A->L1->B->L2->C->L3->D.
+
+This gives us a PI depth of 4 (four processes), but looking at any of the
+functions individually, it seems as though they only have at most a locking
+depth of two.  So, although the locking depth is defined at compile time,
+it still is very difficult to find the possibilities of that depth.
+
+Now since mutexes can be defined by user-land applications, we don't want a DOS
+type of application that nests large amounts of mutexes to create a large
+PI chain, and have the code holding spin locks while looking at a large
+amount of data.  So to prevent this, the implementation not only implements
+a maximum lock depth, but also only holds at most two different locks at a
+time, as it walks the PI chain.  More about this below.
+
+
+Mutex owner and flags
+---------------------
+
+The mutex structure contains a pointer to the owner of the mutex.  If the
+mutex is not owned, this owner is set to NULL.  Since all architectures
+have the task structure on at least a four byte alignment (and if this is
+not true, the rtmutex.c code will be broken!), this allows for the two
+least significant bits to be used as flags.  This part is also described
+in Documentation/rt-mutex.txt, but will also be briefly described here.
+
+Bit 0 is used as the "Pending Owner" flag.  This is described later.
+Bit 1 is used as the "Has Waiters" flags.  This is also described later
+  in more detail, but is set whenever there are waiters on a mutex.
+
+
+cmpxchg Tricks
+--------------
+
+Some architectures implement an atomic cmpxchg (Compare and Exchange).  This
+is used (when applicable) to keep the fast path of grabbing and releasing
+mutexes short.
+
+cmpxchg is basically the following function performed atomically:
+
+unsigned long _cmpxchg(unsigned long *A, unsigned long *B, unsigned long *C)
+{
+	unsigned long T = *A;
+	if (*A == *B) {
+		*A = *C;
+	}
+	return T;
+}
+#define cmpxchg(a,b,c) _cmpxchg(&a,&b,&c)
+
+This is really nice to have, since it allows you to only update a variable
+if the variable is what you expect it to be.  You know if it succeeded if
+the return value (the old value of A) is equal to B.
+
+The macro rt_mutex_cmpxchg is used to try to lock and unlock mutexes. If
+the architecture does not support CMPXCHG, then this macro is simply set
+to fail every time.  But if CMPXCHG is supported, then this will
+help out extremely to keep the fast path short.
+
+The use of rt_mutex_cmpxchg with the flags in the owner field help optimize
+the system for architectures that support it.  This will also be explained
+later in this document.
+
+
+Priority adjustments
+--------------------
+
+The implementation of the PI code in rtmutex.c has several places that a
+process must adjust its priority.  With the help of the pi_list of a
+process this is rather easy to know what needs to be adjusted.
+
+The functions implementing the task adjustments are rt_mutex_adjust_prio,
+__rt_mutex_adjust_prio (same as the former, but expects the task pi_lock
+to already be taken), rt_mutex_getprio, and rt_mutex_setprio.
+
+rt_mutex_getprio and rt_mutex_setprio are only used in __rt_mutex_adjust_prio.
+
+rt_mutex_getprio returns the priority that the task should have.  Either the
+task's own normal priority, or if a process of a higher priority is waiting on
+a mutex owned by the task, then that higher priority should be returned.
+Since the pi_list of a task holds an order by priority list of all the top
+waiters of all the mutexes that the task owns, rt_mutex_getprio simply needs
+to compare the top pi waiter to its own normal priority, and return the higher
+priority back.
+
+(Note:  if looking at the code, you will notice that the lower number of
+        prio is returned.  This is because the prio field in the task structure
+        is an inverse order of the actual priority.  So a "prio" of 5 is
+        of higher priority than a "prio" of 10.)
+
+__rt_mutex_adjust_prio examines the result of rt_mutex_getprio, and if the
+result does not equal the task's current priority, then rt_mutex_setprio
+is called to adjust the priority of the task to the new priority.
+Note that rt_mutex_setprio is defined in kernel/sched/core.c to implement the
+actual change in priority.
+
+It is interesting to note that __rt_mutex_adjust_prio can either increase
+or decrease the priority of the task.  In the case that a higher priority
+process has just blocked on a mutex owned by the task, __rt_mutex_adjust_prio
+would increase/boost the task's priority.  But if a higher priority task
+were for some reason to leave the mutex (timeout or signal), this same function
+would decrease/unboost the priority of the task.  That is because the pi_list
+always contains the highest priority task that is waiting on a mutex owned
+by the task, so we only need to compare the priority of that top pi waiter
+to the normal priority of the given task.
+
+
+High level overview of the PI chain walk
+----------------------------------------
+
+The PI chain walk is implemented by the function rt_mutex_adjust_prio_chain.
+
+The implementation has gone through several iterations, and has ended up
+with what we believe is the best.  It walks the PI chain by only grabbing
+at most two locks at a time, and is very efficient.
+
+The rt_mutex_adjust_prio_chain can be used either to boost or lower process
+priorities.
+
+rt_mutex_adjust_prio_chain is called with a task to be checked for PI
+(de)boosting (the owner of a mutex that a process is blocking on), a flag to
+check for deadlocking, the mutex that the task owns, and a pointer to a waiter
+that is the process's waiter struct that is blocked on the mutex (although this
+parameter may be NULL for deboosting).
+
+For this explanation, I will not mention deadlock detection. This explanation
+will try to stay at a high level.
+
+When this function is called, there are no locks held.  That also means
+that the state of the owner and lock can change when entered into this function.
+
+Before this function is called, the task has already had rt_mutex_adjust_prio
+performed on it.  This means that the task is set to the priority that it
+should be at, but the plist nodes of the task's waiter have not been updated
+with the new priorities, and that this task may not be in the proper locations
+in the pi_lists and wait_lists that the task is blocked on.  This function
+solves all that.
+
+A loop is entered, where task is the owner to be checked for PI changes that
+was passed by parameter (for the first iteration).  The pi_lock of this task is
+taken to prevent any more changes to the pi_list of the task.  This also
+prevents new tasks from completing the blocking on a mutex that is owned by this
+task.
+
+If the task is not blocked on a mutex then the loop is exited.  We are at
+the top of the PI chain.
+
+A check is now done to see if the original waiter (the process that is blocked
+on the current mutex) is the top pi waiter of the task.  That is, is this
+waiter on the top of the task's pi_list.  If it is not, it either means that
+there is another process higher in priority that is blocked on one of the
+mutexes that the task owns, or that the waiter has just woken up via a signal
+or timeout and has left the PI chain.  In either case, the loop is exited, since
+we don't need to do any more changes to the priority of the current task, or any
+task that owns a mutex that this current task is waiting on.  A priority chain
+walk is only needed when a new top pi waiter is made to a task.
+
+The next check sees if the task's waiter plist node has the priority equal to
+the priority the task is set at.  If they are equal, then we are done with
+the loop.  Remember that the function started with the priority of the
+task adjusted, but the plist nodes that hold the task in other processes
+pi_lists have not been adjusted.
+
+Next, we look at the mutex that the task is blocked on. The mutex's wait_lock
+is taken.  This is done by a spin_trylock, because the locking order of the
+pi_lock and wait_lock goes in the opposite direction. If we fail to grab the
+lock, the pi_lock is released, and we restart the loop.
+
+Now that we have both the pi_lock of the task as well as the wait_lock of
+the mutex the task is blocked on, we update the task's waiter's plist node
+that is located on the mutex's wait_list.
+
+Now we release the pi_lock of the task.
+
+Next the owner of the mutex has its pi_lock taken, so we can update the
+task's entry in the owner's pi_list.  If the task is the highest priority
+process on the mutex's wait_list, then we remove the previous top waiter
+from the owner's pi_list, and replace it with the task.
+
+Note: It is possible that the task was the current top waiter on the mutex,
+      in which case the task is not yet on the pi_list of the waiter.  This
+      is OK, since plist_del does nothing if the plist node is not on any
+      list.
+
+If the task was not the top waiter of the mutex, but it was before we
+did the priority updates, that means we are deboosting/lowering the
+task.  In this case, the task is removed from the pi_list of the owner,
+and the new top waiter is added.
+
+Lastly, we unlock both the pi_lock of the task, as well as the mutex's
+wait_lock, and continue the loop again.  On the next iteration of the
+loop, the previous owner of the mutex will be the task that will be
+processed.
+
+Note: One might think that the owner of this mutex might have changed
+      since we just grab the mutex's wait_lock. And one could be right.
+      The important thing to remember is that the owner could not have
+      become the task that is being processed in the PI chain, since
+      we have taken that task's pi_lock at the beginning of the loop.
+      So as long as there is an owner of this mutex that is not the same
+      process as the tasked being worked on, we are OK.
+
+      Looking closely at the code, one might be confused.  The check for the
+      end of the PI chain is when the task isn't blocked on anything or the
+      task's waiter structure "task" element is NULL.  This check is
+      protected only by the task's pi_lock.  But the code to unlock the mutex
+      sets the task's waiter structure "task" element to NULL with only
+      the protection of the mutex's wait_lock, which was not taken yet.
+      Isn't this a race condition if the task becomes the new owner?
+
+      The answer is No!  The trick is the spin_trylock of the mutex's
+      wait_lock.  If we fail that lock, we release the pi_lock of the
+      task and continue the loop, doing the end of PI chain check again.
+
+      In the code to release the lock, the wait_lock of the mutex is held
+      the entire time, and it is not let go when we grab the pi_lock of the
+      new owner of the mutex.  So if the switch of a new owner were to happen
+      after the check for end of the PI chain and the grabbing of the
+      wait_lock, the unlocking code would spin on the new owner's pi_lock
+      but never give up the wait_lock.  So the PI chain loop is guaranteed to
+      fail the spin_trylock on the wait_lock, release the pi_lock, and
+      try again.
+
+      If you don't quite understand the above, that's OK. You don't have to,
+      unless you really want to make a proof out of it ;)
+
+
+Pending Owners and Lock stealing
+--------------------------------
+
+One of the flags in the owner field of the mutex structure is "Pending Owner".
+What this means is that an owner was chosen by the process releasing the
+mutex, but that owner has yet to wake up and actually take the mutex.
+
+Why is this important?  Why can't we just give the mutex to another process
+and be done with it?
+
+The PI code is to help with real-time processes, and to let the highest
+priority process run as long as possible with little latencies and delays.
+If a high priority process owns a mutex that a lower priority process is
+blocked on, when the mutex is released it would be given to the lower priority
+process.  What if the higher priority process wants to take that mutex again.
+The high priority process would fail to take that mutex that it just gave up
+and it would need to boost the lower priority process to run with full
+latency of that critical section (since the low priority process just entered
+it).
+
+There's no reason a high priority process that gives up a mutex should be
+penalized if it tries to take that mutex again.  If the new owner of the
+mutex has not woken up yet, there's no reason that the higher priority process
+could not take that mutex away.
+
+To solve this, we introduced Pending Ownership and Lock Stealing.  When a
+new process is given a mutex that it was blocked on, it is only given
+pending ownership.  This means that it's the new owner, unless a higher
+priority process comes in and tries to grab that mutex.  If a higher priority
+process does come along and wants that mutex, we let the higher priority
+process "steal" the mutex from the pending owner (only if it is still pending)
+and continue with the mutex.
+
+
+Taking of a mutex (The walk through)
+------------------------------------
+
+OK, now let's take a look at the detailed walk through of what happens when
+taking a mutex.
+
+The first thing that is tried is the fast taking of the mutex.  This is
+done when we have CMPXCHG enabled (otherwise the fast taking automatically
+fails).  Only when the owner field of the mutex is NULL can the lock be
+taken with the CMPXCHG and nothing else needs to be done.
+
+If there is contention on the lock, whether it is owned or pending owner
+we go about the slow path (rt_mutex_slowlock).
+
+The slow path function is where the task's waiter structure is created on
+the stack.  This is because the waiter structure is only needed for the
+scope of this function.  The waiter structure holds the nodes to store
+the task on the wait_list of the mutex, and if need be, the pi_list of
+the owner.
+
+The wait_lock of the mutex is taken since the slow path of unlocking the
+mutex also takes this lock.
+
+We then call try_to_take_rt_mutex.  This is where the architecture that
+does not implement CMPXCHG would always grab the lock (if there's no
+contention).
+
+try_to_take_rt_mutex is used every time the task tries to grab a mutex in the
+slow path.  The first thing that is done here is an atomic setting of
+the "Has Waiters" flag of the mutex's owner field.  Yes, this could really
+be false, because if the mutex has no owner, there are no waiters and
+the current task also won't have any waiters.  But we don't have the lock
+yet, so we assume we are going to be a waiter.  The reason for this is to
+play nice for those architectures that do have CMPXCHG.  By setting this flag
+now, the owner of the mutex can't release the mutex without going into the
+slow unlock path, and it would then need to grab the wait_lock, which this
+code currently holds.  So setting the "Has Waiters" flag forces the owner
+to synchronize with this code.
+
+Now that we know that we can't have any races with the owner releasing the
+mutex, we check to see if we can take the ownership.  This is done if the
+mutex doesn't have a owner, or if we can steal the mutex from a pending
+owner.  Let's look at the situations we have here.
+
+  1) Has owner that is pending
+  ----------------------------
+
+  The mutex has a owner, but it hasn't woken up and the mutex flag
+  "Pending Owner" is set.  The first check is to see if the owner isn't the
+  current task.  This is because this function is also used for the pending
+  owner to grab the mutex.  When a pending owner wakes up, it checks to see
+  if it can take the mutex, and this is done if the owner is already set to
+  itself.  If so, we succeed and leave the function, clearing the "Pending
+  Owner" bit.
+
+  If the pending owner is not current, we check to see if the current priority is
+  higher than the pending owner.  If not, we fail the function and return.
+
+  There's also something special about a pending owner.  That is a pending owner
+  is never blocked on a mutex.  So there is no PI chain to worry about.  It also
+  means that if the mutex doesn't have any waiters, there's no accounting needed
+  to update the pending owner's pi_list, since we only worry about processes
+  blocked on the current mutex.
+
+  If there are waiters on this mutex, and we just stole the ownership, we need
+  to take the top waiter, remove it from the pi_list of the pending owner, and
+  add it to the current pi_list.  Note that at this moment, the pending owner
+  is no longer on the list of waiters.  This is fine, since the pending owner
+  would add itself back when it realizes that it had the ownership stolen
+  from itself.  When the pending owner tries to grab the mutex, it will fail
+  in try_to_take_rt_mutex if the owner field points to another process.
+
+  2) No owner
+  -----------
+
+  If there is no owner (or we successfully stole the lock), we set the owner
+  of the mutex to current, and set the flag of "Has Waiters" if the current
+  mutex actually has waiters, or we clear the flag if it doesn't.  See, it was
+  OK that we set that flag early, since now it is cleared.
+
+  3) Failed to grab ownership
+  ---------------------------
+
+  The most interesting case is when we fail to take ownership. This means that
+  there exists an owner, or there's a pending owner with equal or higher
+  priority than the current task.
+
+We'll continue on the failed case.
+
+If the mutex has a timeout, we set up a timer to go off to break us out
+of this mutex if we failed to get it after a specified amount of time.
+
+Now we enter a loop that will continue to try to take ownership of the mutex, or
+fail from a timeout or signal.
+
+Once again we try to take the mutex.  This will usually fail the first time
+in the loop, since it had just failed to get the mutex.  But the second time
+in the loop, this would likely succeed, since the task would likely be
+the pending owner.
+
+If the mutex is TASK_INTERRUPTIBLE a check for signals and timeout is done
+here.
+
+The waiter structure has a "task" field that points to the task that is blocked
+on the mutex.  This field can be NULL the first time it goes through the loop
+or if the task is a pending owner and had its mutex stolen.  If the "task"
+field is NULL then we need to set up the accounting for it.
+
+Task blocks on mutex
+--------------------
+
+The accounting of a mutex and process is done with the waiter structure of
+the process.  The "task" field is set to the process, and the "lock" field
+to the mutex.  The plist nodes are initialized to the processes current
+priority.
+
+Since the wait_lock was taken at the entry of the slow lock, we can safely
+add the waiter to the wait_list.  If the current process is the highest
+priority process currently waiting on this mutex, then we remove the
+previous top waiter process (if it exists) from the pi_list of the owner,
+and add the current process to that list.  Since the pi_list of the owner
+has changed, we call rt_mutex_adjust_prio on the owner to see if the owner
+should adjust its priority accordingly.
+
+If the owner is also blocked on a lock, and had its pi_list changed
+(or deadlock checking is on), we unlock the wait_lock of the mutex and go ahead
+and run rt_mutex_adjust_prio_chain on the owner, as described earlier.
+
+Now all locks are released, and if the current process is still blocked on a
+mutex (waiter "task" field is not NULL), then we go to sleep (call schedule).
+
+Waking up in the loop
+---------------------
+
+The schedule can then wake up for a few reasons.
+  1) we were given pending ownership of the mutex.
+  2) we received a signal and was TASK_INTERRUPTIBLE
+  3) we had a timeout and was TASK_INTERRUPTIBLE
+
+In any of these cases, we continue the loop and once again try to grab the
+ownership of the mutex.  If we succeed, we exit the loop, otherwise we continue
+and on signal and timeout, will exit the loop, or if we had the mutex stolen
+we just simply add ourselves back on the lists and go back to sleep.
+
+Note: For various reasons, because of timeout and signals, the steal mutex
+      algorithm needs to be careful. This is because the current process is
+      still on the wait_list. And because of dynamic changing of priorities,
+      especially on SCHED_OTHER tasks, the current process can be the
+      highest priority task on the wait_list.
+
+Failed to get mutex on Timeout or Signal
+----------------------------------------
+
+If a timeout or signal occurred, the waiter's "task" field would not be
+NULL and the task needs to be taken off the wait_list of the mutex and perhaps
+pi_list of the owner.  If this process was a high priority process, then
+the rt_mutex_adjust_prio_chain needs to be executed again on the owner,
+but this time it will be lowering the priorities.
+
+
+Unlocking the Mutex
+-------------------
+
+The unlocking of a mutex also has a fast path for those architectures with
+CMPXCHG.  Since the taking of a mutex on contention always sets the
+"Has Waiters" flag of the mutex's owner, we use this to know if we need to
+take the slow path when unlocking the mutex.  If the mutex doesn't have any
+waiters, the owner field of the mutex would equal the current process and
+the mutex can be unlocked by just replacing the owner field with NULL.
+
+If the owner field has the "Has Waiters" bit set (or CMPXCHG is not available),
+the slow unlock path is taken.
+
+The first thing done in the slow unlock path is to take the wait_lock of the
+mutex.  This synchronizes the locking and unlocking of the mutex.
+
+A check is made to see if the mutex has waiters or not.  On architectures that
+do not have CMPXCHG, this is the location that the owner of the mutex will
+determine if a waiter needs to be awoken or not.  On architectures that
+do have CMPXCHG, that check is done in the fast path, but it is still needed
+in the slow path too.  If a waiter of a mutex woke up because of a signal
+or timeout between the time the owner failed the fast path CMPXCHG check and
+the grabbing of the wait_lock, the mutex may not have any waiters, thus the
+owner still needs to make this check. If there are no waiters then the mutex
+owner field is set to NULL, the wait_lock is released and nothing more is
+needed.
+
+If there are waiters, then we need to wake one up and give that waiter
+pending ownership.
+
+On the wake up code, the pi_lock of the current owner is taken.  The top
+waiter of the lock is found and removed from the wait_list of the mutex
+as well as the pi_list of the current owner.  The task field of the new
+pending owner's waiter structure is set to NULL, and the owner field of the
+mutex is set to the new owner with the "Pending Owner" bit set, as well
+as the "Has Waiters" bit if there still are other processes blocked on the
+mutex.
+
+The pi_lock of the previous owner is released, and the new pending owner's
+pi_lock is taken.  Remember that this is the trick to prevent the race
+condition in rt_mutex_adjust_prio_chain from adding itself as a waiter
+on the mutex.
+
+We now clear the "pi_blocked_on" field of the new pending owner, and if
+the mutex still has waiters pending, we add the new top waiter to the pi_list
+of the pending owner.
+
+Finally we unlock the pi_lock of the pending owner and wake it up.
+
+
+Contact
+-------
+
+For updates on this document, please email Steven Rostedt <rostedt@goodmis.org>
+
+
+Credits
+-------
+
+Author:  Steven Rostedt <rostedt@goodmis.org>
+
+Reviewers:  Ingo Molnar, Thomas Gleixner, Thomas Duetsch, and Randy Dunlap
+
+Updates
+-------
+
+This document was originally written for 2.6.17-rc3-mm1
diff --git a/Documentation/locking/rt-mutex.txt b/Documentation/locking/rt-mutex.txt
new file mode 100644
index 000000000000..243393d882ee
--- /dev/null
+++ b/Documentation/locking/rt-mutex.txt
@@ -0,0 +1,79 @@
+RT-mutex subsystem with PI support
+----------------------------------
+
+RT-mutexes with priority inheritance are used to support PI-futexes,
+which enable pthread_mutex_t priority inheritance attributes
+(PTHREAD_PRIO_INHERIT). [See Documentation/pi-futex.txt for more details
+about PI-futexes.]
+
+This technology was developed in the -rt tree and streamlined for
+pthread_mutex support.
+
+Basic principles:
+-----------------
+
+RT-mutexes extend the semantics of simple mutexes by the priority
+inheritance protocol.
+
+A low priority owner of a rt-mutex inherits the priority of a higher
+priority waiter until the rt-mutex is released. If the temporarily
+boosted owner blocks on a rt-mutex itself it propagates the priority
+boosting to the owner of the other rt_mutex it gets blocked on. The
+priority boosting is immediately removed once the rt_mutex has been
+unlocked.
+
+This approach allows us to shorten the block of high-prio tasks on
+mutexes which protect shared resources. Priority inheritance is not a
+magic bullet for poorly designed applications, but it allows
+well-designed applications to use userspace locks in critical parts of
+an high priority thread, without losing determinism.
+
+The enqueueing of the waiters into the rtmutex waiter list is done in
+priority order. For same priorities FIFO order is chosen. For each
+rtmutex, only the top priority waiter is enqueued into the owner's
+priority waiters list. This list too queues in priority order. Whenever
+the top priority waiter of a task changes (for example it timed out or
+got a signal), the priority of the owner task is readjusted. [The
+priority enqueueing is handled by "plists", see include/linux/plist.h
+for more details.]
+
+RT-mutexes are optimized for fastpath operations and have no internal
+locking overhead when locking an uncontended mutex or unlocking a mutex
+without waiters. The optimized fastpath operations require cmpxchg
+support. [If that is not available then the rt-mutex internal spinlock
+is used]
+
+The state of the rt-mutex is tracked via the owner field of the rt-mutex
+structure:
+
+rt_mutex->owner holds the task_struct pointer of the owner. Bit 0 and 1
+are used to keep track of the "owner is pending" and "rtmutex has
+waiters" state.
+
+ owner		bit1	bit0
+ NULL		0	0	mutex is free (fast acquire possible)
+ NULL		0	1	invalid state
+ NULL		1	0	Transitional state*
+ NULL		1	1	invalid state
+ taskpointer	0	0	mutex is held (fast release possible)
+ taskpointer	0	1	task is pending owner
+ taskpointer	1	0	mutex is held and has waiters
+ taskpointer	1	1	task is pending owner and mutex has waiters
+
+Pending-ownership handling is a performance optimization:
+pending-ownership is assigned to the first (highest priority) waiter of
+the mutex, when the mutex is released. The thread is woken up and once
+it starts executing it can acquire the mutex. Until the mutex is taken
+by it (bit 0 is cleared) a competing higher priority thread can "steal"
+the mutex which puts the woken up thread back on the waiters list.
+
+The pending-ownership optimization is especially important for the
+uninterrupted workflow of high-prio tasks which repeatedly
+takes/releases locks that have lower-prio waiters. Without this
+optimization the higher-prio thread would ping-pong to the lower-prio
+task [because at unlock time we always assign a new owner].
+
+(*) The "mutex has waiters" bit gets set to take the lock. If the lock
+doesn't already have an owner, this bit is quickly cleared if there are
+no waiters.  So this is a transitional state to synchronize with looking
+at the owner field of the mutex and the mutex owner releasing the lock.
diff --git a/Documentation/locking/spinlocks.txt b/Documentation/locking/spinlocks.txt
new file mode 100644
index 000000000000..ff35e40bdf5b
--- /dev/null
+++ b/Documentation/locking/spinlocks.txt
@@ -0,0 +1,167 @@
+Lesson 1: Spin locks
+
+The most basic primitive for locking is spinlock.
+
+static DEFINE_SPINLOCK(xxx_lock);
+
+	unsigned long flags;
+
+	spin_lock_irqsave(&xxx_lock, flags);
+	... critical section here ..
+	spin_unlock_irqrestore(&xxx_lock, flags);
+
+The above is always safe. It will disable interrupts _locally_, but the
+spinlock itself will guarantee the global lock, so it will guarantee that
+there is only one thread-of-control within the region(s) protected by that
+lock. This works well even under UP also, so the code does _not_ need to
+worry about UP vs SMP issues: the spinlocks work correctly under both.
+
+   NOTE! Implications of spin_locks for memory are further described in:
+
+     Documentation/memory-barriers.txt
+       (5) LOCK operations.
+       (6) UNLOCK operations.
+
+The above is usually pretty simple (you usually need and want only one
+spinlock for most things - using more than one spinlock can make things a
+lot more complex and even slower and is usually worth it only for
+sequences that you _know_ need to be split up: avoid it at all cost if you
+aren't sure).
+
+This is really the only really hard part about spinlocks: once you start
+using spinlocks they tend to expand to areas you might not have noticed
+before, because you have to make sure the spinlocks correctly protect the
+shared data structures _everywhere_ they are used. The spinlocks are most
+easily added to places that are completely independent of other code (for
+example, internal driver data structures that nobody else ever touches).
+
+   NOTE! The spin-lock is safe only when you _also_ use the lock itself
+   to do locking across CPU's, which implies that EVERYTHING that
+   touches a shared variable has to agree about the spinlock they want
+   to use.
+
+----
+
+Lesson 2: reader-writer spinlocks.
+
+If your data accesses have a very natural pattern where you usually tend
+to mostly read from the shared variables, the reader-writer locks
+(rw_lock) versions of the spinlocks are sometimes useful. They allow multiple
+readers to be in the same critical region at once, but if somebody wants
+to change the variables it has to get an exclusive write lock.
+
+   NOTE! reader-writer locks require more atomic memory operations than
+   simple spinlocks.  Unless the reader critical section is long, you
+   are better off just using spinlocks.
+
+The routines look the same as above:
+
+   rwlock_t xxx_lock = __RW_LOCK_UNLOCKED(xxx_lock);
+
+	unsigned long flags;
+
+	read_lock_irqsave(&xxx_lock, flags);
+	.. critical section that only reads the info ...
+	read_unlock_irqrestore(&xxx_lock, flags);
+
+	write_lock_irqsave(&xxx_lock, flags);
+	.. read and write exclusive access to the info ...
+	write_unlock_irqrestore(&xxx_lock, flags);
+
+The above kind of lock may be useful for complex data structures like
+linked lists, especially searching for entries without changing the list
+itself.  The read lock allows many concurrent readers.  Anything that
+_changes_ the list will have to get the write lock.
+
+   NOTE! RCU is better for list traversal, but requires careful
+   attention to design detail (see Documentation/RCU/listRCU.txt).
+
+Also, you cannot "upgrade" a read-lock to a write-lock, so if you at _any_
+time need to do any changes (even if you don't do it every time), you have
+to get the write-lock at the very beginning.
+
+   NOTE! We are working hard to remove reader-writer spinlocks in most
+   cases, so please don't add a new one without consensus.  (Instead, see
+   Documentation/RCU/rcu.txt for complete information.)
+
+----
+
+Lesson 3: spinlocks revisited.
+
+The single spin-lock primitives above are by no means the only ones. They
+are the most safe ones, and the ones that work under all circumstances,
+but partly _because_ they are safe they are also fairly slow. They are slower
+than they'd need to be, because they do have to disable interrupts
+(which is just a single instruction on a x86, but it's an expensive one -
+and on other architectures it can be worse).
+
+If you have a case where you have to protect a data structure across
+several CPU's and you want to use spinlocks you can potentially use
+cheaper versions of the spinlocks. IFF you know that the spinlocks are
+never used in interrupt handlers, you can use the non-irq versions:
+
+	spin_lock(&lock);
+	...
+	spin_unlock(&lock);
+
+(and the equivalent read-write versions too, of course). The spinlock will
+guarantee the same kind of exclusive access, and it will be much faster.
+This is useful if you know that the data in question is only ever
+manipulated from a "process context", ie no interrupts involved.
+
+The reasons you mustn't use these versions if you have interrupts that
+play with the spinlock is that you can get deadlocks:
+
+	spin_lock(&lock);
+	...
+		<- interrupt comes in:
+			spin_lock(&lock);
+
+where an interrupt tries to lock an already locked variable. This is ok if
+the other interrupt happens on another CPU, but it is _not_ ok if the
+interrupt happens on the same CPU that already holds the lock, because the
+lock will obviously never be released (because the interrupt is waiting
+for the lock, and the lock-holder is interrupted by the interrupt and will
+not continue until the interrupt has been processed).
+
+(This is also the reason why the irq-versions of the spinlocks only need
+to disable the _local_ interrupts - it's ok to use spinlocks in interrupts
+on other CPU's, because an interrupt on another CPU doesn't interrupt the
+CPU that holds the lock, so the lock-holder can continue and eventually
+releases the lock).
+
+Note that you can be clever with read-write locks and interrupts. For
+example, if you know that the interrupt only ever gets a read-lock, then
+you can use a non-irq version of read locks everywhere - because they
+don't block on each other (and thus there is no dead-lock wrt interrupts.
+But when you do the write-lock, you have to use the irq-safe version.
+
+For an example of being clever with rw-locks, see the "waitqueue_lock"
+handling in kernel/sched/core.c - nothing ever _changes_ a wait-queue from
+within an interrupt, they only read the queue in order to know whom to
+wake up. So read-locks are safe (which is good: they are very common
+indeed), while write-locks need to protect themselves against interrupts.
+
+		Linus
+
+----
+
+Reference information:
+
+For dynamic initialization, use spin_lock_init() or rwlock_init() as
+appropriate:
+
+   spinlock_t xxx_lock;
+   rwlock_t xxx_rw_lock;
+
+   static int __init xxx_init(void)
+   {
+	spin_lock_init(&xxx_lock);
+	rwlock_init(&xxx_rw_lock);
+	...
+   }
+
+   module_init(xxx_init);
+
+For static initialization, use DEFINE_SPINLOCK() / DEFINE_RWLOCK() or
+__SPIN_LOCK_UNLOCKED() / __RW_LOCK_UNLOCKED() as appropriate.
diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt
new file mode 100644
index 000000000000..8a112dc304c3
--- /dev/null
+++ b/Documentation/locking/ww-mutex-design.txt
@@ -0,0 +1,344 @@
+Wait/Wound Deadlock-Proof Mutex Design
+======================================
+
+Please read mutex-design.txt first, as it applies to wait/wound mutexes too.
+
+Motivation for WW-Mutexes
+-------------------------
+
+GPU's do operations that commonly involve many buffers.  Those buffers
+can be shared across contexts/processes, exist in different memory
+domains (for example VRAM vs system memory), and so on.  And with
+PRIME / dmabuf, they can even be shared across devices.  So there are
+a handful of situations where the driver needs to wait for buffers to
+become ready.  If you think about this in terms of waiting on a buffer
+mutex for it to become available, this presents a problem because
+there is no way to guarantee that buffers appear in a execbuf/batch in
+the same order in all contexts.  That is directly under control of
+userspace, and a result of the sequence of GL calls that an application
+makes.	Which results in the potential for deadlock.  The problem gets
+more complex when you consider that the kernel may need to migrate the
+buffer(s) into VRAM before the GPU operates on the buffer(s), which
+may in turn require evicting some other buffers (and you don't want to
+evict other buffers which are already queued up to the GPU), but for a
+simplified understanding of the problem you can ignore this.
+
+The algorithm that the TTM graphics subsystem came up with for dealing with
+this problem is quite simple.  For each group of buffers (execbuf) that need
+to be locked, the caller would be assigned a unique reservation id/ticket,
+from a global counter.  In case of deadlock while locking all the buffers
+associated with a execbuf, the one with the lowest reservation ticket (i.e.
+the oldest task) wins, and the one with the higher reservation id (i.e. the
+younger task) unlocks all of the buffers that it has already locked, and then
+tries again.
+
+In the RDBMS literature this deadlock handling approach is called wait/wound:
+The older tasks waits until it can acquire the contended lock. The younger tasks
+needs to back off and drop all the locks it is currently holding, i.e. the
+younger task is wounded.
+
+Concepts
+--------
+
+Compared to normal mutexes two additional concepts/objects show up in the lock
+interface for w/w mutexes:
+
+Acquire context: To ensure eventual forward progress it is important the a task
+trying to acquire locks doesn't grab a new reservation id, but keeps the one it
+acquired when starting the lock acquisition. This ticket is stored in the
+acquire context. Furthermore the acquire context keeps track of debugging state
+to catch w/w mutex interface abuse.
+
+W/w class: In contrast to normal mutexes the lock class needs to be explicit for
+w/w mutexes, since it is required to initialize the acquire context.
+
+Furthermore there are three different class of w/w lock acquire functions:
+
+* Normal lock acquisition with a context, using ww_mutex_lock.
+
+* Slowpath lock acquisition on the contending lock, used by the wounded task
+  after having dropped all already acquired locks. These functions have the
+  _slow postfix.
+
+  From a simple semantics point-of-view the _slow functions are not strictly
+  required, since simply calling the normal ww_mutex_lock functions on the
+  contending lock (after having dropped all other already acquired locks) will
+  work correctly. After all if no other ww mutex has been acquired yet there's
+  no deadlock potential and hence the ww_mutex_lock call will block and not
+  prematurely return -EDEADLK. The advantage of the _slow functions is in
+  interface safety:
+  - ww_mutex_lock has a __must_check int return type, whereas ww_mutex_lock_slow
+    has a void return type. Note that since ww mutex code needs loops/retries
+    anyway the __must_check doesn't result in spurious warnings, even though the
+    very first lock operation can never fail.
+  - When full debugging is enabled ww_mutex_lock_slow checks that all acquired
+    ww mutex have been released (preventing deadlocks) and makes sure that we
+    block on the contending lock (preventing spinning through the -EDEADLK
+    slowpath until the contended lock can be acquired).
+
+* Functions to only acquire a single w/w mutex, which results in the exact same
+  semantics as a normal mutex. This is done by calling ww_mutex_lock with a NULL
+  context.
+
+  Again this is not strictly required. But often you only want to acquire a
+  single lock in which case it's pointless to set up an acquire context (and so
+  better to avoid grabbing a deadlock avoidance ticket).
+
+Of course, all the usual variants for handling wake-ups due to signals are also
+provided.
+
+Usage
+-----
+
+Three different ways to acquire locks within the same w/w class. Common
+definitions for methods #1 and #2:
+
+static DEFINE_WW_CLASS(ww_class);
+
+struct obj {
+	struct ww_mutex lock;
+	/* obj data */
+};
+
+struct obj_entry {
+	struct list_head head;
+	struct obj *obj;
+};
+
+Method 1, using a list in execbuf->buffers that's not allowed to be reordered.
+This is useful if a list of required objects is already tracked somewhere.
+Furthermore the lock helper can use propagate the -EALREADY return code back to
+the caller as a signal that an object is twice on the list. This is useful if
+the list is constructed from userspace input and the ABI requires userspace to
+not have duplicate entries (e.g. for a gpu commandbuffer submission ioctl).
+
+int lock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
+{
+	struct obj *res_obj = NULL;
+	struct obj_entry *contended_entry = NULL;
+	struct obj_entry *entry;
+
+	ww_acquire_init(ctx, &ww_class);
+
+retry:
+	list_for_each_entry (entry, list, head) {
+		if (entry->obj == res_obj) {
+			res_obj = NULL;
+			continue;
+		}
+		ret = ww_mutex_lock(&entry->obj->lock, ctx);
+		if (ret < 0) {
+			contended_entry = entry;
+			goto err;
+		}
+	}
+
+	ww_acquire_done(ctx);
+	return 0;
+
+err:
+	list_for_each_entry_continue_reverse (entry, list, head)
+		ww_mutex_unlock(&entry->obj->lock);
+
+	if (res_obj)
+		ww_mutex_unlock(&res_obj->lock);
+
+	if (ret == -EDEADLK) {
+		/* we lost out in a seqno race, lock and retry.. */
+		ww_mutex_lock_slow(&contended_entry->obj->lock, ctx);
+		res_obj = contended_entry->obj;
+		goto retry;
+	}
+	ww_acquire_fini(ctx);
+
+	return ret;
+}
+
+Method 2, using a list in execbuf->buffers that can be reordered. Same semantics
+of duplicate entry detection using -EALREADY as method 1 above. But the
+list-reordering allows for a bit more idiomatic code.
+
+int lock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
+{
+	struct obj_entry *entry, *entry2;
+
+	ww_acquire_init(ctx, &ww_class);
+
+	list_for_each_entry (entry, list, head) {
+		ret = ww_mutex_lock(&entry->obj->lock, ctx);
+		if (ret < 0) {
+			entry2 = entry;
+
+			list_for_each_entry_continue_reverse (entry2, list, head)
+				ww_mutex_unlock(&entry2->obj->lock);
+
+			if (ret != -EDEADLK) {
+				ww_acquire_fini(ctx);
+				return ret;
+			}
+
+			/* we lost out in a seqno race, lock and retry.. */
+			ww_mutex_lock_slow(&entry->obj->lock, ctx);
+
+			/*
+			 * Move buf to head of the list, this will point
+			 * buf->next to the first unlocked entry,
+			 * restarting the for loop.
+			 */
+			list_del(&entry->head);
+			list_add(&entry->head, list);
+		}
+	}
+
+	ww_acquire_done(ctx);
+	return 0;
+}
+
+Unlocking works the same way for both methods #1 and #2:
+
+void unlock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
+{
+	struct obj_entry *entry;
+
+	list_for_each_entry (entry, list, head)
+		ww_mutex_unlock(&entry->obj->lock);
+
+	ww_acquire_fini(ctx);
+}
+
+Method 3 is useful if the list of objects is constructed ad-hoc and not upfront,
+e.g. when adjusting edges in a graph where each node has its own ww_mutex lock,
+and edges can only be changed when holding the locks of all involved nodes. w/w
+mutexes are a natural fit for such a case for two reasons:
+- They can handle lock-acquisition in any order which allows us to start walking
+  a graph from a starting point and then iteratively discovering new edges and
+  locking down the nodes those edges connect to.
+- Due to the -EALREADY return code signalling that a given objects is already
+  held there's no need for additional book-keeping to break cycles in the graph
+  or keep track off which looks are already held (when using more than one node
+  as a starting point).
+
+Note that this approach differs in two important ways from the above methods:
+- Since the list of objects is dynamically constructed (and might very well be
+  different when retrying due to hitting the -EDEADLK wound condition) there's
+  no need to keep any object on a persistent list when it's not locked. We can
+  therefore move the list_head into the object itself.
+- On the other hand the dynamic object list construction also means that the -EALREADY return
+  code can't be propagated.
+
+Note also that methods #1 and #2 and method #3 can be combined, e.g. to first lock a
+list of starting nodes (passed in from userspace) using one of the above
+methods. And then lock any additional objects affected by the operations using
+method #3 below. The backoff/retry procedure will be a bit more involved, since
+when the dynamic locking step hits -EDEADLK we also need to unlock all the
+objects acquired with the fixed list. But the w/w mutex debug checks will catch
+any interface misuse for these cases.
+
+Also, method 3 can't fail the lock acquisition step since it doesn't return
+-EALREADY. Of course this would be different when using the _interruptible
+variants, but that's outside of the scope of these examples here.
+
+struct obj {
+	struct ww_mutex ww_mutex;
+	struct list_head locked_list;
+};
+
+static DEFINE_WW_CLASS(ww_class);
+
+void __unlock_objs(struct list_head *list)
+{
+	struct obj *entry, *temp;
+
+	list_for_each_entry_safe (entry, temp, list, locked_list) {
+		/* need to do that before unlocking, since only the current lock holder is
+		allowed to use object */
+		list_del(&entry->locked_list);
+		ww_mutex_unlock(entry->ww_mutex)
+	}
+}
+
+void lock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
+{
+	struct obj *obj;
+
+	ww_acquire_init(ctx, &ww_class);
+
+retry:
+	/* re-init loop start state */
+	loop {
+		/* magic code which walks over a graph and decides which objects
+		 * to lock */
+
+		ret = ww_mutex_lock(obj->ww_mutex, ctx);
+		if (ret == -EALREADY) {
+			/* we have that one already, get to the next object */
+			continue;
+		}
+		if (ret == -EDEADLK) {
+			__unlock_objs(list);
+
+			ww_mutex_lock_slow(obj, ctx);
+			list_add(&entry->locked_list, list);
+			goto retry;
+		}
+
+		/* locked a new object, add it to the list */
+		list_add_tail(&entry->locked_list, list);
+	}
+
+	ww_acquire_done(ctx);
+	return 0;
+}
+
+void unlock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
+{
+	__unlock_objs(list);
+	ww_acquire_fini(ctx);
+}
+
+Method 4: Only lock one single objects. In that case deadlock detection and
+prevention is obviously overkill, since with grabbing just one lock you can't
+produce a deadlock within just one class. To simplify this case the w/w mutex
+api can be used with a NULL context.
+
+Implementation Details
+----------------------
+
+Design:
+  ww_mutex currently encapsulates a struct mutex, this means no extra overhead for
+  normal mutex locks, which are far more common. As such there is only a small
+  increase in code size if wait/wound mutexes are not used.
+
+  In general, not much contention is expected. The locks are typically used to
+  serialize access to resources for devices. The only way to make wakeups
+  smarter would be at the cost of adding a field to struct mutex_waiter. This
+  would add overhead to all cases where normal mutexes are used, and
+  ww_mutexes are generally less performance sensitive.
+
+Lockdep:
+  Special care has been taken to warn for as many cases of api abuse
+  as possible. Some common api abuses will be caught with
+  CONFIG_DEBUG_MUTEXES, but CONFIG_PROVE_LOCKING is recommended.
+
+  Some of the errors which will be warned about:
+   - Forgetting to call ww_acquire_fini or ww_acquire_init.
+   - Attempting to lock more mutexes after ww_acquire_done.
+   - Attempting to lock the wrong mutex after -EDEADLK and
+     unlocking all mutexes.
+   - Attempting to lock the right mutex after -EDEADLK,
+     before unlocking all mutexes.
+
+   - Calling ww_mutex_lock_slow before -EDEADLK was returned.
+
+   - Unlocking mutexes with the wrong unlock function.
+   - Calling one of the ww_acquire_* twice on the same context.
+   - Using a different ww_class for the mutex than for the ww_acquire_ctx.
+   - Normal lockdep errors that can result in deadlocks.
+
+  Some of the lockdep errors that can result in deadlocks:
+   - Calling ww_acquire_init to initialize a second ww_acquire_ctx before
+     having called ww_acquire_fini on the first.
+   - 'normal' deadlocks that can occur.
+
+FIXME: Update this section once we have the TASK_DEADLOCK task state flag magic
+implemented.
diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt
deleted file mode 100644
index 72d010689751..000000000000
--- a/Documentation/lockstat.txt
+++ /dev/null
@@ -1,178 +0,0 @@
-
-LOCK STATISTICS
-
-- WHAT
-
-As the name suggests, it provides statistics on locks.
-
-- WHY
-
-Because things like lock contention can severely impact performance.
-
-- HOW
-
-Lockdep already has hooks in the lock functions and maps lock instances to
-lock classes. We build on that (see Documentation/lockdep-design.txt).
-The graph below shows the relation between the lock functions and the various
-hooks therein.
-
-        __acquire
-            |
-           lock _____
-            |        \
-            |    __contended
-            |         |
-            |       <wait>
-            | _______/
-            |/
-            |
-       __acquired
-            |
-            .
-          <hold>
-            .
-            |
-       __release
-            |
-         unlock
-
-lock, unlock	- the regular lock functions
-__*		- the hooks
-<> 		- states
-
-With these hooks we provide the following statistics:
-
- con-bounces       - number of lock contention that involved x-cpu data
- contentions       - number of lock acquisitions that had to wait
- wait time min     - shortest (non-0) time we ever had to wait for a lock
-           max     - longest time we ever had to wait for a lock
-	   total   - total time we spend waiting on this lock
-	   avg     - average time spent waiting on this lock
- acq-bounces       - number of lock acquisitions that involved x-cpu data
- acquisitions      - number of times we took the lock
- hold time min     - shortest (non-0) time we ever held the lock
-	   max     - longest time we ever held the lock
-	   total   - total time this lock was held
-	   avg     - average time this lock was held
-
-These numbers are gathered per lock class, per read/write state (when
-applicable).
-
-It also tracks 4 contention points per class. A contention point is a call site
-that had to wait on lock acquisition.
-
- - CONFIGURATION
-
-Lock statistics are enabled via CONFIG_LOCK_STAT.
-
- - USAGE
-
-Enable collection of statistics:
-
-# echo 1 >/proc/sys/kernel/lock_stat
-
-Disable collection of statistics:
-
-# echo 0 >/proc/sys/kernel/lock_stat
-
-Look at the current lock statistics:
-
-( line numbers not part of actual output, done for clarity in the explanation
-  below )
-
-# less /proc/lock_stat
-
-01 lock_stat version 0.4
-02-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
-03                              class name    con-bounces    contentions   waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg
-04-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
-05
-06                         &mm->mmap_sem-W:            46             84           0.26         939.10       16371.53         194.90          47291        2922365           0.16     2220301.69 17464026916.32        5975.99
-07                         &mm->mmap_sem-R:            37            100           1.31      299502.61      325629.52        3256.30         212344       34316685           0.10        7744.91    95016910.20           2.77
-08                         ---------------
-09                           &mm->mmap_sem              1          [<ffffffff811502a7>] khugepaged_scan_mm_slot+0x57/0x280
-19                           &mm->mmap_sem             96          [<ffffffff815351c4>] __do_page_fault+0x1d4/0x510
-11                           &mm->mmap_sem             34          [<ffffffff81113d77>] vm_mmap_pgoff+0x87/0xd0
-12                           &mm->mmap_sem             17          [<ffffffff81127e71>] vm_munmap+0x41/0x80
-13                         ---------------
-14                           &mm->mmap_sem              1          [<ffffffff81046fda>] dup_mmap+0x2a/0x3f0
-15                           &mm->mmap_sem             60          [<ffffffff81129e29>] SyS_mprotect+0xe9/0x250
-16                           &mm->mmap_sem             41          [<ffffffff815351c4>] __do_page_fault+0x1d4/0x510
-17                           &mm->mmap_sem             68          [<ffffffff81113d77>] vm_mmap_pgoff+0x87/0xd0
-18
-19.............................................................................................................................................................................................................................
-20
-21                         unix_table_lock:           110            112           0.21          49.24         163.91           1.46          21094          66312           0.12         624.42       31589.81           0.48
-22                         ---------------
-23                         unix_table_lock             45          [<ffffffff8150ad8e>] unix_create1+0x16e/0x1b0
-24                         unix_table_lock             47          [<ffffffff8150b111>] unix_release_sock+0x31/0x250
-25                         unix_table_lock             15          [<ffffffff8150ca37>] unix_find_other+0x117/0x230
-26                         unix_table_lock              5          [<ffffffff8150a09f>] unix_autobind+0x11f/0x1b0
-27                         ---------------
-28                         unix_table_lock             39          [<ffffffff8150b111>] unix_release_sock+0x31/0x250
-29                         unix_table_lock             49          [<ffffffff8150ad8e>] unix_create1+0x16e/0x1b0
-30                         unix_table_lock             20          [<ffffffff8150ca37>] unix_find_other+0x117/0x230
-31                         unix_table_lock              4          [<ffffffff8150a09f>] unix_autobind+0x11f/0x1b0
-
-
-This excerpt shows the first two lock class statistics. Line 01 shows the
-output version - each time the format changes this will be updated. Line 02-04
-show the header with column descriptions. Lines 05-18 and 20-31 show the actual
-statistics. These statistics come in two parts; the actual stats separated by a
-short separator (line 08, 13) from the contention points.
-
-The first lock (05-18) is a read/write lock, and shows two lines above the
-short separator. The contention points don't match the column descriptors,
-they have two: contentions and [<IP>] symbol. The second set of contention
-points are the points we're contending with.
-
-The integer part of the time values is in us.
-
-Dealing with nested locks, subclasses may appear:
-
-32...........................................................................................................................................................................................................................
-33
-34                               &rq->lock:       13128          13128           0.43         190.53      103881.26           7.91          97454        3453404           0.00         401.11    13224683.11           3.82
-35                               ---------
-36                               &rq->lock          645          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
-37                               &rq->lock          297          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
-38                               &rq->lock          360          [<ffffffff8103c4c5>] select_task_rq_fair+0x1f0/0x74a
-39                               &rq->lock          428          [<ffffffff81045f98>] scheduler_tick+0x46/0x1fb
-40                               ---------
-41                               &rq->lock           77          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
-42                               &rq->lock          174          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
-43                               &rq->lock         4715          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
-44                               &rq->lock          893          [<ffffffff81340524>] schedule+0x157/0x7b8
-45
-46...........................................................................................................................................................................................................................
-47
-48                             &rq->lock/1:        1526          11488           0.33         388.73      136294.31          11.86          21461          38404           0.00          37.93      109388.53           2.84
-49                             -----------
-50                             &rq->lock/1        11526          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
-51                             -----------
-52                             &rq->lock/1         5645          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
-53                             &rq->lock/1         1224          [<ffffffff81340524>] schedule+0x157/0x7b8
-54                             &rq->lock/1         4336          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
-55                             &rq->lock/1          181          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
-
-Line 48 shows statistics for the second subclass (/1) of &rq->lock class
-(subclass starts from 0), since in this case, as line 50 suggests,
-double_rq_lock actually acquires a nested lock of two spinlocks.
-
-View the top contending locks:
-
-# grep : /proc/lock_stat | head
-			clockevents_lock:       2926159        2947636           0.15       46882.81  1784540466.34         605.41        3381345        3879161           0.00        2260.97    53178395.68          13.71
-		     tick_broadcast_lock:        346460         346717           0.18        2257.43    39364622.71         113.54        3642919        4242696           0.00        2263.79    49173646.60          11.59
-		  &mapping->i_mmap_mutex:        203896         203899           3.36      645530.05 31767507988.39      155800.21        3361776        8893984           0.17        2254.15    14110121.02           1.59
-			       &rq->lock:        135014         136909           0.18         606.09      842160.68           6.15        1540728       10436146           0.00         728.72    17606683.41           1.69
-	       &(&zone->lru_lock)->rlock:         93000          94934           0.16          59.18      188253.78           1.98        1199912        3809894           0.15         391.40     3559518.81           0.93
-			 tasklist_lock-W:         40667          41130           0.23        1189.42      428980.51          10.43         270278         510106           0.16         653.51     3939674.91           7.72
-			 tasklist_lock-R:         21298          21305           0.20        1310.05      215511.12          10.12         186204         241258           0.14        1162.33     1179779.23           4.89
-			      rcu_node_1:         47656          49022           0.16         635.41      193616.41           3.95         844888        1865423           0.00         764.26     1656226.96           0.89
-       &(&dentry->d_lockref.lock)->rlock:         39791          40179           0.15        1302.08       88851.96           2.21        2790851       12527025           0.10        1910.75     3379714.27           0.27
-			      rcu_node_0:         29203          30064           0.16         786.55     1555573.00          51.74          88963         244254           0.00         398.87      428872.51           1.76
-
-Clear the statistics:
-
-# echo 0 > /proc/lock_stat
diff --git a/Documentation/mutex-design.txt b/Documentation/mutex-design.txt
deleted file mode 100644
index ee231ed09ec6..000000000000
--- a/Documentation/mutex-design.txt
+++ /dev/null
@@ -1,157 +0,0 @@
-Generic Mutex Subsystem
-
-started by Ingo Molnar <mingo@redhat.com>
-updated by Davidlohr Bueso <davidlohr@hp.com>
-
-What are mutexes?
------------------
-
-In the Linux kernel, mutexes refer to a particular locking primitive
-that enforces serialization on shared memory systems, and not only to
-the generic term referring to 'mutual exclusion' found in academia
-or similar theoretical text books. Mutexes are sleeping locks which
-behave similarly to binary semaphores, and were introduced in 2006[1]
-as an alternative to these. This new data structure provided a number
-of advantages, including simpler interfaces, and at that time smaller
-code (see Disadvantages).
-
-[1] http://lwn.net/Articles/164802/
-
-Implementation
---------------
-
-Mutexes are represented by 'struct mutex', defined in include/linux/mutex.h
-and implemented in kernel/locking/mutex.c. These locks use a three
-state atomic counter (->count) to represent the different possible
-transitions that can occur during the lifetime of a lock:
-
-	  1: unlocked
-	  0: locked, no waiters
-   negative: locked, with potential waiters
-
-In its most basic form it also includes a wait-queue and a spinlock
-that serializes access to it. CONFIG_SMP systems can also include
-a pointer to the lock task owner (->owner) as well as a spinner MCS
-lock (->osq), both described below in (ii).
-
-When acquiring a mutex, there are three possible paths that can be
-taken, depending on the state of the lock:
-
-(i) fastpath: tries to atomically acquire the lock by decrementing the
-    counter. If it was already taken by another task it goes to the next
-    possible path. This logic is architecture specific. On x86-64, the
-    locking fastpath is 2 instructions:
-
-    0000000000000e10 <mutex_lock>:
-    e21:   f0 ff 0b                lock decl (%rbx)
-    e24:   79 08                   jns    e2e <mutex_lock+0x1e>
-
-   the unlocking fastpath is equally tight:
-
-    0000000000000bc0 <mutex_unlock>:
-    bc8:   f0 ff 07                lock incl (%rdi)
-    bcb:   7f 0a                   jg     bd7 <mutex_unlock+0x17>
-
-
-(ii) midpath: aka optimistic spinning, tries to spin for acquisition
-     while the lock owner is running and there are no other tasks ready
-     to run that have higher priority (need_resched). The rationale is
-     that if the lock owner is running, it is likely to release the lock
-     soon. The mutex spinners are queued up using MCS lock so that only
-     one spinner can compete for the mutex.
-
-     The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spinlock
-     with the desirable properties of being fair and with each cpu trying
-     to acquire the lock spinning on a local variable. It avoids expensive
-     cacheline bouncing that common test-and-set spinlock implementations
-     incur. An MCS-like lock is specially tailored for optimistic spinning
-     for sleeping lock implementation. An important feature of the customized
-     MCS lock is that it has the extra property that spinners are able to exit
-     the MCS spinlock queue when they need to reschedule. This further helps
-     avoid situations where MCS spinners that need to reschedule would continue
-     waiting to spin on mutex owner, only to go directly to slowpath upon
-     obtaining the MCS lock.
-
-
-(iii) slowpath: last resort, if the lock is still unable to be acquired,
-      the task is added to the wait-queue and sleeps until woken up by the
-      unlock path. Under normal circumstances it blocks as TASK_UNINTERRUPTIBLE.
-
-While formally kernel mutexes are sleepable locks, it is path (ii) that
-makes them more practically a hybrid type. By simply not interrupting a
-task and busy-waiting for a few cycles instead of immediately sleeping,
-the performance of this lock has been seen to significantly improve a
-number of workloads. Note that this technique is also used for rw-semaphores.
-
-Semantics
----------
-
-The mutex subsystem checks and enforces the following rules:
-
-    - Only one task can hold the mutex at a time.
-    - Only the owner can unlock the mutex.
-    - Multiple unlocks are not permitted.
-    - Recursive locking/unlocking is not permitted.
-    - A mutex must only be initialized via the API (see below).
-    - A task may not exit with a mutex held.
-    - Memory areas where held locks reside must not be freed.
-    - Held mutexes must not be reinitialized.
-    - Mutexes may not be used in hardware or software interrupt
-      contexts such as tasklets and timers.
-
-These semantics are fully enforced when CONFIG DEBUG_MUTEXES is enabled.
-In addition, the mutex debugging code also implements a number of other
-features that make lock debugging easier and faster:
-
-    - Uses symbolic names of mutexes, whenever they are printed
-      in debug output.
-    - Point-of-acquire tracking, symbolic lookup of function names,
-      list of all locks held in the system, printout of them.
-    - Owner tracking.
-    - Detects self-recursing locks and prints out all relevant info.
-    - Detects multi-task circular deadlocks and prints out all affected
-      locks and tasks (and only those tasks).
-
-
-Interfaces
-----------
-Statically define the mutex:
-   DEFINE_MUTEX(name);
-
-Dynamically initialize the mutex:
-   mutex_init(mutex);
-
-Acquire the mutex, uninterruptible:
-   void mutex_lock(struct mutex *lock);
-   void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
-   int  mutex_trylock(struct mutex *lock);
-
-Acquire the mutex, interruptible:
-   int mutex_lock_interruptible_nested(struct mutex *lock,
-				       unsigned int subclass);
-   int mutex_lock_interruptible(struct mutex *lock);
-
-Acquire the mutex, interruptible, if dec to 0:
-   int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
-
-Unlock the mutex:
-   void mutex_unlock(struct mutex *lock);
-
-Test if the mutex is taken:
-   int mutex_is_locked(struct mutex *lock);
-
-Disadvantages
--------------
-
-Unlike its original design and purpose, 'struct mutex' is larger than
-most locks in the kernel. E.g: on x86-64 it is 40 bytes, almost twice
-as large as 'struct semaphore' (24 bytes) and 8 bytes shy of the
-'struct rw_semaphore' variant. Larger structure sizes mean more CPU
-cache and memory footprint.
-
-When to use mutexes
--------------------
-
-Unless the strict semantics of mutexes are unsuitable and/or the critical
-region prevents the lock from being shared, always prefer them to any other
-locking primitive.
diff --git a/Documentation/rt-mutex-design.txt b/Documentation/rt-mutex-design.txt
deleted file mode 100644
index 8666070d3189..000000000000
--- a/Documentation/rt-mutex-design.txt
+++ /dev/null
@@ -1,781 +0,0 @@
-#
-# Copyright (c) 2006 Steven Rostedt
-# Licensed under the GNU Free Documentation License, Version 1.2
-#
-
-RT-mutex implementation design
-------------------------------
-
-This document tries to describe the design of the rtmutex.c implementation.
-It doesn't describe the reasons why rtmutex.c exists. For that please see
-Documentation/rt-mutex.txt.  Although this document does explain problems
-that happen without this code, but that is in the concept to understand
-what the code actually is doing.
-
-The goal of this document is to help others understand the priority
-inheritance (PI) algorithm that is used, as well as reasons for the
-decisions that were made to implement PI in the manner that was done.
-
-
-Unbounded Priority Inversion
-----------------------------
-
-Priority inversion is when a lower priority process executes while a higher
-priority process wants to run.  This happens for several reasons, and
-most of the time it can't be helped.  Anytime a high priority process wants
-to use a resource that a lower priority process has (a mutex for example),
-the high priority process must wait until the lower priority process is done
-with the resource.  This is a priority inversion.  What we want to prevent
-is something called unbounded priority inversion.  That is when the high
-priority process is prevented from running by a lower priority process for
-an undetermined amount of time.
-
-The classic example of unbounded priority inversion is where you have three
-processes, let's call them processes A, B, and C, where A is the highest
-priority process, C is the lowest, and B is in between. A tries to grab a lock
-that C owns and must wait and lets C run to release the lock. But in the
-meantime, B executes, and since B is of a higher priority than C, it preempts C,
-but by doing so, it is in fact preempting A which is a higher priority process.
-Now there's no way of knowing how long A will be sleeping waiting for C
-to release the lock, because for all we know, B is a CPU hog and will
-never give C a chance to release the lock.  This is called unbounded priority
-inversion.
-
-Here's a little ASCII art to show the problem.
-
-   grab lock L1 (owned by C)
-     |
-A ---+
-        C preempted by B
-          |
-C    +----+
-
-B         +-------->
-                B now keeps A from running.
-
-
-Priority Inheritance (PI)
--------------------------
-
-There are several ways to solve this issue, but other ways are out of scope
-for this document.  Here we only discuss PI.
-
-PI is where a process inherits the priority of another process if the other
-process blocks on a lock owned by the current process.  To make this easier
-to understand, let's use the previous example, with processes A, B, and C again.
-
-This time, when A blocks on the lock owned by C, C would inherit the priority
-of A.  So now if B becomes runnable, it would not preempt C, since C now has
-the high priority of A.  As soon as C releases the lock, it loses its
-inherited priority, and A then can continue with the resource that C had.
-
-Terminology
------------
-
-Here I explain some terminology that is used in this document to help describe
-the design that is used to implement PI.
-
-PI chain - The PI chain is an ordered series of locks and processes that cause
-           processes to inherit priorities from a previous process that is
-           blocked on one of its locks.  This is described in more detail
-           later in this document.
-
-mutex    - In this document, to differentiate from locks that implement
-           PI and spin locks that are used in the PI code, from now on
-           the PI locks will be called a mutex.
-
-lock     - In this document from now on, I will use the term lock when
-           referring to spin locks that are used to protect parts of the PI
-           algorithm.  These locks disable preemption for UP (when
-           CONFIG_PREEMPT is enabled) and on SMP prevents multiple CPUs from
-           entering critical sections simultaneously.
-
-spin lock - Same as lock above.
-
-waiter   - A waiter is a struct that is stored on the stack of a blocked
-           process.  Since the scope of the waiter is within the code for
-           a process being blocked on the mutex, it is fine to allocate
-           the waiter on the process's stack (local variable).  This
-           structure holds a pointer to the task, as well as the mutex that
-           the task is blocked on.  It also has the plist node structures to
-           place the task in the waiter_list of a mutex as well as the
-           pi_list of a mutex owner task (described below).
-
-           waiter is sometimes used in reference to the task that is waiting
-           on a mutex. This is the same as waiter->task.
-
-waiters  - A list of processes that are blocked on a mutex.
-
-top waiter - The highest priority process waiting on a specific mutex.
-
-top pi waiter - The highest priority process waiting on one of the mutexes
-                that a specific process owns.
-
-Note:  task and process are used interchangeably in this document, mostly to
-       differentiate between two processes that are being described together.
-
-
-PI chain
---------
-
-The PI chain is a list of processes and mutexes that may cause priority
-inheritance to take place.  Multiple chains may converge, but a chain
-would never diverge, since a process can't be blocked on more than one
-mutex at a time.
-
-Example:
-
-   Process:  A, B, C, D, E
-   Mutexes:  L1, L2, L3, L4
-
-   A owns: L1
-           B blocked on L1
-           B owns L2
-                  C blocked on L2
-                  C owns L3
-                         D blocked on L3
-                         D owns L4
-                                E blocked on L4
-
-The chain would be:
-
-   E->L4->D->L3->C->L2->B->L1->A
-
-To show where two chains merge, we could add another process F and
-another mutex L5 where B owns L5 and F is blocked on mutex L5.
-
-The chain for F would be:
-
-   F->L5->B->L1->A
-
-Since a process may own more than one mutex, but never be blocked on more than
-one, the chains merge.
-
-Here we show both chains:
-
-   E->L4->D->L3->C->L2-+
-                       |
-                       +->B->L1->A
-                       |
-                 F->L5-+
-
-For PI to work, the processes at the right end of these chains (or we may
-also call it the Top of the chain) must be equal to or higher in priority
-than the processes to the left or below in the chain.
-
-Also since a mutex may have more than one process blocked on it, we can
-have multiple chains merge at mutexes.  If we add another process G that is
-blocked on mutex L2:
-
-  G->L2->B->L1->A
-
-And once again, to show how this can grow I will show the merging chains
-again.
-
-   E->L4->D->L3->C-+
-                   +->L2-+
-                   |     |
-                 G-+     +->B->L1->A
-                         |
-                   F->L5-+
-
-
-Plist
------
-
-Before I go further and talk about how the PI chain is stored through lists
-on both mutexes and processes, I'll explain the plist.  This is similar to
-the struct list_head functionality that is already in the kernel.
-The implementation of plist is out of scope for this document, but it is
-very important to understand what it does.
-
-There are a few differences between plist and list, the most important one
-being that plist is a priority sorted linked list.  This means that the
-priorities of the plist are sorted, such that it takes O(1) to retrieve the
-highest priority item in the list.  Obviously this is useful to store processes
-based on their priorities.
-
-Another difference, which is important for implementation, is that, unlike
-list, the head of the list is a different element than the nodes of a list.
-So the head of the list is declared as struct plist_head and nodes that will
-be added to the list are declared as struct plist_node.
-
-
-Mutex Waiter List
------------------
-
-Every mutex keeps track of all the waiters that are blocked on itself. The mutex
-has a plist to store these waiters by priority.  This list is protected by
-a spin lock that is located in the struct of the mutex. This lock is called
-wait_lock.  Since the modification of the waiter list is never done in
-interrupt context, the wait_lock can be taken without disabling interrupts.
-
-
-Task PI List
-------------
-
-To keep track of the PI chains, each process has its own PI list.  This is
-a list of all top waiters of the mutexes that are owned by the process.
-Note that this list only holds the top waiters and not all waiters that are
-blocked on mutexes owned by the process.
-
-The top of the task's PI list is always the highest priority task that
-is waiting on a mutex that is owned by the task.  So if the task has
-inherited a priority, it will always be the priority of the task that is
-at the top of this list.
-
-This list is stored in the task structure of a process as a plist called
-pi_list.  This list is protected by a spin lock also in the task structure,
-called pi_lock.  This lock may also be taken in interrupt context, so when
-locking the pi_lock, interrupts must be disabled.
-
-
-Depth of the PI Chain
----------------------
-
-The maximum depth of the PI chain is not dynamic, and could actually be
-defined.  But is very complex to figure it out, since it depends on all
-the nesting of mutexes.  Let's look at the example where we have 3 mutexes,
-L1, L2, and L3, and four separate functions func1, func2, func3 and func4.
-The following shows a locking order of L1->L2->L3, but may not actually
-be directly nested that way.
-
-void func1(void)
-{
-	mutex_lock(L1);
-
-	/* do anything */
-
-	mutex_unlock(L1);
-}
-
-void func2(void)
-{
-	mutex_lock(L1);
-	mutex_lock(L2);
-
-	/* do something */
-
-	mutex_unlock(L2);
-	mutex_unlock(L1);
-}
-
-void func3(void)
-{
-	mutex_lock(L2);
-	mutex_lock(L3);
-
-	/* do something else */
-
-	mutex_unlock(L3);
-	mutex_unlock(L2);
-}
-
-void func4(void)
-{
-	mutex_lock(L3);
-
-	/* do something again */
-
-	mutex_unlock(L3);
-}
-
-Now we add 4 processes that run each of these functions separately.
-Processes A, B, C, and D which run functions func1, func2, func3 and func4
-respectively, and such that D runs first and A last.  With D being preempted
-in func4 in the "do something again" area, we have a locking that follows:
-
-D owns L3
-       C blocked on L3
-       C owns L2
-              B blocked on L2
-              B owns L1
-                     A blocked on L1
-
-And thus we have the chain A->L1->B->L2->C->L3->D.
-
-This gives us a PI depth of 4 (four processes), but looking at any of the
-functions individually, it seems as though they only have at most a locking
-depth of two.  So, although the locking depth is defined at compile time,
-it still is very difficult to find the possibilities of that depth.
-
-Now since mutexes can be defined by user-land applications, we don't want a DOS
-type of application that nests large amounts of mutexes to create a large
-PI chain, and have the code holding spin locks while looking at a large
-amount of data.  So to prevent this, the implementation not only implements
-a maximum lock depth, but also only holds at most two different locks at a
-time, as it walks the PI chain.  More about this below.
-
-
-Mutex owner and flags
----------------------
-
-The mutex structure contains a pointer to the owner of the mutex.  If the
-mutex is not owned, this owner is set to NULL.  Since all architectures
-have the task structure on at least a four byte alignment (and if this is
-not true, the rtmutex.c code will be broken!), this allows for the two
-least significant bits to be used as flags.  This part is also described
-in Documentation/rt-mutex.txt, but will also be briefly described here.
-
-Bit 0 is used as the "Pending Owner" flag.  This is described later.
-Bit 1 is used as the "Has Waiters" flags.  This is also described later
-  in more detail, but is set whenever there are waiters on a mutex.
-
-
-cmpxchg Tricks
---------------
-
-Some architectures implement an atomic cmpxchg (Compare and Exchange).  This
-is used (when applicable) to keep the fast path of grabbing and releasing
-mutexes short.
-
-cmpxchg is basically the following function performed atomically:
-
-unsigned long _cmpxchg(unsigned long *A, unsigned long *B, unsigned long *C)
-{
-	unsigned long T = *A;
-	if (*A == *B) {
-		*A = *C;
-	}
-	return T;
-}
-#define cmpxchg(a,b,c) _cmpxchg(&a,&b,&c)
-
-This is really nice to have, since it allows you to only update a variable
-if the variable is what you expect it to be.  You know if it succeeded if
-the return value (the old value of A) is equal to B.
-
-The macro rt_mutex_cmpxchg is used to try to lock and unlock mutexes. If
-the architecture does not support CMPXCHG, then this macro is simply set
-to fail every time.  But if CMPXCHG is supported, then this will
-help out extremely to keep the fast path short.
-
-The use of rt_mutex_cmpxchg with the flags in the owner field help optimize
-the system for architectures that support it.  This will also be explained
-later in this document.
-
-
-Priority adjustments
---------------------
-
-The implementation of the PI code in rtmutex.c has several places that a
-process must adjust its priority.  With the help of the pi_list of a
-process this is rather easy to know what needs to be adjusted.
-
-The functions implementing the task adjustments are rt_mutex_adjust_prio,
-__rt_mutex_adjust_prio (same as the former, but expects the task pi_lock
-to already be taken), rt_mutex_getprio, and rt_mutex_setprio.
-
-rt_mutex_getprio and rt_mutex_setprio are only used in __rt_mutex_adjust_prio.
-
-rt_mutex_getprio returns the priority that the task should have.  Either the
-task's own normal priority, or if a process of a higher priority is waiting on
-a mutex owned by the task, then that higher priority should be returned.
-Since the pi_list of a task holds an order by priority list of all the top
-waiters of all the mutexes that the task owns, rt_mutex_getprio simply needs
-to compare the top pi waiter to its own normal priority, and return the higher
-priority back.
-
-(Note:  if looking at the code, you will notice that the lower number of
-        prio is returned.  This is because the prio field in the task structure
-        is an inverse order of the actual priority.  So a "prio" of 5 is
-        of higher priority than a "prio" of 10.)
-
-__rt_mutex_adjust_prio examines the result of rt_mutex_getprio, and if the
-result does not equal the task's current priority, then rt_mutex_setprio
-is called to adjust the priority of the task to the new priority.
-Note that rt_mutex_setprio is defined in kernel/sched/core.c to implement the
-actual change in priority.
-
-It is interesting to note that __rt_mutex_adjust_prio can either increase
-or decrease the priority of the task.  In the case that a higher priority
-process has just blocked on a mutex owned by the task, __rt_mutex_adjust_prio
-would increase/boost the task's priority.  But if a higher priority task
-were for some reason to leave the mutex (timeout or signal), this same function
-would decrease/unboost the priority of the task.  That is because the pi_list
-always contains the highest priority task that is waiting on a mutex owned
-by the task, so we only need to compare the priority of that top pi waiter
-to the normal priority of the given task.
-
-
-High level overview of the PI chain walk
-----------------------------------------
-
-The PI chain walk is implemented by the function rt_mutex_adjust_prio_chain.
-
-The implementation has gone through several iterations, and has ended up
-with what we believe is the best.  It walks the PI chain by only grabbing
-at most two locks at a time, and is very efficient.
-
-The rt_mutex_adjust_prio_chain can be used either to boost or lower process
-priorities.
-
-rt_mutex_adjust_prio_chain is called with a task to be checked for PI
-(de)boosting (the owner of a mutex that a process is blocking on), a flag to
-check for deadlocking, the mutex that the task owns, and a pointer to a waiter
-that is the process's waiter struct that is blocked on the mutex (although this
-parameter may be NULL for deboosting).
-
-For this explanation, I will not mention deadlock detection. This explanation
-will try to stay at a high level.
-
-When this function is called, there are no locks held.  That also means
-that the state of the owner and lock can change when entered into this function.
-
-Before this function is called, the task has already had rt_mutex_adjust_prio
-performed on it.  This means that the task is set to the priority that it
-should be at, but the plist nodes of the task's waiter have not been updated
-with the new priorities, and that this task may not be in the proper locations
-in the pi_lists and wait_lists that the task is blocked on.  This function
-solves all that.
-
-A loop is entered, where task is the owner to be checked for PI changes that
-was passed by parameter (for the first iteration).  The pi_lock of this task is
-taken to prevent any more changes to the pi_list of the task.  This also
-prevents new tasks from completing the blocking on a mutex that is owned by this
-task.
-
-If the task is not blocked on a mutex then the loop is exited.  We are at
-the top of the PI chain.
-
-A check is now done to see if the original waiter (the process that is blocked
-on the current mutex) is the top pi waiter of the task.  That is, is this
-waiter on the top of the task's pi_list.  If it is not, it either means that
-there is another process higher in priority that is blocked on one of the
-mutexes that the task owns, or that the waiter has just woken up via a signal
-or timeout and has left the PI chain.  In either case, the loop is exited, since
-we don't need to do any more changes to the priority of the current task, or any
-task that owns a mutex that this current task is waiting on.  A priority chain
-walk is only needed when a new top pi waiter is made to a task.
-
-The next check sees if the task's waiter plist node has the priority equal to
-the priority the task is set at.  If they are equal, then we are done with
-the loop.  Remember that the function started with the priority of the
-task adjusted, but the plist nodes that hold the task in other processes
-pi_lists have not been adjusted.
-
-Next, we look at the mutex that the task is blocked on. The mutex's wait_lock
-is taken.  This is done by a spin_trylock, because the locking order of the
-pi_lock and wait_lock goes in the opposite direction. If we fail to grab the
-lock, the pi_lock is released, and we restart the loop.
-
-Now that we have both the pi_lock of the task as well as the wait_lock of
-the mutex the task is blocked on, we update the task's waiter's plist node
-that is located on the mutex's wait_list.
-
-Now we release the pi_lock of the task.
-
-Next the owner of the mutex has its pi_lock taken, so we can update the
-task's entry in the owner's pi_list.  If the task is the highest priority
-process on the mutex's wait_list, then we remove the previous top waiter
-from the owner's pi_list, and replace it with the task.
-
-Note: It is possible that the task was the current top waiter on the mutex,
-      in which case the task is not yet on the pi_list of the waiter.  This
-      is OK, since plist_del does nothing if the plist node is not on any
-      list.
-
-If the task was not the top waiter of the mutex, but it was before we
-did the priority updates, that means we are deboosting/lowering the
-task.  In this case, the task is removed from the pi_list of the owner,
-and the new top waiter is added.
-
-Lastly, we unlock both the pi_lock of the task, as well as the mutex's
-wait_lock, and continue the loop again.  On the next iteration of the
-loop, the previous owner of the mutex will be the task that will be
-processed.
-
-Note: One might think that the owner of this mutex might have changed
-      since we just grab the mutex's wait_lock. And one could be right.
-      The important thing to remember is that the owner could not have
-      become the task that is being processed in the PI chain, since
-      we have taken that task's pi_lock at the beginning of the loop.
-      So as long as there is an owner of this mutex that is not the same
-      process as the tasked being worked on, we are OK.
-
-      Looking closely at the code, one might be confused.  The check for the
-      end of the PI chain is when the task isn't blocked on anything or the
-      task's waiter structure "task" element is NULL.  This check is
-      protected only by the task's pi_lock.  But the code to unlock the mutex
-      sets the task's waiter structure "task" element to NULL with only
-      the protection of the mutex's wait_lock, which was not taken yet.
-      Isn't this a race condition if the task becomes the new owner?
-
-      The answer is No!  The trick is the spin_trylock of the mutex's
-      wait_lock.  If we fail that lock, we release the pi_lock of the
-      task and continue the loop, doing the end of PI chain check again.
-
-      In the code to release the lock, the wait_lock of the mutex is held
-      the entire time, and it is not let go when we grab the pi_lock of the
-      new owner of the mutex.  So if the switch of a new owner were to happen
-      after the check for end of the PI chain and the grabbing of the
-      wait_lock, the unlocking code would spin on the new owner's pi_lock
-      but never give up the wait_lock.  So the PI chain loop is guaranteed to
-      fail the spin_trylock on the wait_lock, release the pi_lock, and
-      try again.
-
-      If you don't quite understand the above, that's OK. You don't have to,
-      unless you really want to make a proof out of it ;)
-
-
-Pending Owners and Lock stealing
---------------------------------
-
-One of the flags in the owner field of the mutex structure is "Pending Owner".
-What this means is that an owner was chosen by the process releasing the
-mutex, but that owner has yet to wake up and actually take the mutex.
-
-Why is this important?  Why can't we just give the mutex to another process
-and be done with it?
-
-The PI code is to help with real-time processes, and to let the highest
-priority process run as long as possible with little latencies and delays.
-If a high priority process owns a mutex that a lower priority process is
-blocked on, when the mutex is released it would be given to the lower priority
-process.  What if the higher priority process wants to take that mutex again.
-The high priority process would fail to take that mutex that it just gave up
-and it would need to boost the lower priority process to run with full
-latency of that critical section (since the low priority process just entered
-it).
-
-There's no reason a high priority process that gives up a mutex should be
-penalized if it tries to take that mutex again.  If the new owner of the
-mutex has not woken up yet, there's no reason that the higher priority process
-could not take that mutex away.
-
-To solve this, we introduced Pending Ownership and Lock Stealing.  When a
-new process is given a mutex that it was blocked on, it is only given
-pending ownership.  This means that it's the new owner, unless a higher
-priority process comes in and tries to grab that mutex.  If a higher priority
-process does come along and wants that mutex, we let the higher priority
-process "steal" the mutex from the pending owner (only if it is still pending)
-and continue with the mutex.
-
-
-Taking of a mutex (The walk through)
-------------------------------------
-
-OK, now let's take a look at the detailed walk through of what happens when
-taking a mutex.
-
-The first thing that is tried is the fast taking of the mutex.  This is
-done when we have CMPXCHG enabled (otherwise the fast taking automatically
-fails).  Only when the owner field of the mutex is NULL can the lock be
-taken with the CMPXCHG and nothing else needs to be done.
-
-If there is contention on the lock, whether it is owned or pending owner
-we go about the slow path (rt_mutex_slowlock).
-
-The slow path function is where the task's waiter structure is created on
-the stack.  This is because the waiter structure is only needed for the
-scope of this function.  The waiter structure holds the nodes to store
-the task on the wait_list of the mutex, and if need be, the pi_list of
-the owner.
-
-The wait_lock of the mutex is taken since the slow path of unlocking the
-mutex also takes this lock.
-
-We then call try_to_take_rt_mutex.  This is where the architecture that
-does not implement CMPXCHG would always grab the lock (if there's no
-contention).
-
-try_to_take_rt_mutex is used every time the task tries to grab a mutex in the
-slow path.  The first thing that is done here is an atomic setting of
-the "Has Waiters" flag of the mutex's owner field.  Yes, this could really
-be false, because if the mutex has no owner, there are no waiters and
-the current task also won't have any waiters.  But we don't have the lock
-yet, so we assume we are going to be a waiter.  The reason for this is to
-play nice for those architectures that do have CMPXCHG.  By setting this flag
-now, the owner of the mutex can't release the mutex without going into the
-slow unlock path, and it would then need to grab the wait_lock, which this
-code currently holds.  So setting the "Has Waiters" flag forces the owner
-to synchronize with this code.
-
-Now that we know that we can't have any races with the owner releasing the
-mutex, we check to see if we can take the ownership.  This is done if the
-mutex doesn't have a owner, or if we can steal the mutex from a pending
-owner.  Let's look at the situations we have here.
-
-  1) Has owner that is pending
-  ----------------------------
-
-  The mutex has a owner, but it hasn't woken up and the mutex flag
-  "Pending Owner" is set.  The first check is to see if the owner isn't the
-  current task.  This is because this function is also used for the pending
-  owner to grab the mutex.  When a pending owner wakes up, it checks to see
-  if it can take the mutex, and this is done if the owner is already set to
-  itself.  If so, we succeed and leave the function, clearing the "Pending
-  Owner" bit.
-
-  If the pending owner is not current, we check to see if the current priority is
-  higher than the pending owner.  If not, we fail the function and return.
-
-  There's also something special about a pending owner.  That is a pending owner
-  is never blocked on a mutex.  So there is no PI chain to worry about.  It also
-  means that if the mutex doesn't have any waiters, there's no accounting needed
-  to update the pending owner's pi_list, since we only worry about processes
-  blocked on the current mutex.
-
-  If there are waiters on this mutex, and we just stole the ownership, we need
-  to take the top waiter, remove it from the pi_list of the pending owner, and
-  add it to the current pi_list.  Note that at this moment, the pending owner
-  is no longer on the list of waiters.  This is fine, since the pending owner
-  would add itself back when it realizes that it had the ownership stolen
-  from itself.  When the pending owner tries to grab the mutex, it will fail
-  in try_to_take_rt_mutex if the owner field points to another process.
-
-  2) No owner
-  -----------
-
-  If there is no owner (or we successfully stole the lock), we set the owner
-  of the mutex to current, and set the flag of "Has Waiters" if the current
-  mutex actually has waiters, or we clear the flag if it doesn't.  See, it was
-  OK that we set that flag early, since now it is cleared.
-
-  3) Failed to grab ownership
-  ---------------------------
-
-  The most interesting case is when we fail to take ownership. This means that
-  there exists an owner, or there's a pending owner with equal or higher
-  priority than the current task.
-
-We'll continue on the failed case.
-
-If the mutex has a timeout, we set up a timer to go off to break us out
-of this mutex if we failed to get it after a specified amount of time.
-
-Now we enter a loop that will continue to try to take ownership of the mutex, or
-fail from a timeout or signal.
-
-Once again we try to take the mutex.  This will usually fail the first time
-in the loop, since it had just failed to get the mutex.  But the second time
-in the loop, this would likely succeed, since the task would likely be
-the pending owner.
-
-If the mutex is TASK_INTERRUPTIBLE a check for signals and timeout is done
-here.
-
-The waiter structure has a "task" field that points to the task that is blocked
-on the mutex.  This field can be NULL the first time it goes through the loop
-or if the task is a pending owner and had its mutex stolen.  If the "task"
-field is NULL then we need to set up the accounting for it.
-
-Task blocks on mutex
---------------------
-
-The accounting of a mutex and process is done with the waiter structure of
-the process.  The "task" field is set to the process, and the "lock" field
-to the mutex.  The plist nodes are initialized to the processes current
-priority.
-
-Since the wait_lock was taken at the entry of the slow lock, we can safely
-add the waiter to the wait_list.  If the current process is the highest
-priority process currently waiting on this mutex, then we remove the
-previous top waiter process (if it exists) from the pi_list of the owner,
-and add the current process to that list.  Since the pi_list of the owner
-has changed, we call rt_mutex_adjust_prio on the owner to see if the owner
-should adjust its priority accordingly.
-
-If the owner is also blocked on a lock, and had its pi_list changed
-(or deadlock checking is on), we unlock the wait_lock of the mutex and go ahead
-and run rt_mutex_adjust_prio_chain on the owner, as described earlier.
-
-Now all locks are released, and if the current process is still blocked on a
-mutex (waiter "task" field is not NULL), then we go to sleep (call schedule).
-
-Waking up in the loop
----------------------
-
-The schedule can then wake up for a few reasons.
-  1) we were given pending ownership of the mutex.
-  2) we received a signal and was TASK_INTERRUPTIBLE
-  3) we had a timeout and was TASK_INTERRUPTIBLE
-
-In any of these cases, we continue the loop and once again try to grab the
-ownership of the mutex.  If we succeed, we exit the loop, otherwise we continue
-and on signal and timeout, will exit the loop, or if we had the mutex stolen
-we just simply add ourselves back on the lists and go back to sleep.
-
-Note: For various reasons, because of timeout and signals, the steal mutex
-      algorithm needs to be careful. This is because the current process is
-      still on the wait_list. And because of dynamic changing of priorities,
-      especially on SCHED_OTHER tasks, the current process can be the
-      highest priority task on the wait_list.
-
-Failed to get mutex on Timeout or Signal
-----------------------------------------
-
-If a timeout or signal occurred, the waiter's "task" field would not be
-NULL and the task needs to be taken off the wait_list of the mutex and perhaps
-pi_list of the owner.  If this process was a high priority process, then
-the rt_mutex_adjust_prio_chain needs to be executed again on the owner,
-but this time it will be lowering the priorities.
-
-
-Unlocking the Mutex
--------------------
-
-The unlocking of a mutex also has a fast path for those architectures with
-CMPXCHG.  Since the taking of a mutex on contention always sets the
-"Has Waiters" flag of the mutex's owner, we use this to know if we need to
-take the slow path when unlocking the mutex.  If the mutex doesn't have any
-waiters, the owner field of the mutex would equal the current process and
-the mutex can be unlocked by just replacing the owner field with NULL.
-
-If the owner field has the "Has Waiters" bit set (or CMPXCHG is not available),
-the slow unlock path is taken.
-
-The first thing done in the slow unlock path is to take the wait_lock of the
-mutex.  This synchronizes the locking and unlocking of the mutex.
-
-A check is made to see if the mutex has waiters or not.  On architectures that
-do not have CMPXCHG, this is the location that the owner of the mutex will
-determine if a waiter needs to be awoken or not.  On architectures that
-do have CMPXCHG, that check is done in the fast path, but it is still needed
-in the slow path too.  If a waiter of a mutex woke up because of a signal
-or timeout between the time the owner failed the fast path CMPXCHG check and
-the grabbing of the wait_lock, the mutex may not have any waiters, thus the
-owner still needs to make this check. If there are no waiters then the mutex
-owner field is set to NULL, the wait_lock is released and nothing more is
-needed.
-
-If there are waiters, then we need to wake one up and give that waiter
-pending ownership.
-
-On the wake up code, the pi_lock of the current owner is taken.  The top
-waiter of the lock is found and removed from the wait_list of the mutex
-as well as the pi_list of the current owner.  The task field of the new
-pending owner's waiter structure is set to NULL, and the owner field of the
-mutex is set to the new owner with the "Pending Owner" bit set, as well
-as the "Has Waiters" bit if there still are other processes blocked on the
-mutex.
-
-The pi_lock of the previous owner is released, and the new pending owner's
-pi_lock is taken.  Remember that this is the trick to prevent the race
-condition in rt_mutex_adjust_prio_chain from adding itself as a waiter
-on the mutex.
-
-We now clear the "pi_blocked_on" field of the new pending owner, and if
-the mutex still has waiters pending, we add the new top waiter to the pi_list
-of the pending owner.
-
-Finally we unlock the pi_lock of the pending owner and wake it up.
-
-
-Contact
--------
-
-For updates on this document, please email Steven Rostedt <rostedt@goodmis.org>
-
-
-Credits
--------
-
-Author:  Steven Rostedt <rostedt@goodmis.org>
-
-Reviewers:  Ingo Molnar, Thomas Gleixner, Thomas Duetsch, and Randy Dunlap
-
-Updates
--------
-
-This document was originally written for 2.6.17-rc3-mm1
diff --git a/Documentation/rt-mutex.txt b/Documentation/rt-mutex.txt
deleted file mode 100644
index 243393d882ee..000000000000
--- a/Documentation/rt-mutex.txt
+++ /dev/null
@@ -1,79 +0,0 @@
-RT-mutex subsystem with PI support
-----------------------------------
-
-RT-mutexes with priority inheritance are used to support PI-futexes,
-which enable pthread_mutex_t priority inheritance attributes
-(PTHREAD_PRIO_INHERIT). [See Documentation/pi-futex.txt for more details
-about PI-futexes.]
-
-This technology was developed in the -rt tree and streamlined for
-pthread_mutex support.
-
-Basic principles:
------------------
-
-RT-mutexes extend the semantics of simple mutexes by the priority
-inheritance protocol.
-
-A low priority owner of a rt-mutex inherits the priority of a higher
-priority waiter until the rt-mutex is released. If the temporarily
-boosted owner blocks on a rt-mutex itself it propagates the priority
-boosting to the owner of the other rt_mutex it gets blocked on. The
-priority boosting is immediately removed once the rt_mutex has been
-unlocked.
-
-This approach allows us to shorten the block of high-prio tasks on
-mutexes which protect shared resources. Priority inheritance is not a
-magic bullet for poorly designed applications, but it allows
-well-designed applications to use userspace locks in critical parts of
-an high priority thread, without losing determinism.
-
-The enqueueing of the waiters into the rtmutex waiter list is done in
-priority order. For same priorities FIFO order is chosen. For each
-rtmutex, only the top priority waiter is enqueued into the owner's
-priority waiters list. This list too queues in priority order. Whenever
-the top priority waiter of a task changes (for example it timed out or
-got a signal), the priority of the owner task is readjusted. [The
-priority enqueueing is handled by "plists", see include/linux/plist.h
-for more details.]
-
-RT-mutexes are optimized for fastpath operations and have no internal
-locking overhead when locking an uncontended mutex or unlocking a mutex
-without waiters. The optimized fastpath operations require cmpxchg
-support. [If that is not available then the rt-mutex internal spinlock
-is used]
-
-The state of the rt-mutex is tracked via the owner field of the rt-mutex
-structure:
-
-rt_mutex->owner holds the task_struct pointer of the owner. Bit 0 and 1
-are used to keep track of the "owner is pending" and "rtmutex has
-waiters" state.
-
- owner		bit1	bit0
- NULL		0	0	mutex is free (fast acquire possible)
- NULL		0	1	invalid state
- NULL		1	0	Transitional state*
- NULL		1	1	invalid state
- taskpointer	0	0	mutex is held (fast release possible)
- taskpointer	0	1	task is pending owner
- taskpointer	1	0	mutex is held and has waiters
- taskpointer	1	1	task is pending owner and mutex has waiters
-
-Pending-ownership handling is a performance optimization:
-pending-ownership is assigned to the first (highest priority) waiter of
-the mutex, when the mutex is released. The thread is woken up and once
-it starts executing it can acquire the mutex. Until the mutex is taken
-by it (bit 0 is cleared) a competing higher priority thread can "steal"
-the mutex which puts the woken up thread back on the waiters list.
-
-The pending-ownership optimization is especially important for the
-uninterrupted workflow of high-prio tasks which repeatedly
-takes/releases locks that have lower-prio waiters. Without this
-optimization the higher-prio thread would ping-pong to the lower-prio
-task [because at unlock time we always assign a new owner].
-
-(*) The "mutex has waiters" bit gets set to take the lock. If the lock
-doesn't already have an owner, this bit is quickly cleared if there are
-no waiters.  So this is a transitional state to synchronize with looking
-at the owner field of the mutex and the mutex owner releasing the lock.
diff --git a/Documentation/spinlocks.txt b/Documentation/spinlocks.txt
deleted file mode 100644
index 97eaf5727178..000000000000
--- a/Documentation/spinlocks.txt
+++ /dev/null
@@ -1,167 +0,0 @@
-Lesson 1: Spin locks
-
-The most basic primitive for locking is spinlock.
-
-static DEFINE_SPINLOCK(xxx_lock);
-
-	unsigned long flags;
-
-	spin_lock_irqsave(&xxx_lock, flags);
-	... critical section here ..
-	spin_unlock_irqrestore(&xxx_lock, flags);
-
-The above is always safe. It will disable interrupts _locally_, but the
-spinlock itself will guarantee the global lock, so it will guarantee that
-there is only one thread-of-control within the region(s) protected by that
-lock. This works well even under UP also, so the code does _not_ need to
-worry about UP vs SMP issues: the spinlocks work correctly under both.
-
-   NOTE! Implications of spin_locks for memory are further described in:
-
-     Documentation/memory-barriers.txt
-       (5) LOCK operations.
-       (6) UNLOCK operations.
-
-The above is usually pretty simple (you usually need and want only one
-spinlock for most things - using more than one spinlock can make things a
-lot more complex and even slower and is usually worth it only for
-sequences that you _know_ need to be split up: avoid it at all cost if you
-aren't sure).
-
-This is really the only really hard part about spinlocks: once you start
-using spinlocks they tend to expand to areas you might not have noticed
-before, because you have to make sure the spinlocks correctly protect the
-shared data structures _everywhere_ they are used. The spinlocks are most
-easily added to places that are completely independent of other code (for
-example, internal driver data structures that nobody else ever touches).
-
-   NOTE! The spin-lock is safe only when you _also_ use the lock itself
-   to do locking across CPU's, which implies that EVERYTHING that
-   touches a shared variable has to agree about the spinlock they want
-   to use.
-
-----
-
-Lesson 2: reader-writer spinlocks.
-
-If your data accesses have a very natural pattern where you usually tend
-to mostly read from the shared variables, the reader-writer locks
-(rw_lock) versions of the spinlocks are sometimes useful. They allow multiple
-readers to be in the same critical region at once, but if somebody wants
-to change the variables it has to get an exclusive write lock.
-
-   NOTE! reader-writer locks require more atomic memory operations than
-   simple spinlocks.  Unless the reader critical section is long, you
-   are better off just using spinlocks.
-
-The routines look the same as above:
-
-   rwlock_t xxx_lock = __RW_LOCK_UNLOCKED(xxx_lock);
-
-	unsigned long flags;
-
-	read_lock_irqsave(&xxx_lock, flags);
-	.. critical section that only reads the info ...
-	read_unlock_irqrestore(&xxx_lock, flags);
-
-	write_lock_irqsave(&xxx_lock, flags);
-	.. read and write exclusive access to the info ...
-	write_unlock_irqrestore(&xxx_lock, flags);
-
-The above kind of lock may be useful for complex data structures like
-linked lists, especially searching for entries without changing the list
-itself.  The read lock allows many concurrent readers.  Anything that
-_changes_ the list will have to get the write lock.
-
-   NOTE! RCU is better for list traversal, but requires careful
-   attention to design detail (see Documentation/RCU/listRCU.txt).
-
-Also, you cannot "upgrade" a read-lock to a write-lock, so if you at _any_
-time need to do any changes (even if you don't do it every time), you have
-to get the write-lock at the very beginning.
-
-   NOTE! We are working hard to remove reader-writer spinlocks in most
-   cases, so please don't add a new one without consensus.  (Instead, see
-   Documentation/RCU/rcu.txt for complete information.)
-
-----
-
-Lesson 3: spinlocks revisited.
-
-The single spin-lock primitives above are by no means the only ones. They
-are the most safe ones, and the ones that work under all circumstances,
-but partly _because_ they are safe they are also fairly slow. They are slower
-than they'd need to be, because they do have to disable interrupts
-(which is just a single instruction on a x86, but it's an expensive one -
-and on other architectures it can be worse).
-
-If you have a case where you have to protect a data structure across
-several CPU's and you want to use spinlocks you can potentially use
-cheaper versions of the spinlocks. IFF you know that the spinlocks are
-never used in interrupt handlers, you can use the non-irq versions:
-
-	spin_lock(&lock);
-	...
-	spin_unlock(&lock);
-
-(and the equivalent read-write versions too, of course). The spinlock will
-guarantee the same kind of exclusive access, and it will be much faster. 
-This is useful if you know that the data in question is only ever
-manipulated from a "process context", ie no interrupts involved. 
-
-The reasons you mustn't use these versions if you have interrupts that
-play with the spinlock is that you can get deadlocks:
-
-	spin_lock(&lock);
-	...
-		<- interrupt comes in:
-			spin_lock(&lock);
-
-where an interrupt tries to lock an already locked variable. This is ok if
-the other interrupt happens on another CPU, but it is _not_ ok if the
-interrupt happens on the same CPU that already holds the lock, because the
-lock will obviously never be released (because the interrupt is waiting
-for the lock, and the lock-holder is interrupted by the interrupt and will
-not continue until the interrupt has been processed). 
-
-(This is also the reason why the irq-versions of the spinlocks only need
-to disable the _local_ interrupts - it's ok to use spinlocks in interrupts
-on other CPU's, because an interrupt on another CPU doesn't interrupt the
-CPU that holds the lock, so the lock-holder can continue and eventually
-releases the lock). 
-
-Note that you can be clever with read-write locks and interrupts. For
-example, if you know that the interrupt only ever gets a read-lock, then
-you can use a non-irq version of read locks everywhere - because they
-don't block on each other (and thus there is no dead-lock wrt interrupts. 
-But when you do the write-lock, you have to use the irq-safe version. 
-
-For an example of being clever with rw-locks, see the "waitqueue_lock" 
-handling in kernel/sched/core.c - nothing ever _changes_ a wait-queue from
-within an interrupt, they only read the queue in order to know whom to
-wake up. So read-locks are safe (which is good: they are very common
-indeed), while write-locks need to protect themselves against interrupts.
-
-		Linus
-
-----
-
-Reference information:
-
-For dynamic initialization, use spin_lock_init() or rwlock_init() as
-appropriate:
-
-   spinlock_t xxx_lock;
-   rwlock_t xxx_rw_lock;
-
-   static int __init xxx_init(void)
-   {
-	spin_lock_init(&xxx_lock);
-	rwlock_init(&xxx_rw_lock);
-	...
-   }
-
-   module_init(xxx_init);
-
-For static initialization, use DEFINE_SPINLOCK() / DEFINE_RWLOCK() or
-__SPIN_LOCK_UNLOCKED() / __RW_LOCK_UNLOCKED() as appropriate.
diff --git a/Documentation/ww-mutex-design.txt b/Documentation/ww-mutex-design.txt
deleted file mode 100644
index 8a112dc304c3..000000000000
--- a/Documentation/ww-mutex-design.txt
+++ /dev/null
@@ -1,344 +0,0 @@
-Wait/Wound Deadlock-Proof Mutex Design
-======================================
-
-Please read mutex-design.txt first, as it applies to wait/wound mutexes too.
-
-Motivation for WW-Mutexes
--------------------------
-
-GPU's do operations that commonly involve many buffers.  Those buffers
-can be shared across contexts/processes, exist in different memory
-domains (for example VRAM vs system memory), and so on.  And with
-PRIME / dmabuf, they can even be shared across devices.  So there are
-a handful of situations where the driver needs to wait for buffers to
-become ready.  If you think about this in terms of waiting on a buffer
-mutex for it to become available, this presents a problem because
-there is no way to guarantee that buffers appear in a execbuf/batch in
-the same order in all contexts.  That is directly under control of
-userspace, and a result of the sequence of GL calls that an application
-makes.	Which results in the potential for deadlock.  The problem gets
-more complex when you consider that the kernel may need to migrate the
-buffer(s) into VRAM before the GPU operates on the buffer(s), which
-may in turn require evicting some other buffers (and you don't want to
-evict other buffers which are already queued up to the GPU), but for a
-simplified understanding of the problem you can ignore this.
-
-The algorithm that the TTM graphics subsystem came up with for dealing with
-this problem is quite simple.  For each group of buffers (execbuf) that need
-to be locked, the caller would be assigned a unique reservation id/ticket,
-from a global counter.  In case of deadlock while locking all the buffers
-associated with a execbuf, the one with the lowest reservation ticket (i.e.
-the oldest task) wins, and the one with the higher reservation id (i.e. the
-younger task) unlocks all of the buffers that it has already locked, and then
-tries again.
-
-In the RDBMS literature this deadlock handling approach is called wait/wound:
-The older tasks waits until it can acquire the contended lock. The younger tasks
-needs to back off and drop all the locks it is currently holding, i.e. the
-younger task is wounded.
-
-Concepts
---------
-
-Compared to normal mutexes two additional concepts/objects show up in the lock
-interface for w/w mutexes:
-
-Acquire context: To ensure eventual forward progress it is important the a task
-trying to acquire locks doesn't grab a new reservation id, but keeps the one it
-acquired when starting the lock acquisition. This ticket is stored in the
-acquire context. Furthermore the acquire context keeps track of debugging state
-to catch w/w mutex interface abuse.
-
-W/w class: In contrast to normal mutexes the lock class needs to be explicit for
-w/w mutexes, since it is required to initialize the acquire context.
-
-Furthermore there are three different class of w/w lock acquire functions:
-
-* Normal lock acquisition with a context, using ww_mutex_lock.
-
-* Slowpath lock acquisition on the contending lock, used by the wounded task
-  after having dropped all already acquired locks. These functions have the
-  _slow postfix.
-
-  From a simple semantics point-of-view the _slow functions are not strictly
-  required, since simply calling the normal ww_mutex_lock functions on the
-  contending lock (after having dropped all other already acquired locks) will
-  work correctly. After all if no other ww mutex has been acquired yet there's
-  no deadlock potential and hence the ww_mutex_lock call will block and not
-  prematurely return -EDEADLK. The advantage of the _slow functions is in
-  interface safety:
-  - ww_mutex_lock has a __must_check int return type, whereas ww_mutex_lock_slow
-    has a void return type. Note that since ww mutex code needs loops/retries
-    anyway the __must_check doesn't result in spurious warnings, even though the
-    very first lock operation can never fail.
-  - When full debugging is enabled ww_mutex_lock_slow checks that all acquired
-    ww mutex have been released (preventing deadlocks) and makes sure that we
-    block on the contending lock (preventing spinning through the -EDEADLK
-    slowpath until the contended lock can be acquired).
-
-* Functions to only acquire a single w/w mutex, which results in the exact same
-  semantics as a normal mutex. This is done by calling ww_mutex_lock with a NULL
-  context.
-
-  Again this is not strictly required. But often you only want to acquire a
-  single lock in which case it's pointless to set up an acquire context (and so
-  better to avoid grabbing a deadlock avoidance ticket).
-
-Of course, all the usual variants for handling wake-ups due to signals are also
-provided.
-
-Usage
------
-
-Three different ways to acquire locks within the same w/w class. Common
-definitions for methods #1 and #2:
-
-static DEFINE_WW_CLASS(ww_class);
-
-struct obj {
-	struct ww_mutex lock;
-	/* obj data */
-};
-
-struct obj_entry {
-	struct list_head head;
-	struct obj *obj;
-};
-
-Method 1, using a list in execbuf->buffers that's not allowed to be reordered.
-This is useful if a list of required objects is already tracked somewhere.
-Furthermore the lock helper can use propagate the -EALREADY return code back to
-the caller as a signal that an object is twice on the list. This is useful if
-the list is constructed from userspace input and the ABI requires userspace to
-not have duplicate entries (e.g. for a gpu commandbuffer submission ioctl).
-
-int lock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
-{
-	struct obj *res_obj = NULL;
-	struct obj_entry *contended_entry = NULL;
-	struct obj_entry *entry;
-
-	ww_acquire_init(ctx, &ww_class);
-
-retry:
-	list_for_each_entry (entry, list, head) {
-		if (entry->obj == res_obj) {
-			res_obj = NULL;
-			continue;
-		}
-		ret = ww_mutex_lock(&entry->obj->lock, ctx);
-		if (ret < 0) {
-			contended_entry = entry;
-			goto err;
-		}
-	}
-
-	ww_acquire_done(ctx);
-	return 0;
-
-err:
-	list_for_each_entry_continue_reverse (entry, list, head)
-		ww_mutex_unlock(&entry->obj->lock);
-
-	if (res_obj)
-		ww_mutex_unlock(&res_obj->lock);
-
-	if (ret == -EDEADLK) {
-		/* we lost out in a seqno race, lock and retry.. */
-		ww_mutex_lock_slow(&contended_entry->obj->lock, ctx);
-		res_obj = contended_entry->obj;
-		goto retry;
-	}
-	ww_acquire_fini(ctx);
-
-	return ret;
-}
-
-Method 2, using a list in execbuf->buffers that can be reordered. Same semantics
-of duplicate entry detection using -EALREADY as method 1 above. But the
-list-reordering allows for a bit more idiomatic code.
-
-int lock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
-{
-	struct obj_entry *entry, *entry2;
-
-	ww_acquire_init(ctx, &ww_class);
-
-	list_for_each_entry (entry, list, head) {
-		ret = ww_mutex_lock(&entry->obj->lock, ctx);
-		if (ret < 0) {
-			entry2 = entry;
-
-			list_for_each_entry_continue_reverse (entry2, list, head)
-				ww_mutex_unlock(&entry2->obj->lock);
-
-			if (ret != -EDEADLK) {
-				ww_acquire_fini(ctx);
-				return ret;
-			}
-
-			/* we lost out in a seqno race, lock and retry.. */
-			ww_mutex_lock_slow(&entry->obj->lock, ctx);
-
-			/*
-			 * Move buf to head of the list, this will point
-			 * buf->next to the first unlocked entry,
-			 * restarting the for loop.
-			 */
-			list_del(&entry->head);
-			list_add(&entry->head, list);
-		}
-	}
-
-	ww_acquire_done(ctx);
-	return 0;
-}
-
-Unlocking works the same way for both methods #1 and #2:
-
-void unlock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
-{
-	struct obj_entry *entry;
-
-	list_for_each_entry (entry, list, head)
-		ww_mutex_unlock(&entry->obj->lock);
-
-	ww_acquire_fini(ctx);
-}
-
-Method 3 is useful if the list of objects is constructed ad-hoc and not upfront,
-e.g. when adjusting edges in a graph where each node has its own ww_mutex lock,
-and edges can only be changed when holding the locks of all involved nodes. w/w
-mutexes are a natural fit for such a case for two reasons:
-- They can handle lock-acquisition in any order which allows us to start walking
-  a graph from a starting point and then iteratively discovering new edges and
-  locking down the nodes those edges connect to.
-- Due to the -EALREADY return code signalling that a given objects is already
-  held there's no need for additional book-keeping to break cycles in the graph
-  or keep track off which looks are already held (when using more than one node
-  as a starting point).
-
-Note that this approach differs in two important ways from the above methods:
-- Since the list of objects is dynamically constructed (and might very well be
-  different when retrying due to hitting the -EDEADLK wound condition) there's
-  no need to keep any object on a persistent list when it's not locked. We can
-  therefore move the list_head into the object itself.
-- On the other hand the dynamic object list construction also means that the -EALREADY return
-  code can't be propagated.
-
-Note also that methods #1 and #2 and method #3 can be combined, e.g. to first lock a
-list of starting nodes (passed in from userspace) using one of the above
-methods. And then lock any additional objects affected by the operations using
-method #3 below. The backoff/retry procedure will be a bit more involved, since
-when the dynamic locking step hits -EDEADLK we also need to unlock all the
-objects acquired with the fixed list. But the w/w mutex debug checks will catch
-any interface misuse for these cases.
-
-Also, method 3 can't fail the lock acquisition step since it doesn't return
--EALREADY. Of course this would be different when using the _interruptible
-variants, but that's outside of the scope of these examples here.
-
-struct obj {
-	struct ww_mutex ww_mutex;
-	struct list_head locked_list;
-};
-
-static DEFINE_WW_CLASS(ww_class);
-
-void __unlock_objs(struct list_head *list)
-{
-	struct obj *entry, *temp;
-
-	list_for_each_entry_safe (entry, temp, list, locked_list) {
-		/* need to do that before unlocking, since only the current lock holder is
-		allowed to use object */
-		list_del(&entry->locked_list);
-		ww_mutex_unlock(entry->ww_mutex)
-	}
-}
-
-void lock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
-{
-	struct obj *obj;
-
-	ww_acquire_init(ctx, &ww_class);
-
-retry:
-	/* re-init loop start state */
-	loop {
-		/* magic code which walks over a graph and decides which objects
-		 * to lock */
-
-		ret = ww_mutex_lock(obj->ww_mutex, ctx);
-		if (ret == -EALREADY) {
-			/* we have that one already, get to the next object */
-			continue;
-		}
-		if (ret == -EDEADLK) {
-			__unlock_objs(list);
-
-			ww_mutex_lock_slow(obj, ctx);
-			list_add(&entry->locked_list, list);
-			goto retry;
-		}
-
-		/* locked a new object, add it to the list */
-		list_add_tail(&entry->locked_list, list);
-	}
-
-	ww_acquire_done(ctx);
-	return 0;
-}
-
-void unlock_objs(struct list_head *list, struct ww_acquire_ctx *ctx)
-{
-	__unlock_objs(list);
-	ww_acquire_fini(ctx);
-}
-
-Method 4: Only lock one single objects. In that case deadlock detection and
-prevention is obviously overkill, since with grabbing just one lock you can't
-produce a deadlock within just one class. To simplify this case the w/w mutex
-api can be used with a NULL context.
-
-Implementation Details
-----------------------
-
-Design:
-  ww_mutex currently encapsulates a struct mutex, this means no extra overhead for
-  normal mutex locks, which are far more common. As such there is only a small
-  increase in code size if wait/wound mutexes are not used.
-
-  In general, not much contention is expected. The locks are typically used to
-  serialize access to resources for devices. The only way to make wakeups
-  smarter would be at the cost of adding a field to struct mutex_waiter. This
-  would add overhead to all cases where normal mutexes are used, and
-  ww_mutexes are generally less performance sensitive.
-
-Lockdep:
-  Special care has been taken to warn for as many cases of api abuse
-  as possible. Some common api abuses will be caught with
-  CONFIG_DEBUG_MUTEXES, but CONFIG_PROVE_LOCKING is recommended.
-
-  Some of the errors which will be warned about:
-   - Forgetting to call ww_acquire_fini or ww_acquire_init.
-   - Attempting to lock more mutexes after ww_acquire_done.
-   - Attempting to lock the wrong mutex after -EDEADLK and
-     unlocking all mutexes.
-   - Attempting to lock the right mutex after -EDEADLK,
-     before unlocking all mutexes.
-
-   - Calling ww_mutex_lock_slow before -EDEADLK was returned.
-
-   - Unlocking mutexes with the wrong unlock function.
-   - Calling one of the ww_acquire_* twice on the same context.
-   - Using a different ww_class for the mutex than for the ww_acquire_ctx.
-   - Normal lockdep errors that can result in deadlocks.
-
-  Some of the lockdep errors that can result in deadlocks:
-   - Calling ww_acquire_init to initialize a second ww_acquire_ctx before
-     having called ww_acquire_fini on the first.
-   - 'normal' deadlocks that can occur.
-
-FIXME: Update this section once we have the TASK_DEADLOCK task state flag magic
-implemented.
diff --git a/MAINTAINERS b/MAINTAINERS
index 1acc624ecfd7..aac481fcbf5c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5523,8 +5523,8 @@ M:	Ingo Molnar <mingo@redhat.com>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/locking
 S:	Maintained
-F:	Documentation/lockdep*.txt
-F:	Documentation/lockstat.txt
+F:	Documentation/locking/lockdep*.txt
+F:	Documentation/locking/lockstat.txt
 F:	include/linux/lockdep.h
 F:	kernel/locking/
 
diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
index 0dc57d5ecd10..3a02e5e3e9f3 100644
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -35,7 +35,7 @@
  * of extra utility/tracking out of our acquire-ctx.  This is provided
  * by drm_modeset_lock / drm_modeset_acquire_ctx.
  *
- * For basic principles of ww_mutex, see: Documentation/ww-mutex-design.txt
+ * For basic principles of ww_mutex, see: Documentation/locking/ww-mutex-design.txt
  *
  * The basic usage pattern is to:
  *
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 008388f920d7..f388481201cd 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -4,7 +4,7 @@
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
  *
- * see Documentation/lockdep-design.txt for more details.
+ * see Documentation/locking/lockdep-design.txt for more details.
  */
 #ifndef __LINUX_LOCKDEP_H
 #define __LINUX_LOCKDEP_H
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index e4c29418f407..cc31498fc526 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -133,7 +133,7 @@ static inline int mutex_is_locked(struct mutex *lock)
 
 /*
  * See kernel/locking/mutex.c for detailed documentation of these APIs.
- * Also see Documentation/mutex-design.txt.
+ * Also see Documentation/locking/mutex-design.txt.
  */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 035d3c57fc8a..8f498cdde280 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -149,7 +149,7 @@ extern void downgrade_write(struct rw_semaphore *sem);
  * static then another method for expressing nested locking is
  * the explicit definition of lock class keys and the use of
  * lockdep_set_class() at lock initialization time.
- * See Documentation/lockdep-design.txt for more details.)
+ * See Documentation/locking/lockdep-design.txt for more details.)
  */
 extern void down_read_nested(struct rw_semaphore *sem, int subclass);
 extern void down_write_nested(struct rw_semaphore *sem, int subclass);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 0d8b6ed93874..dadbf88c22c4 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -15,7 +15,7 @@
  *    by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale
  *    and Sven Dietrich.
  *
- * Also see Documentation/mutex-design.txt.
+ * Also see Documentation/locking/mutex-design.txt.
  */
 #include <linux/mutex.h>
 #include <linux/ww_mutex.h>
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index a0ea2a141b3b..7c98873a3077 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -8,7 +8,7 @@
  *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
  *  Copyright (C) 2006 Esben Nielsen
  *
- *  See Documentation/rt-mutex-design.txt for details.
+ *  See Documentation/locking/rt-mutex-design.txt for details.
  */
 #include <linux/spinlock.h>
 #include <linux/export.h>
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 901096d31c66..9b94a063e26c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -924,7 +924,7 @@ config PROVE_LOCKING
 	 the proof of observed correctness is also maintained for an
 	 arbitrary combination of these separate locking variants.
 
-	 For more details, see Documentation/lockdep-design.txt.
+	 For more details, see Documentation/locking/lockdep-design.txt.
 
 config LOCKDEP
 	bool
@@ -945,7 +945,7 @@ config LOCK_STAT
 	help
 	 This feature enables tracking lock contention points
 
-	 For more details, see Documentation/lockstat.txt
+	 For more details, see Documentation/locking/lockstat.txt
 
 	 This also enables lock events required by "perf lock",
 	 subcommand of perf.
-- 
cgit v1.2.3


From 4999201a59ef555f9105d2bb2459ed895627f7aa Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Fri, 8 Aug 2014 12:35:36 +0200
Subject: locking/spinlocks: Always evaluate the second argument of
 spin_lock_nested()

Evaluating a macro argument only if certain configuration options
have been selected is confusing and error-prone. Hence always
evaluate the second argument of spin_lock_nested().

An intentional side effect of this patch is that it avoids that
the following warning is reported for netif_addr_lock_nested()
when building with CONFIG_DEBUG_LOCK_ALLOC=n and with W=1:

  include/linux/netdevice.h: In function 'netif_addr_lock_nested':
  include/linux/netdevice.h:2865:6: warning: variable 'subclass' set but not used [-Wunused-but-set-variable]
    int subclass = SINGLE_DEPTH_NESTING;
        ^

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: David Rientjes <rientjes@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/53E4A7F8.1040700@acm.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/spinlock.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 3f2867ff0ced..262ba4ef9a8e 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -197,7 +197,13 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 		 _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map);	\
 	 } while (0)
 #else
-# define raw_spin_lock_nested(lock, subclass)		_raw_spin_lock(lock)
+/*
+ * Always evaluate the 'subclass' argument to avoid that the compiler
+ * warns about set-but-not-used variables when building with
+ * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1.
+ */
+# define raw_spin_lock_nested(lock, subclass)		\
+	_raw_spin_lock(((void)(subclass), (lock)))
 # define raw_spin_lock_nest_lock(lock, nest_lock)	_raw_spin_lock(lock)
 #endif
 
-- 
cgit v1.2.3


From f0bab73cb539fb803c4d419951e8d28aa4964f8f Mon Sep 17 00:00:00 2001
From: Waiman Long <Waiman.Long@hp.com>
Date: Wed, 6 Aug 2014 13:22:01 -0400
Subject: locking/lockdep: Restrict the use of recursive read_lock() with
 qrwlock

Unlike the original unfair rwlock implementation, queued rwlock
will grant lock according to the chronological sequence of the lock
requests except when the lock requester is in the interrupt context.
Consequently, recursive read_lock calls will now hang the process if
there is a write_lock call somewhere in between the read_lock calls.

This patch updates the lockdep implementation to look for recursive
read_lock calls. A new read state (3) is used to mark those read_lock
call that cannot be recursively called except in the interrupt
context. The new read state does exhaust the 2 bits available in
held_lock:read bit field. The addition of any new read state in the
future may require a redesign of how all those bits are squeezed
together in the held_lock structure.

Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1407345722-61615-2-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/lockdep.h  | 10 +++++++++-
 kernel/locking/lockdep.c |  6 ++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index f388481201cd..b5a84b62fb84 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -478,16 +478,24 @@ static inline void print_irqtrace_events(struct task_struct *curr)
  * on the per lock-class debug mode:
  */
 
+/*
+ * Read states in the 2-bit held_lock:read field:
+ *  0: Exclusive lock
+ *  1: Shareable lock, cannot be recursively called
+ *  2: Shareable lock, can be recursively called
+ *  3: Shareable lock, cannot be recursively called except in interrupt context
+ */
 #define lock_acquire_exclusive(l, s, t, n, i)		lock_acquire(l, s, t, 0, 1, n, i)
 #define lock_acquire_shared(l, s, t, n, i)		lock_acquire(l, s, t, 1, 1, n, i)
 #define lock_acquire_shared_recursive(l, s, t, n, i)	lock_acquire(l, s, t, 2, 1, n, i)
+#define lock_acquire_shared_irecursive(l, s, t, n, i)	lock_acquire(l, s, t, 3, 1, n, i)
 
 #define spin_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define spin_acquire_nest(l, s, t, n, i)	lock_acquire_exclusive(l, s, t, n, i)
 #define spin_release(l, n, i)			lock_release(l, n, i)
 
 #define rwlock_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
-#define rwlock_acquire_read(l, s, t, i)		lock_acquire_shared_recursive(l, s, t, NULL, i)
+#define rwlock_acquire_read(l, s, t, i)		lock_acquire_shared_irecursive(l, s, t, NULL, i)
 #define rwlock_release(l, n, i)			lock_release(l, n, i)
 
 #define seqcount_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 88d0d4420ad2..420ba685c4e5 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3597,6 +3597,12 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
+	/*
+	 * An interrupt recursive read in interrupt context can be considered
+	 * to be the same as a recursive read from checking perspective.
+	 */
+	if ((read == 3) && in_interrupt())
+		read = 2;
 	current->lockdep_recursion = 1;
 	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 	__lock_acquire(lock, subclass, trylock, read, check,
-- 
cgit v1.2.3


From 2c67568903d6ae1b8cfa343c649029180239418e Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 8 Aug 2014 13:02:36 +0200
Subject: spi: Add missing kerneldoc bits

These are all arguments or fields that got added without updating the
kerneldoc comments.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/spi/spi.c       | 1 +
 include/linux/spi/spi.h | 7 +++++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index e6f076d5ffd5..f52f3e647ef8 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -843,6 +843,7 @@ out:
 
 /**
  * spi_finalize_current_transfer - report completion of a transfer
+ * @master: the master reporting completion
  *
  * Called by SPI drivers using the core transfer_one_message()
  * implementation to notify it that the current interrupt driven
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index e713543336f1..46d188a9947c 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -253,6 +253,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  *	the device whose settings are being modified.
  * @transfer: adds a message to the controller's transfer queue.
  * @cleanup: frees controller-specific state
+ * @can_dma: determine whether this master supports DMA
  * @queued: whether this master is providing an internal message queue
  * @kworker: thread struct for message pump
  * @kworker_task: pointer to task for message pump kworker thread
@@ -262,6 +263,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @cur_msg: the currently in-flight message
  * @cur_msg_prepared: spi_prepare_message was called for the currently
  *                    in-flight message
+ * @cur_msg_mapped: message has been mapped for DMA
  * @xfer_completion: used by core transfer_one_message()
  * @busy: message pump is busy
  * @running: message pump is running
@@ -299,6 +301,10 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
  *	number. Any individual value may be -ENOENT for CS lines that
  *	are not GPIOs (driven by the SPI controller itself).
+ * @dma_tx: DMA transmit channel
+ * @dma_rx: DMA receive channel
+ * @dummy_rx: dummy receive buffer for full-duplex devices
+ * @dummy_tx: dummy transmit buffer for full-duplex devices
  *
  * Each SPI master controller can communicate with one or more @spi_device
  * children.  These make a small bus, sharing MOSI, MISO and SCK signals
@@ -632,6 +638,7 @@ struct spi_transfer {
  *	addresses for each transfer buffer
  * @complete: called to report transaction completions
  * @context: the argument to complete() when it's called
+ * @frame_length: the total number of bytes in the message
  * @actual_length: the total number of bytes that were transferred in all
  *	successful segments
  * @status: zero for success, else negative errno
-- 
cgit v1.2.3


From 84c61d92bb6e9048eecc0738a83f1bf66f053026 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 1 Aug 2014 11:13:30 +0300
Subject: Bluetooth: Add convenience function to check for pending power off

There are several situations where we're interested in knowing whether
we're currently in the process of powering off an adapter. This patch
adds a convenience function for the purpose and makes it public since
we'll soon need to access it from hci_event.c as well.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/mgmt.c             | 52 +++++++++++++++++++++-------------------
 2 files changed, 29 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b5d5af3aa469..8394abc4fd87 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1351,6 +1351,7 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, s8 rssi, u8 *name, u8 name_len);
 void mgmt_discovering(struct hci_dev *hdev, u8 discovering);
+bool mgmt_powering_down(struct hci_dev *hdev);
 void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent);
 void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk);
 void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index b8554d429d88..c9de0d9945f5 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -6281,25 +6281,35 @@ static void unpair_device_rsp(struct pending_cmd *cmd, void *data)
 	mgmt_pending_remove(cmd);
 }
 
+bool mgmt_powering_down(struct hci_dev *hdev)
+{
+	struct pending_cmd *cmd;
+	struct mgmt_mode *cp;
+
+	cmd = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev);
+	if (!cmd)
+		return false;
+
+	cp = cmd->param;
+	if (!cp->val)
+		return true;
+
+	return false;
+}
+
 void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			      u8 link_type, u8 addr_type, u8 reason,
 			      bool mgmt_connected)
 {
 	struct mgmt_ev_device_disconnected ev;
-	struct pending_cmd *power_off;
 	struct sock *sk = NULL;
 
-	power_off = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev);
-	if (power_off) {
-		struct mgmt_mode *cp = power_off->param;
-
-		/* The connection is still in hci_conn_hash so test for 1
-		 * instead of 0 to know if this is the last one.
-		 */
-		if (!cp->val && hci_conn_count(hdev) == 1) {
-			cancel_delayed_work(&hdev->power_off);
-			queue_work(hdev->req_workqueue, &hdev->power_off.work);
-		}
+	/* The connection is still in hci_conn_hash so test for 1
+	 * instead of 0 to know if this is the last one.
+	 */
+	if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) {
+		cancel_delayed_work(&hdev->power_off);
+		queue_work(hdev->req_workqueue, &hdev->power_off.work);
 	}
 
 	if (!mgmt_connected)
@@ -6359,19 +6369,13 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			 u8 addr_type, u8 status)
 {
 	struct mgmt_ev_connect_failed ev;
-	struct pending_cmd *power_off;
-
-	power_off = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev);
-	if (power_off) {
-		struct mgmt_mode *cp = power_off->param;
 
-		/* The connection is still in hci_conn_hash so test for 1
-		 * instead of 0 to know if this is the last one.
-		 */
-		if (!cp->val && hci_conn_count(hdev) == 1) {
-			cancel_delayed_work(&hdev->power_off);
-			queue_work(hdev->req_workqueue, &hdev->power_off.work);
-		}
+	/* The connection is still in hci_conn_hash so test for 1
+	 * instead of 0 to know if this is the last one.
+	 */
+	if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) {
+		cancel_delayed_work(&hdev->power_off);
+		queue_work(hdev->req_workqueue, &hdev->power_off.work);
 	}
 
 	bacpy(&ev.addr.bdaddr, bdaddr);
-- 
cgit v1.2.3


From 432df05eb1e57adfc46df08abbedca6c3b8862f7 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 1 Aug 2014 11:13:31 +0300
Subject: Bluetooth: Create unified helper function for updating page scan

Similar to our hci_update_background_scan() function we can simplify a
lot of code by creating a unified helper function for doing page scan
updates. This patch adds such a function to hci_core.c and updates all
the relevant places to use it.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  5 +++
 net/bluetooth/hci_core.c         | 31 +++++++++++++++++
 net/bluetooth/mgmt.c             | 72 +++++++---------------------------------
 3 files changed, 48 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 8394abc4fd87..cc2eb7730fbc 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -968,6 +968,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_host_le_capable(dev)   (!!((dev)->features[1][0] & LMP_HOST_LE))
 #define lmp_host_le_br_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE_BREDR))
 
+#define hdev_is_powered(hdev) (test_bit(HCI_UP, &hdev->flags) && \
+				!test_bit(HCI_AUTO_OFF, &hdev->dev_flags))
+
 /* ----- HCI protocols ----- */
 #define HCI_PROTO_DEFER             0x01
 
@@ -1256,6 +1259,8 @@ bool hci_req_pending(struct hci_dev *hdev);
 void hci_req_add_le_scan_disable(struct hci_request *req);
 void hci_req_add_le_passive_scan(struct hci_request *req);
 
+void hci_update_page_scan(struct hci_dev *hdev, struct hci_request *req);
+
 struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen,
 			       const void *param, u32 timeout);
 struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen,
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index c32d361c0cf7..a031589598b2 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -5680,3 +5680,34 @@ void hci_update_background_scan(struct hci_dev *hdev)
 	if (err)
 		BT_ERR("Failed to run HCI request: err %d", err);
 }
+
+void hci_update_page_scan(struct hci_dev *hdev, struct hci_request *req)
+{
+	u8 scan;
+
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+		return;
+
+	if (!hdev_is_powered(hdev))
+		return;
+
+	if (mgmt_powering_down(hdev))
+		return;
+
+	if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags) ||
+	    !list_empty(&hdev->whitelist))
+		scan = SCAN_PAGE;
+	else
+		scan = SCAN_DISABLED;
+
+	if (test_bit(HCI_PSCAN, &hdev->flags) == !!(scan & SCAN_PAGE))
+		return;
+
+	if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags))
+		scan |= SCAN_INQUIRY;
+
+	if (req)
+		hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
+	else
+		hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
+}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index c9de0d9945f5..c2457435a670 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -129,9 +129,6 @@ static const u16 mgmt_events[] = {
 
 #define CACHE_TIMEOUT	msecs_to_jiffies(2 * 1000)
 
-#define hdev_is_powered(hdev) (test_bit(HCI_UP, &hdev->flags) && \
-				!test_bit(HCI_AUTO_OFF, &hdev->dev_flags))
-
 struct pending_cmd {
 	struct list_head list;
 	u16 opcode;
@@ -1536,9 +1533,11 @@ static void set_discoverable_complete(struct hci_dev *hdev, u8 status)
 
 	/* When the discoverable mode gets changed, make sure
 	 * that class of device has the limited discoverable
-	 * bit correctly set.
+	 * bit correctly set. Also update page scan based on whitelist
+	 * entries.
 	 */
 	hci_req_init(&req, hdev);
+	hci_update_page_scan(hdev, &req);
 	update_class(&req);
 	hci_req_run(&req, NULL);
 
@@ -1785,6 +1784,7 @@ static void set_connectable_complete(struct hci_dev *hdev, u8 status)
 
 	if (conn_changed || discov_changed) {
 		new_settings(hdev, cmd->sk);
+		hci_update_page_scan(hdev, NULL);
 		if (discov_changed)
 			mgmt_update_adv_data(hdev);
 		hci_update_background_scan(hdev);
@@ -1818,6 +1818,7 @@ static int set_connectable_update_settings(struct hci_dev *hdev,
 		return err;
 
 	if (changed) {
+		hci_update_page_scan(hdev, NULL);
 		hci_update_background_scan(hdev);
 		return new_settings(hdev, sk);
 	}
@@ -4381,27 +4382,6 @@ unlock:
 	return err;
 }
 
-static void set_bredr_scan(struct hci_request *req)
-{
-	struct hci_dev *hdev = req->hdev;
-	u8 scan = 0;
-
-	/* Ensure that fast connectable is disabled. This function will
-	 * not do anything if the page scan parameters are already what
-	 * they should be.
-	 */
-	write_fast_connectable(req, false);
-
-	if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags) ||
-	    !list_empty(&hdev->whitelist))
-		scan |= SCAN_PAGE;
-	if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags))
-		scan |= SCAN_INQUIRY;
-
-	if (scan)
-		hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
-}
-
 static void set_bredr_complete(struct hci_dev *hdev, u8 status)
 {
 	struct pending_cmd *cmd;
@@ -4507,9 +4487,8 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	hci_req_init(&req, hdev);
 
-	if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags) ||
-	    !list_empty(&hdev->whitelist))
-		set_bredr_scan(&req);
+	write_fast_connectable(&req, false);
+	hci_update_page_scan(hdev, &req);
 
 	/* Since only the advertising data flags will change, there
 	 * is no need to update the scan response data.
@@ -5235,27 +5214,6 @@ unlock:
 	return err;
 }
 
-/* Helper for Add/Remove Device commands */
-static void update_page_scan(struct hci_dev *hdev, u8 scan)
-{
-	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
-		return;
-
-	if (!hdev_is_powered(hdev))
-		return;
-
-	/* If HCI_CONNECTABLE is set then Add/Remove Device should not
-	 * make any changes to page scanning.
-	 */
-	if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags))
-		return;
-
-	if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags))
-		scan |= SCAN_INQUIRY;
-
-	hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
-}
-
 static void device_added(struct sock *sk, struct hci_dev *hdev,
 			 bdaddr_t *bdaddr, u8 type, u8 action)
 {
@@ -5291,8 +5249,6 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 	hci_dev_lock(hdev);
 
 	if (cp->addr.type == BDADDR_BREDR) {
-		bool update_scan;
-
 		/* Only incoming connections action is supported for now */
 		if (cp->action != 0x01) {
 			err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
@@ -5301,15 +5257,12 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 			goto unlock;
 		}
 
-		update_scan = list_empty(&hdev->whitelist);
-
 		err = hci_bdaddr_list_add(&hdev->whitelist, &cp->addr.bdaddr,
 					  cp->addr.type);
 		if (err)
 			goto unlock;
 
-		if (update_scan)
-			update_page_scan(hdev, SCAN_PAGE);
+		hci_update_page_scan(hdev, NULL);
 
 		goto added;
 	}
@@ -5392,8 +5345,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev,
 				goto unlock;
 			}
 
-			if (list_empty(&hdev->whitelist))
-				update_page_scan(hdev, SCAN_DISABLED);
+			hci_update_page_scan(hdev, NULL);
 
 			device_removed(sk, hdev, &cp->addr.bdaddr,
 				       cp->addr.type);
@@ -5444,7 +5396,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev,
 			kfree(b);
 		}
 
-		update_page_scan(hdev, SCAN_DISABLED);
+		hci_update_page_scan(hdev, NULL);
 
 		list_for_each_entry_safe(p, tmp, &hdev->le_conn_params, list) {
 			if (p->auto_connect == HCI_AUTO_CONN_DISABLED)
@@ -5969,8 +5921,8 @@ static int powered_update_hci(struct hci_dev *hdev)
 			    sizeof(link_sec), &link_sec);
 
 	if (lmp_bredr_capable(hdev)) {
-		if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
-			set_bredr_scan(&req);
+		write_fast_connectable(&req, false);
+		hci_update_page_scan(hdev, &req);
 		update_class(&req);
 		update_name(&req);
 		update_eir(&req);
-- 
cgit v1.2.3


From d52deb17489b8155e031fb1a9f116c602d719e11 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Thu, 7 Aug 2014 22:56:44 +0300
Subject: Bluetooth: Resume BT_CONNECTED state after LE security elevation

The LE ATT socket uses a special trick where it temporarily sets
BT_CONFIG state for the duration of a security level elevation. In order
to not require special hacks for going back to BT_CONNECTED state in the
l2cap_core.c code the most reasonable place to resume the state is the
resume callback. This patch adds a new flag to track the pending
security level change and ensures that the state is set back to
BT_CONNECTED in the resume callback in case the flag is set.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h | 1 +
 net/bluetooth/l2cap_sock.c    | 6 ++++++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 8df15ad0d43f..4a51e7596608 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -708,6 +708,7 @@ enum {
 	FLAG_EFS_ENABLE,
 	FLAG_DEFER_SETUP,
 	FLAG_LE_CONN_REQ_SENT,
+	FLAG_PENDING_SECURITY,
 };
 
 enum {
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 1884f72083c2..5a42f6a818c0 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -790,6 +790,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 		if (chan->scid == L2CAP_CID_ATT) {
 			if (smp_conn_security(conn->hcon, sec.level))
 				break;
+			set_bit(FLAG_PENDING_SECURITY, &chan->flags);
 			sk->sk_state = BT_CONFIG;
 			chan->state = BT_CONFIG;
 
@@ -1359,6 +1360,11 @@ static void l2cap_sock_resume_cb(struct l2cap_chan *chan)
 {
 	struct sock *sk = chan->data;
 
+	if (test_and_clear_bit(FLAG_PENDING_SECURITY, &chan->flags)) {
+		sk->sk_state = BT_CONNECTED;
+		chan->state = BT_CONNECTED;
+	}
+
 	clear_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags);
 	sk->sk_state_change(sk);
 }
-- 
cgit v1.2.3


From f193844c51e88ea3d2137bb0c1d38d27d37691a2 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 8 Aug 2014 09:37:15 +0300
Subject: Bluetooth: Add more L2CAP convenience callbacks

In preparation for converting SMP to use l2cap_chan it's useful to add a
few more callback helpers so that smp.c won't need to define all of its
own.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 4a51e7596608..a72965f6bc2f 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -838,18 +838,43 @@ static inline struct l2cap_chan *l2cap_chan_no_new_connection(struct l2cap_chan
 	return NULL;
 }
 
+static inline int l2cap_chan_no_recv(struct l2cap_chan *chan, struct sk_buff *skb)
+{
+	return -ENOSYS;
+}
+
+static inline struct sk_buff *l2cap_chan_no_alloc_skb(struct l2cap_chan *chan,
+						      unsigned long hdr_len,
+						      unsigned long len, int nb)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 static inline void l2cap_chan_no_teardown(struct l2cap_chan *chan, int err)
 {
 }
 
+static inline void l2cap_chan_no_close(struct l2cap_chan *chan)
+{
+}
+
 static inline void l2cap_chan_no_ready(struct l2cap_chan *chan)
 {
 }
 
+static inline void l2cap_chan_no_state_change(struct l2cap_chan *chan,
+					      int state, int err)
+{
+}
+
 static inline void l2cap_chan_no_defer(struct l2cap_chan *chan)
 {
 }
 
+static inline void l2cap_chan_no_suspend(struct l2cap_chan *chan)
+{
+}
+
 static inline void l2cap_chan_no_resume(struct l2cap_chan *chan)
 {
 }
-- 
cgit v1.2.3


From 70db83c4bcdc1447bbcb318389561c90d7056b18 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 8 Aug 2014 09:37:16 +0300
Subject: Bluetooth: Add SMP L2CAP channel skeleton

This patch creates the initial SMP L2CAP channels and a skeleton for
their callbacks. There is one per-adapter channel created upon adapter
registration, and then one channel per-connection created through the
new_connection callback. The channels are registered with the reserved
CID 0x1f for now in order to not conflict with existing SMP
functionality. Once everything is in place the value can be changed to
what it should be, i.e. L2CAP_CID_SMP.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |   1 +
 include/net/bluetooth/l2cap.h    |   1 +
 net/bluetooth/smp.c              | 131 ++++++++++++++++++++++++++++++++++++++-
 3 files changed, 132 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index cc2eb7730fbc..2571fc1cb1c5 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -303,6 +303,7 @@ struct hci_dev {
 	__u32			req_result;
 
 	struct crypto_blkcipher	*tfm_aes;
+	void			*smp_data;
 
 	struct discovery_state	discovery;
 	struct hci_conn_hash	conn_hash;
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index a72965f6bc2f..1a037ba4b6f4 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -637,6 +637,7 @@ struct l2cap_conn {
 
 	struct delayed_work	security_timer;
 	struct smp_chan		*smp_chan;
+	struct l2cap_chan	*smp;
 
 	struct list_head	chan_l;
 	struct mutex		chan_lock;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index ab07649ecc77..2362ae35a4d5 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1456,8 +1456,106 @@ int smp_distribute_keys(struct l2cap_conn *conn)
 	return 0;
 }
 
+static void smp_teardown_cb(struct l2cap_chan *chan, int err)
+{
+	struct l2cap_conn *conn = chan->conn;
+
+	BT_DBG("chan %p", chan);
+
+	conn->smp = NULL;
+	l2cap_chan_put(chan);
+}
+
+static void smp_ready_cb(struct l2cap_chan *chan)
+{
+	struct l2cap_conn *conn = chan->conn;
+
+	BT_DBG("chan %p", chan);
+
+	conn->smp = chan;
+	l2cap_chan_hold(chan);
+}
+
+static struct sk_buff *smp_alloc_skb_cb(struct l2cap_chan *chan,
+					unsigned long hdr_len,
+					unsigned long len, int nb)
+{
+	struct sk_buff *skb;
+
+	skb = bt_skb_alloc(hdr_len + len, GFP_KERNEL);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	skb->priority = HCI_PRIO_MAX;
+	bt_cb(skb)->chan = chan;
+
+	return skb;
+}
+
+static const struct l2cap_ops smp_chan_ops = {
+	.name			= "Security Manager",
+	.ready			= smp_ready_cb,
+	.alloc_skb		= smp_alloc_skb_cb,
+	.teardown		= smp_teardown_cb,
+
+	.new_connection		= l2cap_chan_no_new_connection,
+	.recv			= l2cap_chan_no_recv,
+	.state_change		= l2cap_chan_no_state_change,
+	.close			= l2cap_chan_no_close,
+	.defer			= l2cap_chan_no_defer,
+	.suspend		= l2cap_chan_no_suspend,
+	.resume			= l2cap_chan_no_resume,
+	.set_shutdown		= l2cap_chan_no_set_shutdown,
+	.get_sndtimeo		= l2cap_chan_no_get_sndtimeo,
+	.memcpy_fromiovec	= l2cap_chan_no_memcpy_fromiovec,
+};
+
+static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan)
+{
+	struct l2cap_chan *chan;
+
+	BT_DBG("pchan %p", pchan);
+
+	chan = l2cap_chan_create();
+	if (!chan)
+		return NULL;
+
+	chan->chan_type	= pchan->chan_type;
+	chan->ops	= &smp_chan_ops;
+	chan->scid	= pchan->scid;
+	chan->dcid	= chan->scid;
+	chan->imtu	= pchan->imtu;
+	chan->omtu	= pchan->omtu;
+	chan->mode	= pchan->mode;
+
+	BT_DBG("created chan %p", chan);
+
+	return chan;
+}
+
+static const struct l2cap_ops smp_root_chan_ops = {
+	.name			= "Security Manager Root",
+	.new_connection		= smp_new_conn_cb,
+
+	/* None of these are implemented for the root channel */
+	.close			= l2cap_chan_no_close,
+	.alloc_skb		= l2cap_chan_no_alloc_skb,
+	.recv			= l2cap_chan_no_recv,
+	.state_change		= l2cap_chan_no_state_change,
+	.teardown		= l2cap_chan_no_teardown,
+	.ready			= l2cap_chan_no_ready,
+	.defer			= l2cap_chan_no_defer,
+	.suspend		= l2cap_chan_no_suspend,
+	.resume			= l2cap_chan_no_resume,
+	.set_shutdown		= l2cap_chan_no_set_shutdown,
+	.get_sndtimeo		= l2cap_chan_no_get_sndtimeo,
+	.memcpy_fromiovec	= l2cap_chan_no_memcpy_fromiovec,
+};
+
 int smp_register(struct hci_dev *hdev)
 {
+	struct l2cap_chan *chan;
+
 	BT_DBG("%s", hdev->name);
 
 	hdev->tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0,
@@ -1469,15 +1567,46 @@ int smp_register(struct hci_dev *hdev)
 		return err;
 	}
 
+	chan = l2cap_chan_create();
+	if (!chan) {
+		crypto_free_blkcipher(hdev->tfm_aes);
+		hdev->tfm_aes = NULL;
+		return -ENOMEM;
+	}
+
+	/* FIXME: Using reserved 0x1f value for now - to be changed to
+	 * L2CAP_CID_SMP once all functionality is in place.
+	 */
+	l2cap_add_scid(chan, 0x1f);
+
+	l2cap_chan_set_defaults(chan);
+
+	bacpy(&chan->src, &hdev->bdaddr);
+	chan->src_type = BDADDR_LE_PUBLIC;
+	chan->state = BT_LISTEN;
+	chan->mode = L2CAP_MODE_BASIC;
+	chan->imtu = L2CAP_DEFAULT_MTU;
+	chan->ops = &smp_root_chan_ops;
+
+	hdev->smp_data = chan;
+
 	return 0;
 }
 
 void smp_unregister(struct hci_dev *hdev)
 {
-	BT_DBG("%s", hdev->name);
+	struct l2cap_chan *chan = hdev->smp_data;
+
+	if (!chan)
+		return;
+
+	BT_DBG("%s chan %p", hdev->name, chan);
 
 	if (hdev->tfm_aes) {
 		crypto_free_blkcipher(hdev->tfm_aes);
 		hdev->tfm_aes = NULL;
 	}
+
+	hdev->smp_data = NULL;
+	l2cap_chan_put(chan);
 }
-- 
cgit v1.2.3


From defce9e83666658d4420d65e45ab1ad190992f72 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 8 Aug 2014 09:37:17 +0300
Subject: Bluetooth: Make AES crypto context private to SMP

Now that we have per-adapter SMP data thanks to the root SMP L2CAP
channel we can take advantage of it and attach the AES crypto context
(only used for SMP) to it. This means that the smp_irk_matches() and
smp_generate_rpa() function can be converted to internally handle the
AES context.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/hci_core.c         | 13 ++-----------
 net/bluetooth/smp.c              | 41 +++++++++++++++++++++++++++-------------
 net/bluetooth/smp.h              |  5 ++---
 4 files changed, 32 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2571fc1cb1c5..5f0b77b71b45 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -302,7 +302,6 @@ struct hci_dev {
 	__u32			req_status;
 	__u32			req_result;
 
-	struct crypto_blkcipher	*tfm_aes;
 	void			*smp_data;
 
 	struct discovery_state	discovery;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 88575a633601..abeb5e47311e 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3234,11 +3234,8 @@ struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa)
 			return irk;
 	}
 
-	if (!hdev->tfm_aes)
-		return NULL;
-
 	list_for_each_entry(irk, &hdev->identity_resolving_keys, list) {
-		if (smp_irk_matches(hdev->tfm_aes, irk->val, rpa)) {
+		if (smp_irk_matches(hdev, irk->val, rpa)) {
 			bacpy(&irk->rpa, rpa);
 			return irk;
 		}
@@ -3887,13 +3884,7 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy,
 		    !bacmp(&hdev->random_addr, &hdev->rpa))
 			return 0;
 
-		if (!hdev->tfm_aes) {
-			BT_ERR("%s crypto not available to generate RPA",
-			       hdev->name);
-			return -EOPNOTSUPP;
-		}
-
-		err = smp_generate_rpa(hdev->tfm_aes, hdev->irk, &hdev->rpa);
+		err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa);
 		if (err < 0) {
 			BT_ERR("%s failed to generate new RPA", hdev->name);
 			return err;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 2362ae35a4d5..6925fc4caaee 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -139,12 +139,18 @@ static int smp_ah(struct crypto_blkcipher *tfm, u8 irk[16], u8 r[3], u8 res[3])
 	return 0;
 }
 
-bool smp_irk_matches(struct crypto_blkcipher *tfm, u8 irk[16],
-		     bdaddr_t *bdaddr)
+bool smp_irk_matches(struct hci_dev *hdev, u8 irk[16], bdaddr_t *bdaddr)
 {
+	struct l2cap_chan *chan = hdev->smp_data;
+	struct crypto_blkcipher *tfm;
 	u8 hash[3];
 	int err;
 
+	if (!chan || !chan->data)
+		return false;
+
+	tfm = chan->data;
+
 	BT_DBG("RPA %pMR IRK %*phN", bdaddr, 16, irk);
 
 	err = smp_ah(tfm, irk, &bdaddr->b[3], hash);
@@ -154,10 +160,17 @@ bool smp_irk_matches(struct crypto_blkcipher *tfm, u8 irk[16],
 	return !memcmp(bdaddr->b, hash, 3);
 }
 
-int smp_generate_rpa(struct crypto_blkcipher *tfm, u8 irk[16], bdaddr_t *rpa)
+int smp_generate_rpa(struct hci_dev *hdev, u8 irk[16], bdaddr_t *rpa)
 {
+	struct l2cap_chan *chan = hdev->smp_data;
+	struct crypto_blkcipher *tfm;
 	int err;
 
+	if (!chan || !chan->data)
+		return -EOPNOTSUPP;
+
+	tfm = chan->data;
+
 	get_random_bytes(&rpa->b[3], 3);
 
 	rpa->b[5] &= 0x3f;	/* Clear two most significant bits */
@@ -1555,25 +1568,25 @@ static const struct l2cap_ops smp_root_chan_ops = {
 int smp_register(struct hci_dev *hdev)
 {
 	struct l2cap_chan *chan;
+	struct crypto_blkcipher	*tfm_aes;
 
 	BT_DBG("%s", hdev->name);
 
-	hdev->tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0,
-					       CRYPTO_ALG_ASYNC);
-	if (IS_ERR(hdev->tfm_aes)) {
-		int err = PTR_ERR(hdev->tfm_aes);
+	tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm_aes)) {
+		int err = PTR_ERR(tfm_aes);
 		BT_ERR("Unable to create crypto context");
-		hdev->tfm_aes = NULL;
 		return err;
 	}
 
 	chan = l2cap_chan_create();
 	if (!chan) {
-		crypto_free_blkcipher(hdev->tfm_aes);
-		hdev->tfm_aes = NULL;
+		crypto_free_blkcipher(tfm_aes);
 		return -ENOMEM;
 	}
 
+	chan->data = tfm_aes;
+
 	/* FIXME: Using reserved 0x1f value for now - to be changed to
 	 * L2CAP_CID_SMP once all functionality is in place.
 	 */
@@ -1596,15 +1609,17 @@ int smp_register(struct hci_dev *hdev)
 void smp_unregister(struct hci_dev *hdev)
 {
 	struct l2cap_chan *chan = hdev->smp_data;
+	struct crypto_blkcipher *tfm_aes;
 
 	if (!chan)
 		return;
 
 	BT_DBG("%s chan %p", hdev->name, chan);
 
-	if (hdev->tfm_aes) {
-		crypto_free_blkcipher(hdev->tfm_aes);
-		hdev->tfm_aes = NULL;
+	tfm_aes = chan->data;
+	if (tfm_aes) {
+		chan->data = NULL;
+		crypto_free_blkcipher(tfm_aes);
 	}
 
 	hdev->smp_data = NULL;
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
index 6e29359f60a3..d3f6bd617940 100644
--- a/net/bluetooth/smp.h
+++ b/net/bluetooth/smp.h
@@ -132,9 +132,8 @@ int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey);
 
 void smp_chan_destroy(struct l2cap_conn *conn);
 
-bool smp_irk_matches(struct crypto_blkcipher *tfm, u8 irk[16],
-		     bdaddr_t *bdaddr);
-int smp_generate_rpa(struct crypto_blkcipher *tfm, u8 irk[16], bdaddr_t *rpa);
+bool smp_irk_matches(struct hci_dev *hdev, u8 irk[16], bdaddr_t *bdaddr);
+int smp_generate_rpa(struct hci_dev *hdev, u8 irk[16], bdaddr_t *rpa);
 
 int smp_register(struct hci_dev *hdev);
 void smp_unregister(struct hci_dev *hdev);
-- 
cgit v1.2.3


From 5d88cc73dded31a93fcc4821f33a8c3d755bf454 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 8 Aug 2014 09:37:18 +0300
Subject: Bluetooth: Convert SMP to use l2cap_chan infrastructure

Now that we have all the necessary pieces in place we can fully convert
SMP to use the L2CAP channel infrastructure. This patch adds the
necessary callbacks and removes the now unneeded conn->smp_chan pointer.

One notable behavioral change in this patch comes from the following
code snippet:

-       case L2CAP_CID_SMP:
-               if (smp_sig_channel(conn, skb))
-                       l2cap_conn_del(conn->hcon, EACCES);

This piece of code was essentially forcing a disconnection if garbage
SMP data was received. The l2cap_conn_del() function is private to
l2cap_conn.c so we don't have access to it anymore when using the L2CAP
channel callbacks. Therefore, the behavior of the new code is simply to
return errors in the recv() callback (which is simply the old
smp_sig_channel()), but no disconnection will occur.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |   1 -
 net/bluetooth/l2cap_core.c    |  10 ----
 net/bluetooth/smp.c           | 122 +++++++++++++++++++++++-------------------
 net/bluetooth/smp.h           |   1 -
 4 files changed, 66 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 1a037ba4b6f4..bda6252e3722 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -636,7 +636,6 @@ struct l2cap_conn {
 	__u8			disc_reason;
 
 	struct delayed_work	security_timer;
-	struct smp_chan		*smp_chan;
 	struct l2cap_chan	*smp;
 
 	struct list_head	chan_l;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 8acfe6f57b5e..40b6c06ab2c0 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1651,11 +1651,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 	if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT)
 		cancel_delayed_work_sync(&conn->info_timer);
 
-	if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags)) {
-		cancel_delayed_work_sync(&conn->security_timer);
-		smp_chan_destroy(conn);
-	}
-
 	hcon->l2cap_data = NULL;
 	conn->hchan = NULL;
 	l2cap_conn_put(conn);
@@ -6862,11 +6857,6 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb)
 		l2cap_le_sig_channel(conn, skb);
 		break;
 
-	case L2CAP_CID_SMP:
-		if (smp_sig_channel(conn, skb))
-			l2cap_conn_del(conn->hcon, EACCES);
-		break;
-
 	default:
 		l2cap_data_channel(conn, cid, skb);
 		break;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 6925fc4caaee..744f678ac3e8 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -248,44 +248,29 @@ static int smp_s1(struct smp_chan *smp, u8 k[16], u8 r1[16], u8 r2[16],
 	return err;
 }
 
-static struct sk_buff *smp_build_cmd(struct l2cap_conn *conn, u8 code,
-				     u16 dlen, void *data)
+static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
 {
-	struct sk_buff *skb;
-	struct l2cap_hdr *lh;
-	int len;
-
-	len = L2CAP_HDR_SIZE + sizeof(code) + dlen;
-
-	if (len > conn->mtu)
-		return NULL;
+	struct l2cap_chan *chan = conn->smp;
+	struct kvec iv[2];
+	struct msghdr msg;
 
-	skb = bt_skb_alloc(len, GFP_ATOMIC);
-	if (!skb)
-		return NULL;
+	if (!chan)
+		return;
 
-	lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE);
-	lh->len = cpu_to_le16(sizeof(code) + dlen);
-	lh->cid = cpu_to_le16(L2CAP_CID_SMP);
+	BT_DBG("code 0x%2.2x", code);
 
-	memcpy(skb_put(skb, sizeof(code)), &code, sizeof(code));
+	iv[0].iov_base = &code;
+	iv[0].iov_len = 1;
 
-	memcpy(skb_put(skb, dlen), data, dlen);
+	iv[1].iov_base = data;
+	iv[1].iov_len = len;
 
-	return skb;
-}
+	memset(&msg, 0, sizeof(msg));
 
-static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
-{
-	struct sk_buff *skb = smp_build_cmd(conn, code, len, data);
+	msg.msg_iov = (struct iovec *) &iv;
+	msg.msg_iovlen = 2;
 
-	BT_DBG("code 0x%2.2x", code);
-
-	if (!skb)
-		return;
-
-	skb->priority = HCI_PRIO_MAX;
-	hci_send_acl(conn->hchan, skb, 0);
+	l2cap_chan_send(chan, &msg, 1 + len);
 
 	cancel_delayed_work_sync(&conn->security_timer);
 	schedule_delayed_work(&conn->security_timer, SMP_TIMEOUT);
@@ -315,7 +300,8 @@ static void build_pairing_cmd(struct l2cap_conn *conn,
 			      struct smp_cmd_pairing *req,
 			      struct smp_cmd_pairing *rsp, __u8 authreq)
 {
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 	struct hci_conn *hcon = conn->hcon;
 	struct hci_dev *hdev = hcon->hdev;
 	u8 local_dist = 0, remote_dist = 0;
@@ -358,7 +344,8 @@ static void build_pairing_cmd(struct l2cap_conn *conn,
 
 static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size)
 {
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 
 	if ((max_key_size > SMP_MAX_ENC_KEY_SIZE) ||
 	    (max_key_size < SMP_MIN_ENC_KEY_SIZE))
@@ -418,7 +405,8 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 						u8 local_io, u8 remote_io)
 {
 	struct hci_conn *hcon = conn->hcon;
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 	u8 method;
 	u32 passkey = 0;
 	int ret = 0;
@@ -589,6 +577,7 @@ static u8 smp_random(struct smp_chan *smp)
 
 static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 {
+	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp;
 
 	smp = kzalloc(sizeof(*smp), GFP_ATOMIC);
@@ -606,7 +595,7 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 	}
 
 	smp->conn = conn;
-	conn->smp_chan = smp;
+	chan->data = smp;
 
 	hci_conn_hold(conn->hcon);
 
@@ -615,7 +604,8 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 
 void smp_chan_destroy(struct l2cap_conn *conn)
 {
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 	bool complete;
 
 	BUG_ON(!smp);
@@ -646,14 +636,15 @@ void smp_chan_destroy(struct l2cap_conn *conn)
 		}
 	}
 
+	chan->data = NULL;
 	kfree(smp);
-	conn->smp_chan = NULL;
 	hci_conn_drop(conn->hcon);
 }
 
 int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 {
 	struct l2cap_conn *conn = hcon->l2cap_data;
+	struct l2cap_chan *chan;
 	struct smp_chan *smp;
 	u32 value;
 
@@ -662,7 +653,11 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 	if (!conn || !test_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags))
 		return -ENOTCONN;
 
-	smp = conn->smp_chan;
+	chan = conn->smp;
+	if (!chan)
+		return -ENOTCONN;
+
+	smp = chan->data;
 
 	switch (mgmt_op) {
 	case MGMT_OP_USER_PASSKEY_REPLY:
@@ -709,10 +704,12 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (conn->hcon->role != HCI_ROLE_SLAVE)
 		return SMP_CMD_NOTSUPP;
 
-	if (!test_and_set_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags))
+	if (!test_and_set_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) {
 		smp = smp_chan_create(conn);
-	else
-		smp = conn->smp_chan;
+	} else {
+		struct l2cap_chan *chan = conn->smp;
+		smp = chan->data;
+	}
 
 	if (!smp)
 		return SMP_UNSPECIFIED;
@@ -766,7 +763,8 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_pairing *req, *rsp = (void *) skb->data;
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 	u8 key_size, auth = SMP_AUTH_NONE;
 	int ret;
 
@@ -827,7 +825,8 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 
 static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 {
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 
 	BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave");
 
@@ -850,7 +849,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 
 static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 {
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 
 	BT_DBG("conn %p", conn);
 
@@ -1023,7 +1023,8 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_encrypt_info *rp = (void *) skb->data;
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 
 	BT_DBG("conn %p", conn);
 
@@ -1044,7 +1045,8 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb)
 static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_master_ident *rp = (void *) skb->data;
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 	struct hci_dev *hdev = conn->hcon->hdev;
 	struct hci_conn *hcon = conn->hcon;
 	struct smp_ltk *ltk;
@@ -1080,7 +1082,8 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb)
 static int smp_cmd_ident_info(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_ident_info *info = (void *) skb->data;
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 
 	BT_DBG("");
 
@@ -1102,7 +1105,8 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn,
 				   struct sk_buff *skb)
 {
 	struct smp_cmd_ident_addr_info *info = (void *) skb->data;
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 	struct hci_conn *hcon = conn->hcon;
 	bdaddr_t rpa;
 
@@ -1156,7 +1160,8 @@ distribute:
 static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_sign_info *rp = (void *) skb->data;
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 	struct hci_dev *hdev = conn->hcon->hdev;
 	struct smp_csrk *csrk;
 
@@ -1187,8 +1192,9 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)
 	return 0;
 }
 
-int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb)
+static int smp_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
 {
+	struct l2cap_conn *conn = chan->conn;
 	struct hci_conn *hcon = conn->hcon;
 	__u8 code, reason;
 	int err = 0;
@@ -1290,7 +1296,8 @@ done:
 
 static void smp_notify_keys(struct l2cap_conn *conn)
 {
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 	struct hci_conn *hcon = conn->hcon;
 	struct hci_dev *hdev = hcon->hdev;
 	struct smp_cmd_pairing *req = (void *) &smp->preq[1];
@@ -1357,7 +1364,8 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 int smp_distribute_keys(struct l2cap_conn *conn)
 {
 	struct smp_cmd_pairing *req, *rsp;
-	struct smp_chan *smp = conn->smp_chan;
+	struct l2cap_chan *chan = conn->smp;
+	struct smp_chan *smp = chan->data;
 	struct hci_conn *hcon = conn->hcon;
 	struct hci_dev *hdev = hcon->hdev;
 	__u8 *keydist;
@@ -1475,6 +1483,11 @@ static void smp_teardown_cb(struct l2cap_chan *chan, int err)
 
 	BT_DBG("chan %p", chan);
 
+	if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) {
+		cancel_delayed_work_sync(&conn->security_timer);
+		smp_chan_destroy(conn);
+	}
+
 	conn->smp = NULL;
 	l2cap_chan_put(chan);
 }
@@ -1508,11 +1521,11 @@ static struct sk_buff *smp_alloc_skb_cb(struct l2cap_chan *chan,
 static const struct l2cap_ops smp_chan_ops = {
 	.name			= "Security Manager",
 	.ready			= smp_ready_cb,
+	.recv			= smp_recv_cb,
 	.alloc_skb		= smp_alloc_skb_cb,
 	.teardown		= smp_teardown_cb,
 
 	.new_connection		= l2cap_chan_no_new_connection,
-	.recv			= l2cap_chan_no_recv,
 	.state_change		= l2cap_chan_no_state_change,
 	.close			= l2cap_chan_no_close,
 	.defer			= l2cap_chan_no_defer,
@@ -1587,10 +1600,7 @@ int smp_register(struct hci_dev *hdev)
 
 	chan->data = tfm_aes;
 
-	/* FIXME: Using reserved 0x1f value for now - to be changed to
-	 * L2CAP_CID_SMP once all functionality is in place.
-	 */
-	l2cap_add_scid(chan, 0x1f);
+	l2cap_add_scid(chan, L2CAP_CID_SMP);
 
 	l2cap_chan_set_defaults(chan);
 
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
index d3f6bd617940..161ace3c3234 100644
--- a/net/bluetooth/smp.h
+++ b/net/bluetooth/smp.h
@@ -126,7 +126,6 @@ enum {
 /* SMP Commands */
 bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level);
 int smp_conn_security(struct hci_conn *hcon, __u8 sec_level);
-int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb);
 int smp_distribute_keys(struct l2cap_conn *conn);
 int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey);
 
-- 
cgit v1.2.3


From dec5b49235e2526d7aacf5b93ea48f5e30c2f7c3 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 11 Aug 2014 22:06:37 +0300
Subject: Bluetooth: Add public l2cap_conn_shutdown() API to request
 disconnection

Since we no-longer do special handling of SMP within l2cap_core.c we
don't have any code for calling l2cap_conn_del() when smp.c doesn't like
the data it gets. At the same time we cannot simply export
l2cap_conn_del() since it will try to lock the channels it calls into
whereas we already hold the lock in the smp.c l2cap_chan callbacks (i.e.
it'd lead to a deadlock).

This patch adds a new l2cap_conn_shutdown() API which is very similar to
l2cap_conn_del() except that it defers the call to l2cap_conn_del()
through a workqueue, thereby making it safe to use it from an L2CAP
channel callback.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |  4 ++++
 net/bluetooth/l2cap_core.c    | 25 +++++++++++++++++++++++++
 2 files changed, 29 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index bda6252e3722..40f34866b6da 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -625,6 +625,9 @@ struct l2cap_conn {
 
 	struct delayed_work	info_timer;
 
+	int			disconn_err;
+	struct work_struct	disconn_work;
+
 	struct sk_buff		*rx_skb;
 	__u32			rx_len;
 	__u8			tx_ident;
@@ -944,6 +947,7 @@ void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
 		       u8 status);
 void __l2cap_physical_cfm(struct l2cap_chan *chan, int result);
 
+void l2cap_conn_shutdown(struct l2cap_conn *conn, int err);
 void l2cap_conn_get(struct l2cap_conn *conn);
 void l2cap_conn_put(struct l2cap_conn *conn);
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 4de1e1827055..404998efa7e2 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1627,6 +1627,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 	if (work_pending(&conn->pending_rx_work))
 		cancel_work_sync(&conn->pending_rx_work);
 
+	if (work_pending(&conn->disconn_work))
+		cancel_work_sync(&conn->disconn_work);
+
 	l2cap_unregister_all_users(conn);
 
 	mutex_lock(&conn->chan_lock);
@@ -1669,6 +1672,26 @@ static void security_timeout(struct work_struct *work)
 	}
 }
 
+static void disconn_work(struct work_struct *work)
+{
+	struct l2cap_conn *conn = container_of(work, struct l2cap_conn,
+					       disconn_work);
+
+	BT_DBG("conn %p", conn);
+
+	l2cap_conn_del(conn->hcon, conn->disconn_err);
+}
+
+void l2cap_conn_shutdown(struct l2cap_conn *conn, int err)
+{
+	struct hci_dev *hdev = conn->hcon->hdev;
+
+	BT_DBG("conn %p err %d", conn, err);
+
+	conn->disconn_err = err;
+	queue_work(hdev->workqueue, &conn->disconn_work);
+}
+
 static void l2cap_conn_free(struct kref *ref)
 {
 	struct l2cap_conn *conn = container_of(ref, struct l2cap_conn, ref);
@@ -6930,6 +6953,8 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
 	else
 		INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout);
 
+	INIT_WORK(&conn->disconn_work, disconn_work);
+
 	skb_queue_head_init(&conn->pending_rx);
 	INIT_WORK(&conn->pending_rx_work, process_pending_rx);
 
-- 
cgit v1.2.3


From 276d807317dead63ef2f13aa46e3c17d57ba0713 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 11 Aug 2014 22:06:41 +0300
Subject: Bluetooth: Remove unused l2cap_conn->security_timer

Now that there are no-longer any users for l2cap_conn->security_timer we
can go ahead and simply remove it. The patch makes initialization of the
conn->info_timer unconditional since it's better not to leave any
l2cap_conn data structures uninitialized no matter what the underlying
transport.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |  1 -
 net/bluetooth/l2cap_core.c    | 18 +-----------------
 2 files changed, 1 insertion(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 40f34866b6da..cedda399f9c0 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -638,7 +638,6 @@ struct l2cap_conn {
 
 	__u8			disc_reason;
 
-	struct delayed_work	security_timer;
 	struct l2cap_chan	*smp;
 
 	struct list_head	chan_l;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 404998efa7e2..0cd7ed99558b 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1659,19 +1659,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 	l2cap_conn_put(conn);
 }
 
-static void security_timeout(struct work_struct *work)
-{
-	struct l2cap_conn *conn = container_of(work, struct l2cap_conn,
-					       security_timer.work);
-
-	BT_DBG("conn %p", conn);
-
-	if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) {
-		smp_chan_destroy(conn);
-		l2cap_conn_del(conn->hcon, ETIMEDOUT);
-	}
-}
-
 static void disconn_work(struct work_struct *work)
 {
 	struct l2cap_conn *conn = container_of(work, struct l2cap_conn,
@@ -6948,10 +6935,7 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
 	INIT_LIST_HEAD(&conn->chan_l);
 	INIT_LIST_HEAD(&conn->users);
 
-	if (hcon->type == LE_LINK)
-		INIT_DELAYED_WORK(&conn->security_timer, security_timeout);
-	else
-		INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout);
+	INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout);
 
 	INIT_WORK(&conn->disconn_work, disconn_work);
 
-- 
cgit v1.2.3


From 560cb12a4080a48b84da8b96878cafbd193c4d64 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 23 Apr 2014 16:12:30 +0200
Subject: locking,arch: Rewrite generic atomic support

Rewrite generic atomic support to only require cmpxchg(), generate all
other primitives from that.

Furthermore reduce the endless repetition for all these primitives to
a few CPP macros. This way we get more for less lines.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140508135852.940119622@infradead.org
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Howells <dhowells@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-arch@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/asm-generic/atomic.h   | 192 ++++++++++++++++++++---------------------
 include/asm-generic/atomic64.h |  20 ++++-
 lib/atomic64.c                 |  83 ++++++++----------
 3 files changed, 148 insertions(+), 147 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 9c79e7603459..56d4d36e1531 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -18,14 +18,100 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
+/*
+ * atomic_$op() - $op integer to atomic variable
+ * @i: integer value to $op
+ * @v: pointer to the atomic variable
+ *
+ * Atomically $ops @i to @v. Does not strictly guarantee a memory-barrier, use
+ * smp_mb__{before,after}_atomic().
+ */
+
+/*
+ * atomic_$op_return() - $op interer to atomic variable and returns the result
+ * @i: integer value to $op
+ * @v: pointer to the atomic variable
+ *
+ * Atomically $ops @i to @v. Does imply a full memory barrier.
+ */
+
 #ifdef CONFIG_SMP
-/* Force people to define core atomics */
-# if !defined(atomic_add_return) || !defined(atomic_sub_return) || \
-     !defined(atomic_clear_mask) || !defined(atomic_set_mask)
-#  error "SMP requires a little arch-specific magic"
-# endif
+
+/* we can build all atomic primitives from cmpxchg */
+
+#define ATOMIC_OP(op, c_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = cmpxchg(&v->counter, c, c c_op i)) != c)		\
+		c = old;						\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = cmpxchg(&v->counter, c, c c_op i)) != c)		\
+		c = old;						\
+									\
+	return c c_op i;						\
+}
+
+#else
+
+#include <linux/irqflags.h>
+
+#define ATOMIC_OP(op, c_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter = v->counter c_op i;					\
+	raw_local_irq_restore(flags);					\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	raw_local_irq_save(flags);					\
+	ret = (v->counter = v->counter c_op i);				\
+	raw_local_irq_restore(flags);					\
+									\
+	return ret;							\
+}
+
+#endif /* CONFIG_SMP */
+
+#ifndef atomic_add_return
+ATOMIC_OP_RETURN(add, +)
+#endif
+
+#ifndef atomic_sub_return
+ATOMIC_OP_RETURN(sub, -)
+#endif
+
+#ifndef atomic_clear_mask
+ATOMIC_OP(and, &)
+#define atomic_clear_mask(i, v) atomic_and(~(i), (v))
 #endif
 
+#ifndef atomic_set_mask
+#define CONFIG_ARCH_HAS_ATOMIC_OR
+ATOMIC_OP(or, |)
+#define atomic_set_mask(i, v)	atomic_or((i), (v))
+#endif
+
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
 /*
  * Atomic operations that C can't guarantee us.  Useful for
  * resource counting etc..
@@ -33,8 +119,6 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#ifdef __KERNEL__
-
 /**
  * atomic_read - read atomic variable
  * @v: pointer of type atomic_t
@@ -56,52 +140,6 @@
 
 #include <linux/irqflags.h>
 
-/**
- * atomic_add_return - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns the result
- */
-#ifndef atomic_add_return
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int temp;
-
-	raw_local_irq_save(flags); /* Don't trace it in an irqsoff handler */
-	temp = v->counter;
-	temp += i;
-	v->counter = temp;
-	raw_local_irq_restore(flags);
-
-	return temp;
-}
-#endif
-
-/**
- * atomic_sub_return - subtract integer from atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns the result
- */
-#ifndef atomic_sub_return
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int temp;
-
-	raw_local_irq_save(flags); /* Don't trace it in an irqsoff handler */
-	temp = v->counter;
-	temp -= i;
-	v->counter = temp;
-	raw_local_irq_restore(flags);
-
-	return temp;
-}
-#endif
-
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
 	return atomic_add_return(i, v) < 0;
@@ -139,49 +177,11 @@ static inline void atomic_dec(atomic_t *v)
 
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
-  int c, old;
-  c = atomic_read(v);
-  while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
-    c = old;
-  return c;
-}
-
-/**
- * atomic_clear_mask - Atomically clear bits in atomic variable
- * @mask: Mask of the bits to be cleared
- * @v: pointer of type atomic_t
- *
- * Atomically clears the bits set in @mask from @v
- */
-#ifndef atomic_clear_mask
-static inline void atomic_clear_mask(unsigned long mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	mask = ~mask;
-	raw_local_irq_save(flags); /* Don't trace it in a irqsoff handler */
-	v->counter &= mask;
-	raw_local_irq_restore(flags);
+	int c, old;
+	c = atomic_read(v);
+	while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
+		c = old;
+	return c;
 }
-#endif
-
-/**
- * atomic_set_mask - Atomically set bits in atomic variable
- * @mask: Mask of the bits to be set
- * @v: pointer of type atomic_t
- *
- * Atomically sets the bits set in @mask in @v
- */
-#ifndef atomic_set_mask
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags); /* Don't trace it in a irqsoff handler */
-	v->counter |= mask;
-	raw_local_irq_restore(flags);
-}
-#endif
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_GENERIC_ATOMIC_H */
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index b18ce4f9ee3d..30ad9c86cebb 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -20,10 +20,22 @@ typedef struct {
 
 extern long long atomic64_read(const atomic64_t *v);
 extern void	 atomic64_set(atomic64_t *v, long long i);
-extern void	 atomic64_add(long long a, atomic64_t *v);
-extern long long atomic64_add_return(long long a, atomic64_t *v);
-extern void	 atomic64_sub(long long a, atomic64_t *v);
-extern long long atomic64_sub_return(long long a, atomic64_t *v);
+
+#define ATOMIC64_OP(op)							\
+extern void	 atomic64_##op(long long a, atomic64_t *v);
+
+#define ATOMIC64_OP_RETURN(op)						\
+extern long long atomic64_##op##_return(long long a, atomic64_t *v);
+
+#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+
+ATOMIC64_OPS(add)
+ATOMIC64_OPS(sub)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
 extern long long atomic64_dec_if_positive(atomic64_t *v);
 extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
 extern long long atomic64_xchg(atomic64_t *v, long long new);
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 08a4f068e61e..1298c05ef528 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -70,53 +70,42 @@ void atomic64_set(atomic64_t *v, long long i)
 }
 EXPORT_SYMBOL(atomic64_set);
 
-void atomic64_add(long long a, atomic64_t *v)
-{
-	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
-
-	raw_spin_lock_irqsave(lock, flags);
-	v->counter += a;
-	raw_spin_unlock_irqrestore(lock, flags);
-}
-EXPORT_SYMBOL(atomic64_add);
-
-long long atomic64_add_return(long long a, atomic64_t *v)
-{
-	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
-
-	raw_spin_lock_irqsave(lock, flags);
-	val = v->counter += a;
-	raw_spin_unlock_irqrestore(lock, flags);
-	return val;
-}
-EXPORT_SYMBOL(atomic64_add_return);
-
-void atomic64_sub(long long a, atomic64_t *v)
-{
-	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
-
-	raw_spin_lock_irqsave(lock, flags);
-	v->counter -= a;
-	raw_spin_unlock_irqrestore(lock, flags);
-}
-EXPORT_SYMBOL(atomic64_sub);
-
-long long atomic64_sub_return(long long a, atomic64_t *v)
-{
-	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
-
-	raw_spin_lock_irqsave(lock, flags);
-	val = v->counter -= a;
-	raw_spin_unlock_irqrestore(lock, flags);
-	return val;
-}
-EXPORT_SYMBOL(atomic64_sub_return);
+#define ATOMIC64_OP(op, c_op)						\
+void atomic64_##op(long long a, atomic64_t *v)				\
+{									\
+	unsigned long flags;						\
+	raw_spinlock_t *lock = lock_addr(v);				\
+									\
+	raw_spin_lock_irqsave(lock, flags);				\
+	v->counter c_op a;						\
+	raw_spin_unlock_irqrestore(lock, flags);			\
+}									\
+EXPORT_SYMBOL(atomic64_##op);
+
+#define ATOMIC64_OP_RETURN(op, c_op)					\
+long long atomic64_##op##_return(long long a, atomic64_t *v)		\
+{									\
+	unsigned long flags;						\
+	raw_spinlock_t *lock = lock_addr(v);				\
+	long long val;							\
+									\
+	raw_spin_lock_irqsave(lock, flags);				\
+	val = (v->counter c_op a);					\
+	raw_spin_unlock_irqrestore(lock, flags);			\
+	return val;							\
+}									\
+EXPORT_SYMBOL(atomic64_##op##_return);
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_OP_RETURN(op, c_op)
+
+ATOMIC64_OPS(add, +=)
+ATOMIC64_OPS(sub, -=)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
 long long atomic64_dec_if_positive(atomic64_t *v)
 {
-- 
cgit v1.2.3


From a5fe8e7695dc3f547e955ad2b662e3e72969e506 Mon Sep 17 00:00:00 2001
From: Eliad Peller <eliad@wizery.com>
Date: Wed, 11 Jun 2014 10:23:35 +0300
Subject: regulatory: add NUL to alpha2

alpha2 is defined as 2-chars array, but is used in multiple
places as string (e.g. with nla_put_string calls), which
might leak kernel data.

Solve it by simply adding an extra char for the NULL
terminator, making such operations safe.

Cc: stable@vger.kernel.org
Signed-off-by: Eliad Peller <eliadx.peller@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/regulatory.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/regulatory.h b/include/net/regulatory.h
index 259992444e80..dad7ab20a8cb 100644
--- a/include/net/regulatory.h
+++ b/include/net/regulatory.h
@@ -167,7 +167,7 @@ struct ieee80211_reg_rule {
 struct ieee80211_regdomain {
 	struct rcu_head rcu_head;
 	u32 n_reg_rules;
-	char alpha2[2];
+	char alpha2[3];
 	enum nl80211_dfs_regions dfs_region;
 	struct ieee80211_reg_rule reg_rules[];
 };
-- 
cgit v1.2.3


From a74a8c846fb699f3277c0c21278bd4c414074b4a Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 22 Jul 2014 14:50:47 +0200
Subject: mac80211: don't duplicate station QoS capability data

We currently track the QoS capability twice: for all peer stations
in the WLAN_STA_WME flag, and for any clients associated to an AP
interface separately for drivers in the sta->sta.wme field.

Remove the WLAN_STA_WME flag and track the capability only in the
driver-visible field, getting rid of the limitation that the field
is only valid in AP mode.

Reviewed-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  2 +-
 net/mac80211/cfg.c         | 13 +++----------
 net/mac80211/debugfs_sta.c |  3 ++-
 net/mac80211/ibss.c        |  2 +-
 net/mac80211/mesh_plink.c  |  4 +---
 net/mac80211/mlme.c        |  3 +--
 net/mac80211/sta_info.c    |  4 ++--
 net/mac80211/sta_info.h    |  2 --
 net/mac80211/tdls.c        |  3 +--
 net/mac80211/tx.c          |  6 +++---
 net/mac80211/wme.c         |  4 ++--
 11 files changed, 17 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index dae2e24616e1..1cd84444665c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1405,7 +1405,7 @@ struct ieee80211_sta_rates {
  * @supp_rates: Bitmap of supported rates (per band)
  * @ht_cap: HT capabilities of this STA; restricted to our own capabilities
  * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities
- * @wme: indicates whether the STA supports WME. Only valid during AP-mode.
+ * @wme: indicates whether the STA supports QoS/WME.
  * @drv_priv: data area for driver use, will always be aligned to
  *	sizeof(void *), size is determined in hw information.
  * @uapsd_queues: bitmap of queues configured for uapsd. Only valid
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 927b4ea0128b..4d8989b87960 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1011,15 +1011,8 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 			clear_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE);
 	}
 
-	if (mask & BIT(NL80211_STA_FLAG_WME)) {
-		if (set & BIT(NL80211_STA_FLAG_WME)) {
-			set_sta_flag(sta, WLAN_STA_WME);
-			sta->sta.wme = true;
-		} else {
-			clear_sta_flag(sta, WLAN_STA_WME);
-			sta->sta.wme = false;
-		}
-	}
+	if (mask & BIT(NL80211_STA_FLAG_WME))
+		sta->sta.wme = set & BIT(NL80211_STA_FLAG_WME);
 
 	if (mask & BIT(NL80211_STA_FLAG_MFP)) {
 		if (set & BIT(NL80211_STA_FLAG_MFP))
@@ -3352,7 +3345,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 	band = chanctx_conf->def.chan->band;
 	sta = sta_info_get_bss(sdata, peer);
 	if (sta) {
-		qos = test_sta_flag(sta, WLAN_STA_WME);
+		qos = sta->sta.wme;
 	} else {
 		rcu_read_unlock();
 		return -ENOLINK;
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 3db96648b45a..4a20fb8f1e23 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -77,7 +77,8 @@ static ssize_t sta_flags_read(struct file *file, char __user *userbuf,
 			    TEST(AUTH), TEST(ASSOC), TEST(PS_STA),
 			    TEST(PS_DRIVER), TEST(AUTHORIZED),
 			    TEST(SHORT_PREAMBLE),
-			    TEST(WME), TEST(WDS), TEST(CLEAR_PS_FILT),
+			    sta->sta.wme ? "WME\n" : "",
+			    TEST(WDS), TEST(CLEAR_PS_FILT),
 			    TEST(MFP), TEST(BLOCK_BA), TEST(PSPOLL),
 			    TEST(UAPSD), TEST(SP), TEST(TDLS_PEER),
 			    TEST(TDLS_PEER_AUTH), TEST(4ADDR_EVENT),
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 9713dc54ea4b..5f9654d31a8d 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1038,7 +1038,7 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 		}
 
 		if (sta && elems->wmm_info)
-			set_sta_flag(sta, WLAN_STA_WME);
+			sta->sta.wme = true;
 
 		if (sta && elems->ht_operation && elems->ht_cap_elem &&
 		    sdata->u.ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT &&
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 63b874101b27..8d67c1ebfbda 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -431,14 +431,12 @@ __mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *hw_addr)
 		return NULL;
 
 	sta->plink_state = NL80211_PLINK_LISTEN;
+	sta->sta.wme = true;
 
 	sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
 	sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
 	sta_info_pre_move_state(sta, IEEE80211_STA_AUTHORIZED);
 
-	set_sta_flag(sta, WLAN_STA_WME);
-	sta->sta.wme = true;
-
 	return sta;
 }
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 31a8afaf7332..0e8d59a0e17e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2677,8 +2677,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED)
 		set_sta_flag(sta, WLAN_STA_MFP);
 
-	if (elems.wmm_param)
-		set_sta_flag(sta, WLAN_STA_WME);
+	sta->sta.wme = elems.wmm_param;
 
 	err = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
 	if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT))
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index c6ee2139fbc5..e1f957d5935e 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1179,7 +1179,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 	struct sk_buff *skb;
 	int size = sizeof(*nullfunc);
 	__le16 fc;
-	bool qos = test_sta_flag(sta, WLAN_STA_WME);
+	bool qos = sta->sta.wme;
 	struct ieee80211_tx_info *info;
 	struct ieee80211_chanctx_conf *chanctx_conf;
 
@@ -1834,7 +1834,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 		sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHORIZED);
 	if (test_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE))
 		sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_SHORT_PREAMBLE);
-	if (test_sta_flag(sta, WLAN_STA_WME))
+	if (sta->sta.wme)
 		sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_WME);
 	if (test_sta_flag(sta, WLAN_STA_MFP))
 		sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_MFP);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index d411bcc8ef08..89c40d5c0633 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -31,7 +31,6 @@
  *	when virtual port control is not in use.
  * @WLAN_STA_SHORT_PREAMBLE: Station is capable of receiving short-preamble
  *	frames.
- * @WLAN_STA_WME: Station is a QoS-STA.
  * @WLAN_STA_WDS: Station is one of our WDS peers.
  * @WLAN_STA_CLEAR_PS_FILT: Clear PS filter in hardware (using the
  *	IEEE80211_TX_CTL_CLEAR_PS_FILT control flag) when the next
@@ -69,7 +68,6 @@ enum ieee80211_sta_info_flags {
 	WLAN_STA_PS_STA,
 	WLAN_STA_AUTHORIZED,
 	WLAN_STA_SHORT_PREAMBLE,
-	WLAN_STA_WME,
 	WLAN_STA_WDS,
 	WLAN_STA_CLEAR_PS_FILT,
 	WLAN_STA_MFP,
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 1b21050be174..f2cb3b6c1871 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -316,8 +316,7 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
 	}
 
 	/* add the QoS param IE if both the peer and we support it */
-	if (local->hw.queues >= IEEE80211_NUM_ACS &&
-	    test_sta_flag(sta, WLAN_STA_WME))
+	if (local->hw.queues >= IEEE80211_NUM_ACS && sta->sta.wme)
 		ieee80211_tdls_add_wmm_param_ie(sdata, skb);
 
 	/* add any custom IEs that go before HT operation */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 464106c023d8..2051cc60f8ce 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1844,7 +1844,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 			memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN);
 			hdrlen = 30;
 			authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED);
-			wme_sta = test_sta_flag(sta, WLAN_STA_WME);
+			wme_sta = sta->sta.wme;
 		}
 		ap_sdata = container_of(sdata->bss, struct ieee80211_sub_if_data,
 					u.ap);
@@ -1957,7 +1957,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 			if (sta) {
 				authorized = test_sta_flag(sta,
 							WLAN_STA_AUTHORIZED);
-				wme_sta = test_sta_flag(sta, WLAN_STA_WME);
+				wme_sta = sta->sta.wme;
 				tdls_peer = test_sta_flag(sta,
 							  WLAN_STA_TDLS_PEER);
 				tdls_auth = test_sta_flag(sta,
@@ -2035,7 +2035,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		sta = sta_info_get(sdata, hdr.addr1);
 		if (sta) {
 			authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED);
-			wme_sta = test_sta_flag(sta, WLAN_STA_WME);
+			wme_sta = sta->sta.wme;
 		}
 	}
 
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index d51422c778de..6459946f0b74 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -118,7 +118,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	case NL80211_IFTYPE_AP_VLAN:
 		sta = rcu_dereference(sdata->u.vlan.sta);
 		if (sta) {
-			qos = test_sta_flag(sta, WLAN_STA_WME);
+			qos = sta->sta.wme;
 			break;
 		}
 	case NL80211_IFTYPE_AP:
@@ -145,7 +145,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	if (!sta && ra && !is_multicast_ether_addr(ra)) {
 		sta = sta_info_get(sdata, ra);
 		if (sta)
-			qos = test_sta_flag(sta, WLAN_STA_WME);
+			qos = sta->sta.wme;
 	}
 	rcu_read_unlock();
 
-- 
cgit v1.2.3


From 8a58d1f1f373238cb0d6d7f8d3dd723aa164b8ac Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Fri, 15 Aug 2014 12:38:41 -0600
Subject: blk-mq: get rid of unused BLK_MQ_F_SHOULD_SORT flag

We used to use this for determining whether to sort the dispatch list,
but it's unused now.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/blk-mq.h | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index eb726b9c5762..a1e31f274fcd 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -127,10 +127,9 @@ enum {
 	BLK_MQ_RQ_QUEUE_ERROR	= 2,	/* end IO with error */
 
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
-	BLK_MQ_F_SHOULD_SORT	= 1 << 1,
-	BLK_MQ_F_TAG_SHARED	= 1 << 2,
-	BLK_MQ_F_SG_MERGE	= 1 << 3,
-	BLK_MQ_F_SYSFS_UP	= 1 << 4,
+	BLK_MQ_F_TAG_SHARED	= 1 << 1,
+	BLK_MQ_F_SG_MERGE	= 1 << 2,
+	BLK_MQ_F_SYSFS_UP	= 1 << 3,
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
-- 
cgit v1.2.3


From 515d9b2c03943ca904cd135e1b1d9ddd168c1b27 Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Date: Tue, 12 Aug 2014 18:22:27 +0200
Subject: ata: remove deprecated struct ahci_platform_data

The last user of the deprecated struct ahci_platform_data has been
cleaned up recently (SPEAr1340 got a proper PHY driver).

Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Acked-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/ahci_platform.c    | 18 +-----------------
 drivers/ata/libahci_platform.c | 23 -----------------------
 include/linux/ahci_platform.h  | 13 -------------
 3 files changed, 1 insertion(+), 53 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index f61ddb9146d6..06f1d59fa678 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -32,7 +32,6 @@ static const struct ata_port_info ahci_port_info = {
 static int ahci_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	struct ahci_host_priv *hpriv;
 	int rc;
 
@@ -44,29 +43,14 @@ static int ahci_probe(struct platform_device *pdev)
 	if (rc)
 		return rc;
 
-	/*
-	 * Some platforms might need to prepare for mmio region access,
-	 * which could be done in the following init call. So, the mmio
-	 * region shouldn't be accessed before init (if provided) has
-	 * returned successfully.
-	 */
-	if (pdata && pdata->init) {
-		rc = pdata->init(dev, hpriv->mmio);
-		if (rc)
-			goto disable_resources;
-	}
-
 	if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci"))
 		hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ;
 
 	rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info);
 	if (rc)
-		goto pdata_exit;
+		goto disable_resources;
 
 	return 0;
-pdata_exit:
-	if (pdata && pdata->exit)
-		pdata->exit(dev);
 disable_resources:
 	ahci_platform_disable_resources(hpriv);
 	return rc;
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 5b92c290e6c6..c0510de8a4c9 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -502,13 +502,8 @@ EXPORT_SYMBOL_GPL(ahci_platform_init_host);
 
 static void ahci_host_stop(struct ata_host *host)
 {
-	struct device *dev = host->dev;
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	struct ahci_host_priv *hpriv = host->private_data;
 
-	if (pdata && pdata->exit)
-		pdata->exit(dev);
-
 	ahci_platform_disable_resources(hpriv);
 }
 
@@ -592,7 +587,6 @@ EXPORT_SYMBOL_GPL(ahci_platform_resume_host);
  */
 int ahci_platform_suspend(struct device *dev)
 {
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	struct ata_host *host = dev_get_drvdata(dev);
 	struct ahci_host_priv *hpriv = host->private_data;
 	int rc;
@@ -601,19 +595,9 @@ int ahci_platform_suspend(struct device *dev)
 	if (rc)
 		return rc;
 
-	if (pdata && pdata->suspend) {
-		rc = pdata->suspend(dev);
-		if (rc)
-			goto resume_host;
-	}
-
 	ahci_platform_disable_resources(hpriv);
 
 	return 0;
-
-resume_host:
-	ahci_platform_resume_host(dev);
-	return rc;
 }
 EXPORT_SYMBOL_GPL(ahci_platform_suspend);
 
@@ -629,7 +613,6 @@ EXPORT_SYMBOL_GPL(ahci_platform_suspend);
  */
 int ahci_platform_resume(struct device *dev)
 {
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	struct ata_host *host = dev_get_drvdata(dev);
 	struct ahci_host_priv *hpriv = host->private_data;
 	int rc;
@@ -638,12 +621,6 @@ int ahci_platform_resume(struct device *dev)
 	if (rc)
 		return rc;
 
-	if (pdata && pdata->resume) {
-		rc = pdata->resume(dev);
-		if (rc)
-			goto disable_resources;
-	}
-
 	rc = ahci_platform_resume_host(dev);
 	if (rc)
 		goto disable_resources;
diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h
index 09a947e8bc87..642d6ae4030c 100644
--- a/include/linux/ahci_platform.h
+++ b/include/linux/ahci_platform.h
@@ -22,19 +22,6 @@ struct ata_port_info;
 struct ahci_host_priv;
 struct platform_device;
 
-/*
- * Note ahci_platform_data is deprecated, it is only kept around for use
- * by the old da850 and spear13xx ahci code.
- * New drivers should instead declare their own platform_driver struct, and
- * use ahci_platform* functions in their own probe, suspend and resume methods.
- */
-struct ahci_platform_data {
-	int (*init)(struct device *dev, void __iomem *addr);
-	void (*exit)(struct device *dev);
-	int (*suspend)(struct device *dev);
-	int (*resume)(struct device *dev);
-};
-
 int ahci_platform_enable_clks(struct ahci_host_priv *hpriv);
 void ahci_platform_disable_clks(struct ahci_host_priv *hpriv);
 int ahci_platform_enable_resources(struct ahci_host_priv *hpriv);
-- 
cgit v1.2.3


From 005547e0828ce9064afebb1e6d56a18efd80e7a3 Mon Sep 17 00:00:00 2001
From: James Ban <james.ban.opensource@diasemi.com>
Date: Fri, 8 Aug 2014 14:27:04 +0900
Subject: regulator: da9211: support DA9213

This is a patch for supporting DA9213.

Signed-off-by: James Ban <james.ban.opensource@diasemi.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/Kconfig            |  9 ++--
 drivers/regulator/da9211-regulator.c | 95 ++++++++++++++++++++++++++++--------
 drivers/regulator/da9211-regulator.h |  7 ++-
 include/linux/regulator/da9211.h     |  7 ++-
 4 files changed, 91 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 2dc8289e5dba..1344aa83b438 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -199,13 +199,14 @@ config REGULATOR_DA9210
 	  interface.
 
 config REGULATOR_DA9211
-	tristate "Dialog Semiconductor DA9211/DA9212 regulator"
+	tristate "Dialog Semiconductor DA9211/DA9212/DA9213/DA9214 regulator"
 	depends on I2C
 	select REGMAP_I2C
 	help
-	  Say y here to support for the Dialog Semiconductor DA9211/DA9212.
-	  The DA9211/DA9212 is a multi-phase synchronous step down
-	  converter 12A DC-DC Buck controlled through an I2C
+	  Say y here to support for the Dialog Semiconductor DA9211/DA9212
+	  /DA9213/DA9214.
+	  The DA9211/DA9212/DA9213/DA9214 is a multi-phase synchronous
+	  step down converter 12A or 16A DC-DC Buck controlled through an I2C
 	  interface.
 
 config REGULATOR_DBX500_PRCMU
diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c
index 1482adafa1ad..ccc2e362d751 100644
--- a/drivers/regulator/da9211-regulator.c
+++ b/drivers/regulator/da9211-regulator.c
@@ -1,5 +1,5 @@
 /*
- * da9211-regulator.c - Regulator device driver for DA9211
+ * da9211-regulator.c - Regulator device driver for DA9211/DA9213
  * Copyright (C) 2014  Dialog Semiconductor Ltd.
  *
  * This library is free software; you can redistribute it and/or
@@ -27,6 +27,10 @@
 #include <linux/regulator/da9211.h>
 #include "da9211-regulator.h"
 
+/* DEVICE IDs */
+#define DA9211_DEVICE_ID	0x22
+#define DA9213_DEVICE_ID	0x23
+
 #define DA9211_BUCK_MODE_SLEEP	1
 #define DA9211_BUCK_MODE_SYNC	2
 #define DA9211_BUCK_MODE_AUTO	3
@@ -42,6 +46,7 @@ struct da9211 {
 	struct regulator_dev *rdev[DA9211_MAX_REGULATORS];
 	int num_regulator;
 	int chip_irq;
+	int chip_id;
 };
 
 static const struct regmap_range_cfg da9211_regmap_range[] = {
@@ -52,14 +57,14 @@ static const struct regmap_range_cfg da9211_regmap_range[] = {
 		.window_start = 0,
 		.window_len = 256,
 		.range_min = 0,
-		.range_max = 2*256,
+		.range_max = 5*128,
 	},
 };
 
 static const struct regmap_config da9211_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
-	.max_register = 2 * 256,
+	.max_register = 5 * 128,
 	.ranges = da9211_regmap_range,
 	.num_ranges = ARRAY_SIZE(da9211_regmap_range),
 };
@@ -69,11 +74,20 @@ static const struct regmap_config da9211_regmap_config = {
 #define DA9211_MAX_MV		1570
 #define DA9211_STEP_MV		10
 
-/* Current limits for buck (uA) indices corresponds with register values */
+/* Current limits for DA9211 buck (uA) indices
+ * corresponds with register values
+ */
 static const int da9211_current_limits[] = {
 	2000000, 2200000, 2400000, 2600000, 2800000, 3000000, 3200000, 3400000,
 	3600000, 3800000, 4000000, 4200000, 4400000, 4600000, 4800000, 5000000
 };
+/* Current limits for DA9213 buck (uA) indices
+ * corresponds with register values
+ */
+static const int da9213_current_limits[] = {
+	3000000, 3200000, 3400000, 3600000, 3800000, 4000000, 4200000, 4400000,
+	4600000, 4800000, 5000000, 5200000, 5400000, 5600000, 5800000, 6000000
+};
 
 static unsigned int da9211_buck_get_mode(struct regulator_dev *rdev)
 {
@@ -129,12 +143,26 @@ static int da9211_set_current_limit(struct regulator_dev *rdev, int min,
 {
 	int id = rdev_get_id(rdev);
 	struct da9211 *chip = rdev_get_drvdata(rdev);
-	int i;
+	int i, max_size;
+	const int *current_limits;
+
+	switch (chip->chip_id) {
+	case DA9211:
+		current_limits = da9211_current_limits;
+		max_size = ARRAY_SIZE(da9211_current_limits)-1;
+		break;
+	case DA9213:
+		current_limits = da9213_current_limits;
+		max_size = ARRAY_SIZE(da9213_current_limits)-1;
+		break;
+	default:
+		return -EINVAL;
+	}
 
 	/* search for closest to maximum */
-	for (i = ARRAY_SIZE(da9211_current_limits)-1; i >= 0; i--) {
-		if (min <= da9211_current_limits[i] &&
-		    max >= da9211_current_limits[i]) {
+	for (i = max_size; i >= 0; i--) {
+		if (min <= current_limits[i] &&
+		    max >= current_limits[i]) {
 				return regmap_update_bits(chip->regmap,
 					DA9211_REG_BUCK_ILIM,
 					(0x0F << id*4), (i << id*4));
@@ -150,14 +178,28 @@ static int da9211_get_current_limit(struct regulator_dev *rdev)
 	struct da9211 *chip = rdev_get_drvdata(rdev);
 	unsigned int data;
 	int ret;
+	const int *current_limits;
+
+	switch (chip->chip_id) {
+	case DA9211:
+		current_limits = da9211_current_limits;
+		break;
+	case DA9213:
+		current_limits = da9213_current_limits;
+		break;
+	default:
+		return -EINVAL;
+	}
 
 	ret = regmap_read(chip->regmap, DA9211_REG_BUCK_ILIM, &data);
 	if (ret < 0)
 		return ret;
 
-	/* select one of 16 values: 0000 (2000mA) to 1111 (5000mA) */
+	/* select one of 16 values: 0000 (2000mA or 3000mA)
+	 * to 1111 (5000mA or 6000mA).
+	 */
 	data = (data >> id*4) & 0x0F;
-	return da9211_current_limits[data];
+	return current_limits[data];
 }
 
 static struct regulator_ops da9211_buck_ops = {
@@ -264,10 +306,7 @@ static int da9211_regulator_init(struct da9211 *chip)
 	}
 
 	for (i = 0; i < chip->num_regulator; i++) {
-		if (chip->pdata)
-			config.init_data =
-				&(chip->pdata->init_data[i]);
-
+		config.init_data = &(chip->pdata->init_data[i]);
 		config.dev = chip->dev;
 		config.driver_data = chip;
 		config.regmap = chip->regmap;
@@ -301,6 +340,7 @@ static int da9211_i2c_probe(struct i2c_client *i2c,
 {
 	struct da9211 *chip;
 	int error, ret;
+	unsigned int data;
 
 	chip = devm_kzalloc(&i2c->dev, sizeof(struct da9211), GFP_KERNEL);
 
@@ -308,7 +348,7 @@ static int da9211_i2c_probe(struct i2c_client *i2c,
 	chip->regmap = devm_regmap_init_i2c(i2c, &da9211_regmap_config);
 	if (IS_ERR(chip->regmap)) {
 		error = PTR_ERR(chip->regmap);
-		dev_err(&i2c->dev, "Failed to allocate register map: %d\n",
+		dev_err(chip->dev, "Failed to allocate register map: %d\n",
 			error);
 		return error;
 	}
@@ -316,8 +356,22 @@ static int da9211_i2c_probe(struct i2c_client *i2c,
 	i2c_set_clientdata(i2c, chip);
 
 	chip->pdata = i2c->dev.platform_data;
-	if (!chip->pdata) {
-		dev_err(&i2c->dev, "No platform init data supplied\n");
+
+	ret = regmap_read(chip->regmap, DA9211_REG_DEVICE_ID, &data);
+	if (ret < 0) {
+		dev_err(chip->dev, "Failed to read DEVICE_ID reg: %d\n", ret);
+		return ret;
+	}
+
+	switch (data) {
+	case DA9211_DEVICE_ID:
+		chip->chip_id = DA9211;
+		break;
+	case DA9213_DEVICE_ID:
+		chip->chip_id = DA9213;
+		break;
+	default:
+		dev_err(chip->dev, "Unsupported device id = 0x%x.\n", data);
 		return -ENODEV;
 	}
 
@@ -340,13 +394,14 @@ static int da9211_i2c_probe(struct i2c_client *i2c,
 	ret = da9211_regulator_init(chip);
 
 	if (ret < 0)
-		dev_err(&i2c->dev, "Failed to initialize regulator: %d\n", ret);
+		dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret);
 
 	return ret;
 }
 
 static const struct i2c_device_id da9211_i2c_id[] = {
-	{"da9211", 0},
+	{"da9211", DA9211},
+	{"da9213", DA9213},
 	{},
 };
 
@@ -364,5 +419,5 @@ static struct i2c_driver da9211_regulator_driver = {
 module_i2c_driver(da9211_regulator_driver);
 
 MODULE_AUTHOR("James Ban <James.Ban.opensource@diasemi.com>");
-MODULE_DESCRIPTION("Regulator device driver for Dialog DA9211");
+MODULE_DESCRIPTION("Regulator device driver for Dialog DA9211/DA9213");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/da9211-regulator.h b/drivers/regulator/da9211-regulator.h
index 88b1769e8058..93fa9df2721c 100644
--- a/drivers/regulator/da9211-regulator.h
+++ b/drivers/regulator/da9211-regulator.h
@@ -1,5 +1,5 @@
 /*
- * da9211-regulator.h - Regulator definitions for DA9211
+ * da9211-regulator.h - Regulator definitions for DA9211/DA9213
  * Copyright (C) 2014  Dialog Semiconductor Ltd.
  *
  * This library is free software; you can redistribute it and/or
@@ -53,12 +53,15 @@
 /* BUCK Phase Selection*/
 #define DA9211_REG_CONFIG_E			0x147
 
+/* Device ID */
+#define	DA9211_REG_DEVICE_ID			0x201
+
 /*
  * Registers bits
  */
 /* DA9211_REG_PAGE_CON (addr=0x00) */
 #define	DA9211_REG_PAGE_SHIFT			1
-#define	DA9211_REG_PAGE_MASK			0x02
+#define	DA9211_REG_PAGE_MASK			0x06
 /* On I2C registers 0x00 - 0xFF */
 #define	DA9211_REG_PAGE0			0
 /* On I2C registers 0x100 - 0x1FF */
diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h
index 0981ce0e72cc..658c3c33f4c0 100644
--- a/include/linux/regulator/da9211.h
+++ b/include/linux/regulator/da9211.h
@@ -1,5 +1,5 @@
 /*
- * da9211.h - Regulator device driver for DA9211
+ * da9211.h - Regulator device driver for DA9211/DA9213
  * Copyright (C) 2014  Dialog Semiconductor Ltd.
  *
  * This library is free software; you can redistribute it and/or
@@ -20,6 +20,11 @@
 
 #define DA9211_MAX_REGULATORS	2
 
+enum da9211_chip_id {
+	DA9211,
+	DA9213,
+};
+
 struct da9211_pdata {
 	/*
 	 * Number of buck
-- 
cgit v1.2.3


From 0e4f417857083f399769491f6e7773d111debd0f Mon Sep 17 00:00:00 2001
From: Amit Daniel Kachhap <amit.daniel@samsung.com>
Date: Tue, 15 Jul 2014 16:32:51 +0530
Subject: regulator: s2mpxxx: Move regulator min/step voltages in common place

This is a cleanup patch and moves min/step voltages in a common samsung
header file so that they can be used by other s2mpxxx PMIC drivers. Only
few required macros are added currently and others can be added if needed.

Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Amit Daniel Kachhap <amit.daniel@samsung.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/s2mpa01.c         | 32 ++++++++++++------------
 drivers/regulator/s2mps11.c         | 50 ++++++++++++++++++-------------------
 include/linux/mfd/samsung/core.h    | 21 ++++++++++++++++
 include/linux/mfd/samsung/s2mpa01.h | 12 ---------
 include/linux/mfd/samsung/s2mps11.h |  9 -------
 include/linux/mfd/samsung/s2mps14.h | 10 --------
 6 files changed, 62 insertions(+), 72 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/s2mpa01.c b/drivers/regulator/s2mpa01.c
index ee83b4876420..962c5f192f7c 100644
--- a/drivers/regulator/s2mpa01.c
+++ b/drivers/regulator/s2mpa01.c
@@ -241,8 +241,8 @@ static struct regulator_ops s2mpa01_buck_ops = {
 	.ops		= &s2mpa01_ldo_ops,		\
 	.type		= REGULATOR_VOLTAGE,		\
 	.owner		= THIS_MODULE,			\
-	.min_uV		= S2MPA01_LDO_MIN,		\
-	.uV_step	= S2MPA01_LDO_STEP1,		\
+	.min_uV		= MIN_800_MV,			\
+	.uV_step	= STEP_50_MV,			\
 	.n_voltages	= S2MPA01_LDO_N_VOLTAGES,	\
 	.vsel_reg	= S2MPA01_REG_L1CTRL + num - 1,	\
 	.vsel_mask	= S2MPA01_LDO_VSEL_MASK,	\
@@ -255,8 +255,8 @@ static struct regulator_ops s2mpa01_buck_ops = {
 	.ops		= &s2mpa01_ldo_ops,		\
 	.type		= REGULATOR_VOLTAGE,		\
 	.owner		= THIS_MODULE,			\
-	.min_uV		= S2MPA01_LDO_MIN,		\
-	.uV_step	= S2MPA01_LDO_STEP2,		\
+	.min_uV		= MIN_800_MV,			\
+	.uV_step	= STEP_25_MV,			\
 	.n_voltages	= S2MPA01_LDO_N_VOLTAGES,	\
 	.vsel_reg	= S2MPA01_REG_L1CTRL + num - 1,	\
 	.vsel_mask	= S2MPA01_LDO_VSEL_MASK,	\
@@ -270,8 +270,8 @@ static struct regulator_ops s2mpa01_buck_ops = {
 	.ops		= &s2mpa01_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPA01_BUCK_MIN1,			\
-	.uV_step	= S2MPA01_BUCK_STEP1,			\
+	.min_uV		= MIN_600_MV,				\
+	.uV_step	= STEP_6_25_MV,				\
 	.n_voltages	= S2MPA01_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPA01_RAMP_DELAY,			\
 	.vsel_reg	= S2MPA01_REG_B1CTRL2 + (num - 1) * 2,	\
@@ -286,8 +286,8 @@ static struct regulator_ops s2mpa01_buck_ops = {
 	.ops		= &s2mpa01_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPA01_BUCK_MIN2,			\
-	.uV_step	= S2MPA01_BUCK_STEP1,			\
+	.min_uV		= MIN_800_MV,				\
+	.uV_step	= STEP_6_25_MV,				\
 	.n_voltages	= S2MPA01_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPA01_RAMP_DELAY,			\
 	.vsel_reg	= S2MPA01_REG_B5CTRL2,			\
@@ -302,8 +302,8 @@ static struct regulator_ops s2mpa01_buck_ops = {
 	.ops		= &s2mpa01_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPA01_BUCK_MIN1,			\
-	.uV_step	= S2MPA01_BUCK_STEP1,			\
+	.min_uV		= MIN_600_MV,				\
+	.uV_step	= STEP_6_25_MV,				\
 	.n_voltages	= S2MPA01_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPA01_RAMP_DELAY,			\
 	.vsel_reg	= S2MPA01_REG_B6CTRL2 + (num - 6) * 2,	\
@@ -318,8 +318,8 @@ static struct regulator_ops s2mpa01_buck_ops = {
 	.ops		= &s2mpa01_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPA01_BUCK_MIN2,			\
-	.uV_step	= S2MPA01_BUCK_STEP2,			\
+	.min_uV		= MIN_800_MV,				\
+	.uV_step	= STEP_12_5_MV,				\
 	.n_voltages	= S2MPA01_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPA01_RAMP_DELAY,			\
 	.vsel_reg	= S2MPA01_REG_B8CTRL2,			\
@@ -334,8 +334,8 @@ static struct regulator_ops s2mpa01_buck_ops = {
 	.ops		= &s2mpa01_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPA01_BUCK_MIN4,			\
-	.uV_step	= S2MPA01_BUCK_STEP2,			\
+	.min_uV		= MIN_1500_MV,				\
+	.uV_step	= STEP_12_5_MV,				\
 	.n_voltages	= S2MPA01_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPA01_RAMP_DELAY,			\
 	.vsel_reg	= S2MPA01_REG_B9CTRL2,			\
@@ -350,8 +350,8 @@ static struct regulator_ops s2mpa01_buck_ops = {
 	.ops		= &s2mpa01_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPA01_BUCK_MIN3,			\
-	.uV_step	= S2MPA01_BUCK_STEP2,			\
+	.min_uV		= MIN_1000_MV,				\
+	.uV_step	= STEP_12_5_MV,				\
 	.n_voltages	= S2MPA01_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPA01_RAMP_DELAY,			\
 	.vsel_reg	= S2MPA01_REG_B10CTRL2,			\
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index b16c53a8272f..3dede776a837 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -255,14 +255,14 @@ static struct regulator_ops s2mps11_buck_ops = {
 	.set_ramp_delay		= s2mps11_set_ramp_delay,
 };
 
-#define regulator_desc_s2mps11_ldo1(num)	{		\
+#define regulator_desc_s2mps11_ldo1(num)	{	\
 	.name		= "LDO"#num,			\
 	.id		= S2MPS11_LDO##num,		\
 	.ops		= &s2mps11_ldo_ops,		\
 	.type		= REGULATOR_VOLTAGE,		\
 	.owner		= THIS_MODULE,			\
-	.min_uV		= S2MPS11_LDO_MIN,		\
-	.uV_step	= S2MPS11_LDO_STEP1,		\
+	.min_uV		= MIN_800_MV,			\
+	.uV_step	= STEP_50_MV,			\
 	.n_voltages	= S2MPS11_LDO_N_VOLTAGES,	\
 	.vsel_reg	= S2MPS11_REG_L1CTRL + num - 1,	\
 	.vsel_mask	= S2MPS11_LDO_VSEL_MASK,	\
@@ -275,8 +275,8 @@ static struct regulator_ops s2mps11_buck_ops = {
 	.ops		= &s2mps11_ldo_ops,		\
 	.type		= REGULATOR_VOLTAGE,		\
 	.owner		= THIS_MODULE,			\
-	.min_uV		= S2MPS11_LDO_MIN,		\
-	.uV_step	= S2MPS11_LDO_STEP2,		\
+	.min_uV		= MIN_800_MV,			\
+	.uV_step	= STEP_25_MV,			\
 	.n_voltages	= S2MPS11_LDO_N_VOLTAGES,	\
 	.vsel_reg	= S2MPS11_REG_L1CTRL + num - 1,	\
 	.vsel_mask	= S2MPS11_LDO_VSEL_MASK,	\
@@ -290,8 +290,8 @@ static struct regulator_ops s2mps11_buck_ops = {
 	.ops		= &s2mps11_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPS11_BUCK_MIN1,			\
-	.uV_step	= S2MPS11_BUCK_STEP1,			\
+	.min_uV		= MIN_600_MV,				\
+	.uV_step	= STEP_6_25_MV,				\
 	.n_voltages	= S2MPS11_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPS11_RAMP_DELAY,			\
 	.vsel_reg	= S2MPS11_REG_B1CTRL2 + (num - 1) * 2,	\
@@ -306,8 +306,8 @@ static struct regulator_ops s2mps11_buck_ops = {
 	.ops		= &s2mps11_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPS11_BUCK_MIN1,			\
-	.uV_step	= S2MPS11_BUCK_STEP1,			\
+	.min_uV		= MIN_600_MV,				\
+	.uV_step	= STEP_6_25_MV,				\
 	.n_voltages	= S2MPS11_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPS11_RAMP_DELAY,			\
 	.vsel_reg	= S2MPS11_REG_B5CTRL2,			\
@@ -322,8 +322,8 @@ static struct regulator_ops s2mps11_buck_ops = {
 	.ops		= &s2mps11_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPS11_BUCK_MIN1,			\
-	.uV_step	= S2MPS11_BUCK_STEP1,			\
+	.min_uV		= MIN_600_MV,				\
+	.uV_step	= STEP_6_25_MV,				\
 	.n_voltages	= S2MPS11_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPS11_RAMP_DELAY,			\
 	.vsel_reg	= S2MPS11_REG_B6CTRL2 + (num - 6) * 2,	\
@@ -338,8 +338,8 @@ static struct regulator_ops s2mps11_buck_ops = {
 	.ops		= &s2mps11_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPS11_BUCK_MIN3,			\
-	.uV_step	= S2MPS11_BUCK_STEP3,			\
+	.min_uV		= MIN_3000_MV,				\
+	.uV_step	= STEP_25_MV,				\
 	.n_voltages	= S2MPS11_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPS11_RAMP_DELAY,			\
 	.vsel_reg	= S2MPS11_REG_B9CTRL2,			\
@@ -354,8 +354,8 @@ static struct regulator_ops s2mps11_buck_ops = {
 	.ops		= &s2mps11_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPS11_BUCK_MIN2,			\
-	.uV_step	= S2MPS11_BUCK_STEP2,			\
+	.min_uV		= MIN_750_MV,				\
+	.uV_step	= STEP_12_5_MV,				\
 	.n_voltages	= S2MPS11_BUCK_N_VOLTAGES,		\
 	.ramp_delay	= S2MPS11_RAMP_DELAY,			\
 	.vsel_reg	= S2MPS11_REG_B10CTRL2,			\
@@ -516,8 +516,8 @@ static struct regulator_ops s2mps14_reg_ops = {
 	.ops		= &s2mps14_reg_ops,		\
 	.type		= REGULATOR_VOLTAGE,		\
 	.owner		= THIS_MODULE,			\
-	.min_uV		= S2MPS14_LDO_MIN_800MV,	\
-	.uV_step	= S2MPS14_LDO_STEP_25MV,	\
+	.min_uV		= MIN_800_MV,			\
+	.uV_step	= STEP_25_MV,			\
 	.n_voltages	= S2MPS14_LDO_N_VOLTAGES,	\
 	.vsel_reg	= S2MPS14_REG_L1CTRL + num - 1,	\
 	.vsel_mask	= S2MPS14_LDO_VSEL_MASK,	\
@@ -530,8 +530,8 @@ static struct regulator_ops s2mps14_reg_ops = {
 	.ops		= &s2mps14_reg_ops,		\
 	.type		= REGULATOR_VOLTAGE,		\
 	.owner		= THIS_MODULE,			\
-	.min_uV		= S2MPS14_LDO_MIN_1800MV,	\
-	.uV_step	= S2MPS14_LDO_STEP_25MV,	\
+	.min_uV		= MIN_1800_MV,			\
+	.uV_step	= STEP_25_MV,			\
 	.n_voltages	= S2MPS14_LDO_N_VOLTAGES,	\
 	.vsel_reg	= S2MPS14_REG_L1CTRL + num - 1,	\
 	.vsel_mask	= S2MPS14_LDO_VSEL_MASK,	\
@@ -544,8 +544,8 @@ static struct regulator_ops s2mps14_reg_ops = {
 	.ops		= &s2mps14_reg_ops,		\
 	.type		= REGULATOR_VOLTAGE,		\
 	.owner		= THIS_MODULE,			\
-	.min_uV		= S2MPS14_LDO_MIN_800MV,	\
-	.uV_step	= S2MPS14_LDO_STEP_12_5MV,	\
+	.min_uV		= MIN_800_MV,			\
+	.uV_step	= STEP_12_5_MV,			\
 	.n_voltages	= S2MPS14_LDO_N_VOLTAGES,	\
 	.vsel_reg	= S2MPS14_REG_L1CTRL + num - 1,	\
 	.vsel_mask	= S2MPS14_LDO_VSEL_MASK,	\
@@ -558,8 +558,8 @@ static struct regulator_ops s2mps14_reg_ops = {
 	.ops		= &s2mps14_reg_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPS14_BUCK1235_MIN_600MV,		\
-	.uV_step	= S2MPS14_BUCK1235_STEP_6_25MV,		\
+	.min_uV		= MIN_600_MV,				\
+	.uV_step	= STEP_6_25_MV,				\
 	.n_voltages	= S2MPS14_BUCK_N_VOLTAGES,		\
 	.linear_min_sel = S2MPS14_BUCK1235_START_SEL,		\
 	.ramp_delay	= S2MPS14_BUCK_RAMP_DELAY,		\
@@ -574,8 +574,8 @@ static struct regulator_ops s2mps14_reg_ops = {
 	.ops		= &s2mps14_reg_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
 	.owner		= THIS_MODULE,				\
-	.min_uV		= S2MPS14_BUCK4_MIN_1400MV,		\
-	.uV_step	= S2MPS14_BUCK4_STEP_12_5MV,		\
+	.min_uV		= MIN_1400_MV,				\
+	.uV_step	= STEP_12_5_MV,				\
 	.n_voltages	= S2MPS14_BUCK_N_VOLTAGES,		\
 	.linear_min_sel = S2MPS14_BUCK4_START_SEL,		\
 	.ramp_delay	= S2MPS14_BUCK_RAMP_DELAY,		\
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index b5f73de81aad..1825edacbda7 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -14,6 +14,27 @@
 #ifndef __LINUX_MFD_SEC_CORE_H
 #define __LINUX_MFD_SEC_CORE_H
 
+/* Macros to represent minimum voltages for LDO/BUCK */
+#define MIN_3000_MV		3000000
+#define MIN_2500_MV		2500000
+#define MIN_2000_MV		2000000
+#define MIN_1800_MV		1800000
+#define MIN_1500_MV		1500000
+#define MIN_1400_MV		1400000
+#define MIN_1000_MV		1000000
+
+#define MIN_900_MV		900000
+#define MIN_850_MV		850000
+#define MIN_800_MV		800000
+#define MIN_750_MV		750000
+#define MIN_600_MV		600000
+
+/* Macros to represent steps for LDO/BUCK */
+#define STEP_50_MV		50000
+#define STEP_25_MV		25000
+#define STEP_12_5_MV		12500
+#define STEP_6_25_MV		6250
+
 enum sec_device_type {
 	S5M8751X,
 	S5M8763X,
diff --git a/include/linux/mfd/samsung/s2mpa01.h b/include/linux/mfd/samsung/s2mpa01.h
index fbc63bc0d6a2..2766108bca2f 100644
--- a/include/linux/mfd/samsung/s2mpa01.h
+++ b/include/linux/mfd/samsung/s2mpa01.h
@@ -155,18 +155,6 @@ enum s2mpa01_regulators {
 	S2MPA01_REGULATOR_MAX,
 };
 
-#define S2MPA01_BUCK_MIN1	600000
-#define S2MPA01_BUCK_MIN2	800000
-#define S2MPA01_BUCK_MIN3	1000000
-#define S2MPA01_BUCK_MIN4	1500000
-#define S2MPA01_LDO_MIN		800000
-
-#define S2MPA01_BUCK_STEP1	6250
-#define S2MPA01_BUCK_STEP2	12500
-
-#define S2MPA01_LDO_STEP1	50000
-#define S2MPA01_LDO_STEP2	25000
-
 #define S2MPA01_LDO_VSEL_MASK	0x3F
 #define S2MPA01_BUCK_VSEL_MASK	0xFF
 #define S2MPA01_ENABLE_MASK	(0x03 << S2MPA01_ENABLE_SHIFT)
diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h
index b3ddf98dec37..7981a9d77d3f 100644
--- a/include/linux/mfd/samsung/s2mps11.h
+++ b/include/linux/mfd/samsung/s2mps11.h
@@ -171,15 +171,6 @@ enum s2mps11_regulators {
 	S2MPS11_REGULATOR_MAX,
 };
 
-#define S2MPS11_BUCK_MIN1	600000
-#define S2MPS11_BUCK_MIN2	750000
-#define S2MPS11_BUCK_MIN3	3000000
-#define S2MPS11_LDO_MIN	800000
-#define S2MPS11_BUCK_STEP1	6250
-#define S2MPS11_BUCK_STEP2	12500
-#define S2MPS11_BUCK_STEP3	25000
-#define S2MPS11_LDO_STEP1	50000
-#define S2MPS11_LDO_STEP2	25000
 #define S2MPS11_LDO_VSEL_MASK	0x3F
 #define S2MPS11_BUCK_VSEL_MASK	0xFF
 #define S2MPS11_ENABLE_MASK	(0x03 << S2MPS11_ENABLE_SHIFT)
diff --git a/include/linux/mfd/samsung/s2mps14.h b/include/linux/mfd/samsung/s2mps14.h
index 900cd7a04314..c92f4782afb5 100644
--- a/include/linux/mfd/samsung/s2mps14.h
+++ b/include/linux/mfd/samsung/s2mps14.h
@@ -123,10 +123,6 @@ enum s2mps14_regulators {
 };
 
 /* Regulator constraints for BUCKx */
-#define S2MPS14_BUCK1235_MIN_600MV	600000
-#define S2MPS14_BUCK4_MIN_1400MV	1400000
-#define S2MPS14_BUCK1235_STEP_6_25MV	6250
-#define S2MPS14_BUCK4_STEP_12_5MV	12500
 #define S2MPS14_BUCK1235_START_SEL	0x20
 #define S2MPS14_BUCK4_START_SEL		0x40
 /*
@@ -136,12 +132,6 @@ enum s2mps14_regulators {
  */
 #define S2MPS14_BUCK_RAMP_DELAY		12500
 
-/* Regulator constraints for different types of LDOx */
-#define S2MPS14_LDO_MIN_800MV		800000
-#define S2MPS14_LDO_MIN_1800MV		1800000
-#define S2MPS14_LDO_STEP_12_5MV		12500
-#define S2MPS14_LDO_STEP_25MV		25000
-
 #define S2MPS14_LDO_VSEL_MASK		0x3F
 #define S2MPS14_BUCK_VSEL_MASK		0xFF
 #define S2MPS14_ENABLE_MASK		(0x03 << S2MPS14_ENABLE_SHIFT)
-- 
cgit v1.2.3


From 272e2315fac3bfca0edfa3252b8a643c425602af Mon Sep 17 00:00:00 2001
From: Guodong Xu <guodong.xu@linaro.org>
Date: Wed, 13 Aug 2014 19:33:38 +0800
Subject: regulator: core: add const qualifier to ops in struct regulator_desc

struct regulator_ops *ops is a member in struct regulator_desc, which gets
its value from individual regulator driver upon regulator_register() and
is used by regulator core APIs. It's not allowed for regulator core to
modify any of these callbacks in *ops. Add 'const' qualifier to enforce that.

Signed-off-by: Guodong Xu <guodong.xu@linaro.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/core.c         | 24 ++++++++++++------------
 include/linux/regulator/driver.h |  2 +-
 2 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a3c3785901f5..052e7f1f011d 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -839,7 +839,7 @@ static void print_constraints(struct regulator_dev *rdev)
 static int machine_constraints_voltage(struct regulator_dev *rdev,
 	struct regulation_constraints *constraints)
 {
-	struct regulator_ops *ops = rdev->desc->ops;
+	const struct regulator_ops *ops = rdev->desc->ops;
 	int ret;
 
 	/* do we need to apply the constraint voltage */
@@ -938,7 +938,7 @@ static int machine_constraints_voltage(struct regulator_dev *rdev,
 static int machine_constraints_current(struct regulator_dev *rdev,
 	struct regulation_constraints *constraints)
 {
-	struct regulator_ops *ops = rdev->desc->ops;
+	const struct regulator_ops *ops = rdev->desc->ops;
 	int ret;
 
 	if (!constraints->min_uA && !constraints->max_uA)
@@ -982,7 +982,7 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 	const struct regulation_constraints *constraints)
 {
 	int ret = 0;
-	struct regulator_ops *ops = rdev->desc->ops;
+	const struct regulator_ops *ops = rdev->desc->ops;
 
 	if (constraints)
 		rdev->constraints = kmemdup(constraints, sizeof(*constraints),
@@ -2208,9 +2208,9 @@ EXPORT_SYMBOL_GPL(regulator_count_voltages);
  */
 int regulator_list_voltage(struct regulator *regulator, unsigned selector)
 {
-	struct regulator_dev	*rdev = regulator->rdev;
-	struct regulator_ops	*ops = rdev->desc->ops;
-	int			ret;
+	struct regulator_dev *rdev = regulator->rdev;
+	const struct regulator_ops *ops = rdev->desc->ops;
+	int ret;
 
 	if (rdev->desc->fixed_uV && rdev->desc->n_voltages == 1 && !selector)
 		return rdev->desc->fixed_uV;
@@ -2572,8 +2572,8 @@ EXPORT_SYMBOL_GPL(regulator_set_voltage);
 int regulator_set_voltage_time(struct regulator *regulator,
 			       int old_uV, int new_uV)
 {
-	struct regulator_dev	*rdev = regulator->rdev;
-	struct regulator_ops	*ops = rdev->desc->ops;
+	struct regulator_dev *rdev = regulator->rdev;
+	const struct regulator_ops *ops = rdev->desc->ops;
 	int old_sel = -1;
 	int new_sel = -1;
 	int voltage;
@@ -3336,9 +3336,9 @@ EXPORT_SYMBOL_GPL(regulator_mode_to_status);
  */
 static int add_regulator_attributes(struct regulator_dev *rdev)
 {
-	struct device		*dev = &rdev->dev;
-	struct regulator_ops	*ops = rdev->desc->ops;
-	int			status = 0;
+	struct device *dev = &rdev->dev;
+	const struct regulator_ops *ops = rdev->desc->ops;
+	int status = 0;
 
 	/* some attributes need specific methods to be displayed */
 	if ((ops->get_voltage && ops->get_voltage(rdev) >= 0) ||
@@ -3905,7 +3905,7 @@ core_initcall(regulator_init);
 static int __init regulator_init_complete(void)
 {
 	struct regulator_dev *rdev;
-	struct regulator_ops *ops;
+	const struct regulator_ops *ops;
 	struct regulation_constraints *c;
 	int enabled, ret;
 
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index bbe03a1924c0..4b628139a9cb 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -245,7 +245,7 @@ struct regulator_desc {
 	int id;
 	bool continuous_voltage_range;
 	unsigned n_voltages;
-	struct regulator_ops *ops;
+	const struct regulator_ops *ops;
 	int irq;
 	enum regulator_type type;
 	struct module *owner;
-- 
cgit v1.2.3


From 871f565055ed232e5751da18a331b73e8254adaf Mon Sep 17 00:00:00 2001
From: Guodong Xu <guodong.xu@linaro.org>
Date: Wed, 13 Aug 2014 19:33:40 +0800
Subject: regulator: core: add guard delay between calling regulator_disable
 and _enable

Some regulator require a minimum delay between its disable and next enable.
This is to avoid damages when out-of-range frequent disable/enable of a
single regulator can bring to the regulator chip.

Add @off_on_delay to struct regulator_desc. Device drivers' can use this field
to set this guard time.

Add @last_off_jiffy to struct regulator_dev. When @off_on_delay is set by
driver, regulator core can store its last off (disable) time into this field.

Signed-off-by: Guodong Xu <guodong.xu@linaro.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/core.c         | 31 +++++++++++++++++++++++++++++++
 include/linux/regulator/driver.h |  6 ++++++
 2 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index dc0e9813b62d..1e976b6320a2 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1813,6 +1813,31 @@ static int _regulator_do_enable(struct regulator_dev *rdev)
 
 	trace_regulator_enable(rdev_get_name(rdev));
 
+	if (rdev->desc->off_on_delay) {
+		/* if needed, keep a distance of off_on_delay from last time
+		 * this regulator was disabled.
+		 */
+		unsigned long start_jiffy = jiffies;
+		unsigned long intended, max_delay, remaining;
+
+		max_delay = usecs_to_jiffies(rdev->desc->off_on_delay);
+		intended = rdev->last_off_jiffy + max_delay;
+
+		if (time_before(start_jiffy, intended)) {
+			/* calc remaining jiffies to deal with one-time
+			 * timer wrapping.
+			 * in case of multiple timer wrapping, either it can be
+			 * detected by out-of-range remaining, or it cannot be
+			 * detected and we gets a panelty of
+			 * _regulator_enable_delay().
+			 */
+			remaining = intended - start_jiffy;
+			if (remaining <= max_delay)
+				_regulator_enable_delay(
+						jiffies_to_usecs(remaining));
+		}
+	}
+
 	if (rdev->ena_pin) {
 		ret = regulator_ena_gpio_ctrl(rdev, true);
 		if (ret < 0)
@@ -1925,6 +1950,12 @@ static int _regulator_do_disable(struct regulator_dev *rdev)
 			return ret;
 	}
 
+	/* cares about last_off_jiffy only if off_on_delay is required by
+	 * device.
+	 */
+	if (rdev->desc->off_on_delay)
+		rdev->last_off_jiffy = jiffies;
+
 	trace_regulator_disable_complete(rdev_get_name(rdev));
 
 	return 0;
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 4b628139a9cb..efe058f8f746 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -238,6 +238,7 @@ enum regulator_type {
  * @bypass_val_off: Disabling value for control when using regmap set_bypass
  *
  * @enable_time: Time taken for initial enable of regulator (in uS).
+ * @off_on_delay: guard time (in uS), before re-enabling a regulator
  */
 struct regulator_desc {
 	const char *name;
@@ -276,6 +277,8 @@ struct regulator_desc {
 	unsigned int bypass_val_off;
 
 	unsigned int enable_time;
+
+	unsigned int off_on_delay;
 };
 
 /**
@@ -348,6 +351,9 @@ struct regulator_dev {
 
 	struct regulator_enable_gpio *ena_pin;
 	unsigned int ena_gpio_state:1;
+
+	/* time when this regulator was disabled last time */
+	unsigned long last_off_jiffy;
 };
 
 struct regulator_dev *
-- 
cgit v1.2.3


From 8ad9f9efcc7656cafb56bbbcd545f817a742bf32 Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <s.nawrocki@samsung.com>
Date: Mon, 16 Jun 2014 16:33:46 +0200
Subject: ASoC: Drop const from struct snd_soc_dai_link *of_node members
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Dropping the const qualifiers prevents "passing argument 1 of ‘of_node_put’
discards ‘const’ qualifier from pointer target type" type warnings when
compiling the code dropping reference to cpu_of_node, codec_of_node or
platform_of_node with with an of_node_put() function call.

This lets us to avoid casting to struct device_node * or caching variables
internally in drivers just to be able to properly drop a reference to the
OF node on clean up paths.

Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index be6ecae247b0..fd58371c63ff 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -897,7 +897,7 @@ struct snd_soc_dai_link {
 	 * only for codec to codec links, or systems using device tree.
 	 */
 	const char *cpu_name;
-	const struct device_node *cpu_of_node;
+	struct device_node *cpu_of_node;
 	/*
 	 * You MAY specify the DAI name of the CPU DAI. If this information is
 	 * omitted, the CPU-side DAI is matched using .cpu_name/.cpu_of_node
@@ -909,7 +909,7 @@ struct snd_soc_dai_link {
 	 * DT/OF node, but not both.
 	 */
 	const char *codec_name;
-	const struct device_node *codec_of_node;
+	struct device_node *codec_of_node;
 	/* You MUST specify the DAI name within the codec */
 	const char *codec_dai_name;
 
@@ -922,7 +922,7 @@ struct snd_soc_dai_link {
 	 * do not need a platform.
 	 */
 	const char *platform_name;
-	const struct device_node *platform_of_node;
+	struct device_node *platform_of_node;
 	int be_id;	/* optional ID for machine driver BE identification */
 
 	const struct snd_soc_pcm_stream *params;
-- 
cgit v1.2.3


From eef5bb2445ca49911c93c08ed0fb2ea7363ea945 Mon Sep 17 00:00:00 2001
From: Brian Austin <brian.austin@cirrus.com>
Date: Mon, 4 Aug 2014 15:11:16 -0500
Subject: ASoC: cs35l32: Add support for CS35L32 Boosted Amplifier

This patch adds support for the Cirrus Logic CS35L32 Boosted Amplifier
I2S output provides monitor data to the SOC/CODEC/DSP for speaker protection/enhancement algorithms

Signed-off-by: Brian Austin <brian.austin@cirrus.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/dt-bindings/sound/cs35l32.h |  26 ++
 sound/soc/codecs/Kconfig            |   5 +
 sound/soc/codecs/Makefile           |   2 +
 sound/soc/codecs/cs35l32.c          | 647 ++++++++++++++++++++++++++++++++++++
 sound/soc/codecs/cs35l32.h          |  93 ++++++
 5 files changed, 773 insertions(+)
 create mode 100644 include/dt-bindings/sound/cs35l32.h
 create mode 100644 sound/soc/codecs/cs35l32.c
 create mode 100644 sound/soc/codecs/cs35l32.h

(limited to 'include')

diff --git a/include/dt-bindings/sound/cs35l32.h b/include/dt-bindings/sound/cs35l32.h
new file mode 100644
index 000000000000..0c6d6a3c15a2
--- /dev/null
+++ b/include/dt-bindings/sound/cs35l32.h
@@ -0,0 +1,26 @@
+#ifndef __DT_CS35L32_H
+#define __DT_CS35L32_H
+
+#define CS35L32_BOOST_MGR_AUTO		0
+#define CS35L32_BOOST_MGR_AUTO_AUDIO	1
+#define CS35L32_BOOST_MGR_BYPASS	2
+#define CS35L32_BOOST_MGR_FIXED		3
+
+#define CS35L32_DATA_CFG_LR_VP		0
+#define CS35L32_DATA_CFG_LR_STAT	1
+#define CS35L32_DATA_CFG_LR		2
+#define CS35L32_DATA_CFG_LR_VPSTAT	3
+
+#define CS35L32_BATT_THRESH_3_1V	0
+#define CS35L32_BATT_THRESH_3_2V	1
+#define CS35L32_BATT_THRESH_3_3V	2
+#define CS35L32_BATT_THRESH_3_4V	3
+
+#define CS35L32_BATT_RECOV_3_1V		0
+#define CS35L32_BATT_RECOV_3_2V		1
+#define CS35L32_BATT_RECOV_3_3V		2
+#define CS35L32_BATT_RECOV_3_4V		3
+#define CS35L32_BATT_RECOV_3_5V		4
+#define CS35L32_BATT_RECOV_3_6V		5
+
+#endif /* __DT_CS35L32_H */
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 8838838e25ed..77e5383b4361 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -43,6 +43,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_ALC5623 if I2C
 	select SND_SOC_ALC5632 if I2C
 	select SND_SOC_CQ0093VC if MFD_DAVINCI_VOICECODEC
+	select SND_SOC_CS35L32 if I2C
 	select SND_SOC_CS42L51_I2C if I2C
 	select SND_SOC_CS42L52 if I2C && INPUT
 	select SND_SOC_CS42L56 if I2C && INPUT
@@ -323,6 +324,10 @@ config SND_SOC_ALC5632
 config SND_SOC_CQ0093VC
 	tristate
 
+config SND_SOC_CS35L32
+	tristate "Cirrus Logic CS35L32 CODEC"
+	depends on I2C
+
 config SND_SOC_CS42L51
 	tristate
 
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index 20afe0f0c5be..1dacefbdac3c 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -32,6 +32,7 @@ snd-soc-ak4671-objs := ak4671.o
 snd-soc-ak5386-objs := ak5386.o
 snd-soc-arizona-objs := arizona.o
 snd-soc-cq93vc-objs := cq93vc.o
+snd-soc-cs35l32-objs := cs35l32.o
 snd-soc-cs42l51-objs := cs42l51.o
 snd-soc-cs42l51-i2c-objs := cs42l51-i2c.o
 snd-soc-cs42l52-objs := cs42l52.o
@@ -203,6 +204,7 @@ obj-$(CONFIG_SND_SOC_ALC5623)    += snd-soc-alc5623.o
 obj-$(CONFIG_SND_SOC_ALC5632)	+= snd-soc-alc5632.o
 obj-$(CONFIG_SND_SOC_ARIZONA)	+= snd-soc-arizona.o
 obj-$(CONFIG_SND_SOC_CQ0093VC) += snd-soc-cq93vc.o
+obj-$(CONFIG_SND_SOC_CS35L32)	+= snd-soc-cs35l32.o
 obj-$(CONFIG_SND_SOC_CS42L51)	+= snd-soc-cs42l51.o
 obj-$(CONFIG_SND_SOC_CS42L51_I2C)	+= snd-soc-cs42l51-i2c.o
 obj-$(CONFIG_SND_SOC_CS42L52)	+= snd-soc-cs42l52.o
diff --git a/sound/soc/codecs/cs35l32.c b/sound/soc/codecs/cs35l32.c
new file mode 100644
index 000000000000..90565d59def7
--- /dev/null
+++ b/sound/soc/codecs/cs35l32.c
@@ -0,0 +1,647 @@
+/*
+ * cs35l32.c -- CS35L32 ALSA SoC audio driver
+ *
+ * Copyright 2014 CirrusLogic, Inc.
+ *
+ * Author: Brian Austin <brian.austin@cirrus.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/version.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+#include <dt-bindings/sound/cs35l32.h>
+
+#include "cs35l32.h"
+
+#define CS35L32_NUM_SUPPLIES 2
+static const char *const cs35l32_supply_names[CS35L32_NUM_SUPPLIES] = {
+	"VA",
+	"VP",
+};
+
+struct  cs35l32_private {
+	struct regmap *regmap;
+	struct snd_soc_codec *codec;
+	struct regulator_bulk_data supplies[CS35L32_NUM_SUPPLIES];
+	struct cs35l32_platform_data pdata;
+	struct gpio_desc *reset_gpio;
+};
+
+static const struct reg_default cs35l32_reg_defaults[] = {
+
+	{ 0x06, 0x04 }, /* Power Ctl 1 */
+	{ 0x07, 0xE8 }, /* Power Ctl 2 */
+	{ 0x08, 0x40 }, /* Clock Ctl */
+	{ 0x09, 0x20 }, /* Low Battery Threshold */
+	{ 0x0A, 0x00 }, /* Voltage Monitor [RO] */
+	{ 0x0B, 0x40 }, /* Conv Peak Curr Protection CTL */
+	{ 0x0C, 0x07 }, /* IMON Scaling */
+	{ 0x0D, 0x03 }, /* Audio/LED Pwr Manager */
+	{ 0x0F, 0x20 }, /* Serial Port Control */
+	{ 0x10, 0x14 }, /* Class D Amp CTL */
+	{ 0x11, 0x00 }, /* Protection Release CTL */
+	{ 0x12, 0xFF }, /* Interrupt Mask 1 */
+	{ 0x13, 0xFF }, /* Interrupt Mask 2 */
+	{ 0x14, 0xFF }, /* Interrupt Mask 3 */
+	{ 0x19, 0x00 }, /* LED Flash Mode Current */
+	{ 0x1A, 0x00 }, /* LED Movie Mode Current */
+	{ 0x1B, 0x20 }, /* LED Flash Timer */
+	{ 0x1C, 0x00 }, /* LED Flash Inhibit Current */
+};
+
+static bool cs35l32_readable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS35L32_DEVID_AB:
+	case CS35L32_DEVID_CD:
+	case CS35L32_DEVID_E:
+	case CS35L32_FAB_ID:
+	case CS35L32_REV_ID:
+	case CS35L32_PWRCTL1:
+	case CS35L32_PWRCTL2:
+	case CS35L32_CLK_CTL:
+	case CS35L32_BATT_THRESHOLD:
+	case CS35L32_VMON:
+	case CS35L32_BST_CPCP_CTL:
+	case CS35L32_IMON_SCALING:
+	case CS35L32_AUDIO_LED_MNGR:
+	case CS35L32_ADSP_CTL:
+	case CS35L32_CLASSD_CTL:
+	case CS35L32_PROTECT_CTL:
+	case CS35L32_INT_MASK_1:
+	case CS35L32_INT_MASK_2:
+	case CS35L32_INT_MASK_3:
+	case CS35L32_INT_STATUS_1:
+	case CS35L32_INT_STATUS_2:
+	case CS35L32_INT_STATUS_3:
+	case CS35L32_LED_STATUS:
+	case CS35L32_FLASH_MODE:
+	case CS35L32_MOVIE_MODE:
+	case CS35L32_FLASH_TIMER:
+	case CS35L32_FLASH_INHIBIT:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool cs35l32_volatile_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS35L32_DEVID_AB:
+	case CS35L32_DEVID_CD:
+	case CS35L32_DEVID_E:
+	case CS35L32_FAB_ID:
+	case CS35L32_REV_ID:
+	case CS35L32_INT_STATUS_1:
+	case CS35L32_INT_STATUS_2:
+	case CS35L32_INT_STATUS_3:
+	case CS35L32_LED_STATUS:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static bool cs35l32_precious_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS35L32_INT_STATUS_1:
+	case CS35L32_INT_STATUS_2:
+	case CS35L32_INT_STATUS_3:
+	case CS35L32_LED_STATUS:
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static DECLARE_TLV_DB_SCALE(classd_ctl_tlv, 900, 300, 0);
+
+static const struct snd_kcontrol_new imon_ctl =
+	SOC_DAPM_SINGLE("Switch", CS35L32_PWRCTL2, 6, 1, 1);
+
+static const struct snd_kcontrol_new vmon_ctl =
+	SOC_DAPM_SINGLE("Switch", CS35L32_PWRCTL2, 7, 1, 1);
+
+static const struct snd_kcontrol_new vpmon_ctl =
+	SOC_DAPM_SINGLE("Switch", CS35L32_PWRCTL2, 5, 1, 1);
+
+static const struct snd_kcontrol_new cs35l32_snd_controls[] = {
+	SOC_SINGLE_TLV("Speaker Volume", CS35L32_CLASSD_CTL,
+		       3, 0x04, 1, classd_ctl_tlv),
+	SOC_SINGLE("Zero Cross Switch", CS35L32_CLASSD_CTL, 2, 1, 0),
+	SOC_SINGLE("Gain Manager Switch", CS35L32_AUDIO_LED_MNGR, 3, 1, 0),
+};
+
+static const struct snd_soc_dapm_widget cs35l32_dapm_widgets[] = {
+
+	SND_SOC_DAPM_SUPPLY("BOOST", CS35L32_PWRCTL1, 2, 1, NULL, 0),
+	SND_SOC_DAPM_OUT_DRV("Speaker", CS35L32_PWRCTL1, 7, 1, NULL, 0),
+
+	SND_SOC_DAPM_AIF_OUT("SDOUT", NULL, 0, CS35L32_PWRCTL2, 3, 1),
+
+	SND_SOC_DAPM_INPUT("VP"),
+	SND_SOC_DAPM_INPUT("ISENSE"),
+	SND_SOC_DAPM_INPUT("VSENSE"),
+
+	SND_SOC_DAPM_SWITCH("VMON ADC", CS35L32_PWRCTL2, 7, 1, &vmon_ctl),
+	SND_SOC_DAPM_SWITCH("IMON ADC", CS35L32_PWRCTL2, 6, 1, &imon_ctl),
+	SND_SOC_DAPM_SWITCH("VPMON ADC", CS35L32_PWRCTL2, 5, 1, &vpmon_ctl),
+};
+
+static const struct snd_soc_dapm_route cs35l32_audio_map[] = {
+
+	{"Speaker", NULL, "BOOST"},
+
+	{"VMON ADC", NULL, "VSENSE"},
+	{"IMON ADC", NULL, "ISENSE"},
+	{"VPMON ADC", NULL, "VP"},
+
+	{"SDOUT", "Switch", "VMON ADC"},
+	{"SDOUT",  "Switch", "IMON ADC"},
+	{"SDOUT", "Switch", "VPMON ADC"},
+
+	{"Capture", NULL, "SDOUT"},
+};
+
+static int cs35l32_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
+{
+	struct snd_soc_codec *codec = codec_dai->codec;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		snd_soc_update_bits(codec, CS35L32_ADSP_CTL,
+				    CS35L32_ADSP_MASTER_MASK,
+				CS35L32_ADSP_MASTER_MASK);
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		snd_soc_update_bits(codec, CS35L32_ADSP_CTL,
+				    CS35L32_ADSP_MASTER_MASK, 0);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int cs35l32_set_tristate(struct snd_soc_dai *dai, int tristate)
+{
+	struct snd_soc_codec *codec = dai->codec;
+
+	return snd_soc_update_bits(codec, CS35L32_PWRCTL2,
+					CS35L32_SDOUT_3ST, tristate << 3);
+}
+
+static const struct snd_soc_dai_ops cs35l32_ops = {
+	.set_fmt = cs35l32_set_dai_fmt,
+	.set_tristate = cs35l32_set_tristate,
+};
+
+static struct snd_soc_dai_driver cs35l32_dai[] = {
+	{
+		.name = "cs35l32-monitor",
+		.id = 0,
+		.capture = {
+			.stream_name = "Capture",
+			.channels_min = 2,
+			.channels_max = 2,
+			.rates = CS35L32_RATES,
+			.formats = CS35L32_FORMATS,
+		},
+		.ops = &cs35l32_ops,
+		.symmetric_rates = 1,
+	}
+};
+
+static int cs35l32_codec_set_sysclk(struct snd_soc_codec *codec,
+			      int clk_id, int source, unsigned int freq, int dir)
+{
+
+	switch (freq) {
+	case 6000000:
+		snd_soc_update_bits(codec, CS35L32_CLK_CTL,
+				    CS35L32_MCLK_DIV2_MASK, 0);
+		snd_soc_update_bits(codec, CS35L32_CLK_CTL,
+				    CS35L32_MCLK_RATIO_MASK,
+					CS35L32_MCLK_RATIO);
+		break;
+	case 12000000:
+		snd_soc_update_bits(codec, CS35L32_CLK_CTL,
+				    CS35L32_MCLK_DIV2_MASK,
+					CS35L32_MCLK_DIV2_MASK);
+		snd_soc_update_bits(codec, CS35L32_CLK_CTL,
+				    CS35L32_MCLK_RATIO_MASK,
+					CS35L32_MCLK_RATIO);
+		break;
+	case 6144000:
+		snd_soc_update_bits(codec, CS35L32_CLK_CTL,
+				    CS35L32_MCLK_DIV2_MASK, 0);
+		snd_soc_update_bits(codec, CS35L32_CLK_CTL,
+				    CS35L32_MCLK_RATIO_MASK, 0);
+		break;
+	case 12288000:
+		snd_soc_update_bits(codec, CS35L32_CLK_CTL,
+				    CS35L32_MCLK_DIV2_MASK,
+					CS35L32_MCLK_DIV2_MASK);
+		snd_soc_update_bits(codec, CS35L32_CLK_CTL,
+				    CS35L32_MCLK_RATIO_MASK, 0);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct snd_soc_codec_driver soc_codec_dev_cs35l32 = {
+	.set_sysclk = cs35l32_codec_set_sysclk,
+
+	.dapm_widgets = cs35l32_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(cs35l32_dapm_widgets),
+	.dapm_routes = cs35l32_audio_map,
+	.num_dapm_routes = ARRAY_SIZE(cs35l32_audio_map),
+
+	.controls = cs35l32_snd_controls,
+	.num_controls = ARRAY_SIZE(cs35l32_snd_controls),
+};
+
+/* Current and threshold powerup sequence Pg37 in datasheet */
+static const struct reg_default cs35l32_monitor_patch[] = {
+
+	{ 0x00, 0x99 },
+	{ 0x48, 0x17 },
+	{ 0x49, 0x56 },
+	{ 0x43, 0x01 },
+	{ 0x3B, 0x62 },
+	{ 0x3C, 0x80 },
+	{ 0x00, 0x00 },
+};
+
+static struct regmap_config cs35l32_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = CS35L32_MAX_REGISTER,
+	.reg_defaults = cs35l32_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(cs35l32_reg_defaults),
+	.volatile_reg = cs35l32_volatile_register,
+	.readable_reg = cs35l32_readable_register,
+	.precious_reg = cs35l32_precious_register,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static int cs35l32_handle_of_data(struct i2c_client *i2c_client,
+				    struct cs35l32_platform_data *pdata)
+{
+	struct device_node *np = i2c_client->dev.of_node;
+	unsigned int val;
+
+	if (of_property_read_u32(np, "cirrus,sdout-share", &val) >= 0)
+		pdata->sdout_share = val;
+
+	of_property_read_u32(np, "cirrus,boost-manager", &val);
+	switch (val) {
+	case CS35L32_BOOST_MGR_AUTO:
+	case CS35L32_BOOST_MGR_AUTO_AUDIO:
+	case CS35L32_BOOST_MGR_BYPASS:
+	case CS35L32_BOOST_MGR_FIXED:
+		pdata->boost_mng = val;
+		break;
+	default:
+		dev_err(&i2c_client->dev,
+			"Wrong cirrus,boost-manager DT value %d\n", val);
+		pdata->boost_mng = CS35L32_BOOST_MGR_BYPASS;
+	}
+
+	of_property_read_u32(np, "cirrus,sdout-datacfg", &val);
+	switch (val) {
+	case CS35L32_DATA_CFG_LR_VP:
+	case CS35L32_DATA_CFG_LR_STAT:
+	case CS35L32_DATA_CFG_LR:
+	case CS35L32_DATA_CFG_LR_VPSTAT:
+		pdata->sdout_datacfg = val;
+		break;
+	default:
+		dev_err(&i2c_client->dev,
+			"Wrong cirrus,sdout-datacfg DT value %d\n", val);
+		pdata->sdout_datacfg = CS35L32_DATA_CFG_LR;
+	}
+
+	of_property_read_u32(np, "cirrus,battery-threshold", &val);
+	switch (val) {
+	case CS35L32_BATT_THRESH_3_1V:
+	case CS35L32_BATT_THRESH_3_2V:
+	case CS35L32_BATT_THRESH_3_3V:
+	case CS35L32_BATT_THRESH_3_4V:
+		pdata->batt_thresh = val;
+		break;
+	default:
+		dev_err(&i2c_client->dev,
+			"Wrong cirrus,battery-threshold DT value %d\n", val);
+		pdata->batt_thresh = CS35L32_BATT_THRESH_3_3V;
+	}
+
+	of_property_read_u32(np, "cirrus,battery-recovery", &val);
+	switch (val) {
+	case CS35L32_BATT_RECOV_3_1V:
+	case CS35L32_BATT_RECOV_3_2V:
+	case CS35L32_BATT_RECOV_3_3V:
+	case CS35L32_BATT_RECOV_3_4V:
+	case CS35L32_BATT_RECOV_3_5V:
+	case CS35L32_BATT_RECOV_3_6V:
+		pdata->batt_recov = val;
+		break;
+	default:
+		dev_err(&i2c_client->dev,
+			"Wrong cirrus,battery-recovery DT value %d\n", val);
+		pdata->batt_recov = CS35L32_BATT_RECOV_3_4V;
+	}
+
+	return 0;
+}
+
+static int cs35l32_i2c_probe(struct i2c_client *i2c_client,
+				       const struct i2c_device_id *id)
+{
+	struct cs35l32_private *cs35l32;
+	struct cs35l32_platform_data *pdata =
+		dev_get_platdata(&i2c_client->dev);
+	int ret, i;
+	unsigned int devid = 0;
+	unsigned int reg;
+
+
+	cs35l32 = devm_kzalloc(&i2c_client->dev, sizeof(struct cs35l32_private),
+			       GFP_KERNEL);
+	if (!cs35l32) {
+		dev_err(&i2c_client->dev, "could not allocate codec\n");
+		return -ENOMEM;
+	}
+
+	i2c_set_clientdata(i2c_client, cs35l32);
+
+	cs35l32->regmap = devm_regmap_init_i2c(i2c_client, &cs35l32_regmap);
+	if (IS_ERR(cs35l32->regmap)) {
+		ret = PTR_ERR(cs35l32->regmap);
+		dev_err(&i2c_client->dev, "regmap_init() failed: %d\n", ret);
+		return ret;
+	}
+
+	if (pdata) {
+		cs35l32->pdata = *pdata;
+	} else {
+		pdata = devm_kzalloc(&i2c_client->dev,
+				     sizeof(struct cs35l32_platform_data),
+				GFP_KERNEL);
+		if (!pdata) {
+			dev_err(&i2c_client->dev, "could not allocate pdata\n");
+			return -ENOMEM;
+		}
+		if (i2c_client->dev.of_node) {
+			ret = cs35l32_handle_of_data(i2c_client,
+						     &cs35l32->pdata);
+			if (ret != 0)
+				return ret;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(cs35l32->supplies); i++)
+		cs35l32->supplies[i].supply = cs35l32_supply_names[i];
+
+	ret = devm_regulator_bulk_get(&i2c_client->dev,
+				      ARRAY_SIZE(cs35l32->supplies),
+				      cs35l32->supplies);
+	if (ret != 0) {
+		dev_err(&i2c_client->dev,
+			"Failed to request supplies: %d\n", ret);
+		return ret;
+	}
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(cs35l32->supplies),
+				    cs35l32->supplies);
+	if (ret != 0) {
+		dev_err(&i2c_client->dev,
+			"Failed to enable supplies: %d\n", ret);
+		return ret;
+	}
+
+	/* Reset the Device */
+	cs35l32->reset_gpio = devm_gpiod_get(&i2c_client->dev,
+		"reset-gpios");
+	if (IS_ERR(cs35l32->reset_gpio)) {
+		ret = PTR_ERR(cs35l32->reset_gpio);
+		if (ret != -ENOENT && ret != -ENOSYS)
+			return ret;
+
+		cs35l32->reset_gpio = NULL;
+	} else {
+		ret = gpiod_direction_output(cs35l32->reset_gpio, 0);
+		if (ret)
+			return ret;
+		gpiod_set_value_cansleep(cs35l32->reset_gpio, 1);
+	}
+
+	/* initialize codec */
+	ret = regmap_read(cs35l32->regmap, CS35L32_DEVID_AB, &reg);
+	devid = (reg & 0xFF) << 12;
+
+	ret = regmap_read(cs35l32->regmap, CS35L32_DEVID_CD, &reg);
+	devid |= (reg & 0xFF) << 4;
+
+	ret = regmap_read(cs35l32->regmap, CS35L32_DEVID_E, &reg);
+	devid |= (reg & 0xF0) >> 4;
+
+	if (devid != CS35L32_CHIP_ID) {
+		ret = -ENODEV;
+		dev_err(&i2c_client->dev,
+			"CS35L32 Device ID (%X). Expected %X\n",
+			devid, CS35L32_CHIP_ID);
+		return ret;
+	}
+
+	ret = regmap_read(cs35l32->regmap, CS35L32_REV_ID, &reg);
+	if (ret < 0) {
+		dev_err(&i2c_client->dev, "Get Revision ID failed\n");
+		return ret;
+	}
+
+	ret = regmap_register_patch(cs35l32->regmap, cs35l32_monitor_patch,
+				    ARRAY_SIZE(cs35l32_monitor_patch));
+	if (ret < 0) {
+		dev_err(&i2c_client->dev, "Failed to apply errata patch\n");
+		return ret;
+	}
+
+	dev_info(&i2c_client->dev,
+		 "Cirrus Logic CS35L32, Revision: %02X\n", reg & 0xFF);
+
+	/* Setup VBOOST Management */
+	if (cs35l32->pdata.boost_mng)
+		regmap_update_bits(cs35l32->regmap, CS35L32_AUDIO_LED_MNGR,
+				   CS35L32_BOOST_MASK,
+				cs35l32->pdata.boost_mng);
+
+	/* Setup ADSP Format Config */
+	if (cs35l32->pdata.sdout_share)
+		regmap_update_bits(cs35l32->regmap, CS35L32_ADSP_CTL,
+				    CS35L32_ADSP_SHARE_MASK,
+				cs35l32->pdata.sdout_share << 3);
+
+	/* Setup ADSP Data Configuration */
+	if (cs35l32->pdata.sdout_datacfg)
+		regmap_update_bits(cs35l32->regmap, CS35L32_ADSP_CTL,
+				   CS35L32_ADSP_DATACFG_MASK,
+				cs35l32->pdata.sdout_datacfg << 4);
+
+	/* Setup Low Battery Recovery  */
+	if (cs35l32->pdata.batt_recov)
+		regmap_update_bits(cs35l32->regmap, CS35L32_BATT_THRESHOLD,
+				   CS35L32_BATT_REC_MASK,
+				cs35l32->pdata.batt_recov << 1);
+
+	/* Setup Low Battery Threshold */
+	if (cs35l32->pdata.batt_thresh)
+		regmap_update_bits(cs35l32->regmap, CS35L32_BATT_THRESHOLD,
+				   CS35L32_BATT_THRESH_MASK,
+				cs35l32->pdata.batt_thresh << 4);
+
+	/* Power down the AMP */
+	regmap_update_bits(cs35l32->regmap, CS35L32_PWRCTL1, CS35L32_PDN_AMP,
+			    CS35L32_PDN_AMP);
+
+	/* Clear MCLK Error Bit since we don't have the clock yet */
+	ret = regmap_read(cs35l32->regmap, CS35L32_INT_STATUS_1, &reg);
+
+	ret =  snd_soc_register_codec(&i2c_client->dev,
+			&soc_codec_dev_cs35l32, cs35l32_dai,
+			ARRAY_SIZE(cs35l32_dai));
+	if (ret < 0)
+		goto err_disable;
+
+	return 0;
+
+err_disable:
+	regulator_bulk_disable(ARRAY_SIZE(cs35l32->supplies),
+			       cs35l32->supplies);
+}
+
+static int cs35l32_i2c_remove(struct i2c_client *i2c_client)
+{
+	struct cs35l32_private *cs35l32 = i2c_get_clientdata(i2c_client);
+
+	snd_soc_unregister_codec(&i2c_client->dev);
+
+	/* Hold down reset */
+	if (cs35l32->reset_gpio)
+		gpiod_set_value_cansleep(cs35l32->reset_gpio, 0);
+
+	regulator_bulk_free(ARRAY_SIZE(cs35l32->supplies), cs35l32->supplies);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_RUNTIME
+static int cs35l32_runtime_suspend(struct device *dev)
+{
+	struct cs35l32_private *cs35l32 = dev_get_drvdata(dev);
+
+	regcache_cache_only(cs35l32->regmap, true);
+	regcache_mark_dirty(cs35l32->regmap);
+
+	/* Hold down reset */
+	if (cs35l32->reset_gpio)
+		gpiod_set_value_cansleep(cs35l32->reset_gpio, 0);
+
+	/* remove power */
+	regulator_bulk_disable(ARRAY_SIZE(cs35l32->supplies),
+			       cs35l32->supplies);
+
+	return 0;
+}
+
+static int cs35l32_runtime_resume(struct device *dev)
+{
+	struct cs35l32_private *cs35l32 = dev_get_drvdata(dev);
+	int ret;
+
+	/* Enable power */
+	ret = regulator_bulk_enable(ARRAY_SIZE(cs35l32->supplies),
+				    cs35l32->supplies);
+	if (ret != 0) {
+		dev_err(dev, "Failed to enable supplies: %d\n",
+			ret);
+		return ret;
+	}
+
+	if (cs35l32->reset_gpio)
+		gpiod_set_value_cansleep(cs35l32->reset_gpio, 1);
+
+	regcache_cache_only(cs35l32->regmap, false);
+	regcache_sync(cs35l32->regmap);
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops cs35l32_runtime_pm = {
+	SET_RUNTIME_PM_OPS(cs35l32_runtime_suspend, cs35l32_runtime_resume,
+			   NULL)
+};
+
+static const struct of_device_id cs35l32_of_match[] = {
+	{ .compatible = "cirrus,cs35l32", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, cs35l32_of_match);
+
+
+static const struct i2c_device_id cs35l32_id[] = {
+	{"cs35l32", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, cs35l32_id);
+
+static struct i2c_driver cs35l32_i2c_driver = {
+	.driver = {
+		   .name = "cs35l32",
+		   .owner = THIS_MODULE,
+		   .pm = &cs35l32_runtime_pm,
+		   .of_match_table = cs35l32_of_match,
+		   },
+	.id_table = cs35l32_id,
+	.probe = cs35l32_i2c_probe,
+	.remove = cs35l32_i2c_remove,
+};
+
+module_i2c_driver(cs35l32_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC CS35L32 driver");
+MODULE_AUTHOR("Brian Austin, Cirrus Logic Inc, <brian.austin@cirrus.com>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/cs35l32.h b/sound/soc/codecs/cs35l32.h
new file mode 100644
index 000000000000..31ab804a22bc
--- /dev/null
+++ b/sound/soc/codecs/cs35l32.h
@@ -0,0 +1,93 @@
+/*
+ * cs35l32.h -- CS35L32 ALSA SoC audio driver
+ *
+ * Copyright 2014 CirrusLogic, Inc.
+ *
+ * Author: Brian Austin <brian.austin@cirrus.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __CS35L32_H__
+#define __CS35L32_H__
+
+struct cs35l32_platform_data {
+	/* Low Battery Threshold */
+	unsigned int batt_thresh;
+	/* Low Battery Recovery */
+	unsigned int batt_recov;
+	/* LED Current Management*/
+	unsigned int led_mng;
+	/* Audio Gain w/ LED */
+	unsigned int audiogain_mng;
+	/* Boost Management */
+	unsigned int boost_mng;
+	/* Data CFG for DUAL device */
+	unsigned int sdout_datacfg;
+	/* SDOUT Sharing */
+	unsigned int sdout_share;
+};
+
+#define CS35L32_CHIP_ID		0x00035A32
+#define CS35L32_DEVID_AB	0x01	/* Device ID A & B [RO] */
+#define CS35L32_DEVID_CD	0x02    /* Device ID C & D [RO] */
+#define CS35L32_DEVID_E		0x03    /* Device ID E [RO] */
+#define CS35L32_FAB_ID		0x04	/* Fab ID [RO] */
+#define CS35L32_REV_ID		0x05	/* Revision ID [RO] */
+#define CS35L32_PWRCTL1		0x06    /* Power Ctl 1 */
+#define CS35L32_PWRCTL2		0x07    /* Power Ctl 2 */
+#define CS35L32_CLK_CTL		0x08	/* Clock Ctl */
+#define CS35L32_BATT_THRESHOLD	0x09	/* Low Battery Threshold */
+#define CS35L32_VMON		0x0A	/* Voltage Monitor [RO] */
+#define CS35L32_BST_CPCP_CTL	0x0B	/* Conv Peak Curr Protection CTL */
+#define CS35L32_IMON_SCALING	0x0C	/* IMON Scaling */
+#define CS35L32_AUDIO_LED_MNGR	0x0D	/* Audio/LED Pwr Manager */
+#define CS35L32_ADSP_CTL	0x0F	/* Serial Port Control */
+#define CS35L32_CLASSD_CTL	0x10	/* Class D Amp CTL */
+#define CS35L32_PROTECT_CTL	0x11	/* Protection Release CTL */
+#define CS35L32_INT_MASK_1	0x12	/* Interrupt Mask 1 */
+#define CS35L32_INT_MASK_2	0x13	/* Interrupt Mask 2 */
+#define CS35L32_INT_MASK_3	0x14	/* Interrupt Mask 3 */
+#define CS35L32_INT_STATUS_1	0x15	/* Interrupt Status 1 [RO] */
+#define CS35L32_INT_STATUS_2	0x16	/* Interrupt Status 2 [RO] */
+#define CS35L32_INT_STATUS_3	0x17	/* Interrupt Status 3 [RO] */
+#define CS35L32_LED_STATUS	0x18	/* LED Lighting Status [RO] */
+#define CS35L32_FLASH_MODE	0x19	/* LED Flash Mode Current */
+#define CS35L32_MOVIE_MODE	0x1A	/* LED Movie Mode Current */
+#define CS35L32_FLASH_TIMER	0x1B	/* LED Flash Timer */
+#define CS35L32_FLASH_INHIBIT	0x1C	/* LED Flash Inhibit Current */
+#define CS35L32_MAX_REGISTER	0x1C
+
+#define CS35L32_MCLK_DIV2	0x01
+#define CS35L32_MCLK_RATIO	0x01
+#define CS35L32_MCLKDIS		0x80
+#define CS35L32_PDN_ALL		0x01
+#define CS35L32_PDN_AMP		0x80
+#define CS35L32_PDN_BOOST	0x04
+#define CS35L32_PDN_IMON	0x40
+#define CS35L32_PDN_VMON	0x80
+#define CS35L32_PDN_VPMON	0x20
+#define CS35L32_PDN_ADSP	0x08
+
+#define CS35L32_MCLK_DIV2_MASK		0x40
+#define CS35L32_MCLK_RATIO_MASK		0x01
+#define CS35L32_MCLK_MASK		0x41
+#define CS35L32_ADSP_MASTER_MASK	0x40
+#define CS35L32_BOOST_MASK		0x03
+#define CS35L32_GAIN_MGR_MASK		0x08
+#define CS35L32_ADSP_SHARE_MASK		0x08
+#define CS35L32_ADSP_DATACFG_MASK	0x30
+#define CS35L32_SDOUT_3ST		0x80
+#define CS35L32_BATT_REC_MASK		0x0E
+#define CS35L32_BATT_THRESH_MASK	0x30
+
+#define CS35L32_RATES (SNDRV_PCM_RATE_48000)
+#define CS35L32_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | \
+			SNDRV_PCM_FMTBIT_S24_LE | \
+			SNDRV_PCM_FMTBIT_S32_LE)
+
+
+#endif
-- 
cgit v1.2.3


From 16466f4284154311f163a58b77379eb186274f87 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 14 Aug 2014 16:52:51 -0700
Subject: net: phy: bcm7xxx: remove 28nm wildcard entry

A wildcard entry with the 32-bits OUI 0x600d8400 was added as part of
the BCM7xxx internal PHY driver, but that entry might match other PHYs
that are not covered by this driver, so let's just remove it.

Fixes: b560a58c45c6 ("net: phy: add Broadcom BCM7xxx internal PHY driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@greenl8ke.davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 14 --------------
 include/linux/brcmphy.h   |  1 -
 2 files changed, 15 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 526b94cea569..2b40548c85d5 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -286,19 +286,6 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.suspend	= bcm7xxx_suspend,
 	.resume		= bcm7xxx_28nm_config_init,
 	.driver		= { .owner = THIS_MODULE },
-}, {
-	.name		= "Broadcom BCM7XXX 28nm",
-	.phy_id		= PHY_ID_BCM7XXX_28,
-	.phy_id_mask	= PHY_BCM_OUI_MASK,
-	.features	= PHY_GBIT_FEATURES |
-			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
-	.flags		= PHY_IS_INTERNAL,
-	.config_init	= bcm7xxx_28nm_config_init,
-	.config_aneg	= genphy_config_aneg,
-	.read_status	= genphy_read_status,
-	.suspend	= bcm7xxx_suspend,
-	.resume		= bcm7xxx_28nm_config_init,
-	.driver		= { .owner = THIS_MODULE },
 }, {
 	.phy_id		= PHY_BCM_OUI_4,
 	.phy_id_mask	= 0xffff0000,
@@ -331,7 +318,6 @@ static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
 	{ PHY_ID_BCM7366, 0xfffffff0, },
 	{ PHY_ID_BCM7439, 0xfffffff0, },
 	{ PHY_ID_BCM7445, 0xfffffff0, },
-	{ PHY_ID_BCM7XXX_28, 0xfffffc00 },
 	{ PHY_BCM_OUI_4, 0xffff0000 },
 	{ PHY_BCM_OUI_5, 0xffffff00 },
 	{ }
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 6f76277baf39..61219b9b3445 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -16,7 +16,6 @@
 #define PHY_ID_BCM7366			0x600d8490
 #define PHY_ID_BCM7439			0x600d8480
 #define PHY_ID_BCM7445			0x600d8510
-#define PHY_ID_BCM7XXX_28		0x600d8400
 
 #define PHY_BCM_OUI_MASK		0xfffffc00
 #define PHY_BCM_OUI_1			0x00206000
-- 
cgit v1.2.3


From 983c684466e02b21f83c025ea539deee6c0aeac0 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Sun, 3 Aug 2014 13:03:10 -0400
Subject: SUNRPC: get rid of the request wait queue

We're always _only_ waking up tasks from within the sp_threads list, so
we know that they are enqueued and alive. The rq_wait waitqueue is just
a distraction with extra atomic semantics.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc.h |  1 -
 net/sunrpc/svc.c           |  2 --
 net/sunrpc/svc_xprt.c      | 32 +++++++++++++++++---------------
 3 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index cf61ecd148e0..21678464883a 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -280,7 +280,6 @@ struct svc_rqst {
 	bool			rq_splice_ok;   /* turned off in gss privacy
 						 * to prevent encrypting page
 						 * cache pages */
-	wait_queue_head_t	rq_wait;	/* synchronization */
 	struct task_struct	*rq_task;	/* service thread */
 };
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 1db5007ddbce..ca8a7958f4e6 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -612,8 +612,6 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 	if (!rqstp)
 		goto out_enomem;
 
-	init_waitqueue_head(&rqstp->rq_wait);
-
 	serv->sv_nrthreads++;
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads++;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 08e49d1e17b3..faaf2b46273b 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -348,8 +348,6 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 
 	cpu = get_cpu();
 	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-	put_cpu();
-
 	spin_lock_bh(&pool->sp_lock);
 
 	if (!list_empty(&pool->sp_threads) &&
@@ -382,10 +380,15 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 			printk(KERN_ERR
 				"svc_xprt_enqueue: server %p, rq_xprt=%p!\n",
 				rqstp, rqstp->rq_xprt);
-		rqstp->rq_xprt = xprt;
+		/* Note the order of the following 3 lines:
+		 * We want to assign xprt to rqstp->rq_xprt only _after_
+		 * we've woken up the process, so that we don't race with
+		 * the lockless check in svc_get_next_xprt().
+		 */
 		svc_xprt_get(xprt);
+		wake_up_process(rqstp->rq_task);
+		rqstp->rq_xprt = xprt;
 		pool->sp_stats.threads_woken++;
-		wake_up(&rqstp->rq_wait);
 	} else {
 		dprintk("svc: transport %p put into queue\n", xprt);
 		list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
@@ -394,6 +397,7 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 
 out_unlock:
 	spin_unlock_bh(&pool->sp_lock);
+	put_cpu();
 }
 
 /*
@@ -509,7 +513,7 @@ void svc_wake_up(struct svc_serv *serv)
 			svc_thread_dequeue(pool, rqstp);
 			rqstp->rq_xprt = NULL;
 			 */
-			wake_up(&rqstp->rq_wait);
+			wake_up_process(rqstp->rq_task);
 		} else
 			pool->sp_task_pending = 1;
 		spin_unlock_bh(&pool->sp_lock);
@@ -628,7 +632,6 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 {
 	struct svc_xprt *xprt;
 	struct svc_pool		*pool = rqstp->rq_pool;
-	DECLARE_WAITQUEUE(wait, current);
 	long			time_left;
 
 	/* Normally we will wait up to 5 seconds for any required
@@ -654,15 +657,15 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 			xprt = ERR_PTR(-EAGAIN);
 			goto out;
 		}
-		/* No data pending. Go to sleep */
-		svc_thread_enqueue(pool, rqstp);
-
 		/*
 		 * We have to be able to interrupt this wait
 		 * to bring down the daemons ...
 		 */
 		set_current_state(TASK_INTERRUPTIBLE);
 
+		/* No data pending. Go to sleep */
+		svc_thread_enqueue(pool, rqstp);
+
 		/*
 		 * checking kthread_should_stop() here allows us to avoid
 		 * locking and signalling when stopping kthreads that call
@@ -676,14 +679,13 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 			goto out;
 		}
 
-		add_wait_queue(&rqstp->rq_wait, &wait);
 		spin_unlock_bh(&pool->sp_lock);
 
 		time_left = schedule_timeout(timeout);
+		__set_current_state(TASK_RUNNING);
 
 		try_to_freeze();
 
-		remove_wait_queue(&rqstp->rq_wait, &wait);
 		xprt = rqstp->rq_xprt;
 		if (xprt != NULL)
 			return xprt;
@@ -786,10 +788,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		printk(KERN_ERR
 			"svc_recv: service %p, transport not NULL!\n",
 			 rqstp);
-	if (waitqueue_active(&rqstp->rq_wait))
-		printk(KERN_ERR
-			"svc_recv: service %p, wait queue active!\n",
-			 rqstp);
+
+	/* Make sure the task pointer is set! */
+	if (WARN_ON_ONCE(!rqstp->rq_task))
+		rqstp->rq_task = current_task;
 
 	err = svc_alloc_arg(rqstp);
 	if (err)
-- 
cgit v1.2.3


From 7d2691da901d71ff62ad974510ea7149b391bdfe Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:47 -0700
Subject: gpu: ipu-v3: Add ipu-cpmem unit

Move channel parameter memory setup functions and macros into a new
submodule ipu-cpmem. In the process, cleanup arguments to the functions
to take a channel pointer instead of a pointer into cpmem for that
channel. That allows the structure of the parameter memory to be
private to ipu-cpmem.c.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/Makefile     |   3 +-
 drivers/gpu/ipu-v3/ipu-common.c | 457 +-----------------------------
 drivers/gpu/ipu-v3/ipu-cpmem.c  | 597 ++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/ipu-v3/ipu-prv.h    |  14 +-
 include/video/imx-ipu-v3.h      | 188 +++----------
 5 files changed, 658 insertions(+), 601 deletions(-)
 create mode 100644 drivers/gpu/ipu-v3/ipu-cpmem.c

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/Makefile b/drivers/gpu/ipu-v3/Makefile
index 1887972b4ac2..0b42836caae1 100644
--- a/drivers/gpu/ipu-v3/Makefile
+++ b/drivers/gpu/ipu-v3/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_IMX_IPUV3_CORE) += imx-ipu-v3.o
 
-imx-ipu-v3-objs := ipu-common.o ipu-dc.o ipu-di.o ipu-dp.o ipu-dmfc.o ipu-smfc.o
+imx-ipu-v3-objs := ipu-common.o ipu-cpmem.o ipu-dc.o ipu-di.o \
+		ipu-dp.o ipu-dmfc.o ipu-smfc.o
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 04e7b2eafbdd..5978e7aab8ed 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -44,17 +44,6 @@ static inline void ipu_cm_write(struct ipu_soc *ipu, u32 value, unsigned offset)
 	writel(value, ipu->cm_reg + offset);
 }
 
-static inline u32 ipu_idmac_read(struct ipu_soc *ipu, unsigned offset)
-{
-	return readl(ipu->idmac_reg + offset);
-}
-
-static inline void ipu_idmac_write(struct ipu_soc *ipu, u32 value,
-		unsigned offset)
-{
-	writel(value, ipu->idmac_reg + offset);
-}
-
 void ipu_srm_dp_sync_update(struct ipu_soc *ipu)
 {
 	u32 val;
@@ -65,379 +54,6 @@ void ipu_srm_dp_sync_update(struct ipu_soc *ipu)
 }
 EXPORT_SYMBOL_GPL(ipu_srm_dp_sync_update);
 
-struct ipu_ch_param __iomem *ipu_get_cpmem(struct ipuv3_channel *channel)
-{
-	struct ipu_soc *ipu = channel->ipu;
-
-	return ipu->cpmem_base + channel->num;
-}
-EXPORT_SYMBOL_GPL(ipu_get_cpmem);
-
-void ipu_cpmem_set_high_priority(struct ipuv3_channel *channel)
-{
-	struct ipu_soc *ipu = channel->ipu;
-	struct ipu_ch_param __iomem *p = ipu_get_cpmem(channel);
-	u32 val;
-
-	if (ipu->ipu_type == IPUV3EX)
-		ipu_ch_param_write_field(p, IPU_FIELD_ID, 1);
-
-	val = ipu_idmac_read(ipu, IDMAC_CHA_PRI(channel->num));
-	val |= 1 << (channel->num % 32);
-	ipu_idmac_write(ipu, val, IDMAC_CHA_PRI(channel->num));
-};
-EXPORT_SYMBOL_GPL(ipu_cpmem_set_high_priority);
-
-void ipu_ch_param_write_field(struct ipu_ch_param __iomem *base, u32 wbs, u32 v)
-{
-	u32 bit = (wbs >> 8) % 160;
-	u32 size = wbs & 0xff;
-	u32 word = (wbs >> 8) / 160;
-	u32 i = bit / 32;
-	u32 ofs = bit % 32;
-	u32 mask = (1 << size) - 1;
-	u32 val;
-
-	pr_debug("%s %d %d %d\n", __func__, word, bit , size);
-
-	val = readl(&base->word[word].data[i]);
-	val &= ~(mask << ofs);
-	val |= v << ofs;
-	writel(val, &base->word[word].data[i]);
-
-	if ((bit + size - 1) / 32 > i) {
-		val = readl(&base->word[word].data[i + 1]);
-		val &= ~(mask >> (ofs ? (32 - ofs) : 0));
-		val |= v >> (ofs ? (32 - ofs) : 0);
-		writel(val, &base->word[word].data[i + 1]);
-	}
-}
-EXPORT_SYMBOL_GPL(ipu_ch_param_write_field);
-
-u32 ipu_ch_param_read_field(struct ipu_ch_param __iomem *base, u32 wbs)
-{
-	u32 bit = (wbs >> 8) % 160;
-	u32 size = wbs & 0xff;
-	u32 word = (wbs >> 8) / 160;
-	u32 i = bit / 32;
-	u32 ofs = bit % 32;
-	u32 mask = (1 << size) - 1;
-	u32 val = 0;
-
-	pr_debug("%s %d %d %d\n", __func__, word, bit , size);
-
-	val = (readl(&base->word[word].data[i]) >> ofs) & mask;
-
-	if ((bit + size - 1) / 32 > i) {
-		u32 tmp;
-		tmp = readl(&base->word[word].data[i + 1]);
-		tmp &= mask >> (ofs ? (32 - ofs) : 0);
-		val |= tmp << (ofs ? (32 - ofs) : 0);
-	}
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(ipu_ch_param_read_field);
-
-int ipu_cpmem_set_format_rgb(struct ipu_ch_param __iomem *p,
-		const struct ipu_rgb *rgb)
-{
-	int bpp = 0, npb = 0, ro, go, bo, to;
-
-	ro = rgb->bits_per_pixel - rgb->red.length - rgb->red.offset;
-	go = rgb->bits_per_pixel - rgb->green.length - rgb->green.offset;
-	bo = rgb->bits_per_pixel - rgb->blue.length - rgb->blue.offset;
-	to = rgb->bits_per_pixel - rgb->transp.length - rgb->transp.offset;
-
-	ipu_ch_param_write_field(p, IPU_FIELD_WID0, rgb->red.length - 1);
-	ipu_ch_param_write_field(p, IPU_FIELD_OFS0, ro);
-	ipu_ch_param_write_field(p, IPU_FIELD_WID1, rgb->green.length - 1);
-	ipu_ch_param_write_field(p, IPU_FIELD_OFS1, go);
-	ipu_ch_param_write_field(p, IPU_FIELD_WID2, rgb->blue.length - 1);
-	ipu_ch_param_write_field(p, IPU_FIELD_OFS2, bo);
-
-	if (rgb->transp.length) {
-		ipu_ch_param_write_field(p, IPU_FIELD_WID3,
-				rgb->transp.length - 1);
-		ipu_ch_param_write_field(p, IPU_FIELD_OFS3, to);
-	} else {
-		ipu_ch_param_write_field(p, IPU_FIELD_WID3, 7);
-		ipu_ch_param_write_field(p, IPU_FIELD_OFS3,
-				rgb->bits_per_pixel);
-	}
-
-	switch (rgb->bits_per_pixel) {
-	case 32:
-		bpp = 0;
-		npb = 15;
-		break;
-	case 24:
-		bpp = 1;
-		npb = 19;
-		break;
-	case 16:
-		bpp = 3;
-		npb = 31;
-		break;
-	case 8:
-		bpp = 5;
-		npb = 63;
-		break;
-	default:
-		return -EINVAL;
-	}
-	ipu_ch_param_write_field(p, IPU_FIELD_BPP, bpp);
-	ipu_ch_param_write_field(p, IPU_FIELD_NPB, npb);
-	ipu_ch_param_write_field(p, IPU_FIELD_PFS, 7); /* rgb mode */
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(ipu_cpmem_set_format_rgb);
-
-int ipu_cpmem_set_format_passthrough(struct ipu_ch_param __iomem *p,
-		int width)
-{
-	int bpp = 0, npb = 0;
-
-	switch (width) {
-	case 32:
-		bpp = 0;
-		npb = 15;
-		break;
-	case 24:
-		bpp = 1;
-		npb = 19;
-		break;
-	case 16:
-		bpp = 3;
-		npb = 31;
-		break;
-	case 8:
-		bpp = 5;
-		npb = 63;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ipu_ch_param_write_field(p, IPU_FIELD_BPP, bpp);
-	ipu_ch_param_write_field(p, IPU_FIELD_NPB, npb);
-	ipu_ch_param_write_field(p, IPU_FIELD_PFS, 6); /* raw mode */
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(ipu_cpmem_set_format_passthrough);
-
-void ipu_cpmem_set_yuv_interleaved(struct ipu_ch_param __iomem *p,
-				   u32 pixel_format)
-{
-	switch (pixel_format) {
-	case V4L2_PIX_FMT_UYVY:
-		ipu_ch_param_write_field(p, IPU_FIELD_BPP, 3);    /* bits/pixel */
-		ipu_ch_param_write_field(p, IPU_FIELD_PFS, 0xA);  /* pix format */
-		ipu_ch_param_write_field(p, IPU_FIELD_NPB, 31);   /* burst size */
-		break;
-	case V4L2_PIX_FMT_YUYV:
-		ipu_ch_param_write_field(p, IPU_FIELD_BPP, 3);    /* bits/pixel */
-		ipu_ch_param_write_field(p, IPU_FIELD_PFS, 0x8);  /* pix format */
-		ipu_ch_param_write_field(p, IPU_FIELD_NPB, 31);   /* burst size */
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(ipu_cpmem_set_yuv_interleaved);
-
-void ipu_cpmem_set_yuv_planar_full(struct ipu_ch_param __iomem *p,
-		u32 pixel_format, int stride, int u_offset, int v_offset)
-{
-	switch (pixel_format) {
-	case V4L2_PIX_FMT_YUV420:
-		ipu_ch_param_write_field(p, IPU_FIELD_SLUV, (stride / 2) - 1);
-		ipu_ch_param_write_field(p, IPU_FIELD_UBO, u_offset / 8);
-		ipu_ch_param_write_field(p, IPU_FIELD_VBO, v_offset / 8);
-		break;
-	case V4L2_PIX_FMT_YVU420:
-		ipu_ch_param_write_field(p, IPU_FIELD_SLUV, (stride / 2) - 1);
-		ipu_ch_param_write_field(p, IPU_FIELD_UBO, v_offset / 8);
-		ipu_ch_param_write_field(p, IPU_FIELD_VBO, u_offset / 8);
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(ipu_cpmem_set_yuv_planar_full);
-
-void ipu_cpmem_set_yuv_planar(struct ipu_ch_param __iomem *p, u32 pixel_format,
-		int stride, int height)
-{
-	int u_offset, v_offset;
-	int uv_stride = 0;
-
-	switch (pixel_format) {
-	case V4L2_PIX_FMT_YUV420:
-	case V4L2_PIX_FMT_YVU420:
-		uv_stride = stride / 2;
-		u_offset = stride * height;
-		v_offset = u_offset + (uv_stride * height / 2);
-		ipu_cpmem_set_yuv_planar_full(p, pixel_format, stride,
-				u_offset, v_offset);
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(ipu_cpmem_set_yuv_planar);
-
-static const struct ipu_rgb def_rgb_32 = {
-	.red	= { .offset = 16, .length = 8, },
-	.green	= { .offset =  8, .length = 8, },
-	.blue	= { .offset =  0, .length = 8, },
-	.transp = { .offset = 24, .length = 8, },
-	.bits_per_pixel = 32,
-};
-
-static const struct ipu_rgb def_bgr_32 = {
-	.red	= { .offset =  0, .length = 8, },
-	.green	= { .offset =  8, .length = 8, },
-	.blue	= { .offset = 16, .length = 8, },
-	.transp = { .offset = 24, .length = 8, },
-	.bits_per_pixel = 32,
-};
-
-static const struct ipu_rgb def_rgb_24 = {
-	.red	= { .offset = 16, .length = 8, },
-	.green	= { .offset =  8, .length = 8, },
-	.blue	= { .offset =  0, .length = 8, },
-	.transp = { .offset =  0, .length = 0, },
-	.bits_per_pixel = 24,
-};
-
-static const struct ipu_rgb def_bgr_24 = {
-	.red	= { .offset =  0, .length = 8, },
-	.green	= { .offset =  8, .length = 8, },
-	.blue	= { .offset = 16, .length = 8, },
-	.transp = { .offset =  0, .length = 0, },
-	.bits_per_pixel = 24,
-};
-
-static const struct ipu_rgb def_rgb_16 = {
-	.red	= { .offset = 11, .length = 5, },
-	.green	= { .offset =  5, .length = 6, },
-	.blue	= { .offset =  0, .length = 5, },
-	.transp = { .offset =  0, .length = 0, },
-	.bits_per_pixel = 16,
-};
-
-static const struct ipu_rgb def_bgr_16 = {
-	.red	= { .offset =  0, .length = 5, },
-	.green	= { .offset =  5, .length = 6, },
-	.blue	= { .offset = 11, .length = 5, },
-	.transp = { .offset =  0, .length = 0, },
-	.bits_per_pixel = 16,
-};
-
-#define Y_OFFSET(pix, x, y)	((x) + pix->width * (y))
-#define U_OFFSET(pix, x, y)	((pix->width * pix->height) + \
-					(pix->width * (y) / 4) + (x) / 2)
-#define V_OFFSET(pix, x, y)	((pix->width * pix->height) + \
-					(pix->width * pix->height / 4) + \
-					(pix->width * (y) / 4) + (x) / 2)
-
-int ipu_cpmem_set_fmt(struct ipu_ch_param __iomem *cpmem, u32 drm_fourcc)
-{
-	switch (drm_fourcc) {
-	case DRM_FORMAT_YUV420:
-	case DRM_FORMAT_YVU420:
-		/* pix format */
-		ipu_ch_param_write_field(cpmem, IPU_FIELD_PFS, 2);
-		/* burst size */
-		ipu_ch_param_write_field(cpmem, IPU_FIELD_NPB, 63);
-		break;
-	case DRM_FORMAT_UYVY:
-		/* bits/pixel */
-		ipu_ch_param_write_field(cpmem, IPU_FIELD_BPP, 3);
-		/* pix format */
-		ipu_ch_param_write_field(cpmem, IPU_FIELD_PFS, 0xA);
-		/* burst size */
-		ipu_ch_param_write_field(cpmem, IPU_FIELD_NPB, 31);
-		break;
-	case DRM_FORMAT_YUYV:
-		/* bits/pixel */
-		ipu_ch_param_write_field(cpmem, IPU_FIELD_BPP, 3);
-		/* pix format */
-		ipu_ch_param_write_field(cpmem, IPU_FIELD_PFS, 0x8);
-		/* burst size */
-		ipu_ch_param_write_field(cpmem, IPU_FIELD_NPB, 31);
-		break;
-	case DRM_FORMAT_ABGR8888:
-	case DRM_FORMAT_XBGR8888:
-		ipu_cpmem_set_format_rgb(cpmem, &def_bgr_32);
-		break;
-	case DRM_FORMAT_ARGB8888:
-	case DRM_FORMAT_XRGB8888:
-		ipu_cpmem_set_format_rgb(cpmem, &def_rgb_32);
-		break;
-	case DRM_FORMAT_BGR888:
-		ipu_cpmem_set_format_rgb(cpmem, &def_bgr_24);
-		break;
-	case DRM_FORMAT_RGB888:
-		ipu_cpmem_set_format_rgb(cpmem, &def_rgb_24);
-		break;
-	case DRM_FORMAT_RGB565:
-		ipu_cpmem_set_format_rgb(cpmem, &def_rgb_16);
-		break;
-	case DRM_FORMAT_BGR565:
-		ipu_cpmem_set_format_rgb(cpmem, &def_bgr_16);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(ipu_cpmem_set_fmt);
-
-/*
- * The V4L2 spec defines packed RGB formats in memory byte order, which from
- * point of view of the IPU corresponds to little-endian words with the first
- * component in the least significant bits.
- * The DRM pixel formats and IPU internal representation are ordered the other
- * way around, with the first named component ordered at the most significant
- * bits. Further, V4L2 formats are not well defined:
- *     http://linuxtv.org/downloads/v4l-dvb-apis/packed-rgb.html
- * We choose the interpretation which matches GStreamer behavior.
- */
-static int v4l2_pix_fmt_to_drm_fourcc(u32 pixelformat)
-{
-	switch (pixelformat) {
-	case V4L2_PIX_FMT_RGB565:
-		/*
-		 * Here we choose the 'corrected' interpretation of RGBP, a
-		 * little-endian 16-bit word with the red component at the most
-		 * significant bits:
-		 * g[2:0]b[4:0] r[4:0]g[5:3] <=> [16:0] R:G:B
-		 */
-		return DRM_FORMAT_RGB565;
-	case V4L2_PIX_FMT_BGR24:
-		/* B G R <=> [24:0] R:G:B */
-		return DRM_FORMAT_RGB888;
-	case V4L2_PIX_FMT_RGB24:
-		/* R G B <=> [24:0] B:G:R */
-		return DRM_FORMAT_BGR888;
-	case V4L2_PIX_FMT_BGR32:
-		/* B G R A <=> [32:0] A:B:G:R */
-		return DRM_FORMAT_XRGB8888;
-	case V4L2_PIX_FMT_RGB32:
-		/* R G B A <=> [32:0] A:B:G:R */
-		return DRM_FORMAT_XBGR8888;
-	case V4L2_PIX_FMT_UYVY:
-		return DRM_FORMAT_UYVY;
-	case V4L2_PIX_FMT_YUYV:
-		return DRM_FORMAT_YUYV;
-	case V4L2_PIX_FMT_YUV420:
-		return DRM_FORMAT_YUV420;
-	case V4L2_PIX_FMT_YVU420:
-		return DRM_FORMAT_YVU420;
-	}
-
-	return -EINVAL;
-}
-
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc)
 {
 	switch (drm_fourcc) {
@@ -465,66 +81,6 @@ enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc)
 }
 EXPORT_SYMBOL_GPL(ipu_drm_fourcc_to_colorspace);
 
-int ipu_cpmem_set_image(struct ipu_ch_param __iomem *cpmem,
-		struct ipu_image *image)
-{
-	struct v4l2_pix_format *pix = &image->pix;
-	int y_offset, u_offset, v_offset;
-
-	pr_debug("%s: resolution: %dx%d stride: %d\n",
-			__func__, pix->width, pix->height,
-			pix->bytesperline);
-
-	ipu_cpmem_set_resolution(cpmem, image->rect.width,
-			image->rect.height);
-	ipu_cpmem_set_stride(cpmem, pix->bytesperline);
-
-	ipu_cpmem_set_fmt(cpmem, v4l2_pix_fmt_to_drm_fourcc(pix->pixelformat));
-
-	switch (pix->pixelformat) {
-	case V4L2_PIX_FMT_YUV420:
-	case V4L2_PIX_FMT_YVU420:
-		y_offset = Y_OFFSET(pix, image->rect.left, image->rect.top);
-		u_offset = U_OFFSET(pix, image->rect.left,
-				image->rect.top) - y_offset;
-		v_offset = V_OFFSET(pix, image->rect.left,
-				image->rect.top) - y_offset;
-
-		ipu_cpmem_set_yuv_planar_full(cpmem, pix->pixelformat,
-				pix->bytesperline, u_offset, v_offset);
-		ipu_cpmem_set_buffer(cpmem, 0, image->phys + y_offset);
-		break;
-	case V4L2_PIX_FMT_UYVY:
-	case V4L2_PIX_FMT_YUYV:
-		ipu_cpmem_set_buffer(cpmem, 0, image->phys +
-				image->rect.left * 2 +
-				image->rect.top * image->pix.bytesperline);
-		break;
-	case V4L2_PIX_FMT_RGB32:
-	case V4L2_PIX_FMT_BGR32:
-		ipu_cpmem_set_buffer(cpmem, 0, image->phys +
-				image->rect.left * 4 +
-				image->rect.top * image->pix.bytesperline);
-		break;
-	case V4L2_PIX_FMT_RGB565:
-		ipu_cpmem_set_buffer(cpmem, 0, image->phys +
-				image->rect.left * 2 +
-				image->rect.top * image->pix.bytesperline);
-		break;
-	case V4L2_PIX_FMT_RGB24:
-	case V4L2_PIX_FMT_BGR24:
-		ipu_cpmem_set_buffer(cpmem, 0, image->phys +
-				image->rect.left * 3 +
-				image->rect.top * image->pix.bytesperline);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(ipu_cpmem_set_image);
-
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat)
 {
 	switch (pixelformat) {
@@ -895,6 +451,12 @@ static int ipu_submodules_init(struct ipu_soc *ipu,
 	struct device *dev = &pdev->dev;
 	const struct ipu_devtype *devtype = ipu->devtype;
 
+	ret = ipu_cpmem_init(ipu, dev, ipu_base + devtype->cpmem_ofs);
+	if (ret) {
+		unit = "cpmem";
+		goto err_cpmem;
+	}
+
 	ret = ipu_di_init(ipu, dev, 0, ipu_base + devtype->disp0_ofs,
 			IPU_CONF_DI0_EN, ipu_clk);
 	if (ret) {
@@ -949,6 +511,8 @@ err_dc:
 err_di_1:
 	ipu_di_exit(ipu, 0);
 err_di_0:
+	ipu_cpmem_exit(ipu);
+err_cpmem:
 	dev_err(&pdev->dev, "init %s failed with %d\n", unit, ret);
 	return ret;
 }
@@ -1025,6 +589,7 @@ static void ipu_submodules_exit(struct ipu_soc *ipu)
 	ipu_dc_exit(ipu);
 	ipu_di_exit(ipu, 1);
 	ipu_di_exit(ipu, 0);
+	ipu_cpmem_exit(ipu);
 }
 
 static int platform_remove_devices_fn(struct device *dev, void *unused)
@@ -1265,10 +830,8 @@ static int ipu_probe(struct platform_device *pdev)
 	ipu->idmac_reg = devm_ioremap(&pdev->dev,
 			ipu_base + devtype->cm_ofs + IPU_CM_IDMAC_REG_OFS,
 			PAGE_SIZE);
-	ipu->cpmem_base = devm_ioremap(&pdev->dev,
-			ipu_base + devtype->cpmem_ofs, PAGE_SIZE);
 
-	if (!ipu->cm_reg || !ipu->idmac_reg || !ipu->cpmem_base)
+	if (!ipu->cm_reg || !ipu->idmac_reg)
 		return -ENOMEM;
 
 	ipu->clk = devm_clk_get(&pdev->dev, "bus");
diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
new file mode 100644
index 000000000000..7adfa78a48bc
--- /dev/null
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -0,0 +1,597 @@
+/*
+ * Copyright (C) 2012 Mentor Graphics Inc.
+ * Copyright 2005-2012 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+#include <linux/types.h>
+#include <linux/bitrev.h>
+#include <linux/io.h>
+#include <drm/drm_fourcc.h>
+#include "ipu-prv.h"
+
+struct ipu_cpmem_word {
+	u32 data[5];
+	u32 res[3];
+};
+
+struct ipu_ch_param {
+	struct ipu_cpmem_word word[2];
+};
+
+struct ipu_cpmem {
+	struct ipu_ch_param __iomem *base;
+	u32 module;
+	spinlock_t lock;
+	int use_count;
+	struct ipu_soc *ipu;
+};
+
+#define IPU_CPMEM_WORD(word, ofs, size) ((((word) * 160 + (ofs)) << 8) | (size))
+
+#define IPU_FIELD_UBO		IPU_CPMEM_WORD(0, 46, 22)
+#define IPU_FIELD_VBO		IPU_CPMEM_WORD(0, 68, 22)
+#define IPU_FIELD_IOX		IPU_CPMEM_WORD(0, 90, 4)
+#define IPU_FIELD_RDRW		IPU_CPMEM_WORD(0, 94, 1)
+#define IPU_FIELD_SO		IPU_CPMEM_WORD(0, 113, 1)
+#define IPU_FIELD_SLY		IPU_CPMEM_WORD(1, 102, 14)
+#define IPU_FIELD_SLUV		IPU_CPMEM_WORD(1, 128, 14)
+
+#define IPU_FIELD_XV		IPU_CPMEM_WORD(0, 0, 10)
+#define IPU_FIELD_YV		IPU_CPMEM_WORD(0, 10, 9)
+#define IPU_FIELD_XB		IPU_CPMEM_WORD(0, 19, 13)
+#define IPU_FIELD_YB		IPU_CPMEM_WORD(0, 32, 12)
+#define IPU_FIELD_NSB_B		IPU_CPMEM_WORD(0, 44, 1)
+#define IPU_FIELD_CF		IPU_CPMEM_WORD(0, 45, 1)
+#define IPU_FIELD_SX		IPU_CPMEM_WORD(0, 46, 12)
+#define IPU_FIELD_SY		IPU_CPMEM_WORD(0, 58, 11)
+#define IPU_FIELD_NS		IPU_CPMEM_WORD(0, 69, 10)
+#define IPU_FIELD_SDX		IPU_CPMEM_WORD(0, 79, 7)
+#define IPU_FIELD_SM		IPU_CPMEM_WORD(0, 86, 10)
+#define IPU_FIELD_SCC		IPU_CPMEM_WORD(0, 96, 1)
+#define IPU_FIELD_SCE		IPU_CPMEM_WORD(0, 97, 1)
+#define IPU_FIELD_SDY		IPU_CPMEM_WORD(0, 98, 7)
+#define IPU_FIELD_SDRX		IPU_CPMEM_WORD(0, 105, 1)
+#define IPU_FIELD_SDRY		IPU_CPMEM_WORD(0, 106, 1)
+#define IPU_FIELD_BPP		IPU_CPMEM_WORD(0, 107, 3)
+#define IPU_FIELD_DEC_SEL	IPU_CPMEM_WORD(0, 110, 2)
+#define IPU_FIELD_DIM		IPU_CPMEM_WORD(0, 112, 1)
+#define IPU_FIELD_BNDM		IPU_CPMEM_WORD(0, 114, 3)
+#define IPU_FIELD_BM		IPU_CPMEM_WORD(0, 117, 2)
+#define IPU_FIELD_ROT		IPU_CPMEM_WORD(0, 119, 1)
+#define IPU_FIELD_HF		IPU_CPMEM_WORD(0, 120, 1)
+#define IPU_FIELD_VF		IPU_CPMEM_WORD(0, 121, 1)
+#define IPU_FIELD_THE		IPU_CPMEM_WORD(0, 122, 1)
+#define IPU_FIELD_CAP		IPU_CPMEM_WORD(0, 123, 1)
+#define IPU_FIELD_CAE		IPU_CPMEM_WORD(0, 124, 1)
+#define IPU_FIELD_FW		IPU_CPMEM_WORD(0, 125, 13)
+#define IPU_FIELD_FH		IPU_CPMEM_WORD(0, 138, 12)
+#define IPU_FIELD_EBA0		IPU_CPMEM_WORD(1, 0, 29)
+#define IPU_FIELD_EBA1		IPU_CPMEM_WORD(1, 29, 29)
+#define IPU_FIELD_ILO		IPU_CPMEM_WORD(1, 58, 20)
+#define IPU_FIELD_NPB		IPU_CPMEM_WORD(1, 78, 7)
+#define IPU_FIELD_PFS		IPU_CPMEM_WORD(1, 85, 4)
+#define IPU_FIELD_ALU		IPU_CPMEM_WORD(1, 89, 1)
+#define IPU_FIELD_ALBM		IPU_CPMEM_WORD(1, 90, 3)
+#define IPU_FIELD_ID		IPU_CPMEM_WORD(1, 93, 2)
+#define IPU_FIELD_TH		IPU_CPMEM_WORD(1, 95, 7)
+#define IPU_FIELD_SL		IPU_CPMEM_WORD(1, 102, 14)
+#define IPU_FIELD_WID0		IPU_CPMEM_WORD(1, 116, 3)
+#define IPU_FIELD_WID1		IPU_CPMEM_WORD(1, 119, 3)
+#define IPU_FIELD_WID2		IPU_CPMEM_WORD(1, 122, 3)
+#define IPU_FIELD_WID3		IPU_CPMEM_WORD(1, 125, 3)
+#define IPU_FIELD_OFS0		IPU_CPMEM_WORD(1, 128, 5)
+#define IPU_FIELD_OFS1		IPU_CPMEM_WORD(1, 133, 5)
+#define IPU_FIELD_OFS2		IPU_CPMEM_WORD(1, 138, 5)
+#define IPU_FIELD_OFS3		IPU_CPMEM_WORD(1, 143, 5)
+#define IPU_FIELD_SXYS		IPU_CPMEM_WORD(1, 148, 1)
+#define IPU_FIELD_CRE		IPU_CPMEM_WORD(1, 149, 1)
+#define IPU_FIELD_DEC_SEL2	IPU_CPMEM_WORD(1, 150, 1)
+
+static inline struct ipu_ch_param __iomem *
+ipu_get_cpmem(struct ipuv3_channel *ch)
+{
+	struct ipu_cpmem *cpmem = ch->ipu->cpmem_priv;
+
+	return cpmem->base + ch->num;
+}
+
+static void ipu_ch_param_write_field(struct ipuv3_channel *ch, u32 wbs, u32 v)
+{
+	struct ipu_ch_param __iomem *base = ipu_get_cpmem(ch);
+	u32 bit = (wbs >> 8) % 160;
+	u32 size = wbs & 0xff;
+	u32 word = (wbs >> 8) / 160;
+	u32 i = bit / 32;
+	u32 ofs = bit % 32;
+	u32 mask = (1 << size) - 1;
+	u32 val;
+
+	pr_debug("%s %d %d %d\n", __func__, word, bit , size);
+
+	val = readl(&base->word[word].data[i]);
+	val &= ~(mask << ofs);
+	val |= v << ofs;
+	writel(val, &base->word[word].data[i]);
+
+	if ((bit + size - 1) / 32 > i) {
+		val = readl(&base->word[word].data[i + 1]);
+		val &= ~(mask >> (ofs ? (32 - ofs) : 0));
+		val |= v >> (ofs ? (32 - ofs) : 0);
+		writel(val, &base->word[word].data[i + 1]);
+	}
+}
+
+static u32 ipu_ch_param_read_field(struct ipuv3_channel *ch, u32 wbs)
+{
+	struct ipu_ch_param __iomem *base = ipu_get_cpmem(ch);
+	u32 bit = (wbs >> 8) % 160;
+	u32 size = wbs & 0xff;
+	u32 word = (wbs >> 8) / 160;
+	u32 i = bit / 32;
+	u32 ofs = bit % 32;
+	u32 mask = (1 << size) - 1;
+	u32 val = 0;
+
+	pr_debug("%s %d %d %d\n", __func__, word, bit , size);
+
+	val = (readl(&base->word[word].data[i]) >> ofs) & mask;
+
+	if ((bit + size - 1) / 32 > i) {
+		u32 tmp;
+
+		tmp = readl(&base->word[word].data[i + 1]);
+		tmp &= mask >> (ofs ? (32 - ofs) : 0);
+		val |= tmp << (ofs ? (32 - ofs) : 0);
+	}
+
+	return val;
+}
+
+/*
+ * The V4L2 spec defines packed RGB formats in memory byte order, which from
+ * point of view of the IPU corresponds to little-endian words with the first
+ * component in the least significant bits.
+ * The DRM pixel formats and IPU internal representation are ordered the other
+ * way around, with the first named component ordered at the most significant
+ * bits. Further, V4L2 formats are not well defined:
+ *     http://linuxtv.org/downloads/v4l-dvb-apis/packed-rgb.html
+ * We choose the interpretation which matches GStreamer behavior.
+ */
+static int v4l2_pix_fmt_to_drm_fourcc(u32 pixelformat)
+{
+	switch (pixelformat) {
+	case V4L2_PIX_FMT_RGB565:
+		/*
+		 * Here we choose the 'corrected' interpretation of RGBP, a
+		 * little-endian 16-bit word with the red component at the most
+		 * significant bits:
+		 * g[2:0]b[4:0] r[4:0]g[5:3] <=> [16:0] R:G:B
+		 */
+		return DRM_FORMAT_RGB565;
+	case V4L2_PIX_FMT_BGR24:
+		/* B G R <=> [24:0] R:G:B */
+		return DRM_FORMAT_RGB888;
+	case V4L2_PIX_FMT_RGB24:
+		/* R G B <=> [24:0] B:G:R */
+		return DRM_FORMAT_BGR888;
+	case V4L2_PIX_FMT_BGR32:
+		/* B G R A <=> [32:0] A:B:G:R */
+		return DRM_FORMAT_XRGB8888;
+	case V4L2_PIX_FMT_RGB32:
+		/* R G B A <=> [32:0] A:B:G:R */
+		return DRM_FORMAT_XBGR8888;
+	case V4L2_PIX_FMT_UYVY:
+		return DRM_FORMAT_UYVY;
+	case V4L2_PIX_FMT_YUYV:
+		return DRM_FORMAT_YUYV;
+	case V4L2_PIX_FMT_YUV420:
+		return DRM_FORMAT_YUV420;
+	case V4L2_PIX_FMT_YVU420:
+		return DRM_FORMAT_YVU420;
+	}
+
+	return -EINVAL;
+}
+
+void ipu_cpmem_zero(struct ipuv3_channel *ch)
+{
+	struct ipu_ch_param __iomem *p = ipu_get_cpmem(ch);
+	void __iomem *base = p;
+	int i;
+
+	for (i = 0; i < sizeof(*p) / sizeof(u32); i++)
+		writel(0, base + i * sizeof(u32));
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_zero);
+
+void ipu_cpmem_set_resolution(struct ipuv3_channel *ch, int xres, int yres)
+{
+	ipu_ch_param_write_field(ch, IPU_FIELD_FW, xres - 1);
+	ipu_ch_param_write_field(ch, IPU_FIELD_FH, yres - 1);
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_resolution);
+
+void ipu_cpmem_set_stride(struct ipuv3_channel *ch, int stride)
+{
+	ipu_ch_param_write_field(ch, IPU_FIELD_SLY, stride - 1);
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_stride);
+
+void ipu_cpmem_set_high_priority(struct ipuv3_channel *ch)
+{
+	struct ipu_soc *ipu = ch->ipu;
+	u32 val;
+
+	if (ipu->ipu_type == IPUV3EX)
+		ipu_ch_param_write_field(ch, IPU_FIELD_ID, 1);
+
+	val = ipu_idmac_read(ipu, IDMAC_CHA_PRI(ch->num));
+	val |= 1 << (ch->num % 32);
+	ipu_idmac_write(ipu, val, IDMAC_CHA_PRI(ch->num));
+};
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_high_priority);
+
+void ipu_cpmem_set_buffer(struct ipuv3_channel *ch, int bufnum, dma_addr_t buf)
+{
+	if (bufnum)
+		ipu_ch_param_write_field(ch, IPU_FIELD_EBA1, buf >> 3);
+	else
+		ipu_ch_param_write_field(ch, IPU_FIELD_EBA0, buf >> 3);
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_buffer);
+
+void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride)
+{
+	ipu_ch_param_write_field(ch, IPU_FIELD_SO, 1);
+	ipu_ch_param_write_field(ch, IPU_FIELD_ILO, stride / 8);
+	ipu_ch_param_write_field(ch, IPU_FIELD_SLY, (stride * 2) - 1);
+};
+EXPORT_SYMBOL_GPL(ipu_cpmem_interlaced_scan);
+
+void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize)
+{
+	ipu_ch_param_write_field(ch, IPU_FIELD_NPB, burstsize - 1);
+};
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_burstsize);
+
+int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
+			     const struct ipu_rgb *rgb)
+{
+	int bpp = 0, npb = 0, ro, go, bo, to;
+
+	ro = rgb->bits_per_pixel - rgb->red.length - rgb->red.offset;
+	go = rgb->bits_per_pixel - rgb->green.length - rgb->green.offset;
+	bo = rgb->bits_per_pixel - rgb->blue.length - rgb->blue.offset;
+	to = rgb->bits_per_pixel - rgb->transp.length - rgb->transp.offset;
+
+	ipu_ch_param_write_field(ch, IPU_FIELD_WID0, rgb->red.length - 1);
+	ipu_ch_param_write_field(ch, IPU_FIELD_OFS0, ro);
+	ipu_ch_param_write_field(ch, IPU_FIELD_WID1, rgb->green.length - 1);
+	ipu_ch_param_write_field(ch, IPU_FIELD_OFS1, go);
+	ipu_ch_param_write_field(ch, IPU_FIELD_WID2, rgb->blue.length - 1);
+	ipu_ch_param_write_field(ch, IPU_FIELD_OFS2, bo);
+
+	if (rgb->transp.length) {
+		ipu_ch_param_write_field(ch, IPU_FIELD_WID3,
+				rgb->transp.length - 1);
+		ipu_ch_param_write_field(ch, IPU_FIELD_OFS3, to);
+	} else {
+		ipu_ch_param_write_field(ch, IPU_FIELD_WID3, 7);
+		ipu_ch_param_write_field(ch, IPU_FIELD_OFS3,
+				rgb->bits_per_pixel);
+	}
+
+	switch (rgb->bits_per_pixel) {
+	case 32:
+		bpp = 0;
+		npb = 15;
+		break;
+	case 24:
+		bpp = 1;
+		npb = 19;
+		break;
+	case 16:
+		bpp = 3;
+		npb = 31;
+		break;
+	case 8:
+		bpp = 5;
+		npb = 63;
+		break;
+	default:
+		return -EINVAL;
+	}
+	ipu_ch_param_write_field(ch, IPU_FIELD_BPP, bpp);
+	ipu_ch_param_write_field(ch, IPU_FIELD_NPB, npb);
+	ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 7); /* rgb mode */
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_format_rgb);
+
+int ipu_cpmem_set_format_passthrough(struct ipuv3_channel *ch, int width)
+{
+	int bpp = 0, npb = 0;
+
+	switch (width) {
+	case 32:
+		bpp = 0;
+		npb = 15;
+		break;
+	case 24:
+		bpp = 1;
+		npb = 19;
+		break;
+	case 16:
+		bpp = 3;
+		npb = 31;
+		break;
+	case 8:
+		bpp = 5;
+		npb = 63;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ipu_ch_param_write_field(ch, IPU_FIELD_BPP, bpp);
+	ipu_ch_param_write_field(ch, IPU_FIELD_NPB, npb);
+	ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 6); /* raw mode */
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_format_passthrough);
+
+void ipu_cpmem_set_yuv_interleaved(struct ipuv3_channel *ch, u32 pixel_format)
+{
+	switch (pixel_format) {
+	case V4L2_PIX_FMT_UYVY:
+		ipu_ch_param_write_field(ch, IPU_FIELD_BPP, 3); /* bits/pixel */
+		ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 0xA);/* pix fmt */
+		ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);/* burst size */
+		break;
+	case V4L2_PIX_FMT_YUYV:
+		ipu_ch_param_write_field(ch, IPU_FIELD_BPP, 3); /* bits/pixel */
+		ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 0x8);/* pix fmt */
+		ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);/* burst size */
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_yuv_interleaved);
+
+void ipu_cpmem_set_yuv_planar_full(struct ipuv3_channel *ch,
+				   u32 pixel_format, int stride,
+				   int u_offset, int v_offset)
+{
+	switch (pixel_format) {
+	case V4L2_PIX_FMT_YUV420:
+		ipu_ch_param_write_field(ch, IPU_FIELD_SLUV, (stride / 2) - 1);
+		ipu_ch_param_write_field(ch, IPU_FIELD_UBO, u_offset / 8);
+		ipu_ch_param_write_field(ch, IPU_FIELD_VBO, v_offset / 8);
+		break;
+	case V4L2_PIX_FMT_YVU420:
+		ipu_ch_param_write_field(ch, IPU_FIELD_SLUV, (stride / 2) - 1);
+		ipu_ch_param_write_field(ch, IPU_FIELD_UBO, v_offset / 8);
+		ipu_ch_param_write_field(ch, IPU_FIELD_VBO, u_offset / 8);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_yuv_planar_full);
+
+void ipu_cpmem_set_yuv_planar(struct ipuv3_channel *ch,
+			      u32 pixel_format, int stride, int height)
+{
+	int u_offset, v_offset;
+	int uv_stride = 0;
+
+	switch (pixel_format) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YVU420:
+		uv_stride = stride / 2;
+		u_offset = stride * height;
+		v_offset = u_offset + (uv_stride * height / 2);
+		ipu_cpmem_set_yuv_planar_full(ch, pixel_format, stride,
+					      u_offset, v_offset);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_yuv_planar);
+
+static const struct ipu_rgb def_rgb_32 = {
+	.red	= { .offset = 16, .length = 8, },
+	.green	= { .offset =  8, .length = 8, },
+	.blue	= { .offset =  0, .length = 8, },
+	.transp = { .offset = 24, .length = 8, },
+	.bits_per_pixel = 32,
+};
+
+static const struct ipu_rgb def_bgr_32 = {
+	.red	= { .offset =  0, .length = 8, },
+	.green	= { .offset =  8, .length = 8, },
+	.blue	= { .offset = 16, .length = 8, },
+	.transp = { .offset = 24, .length = 8, },
+	.bits_per_pixel = 32,
+};
+
+static const struct ipu_rgb def_rgb_24 = {
+	.red	= { .offset = 16, .length = 8, },
+	.green	= { .offset =  8, .length = 8, },
+	.blue	= { .offset =  0, .length = 8, },
+	.transp = { .offset =  0, .length = 0, },
+	.bits_per_pixel = 24,
+};
+
+static const struct ipu_rgb def_bgr_24 = {
+	.red	= { .offset =  0, .length = 8, },
+	.green	= { .offset =  8, .length = 8, },
+	.blue	= { .offset = 16, .length = 8, },
+	.transp = { .offset =  0, .length = 0, },
+	.bits_per_pixel = 24,
+};
+
+static const struct ipu_rgb def_rgb_16 = {
+	.red	= { .offset = 11, .length = 5, },
+	.green	= { .offset =  5, .length = 6, },
+	.blue	= { .offset =  0, .length = 5, },
+	.transp = { .offset =  0, .length = 0, },
+	.bits_per_pixel = 16,
+};
+
+static const struct ipu_rgb def_bgr_16 = {
+	.red	= { .offset =  0, .length = 5, },
+	.green	= { .offset =  5, .length = 6, },
+	.blue	= { .offset = 11, .length = 5, },
+	.transp = { .offset =  0, .length = 0, },
+	.bits_per_pixel = 16,
+};
+
+#define Y_OFFSET(pix, x, y)	((x) + pix->width * (y))
+#define U_OFFSET(pix, x, y)	((pix->width * pix->height) + \
+					(pix->width * (y) / 4) + (x) / 2)
+#define V_OFFSET(pix, x, y)	((pix->width * pix->height) + \
+					(pix->width * pix->height / 4) + \
+					(pix->width * (y) / 4) + (x) / 2)
+
+int ipu_cpmem_set_fmt(struct ipuv3_channel *ch, u32 drm_fourcc)
+{
+	switch (drm_fourcc) {
+	case DRM_FORMAT_YUV420:
+	case DRM_FORMAT_YVU420:
+		/* pix format */
+		ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 2);
+		/* burst size */
+		ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);
+		break;
+	case DRM_FORMAT_UYVY:
+		/* bits/pixel */
+		ipu_ch_param_write_field(ch, IPU_FIELD_BPP, 3);
+		/* pix format */
+		ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 0xA);
+		/* burst size */
+		ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);
+		break;
+	case DRM_FORMAT_YUYV:
+		/* bits/pixel */
+		ipu_ch_param_write_field(ch, IPU_FIELD_BPP, 3);
+		/* pix format */
+		ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 0x8);
+		/* burst size */
+		ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);
+		break;
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_XBGR8888:
+		ipu_cpmem_set_format_rgb(ch, &def_bgr_32);
+		break;
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XRGB8888:
+		ipu_cpmem_set_format_rgb(ch, &def_rgb_32);
+		break;
+	case DRM_FORMAT_BGR888:
+		ipu_cpmem_set_format_rgb(ch, &def_bgr_24);
+		break;
+	case DRM_FORMAT_RGB888:
+		ipu_cpmem_set_format_rgb(ch, &def_rgb_24);
+		break;
+	case DRM_FORMAT_RGB565:
+		ipu_cpmem_set_format_rgb(ch, &def_rgb_16);
+		break;
+	case DRM_FORMAT_BGR565:
+		ipu_cpmem_set_format_rgb(ch, &def_bgr_16);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_fmt);
+
+int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image)
+{
+	struct v4l2_pix_format *pix = &image->pix;
+	int y_offset, u_offset, v_offset;
+
+	pr_debug("%s: resolution: %dx%d stride: %d\n",
+		 __func__, pix->width, pix->height,
+		 pix->bytesperline);
+
+	ipu_cpmem_set_resolution(ch, image->rect.width, image->rect.height);
+	ipu_cpmem_set_stride(ch, pix->bytesperline);
+
+	ipu_cpmem_set_fmt(ch, v4l2_pix_fmt_to_drm_fourcc(pix->pixelformat));
+
+	switch (pix->pixelformat) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YVU420:
+		y_offset = Y_OFFSET(pix, image->rect.left, image->rect.top);
+		u_offset = U_OFFSET(pix, image->rect.left,
+				    image->rect.top) - y_offset;
+		v_offset = V_OFFSET(pix, image->rect.left,
+				    image->rect.top) - y_offset;
+
+		ipu_cpmem_set_yuv_planar_full(ch, pix->pixelformat,
+				pix->bytesperline, u_offset, v_offset);
+		ipu_cpmem_set_buffer(ch, 0, image->phys + y_offset);
+		break;
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_YUYV:
+		ipu_cpmem_set_buffer(ch, 0, image->phys +
+				     image->rect.left * 2 +
+				     image->rect.top * image->pix.bytesperline);
+		break;
+	case V4L2_PIX_FMT_RGB32:
+	case V4L2_PIX_FMT_BGR32:
+		ipu_cpmem_set_buffer(ch, 0, image->phys +
+				     image->rect.left * 4 +
+				     image->rect.top * image->pix.bytesperline);
+		break;
+	case V4L2_PIX_FMT_RGB565:
+		ipu_cpmem_set_buffer(ch, 0, image->phys +
+				     image->rect.left * 2 +
+				     image->rect.top * image->pix.bytesperline);
+		break;
+	case V4L2_PIX_FMT_RGB24:
+	case V4L2_PIX_FMT_BGR24:
+		ipu_cpmem_set_buffer(ch, 0, image->phys +
+				     image->rect.left * 3 +
+				     image->rect.top * image->pix.bytesperline);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_image);
+
+int ipu_cpmem_init(struct ipu_soc *ipu, struct device *dev, unsigned long base)
+{
+	struct ipu_cpmem *cpmem;
+
+	cpmem = devm_kzalloc(dev, sizeof(*cpmem), GFP_KERNEL);
+	if (!cpmem)
+		return -ENOMEM;
+
+	ipu->cpmem_priv = cpmem;
+
+	spin_lock_init(&cpmem->lock);
+	cpmem->base = devm_ioremap(dev, base, SZ_128K);
+	if (!cpmem->base)
+		return -ENOMEM;
+
+	dev_dbg(dev, "CPMEM base: 0x%08lx remapped to %p\n",
+		base, cpmem->base);
+	cpmem->ipu = ipu;
+
+	return 0;
+}
+
+void ipu_cpmem_exit(struct ipu_soc *ipu)
+{
+}
diff --git a/drivers/gpu/ipu-v3/ipu-prv.h b/drivers/gpu/ipu-v3/ipu-prv.h
index c93f50ec04f7..0a7b2adaba39 100644
--- a/drivers/gpu/ipu-v3/ipu-prv.h
+++ b/drivers/gpu/ipu-v3/ipu-prv.h
@@ -148,6 +148,7 @@ struct ipuv3_channel {
 	struct ipu_soc *ipu;
 };
 
+struct ipu_cpmem;
 struct ipu_dc_priv;
 struct ipu_dmfc_priv;
 struct ipu_di;
@@ -164,7 +165,6 @@ struct ipu_soc {
 
 	void __iomem		*cm_reg;
 	void __iomem		*idmac_reg;
-	struct ipu_ch_param __iomem	*cpmem_base;
 
 	int			usecount;
 
@@ -176,6 +176,7 @@ struct ipu_soc {
 	int			irq_err;
 	struct irq_domain	*domain;
 
+	struct ipu_cpmem	*cpmem_priv;
 	struct ipu_dc_priv	*dc_priv;
 	struct ipu_dp_priv	*dp_priv;
 	struct ipu_dmfc_priv	*dmfc_priv;
@@ -183,6 +184,17 @@ struct ipu_soc {
 	struct ipu_smfc_priv	*smfc_priv;
 };
 
+static inline u32 ipu_idmac_read(struct ipu_soc *ipu, unsigned offset)
+{
+	return readl(ipu->idmac_reg + offset);
+}
+
+static inline void ipu_idmac_write(struct ipu_soc *ipu, u32 value,
+				   unsigned offset)
+{
+	writel(value, ipu->idmac_reg + offset);
+}
+
 void ipu_srm_dp_sync_update(struct ipu_soc *ipu);
 
 int ipu_module_enable(struct ipu_soc *ipu, u32 mask);
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 3e43e22cdff9..ef64b66b18df 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -107,6 +107,42 @@ void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
 int ipu_idmac_get_current_buffer(struct ipuv3_channel *channel);
 void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num);
 
+/*
+ * IPU Channel Parameter Memory (cpmem) functions
+ */
+struct ipu_rgb {
+	struct fb_bitfield      red;
+	struct fb_bitfield      green;
+	struct fb_bitfield      blue;
+	struct fb_bitfield      transp;
+	int                     bits_per_pixel;
+};
+
+struct ipu_image {
+	struct v4l2_pix_format pix;
+	struct v4l2_rect rect;
+	dma_addr_t phys;
+};
+
+void ipu_cpmem_zero(struct ipuv3_channel *ch);
+void ipu_cpmem_set_resolution(struct ipuv3_channel *ch, int xres, int yres);
+void ipu_cpmem_set_stride(struct ipuv3_channel *ch, int stride);
+void ipu_cpmem_set_high_priority(struct ipuv3_channel *ch);
+void ipu_cpmem_set_buffer(struct ipuv3_channel *ch, int bufnum, dma_addr_t buf);
+void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride);
+void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize);
+int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
+			     const struct ipu_rgb *rgb);
+int ipu_cpmem_set_format_passthrough(struct ipuv3_channel *ch, int width);
+void ipu_cpmem_set_yuv_interleaved(struct ipuv3_channel *ch, u32 pixel_format);
+void ipu_cpmem_set_yuv_planar_full(struct ipuv3_channel *ch,
+				   u32 pixel_format, int stride,
+				   int u_offset, int v_offset);
+void ipu_cpmem_set_yuv_planar(struct ipuv3_channel *ch,
+			      u32 pixel_format, int stride, int height);
+int ipu_cpmem_set_fmt(struct ipuv3_channel *ch, u32 drm_fourcc);
+int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image);
+
 /*
  * IPU Display Controller (dc) functions
  */
@@ -180,161 +216,9 @@ int ipu_smfc_disable(struct ipu_soc *ipu);
 int ipu_smfc_map_channel(struct ipu_soc *ipu, int channel, int csi_id, int mipi_id);
 int ipu_smfc_set_burstsize(struct ipu_soc *ipu, int channel, int burstsize);
 
-#define IPU_CPMEM_WORD(word, ofs, size) ((((word) * 160 + (ofs)) << 8) | (size))
-
-#define IPU_FIELD_UBO		IPU_CPMEM_WORD(0, 46, 22)
-#define IPU_FIELD_VBO		IPU_CPMEM_WORD(0, 68, 22)
-#define IPU_FIELD_IOX		IPU_CPMEM_WORD(0, 90, 4)
-#define IPU_FIELD_RDRW		IPU_CPMEM_WORD(0, 94, 1)
-#define IPU_FIELD_SO		IPU_CPMEM_WORD(0, 113, 1)
-#define IPU_FIELD_SLY		IPU_CPMEM_WORD(1, 102, 14)
-#define IPU_FIELD_SLUV		IPU_CPMEM_WORD(1, 128, 14)
-
-#define IPU_FIELD_XV		IPU_CPMEM_WORD(0, 0, 10)
-#define IPU_FIELD_YV		IPU_CPMEM_WORD(0, 10, 9)
-#define IPU_FIELD_XB		IPU_CPMEM_WORD(0, 19, 13)
-#define IPU_FIELD_YB		IPU_CPMEM_WORD(0, 32, 12)
-#define IPU_FIELD_NSB_B		IPU_CPMEM_WORD(0, 44, 1)
-#define IPU_FIELD_CF		IPU_CPMEM_WORD(0, 45, 1)
-#define IPU_FIELD_SX		IPU_CPMEM_WORD(0, 46, 12)
-#define IPU_FIELD_SY		IPU_CPMEM_WORD(0, 58, 11)
-#define IPU_FIELD_NS		IPU_CPMEM_WORD(0, 69, 10)
-#define IPU_FIELD_SDX		IPU_CPMEM_WORD(0, 79, 7)
-#define IPU_FIELD_SM		IPU_CPMEM_WORD(0, 86, 10)
-#define IPU_FIELD_SCC		IPU_CPMEM_WORD(0, 96, 1)
-#define IPU_FIELD_SCE		IPU_CPMEM_WORD(0, 97, 1)
-#define IPU_FIELD_SDY		IPU_CPMEM_WORD(0, 98, 7)
-#define IPU_FIELD_SDRX		IPU_CPMEM_WORD(0, 105, 1)
-#define IPU_FIELD_SDRY		IPU_CPMEM_WORD(0, 106, 1)
-#define IPU_FIELD_BPP		IPU_CPMEM_WORD(0, 107, 3)
-#define IPU_FIELD_DEC_SEL	IPU_CPMEM_WORD(0, 110, 2)
-#define IPU_FIELD_DIM		IPU_CPMEM_WORD(0, 112, 1)
-#define IPU_FIELD_BNDM		IPU_CPMEM_WORD(0, 114, 3)
-#define IPU_FIELD_BM		IPU_CPMEM_WORD(0, 117, 2)
-#define IPU_FIELD_ROT		IPU_CPMEM_WORD(0, 119, 1)
-#define IPU_FIELD_HF		IPU_CPMEM_WORD(0, 120, 1)
-#define IPU_FIELD_VF		IPU_CPMEM_WORD(0, 121, 1)
-#define IPU_FIELD_THE		IPU_CPMEM_WORD(0, 122, 1)
-#define IPU_FIELD_CAP		IPU_CPMEM_WORD(0, 123, 1)
-#define IPU_FIELD_CAE		IPU_CPMEM_WORD(0, 124, 1)
-#define IPU_FIELD_FW		IPU_CPMEM_WORD(0, 125, 13)
-#define IPU_FIELD_FH		IPU_CPMEM_WORD(0, 138, 12)
-#define IPU_FIELD_EBA0		IPU_CPMEM_WORD(1, 0, 29)
-#define IPU_FIELD_EBA1		IPU_CPMEM_WORD(1, 29, 29)
-#define IPU_FIELD_ILO		IPU_CPMEM_WORD(1, 58, 20)
-#define IPU_FIELD_NPB		IPU_CPMEM_WORD(1, 78, 7)
-#define IPU_FIELD_PFS		IPU_CPMEM_WORD(1, 85, 4)
-#define IPU_FIELD_ALU		IPU_CPMEM_WORD(1, 89, 1)
-#define IPU_FIELD_ALBM		IPU_CPMEM_WORD(1, 90, 3)
-#define IPU_FIELD_ID		IPU_CPMEM_WORD(1, 93, 2)
-#define IPU_FIELD_TH		IPU_CPMEM_WORD(1, 95, 7)
-#define IPU_FIELD_SL		IPU_CPMEM_WORD(1, 102, 14)
-#define IPU_FIELD_WID0		IPU_CPMEM_WORD(1, 116, 3)
-#define IPU_FIELD_WID1		IPU_CPMEM_WORD(1, 119, 3)
-#define IPU_FIELD_WID2		IPU_CPMEM_WORD(1, 122, 3)
-#define IPU_FIELD_WID3		IPU_CPMEM_WORD(1, 125, 3)
-#define IPU_FIELD_OFS0		IPU_CPMEM_WORD(1, 128, 5)
-#define IPU_FIELD_OFS1		IPU_CPMEM_WORD(1, 133, 5)
-#define IPU_FIELD_OFS2		IPU_CPMEM_WORD(1, 138, 5)
-#define IPU_FIELD_OFS3		IPU_CPMEM_WORD(1, 143, 5)
-#define IPU_FIELD_SXYS		IPU_CPMEM_WORD(1, 148, 1)
-#define IPU_FIELD_CRE		IPU_CPMEM_WORD(1, 149, 1)
-#define IPU_FIELD_DEC_SEL2	IPU_CPMEM_WORD(1, 150, 1)
-
-struct ipu_cpmem_word {
-	u32 data[5];
-	u32 res[3];
-};
-
-struct ipu_ch_param {
-	struct ipu_cpmem_word word[2];
-};
-
-void ipu_ch_param_write_field(struct ipu_ch_param __iomem *base, u32 wbs, u32 v);
-u32 ipu_ch_param_read_field(struct ipu_ch_param __iomem *base, u32 wbs);
-struct ipu_ch_param __iomem *ipu_get_cpmem(struct ipuv3_channel *channel);
-void ipu_ch_param_dump(struct ipu_ch_param __iomem *p);
-
-static inline void ipu_ch_param_zero(struct ipu_ch_param __iomem *p)
-{
-	int i;
-	void __iomem *base = p;
-
-	for (i = 0; i < sizeof(*p) / sizeof(u32); i++)
-		writel(0, base + i * sizeof(u32));
-}
-
-static inline void ipu_cpmem_set_buffer(struct ipu_ch_param __iomem *p,
-		int bufnum, dma_addr_t buf)
-{
-	if (bufnum)
-		ipu_ch_param_write_field(p, IPU_FIELD_EBA1, buf >> 3);
-	else
-		ipu_ch_param_write_field(p, IPU_FIELD_EBA0, buf >> 3);
-}
-
-static inline void ipu_cpmem_set_resolution(struct ipu_ch_param __iomem *p,
-		int xres, int yres)
-{
-	ipu_ch_param_write_field(p, IPU_FIELD_FW, xres - 1);
-	ipu_ch_param_write_field(p, IPU_FIELD_FH, yres - 1);
-}
-
-static inline void ipu_cpmem_set_stride(struct ipu_ch_param __iomem *p,
-		int stride)
-{
-	ipu_ch_param_write_field(p, IPU_FIELD_SLY, stride - 1);
-}
-
-void ipu_cpmem_set_high_priority(struct ipuv3_channel *channel);
-
-struct ipu_rgb {
-	struct fb_bitfield	red;
-	struct fb_bitfield	green;
-	struct fb_bitfield	blue;
-	struct fb_bitfield	transp;
-	int			bits_per_pixel;
-};
-
-struct ipu_image {
-	struct v4l2_pix_format pix;
-	struct v4l2_rect rect;
-	dma_addr_t phys;
-};
-
-int ipu_cpmem_set_format_passthrough(struct ipu_ch_param __iomem *p,
-		int width);
-
-int ipu_cpmem_set_format_rgb(struct ipu_ch_param __iomem *,
-		const struct ipu_rgb *rgb);
-
-static inline void ipu_cpmem_interlaced_scan(struct ipu_ch_param *p,
-		int stride)
-{
-	ipu_ch_param_write_field(p, IPU_FIELD_SO, 1);
-	ipu_ch_param_write_field(p, IPU_FIELD_ILO, stride / 8);
-	ipu_ch_param_write_field(p, IPU_FIELD_SLY, (stride * 2) - 1);
-};
-
-void ipu_cpmem_set_yuv_planar(struct ipu_ch_param __iomem *p, u32 pixel_format,
-			int stride, int height);
-void ipu_cpmem_set_yuv_interleaved(struct ipu_ch_param __iomem *p,
-				   u32 pixel_format);
-void ipu_cpmem_set_yuv_planar_full(struct ipu_ch_param __iomem *p,
-		u32 pixel_format, int stride, int u_offset, int v_offset);
-int ipu_cpmem_set_fmt(struct ipu_ch_param __iomem *cpmem, u32 pixelformat);
-int ipu_cpmem_set_image(struct ipu_ch_param __iomem *cpmem,
-		struct ipu_image *image);
-
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
 
-static inline void ipu_cpmem_set_burstsize(struct ipu_ch_param __iomem *p,
-		int burstsize)
-{
-	ipu_ch_param_write_field(p, IPU_FIELD_NPB, burstsize - 1);
-};
-
 struct ipu_client_platformdata {
 	int csi;
 	int di;
-- 
cgit v1.2.3


From ba07975f0fe5bf95107d71d0df0405c16f5c3266 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:30 -0700
Subject: gpu: ipu-v3: Add functions to set CSI/IC source muxes

Adds two new functions, ipu_set_csi_src_mux() and ipu_set_ic_src_mux(),
that select the inputs to the CSI and IC respectively. Both muxes are
programmed in the IPU_CONF register.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 51 +++++++++++++++++++++++++++++++++++++++++
 include/video/imx-ipu-v3.h      |  6 +++++
 2 files changed, 57 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 5978e7aab8ed..cae543115856 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -382,6 +382,57 @@ static int ipu_memory_reset(struct ipu_soc *ipu)
 	return 0;
 }
 
+/*
+ * Set the source mux for the given CSI. Selects either parallel or
+ * MIPI CSI2 sources.
+ */
+void ipu_set_csi_src_mux(struct ipu_soc *ipu, int csi_id, bool mipi_csi2)
+{
+	unsigned long flags;
+	u32 val, mask;
+
+	mask = (csi_id == 1) ? IPU_CONF_CSI1_DATA_SOURCE :
+		IPU_CONF_CSI0_DATA_SOURCE;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	val = ipu_cm_read(ipu, IPU_CONF);
+	if (mipi_csi2)
+		val |= mask;
+	else
+		val &= ~mask;
+	ipu_cm_write(ipu, val, IPU_CONF);
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_set_csi_src_mux);
+
+/*
+ * Set the source mux for the IC. Selects either CSI[01] or the VDI.
+ */
+void ipu_set_ic_src_mux(struct ipu_soc *ipu, int csi_id, bool vdi)
+{
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	val = ipu_cm_read(ipu, IPU_CONF);
+	if (vdi) {
+		val |= IPU_CONF_IC_INPUT;
+	} else {
+		val &= ~IPU_CONF_IC_INPUT;
+		if (csi_id == 1)
+			val |= IPU_CONF_CSI_SEL;
+		else
+			val &= ~IPU_CONF_CSI_SEL;
+	}
+	ipu_cm_write(ipu, val, IPU_CONF);
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_set_ic_src_mux);
+
 struct ipu_devtype {
 	const char *name;
 	unsigned long cm_ofs;
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index ef64b66b18df..f80fe13b0d4d 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -92,6 +92,12 @@ int ipu_idmac_channel_irq(struct ipu_soc *ipu, struct ipuv3_channel *channel,
 #define IPU_IRQ_VSYNC_PRE_0		(448 + 14)
 #define IPU_IRQ_VSYNC_PRE_1		(448 + 15)
 
+/*
+ * IPU Common functions
+ */
+void ipu_set_csi_src_mux(struct ipu_soc *ipu, int csi_id, bool mipi_csi2);
+void ipu_set_ic_src_mux(struct ipu_soc *ipu, int csi_id, bool vdi);
+
 /*
  * IPU Image DMA Controller (idmac) functions
  */
-- 
cgit v1.2.3


From 4d61b39bc117b36682c1dd67ee386960ae826bef Mon Sep 17 00:00:00 2001
From: "Subhransu S. Prusty" <subhransu.s.prusty@intel.com>
Date: Mon, 18 Aug 2014 14:53:03 +0530
Subject: ASoC: core: fix .info for SND_SOC_BYTES_TLV

Commit 7523a271 - "ASoC: core: add a helper for extended byte controls using
TLV" introduced support for TLV byte controls but had a typo for the info
function, so fix the same

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index be6ecae247b0..c83a334dd00f 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -277,7 +277,7 @@
 	.access = SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE | \
 		  SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK, \
 	.tlv.c = (snd_soc_bytes_tlv_callback), \
-	.info = snd_soc_info_bytes_ext, \
+	.info = snd_soc_bytes_info_ext, \
 	.private_value = (unsigned long)&(struct soc_bytes_ext) \
 		{.max = xcount, .get = xhandler_get, .put = xhandler_put, } }
 #define SOC_SINGLE_XR_SX(xname, xregbase, xregcount, xnbits, \
-- 
cgit v1.2.3


From 716845ebeb505353d900320b4a74e8330520410d Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Mon, 18 Aug 2014 10:34:08 +0800
Subject: regulator: core: Fix build error due to const qualifier for ops

Drop const qualifier for ops of struct regulator_desc.
Allow regulator drivers to update ops before registering regulator.

Fix below build error:
  CC [M]  drivers/regulator/mc13892-regulator.o
drivers/regulator/mc13892-regulator.c: In function 'mc13892_regulator_probe':
drivers/regulator/mc13892-regulator.c:586:3: error: assignment of member 'set_mode' in read-only object
drivers/regulator/mc13892-regulator.c:588:3: error: assignment of member 'get_mode' in read-only object
make[2]: *** [drivers/regulator/mc13892-regulator.o] Error 1
make[1]: *** [drivers/regulator] Error 2
make: *** [drivers] Error 2

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/regulator/driver.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index efe058f8f746..3abda7554d82 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -246,7 +246,7 @@ struct regulator_desc {
 	int id;
 	bool continuous_voltage_range;
 	unsigned n_voltages;
-	const struct regulator_ops *ops;
+	struct regulator_ops *ops;
 	int irq;
 	enum regulator_type type;
 	struct module *owner;
-- 
cgit v1.2.3


From 503e6636b6f96056210062be703356f4253b6db9 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Mon, 11 Aug 2014 14:24:47 +0100
Subject: asm-generic: add memfd_create system call to unistd.h

Commit 9183df25fe7b ("shm: add memfd_create() syscall") added a new
system call (memfd_create) but didn't update the asm-generic unistd
header.

This patch adds the new system call to the asm-generic version of
unistd.h so that it can be used by architectures such as arm64.

Cc: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 include/uapi/asm-generic/unistd.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index f1afd607f043..11d11bc5c78f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -703,9 +703,11 @@ __SYSCALL(__NR_renameat2, sys_renameat2)
 __SYSCALL(__NR_seccomp, sys_seccomp)
 #define __NR_getrandom 278
 __SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 279
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
 
 #undef __NR_syscalls
-#define __NR_syscalls 279
+#define __NR_syscalls 280
 
 /*
  * All syscalls below here should go away really,
-- 
cgit v1.2.3


From 18c01ab30288d9d0a7d80b08b659531f37ed379d Mon Sep 17 00:00:00 2001
From: Rajesh Ghanekar <Rajesh_Ghanekar@symantec.com>
Date: Fri, 1 Aug 2014 22:17:30 -0400
Subject: nfsd: allow turning off nfsv3 readdir_plus

One of our customer's application only needs file names, not file
attributes. With directories having 10K+ inodes (assuming buffer cache
has directory blocks cached having file names, but inode cache is
limited and hence need eviction of older cached inodes), older inodes
are evicted periodically. So if they keep on doing readdir(2) from NSF
client on multiple directories, some directory's files are periodically
removed from inode cache and hence new readdir(2) on same directory
requires disk access to bring back inodes again to inode cache.

As READDIRPLUS request fetches attributes also, doing getattr on each
file on server, it causes unnecessary disk accesses. If READDIRPLUS on
NFS client is returned with -ENOTSUPP, NFS client uses READDIR request
which just gets the names of the files in a directory, not attributes,
hence avoiding disk accesses on server.

There's already a corresponding client-side mount option, but an export
option reduces the need for configuration across multiple clients.

This flag affects NFSv3 only.  If it turns out it's needed for NFSv4 as
well then we may have to figure out how to extend the behavior to NFSv4,
but it's not currently obvious how to do that.

Signed-off-by: Rajesh Ghanekar <rajesh_ghanekar@symantec.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/export.c                 | 1 +
 fs/nfsd/nfs3proc.c               | 8 ++++++++
 include/uapi/linux/nfsd/export.h | 5 +++--
 3 files changed, 12 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 72ffd7cce3c3..30a739d896ff 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1145,6 +1145,7 @@ static struct flags {
 	{ NFSEXP_ALLSQUASH, {"all_squash", ""}},
 	{ NFSEXP_ASYNC, {"async", "sync"}},
 	{ NFSEXP_GATHERED_WRITES, {"wdelay", "no_wdelay"}},
+	{ NFSEXP_NOREADDIRPLUS, {"nordirplus", ""}},
 	{ NFSEXP_NOHIDE, {"nohide", ""}},
 	{ NFSEXP_CROSSMOUNT, {"crossmnt", ""}},
 	{ NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}},
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index fc51f7f6b36d..12f2aab4f614 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -466,6 +466,14 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
 	resp->buflen = resp->count;
 	resp->rqstp = rqstp;
 	offset = argp->cookie;
+
+	nfserr = fh_verify(rqstp, &resp->fh, S_IFDIR, NFSD_MAY_NOP);
+	if (nfserr)
+		RETURN_STATUS(nfserr);
+
+	if (resp->fh.fh_export->ex_flags & NFSEXP_NOREADDIRPLUS)
+		RETURN_STATUS(nfserr_notsupp);
+
 	nfserr = nfsd_readdir(rqstp, &resp->fh,
 				     &offset,
 				     &resp->common,
diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h
index cf47c313794e..584b6ef3a5e8 100644
--- a/include/uapi/linux/nfsd/export.h
+++ b/include/uapi/linux/nfsd/export.h
@@ -28,7 +28,8 @@
 #define NFSEXP_ALLSQUASH	0x0008
 #define NFSEXP_ASYNC		0x0010
 #define NFSEXP_GATHERED_WRITES	0x0020
-/* 40 80 100 currently unused */
+#define NFSEXP_NOREADDIRPLUS    0x0040
+/* 80 100 currently unused */
 #define NFSEXP_NOHIDE		0x0200
 #define NFSEXP_NOSUBTREECHECK	0x0400
 #define	NFSEXP_NOAUTHNLM	0x0800		/* Don't authenticate NLM requests - just trust */
@@ -47,7 +48,7 @@
  */
 #define	NFSEXP_V4ROOT		0x10000
 /* All flags that we claim to support.  (Note we don't support NOACL.) */
-#define NFSEXP_ALLFLAGS		0x17E3F
+#define NFSEXP_ALLFLAGS		0x1FE7F
 
 /* The flags that may vary depending on security flavor: */
 #define NFSEXP_SECINFO_FLAGS	(NFSEXP_READONLY | NFSEXP_ROOTSQUASH \
-- 
cgit v1.2.3


From 701e1e789142042144c8cc10b8f6d1554e960144 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 15 Aug 2014 11:52:53 +0200
Subject: drm/radeon: properly document reloc priority mask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of hard coding the value properly document
that this is an userspace interface.

No intended functional change.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/radeon/radeon_cs.c | 3 ++-
 include/uapi/drm/radeon_drm.h      | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index ee712c199b25..cb12df784d83 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -132,7 +132,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		 * the buffers used for read only, which doubles the range
 		 * to 0 to 31. 32 is reserved for the kernel driver.
 		 */
-		priority = (r->flags & 0xf) * 2 + !!r->write_domain;
+		priority = (r->flags & RADEON_RELOC_PRIO_MASK) * 2
+			   + !!r->write_domain;
 
 		/* the first reloc of an UVD job is the msg and that must be in
 		   VRAM, also but everything into VRAM on AGP cards to avoid
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 509b2d7a41b7..fea6099608ef 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -944,6 +944,7 @@ struct drm_radeon_cs_chunk {
 };
 
 /* drm_radeon_cs_reloc.flags */
+#define RADEON_RELOC_PRIO_MASK		(0xf << 0)
 
 struct drm_radeon_cs_reloc {
 	uint32_t		handle;
-- 
cgit v1.2.3


From e5f81539f657af7e9f54ea37986fde8f92acef22 Mon Sep 17 00:00:00 2001
From: Feng Kan <fkan@apm.com>
Date: Wed, 30 Jul 2014 14:56:58 -0700
Subject: irqchip: gic: Replace hex numbers with defines.

This is to cleanup some hex numbers used in the code and replace
them with defines to make the code cleaner.

Signed-off-by: Feng Kan <fkan@apm.com>
Reviewed-by: Anup Patel <apatel@apm.com>
Link: https://lkml.kernel.org/r/1406757419-18729-2-git-send-email-fkan@apm.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 drivers/irqchip/irq-gic-common.c | 15 +++++++++------
 drivers/irqchip/irq-gic.c        | 25 +++++++++++++------------
 include/linux/irqchip/arm-gic.h  | 15 +++++++++++++++
 3 files changed, 37 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
index 60ac704d2090..61541ff24397 100644
--- a/drivers/irqchip/irq-gic-common.c
+++ b/drivers/irqchip/irq-gic-common.c
@@ -74,20 +74,22 @@ void __init gic_dist_config(void __iomem *base, int gic_irqs,
 	 * Set all global interrupts to be level triggered, active low.
 	 */
 	for (i = 32; i < gic_irqs; i += 16)
-		writel_relaxed(0, base + GIC_DIST_CONFIG + i / 4);
+		writel_relaxed(GICD_INT_ACTLOW_LVLTRIG,
+					base + GIC_DIST_CONFIG + i / 4);
 
 	/*
 	 * Set priority on all global interrupts.
 	 */
 	for (i = 32; i < gic_irqs; i += 4)
-		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i);
+		writel_relaxed(GICD_INT_DEF_PRI_X4, base + GIC_DIST_PRI + i);
 
 	/*
 	 * Disable all interrupts.  Leave the PPI and SGIs alone
 	 * as they are enabled by redistributor registers.
 	 */
 	for (i = 32; i < gic_irqs; i += 32)
-		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i / 8);
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+					base + GIC_DIST_ENABLE_CLEAR + i / 8);
 
 	if (sync_access)
 		sync_access();
@@ -101,14 +103,15 @@ void gic_cpu_config(void __iomem *base, void (*sync_access)(void))
 	 * Deal with the banked PPI and SGI interrupts - disable all
 	 * PPI interrupts, ensure all SGI interrupts are enabled.
 	 */
-	writel_relaxed(0xffff0000, base + GIC_DIST_ENABLE_CLEAR);
-	writel_relaxed(0x0000ffff, base + GIC_DIST_ENABLE_SET);
+	writel_relaxed(GICD_INT_EN_CLR_PPI, base + GIC_DIST_ENABLE_CLEAR);
+	writel_relaxed(GICD_INT_EN_SET_SGI, base + GIC_DIST_ENABLE_SET);
 
 	/*
 	 * Set priority on PPI and SGI interrupts
 	 */
 	for (i = 0; i < 32; i += 4)
-		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
+		writel_relaxed(GICD_INT_DEF_PRI_X4,
+					base + GIC_DIST_PRI + i * 4 / 4);
 
 	if (sync_access)
 		sync_access();
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 4b959e606fe8..35847453cecb 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -298,8 +298,8 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 	status = readl_relaxed(gic_data_cpu_base(chip_data) + GIC_CPU_INTACK);
 	raw_spin_unlock(&irq_controller_lock);
 
-	gic_irq = (status & 0x3ff);
-	if (gic_irq == 1023)
+	gic_irq = (status & GICC_IAR_INT_ID_MASK);
+	if (gic_irq == GICC_INT_SPURIOUS)
 		goto out;
 
 	cascade_irq = irq_find_mapping(chip_data->domain, gic_irq);
@@ -360,7 +360,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	unsigned int gic_irqs = gic->gic_irqs;
 	void __iomem *base = gic_data_dist_base(gic);
 
-	writel_relaxed(0, base + GIC_DIST_CTRL);
+	writel_relaxed(GICD_DISABLE, base + GIC_DIST_CTRL);
 
 	/*
 	 * Set all global interrupts to this CPU only.
@@ -373,7 +373,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 
 	gic_dist_config(base, gic_irqs, NULL);
 
-	writel_relaxed(1, base + GIC_DIST_CTRL);
+	writel_relaxed(GICD_ENABLE, base + GIC_DIST_CTRL);
 }
 
 static void gic_cpu_init(struct gic_chip_data *gic)
@@ -400,8 +400,8 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 
 	gic_cpu_config(dist_base, NULL);
 
-	writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
-	writel_relaxed(1, base + GIC_CPU_CTRL);
+	writel_relaxed(GICC_INT_PRI_THRESHOLD, base + GIC_CPU_PRIMASK);
+	writel_relaxed(GICC_ENABLE, base + GIC_CPU_CTRL);
 }
 
 void gic_cpu_if_down(void)
@@ -467,14 +467,14 @@ static void gic_dist_restore(unsigned int gic_nr)
 	if (!dist_base)
 		return;
 
-	writel_relaxed(0, dist_base + GIC_DIST_CTRL);
+	writel_relaxed(GICD_DISABLE, dist_base + GIC_DIST_CTRL);
 
 	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
 		writel_relaxed(gic_data[gic_nr].saved_spi_conf[i],
 			dist_base + GIC_DIST_CONFIG + i * 4);
 
 	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
-		writel_relaxed(0xa0a0a0a0,
+		writel_relaxed(GICD_INT_DEF_PRI_X4,
 			dist_base + GIC_DIST_PRI + i * 4);
 
 	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
@@ -485,7 +485,7 @@ static void gic_dist_restore(unsigned int gic_nr)
 		writel_relaxed(gic_data[gic_nr].saved_spi_enable[i],
 			dist_base + GIC_DIST_ENABLE_SET + i * 4);
 
-	writel_relaxed(1, dist_base + GIC_DIST_CTRL);
+	writel_relaxed(GICD_ENABLE, dist_base + GIC_DIST_CTRL);
 }
 
 static void gic_cpu_save(unsigned int gic_nr)
@@ -539,10 +539,11 @@ static void gic_cpu_restore(unsigned int gic_nr)
 		writel_relaxed(ptr[i], dist_base + GIC_DIST_CONFIG + i * 4);
 
 	for (i = 0; i < DIV_ROUND_UP(32, 4); i++)
-		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4);
+		writel_relaxed(GICD_INT_DEF_PRI_X4,
+					dist_base + GIC_DIST_PRI + i * 4);
 
-	writel_relaxed(0xf0, cpu_base + GIC_CPU_PRIMASK);
-	writel_relaxed(1, cpu_base + GIC_CPU_CTRL);
+	writel_relaxed(GICC_INT_PRI_THRESHOLD, cpu_base + GIC_CPU_PRIMASK);
+	writel_relaxed(GICC_ENABLE, cpu_base + GIC_CPU_CTRL);
 }
 
 static int gic_notifier(struct notifier_block *self, unsigned long cmd,	void *v)
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 45e2d8c15bd2..5cb9d41af5be 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -21,7 +21,10 @@
 #define GIC_CPU_ACTIVEPRIO		0xd0
 #define GIC_CPU_IDENT			0xfc
 
+#define GICC_ENABLE			0x1
+#define GICC_INT_PRI_THRESHOLD		0xf0
 #define GICC_IAR_INT_ID_MASK		0x3ff
+#define GICC_INT_SPURIOUS		1023
 
 #define GIC_DIST_CTRL			0x000
 #define GIC_DIST_CTR			0x004
@@ -39,6 +42,18 @@
 #define GIC_DIST_SGI_PENDING_CLEAR	0xf10
 #define GIC_DIST_SGI_PENDING_SET	0xf20
 
+#define GICD_ENABLE			0x1
+#define GICD_DISABLE			0x0
+#define GICD_INT_ACTLOW_LVLTRIG		0x0
+#define GICD_INT_EN_CLR_X32		0xffffffff
+#define GICD_INT_EN_SET_SGI		0x0000ffff
+#define GICD_INT_EN_CLR_PPI		0xffff0000
+#define GICD_INT_DEF_PRI		0xa0
+#define GICD_INT_DEF_PRI_X4		((GICD_INT_DEF_PRI << 24) |\
+					(GICD_INT_DEF_PRI << 16) |\
+					(GICD_INT_DEF_PRI << 8) |\
+					GICD_INT_DEF_PRI)
+
 #define GICH_HCR			0x0
 #define GICH_VTR			0x4
 #define GICH_VMCR			0x8
-- 
cgit v1.2.3


From 3228950621d92f0f212378f95a6998ef3a1be0bb Mon Sep 17 00:00:00 2001
From: Feng Kan <fkan@apm.com>
Date: Wed, 30 Jul 2014 14:56:59 -0700
Subject: irqchip: gic: Preserve gic V2 bypass bits in cpu ctrl register

This change is made to preserve the GIC v2 bypass bits in the
GIC_CPU_CTRL register (also known as the GICC_CTLR register in spec).
This code will preserve all bits configured by the bootloader regarding
v2 bypass group bits. In the X-Gene platform, the bypass functionality
is not used and bypass bits should not be changed by the kernel gic
code as it could lead to incorrect behavior.

Signed-off-by: Feng Kan <fkan@apm.com>
Reviewed-by: Vinayak Kale <vkale@apm.com>
Reviewed-by: Anup Patel <apatel@apm.com>
Link: https://lkml.kernel.org/r/1406757419-18729-3-git-send-email-fkan@apm.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 drivers/irqchip/irq-gic.c       | 25 ++++++++++++++++++++++---
 include/linux/irqchip/arm-gic.h |  1 +
 2 files changed, 23 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 35847453cecb..2500f6ba29e1 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -353,6 +353,21 @@ static u8 gic_get_cpumask(struct gic_chip_data *gic)
 	return mask;
 }
 
+static void gic_cpu_if_up(void)
+{
+	void __iomem *cpu_base = gic_data_cpu_base(&gic_data[0]);
+	u32 bypass = 0;
+
+	/*
+	* Preserve bypass disable bits to be written back later
+	*/
+	bypass = readl(cpu_base + GIC_CPU_CTRL);
+	bypass &= GICC_DIS_BYPASS_MASK;
+
+	writel_relaxed(bypass | GICC_ENABLE, cpu_base + GIC_CPU_CTRL);
+}
+
+
 static void __init gic_dist_init(struct gic_chip_data *gic)
 {
 	unsigned int i;
@@ -401,13 +416,17 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 	gic_cpu_config(dist_base, NULL);
 
 	writel_relaxed(GICC_INT_PRI_THRESHOLD, base + GIC_CPU_PRIMASK);
-	writel_relaxed(GICC_ENABLE, base + GIC_CPU_CTRL);
+	gic_cpu_if_up();
 }
 
 void gic_cpu_if_down(void)
 {
 	void __iomem *cpu_base = gic_data_cpu_base(&gic_data[0]);
-	writel_relaxed(0, cpu_base + GIC_CPU_CTRL);
+	u32 val = 0;
+
+	val = readl(cpu_base + GIC_CPU_CTRL);
+	val &= ~GICC_ENABLE;
+	writel_relaxed(val, cpu_base + GIC_CPU_CTRL);
 }
 
 #ifdef CONFIG_CPU_PM
@@ -543,7 +562,7 @@ static void gic_cpu_restore(unsigned int gic_nr)
 					dist_base + GIC_DIST_PRI + i * 4);
 
 	writel_relaxed(GICC_INT_PRI_THRESHOLD, cpu_base + GIC_CPU_PRIMASK);
-	writel_relaxed(GICC_ENABLE, cpu_base + GIC_CPU_CTRL);
+	gic_cpu_if_up();
 }
 
 static int gic_notifier(struct notifier_block *self, unsigned long cmd,	void *v)
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 5cb9d41af5be..13eed92c7d24 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -25,6 +25,7 @@
 #define GICC_INT_PRI_THRESHOLD		0xf0
 #define GICC_IAR_INT_ID_MASK		0x3ff
 #define GICC_INT_SPURIOUS		1023
+#define GICC_DIS_BYPASS_MASK		0x1e0
 
 #define GIC_DIST_CTRL			0x000
 #define GIC_DIST_CTR			0x004
-- 
cgit v1.2.3


From 366047515c6eab2ff886bc28d1c2b0ad041d040a Mon Sep 17 00:00:00 2001
From: Lan Tianyu <tianyu.lan@intel.com>
Date: Fri, 15 Aug 2014 13:38:59 +0800
Subject: i2c: rework kernel config I2C_ACPI

Commit da3c6647(I2C/ACPI: Clean up I2C ACPI code and Add CONFIG_I2C_ACPI
config) adds a new kernel config I2C_ACPI and make I2C core built in
when the config is selected. This is wrong because distributions
etc generally compile I2C as a module and the commit broken that.
This patch is to rename I2C_ACPI to ACPI_I2C_OPREGION. New config
only controls ACPI I2C operation region code and depends on I2C=y.

Signed-off-by: Lan Tianyu <tianyu.lan@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
[wsa: removed unrelated change for Kconfig]
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/Kconfig    | 15 ++++++---------
 drivers/i2c/Makefile   |  2 +-
 drivers/i2c/i2c-acpi.c |  2 ++
 include/linux/i2c.h    | 12 ++++++++----
 4 files changed, 17 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/Kconfig b/drivers/i2c/Kconfig
index 3e3b680dc007..b51a402752c4 100644
--- a/drivers/i2c/Kconfig
+++ b/drivers/i2c/Kconfig
@@ -23,17 +23,14 @@ config I2C
 	  This I2C support can also be built as a module.  If so, the module
 	  will be called i2c-core.
 
-config I2C_ACPI
-	bool "I2C ACPI support"
-	select I2C
-	depends on ACPI
+config ACPI_I2C_OPREGION
+	bool "ACPI I2C Operation region support"
+	depends on I2C=y && ACPI
 	default y
 	help
-	  Say Y here if you want to enable ACPI I2C support. This includes support
-	  for automatic enumeration of I2C slave devices and support for ACPI I2C
-	  Operation Regions. Operation Regions allow firmware (BIOS) code to
-	  access I2C slave devices, such as smart batteries through an I2C host
-	  controller driver.
+	  Say Y here if you want to enable ACPI I2C operation region support.
+	  Operation Regions allow firmware (BIOS) code to access I2C slave devices,
+	  such as smart batteries through an I2C host controller driver.
 
 if I2C
 
diff --git a/drivers/i2c/Makefile b/drivers/i2c/Makefile
index a1f590cbb435..e0228b228256 100644
--- a/drivers/i2c/Makefile
+++ b/drivers/i2c/Makefile
@@ -3,7 +3,7 @@
 #
 
 i2ccore-y := i2c-core.o
-i2ccore-$(CONFIG_I2C_ACPI)	+= i2c-acpi.o
+i2ccore-$(CONFIG_ACPI)	 	+= i2c-acpi.o
 
 obj-$(CONFIG_I2C_BOARDINFO)	+= i2c-boardinfo.o
 obj-$(CONFIG_I2C)		+= i2ccore.o
diff --git a/drivers/i2c/i2c-acpi.c b/drivers/i2c/i2c-acpi.c
index e8b61967334b..0dbc18c15c43 100644
--- a/drivers/i2c/i2c-acpi.c
+++ b/drivers/i2c/i2c-acpi.c
@@ -126,6 +126,7 @@ void acpi_i2c_register_devices(struct i2c_adapter *adap)
 		dev_warn(&adap->dev, "failed to enumerate I2C slaves\n");
 }
 
+#ifdef CONFIG_ACPI_I2C_OPREGION
 static int acpi_gsb_i2c_read_bytes(struct i2c_client *client,
 		u8 cmd, u8 *data, u8 data_len)
 {
@@ -360,3 +361,4 @@ void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter)
 
 	acpi_bus_detach_private_data(handle);
 }
+#endif
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index ea507665896c..a95efeb53a8b 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -577,16 +577,20 @@ static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node
 }
 #endif /* CONFIG_OF */
 
-#ifdef CONFIG_I2C_ACPI
-int acpi_i2c_install_space_handler(struct i2c_adapter *adapter);
-void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter);
+#ifdef CONFIG_ACPI
 void acpi_i2c_register_devices(struct i2c_adapter *adap);
 #else
 static inline void acpi_i2c_register_devices(struct i2c_adapter *adap) { }
+#endif /* CONFIG_ACPI */
+
+#ifdef CONFIG_ACPI_I2C_OPREGION
+int acpi_i2c_install_space_handler(struct i2c_adapter *adapter);
+void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter);
+#else
 static inline void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter)
 { }
 static inline int acpi_i2c_install_space_handler(struct i2c_adapter *adapter)
 { return 0; }
-#endif
+#endif /* CONFIG_ACPI_I2C_OPREGION */
 
 #endif /* _LINUX_I2C_H */
-- 
cgit v1.2.3


From 81c7cfd1b22a0ee5e40efef72ec2cd17dbf12e6d Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 19 Aug 2014 15:51:18 +0200
Subject: ASoC: Move debugfs registration to the component level

The debugfs registration is mostly identical between platforms and CODECs. This
patches consolidates the two implementations at the component level.

Unfortunately there are still a couple of CODEC specific debugfs files that are
related to legacy ASoC IO that need to be registered. For this a new callback is
added to the component struct that will be initialized when a CODEC is
registered and will be used to register the CODEC specific files. Once there are
no drivers left using legacy IO this can be removed again.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h  |  20 ++++++---
 sound/soc/soc-core.c | 122 ++++++++++++++++++++++-----------------------------
 2 files changed, 67 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index be6ecae247b0..0ab8b1e4a5d2 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -728,9 +728,24 @@ struct snd_soc_component {
 
 	struct mutex io_mutex;
 
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debugfs_root;
+#endif
+
+	/*
+	* DO NOT use any of the fields below in drivers, they are temporary and
+	* are going to be removed again soon. If you use them in driver code the
+	* driver will be marked as BROKEN when these fields are removed.
+	*/
+
 	/* Don't use these, use snd_soc_component_get_dapm() */
 	struct snd_soc_dapm_context dapm;
 	struct snd_soc_dapm_context *dapm_ptr;
+
+#ifdef CONFIG_DEBUG_FS
+	void (*init_debugfs)(struct snd_soc_component *component);
+	const char *debugfs_prefix;
+#endif
 };
 
 /* SoC Audio Codec device */
@@ -766,7 +781,6 @@ struct snd_soc_codec {
 	struct snd_soc_dapm_context dapm;
 
 #ifdef CONFIG_DEBUG_FS
-	struct dentry *debugfs_codec_root;
 	struct dentry *debugfs_reg;
 #endif
 };
@@ -879,10 +893,6 @@ struct snd_soc_platform {
 	struct list_head list;
 
 	struct snd_soc_component component;
-
-#ifdef CONFIG_DEBUG_FS
-	struct dentry *debugfs_platform_root;
-#endif
 };
 
 struct snd_soc_dai_link {
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index d4bfd4a9076f..79371a77f324 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -270,79 +270,56 @@ static const struct file_operations codec_reg_fops = {
 	.llseek = default_llseek,
 };
 
-static struct dentry *soc_debugfs_create_dir(struct dentry *parent,
-	const char *fmt, ...)
+static void soc_init_component_debugfs(struct snd_soc_component *component)
 {
-	struct dentry *de;
-	va_list ap;
-	char *s;
+	if (component->debugfs_prefix) {
+		char *name;
 
-	va_start(ap, fmt);
-	s = kvasprintf(GFP_KERNEL, fmt, ap);
-	va_end(ap);
+		name = kasprintf(GFP_KERNEL, "%s:%s",
+			component->debugfs_prefix, component->name);
+		if (name) {
+			component->debugfs_root = debugfs_create_dir(name,
+				component->card->debugfs_card_root);
+			kfree(name);
+		}
+	} else {
+		component->debugfs_root = debugfs_create_dir(component->name,
+				component->card->debugfs_card_root);
+	}
 
-	if (!s)
-		return NULL;
+	if (!component->debugfs_root) {
+		dev_warn(component->dev,
+			"ASoC: Failed to create component debugfs directory\n");
+		return;
+	}
 
-	de = debugfs_create_dir(s, parent);
-	kfree(s);
+	snd_soc_dapm_debugfs_init(snd_soc_component_get_dapm(component),
+		component->debugfs_root);
 
-	return de;
+	if (component->init_debugfs)
+		component->init_debugfs(component);
 }
 
-static void soc_init_codec_debugfs(struct snd_soc_codec *codec)
+static void soc_cleanup_component_debugfs(struct snd_soc_component *component)
 {
-	struct dentry *debugfs_card_root = codec->component.card->debugfs_card_root;
+	debugfs_remove_recursive(component->debugfs_root);
+}
 
-	codec->debugfs_codec_root = soc_debugfs_create_dir(debugfs_card_root,
-						"codec:%s",
-						codec->component.name);
-	if (!codec->debugfs_codec_root) {
-		dev_warn(codec->dev,
-			"ASoC: Failed to create codec debugfs directory\n");
-		return;
-	}
+static void soc_init_codec_debugfs(struct snd_soc_component *component)
+{
+	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
 
-	debugfs_create_bool("cache_sync", 0444, codec->debugfs_codec_root,
+	debugfs_create_bool("cache_sync", 0444, codec->component.debugfs_root,
 			    &codec->cache_sync);
-	debugfs_create_bool("cache_only", 0444, codec->debugfs_codec_root,
+	debugfs_create_bool("cache_only", 0444, codec->component.debugfs_root,
 			    &codec->cache_only);
 
 	codec->debugfs_reg = debugfs_create_file("codec_reg", 0644,
-						 codec->debugfs_codec_root,
+						 codec->component.debugfs_root,
 						 codec, &codec_reg_fops);
 	if (!codec->debugfs_reg)
 		dev_warn(codec->dev,
 			"ASoC: Failed to create codec register debugfs file\n");
-
-	snd_soc_dapm_debugfs_init(&codec->dapm, codec->debugfs_codec_root);
-}
-
-static void soc_cleanup_codec_debugfs(struct snd_soc_codec *codec)
-{
-	debugfs_remove_recursive(codec->debugfs_codec_root);
-}
-
-static void soc_init_platform_debugfs(struct snd_soc_platform *platform)
-{
-	struct dentry *debugfs_card_root = platform->component.card->debugfs_card_root;
-
-	platform->debugfs_platform_root = soc_debugfs_create_dir(debugfs_card_root,
-						"platform:%s",
-						platform->component.name);
-	if (!platform->debugfs_platform_root) {
-		dev_warn(platform->dev,
-			"ASoC: Failed to create platform debugfs directory\n");
-		return;
-	}
-
-	snd_soc_dapm_debugfs_init(&platform->component.dapm,
-		platform->debugfs_platform_root);
-}
-
-static void soc_cleanup_platform_debugfs(struct snd_soc_platform *platform)
-{
-	debugfs_remove_recursive(platform->debugfs_platform_root);
 }
 
 static ssize_t codec_list_read_file(struct file *file, char __user *user_buf,
@@ -474,19 +451,15 @@ static void soc_cleanup_card_debugfs(struct snd_soc_card *card)
 
 #else
 
-static inline void soc_init_codec_debugfs(struct snd_soc_codec *codec)
-{
-}
+#define soc_init_codec_debugfs NULL
 
-static inline void soc_cleanup_codec_debugfs(struct snd_soc_codec *codec)
+static inline void soc_init_component_debugfs(
+	struct snd_soc_component *component)
 {
 }
 
-static inline void soc_init_platform_debugfs(struct snd_soc_platform *platform)
-{
-}
-
-static inline void soc_cleanup_platform_debugfs(struct snd_soc_platform *platform)
+static inline void soc_cleanup_component_debugfs(
+	struct snd_soc_component *component)
 {
 }
 
@@ -1026,7 +999,7 @@ static int soc_remove_platform(struct snd_soc_platform *platform)
 	/* Make sure all DAPM widgets are freed */
 	snd_soc_dapm_free(&platform->component.dapm);
 
-	soc_cleanup_platform_debugfs(platform);
+	soc_cleanup_component_debugfs(&platform->component);
 	platform->probed = 0;
 	module_put(platform->dev->driver->owner);
 
@@ -1046,7 +1019,7 @@ static void soc_remove_codec(struct snd_soc_codec *codec)
 	/* Make sure all DAPM widgets are freed */
 	snd_soc_dapm_free(&codec->dapm);
 
-	soc_cleanup_codec_debugfs(codec);
+	soc_cleanup_component_debugfs(&codec->component);
 	codec->probed = 0;
 	list_del(&codec->card_list);
 	module_put(codec->dev->driver->owner);
@@ -1187,7 +1160,7 @@ static int soc_probe_codec(struct snd_soc_card *card,
 	if (!try_module_get(codec->dev->driver->owner))
 		return -ENODEV;
 
-	soc_init_codec_debugfs(codec);
+	soc_init_component_debugfs(&codec->component);
 
 	if (driver->dapm_widgets) {
 		ret = snd_soc_dapm_new_controls(&codec->dapm,
@@ -1242,7 +1215,7 @@ static int soc_probe_codec(struct snd_soc_card *card,
 	return 0;
 
 err_probe:
-	soc_cleanup_codec_debugfs(codec);
+	soc_cleanup_component_debugfs(&codec->component);
 	module_put(codec->dev->driver->owner);
 
 	return ret;
@@ -1262,7 +1235,7 @@ static int soc_probe_platform(struct snd_soc_card *card,
 	if (!try_module_get(platform->dev->driver->owner))
 		return -ENODEV;
 
-	soc_init_platform_debugfs(platform);
+	soc_init_component_debugfs(&platform->component);
 
 	if (driver->dapm_widgets)
 		snd_soc_dapm_new_controls(&platform->component.dapm,
@@ -1302,7 +1275,7 @@ static int soc_probe_platform(struct snd_soc_card *card,
 	return 0;
 
 err_probe:
-	soc_cleanup_platform_debugfs(platform);
+	soc_cleanup_component_debugfs(&platform->component);
 	module_put(platform->dev->driver->owner);
 
 	return ret;
@@ -4266,6 +4239,10 @@ int snd_soc_add_platform(struct device *dev, struct snd_soc_platform *platform,
 	if (platform_drv->read)
 		platform->component.read = snd_soc_platform_drv_read;
 
+#ifdef CONFIG_DEBUG_FS
+	platform->component.debugfs_prefix = "platform";
+#endif
+
 	mutex_lock(&client_mutex);
 	snd_soc_component_add_unlocked(&platform->component);
 	list_add(&platform->list, &platform_list);
@@ -4455,6 +4432,11 @@ int snd_soc_register_codec(struct device *dev,
 	codec->component.val_bytes = codec_drv->reg_word_size;
 	mutex_init(&codec->mutex);
 
+#ifdef CONFIG_DEBUG_FS
+	codec->component.init_debugfs = soc_init_codec_debugfs;
+	codec->component.debugfs_prefix = "codec";
+#endif
+
 	if (!codec->component.write) {
 		if (codec_drv->get_regmap)
 			regmap = codec_drv->get_regmap(dev);
-- 
cgit v1.2.3


From f1d45cc3ae96a6173129b2c164c216272faa5fc0 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 19 Aug 2014 15:51:19 +0200
Subject: ASoC: Consolidate platform and CODEC probe/remove

The platform and CODEC probe and remove code is now largely identical. This
patch consolidates it at the component level.

The resulting code is slightly larger due to all the boiler plate code setting
up the indirection for the table based control and DAPM registration.  Once all
drivers have been update to no longer use the snd_soc_codec_driver and
snd_soc_platform_driver specific fields for this the indirection can be removed
again.

This patch contains two noteworthy hacks that are only meant to be temporary to
be able to update drivers and the core in separate incremental patches.

The first hack is related to that some DPCM platforms expect that the DAPM
widgets for the DAIs of a snd_soc_component are created in the DAPM context of
the snd_soc_platform that has the same parent device. For handling this the
steal_sibling_dai_widgets attribute is introduced. It gets set for
snd_soc_platforms that register DAPM elements. When creating the DAI widgets for
a component this flag is checked and if it is found on one of the siblings the
component will not create any DAI widgets in its own DAPM context. If the
attribute is set on a platform it will look for siblings components and create
DAI widgets for them in its own context. The fix for this will be to update
the offending drivers to only register a single component rather than two.

The second hack deals with the fact that the ASoC card suspend and resume code
still needs a list of CODECs that have been registered for the card. To handle
this the generic probe and remove path have a check to see if the component is
CODEC and if yes add/remove it to the card's CODEC list. While it is possible to
clean up the suspend/resume code to not need the CODEC list anymore this is a
bit of a chicken and egg problem since it will become easier to clean up the
suspend/resume code once there is a unified component layer.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h                   |  27 ++-
 sound/soc/soc-core.c                  | 335 ++++++++++++++++++----------------
 sound/soc/soc-generic-dmaengine-pcm.c |   4 +-
 3 files changed, 194 insertions(+), 172 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 0ab8b1e4a5d2..22543acfae4b 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -697,6 +697,10 @@ struct snd_soc_component_driver {
 	void (*seq_notifier)(struct snd_soc_component *, enum snd_soc_dapm_type,
 		int subseq);
 	int (*stream_event)(struct snd_soc_component *, int event);
+
+	/* probe ordering - for components with runtime dependencies */
+	int probe_order;
+	int remove_order;
 };
 
 struct snd_soc_component {
@@ -710,6 +714,7 @@ struct snd_soc_component {
 
 	unsigned int ignore_pmdown_time:1; /* pmdown_time is ignored at stop */
 	unsigned int registered_as_component:1;
+	unsigned int probed:1;
 
 	struct list_head list;
 
@@ -742,6 +747,18 @@ struct snd_soc_component {
 	struct snd_soc_dapm_context dapm;
 	struct snd_soc_dapm_context *dapm_ptr;
 
+	const struct snd_kcontrol_new *controls;
+	unsigned int num_controls;
+	const struct snd_soc_dapm_widget *dapm_widgets;
+	unsigned int num_dapm_widgets;
+	const struct snd_soc_dapm_route *dapm_routes;
+	unsigned int num_dapm_routes;
+	bool steal_sibling_dai_widgets;
+	struct snd_soc_codec *codec;
+
+	int (*probe)(struct snd_soc_component *);
+	void (*remove)(struct snd_soc_component *);
+
 #ifdef CONFIG_DEBUG_FS
 	void (*init_debugfs)(struct snd_soc_component *component);
 	const char *debugfs_prefix;
@@ -761,7 +778,6 @@ struct snd_soc_codec {
 	struct snd_ac97 *ac97;  /* for ad-hoc ac97 devices */
 	unsigned int cache_bypass:1; /* Suppress access to the cache */
 	unsigned int suspended:1; /* Codec is in suspend PM state */
-	unsigned int probed:1; /* Codec has been probed */
 	unsigned int ac97_registered:1; /* Codec has been AC97 registered */
 	unsigned int ac97_created:1; /* Codec has been created by SoC */
 	unsigned int cache_init:1; /* codec cache has been initialized */
@@ -827,10 +843,6 @@ struct snd_soc_codec_driver {
 			     enum snd_soc_dapm_type, int);
 
 	bool ignore_pmdown_time;  /* Doesn't benefit from pmdown delay */
-
-	/* probe ordering - for components with runtime dependencies */
-	int probe_order;
-	int remove_order;
 };
 
 /* SoC platform interface */
@@ -867,10 +879,6 @@ struct snd_soc_platform_driver {
 	/* platform stream compress ops */
 	const struct snd_compr_ops *compr_ops;
 
-	/* probe ordering - for components with runtime dependencies */
-	int probe_order;
-	int remove_order;
-
 	/* platform IO - used for platform DAPM */
 	unsigned int (*read)(struct snd_soc_platform *, unsigned int);
 	int (*write)(struct snd_soc_platform *, unsigned int, unsigned int);
@@ -888,7 +896,6 @@ struct snd_soc_platform {
 	const struct snd_soc_platform_driver *driver;
 
 	unsigned int suspended:1; /* platform is suspended */
-	unsigned int probed:1;
 
 	struct list_head list;
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 79371a77f324..b833cc6fd86d 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -985,44 +985,20 @@ static int soc_bind_dai_link(struct snd_soc_card *card, int num)
 	return 0;
 }
 
-static int soc_remove_platform(struct snd_soc_platform *platform)
+static void soc_remove_component(struct snd_soc_component *component)
 {
-	int ret;
-
-	if (platform->driver->remove) {
-		ret = platform->driver->remove(platform);
-		if (ret < 0)
-			dev_err(platform->dev, "ASoC: failed to remove %d\n",
-				ret);
-	}
-
-	/* Make sure all DAPM widgets are freed */
-	snd_soc_dapm_free(&platform->component.dapm);
-
-	soc_cleanup_component_debugfs(&platform->component);
-	platform->probed = 0;
-	module_put(platform->dev->driver->owner);
-
-	return 0;
-}
-
-static void soc_remove_codec(struct snd_soc_codec *codec)
-{
-	int err;
+	/* This is a HACK and will be removed soon */
+	if (component->codec)
+		list_del(&component->codec->card_list);
 
-	if (codec->driver->remove) {
-		err = codec->driver->remove(codec);
-		if (err < 0)
-			dev_err(codec->dev, "ASoC: failed to remove %d\n", err);
-	}
+	if (component->remove)
+		component->remove(component);
 
-	/* Make sure all DAPM widgets are freed */
-	snd_soc_dapm_free(&codec->dapm);
+	snd_soc_dapm_free(snd_soc_component_get_dapm(component));
 
-	soc_cleanup_component_debugfs(&codec->component);
-	codec->probed = 0;
-	list_del(&codec->card_list);
-	module_put(codec->dev->driver->owner);
+	soc_cleanup_component_debugfs(component);
+	component->probed = 0;
+	module_put(component->dev->driver->owner);
 }
 
 static void soc_remove_codec_dai(struct snd_soc_dai *codec_dai, int order)
@@ -1086,25 +1062,24 @@ static void soc_remove_link_components(struct snd_soc_card *card, int num,
 	int i;
 
 	/* remove the platform */
-	if (platform && platform->probed &&
-	    platform->driver->remove_order == order) {
-		soc_remove_platform(platform);
-	}
+	if (platform && platform->component.probed &&
+	    platform->component.driver->remove_order == order)
+		soc_remove_component(&platform->component);
 
 	/* remove the CODEC-side CODEC */
 	for (i = 0; i < rtd->num_codecs; i++) {
 		codec = rtd->codec_dais[i]->codec;
-		if (codec && codec->probed &&
-		    codec->driver->remove_order == order)
-			soc_remove_codec(codec);
+		if (codec && codec->component.probed &&
+		    codec->component.driver->remove_order == order)
+			soc_remove_component(&codec->component);
 	}
 
 	/* remove any CPU-side CODEC */
 	if (cpu_dai) {
 		codec = cpu_dai->codec;
-		if (codec && codec->probed &&
-		    codec->driver->remove_order == order)
-			soc_remove_codec(codec);
+		if (codec && codec->component.probed &&
+		    codec->component.driver->remove_order == order)
+			soc_remove_component(&codec->component);
 	}
 }
 
@@ -1146,137 +1121,108 @@ static void soc_set_name_prefix(struct snd_soc_card *card,
 	}
 }
 
-static int soc_probe_codec(struct snd_soc_card *card,
-			   struct snd_soc_codec *codec)
+static int soc_probe_component(struct snd_soc_card *card,
+	struct snd_soc_component *component)
 {
-	int ret = 0;
-	const struct snd_soc_codec_driver *driver = codec->driver;
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
+	struct snd_soc_component *dai_component, *component2;
 	struct snd_soc_dai *dai;
+	int ret;
 
-	codec->component.card = card;
-	codec->dapm.card = card;
-	soc_set_name_prefix(card, &codec->component);
+	component->card = card;
+	dapm->card = card;
+	soc_set_name_prefix(card, component);
 
-	if (!try_module_get(codec->dev->driver->owner))
+	if (!try_module_get(component->dev->driver->owner))
 		return -ENODEV;
 
-	soc_init_component_debugfs(&codec->component);
+	soc_init_component_debugfs(component);
 
-	if (driver->dapm_widgets) {
-		ret = snd_soc_dapm_new_controls(&codec->dapm,
-						driver->dapm_widgets,
-					 	driver->num_dapm_widgets);
+	if (component->dapm_widgets) {
+		ret = snd_soc_dapm_new_controls(dapm, component->dapm_widgets,
+			component->num_dapm_widgets);
 
 		if (ret != 0) {
-			dev_err(codec->dev,
+			dev_err(component->dev,
 				"Failed to create new controls %d\n", ret);
 			goto err_probe;
 		}
 	}
 
-	/* Create DAPM widgets for each DAI stream */
-	list_for_each_entry(dai, &codec->component.dai_list, list) {
-		ret = snd_soc_dapm_new_dai_widgets(&codec->dapm, dai);
+	/*
+	 * This is rather ugly, but certain platforms expect that the DAPM
+	 * widgets for the DAIs for components with the same parent device are
+	 * created in the platforms DAPM context. Until that is fixed we need to
+	 * keep this.
+	 */
+	if (component->steal_sibling_dai_widgets) {
+		dai_component = NULL;
+		list_for_each_entry(component2, &component_list, list) {
+			if (component == component2)
+				continue;
 
-		if (ret != 0) {
-			dev_err(codec->dev,
-				"Failed to create DAI widgets %d\n", ret);
-			goto err_probe;
+			if (component2->dev == component->dev &&
+			    !list_empty(&component2->dai_list)) {
+				dai_component = component2;
+				break;
+			}
 		}
-	}
-
-	codec->dapm.idle_bias_off = driver->idle_bias_off;
-
-	if (driver->probe) {
-		ret = driver->probe(codec);
-		if (ret < 0) {
-			dev_err(codec->dev,
-				"ASoC: failed to probe CODEC %d\n", ret);
-			goto err_probe;
+	} else {
+		dai_component = component;
+		list_for_each_entry(component2, &component_list, list) {
+			if (component2->dev == component->dev &&
+			    component2->steal_sibling_dai_widgets) {
+				dai_component = NULL;
+				break;
+			}
 		}
-		WARN(codec->dapm.idle_bias_off &&
-			codec->dapm.bias_level != SND_SOC_BIAS_OFF,
-			"codec %s can not start from non-off bias with idle_bias_off==1\n",
-			codec->component.name);
 	}
 
-	if (driver->controls)
-		snd_soc_add_codec_controls(codec, driver->controls,
-				     driver->num_controls);
-	if (driver->dapm_routes)
-		snd_soc_dapm_add_routes(&codec->dapm, driver->dapm_routes,
-					driver->num_dapm_routes);
-
-	/* mark codec as probed and add to card codec list */
-	codec->probed = 1;
-	list_add(&codec->card_list, &card->codec_dev_list);
-	list_add(&codec->dapm.list, &card->dapm_list);
-
-	return 0;
-
-err_probe:
-	soc_cleanup_component_debugfs(&codec->component);
-	module_put(codec->dev->driver->owner);
-
-	return ret;
-}
-
-static int soc_probe_platform(struct snd_soc_card *card,
-			   struct snd_soc_platform *platform)
-{
-	int ret = 0;
-	const struct snd_soc_platform_driver *driver = platform->driver;
-	struct snd_soc_component *component;
-	struct snd_soc_dai *dai;
-
-	platform->component.card = card;
-	platform->component.dapm.card = card;
-
-	if (!try_module_get(platform->dev->driver->owner))
-		return -ENODEV;
-
-	soc_init_component_debugfs(&platform->component);
-
-	if (driver->dapm_widgets)
-		snd_soc_dapm_new_controls(&platform->component.dapm,
-			driver->dapm_widgets, driver->num_dapm_widgets);
-
-	/* Create DAPM widgets for each DAI stream */
-	list_for_each_entry(component, &component_list, list) {
-		if (component->dev != platform->dev)
-			continue;
-		list_for_each_entry(dai, &component->dai_list, list)
-			snd_soc_dapm_new_dai_widgets(&platform->component.dapm,
-				dai);
+	if (dai_component) {
+		list_for_each_entry(dai, &dai_component->dai_list, list) {
+			snd_soc_dapm_new_dai_widgets(dapm, dai);
+			if (ret != 0) {
+				dev_err(component->dev,
+					"Failed to create DAI widgets %d\n",
+					ret);
+				goto err_probe;
+			}
+		}
 	}
 
-	platform->component.dapm.idle_bias_off = 1;
-
-	if (driver->probe) {
-		ret = driver->probe(platform);
+	if (component->probe) {
+		ret = component->probe(component);
 		if (ret < 0) {
-			dev_err(platform->dev,
-				"ASoC: failed to probe platform %d\n", ret);
+			dev_err(component->dev,
+				"ASoC: failed to probe component %d\n", ret);
 			goto err_probe;
 		}
+
+		WARN(dapm->idle_bias_off &&
+			dapm->bias_level != SND_SOC_BIAS_OFF,
+			"codec %s can not start from non-off bias with idle_bias_off==1\n",
+			component->name);
 	}
 
-	if (driver->controls)
-		snd_soc_add_platform_controls(platform, driver->controls,
-				     driver->num_controls);
-	if (driver->dapm_routes)
-		snd_soc_dapm_add_routes(&platform->component.dapm,
-			driver->dapm_routes, driver->num_dapm_routes);
+	if (component->controls)
+		snd_soc_add_component_controls(component, component->controls,
+				     component->num_controls);
+	if (component->dapm_routes)
+		snd_soc_dapm_add_routes(dapm, component->dapm_routes,
+					component->num_dapm_routes);
 
-	/* mark platform as probed and add to card platform list */
-	platform->probed = 1;
-	list_add(&platform->component.dapm.list, &card->dapm_list);
+	component->probed = 1;
+	list_add(&dapm->list, &card->dapm_list);
+
+	/* This is a HACK and will be removed soon */
+	if (component->codec)
+		list_add(&component->codec->card_list, &card->codec_dev_list);
 
 	return 0;
 
 err_probe:
-	soc_cleanup_component_debugfs(&platform->component);
-	module_put(platform->dev->driver->owner);
+	soc_cleanup_component_debugfs(component);
+	module_put(component->dev->driver->owner);
 
 	return ret;
 }
@@ -1334,33 +1280,36 @@ static int soc_probe_link_components(struct snd_soc_card *card, int num,
 				     int order)
 {
 	struct snd_soc_pcm_runtime *rtd = &card->rtd[num];
-	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_platform *platform = rtd->platform;
+	struct snd_soc_component *component;
 	int i, ret;
 
 	/* probe the CPU-side component, if it is a CODEC */
-	if (cpu_dai->codec &&
-	    !cpu_dai->codec->probed &&
-	    cpu_dai->codec->driver->probe_order == order) {
-		ret = soc_probe_codec(card, cpu_dai->codec);
-		if (ret < 0)
-			return ret;
+	if (rtd->cpu_dai->codec) {
+		component = &rtd->cpu_dai->codec->component;
+		if (!component->probed &&
+		    component->driver->probe_order == order) {
+			ret = soc_probe_component(card, component);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
 	/* probe the CODEC-side components */
 	for (i = 0; i < rtd->num_codecs; i++) {
-		if (!rtd->codec_dais[i]->codec->probed &&
-		    rtd->codec_dais[i]->codec->driver->probe_order == order) {
-			ret = soc_probe_codec(card, rtd->codec_dais[i]->codec);
+		component = &rtd->codec_dais[i]->codec->component;
+		if (!component->probed &&
+		    component->driver->probe_order == order) {
+			ret = soc_probe_component(card, component);
 			if (ret < 0)
 				return ret;
 		}
 	}
 
 	/* probe the platform */
-	if (!platform->probed &&
-	    platform->driver->probe_order == order) {
-		ret = soc_probe_platform(card, platform);
+	if (!platform->component.probed &&
+	    platform->component.driver->probe_order == order) {
+		ret = soc_probe_component(card, &platform->component);
 		if (ret < 0)
 			return ret;
 	}
@@ -1647,12 +1596,12 @@ static int soc_probe_aux_dev(struct snd_soc_card *card, int num)
 	struct snd_soc_aux_dev *aux_dev = &card->aux_dev[num];
 	int ret;
 
-	if (rtd->codec->probed) {
+	if (rtd->codec->component.probed) {
 		dev_err(rtd->codec->dev, "ASoC: codec already probed\n");
 		return -EBUSY;
 	}
 
-	ret = soc_probe_codec(card, rtd->codec);
+	ret = soc_probe_component(card, &rtd->codec->component);
 	if (ret < 0)
 		return ret;
 
@@ -1681,8 +1630,8 @@ static void soc_remove_aux_dev(struct snd_soc_card *card, int num)
 		rtd->dev_registered = 0;
 	}
 
-	if (codec && codec->probed)
-		soc_remove_codec(codec);
+	if (codec && codec->component.probed)
+		soc_remove_component(&codec->component);
 }
 
 static int snd_soc_init_codec_cache(struct snd_soc_codec *codec)
@@ -4198,6 +4147,20 @@ found:
 }
 EXPORT_SYMBOL_GPL(snd_soc_unregister_component);
 
+static int snd_soc_platform_drv_probe(struct snd_soc_component *component)
+{
+	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
+
+	return platform->driver->probe(platform);
+}
+
+static void snd_soc_platform_drv_remove(struct snd_soc_component *component)
+{
+	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
+
+	platform->driver->remove(platform);
+}
+
 static int snd_soc_platform_drv_write(struct snd_soc_component *component,
 	unsigned int reg, unsigned int val)
 {
@@ -4234,6 +4197,24 @@ int snd_soc_add_platform(struct device *dev, struct snd_soc_platform *platform,
 
 	platform->dev = dev;
 	platform->driver = platform_drv;
+	if (platform_drv->controls) {
+		platform->component.controls = platform_drv->controls;
+		platform->component.num_controls = platform_drv->num_controls;
+	}
+	if (platform_drv->dapm_widgets) {
+		platform->component.dapm_widgets = platform_drv->dapm_widgets;
+		platform->component.num_dapm_widgets = platform_drv->num_dapm_widgets;
+		platform->component.steal_sibling_dai_widgets = true;
+	}
+	if (platform_drv->dapm_routes) {
+		platform->component.dapm_routes = platform_drv->dapm_routes;
+		platform->component.num_dapm_routes = platform_drv->num_dapm_routes;
+	}
+
+	if (platform_drv->probe)
+		platform->component.probe = snd_soc_platform_drv_probe;
+	if (platform_drv->remove)
+		platform->component.remove = snd_soc_platform_drv_remove;
 	if (platform_drv->write)
 		platform->component.write = snd_soc_platform_drv_write;
 	if (platform_drv->read)
@@ -4363,6 +4344,20 @@ static void fixup_codec_formats(struct snd_soc_pcm_stream *stream)
 			stream->formats |= codec_format_map[i];
 }
 
+static int snd_soc_codec_drv_probe(struct snd_soc_component *component)
+{
+	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
+
+	return codec->driver->probe(codec);
+}
+
+static void snd_soc_codec_drv_remove(struct snd_soc_component *component)
+{
+	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
+
+	codec->driver->remove(codec);
+}
+
 static int snd_soc_codec_drv_write(struct snd_soc_component *component,
 	unsigned int reg, unsigned int val)
 {
@@ -4411,12 +4406,30 @@ int snd_soc_register_codec(struct device *dev,
 		return -ENOMEM;
 
 	codec->component.dapm_ptr = &codec->dapm;
+	codec->component.codec = codec;
 
 	ret = snd_soc_component_initialize(&codec->component,
 			&codec_drv->component_driver, dev);
 	if (ret)
 		goto err_free;
 
+	if (codec_drv->controls) {
+		codec->component.controls = codec_drv->controls;
+		codec->component.num_controls = codec_drv->num_controls;
+	}
+	if (codec_drv->dapm_widgets) {
+		codec->component.dapm_widgets = codec_drv->dapm_widgets;
+		codec->component.num_dapm_widgets = codec_drv->num_dapm_widgets;
+	}
+	if (codec_drv->dapm_routes) {
+		codec->component.dapm_routes = codec_drv->dapm_routes;
+		codec->component.num_dapm_routes = codec_drv->num_dapm_routes;
+	}
+
+	if (codec_drv->probe)
+		codec->component.probe = snd_soc_codec_drv_probe;
+	if (codec_drv->remove)
+		codec->component.remove = snd_soc_codec_drv_remove;
 	if (codec_drv->write)
 		codec->component.write = snd_soc_codec_drv_write;
 	if (codec_drv->read)
diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index 6307f85e871b..b329b84bc5af 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -336,10 +336,12 @@ static const struct snd_pcm_ops dmaengine_pcm_ops = {
 };
 
 static const struct snd_soc_platform_driver dmaengine_pcm_platform = {
+	.component_driver = {
+		.probe_order = SND_SOC_COMP_ORDER_LATE,
+	},
 	.ops		= &dmaengine_pcm_ops,
 	.pcm_new	= dmaengine_pcm_new,
 	.pcm_free	= dmaengine_pcm_free,
-	.probe_order	= SND_SOC_COMP_ORDER_LATE,
 };
 
 static const char * const dmaengine_pcm_dma_channel_names[] = {
-- 
cgit v1.2.3


From 61aca5646b736a794d40de29a197144db3f0c5ba Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 19 Aug 2014 15:51:21 +0200
Subject: ASoC: Add component level probe/remove support

Now that we have a unified probe and remove path make sure to call them for all
components. soc_{probe,remove}_component are responsible for setting up the DAPM
context for the component, initialize the component prefix, manage the debugfs
entries as well as do the registration of table based controls and DAPM
elements. They also call the component drivers probe and remove callbacks. This
patch makes these things available for generic snd_soc_component drivers rather
than only having them for snd_soc_codec and snd_soc_platform drivers.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h  | 11 +++++++++++
 sound/soc/soc-core.c | 42 ++++++++++++++++++++++++------------------
 2 files changed, 35 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 22543acfae4b..4a223a895f00 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -690,6 +690,17 @@ struct snd_soc_compr_ops {
 struct snd_soc_component_driver {
 	const char *name;
 
+	/* Default control and setup, added after probe() is run */
+	const struct snd_kcontrol_new *controls;
+	unsigned int num_controls;
+	const struct snd_soc_dapm_widget *dapm_widgets;
+	unsigned int num_dapm_widgets;
+	const struct snd_soc_dapm_route *dapm_routes;
+	unsigned int num_dapm_routes;
+
+	int (*probe)(struct snd_soc_component *);
+	void (*remove)(struct snd_soc_component *);
+
 	/* DT */
 	int (*of_xlate_dai_name)(struct snd_soc_component *component,
 				 struct of_phandle_args *args,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 1c705c28389c..08fd85e8c751 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1058,7 +1058,7 @@ static void soc_remove_link_components(struct snd_soc_card *card, int num,
 	struct snd_soc_pcm_runtime *rtd = &card->rtd[num];
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_platform *platform = rtd->platform;
-	struct snd_soc_codec *codec;
+	struct snd_soc_component *component;
 	int i;
 
 	/* remove the platform */
@@ -1068,18 +1068,17 @@ static void soc_remove_link_components(struct snd_soc_card *card, int num,
 
 	/* remove the CODEC-side CODEC */
 	for (i = 0; i < rtd->num_codecs; i++) {
-		codec = rtd->codec_dais[i]->codec;
-		if (codec && codec->component.probed &&
-		    codec->component.driver->remove_order == order)
-			soc_remove_component(&codec->component);
+		component = rtd->codec_dais[i]->component;
+		if (component->probed &&
+		    component->driver->remove_order == order)
+			soc_remove_component(component);
 	}
 
 	/* remove any CPU-side CODEC */
 	if (cpu_dai) {
-		codec = cpu_dai->codec;
-		if (codec && codec->component.probed &&
-		    codec->component.driver->remove_order == order)
-			soc_remove_component(&codec->component);
+		if (cpu_dai->component->probed &&
+		    cpu_dai->component->driver->remove_order == order)
+			soc_remove_component(cpu_dai->component);
 	}
 }
 
@@ -1289,19 +1288,17 @@ static int soc_probe_link_components(struct snd_soc_card *card, int num,
 	int i, ret;
 
 	/* probe the CPU-side component, if it is a CODEC */
-	if (rtd->cpu_dai->codec) {
-		component = &rtd->cpu_dai->codec->component;
-		if (!component->probed &&
-		    component->driver->probe_order == order) {
-			ret = soc_probe_component(card, component);
-			if (ret < 0)
-				return ret;
-		}
+	component = rtd->cpu_dai->component;
+	if (!component->probed &&
+	    component->driver->probe_order == order) {
+		ret = soc_probe_component(card, component);
+		if (ret < 0)
+			return ret;
 	}
 
 	/* probe the CODEC-side components */
 	for (i = 0; i < rtd->num_codecs; i++) {
-		component = &rtd->codec_dais[i]->codec->component;
+		component = rtd->codec_dais[i]->component;
 		if (!component->probed &&
 		    component->driver->probe_order == order) {
 			ret = soc_probe_component(card, component);
@@ -4042,6 +4039,8 @@ static int snd_soc_component_initialize(struct snd_soc_component *component,
 
 	component->dev = dev;
 	component->driver = driver;
+	component->probe = component->driver->probe;
+	component->remove = component->driver->remove;
 
 	if (!component->dapm_ptr)
 		component->dapm_ptr = &component->dapm;
@@ -4055,6 +4054,13 @@ static int snd_soc_component_initialize(struct snd_soc_component *component,
 	if (driver->stream_event)
 		dapm->stream_event = snd_soc_component_stream_event;
 
+	component->controls = driver->controls;
+	component->num_controls = driver->num_controls;
+	component->dapm_widgets = driver->dapm_widgets;
+	component->num_dapm_widgets = driver->num_dapm_widgets;
+	component->dapm_routes = driver->dapm_routes;
+	component->num_dapm_routes = driver->num_dapm_routes;
+
 	INIT_LIST_HEAD(&component->dai_list);
 	mutex_init(&component->io_mutex);
 
-- 
cgit v1.2.3


From 65d9361f0cb50a20641802ee3075145d72e4409c Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 19 Aug 2014 15:51:22 +0200
Subject: ASoC: Move AUX dev support to the component level

This patch makes it possible to register arbitrary components as a AUX dev
for a card. This was previously only possible for CODEC components. With
componentization having made it possible for components to have DAPM contexts
and controls there is no reason why AUX devs should be artificially limited to
snd_soc_codec devices.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h  |  1 +
 sound/soc/soc-core.c | 48 ++++++++++++++++++++++++++++++++++++------------
 2 files changed, 37 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 4a223a895f00..fbc2ad840244 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1140,6 +1140,7 @@ struct snd_soc_pcm_runtime {
 	struct snd_soc_platform *platform;
 	struct snd_soc_dai *codec_dai;
 	struct snd_soc_dai *cpu_dai;
+	struct snd_soc_component *component; /* Only valid for AUX dev rtds */
 
 	struct snd_soc_dai **codec_dais;
 	unsigned int num_codecs;
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 08fd85e8c751..08c04f4c7e62 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -860,6 +860,23 @@ EXPORT_SYMBOL_GPL(snd_soc_resume);
 static const struct snd_soc_dai_ops null_dai_ops = {
 };
 
+static struct snd_soc_component *soc_find_component(
+	const struct device_node *of_node, const char *name)
+{
+	struct snd_soc_component *component;
+
+	list_for_each_entry(component, &component_list, list) {
+		if (of_node) {
+			if (component->dev->of_node == of_node)
+				return component;
+		} else if (strcmp(component->name, name) == 0) {
+			return component;
+		}
+	}
+
+	return NULL;
+}
+
 static struct snd_soc_codec *soc_find_codec(
 					const struct device_node *codec_of_node,
 					const char *codec_name)
@@ -1577,17 +1594,24 @@ static int soc_bind_aux_dev(struct snd_soc_card *card, int num)
 {
 	struct snd_soc_pcm_runtime *rtd = &card->rtd_aux[num];
 	struct snd_soc_aux_dev *aux_dev = &card->aux_dev[num];
-	const char *codecname = aux_dev->codec_name;
+	const char *name = aux_dev->codec_name;
 
-	rtd->codec = soc_find_codec(aux_dev->codec_of_node, codecname);
-	if (!rtd->codec) {
+	rtd->component = soc_find_component(aux_dev->codec_of_node, name);
+	if (!rtd->component) {
 		if (aux_dev->codec_of_node)
-			codecname = of_node_full_name(aux_dev->codec_of_node);
+			name = of_node_full_name(aux_dev->codec_of_node);
 
-		dev_err(card->dev, "ASoC: %s not registered\n", codecname);
+		dev_err(card->dev, "ASoC: %s not registered\n", name);
 		return -EPROBE_DEFER;
 	}
 
+	/*
+	 * Some places still reference rtd->codec, so we have to keep that
+	 * initialized if the component is a CODEC. Once all those references
+	 * have been removed, this code can be removed as well.
+	 */
+	 rtd->codec = rtd->component->codec;
+
 	return 0;
 }
 
@@ -1597,18 +1621,18 @@ static int soc_probe_aux_dev(struct snd_soc_card *card, int num)
 	struct snd_soc_aux_dev *aux_dev = &card->aux_dev[num];
 	int ret;
 
-	if (rtd->codec->component.probed) {
-		dev_err(rtd->codec->dev, "ASoC: codec already probed\n");
+	if (rtd->component->probed) {
+		dev_err(rtd->dev, "ASoC: codec already probed\n");
 		return -EBUSY;
 	}
 
-	ret = soc_probe_component(card, &rtd->codec->component);
+	ret = soc_probe_component(card, rtd->component);
 	if (ret < 0)
 		return ret;
 
 	/* do machine specific initialization */
 	if (aux_dev->init) {
-		ret = aux_dev->init(&rtd->codec->dapm);
+		ret = aux_dev->init(snd_soc_component_get_dapm(rtd->component));
 		if (ret < 0) {
 			dev_err(card->dev, "ASoC: failed to init %s: %d\n",
 				aux_dev->name, ret);
@@ -1622,7 +1646,7 @@ static int soc_probe_aux_dev(struct snd_soc_card *card, int num)
 static void soc_remove_aux_dev(struct snd_soc_card *card, int num)
 {
 	struct snd_soc_pcm_runtime *rtd = &card->rtd_aux[num];
-	struct snd_soc_codec *codec = rtd->codec;
+	struct snd_soc_component *component = rtd->component;
 
 	/* unregister the rtd device */
 	if (rtd->dev_registered) {
@@ -1631,8 +1655,8 @@ static void soc_remove_aux_dev(struct snd_soc_card *card, int num)
 		rtd->dev_registered = 0;
 	}
 
-	if (codec && codec->component.probed)
-		soc_remove_component(&codec->component);
+	if (component && component->probed)
+		soc_remove_component(component);
 }
 
 static int snd_soc_init_codec_cache(struct snd_soc_codec *codec)
-- 
cgit v1.2.3


From 57bf772687700e206c760ba2e4097f78bde97887 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 19 Aug 2014 15:51:23 +0200
Subject: ASoC: Pass component instead of DAPM context to AUX dev init callback

Given that the component is the containing structure it makes more sense to pass
the component rather than the DAPM context to the AUX dev init callback.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h          | 2 +-
 sound/soc/samsung/speyside.c | 6 ++++--
 sound/soc/soc-core.c         | 2 +-
 3 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index fbc2ad840244..3a0031e1f9b4 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1022,7 +1022,7 @@ struct snd_soc_aux_dev {
 	const struct device_node *codec_of_node;
 
 	/* codec/machine specific init - e.g. add machine controls */
-	int (*init)(struct snd_soc_dapm_context *dapm);
+	int (*init)(struct snd_soc_component *component);
 };
 
 /* SoC card */
diff --git a/sound/soc/samsung/speyside.c b/sound/soc/samsung/speyside.c
index 9902efcb8ea1..a05482651aae 100644
--- a/sound/soc/samsung/speyside.c
+++ b/sound/soc/samsung/speyside.c
@@ -228,10 +228,12 @@ static struct snd_soc_dai_link speyside_dai[] = {
 	},
 };
 
-static int speyside_wm9081_init(struct snd_soc_dapm_context *dapm)
+static int speyside_wm9081_init(struct snd_soc_component *component)
 {
+	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
+
 	/* At any time the WM9081 is active it will have this clock */
-	return snd_soc_codec_set_sysclk(dapm->codec, WM9081_SYSCLK_MCLK, 0,
+	return snd_soc_codec_set_sysclk(codec, WM9081_SYSCLK_MCLK, 0,
 					MCLK_AUDIO_RATE, 0);
 }
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 08c04f4c7e62..4393bc33d3af 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1632,7 +1632,7 @@ static int soc_probe_aux_dev(struct snd_soc_card *card, int num)
 
 	/* do machine specific initialization */
 	if (aux_dev->init) {
-		ret = aux_dev->init(snd_soc_component_get_dapm(rtd->component));
+		ret = aux_dev->init(rtd->component);
 		if (ret < 0) {
 			dev_err(card->dev, "ASoC: failed to init %s: %d\n",
 				aux_dev->name, ret);
-- 
cgit v1.2.3


From 886f5692253de1a9509f5cb708432b2157afb57c Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 19 Aug 2014 15:51:28 +0200
Subject: ASoC: Automatically initialize regmap for all components

So far regmap is only automatically initialized for CODECs. Now that we have the
infrastructure in place to let components have DAPM widgets and controls that
want to use the generic regmap based IO also make sure to automatically
initialize regmap for all components.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h  |  3 ---
 sound/soc/soc-core.c | 35 +++++++++++++++++------------------
 sound/soc/soc-io.c   | 28 ----------------------------
 3 files changed, 17 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 3a0031e1f9b4..8ebee30311e3 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1289,9 +1289,6 @@ void snd_soc_component_async_complete(struct snd_soc_component *component);
 int snd_soc_component_test_bits(struct snd_soc_component *component,
 	unsigned int reg, unsigned int mask, unsigned int value);
 
-int snd_soc_component_init_io(struct snd_soc_component *component,
-	struct regmap *regmap);
-
 /* device driver data */
 
 static inline void snd_soc_card_set_drvdata(struct snd_soc_card *card,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 140f43f91635..96f286643ca1 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -4032,8 +4032,23 @@ static int snd_soc_component_initialize(struct snd_soc_component *component,
 	return 0;
 }
 
+static void snd_soc_component_init_regmap(struct snd_soc_component *component)
+{
+	if (!component->regmap)
+		component->regmap = dev_get_regmap(component->dev, NULL);
+	if (component->regmap) {
+		int val_bytes = regmap_get_val_bytes(component->regmap);
+		/* Errors are legitimate for non-integer byte multiples */
+		if (val_bytes > 0)
+			component->val_bytes = val_bytes;
+	}
+}
+
 static void snd_soc_component_add_unlocked(struct snd_soc_component *component)
 {
+	if (!component->write && !component->read)
+		snd_soc_component_init_regmap(component);
+
 	list_add(&component->list, &component_list);
 }
 
@@ -4371,7 +4386,6 @@ int snd_soc_register_codec(struct device *dev,
 {
 	struct snd_soc_codec *codec;
 	struct snd_soc_dai *dai;
-	struct regmap *regmap;
 	int ret, i;
 
 	dev_dbg(dev, "codec register %s\n", dev_name(dev));
@@ -4425,23 +4439,8 @@ int snd_soc_register_codec(struct device *dev,
 	codec->component.debugfs_prefix = "codec";
 #endif
 
-	if (!codec->component.write) {
-		if (codec_drv->get_regmap)
-			regmap = codec_drv->get_regmap(dev);
-		else
-			regmap = dev_get_regmap(dev, NULL);
-
-		if (regmap) {
-			ret = snd_soc_component_init_io(&codec->component,
-				regmap);
-			if (ret) {
-				dev_err(codec->dev,
-						"Failed to set cache I/O:%d\n",
-						ret);
-				goto err_cleanup;
-			}
-		}
-	}
+	if (codec_drv->get_regmap)
+		codec->component.regmap = codec_drv->get_regmap(dev);
 
 	for (i = 0; i < num_dai; i++) {
 		fixup_codec_formats(&dai_drv[i].playback);
diff --git a/sound/soc/soc-io.c b/sound/soc/soc-io.c
index 7767fbd73eb7..9b3939049cef 100644
--- a/sound/soc/soc-io.c
+++ b/sound/soc/soc-io.c
@@ -271,31 +271,3 @@ int snd_soc_platform_write(struct snd_soc_platform *platform,
 	return snd_soc_component_write(&platform->component, reg, val);
 }
 EXPORT_SYMBOL_GPL(snd_soc_platform_write);
-
-/**
- * snd_soc_component_init_io() - Initialize regmap IO
- *
- * @component: component to initialize
- * @regmap: regmap instance to use for IO operations
- *
- * Return: 0 on success, a negative error code otherwise
- */
-int snd_soc_component_init_io(struct snd_soc_component *component,
-	struct regmap *regmap)
-{
-	int ret;
-
-	if (!regmap)
-		return -EINVAL;
-
-	ret = regmap_get_val_bytes(regmap);
-	/* Errors are legitimate for non-integer byte
-	 * multiples */
-	if (ret > 0)
-		component->val_bytes = ret;
-
-	component->regmap = regmap;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_component_init_io);
-- 
cgit v1.2.3


From 75af7c081982d76cef0daf26e96b5d1e8cb9d631 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 19 Aug 2014 15:51:29 +0200
Subject: ASoC: Remove support for legacy snd_soc_platform IO

There were never any actual users of this in upstream and by we have with
regmap a replacement in place, which should be used by new drivers.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h  |  3 ---
 sound/soc/soc-core.c | 22 ----------------------
 2 files changed, 25 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 8ebee30311e3..edbb0d72ab38 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -890,9 +890,6 @@ struct snd_soc_platform_driver {
 	/* platform stream compress ops */
 	const struct snd_compr_ops *compr_ops;
 
-	/* platform IO - used for platform DAPM */
-	unsigned int (*read)(struct snd_soc_platform *, unsigned int);
-	int (*write)(struct snd_soc_platform *, unsigned int, unsigned int);
 	int (*bespoke_trigger)(struct snd_pcm_substream *, int);
 };
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 96f286643ca1..2d7a9ecbb0e3 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -4151,24 +4151,6 @@ static void snd_soc_platform_drv_remove(struct snd_soc_component *component)
 	platform->driver->remove(platform);
 }
 
-static int snd_soc_platform_drv_write(struct snd_soc_component *component,
-	unsigned int reg, unsigned int val)
-{
-	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
-
-	return platform->driver->write(platform, reg, val);
-}
-
-static int snd_soc_platform_drv_read(struct snd_soc_component *component,
-	unsigned int reg, unsigned int *val)
-{
-	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
-
-	*val = platform->driver->read(platform, reg);
-
-	return 0;
-}
-
 /**
  * snd_soc_add_platform - Add a platform to the ASoC core
  * @dev: The parent device for the platform
@@ -4205,10 +4187,6 @@ int snd_soc_add_platform(struct device *dev, struct snd_soc_platform *platform,
 		platform->component.probe = snd_soc_platform_drv_probe;
 	if (platform_drv->remove)
 		platform->component.remove = snd_soc_platform_drv_remove;
-	if (platform_drv->write)
-		platform->component.write = snd_soc_platform_drv_write;
-	if (platform_drv->read)
-		platform->component.read = snd_soc_platform_drv_read;
 
 #ifdef CONFIG_DEBUG_FS
 	platform->component.debugfs_prefix = "platform";
-- 
cgit v1.2.3


From 6697dabe27e03302ddfddc975275e6401defe2dd Mon Sep 17 00:00:00 2001
From: Martin Townsend <martin.townsend@xsilon.com>
Date: Tue, 19 Aug 2014 19:03:32 +0200
Subject: ieee802154: 6lowpan: ensure MTU of 1280 for 6lowpan

This patch drops the userspace accessable sysfs entry for the maximum
datagram size of a 6LoWPAN fragment packet.

A fragment should not have a datagram size value greater than 1280 byte.
Instead of make this value configurable, we accept 1280 datagram size
fragment packets only.

Signed-off-by: Martin Townsend <martin.townsend@xsilon.com>
Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/netns/ieee802154_6lowpan.h |  1 -
 net/ieee802154/reassembly.c            | 15 +++------------
 2 files changed, 3 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h
index e2070960bac0..8170f8d7052b 100644
--- a/include/net/netns/ieee802154_6lowpan.h
+++ b/include/net/netns/ieee802154_6lowpan.h
@@ -16,7 +16,6 @@ struct netns_sysctl_lowpan {
 struct netns_ieee802154_lowpan {
 	struct netns_sysctl_lowpan sysctl;
 	struct netns_frags	frags;
-	int			max_dsize;
 };
 
 #endif
diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c
index ffec6ce51005..32755cb7e64e 100644
--- a/net/ieee802154/reassembly.c
+++ b/net/ieee802154/reassembly.c
@@ -355,8 +355,6 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type)
 	struct net *net = dev_net(skb->dev);
 	struct lowpan_frag_info *frag_info = lowpan_cb(skb);
 	struct ieee802154_addr source, dest;
-	struct netns_ieee802154_lowpan *ieee802154_lowpan =
-		net_ieee802154_lowpan(net);
 	int err;
 
 	source = mac_cb(skb)->source;
@@ -366,8 +364,10 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type)
 	if (err < 0)
 		goto err;
 
-	if (frag_info->d_size > ieee802154_lowpan->max_dsize)
+	if (frag_info->d_size > IPV6_MIN_MTU) {
+		net_warn_ratelimited("lowpan_frag_rcv: datagram size exceeds MTU\n");
 		goto err;
+	}
 
 	fq = fq_find(net, frag_info, &source, &dest);
 	if (fq != NULL) {
@@ -415,13 +415,6 @@ static struct ctl_table lowpan_frags_ns_ctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	{
-		.procname	= "6lowpanfrag_max_datagram_size",
-		.data		= &init_net.ieee802154_lowpan.max_dsize,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{ }
 };
 
@@ -458,7 +451,6 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net)
 		table[1].data = &ieee802154_lowpan->frags.low_thresh;
 		table[1].extra2 = &ieee802154_lowpan->frags.high_thresh;
 		table[2].data = &ieee802154_lowpan->frags.timeout;
-		table[3].data = &ieee802154_lowpan->max_dsize;
 
 		/* Don't export sysctls to unprivileged users */
 		if (net->user_ns != &init_user_ns)
@@ -533,7 +525,6 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
-	ieee802154_lowpan->max_dsize = 0xFFFF;
 
 	inet_frags_init_net(&ieee802154_lowpan->frags);
 
-- 
cgit v1.2.3


From 7b7d8982f0169d5ac67c6c2877449fb7f6968cac Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 27 Jul 2014 14:31:53 -0700
Subject: mtd: fix linux/mtd/nand.h kernel-doc warning

Fix kernel-doc warning in <linux/mtd/nand.h>:

Warning(..//include/linux/mtd/nand.h:795): No description found for parameter 'ecc'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc:	David Woodhouse <dwmw2@infradead.org>
Cc:	Brian Norris <computersforpeace@gmail.com>
Cc:	linux-mtd@lists.infradead.org
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/mtd/nand.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 3083c53e0270..b7c11991cb09 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -766,6 +766,7 @@ struct nand_chip {
  * @options: stores various chip bit options
  * @id_len: The valid length of the @id.
  * @oobsize: OOB size
+ * @ecc: ECC correctability and step information from the datasheet.
  * @ecc.strength_ds: The ECC correctability from the datasheet, same as the
  *                   @ecc_strength_ds in nand_chip{}.
  * @ecc.step_ds: The ECC step required by the @ecc.strength_ds, same as the
-- 
cgit v1.2.3


From 31f754628cbb12c983600f22d9f0fed50dfe2134 Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Mon, 21 Jul 2014 19:07:22 -0700
Subject: mtd: use __packed shorthand

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/mtdswap.c        |  2 +-
 drivers/mtd/nand/sm_common.h |  2 +-
 include/linux/mtd/cfi.h      | 22 +++++++++++-----------
 3 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/mtdswap.c b/drivers/mtd/mtdswap.c
index 48cf6f98df44..fc8b3d16cce7 100644
--- a/drivers/mtd/mtdswap.c
+++ b/drivers/mtd/mtdswap.c
@@ -145,7 +145,7 @@ struct mtdswap_dev {
 struct mtdswap_oobdata {
 	__le16 magic;
 	__le32 count;
-} __attribute__((packed));
+} __packed;
 
 #define MTDSWAP_MAGIC_CLEAN	0x2095
 #define MTDSWAP_MAGIC_DIRTY	(MTDSWAP_MAGIC_CLEAN + 1)
diff --git a/drivers/mtd/nand/sm_common.h b/drivers/mtd/nand/sm_common.h
index 00f4a83359b2..d3e028e58b0f 100644
--- a/drivers/mtd/nand/sm_common.h
+++ b/drivers/mtd/nand/sm_common.h
@@ -18,7 +18,7 @@ struct sm_oob {
 	uint8_t ecc2[3];
 	uint8_t lba_copy2[2];
 	uint8_t ecc1[3];
-} __attribute__((packed));
+} __packed;
 
 
 /* one sector is always 512 bytes, but it can consist of two nand pages */
diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h
index 37ef6b194089..299d7d31fe53 100644
--- a/include/linux/mtd/cfi.h
+++ b/include/linux/mtd/cfi.h
@@ -153,7 +153,7 @@ struct cfi_ident {
 	uint16_t MaxBufWriteSize;
 	uint8_t  NumEraseRegions;
 	uint32_t EraseRegionInfo[0]; /* Not host ordered */
-} __attribute__((packed));
+} __packed;
 
 /* Extended Query Structure for both PRI and ALT */
 
@@ -161,7 +161,7 @@ struct cfi_extquery {
 	uint8_t  pri[3];
 	uint8_t  MajorVersion;
 	uint8_t  MinorVersion;
-} __attribute__((packed));
+} __packed;
 
 /* Vendor-Specific PRI for Intel/Sharp Extended Command Set (0x0001) */
 
@@ -180,7 +180,7 @@ struct cfi_pri_intelext {
 	uint8_t  FactProtRegSize;
 	uint8_t  UserProtRegSize;
 	uint8_t  extra[0];
-} __attribute__((packed));
+} __packed;
 
 struct cfi_intelext_otpinfo {
 	uint32_t ProtRegAddr;
@@ -188,7 +188,7 @@ struct cfi_intelext_otpinfo {
 	uint8_t  FactProtRegSize;
 	uint16_t UserGroups;
 	uint8_t  UserProtRegSize;
-} __attribute__((packed));
+} __packed;
 
 struct cfi_intelext_blockinfo {
 	uint16_t NumIdentBlocks;
@@ -196,7 +196,7 @@ struct cfi_intelext_blockinfo {
 	uint16_t MinBlockEraseCycles;
 	uint8_t  BitsPerCell;
 	uint8_t  BlockCap;
-} __attribute__((packed));
+} __packed;
 
 struct cfi_intelext_regioninfo {
 	uint16_t NumIdentPartitions;
@@ -205,7 +205,7 @@ struct cfi_intelext_regioninfo {
 	uint8_t  NumOpAllowedSimEraMode;
 	uint8_t  NumBlockTypes;
 	struct cfi_intelext_blockinfo BlockTypes[1];
-} __attribute__((packed));
+} __packed;
 
 struct cfi_intelext_programming_regioninfo {
 	uint8_t  ProgRegShift;
@@ -214,7 +214,7 @@ struct cfi_intelext_programming_regioninfo {
 	uint8_t  Reserved2;
 	uint8_t  ControlInvalid;
 	uint8_t  Reserved3;
-} __attribute__((packed));
+} __packed;
 
 /* Vendor-Specific PRI for AMD/Fujitsu Extended Command Set (0x0002) */
 
@@ -233,7 +233,7 @@ struct cfi_pri_amdstd {
 	uint8_t  VppMin;
 	uint8_t  VppMax;
 	uint8_t  TopBottom;
-} __attribute__((packed));
+} __packed;
 
 /* Vendor-Specific PRI for Atmel chips (command set 0x0002) */
 
@@ -245,18 +245,18 @@ struct cfi_pri_atmel {
 	uint8_t BottomBoot;
 	uint8_t BurstMode;
 	uint8_t PageMode;
-} __attribute__((packed));
+} __packed;
 
 struct cfi_pri_query {
 	uint8_t  NumFields;
 	uint32_t ProtField[1]; /* Not host ordered */
-} __attribute__((packed));
+} __packed;
 
 struct cfi_bri_query {
 	uint8_t  PageModeReadCap;
 	uint8_t  NumFields;
 	uint32_t ConfField[1]; /* Not host ordered */
-} __attribute__((packed));
+} __packed;
 
 #define P_ID_NONE               0x0000
 #define P_ID_INTEL_EXT          0x0001
-- 
cgit v1.2.3


From b25046b1e5e3f1423434da77ccc859f2f779d1ce Mon Sep 17 00:00:00 2001
From: Boris BREZILLON <boris.brezillon@free-electrons.com>
Date: Sun, 17 Aug 2014 10:29:42 +0200
Subject: mtd: nand: fix DocBook warnings on nand_sdr_timings doc

Change the comment type (from /** to /*) to prevent DocBook from
complaining about missing description for nand_sdr_timings fields.

There is currently no need in documenting those fields because they are
fully described in the ONFI specification (which is pointed out in the
comment).

Signed-off-by: Boris BREZILLON <boris.brezillon@free-electrons.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/mtd/nand.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 3083c53e0270..c300db3ae285 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -949,7 +949,7 @@ static inline int jedec_feature(struct nand_chip *chip)
 		: 0;
 }
 
-/**
+/*
  * struct nand_sdr_timings - SDR NAND chip timings
  *
  * This struct defines the timing requirements of a SDR NAND chip.
-- 
cgit v1.2.3


From 7132fe4f568721cbd5d9bce5a8a71556e9bc45b4 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Sun, 17 Aug 2014 09:24:26 -0700
Subject: Input: drv260x - add TI drv260x haptics driver

Add the TI drv260x haptics/vibrator driver.  This device uses the input
force feedback to produce a wave form to driver an ERM or LRA actuator
device.

The initial driver supports the devices real time playback mode.  But the
device has additional wave patterns in ROM. This functionality will be
added in future patchsets.

Product data sheet is located here: http://www.ti.com/product/drv2605

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/ti,drv260x.txt       |  51 ++
 drivers/input/misc/Kconfig                         |  11 +
 drivers/input/misc/Makefile                        |   1 +
 drivers/input/misc/drv260x.c                       | 738 +++++++++++++++++++++
 include/dt-bindings/input/ti-drv260x.h             |  36 +
 include/linux/platform_data/drv260x-pdata.h        |  28 +
 6 files changed, 865 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/input/ti,drv260x.txt
 create mode 100644 drivers/input/misc/drv260x.c
 create mode 100644 include/dt-bindings/input/ti-drv260x.h
 create mode 100644 include/linux/platform_data/drv260x-pdata.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/input/ti,drv260x.txt b/Documentation/devicetree/bindings/input/ti,drv260x.txt
new file mode 100644
index 000000000000..a9c8519eb9de
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/ti,drv260x.txt
@@ -0,0 +1,51 @@
+Texas Instruments - drv260x Haptics driver family
+
+The drv260x family serial control bus communicates through I2C protocols
+
+Required properties:
+	- compatible - One of:
+		"ti,drv2604" - DRV2604
+		"ti,drv2605" - DRV2605
+		"ti,drv2605l" - DRV2605L
+	- reg -  I2C slave address
+	- vbat-supply - Required supply regulator
+	- mode - Power up mode of the chip (defined in include/dt-bindings/input/ti-drv260x.h)
+		DRV260X_LRA_MODE - Linear Resonance Actuator mode (Piezoelectric)
+		DRV260X_LRA_NO_CAL_MODE - This is a LRA Mode but there is no calibration
+				sequence during init.  And the device is configured for real
+				time playback mode (RTP mode).
+		DRV260X_ERM_MODE - Eccentric Rotating Mass mode (Rotary vibrator)
+	- library-sel - These are ROM based waveforms pre-programmed into the IC.
+				This should be set to set the library to use at power up.
+				(defined in include/dt-bindings/input/ti-drv260x.h)
+		DRV260X_LIB_EMPTY - Do not use a pre-programmed library
+		DRV260X_ERM_LIB_A - Pre-programmed Library
+		DRV260X_ERM_LIB_B - Pre-programmed Library
+		DRV260X_ERM_LIB_C - Pre-programmed Library
+		DRV260X_ERM_LIB_D - Pre-programmed Library
+		DRV260X_ERM_LIB_E - Pre-programmed Library
+		DRV260X_ERM_LIB_F - Pre-programmed Library
+		DRV260X_LIB_LRA - Pre-programmed LRA Library
+
+Optional properties:
+	- enable-gpio - gpio pin to enable/disable the device.
+	- vib-rated-mv - The rated voltage of the actuator in millivolts.
+			  If this is not set then the value will be defaulted to
+			  3.2 v.
+	- vib-overdrive-mv - The overdrive voltage of the actuator in millivolts.
+			  If this is not set then the value will be defaulted to
+			  3.2 v.
+Example:
+
+drv2605l: drv2605l@5a {
+		compatible = "ti,drv2605l";
+		reg = <0x5a>;
+		enable-gpio = <&gpio1 28 GPIO_ACTIVE_HIGH>;
+		mode = <DRV260X_LRA_MODE>;
+		library-sel = <DRV260X_LIB_LRA>;
+		vib-rated-mv = <3200>;
+		vib-overdriver-mv = <3200>;
+};
+
+For more product information please see the link below:
+http://www.ti.com/product/drv2605
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 2ff4425a893b..41d0ae62ba05 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -676,4 +676,15 @@ config INPUT_SOC_BUTTON_ARRAY
 	  To compile this driver as a module, choose M here: the
 	  module will be called soc_button_array.
 
+config INPUT_DRV260X_HAPTICS
+	tristate "TI DRV260X haptics support"
+	depends on INPUT && I2C && GPIOLIB
+	select INPUT_FF_MEMLESS
+	select REGMAP_I2C
+	help
+	  Say Y to enable support for the TI DRV260X haptics driver.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called drv260x-haptics.
+
 endif
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index 4955ad322a01..cd4bc2d3474f 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_INPUT_COBALT_BTNS)		+= cobalt_btns.o
 obj-$(CONFIG_INPUT_DA9052_ONKEY)	+= da9052_onkey.o
 obj-$(CONFIG_INPUT_DA9055_ONKEY)	+= da9055_onkey.o
 obj-$(CONFIG_INPUT_DM355EVM)		+= dm355evm_keys.o
+obj-$(CONFIG_INPUT_DRV260X_HAPTICS)	+= drv260x.o
 obj-$(CONFIG_INPUT_GP2A)		+= gp2ap002a00f.o
 obj-$(CONFIG_INPUT_GPIO_BEEPER)		+= gpio-beeper.o
 obj-$(CONFIG_INPUT_GPIO_TILT_POLLED)	+= gpio_tilt_polled.o
diff --git a/drivers/input/misc/drv260x.c b/drivers/input/misc/drv260x.c
new file mode 100644
index 000000000000..e90e3b8189f7
--- /dev/null
+++ b/drivers/input/misc/drv260x.c
@@ -0,0 +1,738 @@
+/*
+ * DRV260X haptics driver family
+ *
+ * Author: Dan Murphy <dmurphy@ti.com>
+ *
+ * Copyright:   (C) 2014 Texas Instruments, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/i2c.h>
+#include <linux/input.h>
+#include <linux/module.h>
+#include <linux/of_gpio.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/regulator/consumer.h>
+
+#include <dt-bindings/input/ti-drv260x.h>
+#include <linux/platform_data/drv260x-pdata.h>
+
+#define DRV260X_STATUS		0x0
+#define DRV260X_MODE		0x1
+#define DRV260X_RT_PB_IN	0x2
+#define DRV260X_LIB_SEL		0x3
+#define DRV260X_WV_SEQ_1	0x4
+#define DRV260X_WV_SEQ_2	0x5
+#define DRV260X_WV_SEQ_3	0x6
+#define DRV260X_WV_SEQ_4	0x7
+#define DRV260X_WV_SEQ_5	0x8
+#define DRV260X_WV_SEQ_6	0x9
+#define DRV260X_WV_SEQ_7	0xa
+#define DRV260X_WV_SEQ_8	0xb
+#define DRV260X_GO				0xc
+#define DRV260X_OVERDRIVE_OFF	0xd
+#define DRV260X_SUSTAIN_P_OFF	0xe
+#define DRV260X_SUSTAIN_N_OFF	0xf
+#define DRV260X_BRAKE_OFF		0x10
+#define DRV260X_A_TO_V_CTRL		0x11
+#define DRV260X_A_TO_V_MIN_INPUT	0x12
+#define DRV260X_A_TO_V_MAX_INPUT	0x13
+#define DRV260X_A_TO_V_MIN_OUT	0x14
+#define DRV260X_A_TO_V_MAX_OUT	0x15
+#define DRV260X_RATED_VOLT		0x16
+#define DRV260X_OD_CLAMP_VOLT	0x17
+#define DRV260X_CAL_COMP		0x18
+#define DRV260X_CAL_BACK_EMF	0x19
+#define DRV260X_FEEDBACK_CTRL	0x1a
+#define DRV260X_CTRL1			0x1b
+#define DRV260X_CTRL2			0x1c
+#define DRV260X_CTRL3			0x1d
+#define DRV260X_CTRL4			0x1e
+#define DRV260X_CTRL5			0x1f
+#define DRV260X_LRA_LOOP_PERIOD	0x20
+#define DRV260X_VBAT_MON		0x21
+#define DRV260X_LRA_RES_PERIOD	0x22
+#define DRV260X_MAX_REG			0x23
+
+#define DRV260X_ALLOWED_R_BYTES	25
+#define DRV260X_ALLOWED_W_BYTES	2
+#define DRV260X_MAX_RW_RETRIES	5
+#define DRV260X_I2C_RETRY_DELAY 10
+
+#define DRV260X_GO_BIT				0x01
+
+/* Library Selection */
+#define DRV260X_LIB_SEL_MASK		0x07
+#define DRV260X_LIB_SEL_RAM			0x0
+#define DRV260X_LIB_SEL_OD			0x1
+#define DRV260X_LIB_SEL_40_60		0x2
+#define DRV260X_LIB_SEL_60_80		0x3
+#define DRV260X_LIB_SEL_100_140		0x4
+#define DRV260X_LIB_SEL_140_PLUS	0x5
+
+#define DRV260X_LIB_SEL_HIZ_MASK	0x10
+#define DRV260X_LIB_SEL_HIZ_EN		0x01
+#define DRV260X_LIB_SEL_HIZ_DIS		0
+
+/* Mode register */
+#define DRV260X_STANDBY				(1 << 6)
+#define DRV260X_STANDBY_MASK		0x40
+#define DRV260X_INTERNAL_TRIGGER	0x00
+#define DRV260X_EXT_TRIGGER_EDGE	0x01
+#define DRV260X_EXT_TRIGGER_LEVEL	0x02
+#define DRV260X_PWM_ANALOG_IN		0x03
+#define DRV260X_AUDIOHAPTIC			0x04
+#define DRV260X_RT_PLAYBACK			0x05
+#define DRV260X_DIAGNOSTICS			0x06
+#define DRV260X_AUTO_CAL			0x07
+
+/* Audio to Haptics Control */
+#define DRV260X_AUDIO_HAPTICS_PEAK_10MS		(0 << 2)
+#define DRV260X_AUDIO_HAPTICS_PEAK_20MS		(1 << 2)
+#define DRV260X_AUDIO_HAPTICS_PEAK_30MS		(2 << 2)
+#define DRV260X_AUDIO_HAPTICS_PEAK_40MS		(3 << 2)
+
+#define DRV260X_AUDIO_HAPTICS_FILTER_100HZ	0x00
+#define DRV260X_AUDIO_HAPTICS_FILTER_125HZ	0x01
+#define DRV260X_AUDIO_HAPTICS_FILTER_150HZ	0x02
+#define DRV260X_AUDIO_HAPTICS_FILTER_200HZ	0x03
+
+/* Min/Max Input/Output Voltages */
+#define DRV260X_AUDIO_HAPTICS_MIN_IN_VOLT	0x19
+#define DRV260X_AUDIO_HAPTICS_MAX_IN_VOLT	0x64
+#define DRV260X_AUDIO_HAPTICS_MIN_OUT_VOLT	0x19
+#define DRV260X_AUDIO_HAPTICS_MAX_OUT_VOLT	0xFF
+
+/* Feedback register */
+#define DRV260X_FB_REG_ERM_MODE			0x7f
+#define DRV260X_FB_REG_LRA_MODE			(1 << 7)
+
+#define DRV260X_BRAKE_FACTOR_MASK	0x1f
+#define DRV260X_BRAKE_FACTOR_2X		(1 << 0)
+#define DRV260X_BRAKE_FACTOR_3X		(2 << 4)
+#define DRV260X_BRAKE_FACTOR_4X		(3 << 4)
+#define DRV260X_BRAKE_FACTOR_6X		(4 << 4)
+#define DRV260X_BRAKE_FACTOR_8X		(5 << 4)
+#define DRV260X_BRAKE_FACTOR_16		(6 << 4)
+#define DRV260X_BRAKE_FACTOR_DIS	(7 << 4)
+
+#define DRV260X_LOOP_GAIN_LOW		0xf3
+#define DRV260X_LOOP_GAIN_MED		(1 << 2)
+#define DRV260X_LOOP_GAIN_HIGH		(2 << 2)
+#define DRV260X_LOOP_GAIN_VERY_HIGH	(3 << 2)
+
+#define DRV260X_BEMF_GAIN_0			0xfc
+#define DRV260X_BEMF_GAIN_1		(1 << 0)
+#define DRV260X_BEMF_GAIN_2		(2 << 0)
+#define DRV260X_BEMF_GAIN_3		(3 << 0)
+
+/* Control 1 register */
+#define DRV260X_AC_CPLE_EN			(1 << 5)
+#define DRV260X_STARTUP_BOOST		(1 << 7)
+
+/* Control 2 register */
+
+#define DRV260X_IDISS_TIME_45		0
+#define DRV260X_IDISS_TIME_75		(1 << 0)
+#define DRV260X_IDISS_TIME_150		(1 << 1)
+#define DRV260X_IDISS_TIME_225		0x03
+
+#define DRV260X_BLANK_TIME_45	(0 << 2)
+#define DRV260X_BLANK_TIME_75	(1 << 2)
+#define DRV260X_BLANK_TIME_150	(2 << 2)
+#define DRV260X_BLANK_TIME_225	(3 << 2)
+
+#define DRV260X_SAMP_TIME_150	(0 << 4)
+#define DRV260X_SAMP_TIME_200	(1 << 4)
+#define DRV260X_SAMP_TIME_250	(2 << 4)
+#define DRV260X_SAMP_TIME_300	(3 << 4)
+
+#define DRV260X_BRAKE_STABILIZER	(1 << 6)
+#define DRV260X_UNIDIR_IN			(0 << 7)
+#define DRV260X_BIDIR_IN			(1 << 7)
+
+/* Control 3 Register */
+#define DRV260X_LRA_OPEN_LOOP		(1 << 0)
+#define DRV260X_ANANLOG_IN			(1 << 1)
+#define DRV260X_LRA_DRV_MODE		(1 << 2)
+#define DRV260X_RTP_UNSIGNED_DATA	(1 << 3)
+#define DRV260X_SUPPLY_COMP_DIS		(1 << 4)
+#define DRV260X_ERM_OPEN_LOOP		(1 << 5)
+#define DRV260X_NG_THRESH_0			(0 << 6)
+#define DRV260X_NG_THRESH_2			(1 << 6)
+#define DRV260X_NG_THRESH_4			(2 << 6)
+#define DRV260X_NG_THRESH_8			(3 << 6)
+
+/* Control 4 Register */
+#define DRV260X_AUTOCAL_TIME_150MS		(0 << 4)
+#define DRV260X_AUTOCAL_TIME_250MS		(1 << 4)
+#define DRV260X_AUTOCAL_TIME_500MS		(2 << 4)
+#define DRV260X_AUTOCAL_TIME_1000MS		(3 << 4)
+
+/**
+ * struct drv260x_data -
+ * @input_dev - Pointer to the input device
+ * @client - Pointer to the I2C client
+ * @regmap - Register map of the device
+ * @work - Work item used to off load the enable/disable of the vibration
+ * @enable_gpio - Pointer to the gpio used for enable/disabling
+ * @regulator - Pointer to the regulator for the IC
+ * @magnitude - Magnitude of the vibration event
+ * @mode - The operating mode of the IC (LRA_NO_CAL, ERM or LRA)
+ * @library - The vibration library to be used
+ * @rated_voltage - The rated_voltage of the actuator
+ * @overdriver_voltage - The over drive voltage of the actuator
+**/
+struct drv260x_data {
+	struct input_dev *input_dev;
+	struct i2c_client *client;
+	struct regmap *regmap;
+	struct work_struct work;
+	struct gpio_desc *enable_gpio;
+	struct regulator *regulator;
+	u32 magnitude;
+	u32 mode;
+	u32 library;
+	int rated_voltage;
+	int overdrive_voltage;
+};
+
+static struct reg_default drv260x_reg_defs[] = {
+	{ DRV260X_STATUS, 0xe0 },
+	{ DRV260X_MODE, 0x40 },
+	{ DRV260X_RT_PB_IN, 0x00 },
+	{ DRV260X_LIB_SEL, 0x00 },
+	{ DRV260X_WV_SEQ_1, 0x01 },
+	{ DRV260X_WV_SEQ_2, 0x00 },
+	{ DRV260X_WV_SEQ_3, 0x00 },
+	{ DRV260X_WV_SEQ_4, 0x00 },
+	{ DRV260X_WV_SEQ_5, 0x00 },
+	{ DRV260X_WV_SEQ_6, 0x00 },
+	{ DRV260X_WV_SEQ_7, 0x00 },
+	{ DRV260X_WV_SEQ_8, 0x00 },
+	{ DRV260X_GO, 0x00 },
+	{ DRV260X_OVERDRIVE_OFF, 0x00 },
+	{ DRV260X_SUSTAIN_P_OFF, 0x00 },
+	{ DRV260X_SUSTAIN_N_OFF, 0x00 },
+	{ DRV260X_BRAKE_OFF, 0x00 },
+	{ DRV260X_A_TO_V_CTRL, 0x05 },
+	{ DRV260X_A_TO_V_MIN_INPUT, 0x19 },
+	{ DRV260X_A_TO_V_MAX_INPUT, 0xff },
+	{ DRV260X_A_TO_V_MIN_OUT, 0x19 },
+	{ DRV260X_A_TO_V_MAX_OUT, 0xff },
+	{ DRV260X_RATED_VOLT, 0x3e },
+	{ DRV260X_OD_CLAMP_VOLT, 0x8c },
+	{ DRV260X_CAL_COMP, 0x0c },
+	{ DRV260X_CAL_BACK_EMF, 0x6c },
+	{ DRV260X_FEEDBACK_CTRL, 0x36 },
+	{ DRV260X_CTRL1, 0x93 },
+	{ DRV260X_CTRL2, 0xfa },
+	{ DRV260X_CTRL3, 0xa0 },
+	{ DRV260X_CTRL4, 0x20 },
+	{ DRV260X_CTRL5, 0x80 },
+	{ DRV260X_LRA_LOOP_PERIOD, 0x33 },
+	{ DRV260X_VBAT_MON, 0x00 },
+	{ DRV260X_LRA_RES_PERIOD, 0x00 },
+};
+
+#define DRV260X_DEF_RATED_VOLT		0x90
+#define DRV260X_DEF_OD_CLAMP_VOLT	0x90
+
+/**
+ * Rated and Overdriver Voltages:
+ * Calculated using the formula r = v * 255 / 5.6
+ * where r is what will be written to the register
+ * and v is the rated or overdriver voltage of the actuator
+ **/
+static int drv260x_calculate_voltage(unsigned int voltage)
+{
+	return (voltage * 255 / 5600);
+}
+
+static void drv260x_worker(struct work_struct *work)
+{
+	struct drv260x_data *haptics = container_of(work, struct drv260x_data, work);
+	int error;
+
+	gpiod_set_value(haptics->enable_gpio, 1);
+	/* Data sheet says to wait 250us before trying to communicate */
+	udelay(250);
+
+	error = regmap_write(haptics->regmap,
+			     DRV260X_MODE, DRV260X_RT_PLAYBACK);
+	if (error) {
+		dev_err(&haptics->client->dev,
+			"Failed to write set mode: %d\n", error);
+	} else {
+		error = regmap_write(haptics->regmap,
+				     DRV260X_RT_PB_IN, haptics->magnitude);
+		if (error)
+			dev_err(&haptics->client->dev,
+				"Failed to set magnitude: %d\n", error);
+	}
+}
+
+static int drv260x_haptics_play(struct input_dev *input, void *data,
+				struct ff_effect *effect)
+{
+	struct drv260x_data *haptics = input_get_drvdata(input);
+
+	haptics->mode = DRV260X_LRA_NO_CAL_MODE;
+
+	if (effect->u.rumble.strong_magnitude > 0)
+		haptics->magnitude = effect->u.rumble.strong_magnitude;
+	else if (effect->u.rumble.weak_magnitude > 0)
+		haptics->magnitude = effect->u.rumble.weak_magnitude;
+	else
+		haptics->magnitude = 0;
+
+	schedule_work(&haptics->work);
+
+	return 0;
+}
+
+static void drv260x_close(struct input_dev *input)
+{
+	struct drv260x_data *haptics = input_get_drvdata(input);
+	int error;
+
+	cancel_work_sync(&haptics->work);
+
+	error = regmap_write(haptics->regmap, DRV260X_MODE, DRV260X_STANDBY);
+	if (error)
+		dev_err(&haptics->client->dev,
+			"Failed to enter standby mode: %d\n", error);
+
+	gpiod_set_value(haptics->enable_gpio, 0);
+}
+
+static const struct reg_default drv260x_lra_cal_regs[] = {
+	{ DRV260X_MODE, DRV260X_AUTO_CAL },
+	{ DRV260X_CTRL3, DRV260X_NG_THRESH_2 },
+	{ DRV260X_FEEDBACK_CTRL, DRV260X_FB_REG_LRA_MODE |
+		DRV260X_BRAKE_FACTOR_4X | DRV260X_LOOP_GAIN_HIGH },
+};
+
+static const struct reg_default drv260x_lra_init_regs[] = {
+	{ DRV260X_MODE, DRV260X_RT_PLAYBACK },
+	{ DRV260X_A_TO_V_CTRL, DRV260X_AUDIO_HAPTICS_PEAK_20MS |
+		DRV260X_AUDIO_HAPTICS_FILTER_125HZ },
+	{ DRV260X_A_TO_V_MIN_INPUT, DRV260X_AUDIO_HAPTICS_MIN_IN_VOLT },
+	{ DRV260X_A_TO_V_MAX_INPUT, DRV260X_AUDIO_HAPTICS_MAX_IN_VOLT },
+	{ DRV260X_A_TO_V_MIN_OUT, DRV260X_AUDIO_HAPTICS_MIN_OUT_VOLT },
+	{ DRV260X_A_TO_V_MAX_OUT, DRV260X_AUDIO_HAPTICS_MAX_OUT_VOLT },
+	{ DRV260X_FEEDBACK_CTRL, DRV260X_FB_REG_LRA_MODE |
+		DRV260X_BRAKE_FACTOR_2X | DRV260X_LOOP_GAIN_MED |
+		DRV260X_BEMF_GAIN_3 },
+	{ DRV260X_CTRL1, DRV260X_STARTUP_BOOST },
+	{ DRV260X_CTRL2, DRV260X_SAMP_TIME_250 },
+	{ DRV260X_CTRL3, DRV260X_NG_THRESH_2 | DRV260X_ANANLOG_IN },
+	{ DRV260X_CTRL4, DRV260X_AUTOCAL_TIME_500MS },
+};
+
+static const struct reg_default drv260x_erm_cal_regs[] = {
+	{ DRV260X_MODE, DRV260X_AUTO_CAL },
+	{ DRV260X_A_TO_V_MIN_INPUT, DRV260X_AUDIO_HAPTICS_MIN_IN_VOLT },
+	{ DRV260X_A_TO_V_MAX_INPUT, DRV260X_AUDIO_HAPTICS_MAX_IN_VOLT },
+	{ DRV260X_A_TO_V_MIN_OUT, DRV260X_AUDIO_HAPTICS_MIN_OUT_VOLT },
+	{ DRV260X_A_TO_V_MAX_OUT, DRV260X_AUDIO_HAPTICS_MAX_OUT_VOLT },
+	{ DRV260X_FEEDBACK_CTRL, DRV260X_BRAKE_FACTOR_3X |
+		DRV260X_LOOP_GAIN_MED | DRV260X_BEMF_GAIN_2 },
+	{ DRV260X_CTRL1, DRV260X_STARTUP_BOOST },
+	{ DRV260X_CTRL2, DRV260X_SAMP_TIME_250 | DRV260X_BLANK_TIME_75 |
+		DRV260X_IDISS_TIME_75 },
+	{ DRV260X_CTRL3, DRV260X_NG_THRESH_2 | DRV260X_ERM_OPEN_LOOP },
+	{ DRV260X_CTRL4, DRV260X_AUTOCAL_TIME_500MS },
+};
+
+static int drv260x_init(struct drv260x_data *haptics)
+{
+	int error;
+	unsigned int cal_buf;
+
+	error = regmap_write(haptics->regmap,
+			     DRV260X_RATED_VOLT, haptics->rated_voltage);
+	if (error) {
+		dev_err(&haptics->client->dev,
+			"Failed to write DRV260X_RATED_VOLT register: %d\n",
+			error);
+		return error;
+	}
+
+	error = regmap_write(haptics->regmap,
+			     DRV260X_OD_CLAMP_VOLT, haptics->overdrive_voltage);
+	if (error) {
+		dev_err(&haptics->client->dev,
+			"Failed to write DRV260X_OD_CLAMP_VOLT register: %d\n",
+			error);
+		return error;
+	}
+
+	switch (haptics->mode) {
+	case DRV260X_LRA_MODE:
+		error = regmap_register_patch(haptics->regmap,
+					      drv260x_lra_cal_regs,
+					      ARRAY_SIZE(drv260x_lra_cal_regs));
+		if (error) {
+			dev_err(&haptics->client->dev,
+				"Failed to write LRA calibration registers: %d\n",
+				error);
+			return error;
+		}
+
+		break;
+
+	case DRV260X_ERM_MODE:
+		error = regmap_register_patch(haptics->regmap,
+					      drv260x_erm_cal_regs,
+					      ARRAY_SIZE(drv260x_erm_cal_regs));
+		if (error) {
+			dev_err(&haptics->client->dev,
+				"Failed to write ERM calibration registers: %d\n",
+				error);
+			return error;
+		}
+
+		error = regmap_update_bits(haptics->regmap, DRV260X_LIB_SEL,
+					   DRV260X_LIB_SEL_MASK,
+					   haptics->library);
+		if (error) {
+			dev_err(&haptics->client->dev,
+				"Failed to write DRV260X_LIB_SEL register: %d\n",
+				error);
+			return error;
+		}
+
+		break;
+
+	default:
+		error = regmap_register_patch(haptics->regmap,
+					      drv260x_lra_init_regs,
+					      ARRAY_SIZE(drv260x_lra_init_regs));
+		if (error) {
+			dev_err(&haptics->client->dev,
+				"Failed to write LRA init registers: %d\n",
+				error);
+			return error;
+		}
+
+		error = regmap_update_bits(haptics->regmap, DRV260X_LIB_SEL,
+					   DRV260X_LIB_SEL_MASK,
+					   haptics->library);
+		if (error) {
+			dev_err(&haptics->client->dev,
+				"Failed to write DRV260X_LIB_SEL register: %d\n",
+				error);
+			return error;
+		}
+
+		/* No need to set GO bit here */
+		return 0;
+	}
+
+	error = regmap_write(haptics->regmap, DRV260X_GO, DRV260X_GO_BIT);
+	if (error) {
+		dev_err(&haptics->client->dev,
+			"Failed to write GO register: %d\n",
+			error);
+		return error;
+	}
+
+	do {
+		error = regmap_read(haptics->regmap, DRV260X_GO, &cal_buf);
+		if (error) {
+			dev_err(&haptics->client->dev,
+				"Failed to read GO register: %d\n",
+				error);
+			return error;
+		}
+	} while (cal_buf == DRV260X_GO_BIT);
+
+	return 0;
+}
+
+static const struct regmap_config drv260x_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = DRV260X_MAX_REG,
+	.reg_defaults = drv260x_reg_defs,
+	.num_reg_defaults = ARRAY_SIZE(drv260x_reg_defs),
+	.cache_type = REGCACHE_NONE,
+};
+
+#ifdef CONFIG_OF
+static int drv260x_parse_dt(struct device *dev,
+			    struct drv260x_data *haptics)
+{
+	struct device_node *np = dev->of_node;
+	unsigned int voltage;
+	int error;
+
+	error = of_property_read_u32(np, "mode", &haptics->mode);
+	if (error) {
+		dev_err(dev, "%s: No entry for mode\n", __func__);
+		return error;
+	}
+
+	error = of_property_read_u32(np, "library-sel", &haptics->library);
+	if (error) {
+		dev_err(dev, "%s: No entry for library selection\n",
+			__func__);
+		return error;
+	}
+
+	error = of_property_read_u32(np, "vib-rated-mv", &voltage);
+	if (!error)
+		haptics->rated_voltage = drv260x_calculate_voltage(voltage);
+
+
+	error = of_property_read_u32(np, "vib-overdrive-mv", &voltage);
+	if (!error)
+		haptics->overdrive_voltage = drv260x_calculate_voltage(voltage);
+
+	return 0;
+}
+#else
+static inline int drv260x_parse_dt(struct device *dev,
+				   struct drv260x_data *haptics)
+{
+	dev_err(dev, "no platform data defined\n");
+
+	return -EINVAL;
+}
+#endif
+
+static int drv260x_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	const struct drv260x_platform_data *pdata = dev_get_platdata(&client->dev);
+	struct drv260x_data *haptics;
+	int error;
+
+	haptics = devm_kzalloc(&client->dev, sizeof(*haptics), GFP_KERNEL);
+	if (!haptics)
+		return -ENOMEM;
+
+	haptics->rated_voltage = DRV260X_DEF_OD_CLAMP_VOLT;
+	haptics->rated_voltage = DRV260X_DEF_RATED_VOLT;
+
+	if (pdata) {
+		haptics->mode = pdata->mode;
+		haptics->library = pdata->library_selection;
+		if (pdata->vib_overdrive_voltage)
+			haptics->overdrive_voltage = drv260x_calculate_voltage(pdata->vib_overdrive_voltage);
+		if (pdata->vib_rated_voltage)
+			haptics->rated_voltage = drv260x_calculate_voltage(pdata->vib_rated_voltage);
+	} else if (client->dev.of_node) {
+		error = drv260x_parse_dt(&client->dev, haptics);
+		if (error)
+			return error;
+	} else {
+		dev_err(&client->dev, "Platform data not set\n");
+		return -ENODEV;
+	}
+
+
+	if (haptics->mode < DRV260X_LRA_MODE ||
+	    haptics->mode > DRV260X_ERM_MODE) {
+		dev_err(&client->dev,
+			"Vibrator mode is invalid: %i\n",
+			haptics->mode);
+		return -EINVAL;
+	}
+
+	if (haptics->library < DRV260X_LIB_EMPTY ||
+	    haptics->library > DRV260X_ERM_LIB_F) {
+		dev_err(&client->dev,
+			"Library value is invalid: %i\n", haptics->library);
+		return -EINVAL;
+	}
+
+	if (haptics->mode == DRV260X_LRA_MODE &&
+	    haptics->library != DRV260X_LIB_EMPTY &&
+	    haptics->library != DRV260X_LIB_LRA) {
+		dev_err(&client->dev,
+			"LRA Mode with ERM Library mismatch\n");
+		return -EINVAL;
+	}
+
+	haptics->regulator = devm_regulator_get(&client->dev, "vbat");
+	if (IS_ERR(haptics->regulator)) {
+		error = PTR_ERR(haptics->regulator);
+		dev_err(&client->dev,
+			"unable to get regulator, error: %d\n", error);
+		return error;
+	}
+
+	haptics->enable_gpio = devm_gpiod_get(&client->dev, "enable");
+	if (IS_ERR(haptics->enable_gpio)) {
+		error = PTR_ERR(haptics->enable_gpio);
+		if (error != -ENOENT && error != -ENOSYS)
+			return error;
+		haptics->enable_gpio = NULL;
+	} else {
+		gpiod_direction_output(haptics->enable_gpio, 1);
+	}
+
+	haptics->input_dev = devm_input_allocate_device(&client->dev);
+	if (!haptics->input_dev) {
+		dev_err(&client->dev, "Failed to allocate input device\n");
+		return -ENOMEM;
+	}
+
+	haptics->input_dev->name = "drv260x:haptics";
+	haptics->input_dev->dev.parent = client->dev.parent;
+	haptics->input_dev->close = drv260x_close;
+	input_set_drvdata(haptics->input_dev, haptics);
+	input_set_capability(haptics->input_dev, EV_FF, FF_RUMBLE);
+
+	error = input_ff_create_memless(haptics->input_dev, NULL,
+					drv260x_haptics_play);
+	if (error) {
+		dev_err(&client->dev, "input_ff_create() failed: %d\n",
+			error);
+		return error;
+	}
+
+	INIT_WORK(&haptics->work, drv260x_worker);
+
+	haptics->client = client;
+	i2c_set_clientdata(client, haptics);
+
+	haptics->regmap = devm_regmap_init_i2c(client, &drv260x_regmap_config);
+	if (IS_ERR(haptics->regmap)) {
+		error = PTR_ERR(haptics->regmap);
+		dev_err(&client->dev, "Failed to allocate register map: %d\n",
+			error);
+		return error;
+	}
+
+	error = drv260x_init(haptics);
+	if (error) {
+		dev_err(&client->dev, "Device init failed: %d\n", error);
+		return error;
+	}
+
+	error = input_register_device(haptics->input_dev);
+	if (error) {
+		dev_err(&client->dev, "couldn't register input device: %d\n",
+			error);
+		return error;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int drv260x_suspend(struct device *dev)
+{
+	struct drv260x_data *haptics = dev_get_drvdata(dev);
+	int ret = 0;
+
+	mutex_lock(&haptics->input_dev->mutex);
+
+	if (haptics->input_dev->users) {
+		ret = regmap_update_bits(haptics->regmap,
+					 DRV260X_MODE,
+					 DRV260X_STANDBY_MASK,
+					 DRV260X_STANDBY);
+		if (ret) {
+			dev_err(dev, "Failed to set standby mode\n");
+			goto out;
+		}
+
+		gpiod_set_value(haptics->enable_gpio, 0);
+
+		ret = regulator_disable(haptics->regulator);
+		if (ret) {
+			dev_err(dev, "Failed to disable regulator\n");
+			regmap_update_bits(haptics->regmap,
+					   DRV260X_MODE,
+					   DRV260X_STANDBY_MASK, 0);
+		}
+	}
+out:
+	mutex_unlock(&haptics->input_dev->mutex);
+	return ret;
+}
+
+static int drv260x_resume(struct device *dev)
+{
+	struct drv260x_data *haptics = dev_get_drvdata(dev);
+	int ret = 0;
+
+	mutex_lock(&haptics->input_dev->mutex);
+
+	if (haptics->input_dev->users) {
+		ret = regulator_enable(haptics->regulator);
+		if (ret) {
+			dev_err(dev, "Failed to enable regulator\n");
+			goto out;
+		}
+
+		ret = regmap_update_bits(haptics->regmap,
+					 DRV260X_MODE,
+					 DRV260X_STANDBY_MASK, 0);
+		if (ret) {
+			dev_err(dev, "Failed to unset standby mode\n");
+			regulator_disable(haptics->regulator);
+			goto out;
+		}
+
+		gpiod_set_value(haptics->enable_gpio, 1);
+	}
+
+out:
+	mutex_unlock(&haptics->input_dev->mutex);
+	return ret;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(drv260x_pm_ops, drv260x_suspend, drv260x_resume);
+
+static const struct i2c_device_id drv260x_id[] = {
+	{ "drv2605l", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, drv260x_id);
+
+#ifdef CONFIG_OF
+static const struct of_device_id drv260x_of_match[] = {
+	{ .compatible = "ti,drv2604", },
+	{ .compatible = "ti,drv2604l", },
+	{ .compatible = "ti,drv2605", },
+	{ .compatible = "ti,drv2605l", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, drv260x_of_match);
+#endif
+
+static struct i2c_driver drv260x_driver = {
+	.probe		= drv260x_probe,
+	.driver		= {
+		.name	= "drv260x-haptics",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(drv260x_of_match),
+		.pm	= &drv260x_pm_ops,
+	},
+	.id_table = drv260x_id,
+};
+module_i2c_driver(drv260x_driver);
+
+MODULE_ALIAS("platform:drv260x-haptics");
+MODULE_DESCRIPTION("TI DRV260x haptics driver");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
diff --git a/include/dt-bindings/input/ti-drv260x.h b/include/dt-bindings/input/ti-drv260x.h
new file mode 100644
index 000000000000..2626e6d9f707
--- /dev/null
+++ b/include/dt-bindings/input/ti-drv260x.h
@@ -0,0 +1,36 @@
+/*
+ * DRV260X haptics driver family
+ *
+ * Author: Dan Murphy <dmurphy@ti.com>
+ *
+ * Copyright:   (C) 2014 Texas Instruments, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_TI_DRV260X_H
+#define _DT_BINDINGS_TI_DRV260X_H
+
+/* Calibration Types */
+#define DRV260X_LRA_MODE		0x00
+#define DRV260X_LRA_NO_CAL_MODE	0x01
+#define DRV260X_ERM_MODE		0x02
+
+/* Library Selection */
+#define DRV260X_LIB_EMPTY			0x00
+#define DRV260X_ERM_LIB_A			0x01
+#define DRV260X_ERM_LIB_B			0x02
+#define DRV260X_ERM_LIB_C			0x03
+#define DRV260X_ERM_LIB_D			0x04
+#define DRV260X_ERM_LIB_E			0x05
+#define DRV260X_LIB_LRA			0x06
+#define DRV260X_ERM_LIB_F			0x07
+
+#endif
diff --git a/include/linux/platform_data/drv260x-pdata.h b/include/linux/platform_data/drv260x-pdata.h
new file mode 100644
index 000000000000..0a03b0944411
--- /dev/null
+++ b/include/linux/platform_data/drv260x-pdata.h
@@ -0,0 +1,28 @@
+/*
+ * Platform data for DRV260X haptics driver family
+ *
+ * Author: Dan Murphy <dmurphy@ti.com>
+ *
+ * Copyright:   (C) 2014 Texas Instruments, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _LINUX_DRV260X_PDATA_H
+#define _LINUX_DRV260X_PDATA_H
+
+struct drv260x_platform_data {
+	u32 library_selection;
+	u32 mode;
+	u32 vib_rated_voltage;
+	u32 vib_overdrive_voltage;
+};
+
+#endif
-- 
cgit v1.2.3


From e91ded8db57472c20b59b2242b100764cc152a10 Mon Sep 17 00:00:00 2001
From: Mike Frysinger <vapier@gentoo.org>
Date: Mon, 4 Aug 2014 04:50:41 -0400
Subject: uapi: netfilter_arp: use __u8 instead of u_int8_t

Similarly, the u_int8_t type is non-standard and not defined.  Change
it to use __u8 like the rest of the netfilter headers.

Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter_arp/arpt_mangle.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter_arp/arpt_mangle.h b/include/uapi/linux/netfilter_arp/arpt_mangle.h
index 250f502902bb..8c2b16a1f5a0 100644
--- a/include/uapi/linux/netfilter_arp/arpt_mangle.h
+++ b/include/uapi/linux/netfilter_arp/arpt_mangle.h
@@ -13,7 +13,7 @@ struct arpt_mangle
 	union {
 		struct in_addr tgt_ip;
 	} u_t;
-	u_int8_t flags;
+	__u8 flags;
 	int target;
 };
 
-- 
cgit v1.2.3


From 3a5f87c286515c54ff5c52c3e64d0c522b7570c0 Mon Sep 17 00:00:00 2001
From: Thomas Wood <thomas.wood@intel.com>
Date: Wed, 20 Aug 2014 14:45:00 +0100
Subject: drm: fix plane rotation when restoring fbdev configuration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make sure plane rotation is reset correctly when restoring the fbdev
configuration by using drm_mode_plane_set_obj_prop which calls the
driver's set_property callback.

The rotation reset feature was introduced in commit 9783de2 (drm:
Resetting rotation property) and the callback issue was originally
addressed in a previous version of the patch, but the fix was not
present in the final version.

v2: Fix documentation warning
    Add some more details to the commit message (Daniel Vetter)

Testcase: igt/kms_rotation_crc
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=82236
Cc: Sonika Jindal <sonika.jindal@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Thomas Wood <thomas.wood@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c      | 25 ++++++++++++++++++++-----
 drivers/gpu/drm/drm_fb_helper.c |  6 +++---
 include/drm/drm_crtc.h          |  3 +++
 3 files changed, 26 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 3c4a62169f28..d7e4c0e2e796 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -4156,12 +4156,25 @@ static int drm_mode_crtc_set_obj_prop(struct drm_mode_object *obj,
 	return ret;
 }
 
-static int drm_mode_plane_set_obj_prop(struct drm_mode_object *obj,
-				      struct drm_property *property,
-				      uint64_t value)
+/**
+ * drm_mode_plane_set_obj_prop - set the value of a property
+ * @plane: drm plane object to set property value for
+ * @property: property to set
+ * @value: value the property should be set to
+ *
+ * This functions sets a given property on a given plane object. This function
+ * calls the driver's ->set_property callback and changes the software state of
+ * the property if the callback succeeds.
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
+int drm_mode_plane_set_obj_prop(struct drm_plane *plane,
+				struct drm_property *property,
+				uint64_t value)
 {
 	int ret = -EINVAL;
-	struct drm_plane *plane = obj_to_plane(obj);
+	struct drm_mode_object *obj = &plane->base;
 
 	if (plane->funcs->set_property)
 		ret = plane->funcs->set_property(plane, property, value);
@@ -4170,6 +4183,7 @@ static int drm_mode_plane_set_obj_prop(struct drm_mode_object *obj,
 
 	return ret;
 }
+EXPORT_SYMBOL(drm_mode_plane_set_obj_prop);
 
 /**
  * drm_mode_getproperty_ioctl - get the current value of a object's property
@@ -4308,7 +4322,8 @@ int drm_mode_obj_set_property_ioctl(struct drm_device *dev, void *data,
 		ret = drm_mode_crtc_set_obj_prop(arg_obj, property, arg->value);
 		break;
 	case DRM_MODE_OBJECT_PLANE:
-		ret = drm_mode_plane_set_obj_prop(arg_obj, property, arg->value);
+		ret = drm_mode_plane_set_obj_prop(obj_to_plane(arg_obj),
+						  property, arg->value);
 		break;
 	}
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index d139eddb3d61..99569ee5adee 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -350,9 +350,9 @@ static bool restore_fbdev_mode(struct drm_fb_helper *fb_helper)
 			drm_plane_force_disable(plane);
 
 		if (dev->mode_config.rotation_property) {
-			drm_object_property_set_value(&plane->base,
-					dev->mode_config.rotation_property,
-					BIT(DRM_ROTATE_0));
+			drm_mode_plane_set_obj_prop(plane,
+						    dev->mode_config.rotation_property,
+						    BIT(DRM_ROTATE_0));
 		}
 	}
 
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 62f73bdbcc47..38fae5d9ad73 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -1121,6 +1121,9 @@ extern int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data,
 					     struct drm_file *file_priv);
 extern int drm_mode_obj_set_property_ioctl(struct drm_device *dev, void *data,
 					   struct drm_file *file_priv);
+extern int drm_mode_plane_set_obj_prop(struct drm_plane *plane,
+				       struct drm_property *property,
+				       uint64_t value);
 
 extern void drm_fb_get_bpp_depth(uint32_t format, unsigned int *depth,
 				 int *bpp);
-- 
cgit v1.2.3


From f161dd4122ffa73e4e12000309dca65bec80d416 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 15 Aug 2014 21:06:54 +0300
Subject: Bluetooth: Fix hci_conn reference counting for auto-connections

Recently the LE passive scanning and auto-connections feature was
introduced. It uses the hci_connect_le() API which returns a hci_conn
along with a reference count to that object. All previous users would
tie this returned reference to some existing object, such as an L2CAP
channel, and there'd be no leaked references this way. For
auto-connections however the reference was returned but not stored
anywhere, leaving established connections with one higher reference
count than they should have.

Instead of playing special tricks with hci_conn_hold/drop this patch
associates the returned reference from hci_connect_le() with the object
that in practice does own this reference, i.e. the hci_conn_params
struct that caused us to initiate a connection in the first place. Once
the connection is established or fails to establish this reference is
removed appropriately.

One extra thing needed is to call hci_pend_le_actions_clear() before
calling hci_conn_hash_flush() so that the reference is cleared before
the hci_conn objects are fully removed.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_conn.c         |  8 ++++++++
 net/bluetooth/hci_core.c         | 14 ++++++++++++--
 net/bluetooth/hci_event.c        | 17 +++++++++++++++--
 4 files changed, 37 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b5d5af3aa469..6f884e6c731e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -464,6 +464,8 @@ struct hci_conn_params {
 		HCI_AUTO_CONN_ALWAYS,
 		HCI_AUTO_CONN_LINK_LOSS,
 	} auto_connect;
+
+	struct hci_conn *conn;
 };
 
 extern struct list_head hci_dev_list;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index b50dabb3f86a..faff6247ac8f 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -589,6 +589,14 @@ EXPORT_SYMBOL(hci_get_route);
 void hci_le_conn_failed(struct hci_conn *conn, u8 status)
 {
 	struct hci_dev *hdev = conn->hdev;
+	struct hci_conn_params *params;
+
+	params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst,
+					   conn->dst_type);
+	if (params && params->conn) {
+		hci_conn_drop(params->conn);
+		params->conn = NULL;
+	}
 
 	conn->state = BT_CLOSED;
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index c32d361c0cf7..1d9c29a00568 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2536,8 +2536,13 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev)
 {
 	struct hci_conn_params *p;
 
-	list_for_each_entry(p, &hdev->le_conn_params, list)
+	list_for_each_entry(p, &hdev->le_conn_params, list) {
+		if (p->conn) {
+			hci_conn_drop(p->conn);
+			p->conn = NULL;
+		}
 		list_del_init(&p->action);
+	}
 
 	BT_DBG("All LE pending actions cleared");
 }
@@ -2578,8 +2583,8 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 
 	hci_dev_lock(hdev);
 	hci_inquiry_cache_flush(hdev);
-	hci_conn_hash_flush(hdev);
 	hci_pend_le_actions_clear(hdev);
+	hci_conn_hash_flush(hdev);
 	hci_dev_unlock(hdev);
 
 	hci_notify(hdev, HCI_DEV_DOWN);
@@ -3727,6 +3732,9 @@ void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type)
 	if (!params)
 		return;
 
+	if (params->conn)
+		hci_conn_drop(params->conn);
+
 	list_del(&params->action);
 	list_del(&params->list);
 	kfree(params);
@@ -3757,6 +3765,8 @@ void hci_conn_params_clear_all(struct hci_dev *hdev)
 	struct hci_conn_params *params, *tmp;
 
 	list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) {
+		if (params->conn)
+			hci_conn_drop(params->conn);
 		list_del(&params->action);
 		list_del(&params->list);
 		kfree(params);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index be35598984d9..a6000823f0ff 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4221,8 +4221,13 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_proto_connect_cfm(conn, ev->status);
 
 	params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type);
-	if (params)
+	if (params) {
 		list_del_init(&params->action);
+		if (params->conn) {
+			hci_conn_drop(params->conn);
+			params->conn = NULL;
+		}
+	}
 
 unlock:
 	hci_update_background_scan(hdev);
@@ -4304,8 +4309,16 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 
 	conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW,
 			      HCI_LE_AUTOCONN_TIMEOUT, HCI_ROLE_MASTER);
-	if (!IS_ERR(conn))
+	if (!IS_ERR(conn)) {
+		/* Store the pointer since we don't really have any
+		 * other owner of the object besides the params that
+		 * triggered it. This way we can abort the connection if
+		 * the parameters get removed and keep the reference
+		 * count consistent once the connection is established.
+		 */
+		params->conn = conn;
 		return;
+	}
 
 	switch (PTR_ERR(conn)) {
 	case -EBUSY:
-- 
cgit v1.2.3


From 58b84f6a97f7f8811e0636836734809ff52cad43 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 19 Aug 2014 12:00:53 -0500
Subject: gpio: move GPIOD flags outside #ifdef

The GPIOD flags are defined inside the #ifdef CONFIG_GPIOLIB
switch, making the gpiolib stubs fail if these flags are used
by a consumer. This is not correct: the stubs should compile
fine without GPIOLIB.

Reported-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio/consumer.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index b7ce0c64c6f3..c7e17de732f3 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -16,8 +16,6 @@ struct device;
  */
 struct gpio_desc;
 
-#ifdef CONFIG_GPIOLIB
-
 #define GPIOD_FLAGS_BIT_DIR_SET		BIT(0)
 #define GPIOD_FLAGS_BIT_DIR_OUT		BIT(1)
 #define GPIOD_FLAGS_BIT_DIR_VAL		BIT(2)
@@ -34,6 +32,8 @@ enum gpiod_flags {
 			  GPIOD_FLAGS_BIT_DIR_VAL,
 };
 
+#ifdef CONFIG_GPIOLIB
+
 /* Acquire and dispose GPIOs */
 struct gpio_desc *__must_check __gpiod_get(struct device *dev,
 					 const char *con_id,
-- 
cgit v1.2.3


From df11e506d330d9a0e5a701cd2c5fcb7d461b6060 Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Thu, 21 Aug 2014 10:11:34 +0800
Subject: regulator: core: Add back the const qualifier for ops of struct
 regulator_desc

Fix below build warning:
CC [M]  drivers/regulator/hi6421-regulator.o
drivers/regulator/hi6421-regulator.c:356:2: warning: initialization discards 'const' qualifier from pointer target type [enabled by default]

This is a revert of commit 716845ebeb50 ("regulator: core: Fix build error due
to const qualifier for ops"). The build error was fixed by commit 39f5460d7f9c
("regulator: core: add const to regulator_ops and fix build error in mc13892").

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/regulator/driver.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 3abda7554d82..efe058f8f746 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -246,7 +246,7 @@ struct regulator_desc {
 	int id;
 	bool continuous_voltage_range;
 	unsigned n_voltages;
-	struct regulator_ops *ops;
+	const struct regulator_ops *ops;
 	int irq;
 	enum regulator_type type;
 	struct module *owner;
-- 
cgit v1.2.3


From e790d9ef6405633b007339d746b709aed43a928d Mon Sep 17 00:00:00 2001
From: Radim Krčmář <rkrcmar@redhat.com>
Date: Thu, 21 Aug 2014 18:08:05 +0200
Subject: KVM: add kvm_arch_sched_in
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce preempt notifiers for architecture specific code.
Advantage over creating a new notifier in every arch is slightly simpler
code and guaranteed call order with respect to kvm_sched_in.

Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm/kvm/arm.c         | 4 ++++
 arch/mips/kvm/mips.c       | 4 ++++
 arch/powerpc/kvm/powerpc.c | 4 ++++
 arch/s390/kvm/kvm-s390.c   | 4 ++++
 arch/x86/kvm/x86.c         | 4 ++++
 include/linux/kvm_host.h   | 2 ++
 virt/kvm/kvm_main.c        | 2 ++
 7 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index a99e0cdf8ba2..9f788ebac55b 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -288,6 +288,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 }
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	vcpu->cpu = cpu;
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index cd7114147ae7..2362df2a79f9 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -1002,6 +1002,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 }
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
 int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 				  struct kvm_translation *tr)
 {
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 4c79284b58be..cbc432f4f0a6 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -720,6 +720,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 	kvmppc_subarch_vcpu_uninit(vcpu);
 }
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 #ifdef CONFIG_BOOKE
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ce81eb2ab76a..a3c324ec4370 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -555,6 +555,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 	/* Nothing todo */
 }
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cd718c01cdf1..7d43dc7bb906 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7171,6 +7171,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 		static_key_slow_dec(&kvm_no_apic_vcpu);
 }
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	if (type)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a4c33b34fe3f..ebd723676633 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -624,6 +624,8 @@ void kvm_arch_exit(void);
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
+
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 39b16035386f..5a0817ee996e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3124,6 +3124,8 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
 	if (vcpu->preempted)
 		vcpu->preempted = false;
 
+	kvm_arch_sched_in(vcpu, cpu);
+
 	kvm_arch_vcpu_load(vcpu, cpu);
 }
 
-- 
cgit v1.2.3


From 0fc87864879c46afe145e20ec09c9dba2328e3be Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Wed, 28 May 2014 09:38:21 -0300
Subject: [media] v4l: Add test pattern colour component controls

In many cases the test pattern has selectable values for each colour
component. Implement controls for raw bayer components. Additional controls
should be defined for colour components that are not covered by these
controls.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 Documentation/DocBook/media/v4l/controls.xml | 34 ++++++++++++++++++++++++++++
 drivers/media/v4l2-core/v4l2-ctrls.c         |  4 ++++
 include/uapi/linux/v4l2-controls.h           |  4 ++++
 3 files changed, 42 insertions(+)

(limited to 'include')

diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml
index 9f5ffd85560b..a7eb1bde8b92 100644
--- a/Documentation/DocBook/media/v4l/controls.xml
+++ b/Documentation/DocBook/media/v4l/controls.xml
@@ -4790,6 +4790,40 @@ interface and may change in the future.</para>
 	    conversion.
 	    </entry>
 	  </row>
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TEST_PATTERN_RED</constant></entry>
+	    <entry>integer</entry>
+	  </row>
+	  <row>
+	    <entry spanname="descr">Test pattern red colour component.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TEST_PATTERN_GREENR</constant></entry>
+	    <entry>integer</entry>
+	  </row>
+	  <row>
+	    <entry spanname="descr">Test pattern green (next to red)
+	    colour component.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TEST_PATTERN_BLUE</constant></entry>
+	    <entry>integer</entry>
+	  </row>
+	  <row>
+	    <entry spanname="descr">Test pattern blue colour component.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TEST_PATTERN_GREENB</constant></entry>
+	    <entry>integer</entry>
+	  </row>
+	  <row>
+	    <entry spanname="descr">Test pattern green (next to blue)
+	    colour component.
+	    </entry>
+	  </row>
 	  <row><entry></entry></row>
 	</tbody>
       </tgroup>
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index f030d6a9e044..35d1f3d5045b 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -859,6 +859,10 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_VBLANK:			return "Vertical Blanking";
 	case V4L2_CID_HBLANK:			return "Horizontal Blanking";
 	case V4L2_CID_ANALOGUE_GAIN:		return "Analogue Gain";
+	case V4L2_CID_TEST_PATTERN_RED:		return "Red Pixel Value";
+	case V4L2_CID_TEST_PATTERN_GREENR:	return "Green (Red) Pixel Value";
+	case V4L2_CID_TEST_PATTERN_BLUE:	return "Blue Pixel Value";
+	case V4L2_CID_TEST_PATTERN_GREENB:	return "Green (Blue) Pixel Value";
 
 	/* Image processing controls */
 	/* Keep the order of the 'case's the same as in v4l2-controls.h! */
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index e946e43fb8d5..8b930210a4b9 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -865,6 +865,10 @@ enum v4l2_jpeg_chroma_subsampling {
 #define V4L2_CID_VBLANK				(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 1)
 #define V4L2_CID_HBLANK				(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 2)
 #define V4L2_CID_ANALOGUE_GAIN			(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 3)
+#define V4L2_CID_TEST_PATTERN_RED		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 4)
+#define V4L2_CID_TEST_PATTERN_GREENR		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 5)
+#define V4L2_CID_TEST_PATTERN_BLUE		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 6)
+#define V4L2_CID_TEST_PATTERN_GREENB		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 7)
 
 
 /* Image processing controls */
-- 
cgit v1.2.3


From a913d8742e275dd2d80726afac02311a0f49d161 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 26 May 2014 09:46:18 -0300
Subject: [media] smiapp: Add driver-specific test pattern menu item
 definitions

Add numeric definitions for menu items used in the smiapp driver's test
pattern menu.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 include/uapi/linux/Kbuild   |  1 +
 include/uapi/linux/smiapp.h | 29 +++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+)
 create mode 100644 include/uapi/linux/smiapp.h

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 24e9033f8b3f..4ec377d103c7 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -353,6 +353,7 @@ header-y += serio.h
 header-y += shm.h
 header-y += signal.h
 header-y += signalfd.h
+header-y += smiapp.h
 header-y += snmp.h
 header-y += sock_diag.h
 header-y += socket.h
diff --git a/include/uapi/linux/smiapp.h b/include/uapi/linux/smiapp.h
new file mode 100644
index 000000000000..53938f4412ee
--- /dev/null
+++ b/include/uapi/linux/smiapp.h
@@ -0,0 +1,29 @@
+/*
+ * include/uapi/linux/smiapp.h
+ *
+ * Generic driver for SMIA/SMIA++ compliant camera modules
+ *
+ * Copyright (C) 2014 Intel Corporation
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ */
+
+#ifndef __UAPI_LINUX_SMIAPP_H_
+#define __UAPI_LINUX_SMIAPP_H_
+
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_DISABLED			0
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_SOLID_COLOUR		1
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_COLOUR_BARS		2
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_COLOUR_BARS_GREY		3
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_PN9			4
+
+#endif /* __UAPI_LINUX_SMIAPP_H_ */
-- 
cgit v1.2.3


From 9a36d8ed33c481a99f69f8a2eeb22e3c7750e522 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 19 May 2014 16:37:38 -0300
Subject: [media] omap3isp: ccdc: Add basic support for interlaced video

When the CCDC input is interlaced enable the alternate field order on
the CCDC output video node. The field signal polarity is specified
through platform data.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Tested-by: Enrico Butera <ebutera@users.sourceforge.net>
Acked-by: Sakari Ailus <sakari.ailus@iki.fi>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/platform/omap3isp/ispccdc.c  | 21 ++++++++++++++++++++-
 drivers/media/platform/omap3isp/ispvideo.c |  6 ++++++
 drivers/media/platform/omap3isp/ispvideo.h |  2 ++
 include/media/omap3isp.h                   |  3 +++
 4 files changed, 31 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/media/platform/omap3isp/ispccdc.c b/drivers/media/platform/omap3isp/ispccdc.c
index 76d4fd73f5e8..49d7256a7de3 100644
--- a/drivers/media/platform/omap3isp/ispccdc.c
+++ b/drivers/media/platform/omap3isp/ispccdc.c
@@ -1001,6 +1001,9 @@ static void ccdc_config_sync_if(struct isp_ccdc_device *ccdc,
 	if (pdata && pdata->vs_pol)
 		syn_mode |= ISPCCDC_SYN_MODE_VDPOL;
 
+	if (pdata && pdata->fld_pol)
+		syn_mode |= ISPCCDC_SYN_MODE_FLDPOL;
+
 	isp_reg_writel(isp, syn_mode, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SYN_MODE);
 
 	/* The CCDC_CFG.Y8POS bit is used in YCbCr8 input mode only. The
@@ -1140,6 +1143,7 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 
 	omap3isp_configure_bridge(isp, ccdc->input, pdata, shift, bridge);
 
+	/* Configure the sync interface. */
 	ccdc_config_sync_if(ccdc, pdata, depth_out);
 
 	syn_mode = isp_reg_readl(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SYN_MODE);
@@ -1499,6 +1503,17 @@ static int ccdc_isr_buffer(struct isp_ccdc_device *ccdc)
 		return 1;
 	}
 
+	/* When capturing fields in alternate order read the current field
+	 * identifier and store it in the pipeline.
+	 */
+	if (ccdc->formats[CCDC_PAD_SOURCE_OF].field == V4L2_FIELD_ALTERNATE) {
+		u32 syn_mode = isp_reg_readl(isp, OMAP3_ISP_IOMEM_CCDC,
+					     ISPCCDC_SYN_MODE);
+
+		pipe->field = syn_mode & ISPCCDC_SYN_MODE_FLDSTAT
+			    ? V4L2_FIELD_BOTTOM : V4L2_FIELD_TOP;
+	}
+
 	if (ccdc_sbl_wait_idle(ccdc, 1000)) {
 		dev_info(isp->dev, "CCDC won't become idle!\n");
 		isp->crashed |= 1U << ccdc->subdev.entity.id;
@@ -1830,6 +1845,11 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 		/* Clamp the input size. */
 		fmt->width = clamp_t(u32, width, 32, 4096);
 		fmt->height = clamp_t(u32, height, 32, 4096);
+
+		/* Default to progressive field order. */
+		if (fmt->field == V4L2_FIELD_ANY)
+			fmt->field = V4L2_FIELD_NONE;
+
 		break;
 
 	case CCDC_PAD_SOURCE_OF:
@@ -1885,7 +1905,6 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 	 * stored on 2 bytes.
 	 */
 	fmt->colorspace = V4L2_COLORSPACE_SRGB;
-	fmt->field = V4L2_FIELD_NONE;
 }
 
 /*
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index 756c1628ef86..c38f1d4cc538 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -482,6 +482,11 @@ struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
 	else
 		buf->vb.v4l2_buf.sequence = atomic_read(&pipe->frame_number);
 
+	if (pipe->field != V4L2_FIELD_NONE)
+		buf->vb.v4l2_buf.sequence /= 2;
+
+	buf->vb.v4l2_buf.field = pipe->field;
+
 	/* Report pipeline errors to userspace on the capture device side. */
 	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->error) {
 		state = VB2_BUF_STATE_ERROR;
@@ -1038,6 +1043,7 @@ isp_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 	video->queue = &vfh->queue;
 	INIT_LIST_HEAD(&video->dmaqueue);
 	atomic_set(&pipe->frame_number, -1);
+	pipe->field = vfh->format.fmt.pix.field;
 
 	mutex_lock(&video->queue_lock);
 	ret = vb2_streamon(&vfh->queue, type);
diff --git a/drivers/media/platform/omap3isp/ispvideo.h b/drivers/media/platform/omap3isp/ispvideo.h
index a76124cd6431..0b7efedc3da9 100644
--- a/drivers/media/platform/omap3isp/ispvideo.h
+++ b/drivers/media/platform/omap3isp/ispvideo.h
@@ -78,6 +78,7 @@ enum isp_pipeline_state {
 
 /*
  * struct isp_pipeline - An ISP hardware pipeline
+ * @field: The field being processed by the pipeline
  * @error: A hardware error occurred during capture
  * @entities: Bitmask of entities in the pipeline (indexed by entity ID)
  */
@@ -91,6 +92,7 @@ struct isp_pipeline {
 	u32 entities;
 	unsigned long l3_ick;
 	unsigned int max_rate;
+	enum v4l2_field field;
 	atomic_t frame_number;
 	bool do_propagation; /* of frame number */
 	bool error;
diff --git a/include/media/omap3isp.h b/include/media/omap3isp.h
index c9d06d9f7e6e..398279dd1922 100644
--- a/include/media/omap3isp.h
+++ b/include/media/omap3isp.h
@@ -57,6 +57,8 @@ enum {
  *		0 - Active high, 1 - Active low
  * @vs_pol: Vertical synchronization polarity
  *		0 - Active high, 1 - Active low
+ * @fld_pol: Field signal polarity
+ *		0 - Positive, 1 - Negative
  * @data_pol: Data polarity
  *		0 - Normal, 1 - One's complement
  */
@@ -65,6 +67,7 @@ struct isp_parallel_platform_data {
 	unsigned int clk_pol:1;
 	unsigned int hs_pol:1;
 	unsigned int vs_pol:1;
+	unsigned int fld_pol:1;
 	unsigned int data_pol:1;
 };
 
-- 
cgit v1.2.3


From f035eb4e976ef5a059e30bc91cfd310ff030a7d3 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Thu, 7 Aug 2014 03:47:14 -0300
Subject: [media] videobuf2: fix lockdep warning

The following lockdep warning has been there ever since commit a517cca6b24fc54ac209e44118ec8962051662e3
one year ago:

[  403.117947] ======================================================
[  403.117949] [ INFO: possible circular locking dependency detected ]
[  403.117953] 3.16.0-rc6-test-media #961 Not tainted
[  403.117954] -------------------------------------------------------
[  403.117956] v4l2-ctl/15377 is trying to acquire lock:
[  403.117959]  (&dev->mutex#3){+.+.+.}, at: [<ffffffffa005a6c3>] vb2_fop_mmap+0x33/0x90 [videobuf2_core]
[  403.117974]
[  403.117974] but task is already holding lock:
[  403.117976]  (&mm->mmap_sem){++++++}, at: [<ffffffff8118291f>] vm_mmap_pgoff+0x6f/0xc0
[  403.117987]
[  403.117987] which lock already depends on the new lock.
[  403.117987]
[  403.117990]
[  403.117990] the existing dependency chain (in reverse order) is:
[  403.117992]
[  403.117992] -> #1 (&mm->mmap_sem){++++++}:
[  403.117997]        [<ffffffff810d733c>] validate_chain.isra.39+0x5fc/0x9a0
[  403.118006]        [<ffffffff810d8bc3>] __lock_acquire+0x4d3/0xd30
[  403.118010]        [<ffffffff810d9da7>] lock_acquire+0xa7/0x160
[  403.118014]        [<ffffffff8118c9ec>] might_fault+0x7c/0xb0
[  403.118018]        [<ffffffffa0028a25>] video_usercopy+0x425/0x610 [videodev]
[  403.118028]        [<ffffffffa0028c25>] video_ioctl2+0x15/0x20 [videodev]
[  403.118034]        [<ffffffffa0022764>] v4l2_ioctl+0x184/0x1a0 [videodev]
[  403.118040]        [<ffffffff811d77d0>] do_vfs_ioctl+0x2f0/0x4f0
[  403.118307]        [<ffffffff811d7a51>] SyS_ioctl+0x81/0xa0
[  403.118311]        [<ffffffff8199dc69>] system_call_fastpath+0x16/0x1b
[  403.118319]
[  403.118319] -> #0 (&dev->mutex#3){+.+.+.}:
[  403.118324]        [<ffffffff810d6a96>] check_prevs_add+0x746/0x9f0
[  403.118329]        [<ffffffff810d733c>] validate_chain.isra.39+0x5fc/0x9a0
[  403.118333]        [<ffffffff810d8bc3>] __lock_acquire+0x4d3/0xd30
[  403.118336]        [<ffffffff810d9da7>] lock_acquire+0xa7/0x160
[  403.118340]        [<ffffffff81999664>] mutex_lock_interruptible_nested+0x64/0x640
[  403.118344]        [<ffffffffa005a6c3>] vb2_fop_mmap+0x33/0x90 [videobuf2_core]
[  403.118349]        [<ffffffffa0022122>] v4l2_mmap+0x62/0xa0 [videodev]
[  403.118354]        [<ffffffff81197270>] mmap_region+0x3d0/0x5d0
[  403.118359]        [<ffffffff8119778d>] do_mmap_pgoff+0x31d/0x400
[  403.118363]        [<ffffffff81182940>] vm_mmap_pgoff+0x90/0xc0
[  403.118366]        [<ffffffff81195cef>] SyS_mmap_pgoff+0x1df/0x2a0
[  403.118369]        [<ffffffff810085c2>] SyS_mmap+0x22/0x30
[  403.118376]        [<ffffffff8199dc69>] system_call_fastpath+0x16/0x1b
[  403.118381]
[  403.118381] other info that might help us debug this:
[  403.118381]
[  403.118383]  Possible unsafe locking scenario:
[  403.118383]
[  403.118385]        CPU0                    CPU1
[  403.118387]        ----                    ----
[  403.118388]   lock(&mm->mmap_sem);
[  403.118391]                                lock(&dev->mutex#3);
[  403.118394]                                lock(&mm->mmap_sem);
[  403.118397]   lock(&dev->mutex#3);
[  403.118400]
[  403.118400]  *** DEADLOCK ***
[  403.118400]
[  403.118403] 1 lock held by v4l2-ctl/15377:
[  403.118405]  #0:  (&mm->mmap_sem){++++++}, at: [<ffffffff8118291f>] vm_mmap_pgoff+0x6f/0xc0
[  403.118411]
[  403.118411] stack backtrace:
[  403.118415] CPU: 0 PID: 15377 Comm: v4l2-ctl Not tainted 3.16.0-rc6-test-media #961
[  403.118418] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013
[  403.118420]  ffffffff82a6c9d0 ffff8800af37fb00 ffffffff819916a2 ffffffff82a6c9d0
[  403.118425]  ffff8800af37fb40 ffffffff810d5715 ffff8802308e4200 0000000000000000
[  403.118429]  ffff8802308e4a48 ffff8802308e4a48 ffff8802308e4200 0000000000000001
[  403.118433] Call Trace:
[  403.118441]  [<ffffffff819916a2>] dump_stack+0x4e/0x7a
[  403.118445]  [<ffffffff810d5715>] print_circular_bug+0x1d5/0x2a0
[  403.118449]  [<ffffffff810d6a96>] check_prevs_add+0x746/0x9f0
[  403.118455]  [<ffffffff8119c172>] ? find_vmap_area+0x42/0x70
[  403.118459]  [<ffffffff810d733c>] validate_chain.isra.39+0x5fc/0x9a0
[  403.118463]  [<ffffffff810d8bc3>] __lock_acquire+0x4d3/0xd30
[  403.118468]  [<ffffffff810d9da7>] lock_acquire+0xa7/0x160
[  403.118472]  [<ffffffffa005a6c3>] ? vb2_fop_mmap+0x33/0x90 [videobuf2_core]
[  403.118476]  [<ffffffffa005a6c3>] ? vb2_fop_mmap+0x33/0x90 [videobuf2_core]
[  403.118480]  [<ffffffff81999664>] mutex_lock_interruptible_nested+0x64/0x640
[  403.118484]  [<ffffffffa005a6c3>] ? vb2_fop_mmap+0x33/0x90 [videobuf2_core]
[  403.118488]  [<ffffffffa005a6c3>] ? vb2_fop_mmap+0x33/0x90 [videobuf2_core]
[  403.118493]  [<ffffffff810d8055>] ? mark_held_locks+0x75/0xa0
[  403.118497]  [<ffffffffa005a6c3>] vb2_fop_mmap+0x33/0x90 [videobuf2_core]
[  403.118502]  [<ffffffffa0022122>] v4l2_mmap+0x62/0xa0 [videodev]
[  403.118506]  [<ffffffff81197270>] mmap_region+0x3d0/0x5d0
[  403.118510]  [<ffffffff8119778d>] do_mmap_pgoff+0x31d/0x400
[  403.118513]  [<ffffffff81182940>] vm_mmap_pgoff+0x90/0xc0
[  403.118517]  [<ffffffff81195cef>] SyS_mmap_pgoff+0x1df/0x2a0
[  403.118521]  [<ffffffff810085c2>] SyS_mmap+0x22/0x30
[  403.118525]  [<ffffffff8199dc69>] system_call_fastpath+0x16/0x1b

The reason is that vb2_fop_mmap and vb2_fop_get_unmapped_area take the core lock
while they are called with the mmap_sem semaphore held. But elsewhere in the code
the core lock is taken first but calls to copy_to/from_user() can take the mmap_sem
semaphore as well, potentially causing a classical A-B/B-A deadlock.

However, the mmap/get_unmapped_area calls really shouldn't take the core lock
at all. So what would happen if they don't take the core lock anymore?

There are two situations that need to be taken into account: calling mmap while
new buffers are being added and calling mmap while buffers are being deleted.

The first case works almost fine without a lock: in all cases mmap relies on
correctly filled-in q->num_buffers/q->num_planes values and those are only
updated by reqbufs and create_buffers *after* any new buffers have been
initialized completely. Except in one case: if an error occurred while allocating
the buffers it will increase num_buffers and rely on __vb2_queue_free to
decrease it again. So there is a short period where the buffer information
may be wrong.

The second case definitely does pose a problem: buffers may be in the process
of being deleted, without the internal structure being updated.

In order to fix this a new mutex is added to vb2_queue that is taken when
buffers are allocated or deleted, and in vb2_mmap. That way vb2_mmap won't
get stale buffer data. Note that this is a problem only for MEMORY_MMAP, so
even though __qbuf_userptr and __qbuf_dmabuf also mess around with buffers
(mem_priv in particular), this doesn't clash with vb2_mmap or
vb2_get_unmapped_area since those are MMAP specific.

As an additional bonus the hack in __buf_prepare, the USERPTR case, can be
removed as well since mmap() no longer takes the core lock.

All in all a much cleaner solution.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/v4l2-core/videobuf2-core.c | 56 +++++++++++---------------------
 include/media/videobuf2-core.h           |  2 ++
 2 files changed, 21 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index c359006074a8..eb86913349fc 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -882,7 +882,9 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 		 * We already have buffers allocated, so first check if they
 		 * are not in use and can be freed.
 		 */
+		mutex_lock(&q->mmap_lock);
 		if (q->memory == V4L2_MEMORY_MMAP && __buffers_in_use(q)) {
+			mutex_unlock(&q->mmap_lock);
 			dprintk(1, "memory in use, cannot free\n");
 			return -EBUSY;
 		}
@@ -894,6 +896,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 		 */
 		__vb2_queue_cancel(q);
 		ret = __vb2_queue_free(q, q->num_buffers);
+		mutex_unlock(&q->mmap_lock);
 		if (ret)
 			return ret;
 
@@ -955,6 +958,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 		 */
 	}
 
+	mutex_lock(&q->mmap_lock);
 	q->num_buffers = allocated_buffers;
 
 	if (ret < 0) {
@@ -963,8 +967,10 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 		 * from q->num_buffers.
 		 */
 		__vb2_queue_free(q, allocated_buffers);
+		mutex_unlock(&q->mmap_lock);
 		return ret;
 	}
+	mutex_unlock(&q->mmap_lock);
 
 	/*
 	 * Return the number of successfully allocated buffers
@@ -1061,6 +1067,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create
 		 */
 	}
 
+	mutex_lock(&q->mmap_lock);
 	q->num_buffers += allocated_buffers;
 
 	if (ret < 0) {
@@ -1069,8 +1076,10 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create
 		 * from q->num_buffers.
 		 */
 		__vb2_queue_free(q, allocated_buffers);
+		mutex_unlock(&q->mmap_lock);
 		return -ENOMEM;
 	}
+	mutex_unlock(&q->mmap_lock);
 
 	/*
 	 * Return the number of successfully allocated buffers
@@ -1582,7 +1591,6 @@ static void __enqueue_in_driver(struct vb2_buffer *vb)
 static int __buf_prepare(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 {
 	struct vb2_queue *q = vb->vb2_queue;
-	struct rw_semaphore *mmap_sem;
 	int ret;
 
 	ret = __verify_length(vb, b);
@@ -1619,26 +1627,7 @@ static int __buf_prepare(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 		ret = __qbuf_mmap(vb, b);
 		break;
 	case V4L2_MEMORY_USERPTR:
-		/*
-		 * In case of user pointer buffers vb2 allocators need to get
-		 * direct access to userspace pages. This requires getting
-		 * the mmap semaphore for read access in the current process
-		 * structure. The same semaphore is taken before calling mmap
-		 * operation, while both qbuf/prepare_buf and mmap are called
-		 * by the driver or v4l2 core with the driver's lock held.
-		 * To avoid an AB-BA deadlock (mmap_sem then driver's lock in
-		 * mmap and driver's lock then mmap_sem in qbuf/prepare_buf),
-		 * the videobuf2 core releases the driver's lock, takes
-		 * mmap_sem and then takes the driver's lock again.
-		 */
-		mmap_sem = &current->mm->mmap_sem;
-		call_void_qop(q, wait_prepare, q);
-		down_read(mmap_sem);
-		call_void_qop(q, wait_finish, q);
-
 		ret = __qbuf_userptr(vb, b);
-
-		up_read(mmap_sem);
 		break;
 	case V4L2_MEMORY_DMABUF:
 		ret = __qbuf_dmabuf(vb, b);
@@ -2485,7 +2474,9 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma)
 		return -EINVAL;
 	}
 
+	mutex_lock(&q->mmap_lock);
 	ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma);
+	mutex_unlock(&q->mmap_lock);
 	if (ret)
 		return ret;
 
@@ -2504,6 +2495,7 @@ unsigned long vb2_get_unmapped_area(struct vb2_queue *q,
 	unsigned long off = pgoff << PAGE_SHIFT;
 	struct vb2_buffer *vb;
 	unsigned int buffer, plane;
+	void *vaddr;
 	int ret;
 
 	if (q->memory != V4L2_MEMORY_MMAP) {
@@ -2520,7 +2512,8 @@ unsigned long vb2_get_unmapped_area(struct vb2_queue *q,
 
 	vb = q->bufs[buffer];
 
-	return (unsigned long)vb2_plane_vaddr(vb, plane);
+	vaddr = vb2_plane_vaddr(vb, plane);
+	return vaddr ? (unsigned long)vaddr : -EINVAL;
 }
 EXPORT_SYMBOL_GPL(vb2_get_unmapped_area);
 #endif
@@ -2660,6 +2653,7 @@ int vb2_queue_init(struct vb2_queue *q)
 	INIT_LIST_HEAD(&q->queued_list);
 	INIT_LIST_HEAD(&q->done_list);
 	spin_lock_init(&q->done_lock);
+	mutex_init(&q->mmap_lock);
 	init_waitqueue_head(&q->done_wq);
 
 	if (q->buf_struct_size == 0)
@@ -2681,7 +2675,9 @@ void vb2_queue_release(struct vb2_queue *q)
 {
 	__vb2_cleanup_fileio(q);
 	__vb2_queue_cancel(q);
+	mutex_lock(&q->mmap_lock);
 	__vb2_queue_free(q, q->num_buffers);
+	mutex_unlock(&q->mmap_lock);
 }
 EXPORT_SYMBOL_GPL(vb2_queue_release);
 
@@ -3346,15 +3342,8 @@ EXPORT_SYMBOL_GPL(vb2_ioctl_expbuf);
 int vb2_fop_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct video_device *vdev = video_devdata(file);
-	struct mutex *lock = vdev->queue->lock ? vdev->queue->lock : vdev->lock;
-	int err;
 
-	if (lock && mutex_lock_interruptible(lock))
-		return -ERESTARTSYS;
-	err = vb2_mmap(vdev->queue, vma);
-	if (lock)
-		mutex_unlock(lock);
-	return err;
+	return vb2_mmap(vdev->queue, vma);
 }
 EXPORT_SYMBOL_GPL(vb2_fop_mmap);
 
@@ -3473,15 +3462,8 @@ unsigned long vb2_fop_get_unmapped_area(struct file *file, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
 	struct video_device *vdev = video_devdata(file);
-	struct mutex *lock = vdev->queue->lock ? vdev->queue->lock : vdev->lock;
-	int ret;
 
-	if (lock && mutex_lock_interruptible(lock))
-		return -ERESTARTSYS;
-	ret = vb2_get_unmapped_area(vdev->queue, addr, len, pgoff, flags);
-	if (lock)
-		mutex_unlock(lock);
-	return ret;
+	return vb2_get_unmapped_area(vdev->queue, addr, len, pgoff, flags);
 }
 EXPORT_SYMBOL_GPL(vb2_fop_get_unmapped_area);
 #endif
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index fc910a622451..5a10d8d695b4 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -366,6 +366,7 @@ struct v4l2_fh;
  *		cannot be started unless at least this number of buffers
  *		have been queued into the driver.
  *
+ * @mmap_lock:	private mutex used when buffers are allocated/freed/mmapped
  * @memory:	current memory type used
  * @bufs:	videobuf buffer structures
  * @num_buffers: number of allocated/used buffers
@@ -399,6 +400,7 @@ struct vb2_queue {
 	u32				min_buffers_needed;
 
 /* private: internal use only */
+	struct mutex			mmap_lock;
 	enum v4l2_memory		memory;
 	struct vb2_buffer		*bufs[VIDEO_MAX_FRAME];
 	unsigned int			num_buffers;
-- 
cgit v1.2.3


From c200b1aa6cb460ce8c3ecf6fdc690d3949c3cc5d Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Wed, 20 Aug 2014 18:36:46 +0800
Subject: f2fs: fix incorrect calculation with total/free inode num

Theoretically, our total inodes number is the same as total node number, but
there are three node ids are reserved in f2fs, they are 0, 1 (node nid), and 2
(meta nid), and they should never be used by user, so our total/free inode
number calculated in ->statfs is wrong.

This patch indroduces F2FS_RESERVED_NODE_NUM and then fixes this issue by
recalculating total/free inode number with the macro.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/node.c          | 2 +-
 fs/f2fs/super.c         | 4 ++--
 include/linux/f2fs_fs.h | 3 +++
 3 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index b4d964029fc7..044395c20ee9 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1957,7 +1957,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
 
 	/* not used nids: 0, node, meta, (and root counted as valid node) */
-	nm_i->available_nids = nm_i->max_nid - 3;
+	nm_i->available_nids = nm_i->max_nid - F2FS_RESERVED_NODE_NUM;
 	nm_i->fcnt = 0;
 	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index ddb1e9d36363..0f61f5aa587c 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -508,8 +508,8 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
 	buf->f_bavail = user_block_count - valid_user_blocks(sbi);
 
-	buf->f_files = sbi->total_node_count;
-	buf->f_ffree = sbi->total_node_count - valid_inode_count(sbi);
+	buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
+	buf->f_ffree = buf->f_files - valid_inode_count(sbi);
 
 	buf->f_namelen = F2FS_NAME_LEN;
 	buf->f_fsid.val[0] = (u32)id;
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 6ff0b0b42d47..0ed77f32c9ac 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -24,6 +24,9 @@
 #define NULL_ADDR		((block_t)0)	/* used as block_t addresses */
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
 
+/* 0, 1(node nid), 2(meta nid) are reserved node id */
+#define F2FS_RESERVED_NODE_NUM		3
+
 #define F2FS_ROOT_INO(sbi)	(sbi->root_ino_num)
 #define F2FS_NODE_INO(sbi)	(sbi->node_ino_num)
 #define F2FS_META_INO(sbi)	(sbi->meta_ino_num)
-- 
cgit v1.2.3


From 8913dc0bb913ac3dc83ed5c10bac2f4e55431981 Mon Sep 17 00:00:00 2001
From: Paul Zimmerman <Paul.Zimmerman@synopsys.com>
Date: Thu, 21 Aug 2014 20:28:20 +0000
Subject: usb: gadget: document a usb_ep_dequeue() requirement

Document the requirement that the request be dequeued and its
completion routine called before usb_ep_dequeue() returns. Also
fix some capitalization issues in the existing text.

Signed-off-by: Paul Zimmerman <paulz@synopsys.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/linux/usb/gadget.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index c3a61853cd13..c540557b564b 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -345,12 +345,13 @@ static inline int usb_ep_queue(struct usb_ep *ep,
  * @ep:the endpoint associated with the request
  * @req:the request being canceled
  *
- * if the request is still active on the endpoint, it is dequeued and its
+ * If the request is still active on the endpoint, it is dequeued and its
  * completion routine is called (with status -ECONNRESET); else a negative
- * error code is returned.
+ * error code is returned. This is guaranteed to happen before the call to
+ * usb_ep_dequeue() returns.
  *
- * note that some hardware can't clear out write fifos (to unlink the request
- * at the head of the queue) except as part of disconnecting from usb.  such
+ * Note that some hardware can't clear out write fifos (to unlink the request
+ * at the head of the queue) except as part of disconnecting from usb. Such
  * restrictions prevent drivers from supporting configuration changes,
  * even to configuration zero (a "chapter 9" requirement).
  */
-- 
cgit v1.2.3


From da076a888ab19f13816372796ed231e7d6ff5fed Mon Sep 17 00:00:00 2001
From: Mikhail Ulyanov <mikhail.ulyanov@cogentembedded.com>
Date: Tue, 19 Aug 2014 16:50:49 +0400
Subject: ARM: shmobile: r8a7790: Add JPU clock dt and CPG define.

Signed-off-by: Mikhail Ulyanov <mikhail.ulyanov@cogentembedded.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7790.dtsi            | 6 +++---
 include/dt-bindings/clock/r8a7790-clock.h | 1 +
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 2278bd0968d1..c11541d6dc25 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -836,17 +836,17 @@
 		mstp1_clks: mstp1_clks@e6150134 {
 			compatible = "renesas,r8a7790-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
-			clocks = <&p_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
+			clocks = <&m2_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
 				 <&cp_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>,
 				 <&zs_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7790_CLK_TMU1 R8A7790_CLK_TMU3 R8A7790_CLK_TMU2
+				R8A7790_CLK_JPU R8A7790_CLK_TMU1 R8A7790_CLK_TMU3 R8A7790_CLK_TMU2
 				R8A7790_CLK_CMT0 R8A7790_CLK_TMU0 R8A7790_CLK_VSP1_DU1
 				R8A7790_CLK_VSP1_DU0 R8A7790_CLK_VSP1_R R8A7790_CLK_VSP1_S
 			>;
 			clock-output-names =
-				"tmu1", "tmu3", "tmu2", "cmt0", "tmu0", "vsp1-du1",
+				"jpu", "tmu1", "tmu3", "tmu2", "cmt0", "tmu0", "vsp1-du1",
 				"vsp1-du0", "vsp1-rt", "vsp1-sy";
 		};
 		mstp2_clks: mstp2_clks@e6150138 {
diff --git a/include/dt-bindings/clock/r8a7790-clock.h b/include/dt-bindings/clock/r8a7790-clock.h
index f929a79e6998..8ea7ab0346ad 100644
--- a/include/dt-bindings/clock/r8a7790-clock.h
+++ b/include/dt-bindings/clock/r8a7790-clock.h
@@ -26,6 +26,7 @@
 #define R8A7790_CLK_MSIOF0		0
 
 /* MSTP1 */
+#define R8A7790_CLK_JPU		6
 #define R8A7790_CLK_TMU1		11
 #define R8A7790_CLK_TMU3		21
 #define R8A7790_CLK_TMU2		22
-- 
cgit v1.2.3


From ed48b5d6fd339d145df5a6a1e48cf56ef265cf4f Mon Sep 17 00:00:00 2001
From: Mikhail Ulyanov <mikhail.ulyanov@cogentembedded.com>
Date: Tue, 19 Aug 2014 16:50:51 +0400
Subject: ARM: shmobile: r8a7791: Add JPU clock dt and CPG define.

Signed-off-by: Mikhail Ulyanov <mikhail.ulyanov@cogentembedded.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7791.dtsi            | 6 +++---
 include/dt-bindings/clock/r8a7791-clock.h | 1 +
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index f26226e054b3..d62c237e137d 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -857,16 +857,16 @@
 		mstp1_clks: mstp1_clks@e6150134 {
 			compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
-			clocks = <&p_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
+			clocks = <&m2_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
 				 <&cp_clk>, <&zs_clk>, <&zs_clk>, <&zs_clk>;
 			#clock-cells = <1>;
 			renesas,clock-indices = <
-				R8A7791_CLK_TMU1 R8A7791_CLK_TMU3 R8A7791_CLK_TMU2
+				R8A7791_CLK_JPU R8A7791_CLK_TMU1 R8A7791_CLK_TMU3 R8A7791_CLK_TMU2
 				R8A7791_CLK_CMT0 R8A7791_CLK_TMU0 R8A7791_CLK_VSP1_DU1
 				R8A7791_CLK_VSP1_DU0 R8A7791_CLK_VSP1_S
 			>;
 			clock-output-names =
-				"tmu1", "tmu3", "tmu2", "cmt0", "tmu0", "vsp1-du1",
+				"jpu", "tmu1", "tmu3", "tmu2", "cmt0", "tmu0", "vsp1-du1",
 				"vsp1-du0", "vsp1-sy";
 		};
 		mstp2_clks: mstp2_clks@e6150138 {
diff --git a/include/dt-bindings/clock/r8a7791-clock.h b/include/dt-bindings/clock/r8a7791-clock.h
index f0d4d1049162..58c3f49d068c 100644
--- a/include/dt-bindings/clock/r8a7791-clock.h
+++ b/include/dt-bindings/clock/r8a7791-clock.h
@@ -25,6 +25,7 @@
 #define R8A7791_CLK_MSIOF0		0
 
 /* MSTP1 */
+#define R8A7791_CLK_JPU		6
 #define R8A7791_CLK_TMU1		11
 #define R8A7791_CLK_TMU3		21
 #define R8A7791_CLK_TMU2		22
-- 
cgit v1.2.3


From d6fb17ad7c9e0aa28ce0bc2e33790f9459677370 Mon Sep 17 00:00:00 2001
From: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Date: Fri, 8 Aug 2014 16:23:09 +0200
Subject: ARM: shmobile: r8a7740: clock register bits

Contains the header file with the clock pulse generator and MSTP bits.

Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 include/dt-bindings/clock/r8a7740-clock.h | 77 +++++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)
 create mode 100644 include/dt-bindings/clock/r8a7740-clock.h

(limited to 'include')

diff --git a/include/dt-bindings/clock/r8a7740-clock.h b/include/dt-bindings/clock/r8a7740-clock.h
new file mode 100644
index 000000000000..f6b4b0fe7a43
--- /dev/null
+++ b/include/dt-bindings/clock/r8a7740-clock.h
@@ -0,0 +1,77 @@
+/*
+ * Copyright 2014 Ulrich Hecht
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_R8A7740_H__
+#define __DT_BINDINGS_CLOCK_R8A7740_H__
+
+/* CPG */
+#define R8A7740_CLK_SYSTEM	0
+#define R8A7740_CLK_PLLC0	1
+#define R8A7740_CLK_PLLC1	2
+#define R8A7740_CLK_PLLC2	3
+#define R8A7740_CLK_R		4
+#define R8A7740_CLK_USB24S	5
+#define R8A7740_CLK_I		6
+#define R8A7740_CLK_ZG		7
+#define R8A7740_CLK_B		8
+#define R8A7740_CLK_M1		9
+#define R8A7740_CLK_HP		10
+#define R8A7740_CLK_HPP		11
+#define R8A7740_CLK_USBP	12
+#define R8A7740_CLK_S		13
+#define R8A7740_CLK_ZB		14
+#define R8A7740_CLK_M3		15
+#define R8A7740_CLK_CP		16
+
+/* MSTP1 */
+#define R8A7740_CLK_CEU21	28
+#define R8A7740_CLK_CEU20	27
+#define R8A7740_CLK_TMU0	25
+#define R8A7740_CLK_LCDC1	17
+#define R8A7740_CLK_IIC0	16
+#define R8A7740_CLK_TMU1	11
+#define R8A7740_CLK_LCDC0	0
+
+/* MSTP2 */
+#define R8A7740_CLK_SCIFA6	30
+#define R8A7740_CLK_SCIFA7	22
+#define R8A7740_CLK_DMAC1	18
+#define R8A7740_CLK_DMAC2	17
+#define R8A7740_CLK_DMAC3	16
+#define R8A7740_CLK_USBDMAC	14
+#define R8A7740_CLK_SCIFA5	7
+#define R8A7740_CLK_SCIFB	6
+#define R8A7740_CLK_SCIFA0	4
+#define R8A7740_CLK_SCIFA1	3
+#define R8A7740_CLK_SCIFA2	2
+#define R8A7740_CLK_SCIFA3	1
+#define R8A7740_CLK_SCIFA4	0
+
+/* MSTP3 */
+#define R8A7740_CLK_CMT1	29
+#define R8A7740_CLK_FSI		28
+#define R8A7740_CLK_IIC1	23
+#define R8A7740_CLK_USBF	20
+#define R8A7740_CLK_SDHI0	14
+#define R8A7740_CLK_SDHI1	13
+#define R8A7740_CLK_MMC		12
+#define R8A7740_CLK_GETHER	9
+#define R8A7740_CLK_TPU0	4
+
+/* MSTP4 */
+#define R8A7740_CLK_USBH	16
+#define R8A7740_CLK_SDHI2	15
+#define R8A7740_CLK_USBFUNC	7
+#define R8A7740_CLK_USBPHY	6
+
+/* SUBCK* */
+#define R8A7740_CLK_SUBCK	9
+#define R8A7740_CLK_SUBCK2	10
+
+#endif /* __DT_BINDINGS_CLOCK_R8A7740_H__ */
-- 
cgit v1.2.3


From 6dc14baf4ced769017c7a7045019c7a19f373865 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 21 Aug 2014 10:41:42 -0400
Subject: drm/radeon: add new KV pci id

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=82912

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/radeon/cik.c | 1 +
 include/drm/drm_pciids.h     | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index f4e14702639d..79a5a5519bd6 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3544,6 +3544,7 @@ static void cik_gpu_init(struct radeon_device *rdev)
 			   (rdev->pdev->device == 0x130B) ||
 			   (rdev->pdev->device == 0x130E) ||
 			   (rdev->pdev->device == 0x1315) ||
+			   (rdev->pdev->device == 0x1318) ||
 			   (rdev->pdev->device == 0x131B)) {
 			rdev->config.cik.max_cu_per_sh = 4;
 			rdev->config.cik.max_backends_per_se = 1;
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 6dfd64b3a604..3a9281b2f792 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -17,6 +17,7 @@
 	{0x1002, 0x1315, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x1316, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x1317, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x1318, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x131B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x131C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x131D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
-- 
cgit v1.2.3


From 5fc540edc8ea1297c76685f74bc82a2107fe6731 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 21 Aug 2014 10:48:11 -0400
Subject: drm/radeon: add new bonaire pci ids

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 include/drm/drm_pciids.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 3a9281b2f792..b75b9a572222 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -176,6 +176,8 @@
 	{0x1002, 0x6631, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6640, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6641, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6646, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6650, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6651, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
-- 
cgit v1.2.3


From 37dbeab788a8f23fd946c0be083e5484d6f929a1 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 21 Aug 2014 10:55:07 -0400
Subject: drm/radeon: add additional SI pci ids

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 include/drm/drm_pciids.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index b75b9a572222..e973540cd15b 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -165,8 +165,11 @@
 	{0x1002, 0x6601, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6602, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6603, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6604, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6605, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6606, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6607, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6608, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
@@ -300,6 +303,7 @@
 	{0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x682C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
-- 
cgit v1.2.3


From 33b7f99cf003ca6c1d31c42b50e1100ad71aaec0 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 15 Aug 2014 17:23:02 -0400
Subject: ftrace: Allow ftrace_ops to use the hashes from other ops

Currently the top level debug file system function tracer shares its
ftrace_ops with the function graph tracer. This was thought to be fine
because the tracers are not used together, as one can only enable
function or function_graph tracer in the current_tracer file.

But that assumption proved to be incorrect. The function profiler
can use the function graph tracer when function tracing is enabled.
Since all function graph users uses the function tracing ftrace_ops
this causes a conflict and when a user enables both function profiling
as well as the function tracer it will crash ftrace and disable it.

The quick solution so far is to move them as separate ftrace_ops like
it was earlier. The problem though is to synchronize the functions that
are traced because both function and function_graph tracer are limited
by the selections made in the set_ftrace_filter and set_ftrace_notrace
files.

To handle this, a new structure is made called ftrace_ops_hash. This
structure will now hold the filter_hash and notrace_hash, and the
ftrace_ops will point to this structure. That will allow two ftrace_ops
to share the same hashes.

Since most ftrace_ops do not share the hashes, and to keep allocation
simple, the ftrace_ops structure will include both a pointer to the
ftrace_ops_hash called func_hash, as well as the structure itself,
called local_hash. When the ops are registered, the func_hash pointer
will be initialized to point to the local_hash within the ftrace_ops
structure. Some of the ftrace internal ftrace_ops will be initialized
statically. This will allow for the function and function_graph tracer
to have separate ops but still share the same hash tables that determine
what functions they trace.

Cc: stable@vger.kernel.org # 3.16 (apply after 3.17-rc4 is out)
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  14 +++++--
 kernel/trace/ftrace.c  | 100 +++++++++++++++++++++++++------------------------
 2 files changed, 63 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 6bb5e3f2a3b4..f0b0edbf55a9 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -102,6 +102,15 @@ enum {
 	FTRACE_OPS_FL_DELETED			= 1 << 8,
 };
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+/* The hash used to know what functions callbacks trace */
+struct ftrace_ops_hash {
+	struct ftrace_hash		*notrace_hash;
+	struct ftrace_hash		*filter_hash;
+	struct mutex			regex_lock;
+};
+#endif
+
 /*
  * Note, ftrace_ops can be referenced outside of RCU protection.
  * (Although, for perf, the control ops prevent that). If ftrace_ops is
@@ -121,10 +130,9 @@ struct ftrace_ops {
 	int __percpu			*disabled;
 #ifdef CONFIG_DYNAMIC_FTRACE
 	int				nr_trampolines;
-	struct ftrace_hash		*notrace_hash;
-	struct ftrace_hash		*filter_hash;
+	struct ftrace_ops_hash		local_hash;
+	struct ftrace_ops_hash		*func_hash;
 	struct ftrace_hash		*tramp_hash;
-	struct mutex			regex_lock;
 	unsigned long			trampoline;
 #endif
 };
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1654b12c891a..c92757adba79 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -65,15 +65,17 @@
 #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_CONTROL)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-#define INIT_REGEX_LOCK(opsname)	\
-	.regex_lock	= __MUTEX_INITIALIZER(opsname.regex_lock),
+#define INIT_OPS_HASH(opsname)	\
+	.func_hash		= &opsname.local_hash,			\
+	.local_hash.regex_lock	= __MUTEX_INITIALIZER(opsname.local_hash.regex_lock),
 #else
-#define INIT_REGEX_LOCK(opsname)
+#define INIT_OPS_HASH(opsname)
 #endif
 
 static struct ftrace_ops ftrace_list_end __read_mostly = {
 	.func		= ftrace_stub,
 	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB,
+	INIT_OPS_HASH(ftrace_list_end)
 };
 
 /* ftrace_enabled is a method to turn ftrace on or off */
@@ -140,7 +142,8 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops)
 {
 #ifdef CONFIG_DYNAMIC_FTRACE
 	if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) {
-		mutex_init(&ops->regex_lock);
+		mutex_init(&ops->local_hash.regex_lock);
+		ops->func_hash = &ops->local_hash;
 		ops->flags |= FTRACE_OPS_FL_INITIALIZED;
 	}
 #endif
@@ -899,7 +902,7 @@ static void unregister_ftrace_profiler(void)
 static struct ftrace_ops ftrace_profile_ops __read_mostly = {
 	.func		= function_profile_call,
 	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(ftrace_profile_ops)
+	INIT_OPS_HASH(ftrace_profile_ops)
 };
 
 static int register_ftrace_profiler(void)
@@ -1081,11 +1084,12 @@ static const struct ftrace_hash empty_hash = {
 #define EMPTY_HASH	((struct ftrace_hash *)&empty_hash)
 
 static struct ftrace_ops global_ops = {
-	.func			= ftrace_stub,
-	.notrace_hash		= EMPTY_HASH,
-	.filter_hash		= EMPTY_HASH,
-	.flags			= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(global_ops)
+	.func				= ftrace_stub,
+	.local_hash.notrace_hash	= EMPTY_HASH,
+	.local_hash.filter_hash		= EMPTY_HASH,
+	INIT_OPS_HASH(global_ops)
+	.flags				= FTRACE_OPS_FL_RECURSION_SAFE |
+					  FTRACE_OPS_FL_INITIALIZED,
 };
 
 struct ftrace_page {
@@ -1226,8 +1230,8 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
 void ftrace_free_filter(struct ftrace_ops *ops)
 {
 	ftrace_ops_init(ops);
-	free_ftrace_hash(ops->filter_hash);
-	free_ftrace_hash(ops->notrace_hash);
+	free_ftrace_hash(ops->func_hash->filter_hash);
+	free_ftrace_hash(ops->func_hash->notrace_hash);
 }
 
 static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
@@ -1382,8 +1386,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 		return 0;
 #endif
 
-	filter_hash = rcu_dereference_raw_notrace(ops->filter_hash);
-	notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash);
+	filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash);
+	notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash);
 
 	if ((ftrace_hash_empty(filter_hash) ||
 	     ftrace_lookup_ip(filter_hash, ip)) &&
@@ -1554,14 +1558,14 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 	 *   gets inversed.
 	 */
 	if (filter_hash) {
-		hash = ops->filter_hash;
-		other_hash = ops->notrace_hash;
+		hash = ops->func_hash->filter_hash;
+		other_hash = ops->func_hash->notrace_hash;
 		if (ftrace_hash_empty(hash))
 			all = 1;
 	} else {
 		inc = !inc;
-		hash = ops->notrace_hash;
-		other_hash = ops->filter_hash;
+		hash = ops->func_hash->notrace_hash;
+		other_hash = ops->func_hash->filter_hash;
 		/*
 		 * If the notrace hash has no items,
 		 * then there's nothing to do.
@@ -2436,8 +2440,8 @@ static inline int ops_traces_mod(struct ftrace_ops *ops)
 	 * Filter_hash being empty will default to trace module.
 	 * But notrace hash requires a test of individual module functions.
 	 */
-	return ftrace_hash_empty(ops->filter_hash) &&
-		ftrace_hash_empty(ops->notrace_hash);
+	return ftrace_hash_empty(ops->func_hash->filter_hash) &&
+		ftrace_hash_empty(ops->func_hash->notrace_hash);
 }
 
 /*
@@ -2459,12 +2463,12 @@ ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
 		return 0;
 
 	/* The function must be in the filter */
-	if (!ftrace_hash_empty(ops->filter_hash) &&
-	    !ftrace_lookup_ip(ops->filter_hash, rec->ip))
+	if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
+	    !ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))
 		return 0;
 
 	/* If in notrace hash, we ignore it too */
-	if (ftrace_lookup_ip(ops->notrace_hash, rec->ip))
+	if (ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip))
 		return 0;
 
 	return 1;
@@ -2785,10 +2789,10 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 	} else {
 		rec = &iter->pg->records[iter->idx++];
 		if (((iter->flags & FTRACE_ITER_FILTER) &&
-		     !(ftrace_lookup_ip(ops->filter_hash, rec->ip))) ||
+		     !(ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))) ||
 
 		    ((iter->flags & FTRACE_ITER_NOTRACE) &&
-		     !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) ||
+		     !ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) ||
 
 		    ((iter->flags & FTRACE_ITER_ENABLED) &&
 		     !(rec->flags & FTRACE_FL_ENABLED))) {
@@ -2837,9 +2841,9 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 	 * functions are enabled.
 	 */
 	if ((iter->flags & FTRACE_ITER_FILTER &&
-	     ftrace_hash_empty(ops->filter_hash)) ||
+	     ftrace_hash_empty(ops->func_hash->filter_hash)) ||
 	    (iter->flags & FTRACE_ITER_NOTRACE &&
-	     ftrace_hash_empty(ops->notrace_hash))) {
+	     ftrace_hash_empty(ops->func_hash->notrace_hash))) {
 		if (*pos > 0)
 			return t_hash_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
@@ -3001,12 +3005,12 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 	iter->ops = ops;
 	iter->flags = flag;
 
-	mutex_lock(&ops->regex_lock);
+	mutex_lock(&ops->func_hash->regex_lock);
 
 	if (flag & FTRACE_ITER_NOTRACE)
-		hash = ops->notrace_hash;
+		hash = ops->func_hash->notrace_hash;
 	else
-		hash = ops->filter_hash;
+		hash = ops->func_hash->filter_hash;
 
 	if (file->f_mode & FMODE_WRITE) {
 		const int size_bits = FTRACE_HASH_DEFAULT_BITS;
@@ -3041,7 +3045,7 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 		file->private_data = iter;
 
  out_unlock:
-	mutex_unlock(&ops->regex_lock);
+	mutex_unlock(&ops->func_hash->regex_lock);
 
 	return ret;
 }
@@ -3279,7 +3283,7 @@ static struct ftrace_ops trace_probe_ops __read_mostly =
 {
 	.func		= function_trace_probe_call,
 	.flags		= FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(trace_probe_ops)
+	INIT_OPS_HASH(trace_probe_ops)
 };
 
 static int ftrace_probe_registered;
@@ -3342,7 +3346,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 			      void *data)
 {
 	struct ftrace_func_probe *entry;
-	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
 	struct ftrace_hash *hash;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
@@ -3359,7 +3363,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	if (WARN_ON(not))
 		return -EINVAL;
 
-	mutex_lock(&trace_probe_ops.regex_lock);
+	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
 	if (!hash) {
@@ -3428,7 +3432,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
  out_unlock:
 	mutex_unlock(&ftrace_lock);
  out:
-	mutex_unlock(&trace_probe_ops.regex_lock);
+	mutex_unlock(&trace_probe_ops.func_hash->regex_lock);
 	free_ftrace_hash(hash);
 
 	return count;
@@ -3446,7 +3450,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	struct ftrace_func_entry *rec_entry;
 	struct ftrace_func_probe *entry;
 	struct ftrace_func_probe *p;
-	struct ftrace_hash **orig_hash = &trace_probe_ops.filter_hash;
+	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
 	struct list_head free_list;
 	struct ftrace_hash *hash;
 	struct hlist_node *tmp;
@@ -3468,7 +3472,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 			return;
 	}
 
-	mutex_lock(&trace_probe_ops.regex_lock);
+	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
 	if (!hash)
@@ -3521,7 +3525,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	mutex_unlock(&ftrace_lock);
 		
  out_unlock:
-	mutex_unlock(&trace_probe_ops.regex_lock);
+	mutex_unlock(&trace_probe_ops.func_hash->regex_lock);
 	free_ftrace_hash(hash);
 }
 
@@ -3717,12 +3721,12 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
-	mutex_lock(&ops->regex_lock);
+	mutex_lock(&ops->func_hash->regex_lock);
 
 	if (enable)
-		orig_hash = &ops->filter_hash;
+		orig_hash = &ops->func_hash->filter_hash;
 	else
-		orig_hash = &ops->notrace_hash;
+		orig_hash = &ops->func_hash->notrace_hash;
 
 	if (reset)
 		hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
@@ -3752,7 +3756,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 	mutex_unlock(&ftrace_lock);
 
  out_regex_unlock:
-	mutex_unlock(&ops->regex_lock);
+	mutex_unlock(&ops->func_hash->regex_lock);
 
 	free_ftrace_hash(hash);
 	return ret;
@@ -3975,15 +3979,15 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 
 	trace_parser_put(parser);
 
-	mutex_lock(&iter->ops->regex_lock);
+	mutex_lock(&iter->ops->func_hash->regex_lock);
 
 	if (file->f_mode & FMODE_WRITE) {
 		filter_hash = !!(iter->flags & FTRACE_ITER_FILTER);
 
 		if (filter_hash)
-			orig_hash = &iter->ops->filter_hash;
+			orig_hash = &iter->ops->func_hash->filter_hash;
 		else
-			orig_hash = &iter->ops->notrace_hash;
+			orig_hash = &iter->ops->func_hash->notrace_hash;
 
 		mutex_lock(&ftrace_lock);
 		ret = ftrace_hash_move(iter->ops, filter_hash,
@@ -3994,7 +3998,7 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 		mutex_unlock(&ftrace_lock);
 	}
 
-	mutex_unlock(&iter->ops->regex_lock);
+	mutex_unlock(&iter->ops->func_hash->regex_lock);
 	free_ftrace_hash(iter->hash);
 	kfree(iter);
 
@@ -4611,7 +4615,7 @@ void __init ftrace_init(void)
 static struct ftrace_ops global_ops = {
 	.func			= ftrace_stub,
 	.flags			= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(global_ops)
+	INIT_OPS_HASH(global_ops)
 };
 
 static int __init ftrace_nodyn_init(void)
@@ -4713,7 +4717,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 static struct ftrace_ops control_ops = {
 	.func	= ftrace_ops_control_func,
 	.flags	= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
-	INIT_REGEX_LOCK(control_ops)
+	INIT_OPS_HASH(control_ops)
 };
 
 static inline void
-- 
cgit v1.2.3


From d4261e5650004d6d51137553ea5433d5828562dc Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Tue, 19 Aug 2014 16:02:12 +0200
Subject: bonding: create netlink event when bonding option is changed

Userspace needs to be notified if one changes some option.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Veaceslav Falico <vfalico@gmail.com>
Acked-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 2 ++
 include/linux/netdevice.h          | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index dc73463c2c23..d8dc17faa6b4 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -625,6 +625,8 @@ int __bond_opt_set(struct bonding *bond,
 out:
 	if (ret)
 		bond_opt_error_interpret(bond, opt, ret, val);
+	else
+		call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev);
 
 	return ret;
 }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 38377392d082..7e2b0b8b5cd7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1982,6 +1982,7 @@ struct pcpu_sw_netstats {
 #define NETDEV_CHANGEUPPER	0x0015
 #define NETDEV_RESEND_IGMP	0x0016
 #define NETDEV_PRECHANGEMTU	0x0017 /* notify before mtu change happened */
+#define NETDEV_CHANGEINFODATA	0x0018
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
-- 
cgit v1.2.3


From b5b822050ca3c4fc1f475100cc197cc00ba2d492 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Fri, 22 Aug 2014 16:17:38 +0800
Subject: f2fs: use macro for code readability

This patch introduces DEF_NIDS_PER_INODE/GET_ORPHAN_BLOCKS/F2FS_CP_PACKS macro
instead of numbers in code for readability.

change log from v1:
 o fix typo pointed out by Jaegeuk Kim.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c    | 21 ++++++++++-----------
 include/linux/f2fs_fs.h | 13 ++++++++++---
 2 files changed, 20 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index c9c08d52ecfd..ec3b7a5381fa 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -443,8 +443,8 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 	struct f2fs_orphan_block *orphan_blk = NULL;
 	unsigned int nentries = 0;
 	unsigned short index;
-	unsigned short orphan_blocks = (unsigned short)((sbi->n_orphans +
-		(F2FS_ORPHANS_PER_BLOCK - 1)) / F2FS_ORPHANS_PER_BLOCK);
+	unsigned short orphan_blocks =
+			(unsigned short)GET_ORPHAN_BLOCKS(sbi->n_orphans);
 	struct page *page = NULL;
 	struct ino_entry *orphan = NULL;
 
@@ -837,7 +837,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi));
 	ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
 	ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
-	for (i = 0; i < 3; i++) {
+	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
 		ckpt->cur_node_segno[i] =
 			cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_NODE));
 		ckpt->cur_node_blkoff[i] =
@@ -845,7 +845,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 		ckpt->alloc_type[i + CURSEG_HOT_NODE] =
 				curseg_alloc_type(sbi, i + CURSEG_HOT_NODE);
 	}
-	for (i = 0; i < 3; i++) {
+	for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
 		ckpt->cur_data_segno[i] =
 			cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_DATA));
 		ckpt->cur_data_blkoff[i] =
@@ -860,24 +860,23 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 
 	/* 2 cp  + n data seg summary + orphan inode blocks */
 	data_sum_blocks = npages_for_summary_flush(sbi);
-	if (data_sum_blocks < 3)
+	if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
 		set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 	else
 		clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 
-	orphan_blocks = (sbi->n_orphans + F2FS_ORPHANS_PER_BLOCK - 1)
-					/ F2FS_ORPHANS_PER_BLOCK;
+	orphan_blocks = GET_ORPHAN_BLOCKS(sbi->n_orphans);
 	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
 			orphan_blocks);
 
 	if (is_umount) {
 		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
-		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
+		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks + NR_CURSEG_NODE_TYPE);
 	} else {
 		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
-		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
+		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks);
 	}
@@ -1022,8 +1021,8 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi)
 	 * for cp pack we can have max 1020*504 orphan entries
 	 */
 	sbi->n_orphans = 0;
-	sbi->max_orphans = (sbi->blocks_per_seg - 2 - NR_CURSEG_TYPE)
-				* F2FS_ORPHANS_PER_BLOCK;
+	sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
+			NR_CURSEG_TYPE) * F2FS_ORPHANS_PER_BLOCK;
 }
 
 int __init create_checkpoint_caches(void)
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 0ed77f32c9ac..08ed2b0a96e6 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -90,6 +90,8 @@ struct f2fs_super_block {
 #define CP_ORPHAN_PRESENT_FLAG	0x00000002
 #define CP_UMOUNT_FLAG		0x00000001
 
+#define F2FS_CP_PACKS		2	/* # of checkpoint packs */
+
 struct f2fs_checkpoint {
 	__le64 checkpoint_ver;		/* checkpoint block version number */
 	__le64 user_block_count;	/* # of user blocks */
@@ -126,6 +128,9 @@ struct f2fs_checkpoint {
  */
 #define F2FS_ORPHANS_PER_BLOCK	1020
 
+#define GET_ORPHAN_BLOCKS(n)	((n + F2FS_ORPHANS_PER_BLOCK - 1) / \
+					F2FS_ORPHANS_PER_BLOCK)
+
 struct f2fs_orphan_block {
 	__le32 ino[F2FS_ORPHANS_PER_BLOCK];	/* inode numbers */
 	__le32 reserved;	/* reserved */
@@ -147,6 +152,7 @@ struct f2fs_extent {
 #define F2FS_NAME_LEN		255
 #define F2FS_INLINE_XATTR_ADDRS	50	/* 200 bytes for inline xattrs */
 #define DEF_ADDRS_PER_INODE	923	/* Address Pointers in an Inode */
+#define DEF_NIDS_PER_INODE	5	/* Node IDs in an Inode */
 #define ADDRS_PER_INODE(fi)	addrs_per_inode(fi)
 #define ADDRS_PER_BLOCK		1018	/* Address Pointers in a Direct Block */
 #define NIDS_PER_BLOCK		1018	/* Node IDs in an Indirect Block */
@@ -166,8 +172,9 @@ struct f2fs_extent {
 #define MAX_INLINE_DATA		(sizeof(__le32) * (DEF_ADDRS_PER_INODE - \
 						F2FS_INLINE_XATTR_ADDRS - 1))
 
-#define INLINE_DATA_OFFSET	(PAGE_CACHE_SIZE - sizeof(struct node_footer) \
-			- sizeof(__le32) * (DEF_ADDRS_PER_INODE + 5 - 1))
+#define INLINE_DATA_OFFSET	(PAGE_CACHE_SIZE - sizeof(struct node_footer) -\
+				sizeof(__le32) * (DEF_ADDRS_PER_INODE + \
+				DEF_NIDS_PER_INODE - 1))
 
 struct f2fs_inode {
 	__le16 i_mode;			/* file mode */
@@ -197,7 +204,7 @@ struct f2fs_inode {
 
 	__le32 i_addr[DEF_ADDRS_PER_INODE];	/* Pointers to data blocks */
 
-	__le32 i_nid[5];		/* direct(2), indirect(2),
+	__le32 i_nid[DEF_NIDS_PER_INODE];	/* direct(2), indirect(2),
 						double_indirect(1) node id */
 } __packed;
 
-- 
cgit v1.2.3


From 7c3af975257383ece54b83c0505d3e0656cb7daf Mon Sep 17 00:00:00 2001
From: Weston Andros Adamson <dros@primarydata.com>
Date: Fri, 8 Aug 2014 11:00:57 -0400
Subject: nfs: don't sleep with inode lock in lock_and_join_requests

This handles the 'nonblock=false' case in nfs_lock_and_join_requests.
If the group is already locked and blocking is allowed, drop the inode lock
and wait for the group lock to be cleared before trying it all again.
This should fix warnings found in peterz's tree (sched/wait branch), where
might_sleep() checks are added to wait.[ch].

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Reviewed-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/pagelist.c        | 17 +++++++++++++++++
 fs/nfs/write.c           | 12 +++++++++++-
 include/linux/nfs_page.h |  1 +
 3 files changed, 29 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 30c9626f96b0..4ec67f8d70aa 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -167,6 +167,23 @@ nfs_page_group_lock(struct nfs_page *req, bool nonblock)
 	return -EAGAIN;
 }
 
+/*
+ * nfs_page_group_lock_wait - wait for the lock to clear, but don't grab it
+ * @req - a request in the group
+ *
+ * This is a blocking call to wait for the group lock to be cleared.
+ */
+void
+nfs_page_group_lock_wait(struct nfs_page *req)
+{
+	struct nfs_page *head = req->wb_head;
+
+	WARN_ON_ONCE(head != head->wb_head);
+
+	wait_on_bit(&head->wb_flags, PG_HEADLOCK,
+		TASK_UNINTERRUPTIBLE);
+}
+
 /*
  * nfs_page_group_unlock - unlock the head of the page group
  * @req - request in group that is to be unlocked
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e056f617adf2..175d5d073ccf 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -478,13 +478,23 @@ try_again:
 		return NULL;
 	}
 
-	/* lock each request in the page group */
+	/* holding inode lock, so always make a non-blocking call to try the
+	 * page group lock */
 	ret = nfs_page_group_lock(head, true);
 	if (ret < 0) {
 		spin_unlock(&inode->i_lock);
+
+		if (!nonblock && ret == -EAGAIN) {
+			nfs_page_group_lock_wait(head);
+			nfs_release_request(head);
+			goto try_again;
+		}
+
 		nfs_release_request(head);
 		return ERR_PTR(ret);
 	}
+
+	/* lock each request in the page group */
 	subreq = head;
 	do {
 		/*
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 6ad2bbcad405..6c3e06ee2fb7 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -123,6 +123,7 @@ extern  int nfs_wait_on_request(struct nfs_page *);
 extern	void nfs_unlock_request(struct nfs_page *req);
 extern	void nfs_unlock_and_release_request(struct nfs_page *);
 extern int nfs_page_group_lock(struct nfs_page *, bool);
+extern void nfs_page_group_lock_wait(struct nfs_page *);
 extern void nfs_page_group_unlock(struct nfs_page *);
 extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int);
 
-- 
cgit v1.2.3


From d2de875c6d4cbec8a99c880160181a3ed5b9992e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Aug 2014 18:32:09 -0700
Subject: net: use ktime_get_ns() and ktime_get_real_ns() helpers

ktime_get_ns() replaces ktime_to_ns(ktime_get())

ktime_get_real_ns() replaces ktime_to_ns(ktime_get_real())

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/codel.h                     | 2 +-
 include/net/pkt_sched.h                 | 2 +-
 net/core/secure_seq.c                   | 6 +++---
 net/netfilter/nf_conntrack_core.c       | 2 +-
 net/netfilter/nf_conntrack_netlink.c    | 2 +-
 net/netfilter/nf_conntrack_standalone.c | 2 +-
 net/sched/act_police.c                  | 4 ++--
 net/sched/sch_fq.c                      | 4 ++--
 net/sched/sch_htb.c                     | 6 +++---
 net/sched/sch_tbf.c                     | 6 +++---
 10 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/codel.h b/include/net/codel.h
index fe0eab32ce76..aeee28081245 100644
--- a/include/net/codel.h
+++ b/include/net/codel.h
@@ -66,7 +66,7 @@ typedef s32 codel_tdiff_t;
 
 static inline codel_time_t codel_get_time(void)
 {
-	u64 ns = ktime_to_ns(ktime_get());
+	u64 ns = ktime_get_ns();
 
 	return ns >> CODEL_SHIFT;
 }
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index ec030cd76616..8bbe626e9ece 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -50,7 +50,7 @@ typedef long	psched_tdiff_t;
 
 static inline psched_time_t psched_get_time(void)
 {
-	return PSCHED_NS2TICKS(ktime_to_ns(ktime_get()));
+	return PSCHED_NS2TICKS(ktime_get_ns());
 }
 
 static inline psched_tdiff_t
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index ba71212f0251..51dd3193a33e 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -35,7 +35,7 @@ static u32 seq_scale(u32 seq)
 	 *	overlaps less than one time per MSL (2 minutes).
 	 *	Choosing a clock of 64 ns period is OK. (period of 274 s)
 	 */
-	return seq + (ktime_to_ns(ktime_get_real()) >> 6);
+	return seq + (ktime_get_real_ns() >> 6);
 }
 #endif
 
@@ -135,7 +135,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 	md5_transform(hash, net_secret);
 
 	seq = hash[0] | (((u64)hash[1]) << 32);
-	seq += ktime_to_ns(ktime_get_real());
+	seq += ktime_get_real_ns();
 	seq &= (1ull << 48) - 1;
 
 	return seq;
@@ -163,7 +163,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
 	md5_transform(hash, secret);
 
 	seq = hash[0] | (((u64)hash[1]) << 32);
-	seq += ktime_to_ns(ktime_get_real());
+	seq += ktime_get_real_ns();
 	seq &= (1ull << 48) - 1;
 
 	return seq;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index de88c4ab5146..0b634e7f1652 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -358,7 +358,7 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
 
 	tstamp = nf_conn_tstamp_find(ct);
 	if (tstamp && tstamp->stop == 0)
-		tstamp->stop = ktime_to_ns(ktime_get_real());
+		tstamp->stop = ktime_get_real_ns();
 
 	if (nf_ct_is_dying(ct))
 		goto delete;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 355a5c4ef763..1bd9ed9e62f6 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1737,7 +1737,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
 	}
 	tstamp = nf_conn_tstamp_find(ct);
 	if (tstamp)
-		tstamp->start = ktime_to_ns(ktime_get_real());
+		tstamp->start = ktime_get_real_ns();
 
 	err = nf_conntrack_hash_check_insert(ct);
 	if (err < 0)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index f641751dba9d..cf65a1e040dd 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -101,7 +101,7 @@ static void *ct_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct ct_iter_state *st = seq->private;
 
-	st->time_now = ktime_to_ns(ktime_get_real());
+	st->time_now = ktime_get_real_ns();
 	rcu_read_lock();
 	return ct_get_idx(seq, *pos);
 }
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 0566e4606a4a..f32bcb094915 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -231,7 +231,7 @@ override:
 	if (ret != ACT_P_CREATED)
 		return ret;
 
-	police->tcfp_t_c = ktime_to_ns(ktime_get());
+	police->tcfp_t_c = ktime_get_ns();
 	police->tcf_index = parm->index ? parm->index :
 		tcf_hash_new_index(hinfo);
 	h = tcf_hash(police->tcf_index, POL_TAB_MASK);
@@ -279,7 +279,7 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
 			return police->tcfp_result;
 		}
 
-		now = ktime_to_ns(ktime_get());
+		now = ktime_get_ns();
 		toks = min_t(s64, now - police->tcfp_t_c,
 			     police->tcfp_burst);
 		if (police->peak_present) {
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index ba32c2b005d0..e12f997e1b4c 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -416,7 +416,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
 static struct sk_buff *fq_dequeue(struct Qdisc *sch)
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = ktime_get_ns();
 	struct fq_flow_head *head;
 	struct sk_buff *skb;
 	struct fq_flow *f;
@@ -787,7 +787,7 @@ nla_put_failure:
 static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
-	u64 now = ktime_to_ns(ktime_get());
+	u64 now = ktime_get_ns();
 	struct tc_fq_qd_stats st = {
 		.gc_flows		= q->stat_gc_flows,
 		.highprio_packets	= q->stat_internal_packets,
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 9f949abcacef..aea942ce6008 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -895,7 +895,7 @@ ok:
 
 	if (!sch->q.qlen)
 		goto fin;
-	q->now = ktime_to_ns(ktime_get());
+	q->now = ktime_get_ns();
 	start_at = jiffies;
 
 	next_event = q->now + 5LLU * NSEC_PER_SEC;
@@ -1225,7 +1225,7 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl,
 	parent->un.leaf.q = new_q ? new_q : &noop_qdisc;
 	parent->tokens = parent->buffer;
 	parent->ctokens = parent->cbuffer;
-	parent->t_c = ktime_to_ns(ktime_get());
+	parent->t_c = ktime_get_ns();
 	parent->cmode = HTB_CAN_SEND;
 }
 
@@ -1455,7 +1455,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		cl->tokens = PSCHED_TICKS2NS(hopt->buffer);
 		cl->ctokens = PSCHED_TICKS2NS(hopt->cbuffer);
 		cl->mbuffer = 60ULL * NSEC_PER_SEC;	/* 1min */
-		cl->t_c = ktime_to_ns(ktime_get());
+		cl->t_c = ktime_get_ns();
 		cl->cmode = HTB_CAN_SEND;
 
 		/* attach to the hash list and parent's family */
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 18ff63433709..0c39b754083b 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -239,7 +239,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 		s64 ptoks = 0;
 		unsigned int len = qdisc_pkt_len(skb);
 
-		now = ktime_to_ns(ktime_get());
+		now = ktime_get_ns();
 		toks = min_t(s64, now - q->t_c, q->buffer);
 
 		if (tbf_peak_present(q)) {
@@ -292,7 +292,7 @@ static void tbf_reset(struct Qdisc *sch)
 
 	qdisc_reset(q->qdisc);
 	sch->q.qlen = 0;
-	q->t_c = ktime_to_ns(ktime_get());
+	q->t_c = ktime_get_ns();
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
 	qdisc_watchdog_cancel(&q->watchdog);
@@ -431,7 +431,7 @@ static int tbf_init(struct Qdisc *sch, struct nlattr *opt)
 	if (opt == NULL)
 		return -EINVAL;
 
-	q->t_c = ktime_to_ns(ktime_get());
+	q->t_c = ktime_get_ns();
 	qdisc_watchdog_init(&q->watchdog, sch);
 	q->qdisc = &noop_qdisc;
 
-- 
cgit v1.2.3


From 989e04c5bc3ff77d65e1f0d87bf7904dfa30d41c Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Fri, 22 Aug 2014 14:15:22 -0700
Subject: tcp: improve undo on timeout

Upon timeout, undo (via both timestamps/Eifel and DSACKs) was
disabled if any retransmits were still in flight.  The concern was
perhaps that spurious retransmission sent in a previous recovery
episode may trigger DSACKs to falsely undo the current recovery.

However, this inadvertently misses undo opportunities (using either
TCP timestamps or DSACKs) when timeout occurs during a loss episode,
i.e.  recurring timeouts or timeout during fast recovery. In these
cases some retransmissions will be in flight but we should allow
undo. Furthermore, we should only reset undo_marker and undo_retrans
upon timeout if we are starting a new recovery episode. Finally,
when we do reset our undo state, we now do so in a manner similar
to tcp_enter_recovery(), so that we require a DSACK for each of
the outstsanding retransmissions. This will achieve the original
goal by requiring that we receive the same number of DSACKs as
retransmissions.

This patch increases the undo events by 50% on Google servers.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h  |  2 +-
 net/ipv4/tcp_input.c | 26 +++++++++++---------------
 2 files changed, 12 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index fa5258f322e7..e567f0dbf282 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -276,7 +276,7 @@ struct tcp_sock {
 	u32	retrans_stamp;	/* Timestamp of the last retransmit,
 				 * also used in SYN-SENT to remember stamp of
 				 * the first SYN. */
-	u32	undo_marker;	/* tracking retrans started here. */
+	u32	undo_marker;	/* snd_una upon a new recovery episode. */
 	int	undo_retrans;	/* number of undoable retransmissions. */
 	u32	total_retrans;	/* Total retransmits for entire connection */
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a906e0200ff2..aba4926ca095 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1888,21 +1888,21 @@ static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
 	tp->sacked_out = 0;
 }
 
-static void tcp_clear_retrans_partial(struct tcp_sock *tp)
+void tcp_clear_retrans(struct tcp_sock *tp)
 {
 	tp->retrans_out = 0;
 	tp->lost_out = 0;
-
 	tp->undo_marker = 0;
 	tp->undo_retrans = -1;
+	tp->fackets_out = 0;
+	tp->sacked_out = 0;
 }
 
-void tcp_clear_retrans(struct tcp_sock *tp)
+static inline void tcp_init_undo(struct tcp_sock *tp)
 {
-	tcp_clear_retrans_partial(tp);
-
-	tp->fackets_out = 0;
-	tp->sacked_out = 0;
+	tp->undo_marker = tp->snd_una;
+	/* Retransmission still in flight may cause DSACKs later. */
+	tp->undo_retrans = tp->retrans_out ? : -1;
 }
 
 /* Enter Loss state. If we detect SACK reneging, forget all SACK information
@@ -1925,18 +1925,18 @@ void tcp_enter_loss(struct sock *sk)
 		tp->prior_ssthresh = tcp_current_ssthresh(sk);
 		tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
 		tcp_ca_event(sk, CA_EVENT_LOSS);
+		tcp_init_undo(tp);
 	}
 	tp->snd_cwnd	   = 1;
 	tp->snd_cwnd_cnt   = 0;
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 
-	tcp_clear_retrans_partial(tp);
+	tp->retrans_out = 0;
+	tp->lost_out = 0;
 
 	if (tcp_is_reno(tp))
 		tcp_reset_reno_sack(tp);
 
-	tp->undo_marker = tp->snd_una;
-
 	skb = tcp_write_queue_head(sk);
 	is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
 	if (is_reneg) {
@@ -1950,9 +1950,6 @@ void tcp_enter_loss(struct sock *sk)
 		if (skb == tcp_send_head(sk))
 			break;
 
-		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
-			tp->undo_marker = 0;
-
 		TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
 		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || is_reneg) {
 			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
@@ -2671,8 +2668,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 	NET_INC_STATS_BH(sock_net(sk), mib_idx);
 
 	tp->prior_ssthresh = 0;
-	tp->undo_marker = tp->snd_una;
-	tp->undo_retrans = tp->retrans_out ? : -1;
+	tcp_init_undo(tp);
 
 	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
 		if (!ece_ack)
-- 
cgit v1.2.3


From 477fa2bc4c838eebe8dcd66ff8e88a1ab81734b9 Mon Sep 17 00:00:00 2001
From: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Date: Fri, 8 Aug 2014 16:23:09 +0200
Subject: ARM: shmobile: r8a7740: clock register bits

Contains the header file with the clock pulse generator and MSTP bits.

Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Acked-by: Magnus Damm <damm+renesas@opensource.se>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 include/dt-bindings/clock/r8a7740-clock.h | 77 +++++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)
 create mode 100644 include/dt-bindings/clock/r8a7740-clock.h

(limited to 'include')

diff --git a/include/dt-bindings/clock/r8a7740-clock.h b/include/dt-bindings/clock/r8a7740-clock.h
new file mode 100644
index 000000000000..f6b4b0fe7a43
--- /dev/null
+++ b/include/dt-bindings/clock/r8a7740-clock.h
@@ -0,0 +1,77 @@
+/*
+ * Copyright 2014 Ulrich Hecht
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_R8A7740_H__
+#define __DT_BINDINGS_CLOCK_R8A7740_H__
+
+/* CPG */
+#define R8A7740_CLK_SYSTEM	0
+#define R8A7740_CLK_PLLC0	1
+#define R8A7740_CLK_PLLC1	2
+#define R8A7740_CLK_PLLC2	3
+#define R8A7740_CLK_R		4
+#define R8A7740_CLK_USB24S	5
+#define R8A7740_CLK_I		6
+#define R8A7740_CLK_ZG		7
+#define R8A7740_CLK_B		8
+#define R8A7740_CLK_M1		9
+#define R8A7740_CLK_HP		10
+#define R8A7740_CLK_HPP		11
+#define R8A7740_CLK_USBP	12
+#define R8A7740_CLK_S		13
+#define R8A7740_CLK_ZB		14
+#define R8A7740_CLK_M3		15
+#define R8A7740_CLK_CP		16
+
+/* MSTP1 */
+#define R8A7740_CLK_CEU21	28
+#define R8A7740_CLK_CEU20	27
+#define R8A7740_CLK_TMU0	25
+#define R8A7740_CLK_LCDC1	17
+#define R8A7740_CLK_IIC0	16
+#define R8A7740_CLK_TMU1	11
+#define R8A7740_CLK_LCDC0	0
+
+/* MSTP2 */
+#define R8A7740_CLK_SCIFA6	30
+#define R8A7740_CLK_SCIFA7	22
+#define R8A7740_CLK_DMAC1	18
+#define R8A7740_CLK_DMAC2	17
+#define R8A7740_CLK_DMAC3	16
+#define R8A7740_CLK_USBDMAC	14
+#define R8A7740_CLK_SCIFA5	7
+#define R8A7740_CLK_SCIFB	6
+#define R8A7740_CLK_SCIFA0	4
+#define R8A7740_CLK_SCIFA1	3
+#define R8A7740_CLK_SCIFA2	2
+#define R8A7740_CLK_SCIFA3	1
+#define R8A7740_CLK_SCIFA4	0
+
+/* MSTP3 */
+#define R8A7740_CLK_CMT1	29
+#define R8A7740_CLK_FSI		28
+#define R8A7740_CLK_IIC1	23
+#define R8A7740_CLK_USBF	20
+#define R8A7740_CLK_SDHI0	14
+#define R8A7740_CLK_SDHI1	13
+#define R8A7740_CLK_MMC		12
+#define R8A7740_CLK_GETHER	9
+#define R8A7740_CLK_TPU0	4
+
+/* MSTP4 */
+#define R8A7740_CLK_USBH	16
+#define R8A7740_CLK_SDHI2	15
+#define R8A7740_CLK_USBFUNC	7
+#define R8A7740_CLK_USBPHY	6
+
+/* SUBCK* */
+#define R8A7740_CLK_SUBCK	9
+#define R8A7740_CLK_SUBCK2	10
+
+#endif /* __DT_BINDINGS_CLOCK_R8A7740_H__ */
-- 
cgit v1.2.3


From 53f3cc46336b9e514c98556b4a009a69ed808d3b Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Sat, 23 Aug 2014 14:45:47 +0400
Subject: pata_platform: Remove useless irq_flags field

IRQ flags can be obtained from resource structure, there are no need
to use additional field in the platform_data to store these values.
This patch removes this field and convert existing users of this driver
to use IRQ flags from the resources.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 arch/blackfin/mach-bf537/boards/cm_bf537e.c | 3 +--
 arch/blackfin/mach-bf537/boards/cm_bf537u.c | 3 +--
 arch/blackfin/mach-bf537/boards/stamp.c     | 3 +--
 arch/blackfin/mach-bf537/boards/tcm_bf537.c | 3 +--
 arch/blackfin/mach-bf561/boards/cm_bf561.c  | 3 +--
 drivers/ata/pata_of_platform.c              | 2 --
 drivers/ata/pata_platform.c                 | 4 +---
 include/linux/ata_platform.h                | 5 -----
 8 files changed, 6 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537e.c b/arch/blackfin/mach-bf537/boards/cm_bf537e.c
index 1e7290ef3525..1e1014df5e9e 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537e.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537e.c
@@ -733,7 +733,6 @@ static struct platform_device bfin_mac_device = {
 
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 2,
-	.irq_type = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -750,7 +749,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537u.c b/arch/blackfin/mach-bf537/boards/cm_bf537u.c
index c7495dc74690..d056db9e5592 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537u.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537u.c
@@ -587,7 +587,6 @@ static struct platform_device bfin_mac_device = {
 
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 2,
-	.irq_type = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -604,7 +603,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c
index de19b8a56007..88a19fc9844d 100644
--- a/arch/blackfin/mach-bf537/boards/stamp.c
+++ b/arch/blackfin/mach-bf537/boards/stamp.c
@@ -2462,7 +2462,6 @@ static struct platform_device bfin_sport0_device = {
 #define PATA_INT	IRQ_PF5
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 1,
-	.irq_flags = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -2479,7 +2478,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 #elif defined(CF_IDE_NAND_CARD_USE_CF_IN_COMMON_MEMORY_MODE)
diff --git a/arch/blackfin/mach-bf537/boards/tcm_bf537.c b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
index 6b988ad653d8..ed309c9a62b6 100644
--- a/arch/blackfin/mach-bf537/boards/tcm_bf537.c
+++ b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
@@ -589,7 +589,6 @@ static struct platform_device bfin_mac_device = {
 
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 2,
-	.irq_type = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -606,7 +605,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c
index e862f7823e68..c6db52ba3a06 100644
--- a/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -354,7 +354,6 @@ static struct platform_device bfin_sir0_device = {
 
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 2,
-	.irq_type = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -371,7 +370,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c
index 6af1c9b9a464..64965398914a 100644
--- a/drivers/ata/pata_of_platform.c
+++ b/drivers/ata/pata_of_platform.c
@@ -43,8 +43,6 @@ static int pata_of_platform_probe(struct platform_device *ofdev)
 	}
 
 	irq_res = platform_get_resource(ofdev, IORESOURCE_IRQ, 0);
-	if (irq_res)
-		irq_res->flags = 0;
 
 	prop = of_get_property(dn, "reg-shift", NULL);
 	if (prop)
diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c
index a5579b55e332..f8cff3e247c5 100644
--- a/drivers/ata/pata_platform.c
+++ b/drivers/ata/pata_platform.c
@@ -118,7 +118,7 @@ int __pata_platform_probe(struct device *dev, struct resource *io_res,
 	 */
 	if (irq_res && irq_res->start > 0) {
 		irq = irq_res->start;
-		irq_flags = irq_res->flags;
+		irq_flags = irq_res->flags & IRQF_TRIGGER_MASK;
 	}
 
 	/*
@@ -213,8 +213,6 @@ static int pata_platform_probe(struct platform_device *pdev)
 	 * And the IRQ
 	 */
 	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (irq_res)
-		irq_res->flags = pp_info ? pp_info->irq_flags : 0;
 
 	return __pata_platform_probe(&pdev->dev, io_res, ctl_res, irq_res,
 				     pp_info ? pp_info->ioport_shift : 0,
diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h
index b9fde17f767c..5c618a084225 100644
--- a/include/linux/ata_platform.h
+++ b/include/linux/ata_platform.h
@@ -8,11 +8,6 @@ struct pata_platform_info {
 	 * spacing used by ata_std_ports().
 	 */
 	unsigned int ioport_shift;
-	/* 
-	 * Indicate platform specific irq types and initial
-	 * IRQ flags when call request_irq()
-	 */
-	unsigned int irq_flags;
 };
 
 extern int __pata_platform_probe(struct device *dev,
-- 
cgit v1.2.3


From 3af20efc0f83cdc65ce56ec108c0e81f602364df Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 22 Aug 2014 18:55:39 -0700
Subject: net: phy: broadcom: extract all registers to brcmphy.h

Commit 439d39a9ac8fbbba9c04581361188f33f21ced50 ("net: phy: broadcom:
extract register definitions") added a bunch of registers to brcmphy.h
but left some to broadcom.c, move all of them to the header file since
the BCM54xx and BCM7xxx PHY drivers do share all of these registers.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/broadcom.c | 104 ---------------------------------------------
 include/linux/brcmphy.h    | 103 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 103 insertions(+), 104 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 34088d60da74..6001d76d8676 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -25,110 +25,6 @@
 #define BRCM_PHY_REV(phydev) \
 	((phydev)->drv->phy_id & ~((phydev)->drv->phy_id_mask))
 
-/*
- * Broadcom LED source encodings.  These are used in BCM5461, BCM5481,
- * BCM5482, and possibly some others.
- */
-#define BCM_LED_SRC_LINKSPD1	0x0
-#define BCM_LED_SRC_LINKSPD2	0x1
-#define BCM_LED_SRC_XMITLED	0x2
-#define BCM_LED_SRC_ACTIVITYLED	0x3
-#define BCM_LED_SRC_FDXLED	0x4
-#define BCM_LED_SRC_SLAVE	0x5
-#define BCM_LED_SRC_INTR	0x6
-#define BCM_LED_SRC_QUALITY	0x7
-#define BCM_LED_SRC_RCVLED	0x8
-#define BCM_LED_SRC_MULTICOLOR1	0xa
-#define BCM_LED_SRC_OPENSHORT	0xb
-#define BCM_LED_SRC_OFF		0xe	/* Tied high */
-#define BCM_LED_SRC_ON		0xf	/* Tied low */
-
-
-/*
- * BCM5482: Shadow registers
- * Shadow values go into bits [14:10] of register 0x1c to select a shadow
- * register to access.
- */
-/* 00101: Spare Control Register 3 */
-#define BCM54XX_SHD_SCR3		0x05
-#define  BCM54XX_SHD_SCR3_DEF_CLK125	0x0001
-#define  BCM54XX_SHD_SCR3_DLLAPD_DIS	0x0002
-#define  BCM54XX_SHD_SCR3_TRDDAPD	0x0004
-
-/* 01010: Auto Power-Down */
-#define BCM54XX_SHD_APD			0x0a
-#define  BCM54XX_SHD_APD_EN		0x0020
-
-#define BCM5482_SHD_LEDS1	0x0d	/* 01101: LED Selector 1 */
-					/* LED3 / ~LINKSPD[2] selector */
-#define BCM5482_SHD_LEDS1_LED3(src)	((src & 0xf) << 4)
-					/* LED1 / ~LINKSPD[1] selector */
-#define BCM5482_SHD_LEDS1_LED1(src)	((src & 0xf) << 0)
-#define BCM54XX_SHD_RGMII_MODE	0x0b	/* 01011: RGMII Mode Selector */
-#define BCM5482_SHD_SSD		0x14	/* 10100: Secondary SerDes control */
-#define BCM5482_SHD_SSD_LEDM	0x0008	/* SSD LED Mode enable */
-#define BCM5482_SHD_SSD_EN	0x0001	/* SSD enable */
-#define BCM5482_SHD_MODE	0x1f	/* 11111: Mode Control Register */
-#define BCM5482_SHD_MODE_1000BX	0x0001	/* Enable 1000BASE-X registers */
-
-
-/*
- * EXPANSION SHADOW ACCESS REGISTERS.  (PHY REG 0x15, 0x16, and 0x17)
- */
-#define MII_BCM54XX_EXP_AADJ1CH0		0x001f
-#define  MII_BCM54XX_EXP_AADJ1CH0_SWP_ABCD_OEN	0x0200
-#define  MII_BCM54XX_EXP_AADJ1CH0_SWSEL_THPF	0x0100
-#define MII_BCM54XX_EXP_AADJ1CH3		0x601f
-#define  MII_BCM54XX_EXP_AADJ1CH3_ADCCKADJ	0x0002
-#define MII_BCM54XX_EXP_EXP08			0x0F08
-#define  MII_BCM54XX_EXP_EXP08_RJCT_2MHZ	0x0001
-#define  MII_BCM54XX_EXP_EXP08_EARLY_DAC_WAKE	0x0200
-#define MII_BCM54XX_EXP_EXP75			0x0f75
-#define  MII_BCM54XX_EXP_EXP75_VDACCTRL		0x003c
-#define  MII_BCM54XX_EXP_EXP75_CM_OSC		0x0001
-#define MII_BCM54XX_EXP_EXP96			0x0f96
-#define  MII_BCM54XX_EXP_EXP96_MYST		0x0010
-#define MII_BCM54XX_EXP_EXP97			0x0f97
-#define  MII_BCM54XX_EXP_EXP97_MYST		0x0c0c
-
-/*
- * BCM5482: Secondary SerDes registers
- */
-#define BCM5482_SSD_1000BX_CTL		0x00	/* 1000BASE-X Control */
-#define BCM5482_SSD_1000BX_CTL_PWRDOWN	0x0800	/* Power-down SSD */
-#define BCM5482_SSD_SGMII_SLAVE		0x15	/* SGMII Slave Register */
-#define BCM5482_SSD_SGMII_SLAVE_EN	0x0002	/* Slave mode enable */
-#define BCM5482_SSD_SGMII_SLAVE_AD	0x0001	/* Slave auto-detection */
-
-
-/*****************************************************************************/
-/* Fast Ethernet Transceiver definitions. */
-/*****************************************************************************/
-
-#define MII_BRCM_FET_INTREG		0x1a	/* Interrupt register */
-#define MII_BRCM_FET_IR_MASK		0x0100	/* Mask all interrupts */
-#define MII_BRCM_FET_IR_LINK_EN		0x0200	/* Link status change enable */
-#define MII_BRCM_FET_IR_SPEED_EN	0x0400	/* Link speed change enable */
-#define MII_BRCM_FET_IR_DUPLEX_EN	0x0800	/* Duplex mode change enable */
-#define MII_BRCM_FET_IR_ENABLE		0x4000	/* Interrupt enable */
-
-#define MII_BRCM_FET_BRCMTEST		0x1f	/* Brcm test register */
-#define MII_BRCM_FET_BT_SRE		0x0080	/* Shadow register enable */
-
-
-/*** Shadow register definitions ***/
-
-#define MII_BRCM_FET_SHDW_MISCCTRL	0x10	/* Shadow misc ctrl */
-#define MII_BRCM_FET_SHDW_MC_FAME	0x4000	/* Force Auto MDIX enable */
-
-#define MII_BRCM_FET_SHDW_AUXMODE4	0x1a	/* Auxiliary mode 4 */
-#define MII_BRCM_FET_SHDW_AM4_LED_MASK	0x0003
-#define MII_BRCM_FET_SHDW_AM4_LED_MODE1 0x0001
-
-#define MII_BRCM_FET_SHDW_AUXSTAT2	0x1b	/* Auxiliary status 2 */
-#define MII_BRCM_FET_SHDW_AS2_APDE	0x0020	/* Auto power down enable */
-
-
 MODULE_DESCRIPTION("Broadcom PHY driver");
 MODULE_AUTHOR("Maciej W. Rozycki");
 MODULE_LICENSE("GPL");
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 61219b9b3445..be31bf9f60c2 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -92,4 +92,107 @@
 
 #define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL	0x0000
 
+/*
+ * Broadcom LED source encodings.  These are used in BCM5461, BCM5481,
+ * BCM5482, and possibly some others.
+ */
+#define BCM_LED_SRC_LINKSPD1	0x0
+#define BCM_LED_SRC_LINKSPD2	0x1
+#define BCM_LED_SRC_XMITLED	0x2
+#define BCM_LED_SRC_ACTIVITYLED	0x3
+#define BCM_LED_SRC_FDXLED	0x4
+#define BCM_LED_SRC_SLAVE	0x5
+#define BCM_LED_SRC_INTR	0x6
+#define BCM_LED_SRC_QUALITY	0x7
+#define BCM_LED_SRC_RCVLED	0x8
+#define BCM_LED_SRC_MULTICOLOR1	0xa
+#define BCM_LED_SRC_OPENSHORT	0xb
+#define BCM_LED_SRC_OFF		0xe	/* Tied high */
+#define BCM_LED_SRC_ON		0xf	/* Tied low */
+
+
+/*
+ * BCM5482: Shadow registers
+ * Shadow values go into bits [14:10] of register 0x1c to select a shadow
+ * register to access.
+ */
+/* 00101: Spare Control Register 3 */
+#define BCM54XX_SHD_SCR3		0x05
+#define  BCM54XX_SHD_SCR3_DEF_CLK125	0x0001
+#define  BCM54XX_SHD_SCR3_DLLAPD_DIS	0x0002
+#define  BCM54XX_SHD_SCR3_TRDDAPD	0x0004
+
+/* 01010: Auto Power-Down */
+#define BCM54XX_SHD_APD			0x0a
+#define  BCM54XX_SHD_APD_EN		0x0020
+
+#define BCM5482_SHD_LEDS1	0x0d	/* 01101: LED Selector 1 */
+					/* LED3 / ~LINKSPD[2] selector */
+#define BCM5482_SHD_LEDS1_LED3(src)	((src & 0xf) << 4)
+					/* LED1 / ~LINKSPD[1] selector */
+#define BCM5482_SHD_LEDS1_LED1(src)	((src & 0xf) << 0)
+#define BCM54XX_SHD_RGMII_MODE	0x0b	/* 01011: RGMII Mode Selector */
+#define BCM5482_SHD_SSD		0x14	/* 10100: Secondary SerDes control */
+#define BCM5482_SHD_SSD_LEDM	0x0008	/* SSD LED Mode enable */
+#define BCM5482_SHD_SSD_EN	0x0001	/* SSD enable */
+#define BCM5482_SHD_MODE	0x1f	/* 11111: Mode Control Register */
+#define BCM5482_SHD_MODE_1000BX	0x0001	/* Enable 1000BASE-X registers */
+
+
+/*
+ * EXPANSION SHADOW ACCESS REGISTERS.  (PHY REG 0x15, 0x16, and 0x17)
+ */
+#define MII_BCM54XX_EXP_AADJ1CH0		0x001f
+#define  MII_BCM54XX_EXP_AADJ1CH0_SWP_ABCD_OEN	0x0200
+#define  MII_BCM54XX_EXP_AADJ1CH0_SWSEL_THPF	0x0100
+#define MII_BCM54XX_EXP_AADJ1CH3		0x601f
+#define  MII_BCM54XX_EXP_AADJ1CH3_ADCCKADJ	0x0002
+#define MII_BCM54XX_EXP_EXP08			0x0F08
+#define  MII_BCM54XX_EXP_EXP08_RJCT_2MHZ	0x0001
+#define  MII_BCM54XX_EXP_EXP08_EARLY_DAC_WAKE	0x0200
+#define MII_BCM54XX_EXP_EXP75			0x0f75
+#define  MII_BCM54XX_EXP_EXP75_VDACCTRL		0x003c
+#define  MII_BCM54XX_EXP_EXP75_CM_OSC		0x0001
+#define MII_BCM54XX_EXP_EXP96			0x0f96
+#define  MII_BCM54XX_EXP_EXP96_MYST		0x0010
+#define MII_BCM54XX_EXP_EXP97			0x0f97
+#define  MII_BCM54XX_EXP_EXP97_MYST		0x0c0c
+
+/*
+ * BCM5482: Secondary SerDes registers
+ */
+#define BCM5482_SSD_1000BX_CTL		0x00	/* 1000BASE-X Control */
+#define BCM5482_SSD_1000BX_CTL_PWRDOWN	0x0800	/* Power-down SSD */
+#define BCM5482_SSD_SGMII_SLAVE		0x15	/* SGMII Slave Register */
+#define BCM5482_SSD_SGMII_SLAVE_EN	0x0002	/* Slave mode enable */
+#define BCM5482_SSD_SGMII_SLAVE_AD	0x0001	/* Slave auto-detection */
+
+
+/*****************************************************************************/
+/* Fast Ethernet Transceiver definitions. */
+/*****************************************************************************/
+
+#define MII_BRCM_FET_INTREG		0x1a	/* Interrupt register */
+#define MII_BRCM_FET_IR_MASK		0x0100	/* Mask all interrupts */
+#define MII_BRCM_FET_IR_LINK_EN		0x0200	/* Link status change enable */
+#define MII_BRCM_FET_IR_SPEED_EN	0x0400	/* Link speed change enable */
+#define MII_BRCM_FET_IR_DUPLEX_EN	0x0800	/* Duplex mode change enable */
+#define MII_BRCM_FET_IR_ENABLE		0x4000	/* Interrupt enable */
+
+#define MII_BRCM_FET_BRCMTEST		0x1f	/* Brcm test register */
+#define MII_BRCM_FET_BT_SRE		0x0080	/* Shadow register enable */
+
+
+/*** Shadow register definitions ***/
+
+#define MII_BRCM_FET_SHDW_MISCCTRL	0x10	/* Shadow misc ctrl */
+#define MII_BRCM_FET_SHDW_MC_FAME	0x4000	/* Force Auto MDIX enable */
+
+#define MII_BRCM_FET_SHDW_AUXMODE4	0x1a	/* Auxiliary mode 4 */
+#define MII_BRCM_FET_SHDW_AM4_LED_MASK	0x0003
+#define MII_BRCM_FET_SHDW_AM4_LED_MODE1 0x0001
+
+#define MII_BRCM_FET_SHDW_AUXSTAT2	0x1b	/* Auxiliary status 2 */
+#define MII_BRCM_FET_SHDW_AS2_APDE	0x0020	/* Auto power down enable */
+
 #endif /* _LINUX_BRCMPHY_H */
-- 
cgit v1.2.3


From 705314797b8b997554b7e9d0ea7b65a497356e53 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 22 Aug 2014 18:55:40 -0700
Subject: net: phy: broadcom: move shadow 0x1C register accessors to brcmphy.h

The shadow register 0x1C is used both by the BCM54xxx PHYs and the
BCM7xxx internal PHYs, move the accessors to a common location so both
drivers can use them.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/broadcom.c | 18 ------------------
 include/linux/brcmphy.h    | 20 ++++++++++++++++++++
 2 files changed, 20 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 6001d76d8676..854f2c9a7b2b 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -29,24 +29,6 @@ MODULE_DESCRIPTION("Broadcom PHY driver");
 MODULE_AUTHOR("Maciej W. Rozycki");
 MODULE_LICENSE("GPL");
 
-/*
- * Indirect register access functions for the 1000BASE-T/100BASE-TX/10BASE-T
- * 0x1c shadow registers.
- */
-static int bcm54xx_shadow_read(struct phy_device *phydev, u16 shadow)
-{
-	phy_write(phydev, MII_BCM54XX_SHD, MII_BCM54XX_SHD_VAL(shadow));
-	return MII_BCM54XX_SHD_DATA(phy_read(phydev, MII_BCM54XX_SHD));
-}
-
-static int bcm54xx_shadow_write(struct phy_device *phydev, u16 shadow, u16 val)
-{
-	return phy_write(phydev, MII_BCM54XX_SHD,
-			 MII_BCM54XX_SHD_WRITE |
-			 MII_BCM54XX_SHD_VAL(shadow) |
-			 MII_BCM54XX_SHD_DATA(val));
-}
-
 /* Indirect register access functions for the Expansion Registers */
 static int bcm54xx_exp_read(struct phy_device *phydev, u16 regnum)
 {
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index be31bf9f60c2..722cf26567fa 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -195,4 +195,24 @@
 #define MII_BRCM_FET_SHDW_AUXSTAT2	0x1b	/* Auxiliary status 2 */
 #define MII_BRCM_FET_SHDW_AS2_APDE	0x0020	/* Auto power down enable */
 
+/*
+ * Indirect register access functions for the 1000BASE-T/100BASE-TX/10BASE-T
+ * 0x1c shadow registers.
+ */
+static inline int bcm54xx_shadow_read(struct phy_device *phydev, u16 shadow)
+{
+	phy_write(phydev, MII_BCM54XX_SHD, MII_BCM54XX_SHD_VAL(shadow));
+	return MII_BCM54XX_SHD_DATA(phy_read(phydev, MII_BCM54XX_SHD));
+}
+
+static inline int bcm54xx_shadow_write(struct phy_device *phydev, u16 shadow,
+				       u16 val)
+{
+	return phy_write(phydev, MII_BCM54XX_SHD,
+			 MII_BCM54XX_SHD_WRITE |
+			 MII_BCM54XX_SHD_VAL(shadow) |
+			 MII_BCM54XX_SHD_DATA(val));
+}
+
+
 #endif /* _LINUX_BRCMPHY_H */
-- 
cgit v1.2.3


From 66ce7fb9807b036058aa380bfd2b3851ae25ce39 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 22 Aug 2014 18:55:43 -0700
Subject: net: phy: export phy_{read,write}_mmd_indirect

Some PHY drivers might need to access Clause 45 registers in Clause 22
compatibility mode to e.g: properly advertise EEE support when disabled
by default.

Export these two helper functions: phy_read_mmd_indirect() and
phy_write_mmd_indirect() for drivers to use them.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c |  6 ++++--
 include/linux/phy.h   | 27 +++++++++++++++++++++++++++
 2 files changed, 31 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index c94e2a27446a..e7a5893f32ff 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -955,7 +955,7 @@ static inline void mmd_phy_indirect(struct mii_bus *bus, int prtad, int devad,
  * 3) Write reg 13 // MMD Data Command for MMD DEVAD
  * 3) Read  reg 14 // Read MMD data
  */
-static int phy_read_mmd_indirect(struct phy_device *phydev, int prtad,
+int phy_read_mmd_indirect(struct phy_device *phydev, int prtad,
 				 int devad, int addr)
 {
 	struct phy_driver *phydrv = phydev->drv;
@@ -971,6 +971,7 @@ static int phy_read_mmd_indirect(struct phy_device *phydev, int prtad,
 	}
 	return value;
 }
+EXPORT_SYMBOL(phy_read_mmd_indirect);
 
 /**
  * phy_write_mmd_indirect - writes data to the MMD registers
@@ -988,7 +989,7 @@ static int phy_read_mmd_indirect(struct phy_device *phydev, int prtad,
  * 3) Write reg 13 // MMD Data Command for MMD DEVAD
  * 3) Write reg 14 // Write MMD data
  */
-static void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
+void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
 				   int devad, int addr, u32 data)
 {
 	struct phy_driver *phydrv = phydev->drv;
@@ -1002,6 +1003,7 @@ static void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
 		phydrv->write_mmd_indirect(phydev, prtad, devad, addr, data);
 	}
 }
+EXPORT_SYMBOL(phy_write_mmd_indirect);
 
 /**
  * phy_init_eee - init and check the EEE feature
diff --git a/include/linux/phy.h b/include/linux/phy.h
index ed39956b5613..d090cfcaa167 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -597,6 +597,19 @@ static inline int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum)
 			    MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff));
 }
 
+/**
+ * phy_read_mmd_indirect - reads data from the MMD registers
+ * @phydev: The PHY device bus
+ * @prtad: MMD Address
+ * @devad: MMD DEVAD
+ * @addr: PHY address on the MII bus
+ *
+ * Description: it reads data from the MMD registers (clause 22 to access to
+ * clause 45) of the specified phy address.
+ */
+int phy_read_mmd_indirect(struct phy_device *phydev, int prtad,
+			  int devad, int addr);
+
 /**
  * phy_read - Convenience function for reading a given PHY register
  * @phydev: the phy_device struct
@@ -668,6 +681,20 @@ static inline int phy_write_mmd(struct phy_device *phydev, int devad,
 	return mdiobus_write(phydev->bus, phydev->addr, regnum, val);
 }
 
+/**
+ * phy_write_mmd_indirect - writes data to the MMD registers
+ * @phydev: The PHY device
+ * @prtad: MMD Address
+ * @devad: MMD DEVAD
+ * @addr: PHY address on the MII bus
+ * @data: data to write in the MMD register
+ *
+ * Description: Write data from the MMD registers of the specified
+ * phy address.
+ */
+void phy_write_mmd_indirect(struct phy_device *phydev, int prtad,
+			    int devad, int addr, u32 data);
+
 struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
 				     bool is_c45,
 				     struct phy_c45_device_ids *c45_ids);
-- 
cgit v1.2.3


From b8f9a02924bbeb0c46ca4c19561cbe765b80e264 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 22 Aug 2014 18:55:45 -0700
Subject: net: phy: bcm7xxx: enable EEE at the PHY level

The 28nm Gigabit PHY on BCM7xxx chips comes out of reset with absolutely
no EEE capabilities, such that we would actually return that we do not
support EEE when accessing 3.20 (MDIO_PCS_EEE_ABLE) registers.

Poke through the vendor-specific C45 register to enable EEE globally at
the PHY level, and advertise supported EEE modes.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 31 +++++++++++++++++++++++++++++++
 include/linux/brcmphy.h   |  3 +++
 2 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 29e256a4ed57..e98c510b75c5 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -14,6 +14,7 @@
 #include <linux/delay.h>
 #include <linux/bitops.h>
 #include <linux/brcmphy.h>
+#include <linux/mdio.h>
 
 /* Broadcom BCM7xxx internal PHY registers */
 #define MII_BCM7XXX_CHANNEL_WIDTH	0x2000
@@ -167,6 +168,32 @@ static int bcm7xxx_apd_enable(struct phy_device *phydev)
 	return bcm54xx_shadow_write(phydev, BCM54XX_SHD_APD, val);
 }
 
+static int bcm7xxx_eee_enable(struct phy_device *phydev)
+{
+	int val;
+
+	val = phy_read_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL,
+				    MDIO_MMD_AN, phydev->addr);
+	if (val < 0)
+		return val;
+
+	/* Enable general EEE feature at the PHY level */
+	val |= LPI_FEATURE_EN | LPI_FEATURE_EN_DIG1000X;
+
+	phy_write_mmd_indirect(phydev, BRCM_CL45VEN_EEE_CONTROL,
+			       MDIO_MMD_AN, phydev->addr, val);
+
+	/* Advertise supported modes */
+	val = phy_read_mmd_indirect(phydev, MDIO_AN_EEE_ADV,
+				    MDIO_MMD_AN, phydev->addr);
+
+	val |= (MDIO_AN_EEE_ADV_100TX | MDIO_AN_EEE_ADV_1000T);
+	phy_write_mmd_indirect(phydev, MDIO_AN_EEE_ADV,
+			       MDIO_MMD_AN, phydev->addr, val);
+
+	return 0;
+}
+
 static int bcm7xxx_28nm_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -179,6 +206,10 @@ static int bcm7xxx_28nm_config_init(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
+	ret = bcm7xxx_eee_enable(phydev);
+	if (ret)
+		return ret;
+
 	return bcm7xxx_apd_enable(phydev);
 }
 
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 722cf26567fa..ee1431d976fa 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -214,5 +214,8 @@ static inline int bcm54xx_shadow_write(struct phy_device *phydev, u16 shadow,
 			 MII_BCM54XX_SHD_DATA(val));
 }
 
+#define BRCM_CL45VEN_EEE_CONTROL	0x803d
+#define LPI_FEATURE_EN			0x8000
+#define LPI_FEATURE_EN_DIG1000X		0x4000
 
 #endif /* _LINUX_BRCMPHY_H */
-- 
cgit v1.2.3


From 690e36e726d00d2528bc569809048adf61550d80 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 23 Aug 2014 12:13:41 -0700
Subject: net: Allow raw buffers to be passed into the flow dissector.

Drivers, and perhaps other entities we have not yet considered,
sometimes want to know how deep the protocol headers go before
deciding how large of an SKB to allocate and how much of the packet to
place into the linear SKB area.

For example, consider a driver which has a device which DMAs into
pools of pages and then tells the driver where the data went in the
DMA descriptor(s).  The driver can then build an SKB and reference
most of the data via SKB fragments (which are page/offset/length
triplets).

However at least some of the front of the packet should be placed into
the linear SKB area, which comes before the fragments, so that packet
processing can get at the headers efficiently.  The first thing each
protocol layer is going to do is a "pskb_may_pull()" so we might as
well aggregate as much of this as possible while we're building the
SKB in the driver.

Part of supporting this is that we don't have an SKB yet, so we want
to be able to let the flow dissector operate on a raw buffer in order
to compute the offset of the end of the headers.

So now we have a __skb_flow_dissect() which takes an explicit data
pointer and length.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    | 18 ++++++++++++------
 include/net/flow_keys.h   | 14 ++++++++++++--
 net/core/flow_dissector.c | 40 ++++++++++++++++++++++++++--------------
 3 files changed, 50 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index abde271c18ae..18ddf9684a27 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2567,20 +2567,26 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 __wsum skb_checksum(const struct sk_buff *skb, int offset, int len,
 		    __wsum csum);
 
-static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
-				       int len, void *buffer)
+static inline void *__skb_header_pointer(const struct sk_buff *skb, int offset,
+					 int len, void *data, int hlen, void *buffer)
 {
-	int hlen = skb_headlen(skb);
-
 	if (hlen - offset >= len)
-		return skb->data + offset;
+		return data + offset;
 
-	if (skb_copy_bits(skb, offset, buffer, len) < 0)
+	if (!skb ||
+	    skb_copy_bits(skb, offset, buffer, len) < 0)
 		return NULL;
 
 	return buffer;
 }
 
+static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
+				       int len, void *buffer)
+{
+	return __skb_header_pointer(skb, offset, len, skb->data,
+				    skb_headlen(skb), buffer);
+}
+
 /**
  *	skb_needs_linearize - check if we need to linearize a given skb
  *			      depending on the given device features.
diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index 6667a054763a..4040f63932c5 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -27,7 +27,17 @@ struct flow_keys {
 	u8 ip_proto;
 };
 
-bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow);
-__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto);
+bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
+			void *data, int hlen);
+static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
+{
+	return __skb_flow_dissect(skb, flow, NULL, 0);
+}
+__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
+			    void *data, int hlen_proto);
+static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto)
+{
+	return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
+}
 u32 flow_hash_from_keys(struct flow_keys *keys);
 #endif
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 5f362c1d0332..660c6492fb78 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -34,29 +34,40 @@ static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *i
  * The function will try to retrieve the ports at offset thoff + poff where poff
  * is the protocol port offset returned from proto_ports_offset
  */
-__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto)
+__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
+			    void *data, int hlen)
 {
 	int poff = proto_ports_offset(ip_proto);
 
+	if (!data) {
+		data = skb->data;
+		hlen = skb_headlen(skb);
+	}
+
 	if (poff >= 0) {
 		__be32 *ports, _ports;
 
-		ports = skb_header_pointer(skb, thoff + poff,
-					   sizeof(_ports), &_ports);
+		ports = __skb_header_pointer(skb, thoff + poff,
+					     sizeof(_ports), data, hlen, &_ports);
 		if (ports)
 			return *ports;
 	}
 
 	return 0;
 }
-EXPORT_SYMBOL(skb_flow_get_ports);
+EXPORT_SYMBOL(__skb_flow_get_ports);
 
-bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
+bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, void *data, int hlen)
 {
 	int nhoff = skb_network_offset(skb);
 	u8 ip_proto;
 	__be16 proto = skb->protocol;
 
+	if (!data) {
+		data = skb->data;
+		hlen = skb_headlen(skb);
+	}
+
 	memset(flow, 0, sizeof(*flow));
 
 again:
@@ -65,7 +76,7 @@ again:
 		const struct iphdr *iph;
 		struct iphdr _iph;
 ip:
-		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
 		if (!iph || iph->ihl < 5)
 			return false;
 		nhoff += iph->ihl * 4;
@@ -83,7 +94,7 @@ ip:
 		__be32 flow_label;
 
 ipv6:
-		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
 		if (!iph)
 			return false;
 
@@ -113,7 +124,7 @@ ipv6:
 		const struct vlan_hdr *vlan;
 		struct vlan_hdr _vlan;
 
-		vlan = skb_header_pointer(skb, nhoff, sizeof(_vlan), &_vlan);
+		vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan);
 		if (!vlan)
 			return false;
 
@@ -126,7 +137,7 @@ ipv6:
 			struct pppoe_hdr hdr;
 			__be16 proto;
 		} *hdr, _hdr;
-		hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
 		if (!hdr)
 			return false;
 		proto = hdr->proto;
@@ -151,7 +162,7 @@ ipv6:
 			__be16 proto;
 		} *hdr, _hdr;
 
-		hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
 		if (!hdr)
 			return false;
 		/*
@@ -171,8 +182,9 @@ ipv6:
 				const struct ethhdr *eth;
 				struct ethhdr _eth;
 
-				eth = skb_header_pointer(skb, nhoff,
-							 sizeof(_eth), &_eth);
+				eth = __skb_header_pointer(skb, nhoff,
+							   sizeof(_eth),
+							   data, hlen, &_eth);
 				if (!eth)
 					return false;
 				proto = eth->h_proto;
@@ -194,12 +206,12 @@ ipv6:
 
 	flow->n_proto = proto;
 	flow->ip_proto = ip_proto;
-	flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto);
+	flow->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen);
 	flow->thoff = (u16) nhoff;
 
 	return true;
 }
-EXPORT_SYMBOL(skb_flow_dissect);
+EXPORT_SYMBOL(__skb_flow_dissect);
 
 static u32 hashrnd __read_mostly;
 static __always_inline void __flow_hash_secret_init(void)
-- 
cgit v1.2.3


From 179033b3e064d2cd3f5f9945e76b0a0f0fbf4883 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 7 Aug 2014 11:48:26 -0400
Subject: perf: Add PERF_EVENT_STATE_EXIT state for events with exited task

Adding new perf event state to indicate that the monitored task has
exited.  In this case the event stays alive until the owner task exits
or close the event fd while providing the last data through the read
syscall and ring buffer.

Instead it needs to propagate the error info (monitored task has died)
via poll and read  syscalls by  returning POLLHUP and 0 respectively.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140811120102.GY9918@twins.programming.kicks-ass.net
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-t5y3w8jjx6tfo5w8y6oajsjq@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 include/linux/perf_event.h |  1 +
 kernel/events/core.c       | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f0a1036b1911..893a0d07986f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -269,6 +269,7 @@ struct pmu {
  * enum perf_event_active_state - the states of a event
  */
 enum perf_event_active_state {
+	PERF_EVENT_STATE_EXIT		= -3,
 	PERF_EVENT_STATE_ERROR		= -2,
 	PERF_EVENT_STATE_OFF		= -1,
 	PERF_EVENT_STATE_INACTIVE	=  0,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4575dd6e59ea..d8cb4d21a346 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3600,7 +3600,8 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
 	 * error state (i.e. because it was pinned but it couldn't be
 	 * scheduled on to the CPU at some point).
 	 */
-	if (event->state == PERF_EVENT_STATE_ERROR)
+	if ((event->state == PERF_EVENT_STATE_ERROR) ||
+	    (event->state == PERF_EVENT_STATE_EXIT))
 		return 0;
 
 	if (count < event->read_size)
@@ -3630,6 +3631,10 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	unsigned int events = POLLHUP;
 
 	poll_wait(file, &event->waitq, wait);
+
+	if (event->state == PERF_EVENT_STATE_EXIT)
+		return events;
+
 	/*
 	 * Pin the event->rb by taking event->mmap_mutex; otherwise
 	 * perf_event_set_output() can swizzle our rb and make us miss wakeups.
@@ -7588,6 +7593,9 @@ __perf_event_exit_task(struct perf_event *child_event,
 	if (child_event->parent) {
 		sync_child_event(child_event, child);
 		free_event(child_event);
+	} else {
+		child_event->state = PERF_EVENT_STATE_EXIT;
+		perf_event_wakeup(child_event);
 	}
 }
 
-- 
cgit v1.2.3


From e2a093ff0dbfa4c5d99f25241cf33325e9691d91 Mon Sep 17 00:00:00 2001
From: Ana Rey <anarey@gmail.com>
Date: Wed, 6 Aug 2014 13:52:49 +0200
Subject: netfilter: nft_meta: add pkttype support

Add pkttype support for ip, ipv6 and inet families of tables.

This allows you to fetch the meta packet type based on the link layer
information. The loopback traffic is a special case, the packet type
is guessed from the network layer header.

No special handling for bridge and arp since we're not going to see
such traffic in the loopback interface.

Joint work with Alvaro Neira Ayuso <alvaroneay@gmail.com>

Signed-off-by: Alvaro Neira Ayuso <alvaroneay@gmail.com>
Signed-off-by: Ana Rey <anarey@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nft_meta.c                 | 28 ++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 801bdd1e56e3..98144cdd8986 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -571,6 +571,7 @@ enum nft_exthdr_attributes {
  * @NFT_META_L4PROTO: layer 4 protocol number
  * @NFT_META_BRI_IIFNAME: packet input bridge interface name
  * @NFT_META_BRI_OIFNAME: packet output bridge interface name
+ * @NFT_META_PKTTYPE: packet type (skb->pkt_type), special handling for loopback
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -592,6 +593,7 @@ enum nft_meta_keys {
 	NFT_META_L4PROTO,
 	NFT_META_BRI_IIFNAME,
 	NFT_META_BRI_OIFNAME,
+	NFT_META_PKTTYPE,
 };
 
 /**
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 852b178c6ae7..4f2862fc12c2 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -14,6 +14,9 @@
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/tcp_states.h> /* for TCP_TIME_WAIT */
@@ -124,6 +127,30 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 		dest->data[0] = skb->secmark;
 		break;
 #endif
+	case NFT_META_PKTTYPE:
+		if (skb->pkt_type != PACKET_LOOPBACK) {
+			dest->data[0] = skb->pkt_type;
+			break;
+		}
+
+		switch (pkt->ops->pf) {
+		case NFPROTO_IPV4:
+			if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+				dest->data[0] = PACKET_MULTICAST;
+			else
+				dest->data[0] = PACKET_BROADCAST;
+			break;
+		case NFPROTO_IPV6:
+			if (ipv6_hdr(skb)->daddr.s6_addr[0] == 0xFF)
+				dest->data[0] = PACKET_MULTICAST;
+			else
+				dest->data[0] = PACKET_BROADCAST;
+			break;
+		default:
+			WARN_ON(1);
+			goto err;
+		}
+		break;
 	default:
 		WARN_ON(1);
 		goto err;
@@ -195,6 +222,7 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 #ifdef CONFIG_NETWORK_SECMARK
 	case NFT_META_SECMARK:
 #endif
+	case NFT_META_PKTTYPE:
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From afc5be3079796b024823bad42dc5ebf716453575 Mon Sep 17 00:00:00 2001
From: Ana Rey <anarey@gmail.com>
Date: Sun, 24 Aug 2014 14:08:36 +0200
Subject: netfilter: nft_meta: Add cpu attribute support

Add cpu support to meta expresion.

This allows you to match packets with cpu number.

Signed-off-by: Ana Rey <anarey@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 2 ++
 net/netfilter/nft_meta.c                 | 5 +++++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 98144cdd8986..c9b6f00a3fb7 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -572,6 +572,7 @@ enum nft_exthdr_attributes {
  * @NFT_META_BRI_IIFNAME: packet input bridge interface name
  * @NFT_META_BRI_OIFNAME: packet output bridge interface name
  * @NFT_META_PKTTYPE: packet type (skb->pkt_type), special handling for loopback
+ * @NFT_META_CPU: cpu id through smp_processor_id()
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -594,6 +595,7 @@ enum nft_meta_keys {
 	NFT_META_BRI_IIFNAME,
 	NFT_META_BRI_OIFNAME,
 	NFT_META_PKTTYPE,
+	NFT_META_CPU,
 };
 
 /**
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 4f2862fc12c2..843e099a962d 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -17,6 +17,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/smp.h>
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/tcp_states.h> /* for TCP_TIME_WAIT */
@@ -151,6 +152,9 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 			goto err;
 		}
 		break;
+	case NFT_META_CPU:
+		dest->data[0] = smp_processor_id();
+		break;
 	default:
 		WARN_ON(1);
 		goto err;
@@ -223,6 +227,7 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 	case NFT_META_SECMARK:
 #endif
 	case NFT_META_PKTTYPE:
+	case NFT_META_CPU:
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 1b05756c48ea07ced9604ef01d11194d936da163 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 5 Aug 2014 22:02:34 +0200
Subject: netfilter: ipset: Fix warn: integer overflows 'sizeof(*map) + size *
 set->dsize'

Dan Carpenter reported that the static checker emits the warning

        net/netfilter/ipset/ip_set_list_set.c:600 init_list_set()
        warn: integer overflows 'sizeof(*map) + size * set->dsize'

Limit the maximal number of elements in list type of sets.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set_list.h | 1 +
 net/netfilter/ipset/ip_set_list_set.c       | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set_list.h b/include/linux/netfilter/ipset/ip_set_list.h
index 68c2aea897f5..fe2622a00151 100644
--- a/include/linux/netfilter/ipset/ip_set_list.h
+++ b/include/linux/netfilter/ipset/ip_set_list.h
@@ -6,5 +6,6 @@
 
 #define IP_SET_LIST_DEFAULT_SIZE	8
 #define IP_SET_LIST_MIN_SIZE		4
+#define IP_SET_LIST_MAX_SIZE		65536
 
 #endif /* __IP_SET_LIST_H */
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 3e2317f3cf68..f87adbad6076 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -597,7 +597,9 @@ init_list_set(struct net *net, struct ip_set *set, u32 size)
 	struct set_elem *e;
 	u32 i;
 
-	map = kzalloc(sizeof(*map) + size * set->dsize, GFP_KERNEL);
+	map = kzalloc(sizeof(*map) +
+		      min_t(u32, size, IP_SET_LIST_MAX_SIZE) * set->dsize,
+		      GFP_KERNEL);
 	if (!map)
 		return false;
 
-- 
cgit v1.2.3


From 573e8fca255a27e3573b51f9b183d62641c47a3d Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Fri, 22 Aug 2014 13:33:47 -0700
Subject: net: skb_gro_checksum_* functions

Add skb_gro_checksum_validate, skb_gro_checksum_validate_zero_check,
and skb_gro_checksum_simple_validate, and __skb_gro_checksum_complete.
These are the cognates of the normal checksum functions but are used
in the gro_receive path and operate on GRO related fields in sk_buffs.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 76 +++++++++++++++++++++++++++++++++++++++++++++--
 net/core/dev.c            | 34 ++++++++++++++++++++-
 2 files changed, 107 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7e2b0b8b5cd7..eb73444e1bd0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1883,7 +1883,13 @@ struct napi_gro_cb {
 	u16	proto;
 
 	/* Used in udp_gro_receive */
-	u16	udp_mark;
+	u8	udp_mark:1;
+
+	/* GRO checksum is valid */
+	u8	csum_valid:1;
+
+	/* Number encapsulation layers crossed */
+	u8	encapsulation;
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
@@ -2154,11 +2160,77 @@ static inline void *skb_gro_network_header(struct sk_buff *skb)
 static inline void skb_gro_postpull_rcsum(struct sk_buff *skb,
 					const void *start, unsigned int len)
 {
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
+	if (NAPI_GRO_CB(skb)->csum_valid)
 		NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum,
 						  csum_partial(start, len, 0));
 }
 
+/* GRO checksum functions. These are logical equivalents of the normal
+ * checksum functions (in skbuff.h) except that they operate on the GRO
+ * offsets and fields in sk_buff.
+ */
+
+__sum16 __skb_gro_checksum_complete(struct sk_buff *skb);
+
+static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb,
+						      bool zero_okay,
+						      __sum16 check)
+{
+	return (skb->ip_summed != CHECKSUM_PARTIAL &&
+		(skb->ip_summed != CHECKSUM_UNNECESSARY ||
+		 (NAPI_GRO_CB(skb)->encapsulation > skb->encapsulation)) &&
+		(!zero_okay || check));
+}
+
+static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb,
+							   __wsum psum)
+{
+	if (NAPI_GRO_CB(skb)->csum_valid &&
+	    !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum)))
+		return 0;
+
+	NAPI_GRO_CB(skb)->csum = psum;
+
+	return __skb_gro_checksum_complete(skb);
+}
+
+/* Update skb for CHECKSUM_UNNECESSARY when we verified a top level
+ * checksum or an encapsulated one during GRO. This saves work
+ * if we fallback to normal path with the packet.
+ */
+static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb)
+{
+	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+		if (NAPI_GRO_CB(skb)->encapsulation)
+			skb->encapsulation = 1;
+	} else if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->encapsulation = 0;
+	}
+}
+
+#define __skb_gro_checksum_validate(skb, proto, zero_okay, check,	\
+				    compute_pseudo)			\
+({									\
+	__sum16 __ret = 0;						\
+	if (__skb_gro_checksum_validate_needed(skb, zero_okay, check))	\
+		__ret = __skb_gro_checksum_validate_complete(skb,	\
+				compute_pseudo(skb, proto));		\
+	if (!__ret)							\
+		skb_gro_incr_csum_unnecessary(skb);			\
+	__ret;								\
+})
+
+#define skb_gro_checksum_validate(skb, proto, compute_pseudo)		\
+	__skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo)
+
+#define skb_gro_checksum_validate_zero_check(skb, proto, check,		\
+					     compute_pseudo)		\
+	__skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo)
+
+#define skb_gro_checksum_simple_validate(skb)				\
+	__skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo)
+
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 				  unsigned short type,
 				  const void *daddr, const void *saddr,
diff --git a/net/core/dev.c b/net/core/dev.c
index 1421dad4cb29..b6a718ec11c1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3962,7 +3962,13 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		goto normal;
 
 	gro_list_prepare(napi, skb);
-	NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		NAPI_GRO_CB(skb)->csum = skb->csum;
+		NAPI_GRO_CB(skb)->csum_valid = 1;
+	} else {
+		NAPI_GRO_CB(skb)->csum_valid = 0;
+	}
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
@@ -3975,6 +3981,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->udp_mark = 0;
+		NAPI_GRO_CB(skb)->encapsulation = 0;
 
 		pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
 		break;
@@ -4205,6 +4212,31 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_gro_frags);
 
+/* Compute the checksum from gro_offset and return the folded value
+ * after adding in any pseudo checksum.
+ */
+__sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
+{
+	__wsum wsum;
+	__sum16 sum;
+
+	wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0);
+
+	/* NAPI_GRO_CB(skb)->csum holds pseudo checksum */
+	sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+
+	NAPI_GRO_CB(skb)->csum = wsum;
+	NAPI_GRO_CB(skb)->csum_valid = 1;
+
+	return sum;
+}
+EXPORT_SYMBOL(__skb_gro_checksum_complete);
+
 /*
  * net_rps_action_and_irq_enable sends any pending IPI's for rps.
  * Note: called with local irq disabled, but exits with local irq enabled.
-- 
cgit v1.2.3


From 1933a7852ce6a81349855431b25122d7666bbfca Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Fri, 22 Aug 2014 13:34:04 -0700
Subject: net: add gro_compute_pseudo functions

Add inet_gro_compute_pseudo and ip6_gro_compute_pseudo. These are
the logical equivalents of inet_compute_pseudo and ip6_compute_pseudo
for GRO path. The IP header is taken from skb_gro_network_header.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h           | 8 ++++++++
 include/net/ip6_checksum.h | 8 ++++++++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index db4a771b9ef3..c8fd6112bd0b 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -364,6 +364,14 @@ static inline void inet_set_txhash(struct sock *sk)
 	sk->sk_txhash = flow_hash_from_keys(&keys);
 }
 
+static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto)
+{
+	const struct iphdr *iph = skb_gro_network_header(skb);
+
+	return csum_tcpudp_nofold(iph->saddr, iph->daddr,
+				  skb_gro_len(skb), proto, 0);
+}
+
 /*
  *	Map a multicast IP onto multicast MAC for type ethernet.
  */
diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index 55236cb71174..1a49b73f7f6e 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -48,6 +48,14 @@ static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto)
 					    skb->len, proto, 0));
 }
 
+static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto)
+{
+	const struct ipv6hdr *iph = skb_gro_network_header(skb);
+
+	return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr,
+					    skb_gro_len(skb), proto, 0));
+}
+
 static __inline__ __sum16 tcp_v6_check(int len,
 				   const struct in6_addr *saddr,
 				   const struct in6_addr *daddr,
-- 
cgit v1.2.3


From 57c67ff4bd92af634f7c91c40eb02a96dd785dda Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Fri, 22 Aug 2014 13:34:44 -0700
Subject: udp: additional GRO support

Implement GRO for UDPv6. Add UDP checksum verification in gro_receive
for both UDP4 and UDP6 calling skb_gro_checksum_validate_zero_check.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h      | 18 +++++++++++++++
 net/ipv4/udp.c         |  1 +
 net/ipv4/udp_offload.c | 61 ++++++++++++++++++++++++++++++++++++--------------
 net/ipv6/udp_offload.c | 33 +++++++++++++++++++++++++++
 4 files changed, 96 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/udp.h b/include/net/udp.h
index 70f941368ace..16f4e80f0519 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -158,6 +158,24 @@ static inline __sum16 udp_v4_check(int len, __be32 saddr,
 void udp_set_csum(bool nocheck, struct sk_buff *skb,
 		  __be32 saddr, __be32 daddr, int len);
 
+struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
+				 struct udphdr *uh);
+int udp_gro_complete(struct sk_buff *skb, int nhoff);
+
+static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
+{
+	struct udphdr *uh;
+	unsigned int hlen, off;
+
+	off  = skb_gro_offset(skb);
+	hlen = off + sizeof(*uh);
+	uh   = skb_gro_header_fast(skb, off);
+	if (skb_gro_header_hard(skb, hlen))
+		uh = skb_gro_header_slow(skb, hlen, off);
+
+	return uh;
+}
+
 /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
 static inline void udp_lib_hash(struct sock *sk)
 {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 32f9571e776b..3549c21fe5f7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -99,6 +99,7 @@
 #include <linux/slab.h>
 #include <net/tcp_states.h>
 #include <linux/skbuff.h>
+#include <linux/netdevice.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <net/net_namespace.h>
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 59035bc3008d..8ed460e3753c 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -228,29 +228,22 @@ unlock:
 }
 EXPORT_SYMBOL(udp_del_offload);
 
-static struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
+				 struct udphdr *uh)
 {
 	struct udp_offload_priv *uo_priv;
 	struct sk_buff *p, **pp = NULL;
-	struct udphdr *uh, *uh2;
-	unsigned int hlen, off;
+	struct udphdr *uh2;
+	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
 	if (NAPI_GRO_CB(skb)->udp_mark ||
-	    (!skb->encapsulation && skb->ip_summed != CHECKSUM_COMPLETE))
+	    (!skb->encapsulation && !NAPI_GRO_CB(skb)->csum_valid))
 		goto out;
 
 	/* mark that this skb passed once through the udp gro layer */
 	NAPI_GRO_CB(skb)->udp_mark = 1;
-
-	off  = skb_gro_offset(skb);
-	hlen = off + sizeof(*uh);
-	uh   = skb_gro_header_fast(skb, off);
-	if (skb_gro_header_hard(skb, hlen)) {
-		uh = skb_gro_header_slow(skb, hlen, off);
-		if (unlikely(!uh))
-			goto out;
-	}
+	NAPI_GRO_CB(skb)->encapsulation++;
 
 	rcu_read_lock();
 	uo_priv = rcu_dereference(udp_offload_base);
@@ -269,7 +262,12 @@ unflush:
 			continue;
 
 		uh2 = (struct udphdr   *)(p->data + off);
-		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
+
+		/* Match ports and either checksums are either both zero
+		 * or nonzero.
+		 */
+		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) ||
+		    (!uh->check ^ !uh2->check)) {
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
@@ -286,7 +284,24 @@ out:
 	return pp;
 }
 
-static int udp_gro_complete(struct sk_buff *skb, int nhoff)
+static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_gro_udphdr(skb);
+
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if (unlikely(!uh) ||
+	    (!NAPI_GRO_CB(skb)->flush &&
+	     skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+						  inet_gro_compute_pseudo))) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	return udp_gro_receive(head, skb, uh);
+}
+
+int udp_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	struct udp_offload_priv *uo_priv;
 	__be16 newlen = htons(skb->len - nhoff);
@@ -311,12 +326,24 @@ static int udp_gro_complete(struct sk_buff *skb, int nhoff)
 	return err;
 }
 
+int udp4_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+
+	if (uh->check)
+		uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
+					  iph->daddr, 0);
+
+	return udp_gro_complete(skb, nhoff);
+}
+
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
 		.gso_send_check = udp4_ufo_send_check,
 		.gso_segment = udp4_ufo_fragment,
-		.gro_receive  =	udp_gro_receive,
-		.gro_complete =	udp_gro_complete,
+		.gro_receive  =	udp4_gro_receive,
+		.gro_complete =	udp4_gro_complete,
 	},
 };
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 0ae3d98f83e0..b13e377e9c53 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -10,6 +10,7 @@
  *      UDPv6 GSO support
  */
 #include <linux/skbuff.h>
+#include <linux/netdevice.h>
 #include <net/protocol.h>
 #include <net/ipv6.h>
 #include <net/udp.h>
@@ -127,10 +128,42 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 out:
 	return segs;
 }
+
+static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_gro_udphdr(skb);
+
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if (unlikely(!uh) ||
+	    (!NAPI_GRO_CB(skb)->flush &&
+	     skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+						  ip6_gro_compute_pseudo))) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	return udp_gro_receive(head, skb, uh);
+}
+
+int udp6_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+
+	if (uh->check)
+		uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr,
+					  &ipv6h->daddr, 0);
+
+	return udp_gro_complete(skb, nhoff);
+}
+
 static const struct net_offload udpv6_offload = {
 	.callbacks = {
 		.gso_send_check =	udp6_ufo_send_check,
 		.gso_segment	=	udp6_ufo_fragment,
+		.gro_receive	=	udp6_gro_receive,
+		.gro_complete	=	udp6_gro_complete,
 	},
 };
 
-- 
cgit v1.2.3


From a98406e22c12e514bac28fec0a49dc793edaf3a8 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Sat, 23 Aug 2014 17:03:28 +0200
Subject: random32: improvements to prandom_bytes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch addresses a couple of minor items, mostly addesssing
prandom_bytes(): 1) prandom_bytes{,_state}() should use size_t
for length arguments, 2) We can use put_unaligned() when filling
the array instead of open coding it [ perhaps some archs will
further benefit from their own arch specific implementation when
GCC cannot make up for it ], 3) Fix a typo, 4) Better use unsigned
int as type for getting the arch seed, 5) Make use of
prandom_u32_max() for timer slack.

Regarding the change to put_unaligned(), callers of prandom_bytes()
which internally invoke prandom_bytes_state(), don't bother as
they expect the array to be filled randomly and don't have any
control of the internal state what-so-ever (that's also why we
have periodic reseeding there, etc), so they really don't care.

Now for the direct callers of prandom_bytes_state(), which
are solely located in test cases for MTD devices, that is,
drivers/mtd/tests/{oobtest.c,pagetest.c,subpagetest.c}:

These tests basically fill a test write-vector through
prandom_bytes_state() with an a-priori defined seed each time
and write that to a MTD device. Later on, they set up a read-vector
and read back that blocks from the device. So in the verification
phase, the write-vector is being re-setup [ so same seed and
prandom_bytes_state() called ], and then memcmp()'ed against the
read-vector to check if the data is the same.

Akinobu, Lothar and I also tested this patch and it runs through
the 3 relevant MTD test cases w/o any errors on the nandsim device
(simulator for MTD devs) for x86_64, ppc64, ARM (i.MX28, i.MX53
and i.MX6):

  # modprobe nandsim first_id_byte=0x20 second_id_byte=0xac \
                     third_id_byte=0x00 fourth_id_byte=0x15
  # modprobe mtd_oobtest dev=0
  # modprobe mtd_pagetest dev=0
  # modprobe mtd_subpagetest dev=0

We also don't have any users depending directly on a particular
result of the PRNG (except the PRNG self-test itself), and that's
just fine as it e.g. allowed us easily to do things like upgrading
from taus88 to taus113.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Tested-by: Akinobu Mita <akinobu.mita@gmail.com>
Tested-by: Lothar Waßmann <LW@KARO-electronics.de>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/random.h |  4 ++--
 lib/random32.c         | 39 ++++++++++++++++++---------------------
 2 files changed, 20 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/random.h b/include/linux/random.h
index 57fbbffd77a0..b05856e16b75 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -26,7 +26,7 @@ unsigned int get_random_int(void);
 unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len);
 
 u32 prandom_u32(void);
-void prandom_bytes(void *buf, int nbytes);
+void prandom_bytes(void *buf, size_t nbytes);
 void prandom_seed(u32 seed);
 void prandom_reseed_late(void);
 
@@ -35,7 +35,7 @@ struct rnd_state {
 };
 
 u32 prandom_u32_state(struct rnd_state *state);
-void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes);
+void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
 
 /**
  * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro)
diff --git a/lib/random32.c b/lib/random32.c
index c9b6bf3afe0c..0bee183fa18f 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -37,6 +37,7 @@
 #include <linux/jiffies.h>
 #include <linux/random.h>
 #include <linux/sched.h>
+#include <asm/unaligned.h>
 
 #ifdef CONFIG_RANDOM32_SELFTEST
 static void __init prandom_state_selftest(void);
@@ -96,27 +97,23 @@ EXPORT_SYMBOL(prandom_u32);
  *	This is used for pseudo-randomness with no outside seeding.
  *	For more random results, use prandom_bytes().
  */
-void prandom_bytes_state(struct rnd_state *state, void *buf, int bytes)
+void prandom_bytes_state(struct rnd_state *state, void *buf, size_t bytes)
 {
-	unsigned char *p = buf;
-	int i;
-
-	for (i = 0; i < round_down(bytes, sizeof(u32)); i += sizeof(u32)) {
-		u32 random = prandom_u32_state(state);
-		int j;
+	u8 *ptr = buf;
 
-		for (j = 0; j < sizeof(u32); j++) {
-			p[i + j] = random;
-			random >>= BITS_PER_BYTE;
-		}
+	while (bytes >= sizeof(u32)) {
+		put_unaligned(prandom_u32_state(state), (u32 *) ptr);
+		ptr += sizeof(u32);
+		bytes -= sizeof(u32);
 	}
-	if (i < bytes) {
-		u32 random = prandom_u32_state(state);
 
-		for (; i < bytes; i++) {
-			p[i] = random;
-			random >>= BITS_PER_BYTE;
-		}
+	if (bytes > 0) {
+		u32 rem = prandom_u32_state(state);
+		do {
+			*ptr++ = (u8) rem;
+			bytes--;
+			rem >>= BITS_PER_BYTE;
+		} while (bytes > 0);
 	}
 }
 EXPORT_SYMBOL(prandom_bytes_state);
@@ -126,7 +123,7 @@ EXPORT_SYMBOL(prandom_bytes_state);
  *	@buf: where to copy the pseudo-random bytes to
  *	@bytes: the requested number of bytes
  */
-void prandom_bytes(void *buf, int bytes)
+void prandom_bytes(void *buf, size_t bytes)
 {
 	struct rnd_state *state = &get_cpu_var(net_rand_state);
 
@@ -137,7 +134,7 @@ EXPORT_SYMBOL(prandom_bytes);
 
 static void prandom_warmup(struct rnd_state *state)
 {
-	/* Calling RNG ten times to satify recurrence condition */
+	/* Calling RNG ten times to satisfy recurrence condition */
 	prandom_u32_state(state);
 	prandom_u32_state(state);
 	prandom_u32_state(state);
@@ -152,7 +149,7 @@ static void prandom_warmup(struct rnd_state *state)
 
 static u32 __extract_hwseed(void)
 {
-	u32 val = 0;
+	unsigned int val = 0;
 
 	(void)(arch_get_random_seed_int(&val) ||
 	       arch_get_random_int(&val));
@@ -228,7 +225,7 @@ static void __prandom_timer(unsigned long dontcare)
 	prandom_seed(entropy);
 
 	/* reseed every ~60 seconds, in [40 .. 80) interval with slack */
-	expires = 40 + (prandom_u32() % 40);
+	expires = 40 + prandom_u32_max(40);
 	seed_timer.expires = jiffies + msecs_to_jiffies(expires * MSEC_PER_SEC);
 
 	add_timer(&seed_timer);
-- 
cgit v1.2.3


From 4798248e4e023170e937a65a1d30fcc52496dd42 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 22 Aug 2014 16:21:53 -0700
Subject: net: Add ops->ndo_xmit_flush()

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/dlci.c              |  2 +-
 drivers/usb/gadget/function/f_ncm.c |  2 +-
 include/linux/netdevice.h           | 35 +++++++++++++++++++++++++++++++++++
 net/atm/mpc.c                       |  2 +-
 net/core/dev.c                      |  5 ++---
 net/core/netpoll.c                  |  3 +--
 net/core/pktgen.c                   |  4 +---
 net/packet/af_packet.c              |  3 +--
 net/sched/sch_teql.c                |  3 +--
 9 files changed, 44 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 43c9960dce1c..81b22a180aad 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -193,7 +193,7 @@ static netdev_tx_t dlci_transmit(struct sk_buff *skb, struct net_device *dev)
 	struct dlci_local *dlp = netdev_priv(dev);
 
 	if (skb)
-		dlp->slave->netdev_ops->ndo_start_xmit(skb, dlp->slave);
+		netdev_start_xmit(skb, dlp->slave);
 	return NETDEV_TX_OK;
 }
 
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index bcdc882cd415..cb5d646db6a7 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -1101,7 +1101,7 @@ static void ncm_tx_tasklet(unsigned long data)
 	/* Only send if data is available. */
 	if (ncm->skb_tx_data) {
 		ncm->timer_force_tx = true;
-		ncm->netdev->netdev_ops->ndo_start_xmit(NULL, ncm->netdev);
+		netdev_start_xmit(NULL, ncm->netdev);
 		ncm->timer_force_tx = false;
 	}
 }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index eb73444e1bd0..220c50984688 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -782,6 +782,19 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
  *	Required can not be NULL.
  *
+ * void (*ndo_xmit_flush)(struct net_device *dev, u16 queue);
+ *	A driver implements this function when it wishes to support
+ *	deferred TX queue flushing.  The idea is that the expensive
+ *	operation to trigger TX queue processing can be done after
+ *	N calls to ndo_start_xmit rather than being done every single
+ *	time.  In this regime ndo_start_xmit will be called one or more
+ *	times, and then a final ndo_xmit_flush call will be made to
+ *	have the driver tell the device about the new pending TX queue
+ *	entries.  The kernel keeps track of which queues need flushing
+ *	by monitoring skb->queue_mapping of the packets it submits to
+ *	ndo_start_xmit.  This is the queue value that will be passed
+ *	to ndo_xmit_flush.
+ *
  * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
  *                         void *accel_priv, select_queue_fallback_t fallback);
  *	Called to decide which queue to when device supports multiple
@@ -1005,6 +1018,7 @@ struct net_device_ops {
 	int			(*ndo_stop)(struct net_device *dev);
 	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
 						   struct net_device *dev);
+	void			(*ndo_xmit_flush)(struct net_device *dev, u16 queue);
 	u16			(*ndo_select_queue)(struct net_device *dev,
 						    struct sk_buff *skb,
 						    void *accel_priv,
@@ -3430,6 +3444,27 @@ int __init dev_proc_init(void);
 #define dev_proc_init() 0
 #endif
 
+static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
+					      struct sk_buff *skb, struct net_device *dev)
+{
+	netdev_tx_t ret;
+	u16 q;
+
+	q = skb->queue_mapping;
+	ret = ops->ndo_start_xmit(skb, dev);
+	if (dev_xmit_complete(ret) && ops->ndo_xmit_flush)
+		ops->ndo_xmit_flush(dev, q);
+
+	return ret;
+}
+
+static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	return __netdev_start_xmit(ops, skb, dev);
+}
+
 int netdev_class_create_file_ns(struct class_attribute *class_attr,
 				const void *ns);
 void netdev_class_remove_file_ns(struct class_attribute *class_attr,
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index e8e0e7a8a23d..d662da161e5a 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -599,7 +599,7 @@ static netdev_tx_t mpc_send_packet(struct sk_buff *skb,
 	}
 
 non_ip:
-	return mpc->old_ops->ndo_start_xmit(skb, dev);
+	return __netdev_start_xmit(mpc->old_ops, skb, dev);
 }
 
 static int atm_mpoa_vcc_attach(struct atm_vcc *vcc, void __user *arg)
diff --git a/net/core/dev.c b/net/core/dev.c
index b6a718ec11c1..26d296c2447c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2602,7 +2602,6 @@ EXPORT_SYMBOL(netif_skb_features);
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			struct netdev_queue *txq)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc = NETDEV_TX_OK;
 	unsigned int skb_len;
 
@@ -2667,7 +2666,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 		skb_len = skb->len;
 		trace_net_dev_start_xmit(skb, dev);
-		rc = ops->ndo_start_xmit(skb, dev);
+		rc = netdev_start_xmit(skb, dev);
 		trace_net_dev_xmit(skb, rc, dev, skb_len);
 		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
@@ -2686,7 +2685,7 @@ gso:
 
 		skb_len = nskb->len;
 		trace_net_dev_start_xmit(nskb, dev);
-		rc = ops->ndo_start_xmit(nskb, dev);
+		rc = netdev_start_xmit(nskb, dev);
 		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 907fb5e36c02..a5ad06828d67 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -72,7 +72,6 @@ module_param(carrier_timeout, uint, 0644);
 static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			      struct netdev_queue *txq)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
 	int status = NETDEV_TX_OK;
 	netdev_features_t features;
 
@@ -92,7 +91,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 		skb->vlan_tci = 0;
 	}
 
-	status = ops->ndo_start_xmit(skb, dev);
+	status = netdev_start_xmit(skb, dev);
 	if (status == NETDEV_TX_OK)
 		txq_trans_update(txq);
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 8b849ddfef2e..83e2b4b19eb7 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3285,8 +3285,6 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev)
 static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 {
 	struct net_device *odev = pkt_dev->odev;
-	netdev_tx_t (*xmit)(struct sk_buff *, struct net_device *)
-		= odev->netdev_ops->ndo_start_xmit;
 	struct netdev_queue *txq;
 	u16 queue_map;
 	int ret;
@@ -3339,7 +3337,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 		goto unlock;
 	}
 	atomic_inc(&(pkt_dev->skb->users));
-	ret = (*xmit)(pkt_dev->skb, odev);
+	ret = netdev_start_xmit(pkt_dev->skb, odev);
 
 	switch (ret) {
 	case NETDEV_TX_OK:
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 93896d2092f6..0dfa990d4eaa 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -240,7 +240,6 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
 static int packet_direct_xmit(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
-	const struct net_device_ops *ops = dev->netdev_ops;
 	netdev_features_t features;
 	struct netdev_queue *txq;
 	int ret = NETDEV_TX_BUSY;
@@ -262,7 +261,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_drv_stopped(txq)) {
-		ret = ops->ndo_start_xmit(skb, dev);
+		ret = netdev_start_xmit(skb, dev);
 		if (ret == NETDEV_TX_OK)
 			txq_trans_update(txq);
 	}
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index bd33793b527e..64cd93ca8104 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -301,7 +301,6 @@ restart:
 	do {
 		struct net_device *slave = qdisc_dev(q);
 		struct netdev_queue *slave_txq = netdev_get_tx_queue(slave, 0);
-		const struct net_device_ops *slave_ops = slave->netdev_ops;
 
 		if (slave_txq->qdisc_sleeping != q)
 			continue;
@@ -317,7 +316,7 @@ restart:
 				unsigned int length = qdisc_pkt_len(skb);
 
 				if (!netif_xmit_frozen_or_stopped(slave_txq) &&
-				    slave_ops->ndo_start_xmit(skb, slave) == NETDEV_TX_OK) {
+				    netdev_start_xmit(skb, slave) == NETDEV_TX_OK) {
 					txq_trans_update(slave_txq);
 					__netif_tx_unlock(slave_txq);
 					master->slaves = NEXT_SLAVE(q);
-- 
cgit v1.2.3


From fa71f32b5de2be1644ee671ddbe211d79be7847f Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Tue, 29 Jul 2014 17:14:21 +0200
Subject: HID: uhid: add ABI compatible UHID_GET_REPORT replacing UHID_FEATURE

The old hdev->hid_get_raw_report() was broken by design. It was never
clear what kind of HW request it should trigger. Benjamin fixed that with
the core HID cleanup, though we never really adjusted uhid.

Unfortunately, our old UHID_FEATURE command was modelled around the broken
hid_get_raw_report(). We converted it silently to the new GET_REPORT and
nothing broke. Make this explicit by renaming UHID_FEATURE to
UHID_GET_REPORT and UHID_FEATURE_ANSWER to UHID_GET_REPORT_REPLY.

Note that this is 100% ABI compatible to UHID_FEATURE. This is just a
rename. But we have to keep the old definitions around to not break API.

>From now on, UHID_GET_REPORT must trigger a GET_REPORT request on the
user-space hardware layer. All the ambiguity due to the weird "feature"
name should be gone now.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/uhid.c        | 28 ++++++++++++++--------------
 include/uapi/linux/uhid.h | 23 +++++++++++++++++++++--
 2 files changed, 35 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index 2d2025a027fe..8f5e46b1bb46 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -124,8 +124,8 @@ static int uhid_hid_parse(struct hid_device *hid)
 	return hid_parse_report(hid, uhid->rd_data, uhid->rd_size);
 }
 
-static int uhid_hid_get_raw(struct hid_device *hid, unsigned char rnum,
-			    __u8 *buf, size_t count, unsigned char rtype)
+static int uhid_hid_get_report(struct hid_device *hid, unsigned char rnum,
+			       __u8 *buf, size_t count, unsigned char rtype)
 {
 	struct uhid_device *uhid = hid->driver_data;
 	__u8 report_type;
@@ -133,7 +133,7 @@ static int uhid_hid_get_raw(struct hid_device *hid, unsigned char rnum,
 	unsigned long flags;
 	int ret;
 	size_t uninitialized_var(len);
-	struct uhid_feature_answer_req *req;
+	struct uhid_get_report_reply_req *req;
 
 	if (!uhid->running)
 		return -EIO;
@@ -163,10 +163,10 @@ static int uhid_hid_get_raw(struct hid_device *hid, unsigned char rnum,
 	}
 
 	spin_lock_irqsave(&uhid->qlock, flags);
-	ev->type = UHID_FEATURE;
-	ev->u.feature.id = ++uhid->report_id;
-	ev->u.feature.rnum = rnum;
-	ev->u.feature.rtype = report_type;
+	ev->type = UHID_GET_REPORT;
+	ev->u.get_report.id = ++uhid->report_id;
+	ev->u.get_report.rnum = rnum;
+	ev->u.get_report.rtype = report_type;
 
 	uhid->report_running = true;
 	uhid_queue(uhid, ev);
@@ -182,7 +182,7 @@ static int uhid_hid_get_raw(struct hid_device *hid, unsigned char rnum,
 		ret = -ERESTARTSYS;
 	} else {
 		spin_lock_irqsave(&uhid->qlock, flags);
-		req = &uhid->report_buf.u.feature_answer;
+		req = &uhid->report_buf.u.get_report_reply;
 
 		if (req->err) {
 			ret = -EIO;
@@ -253,7 +253,7 @@ static int uhid_raw_request(struct hid_device *hid, unsigned char reportnum,
 {
 	switch (reqtype) {
 	case HID_REQ_GET_REPORT:
-		return uhid_hid_get_raw(hid, reportnum, buf, len, rtype);
+		return uhid_hid_get_report(hid, reportnum, buf, len, rtype);
 	case HID_REQ_SET_REPORT:
 		/* TODO: implement proper SET_REPORT functionality */
 		return -ENOSYS;
@@ -487,8 +487,8 @@ static int uhid_dev_input2(struct uhid_device *uhid, struct uhid_event *ev)
 	return 0;
 }
 
-static int uhid_dev_feature_answer(struct uhid_device *uhid,
-				   struct uhid_event *ev)
+static int uhid_dev_get_report_reply(struct uhid_device *uhid,
+				     struct uhid_event *ev)
 {
 	unsigned long flags;
 
@@ -498,7 +498,7 @@ static int uhid_dev_feature_answer(struct uhid_device *uhid,
 	spin_lock_irqsave(&uhid->qlock, flags);
 
 	/* id for old report; drop it silently */
-	if (uhid->report_id != ev->u.feature_answer.id)
+	if (uhid->report_id != ev->u.get_report_reply.id)
 		goto unlock;
 	if (!uhid->report_running)
 		goto unlock;
@@ -634,8 +634,8 @@ static ssize_t uhid_char_write(struct file *file, const char __user *buffer,
 	case UHID_INPUT2:
 		ret = uhid_dev_input2(uhid, &uhid->input_buf);
 		break;
-	case UHID_FEATURE_ANSWER:
-		ret = uhid_dev_feature_answer(uhid, &uhid->input_buf);
+	case UHID_GET_REPORT_REPLY:
+		ret = uhid_dev_get_report_reply(uhid, &uhid->input_buf);
 		break;
 	default:
 		ret = -EOPNOTSUPP;
diff --git a/include/uapi/linux/uhid.h b/include/uapi/linux/uhid.h
index 1e3b09c191cd..0a08f2bbe642 100644
--- a/include/uapi/linux/uhid.h
+++ b/include/uapi/linux/uhid.h
@@ -33,8 +33,10 @@ enum uhid_event_type {
 	UHID_OUTPUT,
 	UHID_OUTPUT_EV,			/* obsolete! */
 	UHID_INPUT,
-	UHID_FEATURE,
-	UHID_FEATURE_ANSWER,
+	UHID_FEATURE,			/* obsolete! use UHID_GET_REPORT */
+	UHID_GET_REPORT = UHID_FEATURE,
+	UHID_FEATURE_ANSWER,		/* obsolete! use UHID_GET_REPORT_REPLY */
+	UHID_GET_REPORT_REPLY = UHID_FEATURE_ANSWER,
 	UHID_CREATE2,
 	UHID_INPUT2,
 };
@@ -98,12 +100,20 @@ struct uhid_output_ev_req {
 	__s32 value;
 } __attribute__((__packed__));
 
+/* Obsolete! Kernel uses ABI compatible UHID_GET_REPORT. */
 struct uhid_feature_req {
 	__u32 id;
 	__u8 rnum;
 	__u8 rtype;
 } __attribute__((__packed__));
 
+struct uhid_get_report_req {
+	__u32 id;
+	__u8 rnum;
+	__u8 rtype;
+} __attribute__((__packed__));
+
+/* Obsolete! Use ABI compatible UHID_GET_REPORT_REPLY. */
 struct uhid_feature_answer_req {
 	__u32 id;
 	__u16 err;
@@ -111,6 +121,13 @@ struct uhid_feature_answer_req {
 	__u8 data[UHID_DATA_MAX];
 } __attribute__((__packed__));
 
+struct uhid_get_report_reply_req {
+	__u32 id;
+	__u16 err;
+	__u16 size;
+	__u8 data[UHID_DATA_MAX];
+} __attribute__((__packed__));
+
 struct uhid_event {
 	__u32 type;
 
@@ -120,7 +137,9 @@ struct uhid_event {
 		struct uhid_output_req output;
 		struct uhid_output_ev_req output_ev;
 		struct uhid_feature_req feature;
+		struct uhid_get_report_req get_report;
 		struct uhid_feature_answer_req feature_answer;
+		struct uhid_get_report_reply_req get_report_reply;
 		struct uhid_create2_req create2;
 		struct uhid_input2_req input2;
 	} u;
-- 
cgit v1.2.3


From 50598e7055d0d8610732e7eb2c84cbc3bc7db294 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Tue, 29 Jul 2014 17:14:22 +0200
Subject: HID: uhid: keep legacy definitions at the bottom of uhid.h

Instead of inlining the legacy definitions into the main part of uhid.h,
keep them at the bottom now. This way, the API is much easier to read and
legacy requests can be looked up at a separate place.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/uapi/linux/uhid.h | 101 ++++++++++++++++++++++++++++------------------
 1 file changed, 62 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/uhid.h b/include/uapi/linux/uhid.h
index 0a08f2bbe642..116536eeae62 100644
--- a/include/uapi/linux/uhid.h
+++ b/include/uapi/linux/uhid.h
@@ -24,37 +24,21 @@
 #include <linux/hid.h>
 
 enum uhid_event_type {
-	UHID_CREATE,
+	__UHID_LEGACY_CREATE,
 	UHID_DESTROY,
 	UHID_START,
 	UHID_STOP,
 	UHID_OPEN,
 	UHID_CLOSE,
 	UHID_OUTPUT,
-	UHID_OUTPUT_EV,			/* obsolete! */
-	UHID_INPUT,
-	UHID_FEATURE,			/* obsolete! use UHID_GET_REPORT */
-	UHID_GET_REPORT = UHID_FEATURE,
-	UHID_FEATURE_ANSWER,		/* obsolete! use UHID_GET_REPORT_REPLY */
-	UHID_GET_REPORT_REPLY = UHID_FEATURE_ANSWER,
+	__UHID_LEGACY_OUTPUT_EV,
+	__UHID_LEGACY_INPUT,
+	UHID_GET_REPORT,
+	UHID_GET_REPORT_REPLY,
 	UHID_CREATE2,
 	UHID_INPUT2,
 };
 
-struct uhid_create_req {
-	__u8 name[128];
-	__u8 phys[64];
-	__u8 uniq[64];
-	__u8 __user *rd_data;
-	__u16 rd_size;
-
-	__u16 bus;
-	__u32 vendor;
-	__u32 product;
-	__u32 version;
-	__u32 country;
-} __attribute__((__packed__));
-
 struct uhid_create2_req {
 	__u8 name[128];
 	__u8 phys[64];
@@ -76,24 +60,67 @@ enum uhid_report_type {
 	UHID_INPUT_REPORT,
 };
 
-struct uhid_input_req {
+struct uhid_input2_req {
+	__u16 size;
+	__u8 data[UHID_DATA_MAX];
+} __attribute__((__packed__));
+
+struct uhid_output_req {
 	__u8 data[UHID_DATA_MAX];
 	__u16 size;
+	__u8 rtype;
 } __attribute__((__packed__));
 
-struct uhid_input2_req {
+struct uhid_get_report_req {
+	__u32 id;
+	__u8 rnum;
+	__u8 rtype;
+} __attribute__((__packed__));
+
+struct uhid_get_report_reply_req {
+	__u32 id;
+	__u16 err;
 	__u16 size;
 	__u8 data[UHID_DATA_MAX];
 } __attribute__((__packed__));
 
-struct uhid_output_req {
+/*
+ * Compat Layer
+ * All these commands and requests are obsolete. You should avoid using them in
+ * new code. We support them for backwards-compatibility, but you might not get
+ * access to new feature in case you use them.
+ */
+
+enum uhid_legacy_event_type {
+	UHID_CREATE			= __UHID_LEGACY_CREATE,
+	UHID_OUTPUT_EV			= __UHID_LEGACY_OUTPUT_EV,
+	UHID_INPUT			= __UHID_LEGACY_INPUT,
+	UHID_FEATURE			= UHID_GET_REPORT,
+	UHID_FEATURE_ANSWER		= UHID_GET_REPORT_REPLY,
+};
+
+/* Obsolete! Use UHID_CREATE2. */
+struct uhid_create_req {
+	__u8 name[128];
+	__u8 phys[64];
+	__u8 uniq[64];
+	__u8 __user *rd_data;
+	__u16 rd_size;
+
+	__u16 bus;
+	__u32 vendor;
+	__u32 product;
+	__u32 version;
+	__u32 country;
+} __attribute__((__packed__));
+
+/* Obsolete! Use UHID_INPUT2. */
+struct uhid_input_req {
 	__u8 data[UHID_DATA_MAX];
 	__u16 size;
-	__u8 rtype;
 } __attribute__((__packed__));
 
-/* Obsolete! Newer kernels will no longer send these events but instead convert
- * it into raw output reports via UHID_OUTPUT. */
+/* Obsolete! Kernel uses UHID_OUTPUT exclusively now. */
 struct uhid_output_ev_req {
 	__u16 type;
 	__u16 code;
@@ -107,12 +134,6 @@ struct uhid_feature_req {
 	__u8 rtype;
 } __attribute__((__packed__));
 
-struct uhid_get_report_req {
-	__u32 id;
-	__u8 rnum;
-	__u8 rtype;
-} __attribute__((__packed__));
-
 /* Obsolete! Use ABI compatible UHID_GET_REPORT_REPLY. */
 struct uhid_feature_answer_req {
 	__u32 id;
@@ -121,12 +142,14 @@ struct uhid_feature_answer_req {
 	__u8 data[UHID_DATA_MAX];
 } __attribute__((__packed__));
 
-struct uhid_get_report_reply_req {
-	__u32 id;
-	__u16 err;
-	__u16 size;
-	__u8 data[UHID_DATA_MAX];
-} __attribute__((__packed__));
+/*
+ * UHID Events
+ * All UHID events from and to the kernel are encoded as "struct uhid_event".
+ * The "type" field contains a UHID_* type identifier. All payload depends on
+ * that type and can be accessed via ev->u.XYZ accordingly.
+ * If user-space writes short events, they're extended with 0s by the kernel. If
+ * the kernel writes short events, user-space shall extend them with 0s.
+ */
 
 struct uhid_event {
 	__u32 type;
-- 
cgit v1.2.3


From 11c221553080408b203a00b91ad5f647dfb218d1 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Tue, 29 Jul 2014 17:14:24 +0200
Subject: HID: uhid: implement SET_REPORT

We so far lacked support for hid_hw_raw_request(..., HID_REQ_SET_REPORT);
Add support for it and simply forward the request to user-space. Note that
SET_REPORT is synchronous, just like GET_REPORT, even though it does not
provide any data back besides an error code.

If a transport layer does SET_REPORT asynchronously, they can just ACK it
immediately by writing an uhid_set_report_reply to uhid.

This patch re-uses the synchronous uhid-report infrastructure to query
user-space. Note that this means you cannot run SET_REPORT and GET_REPORT
in parallel. However, that has always been a restriction of HID and due to
its blocking nature, this is just fine. Maybe some future transport layer
supports parallel requests (very unlikely), however, until then lets not
over-complicate things and avoid request-lookup-tables.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/uhid.c        | 206 +++++++++++++++++++++++++++++++---------------
 include/uapi/linux/uhid.h |  17 ++++
 2 files changed, 155 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index 8bf613e3783d..19511481a7d3 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -49,6 +49,7 @@ struct uhid_device {
 	wait_queue_head_t report_wait;
 	bool report_running;
 	u32 report_id;
+	u32 report_type;
 	struct uhid_event report_buf;
 };
 
@@ -124,95 +125,166 @@ static int uhid_hid_parse(struct hid_device *hid)
 	return hid_parse_report(hid, uhid->rd_data, uhid->rd_size);
 }
 
+/* must be called with report_lock held */
+static int __uhid_report_queue_and_wait(struct uhid_device *uhid,
+					struct uhid_event *ev,
+					__u32 *report_id)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&uhid->qlock, flags);
+	*report_id = ++uhid->report_id;
+	uhid->report_type = ev->type;
+	uhid->report_running = true;
+	uhid_queue(uhid, ev);
+	spin_unlock_irqrestore(&uhid->qlock, flags);
+
+	ret = wait_event_interruptible_timeout(uhid->report_wait,
+				!uhid->report_running || !uhid->running,
+				5 * HZ);
+	if (!ret || !uhid->running || uhid->report_running)
+		ret = -EIO;
+	else if (ret < 0)
+		ret = -ERESTARTSYS;
+	else
+		ret = 0;
+
+	uhid->report_running = false;
+
+	return ret;
+}
+
+static void uhid_report_wake_up(struct uhid_device *uhid, u32 id,
+				const struct uhid_event *ev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&uhid->qlock, flags);
+
+	/* id for old report; drop it silently */
+	if (uhid->report_type != ev->type || uhid->report_id != id)
+		goto unlock;
+	if (!uhid->report_running)
+		goto unlock;
+
+	memcpy(&uhid->report_buf, ev, sizeof(*ev));
+	uhid->report_running = false;
+	wake_up_interruptible(&uhid->report_wait);
+
+unlock:
+	spin_unlock_irqrestore(&uhid->qlock, flags);
+}
+
 static int uhid_hid_get_report(struct hid_device *hid, unsigned char rnum,
-			       __u8 *buf, size_t count, unsigned char rtype)
+			       u8 *buf, size_t count, u8 rtype)
 {
 	struct uhid_device *uhid = hid->driver_data;
-	__u8 report_type;
+	struct uhid_get_report_reply_req *req;
 	struct uhid_event *ev;
-	unsigned long flags;
 	int ret;
-	size_t uninitialized_var(len);
-	struct uhid_get_report_reply_req *req;
 
 	if (!uhid->running)
 		return -EIO;
 
-	switch (rtype) {
-	case HID_FEATURE_REPORT:
-		report_type = UHID_FEATURE_REPORT;
-		break;
-	case HID_OUTPUT_REPORT:
-		report_type = UHID_OUTPUT_REPORT;
-		break;
-	case HID_INPUT_REPORT:
-		report_type = UHID_INPUT_REPORT;
-		break;
-	default:
-		return -EINVAL;
-	}
+	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->type = UHID_GET_REPORT;
+	ev->u.get_report.rnum = rnum;
+	ev->u.get_report.rtype = rtype;
 
 	ret = mutex_lock_interruptible(&uhid->report_lock);
-	if (ret)
+	if (ret) {
+		kfree(ev);
 		return ret;
+	}
 
-	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
-	if (!ev) {
-		ret = -ENOMEM;
+	/* this _always_ takes ownership of @ev */
+	ret = __uhid_report_queue_and_wait(uhid, ev, &ev->u.get_report.id);
+	if (ret)
 		goto unlock;
+
+	req = &uhid->report_buf.u.get_report_reply;
+	if (req->err) {
+		ret = -EIO;
+	} else {
+		ret = min3(count, (size_t)req->size, (size_t)UHID_DATA_MAX);
+		memcpy(buf, req->data, ret);
 	}
 
-	spin_lock_irqsave(&uhid->qlock, flags);
-	ev->type = UHID_GET_REPORT;
-	ev->u.get_report.id = ++uhid->report_id;
-	ev->u.get_report.rnum = rnum;
-	ev->u.get_report.rtype = report_type;
+unlock:
+	mutex_unlock(&uhid->report_lock);
+	return ret;
+}
 
-	uhid->report_running = true;
-	uhid_queue(uhid, ev);
-	spin_unlock_irqrestore(&uhid->qlock, flags);
+static int uhid_hid_set_report(struct hid_device *hid, unsigned char rnum,
+			       const u8 *buf, size_t count, u8 rtype)
+{
+	struct uhid_device *uhid = hid->driver_data;
+	struct uhid_event *ev;
+	int ret;
 
-	ret = wait_event_interruptible_timeout(uhid->report_wait,
-				!uhid->report_running || !uhid->running,
-				5 * HZ);
+	if (!uhid->running || count > UHID_DATA_MAX)
+		return -EIO;
 
-	if (!ret || !uhid->running) {
-		ret = -EIO;
-	} else if (ret < 0) {
-		ret = -ERESTARTSYS;
-	} else {
-		spin_lock_irqsave(&uhid->qlock, flags);
-		req = &uhid->report_buf.u.get_report_reply;
+	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
+	if (!ev)
+		return -ENOMEM;
 
-		if (req->err) {
-			ret = -EIO;
-		} else {
-			ret = 0;
-			len = min(count,
-				min_t(size_t, req->size, UHID_DATA_MAX));
-			memcpy(buf, req->data, len);
-		}
+	ev->type = UHID_SET_REPORT;
+	ev->u.set_report.rnum = rnum;
+	ev->u.set_report.rtype = rtype;
+	ev->u.set_report.size = count;
+	memcpy(ev->u.set_report.data, buf, count);
 
-		spin_unlock_irqrestore(&uhid->qlock, flags);
+	ret = mutex_lock_interruptible(&uhid->report_lock);
+	if (ret) {
+		kfree(ev);
+		return ret;
 	}
 
-	uhid->report_running = false;
+	/* this _always_ takes ownership of @ev */
+	ret = __uhid_report_queue_and_wait(uhid, ev, &ev->u.set_report.id);
+	if (ret)
+		goto unlock;
+
+	if (uhid->report_buf.u.set_report_reply.err)
+		ret = -EIO;
+	else
+		ret = count;
 
 unlock:
 	mutex_unlock(&uhid->report_lock);
-	return ret ? ret : len;
+	return ret;
 }
 
 static int uhid_hid_raw_request(struct hid_device *hid, unsigned char reportnum,
 				__u8 *buf, size_t len, unsigned char rtype,
 				int reqtype)
 {
+	u8 u_rtype;
+
+	switch (rtype) {
+	case HID_FEATURE_REPORT:
+		u_rtype = UHID_FEATURE_REPORT;
+		break;
+	case HID_OUTPUT_REPORT:
+		u_rtype = UHID_OUTPUT_REPORT;
+		break;
+	case HID_INPUT_REPORT:
+		u_rtype = UHID_INPUT_REPORT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	switch (reqtype) {
 	case HID_REQ_GET_REPORT:
-		return uhid_hid_get_report(hid, reportnum, buf, len, rtype);
+		return uhid_hid_get_report(hid, reportnum, buf, len, u_rtype);
 	case HID_REQ_SET_REPORT:
-		/* TODO: implement proper SET_REPORT functionality */
-		return -ENOSYS;
+		return uhid_hid_set_report(hid, reportnum, buf, len, u_rtype);
 	default:
 		return -EIO;
 	}
@@ -490,25 +562,20 @@ static int uhid_dev_input2(struct uhid_device *uhid, struct uhid_event *ev)
 static int uhid_dev_get_report_reply(struct uhid_device *uhid,
 				     struct uhid_event *ev)
 {
-	unsigned long flags;
-
 	if (!uhid->running)
 		return -EINVAL;
 
-	spin_lock_irqsave(&uhid->qlock, flags);
-
-	/* id for old report; drop it silently */
-	if (uhid->report_id != ev->u.get_report_reply.id)
-		goto unlock;
-	if (!uhid->report_running)
-		goto unlock;
+	uhid_report_wake_up(uhid, ev->u.get_report_reply.id, ev);
+	return 0;
+}
 
-	memcpy(&uhid->report_buf, ev, sizeof(*ev));
-	uhid->report_running = false;
-	wake_up_interruptible(&uhid->report_wait);
+static int uhid_dev_set_report_reply(struct uhid_device *uhid,
+				     struct uhid_event *ev)
+{
+	if (!uhid->running)
+		return -EINVAL;
 
-unlock:
-	spin_unlock_irqrestore(&uhid->qlock, flags);
+	uhid_report_wake_up(uhid, ev->u.set_report_reply.id, ev);
 	return 0;
 }
 
@@ -637,6 +704,9 @@ static ssize_t uhid_char_write(struct file *file, const char __user *buffer,
 	case UHID_GET_REPORT_REPLY:
 		ret = uhid_dev_get_report_reply(uhid, &uhid->input_buf);
 		break;
+	case UHID_SET_REPORT_REPLY:
+		ret = uhid_dev_set_report_reply(uhid, &uhid->input_buf);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 	}
diff --git a/include/uapi/linux/uhid.h b/include/uapi/linux/uhid.h
index 116536eeae62..62aac0e4edf3 100644
--- a/include/uapi/linux/uhid.h
+++ b/include/uapi/linux/uhid.h
@@ -37,6 +37,8 @@ enum uhid_event_type {
 	UHID_GET_REPORT_REPLY,
 	UHID_CREATE2,
 	UHID_INPUT2,
+	UHID_SET_REPORT,
+	UHID_SET_REPORT_REPLY,
 };
 
 struct uhid_create2_req {
@@ -84,6 +86,19 @@ struct uhid_get_report_reply_req {
 	__u8 data[UHID_DATA_MAX];
 } __attribute__((__packed__));
 
+struct uhid_set_report_req {
+	__u32 id;
+	__u8 rnum;
+	__u8 rtype;
+	__u16 size;
+	__u8 data[UHID_DATA_MAX];
+} __attribute__((__packed__));
+
+struct uhid_set_report_reply_req {
+	__u32 id;
+	__u16 err;
+} __attribute__((__packed__));
+
 /*
  * Compat Layer
  * All these commands and requests are obsolete. You should avoid using them in
@@ -165,6 +180,8 @@ struct uhid_event {
 		struct uhid_get_report_reply_req get_report_reply;
 		struct uhid_create2_req create2;
 		struct uhid_input2_req input2;
+		struct uhid_set_report_req set_report;
+		struct uhid_set_report_reply_req set_report_reply;
 	} u;
 } __attribute__((__packed__));
 
-- 
cgit v1.2.3


From c2b2f16c5c62583d4f8904e44c4b30c94a01eaf1 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Tue, 29 Jul 2014 17:14:25 +0200
Subject: HID: uhid: report to user-space whether reports are numbered

This makes UHID_START include a "dev_flags" field that describes details
of the hid-device in the kernel. The first flags we introduce describe
whether a given report-type uses numbered reports. This is useful for
transport layers that force report-numbers and therefore might have to
prefix kernel-provided HID-messages with the report-number.

Currently, only HoG needs this and the spec only talks about "global
report numbers". That is, it's a global boolean not a per-type boolean.
However, given the quirks we already have in kernel-space, a per-type
value seems much more appropriate.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/uhid.c        | 21 ++++++++++++++++++++-
 include/uapi/linux/uhid.h | 11 +++++++++++
 2 files changed, 31 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index 19511481a7d3..f6ec5eaf6b89 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -92,8 +92,27 @@ static int uhid_queue_event(struct uhid_device *uhid, __u32 event)
 static int uhid_hid_start(struct hid_device *hid)
 {
 	struct uhid_device *uhid = hid->driver_data;
+	struct uhid_event *ev;
+	unsigned long flags;
+
+	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->type = UHID_START;
 
-	return uhid_queue_event(uhid, UHID_START);
+	if (hid->report_enum[HID_FEATURE_REPORT].numbered)
+		ev->u.start.dev_flags |= UHID_DEV_NUMBERED_FEATURE_REPORTS;
+	if (hid->report_enum[HID_OUTPUT_REPORT].numbered)
+		ev->u.start.dev_flags |= UHID_DEV_NUMBERED_OUTPUT_REPORTS;
+	if (hid->report_enum[HID_INPUT_REPORT].numbered)
+		ev->u.start.dev_flags |= UHID_DEV_NUMBERED_INPUT_REPORTS;
+
+	spin_lock_irqsave(&uhid->qlock, flags);
+	uhid_queue(uhid, ev);
+	spin_unlock_irqrestore(&uhid->qlock, flags);
+
+	return 0;
 }
 
 static void uhid_hid_stop(struct hid_device *hid)
diff --git a/include/uapi/linux/uhid.h b/include/uapi/linux/uhid.h
index 62aac0e4edf3..aaa86d6bd1dd 100644
--- a/include/uapi/linux/uhid.h
+++ b/include/uapi/linux/uhid.h
@@ -54,6 +54,16 @@ struct uhid_create2_req {
 	__u8 rd_data[HID_MAX_DESCRIPTOR_SIZE];
 } __attribute__((__packed__));
 
+enum uhid_dev_flag {
+	UHID_DEV_NUMBERED_FEATURE_REPORTS			= (1ULL << 0),
+	UHID_DEV_NUMBERED_OUTPUT_REPORTS			= (1ULL << 1),
+	UHID_DEV_NUMBERED_INPUT_REPORTS				= (1ULL << 2),
+};
+
+struct uhid_start_req {
+	__u64 dev_flags;
+};
+
 #define UHID_DATA_MAX 4096
 
 enum uhid_report_type {
@@ -182,6 +192,7 @@ struct uhid_event {
 		struct uhid_input2_req input2;
 		struct uhid_set_report_req set_report;
 		struct uhid_set_report_reply_req set_report_reply;
+		struct uhid_start_req start;
 	} u;
 } __attribute__((__packed__));
 
-- 
cgit v1.2.3


From d1c85c2ebe7ffe1f1b27846bd1ba0944c513d822 Mon Sep 17 00:00:00 2001
From: Zhouyi Zhou <zhouzhouyi@gmail.com>
Date: Fri, 22 Aug 2014 10:40:15 +0800
Subject: netfilter: HAVE_JUMP_LABEL instead of CONFIG_JUMP_LABEL

Use HAVE_JUMP_LABEL as elsewhere in the kernel to ensure
that the toolchain has the required support in addition to
CONFIG_JUMP_LABEL being set.

Signed-off-by: Zhouyi Zhou <yizhouzhou@ict.ac.cn>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h | 5 +++--
 net/netfilter/core.c      | 6 +++---
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 2077489f9887..2517ece98820 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -9,6 +9,7 @@
 #include <linux/in6.h>
 #include <linux/wait.h>
 #include <linux/list.h>
+#include <linux/static_key.h>
 #include <uapi/linux/netfilter.h>
 #ifdef CONFIG_NETFILTER
 static inline int NF_DROP_GETERR(int verdict)
@@ -99,9 +100,9 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg);
 
 extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 
-#if defined(CONFIG_JUMP_LABEL)
-#include <linux/static_key.h>
+#ifdef HAVE_JUMP_LABEL
 extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+
 static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
 {
 	if (__builtin_constant_p(pf) &&
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index a93c97f106d4..024a2e25c8a4 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -54,7 +54,7 @@ EXPORT_SYMBOL_GPL(nf_unregister_afinfo);
 struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly;
 EXPORT_SYMBOL(nf_hooks);
 
-#if defined(CONFIG_JUMP_LABEL)
+#ifdef HAVE_JUMP_LABEL
 struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 EXPORT_SYMBOL(nf_hooks_needed);
 #endif
@@ -72,7 +72,7 @@ int nf_register_hook(struct nf_hook_ops *reg)
 	}
 	list_add_rcu(&reg->list, elem->list.prev);
 	mutex_unlock(&nf_hook_mutex);
-#if defined(CONFIG_JUMP_LABEL)
+#ifdef HAVE_JUMP_LABEL
 	static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
 	return 0;
@@ -84,7 +84,7 @@ void nf_unregister_hook(struct nf_hook_ops *reg)
 	mutex_lock(&nf_hook_mutex);
 	list_del_rcu(&reg->list);
 	mutex_unlock(&nf_hook_mutex);
-#if defined(CONFIG_JUMP_LABEL)
+#ifdef HAVE_JUMP_LABEL
 	static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
 	synchronize_net();
-- 
cgit v1.2.3


From 2ee507c472939db4b146d545352b8a7c79ef47f8 Mon Sep 17 00:00:00 2001
From: Tim Chen <tim.c.chen@linux.intel.com>
Date: Thu, 31 Jul 2014 10:29:48 -0700
Subject: sched: Add function single_task_running to let a task check if it is
 the only task running on a cpu

This function will help an async task processing batched jobs from
workqueue decide if it wants to keep processing on more chunks of batched
work that can be delayed, or to accumulate more work for more efficient
batched processing later.

If no other tasks are running on the cpu, the batching process can take
advantgae of the available cpu cycles to a make decision to continue
processing the existing accumulated work to minimize delay,
otherwise it will yield.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/sched.h |  1 +
 kernel/sched/core.c   | 12 ++++++++++++
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c2c885ee52b..e6d2c056d8e0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -167,6 +167,7 @@ extern int nr_threads;
 DECLARE_PER_CPU(unsigned long, process_counts);
 extern int nr_processes(void);
 extern unsigned long nr_running(void);
+extern bool single_task_running(void);
 extern unsigned long nr_iowait(void);
 extern unsigned long nr_iowait_cpu(int cpu);
 extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ec1a286684a5..59965ec0b7de 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2366,6 +2366,18 @@ unsigned long nr_running(void)
 	return sum;
 }
 
+/*
+ * Check if only the current task is running on the cpu.
+ */
+bool single_task_running(void)
+{
+	if (cpu_rq(smp_processor_id())->nr_running == 1)
+		return true;
+	else
+		return false;
+}
+EXPORT_SYMBOL(single_task_running);
+
 unsigned long long nr_context_switches(void)
 {
 	int i;
-- 
cgit v1.2.3


From 1e65b81a90df50bf450193065cc9073b706b8dda Mon Sep 17 00:00:00 2001
From: Tim Chen <tim.c.chen@linux.intel.com>
Date: Thu, 31 Jul 2014 10:29:51 -0700
Subject: crypto: sha-mb - multibuffer crypto infrastructure

This patch introduces the multi-buffer crypto daemon which is responsible
for submitting crypto jobs in a work queue to the responsible multi-buffer
crypto algorithm.  The idea of the multi-buffer algorihtm is to put
data streams from multiple jobs in a wide (AVX2) register and then
take advantage of SIMD instructions to do crypto computation on several
buffers simultaneously.

The multi-buffer crypto daemon is also responsbile for flushing the
remaining buffers to complete the computation if no new buffers arrive
for a while.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/Kconfig                 |  30 ++
 crypto/Makefile                |   1 +
 crypto/mcryptd.c               | 705 +++++++++++++++++++++++++++++++++++++++++
 include/crypto/internal/hash.h |   9 +
 include/crypto/mcryptd.h       | 112 +++++++
 5 files changed, 857 insertions(+)
 create mode 100644 crypto/mcryptd.c
 create mode 100644 include/crypto/mcryptd.h

(limited to 'include')

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 00b5906f57b7..86dc81f80bc5 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -158,6 +158,20 @@ config CRYPTO_CRYPTD
 	  converts an arbitrary synchronous software crypto algorithm
 	  into an asynchronous algorithm that executes in a kernel thread.
 
+config CRYPTO_MCRYPTD
+	tristate "Software async multi-buffer crypto daemon"
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_HASH
+	select CRYPTO_MANAGER
+	select CRYPTO_WORKQUEUE
+	help
+	  This is a generic software asynchronous crypto daemon that
+	  provides the kernel thread to assist multi-buffer crypto
+	  algorithms for submitting jobs and flushing jobs in multi-buffer
+	  crypto algorithms.  Multi-buffer crypto algorithms are executed
+	  in the context of this kernel thread and drivers can post
+	  their crypto request asyncrhously and process by this daemon.
+
 config CRYPTO_AUTHENC
 	tristate "Authenc support"
 	select CRYPTO_AEAD
@@ -559,6 +573,22 @@ config CRYPTO_SHA1_PPC
 	  This is the powerpc hardware accelerated implementation of the
 	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2).
 
+config CRYPTO_SHA1_MB
+	tristate "SHA1 digest algorithm (x86_64 Multi-Buffer, Experimental)"
+	depends on X86 && 64BIT
+	select CRYPTO_SHA1
+	select CRYPTO_HASH
+	select CRYPTO_MCRYPTD
+	help
+	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented
+	  using multi-buffer technique.  This algorithm computes on
+	  multiple data lanes concurrently with SIMD instructions for
+	  better throughput.  It should not be enabled by default but
+	  used when there is significant amount of work to keep the keep
+	  the data lanes filled to get performance benefit.  If the data
+	  lanes remain unfilled, a flush operation will be initiated to
+	  process the crypto jobs, adding a slight latency.
+
 config CRYPTO_SHA256
 	tristate "SHA224 and SHA256 digest algorithm"
 	select CRYPTO_HASH
diff --git a/crypto/Makefile b/crypto/Makefile
index cfa57b3f5a4d..1445b9100c05 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -60,6 +60,7 @@ obj-$(CONFIG_CRYPTO_GCM) += gcm.o
 obj-$(CONFIG_CRYPTO_CCM) += ccm.o
 obj-$(CONFIG_CRYPTO_PCRYPT) += pcrypt.o
 obj-$(CONFIG_CRYPTO_CRYPTD) += cryptd.o
+obj-$(CONFIG_CRYPTO_MCRYPTD) += mcryptd.o
 obj-$(CONFIG_CRYPTO_DES) += des_generic.o
 obj-$(CONFIG_CRYPTO_FCRYPT) += fcrypt.o
 obj-$(CONFIG_CRYPTO_BLOWFISH) += blowfish_generic.o
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
new file mode 100644
index 000000000000..dbc20d1f9381
--- /dev/null
+++ b/crypto/mcryptd.c
@@ -0,0 +1,705 @@
+/*
+ * Software multibuffer async crypto daemon.
+ *
+ * Copyright (c) 2014 Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * Adapted from crypto daemon.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/aead.h>
+#include <crypto/mcryptd.h>
+#include <crypto/crypto_wq.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/hardirq.h>
+
+#define MCRYPTD_MAX_CPU_QLEN 100
+#define MCRYPTD_BATCH 9
+
+static void *mcryptd_alloc_instance(struct crypto_alg *alg, unsigned int head,
+				   unsigned int tail);
+
+struct mcryptd_flush_list {
+	struct list_head list;
+	struct mutex lock;
+};
+
+struct mcryptd_flush_list __percpu *mcryptd_flist;
+
+struct hashd_instance_ctx {
+	struct crypto_shash_spawn spawn;
+	struct mcryptd_queue *queue;
+};
+
+static void mcryptd_queue_worker(struct work_struct *work);
+
+void mcryptd_arm_flusher(struct mcryptd_alg_cstate *cstate, unsigned long delay)
+{
+	struct mcryptd_flush_list *flist;
+
+	if (!cstate->flusher_engaged) {
+		/* put the flusher on the flush list */
+		flist = per_cpu_ptr(mcryptd_flist, smp_processor_id());
+		mutex_lock(&flist->lock);
+		list_add_tail(&cstate->flush_list, &flist->list);
+		cstate->flusher_engaged = true;
+		cstate->next_flush = jiffies + delay;
+		queue_delayed_work_on(smp_processor_id(), kcrypto_wq,
+			&cstate->flush, delay);
+		mutex_unlock(&flist->lock);
+	}
+}
+EXPORT_SYMBOL(mcryptd_arm_flusher);
+
+static int mcryptd_init_queue(struct mcryptd_queue *queue,
+			     unsigned int max_cpu_qlen)
+{
+	int cpu;
+	struct mcryptd_cpu_queue *cpu_queue;
+
+	queue->cpu_queue = alloc_percpu(struct mcryptd_cpu_queue);
+	pr_debug("mqueue:%p mcryptd_cpu_queue %p\n", queue, queue->cpu_queue);
+	if (!queue->cpu_queue)
+		return -ENOMEM;
+	for_each_possible_cpu(cpu) {
+		cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu);
+		pr_debug("cpu_queue #%d %p\n", cpu, queue->cpu_queue);
+		crypto_init_queue(&cpu_queue->queue, max_cpu_qlen);
+		INIT_WORK(&cpu_queue->work, mcryptd_queue_worker);
+	}
+	return 0;
+}
+
+static void mcryptd_fini_queue(struct mcryptd_queue *queue)
+{
+	int cpu;
+	struct mcryptd_cpu_queue *cpu_queue;
+
+	for_each_possible_cpu(cpu) {
+		cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu);
+		BUG_ON(cpu_queue->queue.qlen);
+	}
+	free_percpu(queue->cpu_queue);
+}
+
+static int mcryptd_enqueue_request(struct mcryptd_queue *queue,
+				  struct crypto_async_request *request,
+				  struct mcryptd_hash_request_ctx *rctx)
+{
+	int cpu, err;
+	struct mcryptd_cpu_queue *cpu_queue;
+
+	cpu = get_cpu();
+	cpu_queue = this_cpu_ptr(queue->cpu_queue);
+	rctx->tag.cpu = cpu;
+
+	err = crypto_enqueue_request(&cpu_queue->queue, request);
+	pr_debug("enqueue request: cpu %d cpu_queue %p request %p\n",
+		 cpu, cpu_queue, request);
+	queue_work_on(cpu, kcrypto_wq, &cpu_queue->work);
+	put_cpu();
+
+	return err;
+}
+
+/*
+ * Try to opportunisticlly flush the partially completed jobs if
+ * crypto daemon is the only task running.
+ */
+static void mcryptd_opportunistic_flush(void)
+{
+	struct mcryptd_flush_list *flist;
+	struct mcryptd_alg_cstate *cstate;
+
+	flist = per_cpu_ptr(mcryptd_flist, smp_processor_id());
+	while (single_task_running()) {
+		mutex_lock(&flist->lock);
+		if (list_empty(&flist->list)) {
+			mutex_unlock(&flist->lock);
+			return;
+		}
+		cstate = list_entry(flist->list.next,
+				struct mcryptd_alg_cstate, flush_list);
+		if (!cstate->flusher_engaged) {
+			mutex_unlock(&flist->lock);
+			return;
+		}
+		list_del(&cstate->flush_list);
+		cstate->flusher_engaged = false;
+		mutex_unlock(&flist->lock);
+		cstate->alg_state->flusher(cstate);
+	}
+}
+
+/*
+ * Called in workqueue context, do one real cryption work (via
+ * req->complete) and reschedule itself if there are more work to
+ * do.
+ */
+static void mcryptd_queue_worker(struct work_struct *work)
+{
+	struct mcryptd_cpu_queue *cpu_queue;
+	struct crypto_async_request *req, *backlog;
+	int i;
+
+	/*
+	 * Need to loop through more than once for multi-buffer to
+	 * be effective.
+	 */
+
+	cpu_queue = container_of(work, struct mcryptd_cpu_queue, work);
+	i = 0;
+	while (i < MCRYPTD_BATCH || single_task_running()) {
+		/*
+		 * preempt_disable/enable is used to prevent
+		 * being preempted by mcryptd_enqueue_request()
+		 */
+		local_bh_disable();
+		preempt_disable();
+		backlog = crypto_get_backlog(&cpu_queue->queue);
+		req = crypto_dequeue_request(&cpu_queue->queue);
+		preempt_enable();
+		local_bh_enable();
+
+		if (!req) {
+			mcryptd_opportunistic_flush();
+			return;
+		}
+
+		if (backlog)
+			backlog->complete(backlog, -EINPROGRESS);
+		req->complete(req, 0);
+		if (!cpu_queue->queue.qlen)
+			return;
+		++i;
+	}
+	if (cpu_queue->queue.qlen)
+		queue_work(kcrypto_wq, &cpu_queue->work);
+}
+
+void mcryptd_flusher(struct work_struct *__work)
+{
+	struct	mcryptd_alg_cstate	*alg_cpu_state;
+	struct	mcryptd_alg_state	*alg_state;
+	struct	mcryptd_flush_list	*flist;
+	int	cpu;
+
+	cpu = smp_processor_id();
+	alg_cpu_state = container_of(to_delayed_work(__work),
+				     struct mcryptd_alg_cstate, flush);
+	alg_state = alg_cpu_state->alg_state;
+	if (alg_cpu_state->cpu != cpu)
+		pr_debug("mcryptd error: work on cpu %d, should be cpu %d\n",
+				cpu, alg_cpu_state->cpu);
+
+	if (alg_cpu_state->flusher_engaged) {
+		flist = per_cpu_ptr(mcryptd_flist, cpu);
+		mutex_lock(&flist->lock);
+		list_del(&alg_cpu_state->flush_list);
+		alg_cpu_state->flusher_engaged = false;
+		mutex_unlock(&flist->lock);
+		alg_state->flusher(alg_cpu_state);
+	}
+}
+EXPORT_SYMBOL_GPL(mcryptd_flusher);
+
+static inline struct mcryptd_queue *mcryptd_get_queue(struct crypto_tfm *tfm)
+{
+	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
+	struct mcryptd_instance_ctx *ictx = crypto_instance_ctx(inst);
+
+	return ictx->queue;
+}
+
+static void *mcryptd_alloc_instance(struct crypto_alg *alg, unsigned int head,
+				   unsigned int tail)
+{
+	char *p;
+	struct crypto_instance *inst;
+	int err;
+
+	p = kzalloc(head + sizeof(*inst) + tail, GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	inst = (void *)(p + head);
+
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		    "mcryptd(%s)", alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		goto out_free_inst;
+
+	memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
+
+	inst->alg.cra_priority = alg->cra_priority + 50;
+	inst->alg.cra_blocksize = alg->cra_blocksize;
+	inst->alg.cra_alignmask = alg->cra_alignmask;
+
+out:
+	return p;
+
+out_free_inst:
+	kfree(p);
+	p = ERR_PTR(err);
+	goto out;
+}
+
+static int mcryptd_hash_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
+	struct hashd_instance_ctx *ictx = crypto_instance_ctx(inst);
+	struct crypto_shash_spawn *spawn = &ictx->spawn;
+	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_shash *hash;
+
+	hash = crypto_spawn_shash(spawn);
+	if (IS_ERR(hash))
+		return PTR_ERR(hash);
+
+	ctx->child = hash;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct mcryptd_hash_request_ctx) +
+				 crypto_shash_descsize(hash));
+	return 0;
+}
+
+static void mcryptd_hash_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_shash(ctx->child);
+}
+
+static int mcryptd_hash_setkey(struct crypto_ahash *parent,
+				   const u8 *key, unsigned int keylen)
+{
+	struct mcryptd_hash_ctx *ctx   = crypto_ahash_ctx(parent);
+	struct crypto_shash *child = ctx->child;
+	int err;
+
+	crypto_shash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_shash_set_flags(child, crypto_ahash_get_flags(parent) &
+				      CRYPTO_TFM_REQ_MASK);
+	err = crypto_shash_setkey(child, key, keylen);
+	crypto_ahash_set_flags(parent, crypto_shash_get_flags(child) &
+				       CRYPTO_TFM_RES_MASK);
+	return err;
+}
+
+static int mcryptd_hash_enqueue(struct ahash_request *req,
+				crypto_completion_t complete)
+{
+	int ret;
+
+	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct mcryptd_queue *queue =
+		mcryptd_get_queue(crypto_ahash_tfm(tfm));
+
+	rctx->complete = req->base.complete;
+	req->base.complete = complete;
+
+	ret = mcryptd_enqueue_request(queue, &req->base, rctx);
+
+	return ret;
+}
+
+static void mcryptd_hash_init(struct crypto_async_request *req_async, int err)
+{
+	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(req_async->tfm);
+	struct crypto_shash *child = ctx->child;
+	struct ahash_request *req = ahash_request_cast(req_async);
+	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+	struct shash_desc *desc = &rctx->desc;
+
+	if (unlikely(err == -EINPROGRESS))
+		goto out;
+
+	desc->tfm = child;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	err = crypto_shash_init(desc);
+
+	req->base.complete = rctx->complete;
+
+out:
+	local_bh_disable();
+	rctx->complete(&req->base, err);
+	local_bh_enable();
+}
+
+static int mcryptd_hash_init_enqueue(struct ahash_request *req)
+{
+	return mcryptd_hash_enqueue(req, mcryptd_hash_init);
+}
+
+static void mcryptd_hash_update(struct crypto_async_request *req_async, int err)
+{
+	struct ahash_request *req = ahash_request_cast(req_async);
+	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+
+	if (unlikely(err == -EINPROGRESS))
+		goto out;
+
+	err = shash_ahash_mcryptd_update(req, &rctx->desc);
+	if (err) {
+		req->base.complete = rctx->complete;
+		goto out;
+	}
+
+	return;
+out:
+	local_bh_disable();
+	rctx->complete(&req->base, err);
+	local_bh_enable();
+}
+
+static int mcryptd_hash_update_enqueue(struct ahash_request *req)
+{
+	return mcryptd_hash_enqueue(req, mcryptd_hash_update);
+}
+
+static void mcryptd_hash_final(struct crypto_async_request *req_async, int err)
+{
+	struct ahash_request *req = ahash_request_cast(req_async);
+	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+
+	if (unlikely(err == -EINPROGRESS))
+		goto out;
+
+	err = shash_ahash_mcryptd_final(req, &rctx->desc);
+	if (err) {
+		req->base.complete = rctx->complete;
+		goto out;
+	}
+
+	return;
+out:
+	local_bh_disable();
+	rctx->complete(&req->base, err);
+	local_bh_enable();
+}
+
+static int mcryptd_hash_final_enqueue(struct ahash_request *req)
+{
+	return mcryptd_hash_enqueue(req, mcryptd_hash_final);
+}
+
+static void mcryptd_hash_finup(struct crypto_async_request *req_async, int err)
+{
+	struct ahash_request *req = ahash_request_cast(req_async);
+	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+
+	if (unlikely(err == -EINPROGRESS))
+		goto out;
+
+	err = shash_ahash_mcryptd_finup(req, &rctx->desc);
+
+	if (err) {
+		req->base.complete = rctx->complete;
+		goto out;
+	}
+
+	return;
+out:
+	local_bh_disable();
+	rctx->complete(&req->base, err);
+	local_bh_enable();
+}
+
+static int mcryptd_hash_finup_enqueue(struct ahash_request *req)
+{
+	return mcryptd_hash_enqueue(req, mcryptd_hash_finup);
+}
+
+static void mcryptd_hash_digest(struct crypto_async_request *req_async, int err)
+{
+	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(req_async->tfm);
+	struct crypto_shash *child = ctx->child;
+	struct ahash_request *req = ahash_request_cast(req_async);
+	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+	struct shash_desc *desc = &rctx->desc;
+
+	if (unlikely(err == -EINPROGRESS))
+		goto out;
+
+	desc->tfm = child;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;  /* check this again */
+
+	err = shash_ahash_mcryptd_digest(req, desc);
+
+	if (err) {
+		req->base.complete = rctx->complete;
+		goto out;
+	}
+
+	return;
+out:
+	local_bh_disable();
+	rctx->complete(&req->base, err);
+	local_bh_enable();
+}
+
+static int mcryptd_hash_digest_enqueue(struct ahash_request *req)
+{
+	return mcryptd_hash_enqueue(req, mcryptd_hash_digest);
+}
+
+static int mcryptd_hash_export(struct ahash_request *req, void *out)
+{
+	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+
+	return crypto_shash_export(&rctx->desc, out);
+}
+
+static int mcryptd_hash_import(struct ahash_request *req, const void *in)
+{
+	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+
+	return crypto_shash_import(&rctx->desc, in);
+}
+
+static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
+			      struct mcryptd_queue *queue)
+{
+	struct hashd_instance_ctx *ctx;
+	struct ahash_instance *inst;
+	struct shash_alg *salg;
+	struct crypto_alg *alg;
+	int err;
+
+	salg = shash_attr_alg(tb[1], 0, 0);
+	if (IS_ERR(salg))
+		return PTR_ERR(salg);
+
+	alg = &salg->base;
+	pr_debug("crypto: mcryptd hash alg: %s\n", alg->cra_name);
+	inst = mcryptd_alloc_instance(alg, ahash_instance_headroom(),
+					sizeof(*ctx));
+	err = PTR_ERR(inst);
+	if (IS_ERR(inst))
+		goto out_put_alg;
+
+	ctx = ahash_instance_ctx(inst);
+	ctx->queue = queue;
+
+	err = crypto_init_shash_spawn(&ctx->spawn, salg,
+				      ahash_crypto_instance(inst));
+	if (err)
+		goto out_free_inst;
+
+	inst->alg.halg.base.cra_flags = CRYPTO_ALG_ASYNC;
+
+	inst->alg.halg.digestsize = salg->digestsize;
+	inst->alg.halg.base.cra_ctxsize = sizeof(struct mcryptd_hash_ctx);
+
+	inst->alg.halg.base.cra_init = mcryptd_hash_init_tfm;
+	inst->alg.halg.base.cra_exit = mcryptd_hash_exit_tfm;
+
+	inst->alg.init   = mcryptd_hash_init_enqueue;
+	inst->alg.update = mcryptd_hash_update_enqueue;
+	inst->alg.final  = mcryptd_hash_final_enqueue;
+	inst->alg.finup  = mcryptd_hash_finup_enqueue;
+	inst->alg.export = mcryptd_hash_export;
+	inst->alg.import = mcryptd_hash_import;
+	inst->alg.setkey = mcryptd_hash_setkey;
+	inst->alg.digest = mcryptd_hash_digest_enqueue;
+
+	err = ahash_register_instance(tmpl, inst);
+	if (err) {
+		crypto_drop_shash(&ctx->spawn);
+out_free_inst:
+		kfree(inst);
+	}
+
+out_put_alg:
+	crypto_mod_put(alg);
+	return err;
+}
+
+static struct mcryptd_queue mqueue;
+
+static int mcryptd_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct crypto_attr_type *algt;
+
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return PTR_ERR(algt);
+
+	switch (algt->type & algt->mask & CRYPTO_ALG_TYPE_MASK) {
+	case CRYPTO_ALG_TYPE_DIGEST:
+		return mcryptd_create_hash(tmpl, tb, &mqueue);
+	break;
+	}
+
+	return -EINVAL;
+}
+
+static void mcryptd_free(struct crypto_instance *inst)
+{
+	struct mcryptd_instance_ctx *ctx = crypto_instance_ctx(inst);
+	struct hashd_instance_ctx *hctx = crypto_instance_ctx(inst);
+
+	switch (inst->alg.cra_flags & CRYPTO_ALG_TYPE_MASK) {
+	case CRYPTO_ALG_TYPE_AHASH:
+		crypto_drop_shash(&hctx->spawn);
+		kfree(ahash_instance(inst));
+		return;
+	default:
+		crypto_drop_spawn(&ctx->spawn);
+		kfree(inst);
+	}
+}
+
+static struct crypto_template mcryptd_tmpl = {
+	.name = "mcryptd",
+	.create = mcryptd_create,
+	.free = mcryptd_free,
+	.module = THIS_MODULE,
+};
+
+struct mcryptd_ahash *mcryptd_alloc_ahash(const char *alg_name,
+					u32 type, u32 mask)
+{
+	char mcryptd_alg_name[CRYPTO_MAX_ALG_NAME];
+	struct crypto_ahash *tfm;
+
+	if (snprintf(mcryptd_alg_name, CRYPTO_MAX_ALG_NAME,
+		     "mcryptd(%s)", alg_name) >= CRYPTO_MAX_ALG_NAME)
+		return ERR_PTR(-EINVAL);
+	tfm = crypto_alloc_ahash(mcryptd_alg_name, type, mask);
+	if (IS_ERR(tfm))
+		return ERR_CAST(tfm);
+	if (tfm->base.__crt_alg->cra_module != THIS_MODULE) {
+		crypto_free_ahash(tfm);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return __mcryptd_ahash_cast(tfm);
+}
+EXPORT_SYMBOL_GPL(mcryptd_alloc_ahash);
+
+int shash_ahash_mcryptd_digest(struct ahash_request *req,
+			       struct shash_desc *desc)
+{
+	int err;
+
+	err = crypto_shash_init(desc) ?:
+	      shash_ahash_mcryptd_finup(req, desc);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_digest);
+
+int shash_ahash_mcryptd_update(struct ahash_request *req,
+			       struct shash_desc *desc)
+{
+	struct crypto_shash *tfm = desc->tfm;
+	struct shash_alg *shash = crypto_shash_alg(tfm);
+
+	/* alignment is to be done by multi-buffer crypto algorithm if needed */
+
+	return shash->update(desc, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_update);
+
+int shash_ahash_mcryptd_finup(struct ahash_request *req,
+			      struct shash_desc *desc)
+{
+	struct crypto_shash *tfm = desc->tfm;
+	struct shash_alg *shash = crypto_shash_alg(tfm);
+
+	/* alignment is to be done by multi-buffer crypto algorithm if needed */
+
+	return shash->finup(desc, NULL, 0, req->result);
+}
+EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_finup);
+
+int shash_ahash_mcryptd_final(struct ahash_request *req,
+			      struct shash_desc *desc)
+{
+	struct crypto_shash *tfm = desc->tfm;
+	struct shash_alg *shash = crypto_shash_alg(tfm);
+
+	/* alignment is to be done by multi-buffer crypto algorithm if needed */
+
+	return shash->final(desc, req->result);
+}
+EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_final);
+
+struct crypto_shash *mcryptd_ahash_child(struct mcryptd_ahash *tfm)
+{
+	struct mcryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base);
+
+	return ctx->child;
+}
+EXPORT_SYMBOL_GPL(mcryptd_ahash_child);
+
+struct shash_desc *mcryptd_shash_desc(struct ahash_request *req)
+{
+	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+	return &rctx->desc;
+}
+EXPORT_SYMBOL_GPL(mcryptd_shash_desc);
+
+void mcryptd_free_ahash(struct mcryptd_ahash *tfm)
+{
+	crypto_free_ahash(&tfm->base);
+}
+EXPORT_SYMBOL_GPL(mcryptd_free_ahash);
+
+
+static int __init mcryptd_init(void)
+{
+	int err, cpu;
+	struct mcryptd_flush_list *flist;
+
+	mcryptd_flist = alloc_percpu(struct mcryptd_flush_list);
+	for_each_possible_cpu(cpu) {
+		flist = per_cpu_ptr(mcryptd_flist, cpu);
+		INIT_LIST_HEAD(&flist->list);
+		mutex_init(&flist->lock);
+	}
+
+	err = mcryptd_init_queue(&mqueue, MCRYPTD_MAX_CPU_QLEN);
+	if (err) {
+		free_percpu(mcryptd_flist);
+		return err;
+	}
+
+	err = crypto_register_template(&mcryptd_tmpl);
+	if (err) {
+		mcryptd_fini_queue(&mqueue);
+		free_percpu(mcryptd_flist);
+	}
+
+	return err;
+}
+
+static void __exit mcryptd_exit(void)
+{
+	mcryptd_fini_queue(&mqueue);
+	crypto_unregister_template(&mcryptd_tmpl);
+	free_percpu(mcryptd_flist);
+}
+
+subsys_initcall(mcryptd_init);
+module_exit(mcryptd_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Software async multibuffer crypto daemon");
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 9b6f32a6cad1..3b4af1d7c7e9 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -117,6 +117,15 @@ int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc);
 int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc);
 int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc);
 
+int shash_ahash_mcryptd_update(struct ahash_request *req,
+			       struct shash_desc *desc);
+int shash_ahash_mcryptd_final(struct ahash_request *req,
+			      struct shash_desc *desc);
+int shash_ahash_mcryptd_finup(struct ahash_request *req,
+			      struct shash_desc *desc);
+int shash_ahash_mcryptd_digest(struct ahash_request *req,
+			       struct shash_desc *desc);
+
 int crypto_init_shash_ops_async(struct crypto_tfm *tfm);
 
 static inline void *crypto_ahash_ctx(struct crypto_ahash *tfm)
diff --git a/include/crypto/mcryptd.h b/include/crypto/mcryptd.h
new file mode 100644
index 000000000000..c23ee1f7ee80
--- /dev/null
+++ b/include/crypto/mcryptd.h
@@ -0,0 +1,112 @@
+/*
+ * Software async multibuffer crypto daemon headers
+ *
+ *    Author:
+ *             Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ *    Copyright (c) 2014, Intel Corporation.
+ */
+
+#ifndef _CRYPTO_MCRYPT_H
+#define _CRYPTO_MCRYPT_H
+
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <crypto/hash.h>
+
+struct mcryptd_ahash {
+	struct crypto_ahash base;
+};
+
+static inline struct mcryptd_ahash *__mcryptd_ahash_cast(
+	struct crypto_ahash *tfm)
+{
+	return (struct mcryptd_ahash *)tfm;
+}
+
+struct mcryptd_cpu_queue {
+	struct crypto_queue queue;
+	struct work_struct work;
+};
+
+struct mcryptd_queue {
+	struct mcryptd_cpu_queue __percpu *cpu_queue;
+};
+
+struct mcryptd_instance_ctx {
+	struct crypto_spawn spawn;
+	struct mcryptd_queue *queue;
+};
+
+struct mcryptd_hash_ctx {
+	struct crypto_shash *child;
+	struct mcryptd_alg_state *alg_state;
+};
+
+struct mcryptd_tag {
+	/* seq number of request */
+	unsigned seq_num;
+	/* arrival time of request */
+	unsigned long arrival;
+	unsigned long expire;
+	int	cpu;
+};
+
+struct mcryptd_hash_request_ctx {
+	struct list_head waiter;
+	crypto_completion_t complete;
+	struct mcryptd_tag tag;
+	struct crypto_hash_walk walk;
+	u8 *out;
+	int flag;
+	struct shash_desc desc;
+};
+
+struct mcryptd_ahash *mcryptd_alloc_ahash(const char *alg_name,
+					u32 type, u32 mask);
+struct crypto_shash *mcryptd_ahash_child(struct mcryptd_ahash *tfm);
+struct shash_desc *mcryptd_shash_desc(struct ahash_request *req);
+void mcryptd_free_ahash(struct mcryptd_ahash *tfm);
+void mcryptd_flusher(struct work_struct *work);
+
+enum mcryptd_req_type {
+	MCRYPTD_NONE,
+	MCRYPTD_UPDATE,
+	MCRYPTD_FINUP,
+	MCRYPTD_DIGEST,
+	MCRYPTD_FINAL
+};
+
+struct mcryptd_alg_cstate {
+	unsigned long next_flush;
+	unsigned next_seq_num;
+	bool	flusher_engaged;
+	struct  delayed_work flush;
+	int	cpu;
+	struct  mcryptd_alg_state *alg_state;
+	void	*mgr;
+	spinlock_t work_lock;
+	struct list_head work_list;
+	struct list_head flush_list;
+};
+
+struct mcryptd_alg_state {
+	struct mcryptd_alg_cstate __percpu *alg_cstate;
+	unsigned long (*flusher)(struct mcryptd_alg_cstate *cstate);
+};
+
+/* return delay in jiffies from current time */
+static inline unsigned long get_delay(unsigned long t)
+{
+	long delay;
+
+	delay = (long) t - (long) jiffies;
+	if (delay <= 0)
+		return 0;
+	else
+		return (unsigned long) delay;
+}
+
+void mcryptd_arm_flusher(struct mcryptd_alg_cstate *cstate, unsigned long delay);
+
+#endif
-- 
cgit v1.2.3


From 05c81ccd9087d238c10b234eadb55632742e5518 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Sun, 17 Aug 2014 17:41:10 +0200
Subject: crypto: drbg - remove configuration of fixed values

SP800-90A mandates several hard-coded values. The old drbg_cores allows
the setting of these values per DRBG implementation. However, due to the
hard requirement of SP800-90A, these values are now returned globally
for each DRBG.

The ability to set such values per DRBG is therefore removed.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/drbg.c         | 33 ---------------------------------
 include/crypto/drbg.h | 19 ++++++-------------
 2 files changed, 6 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/crypto/drbg.c b/crypto/drbg.c
index 701575734420..b4938bb4c465 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -117,27 +117,18 @@ static const struct drbg_core drbg_cores[] = {
 	{
 		.flags = DRBG_CTR | DRBG_STRENGTH128,
 		.statelen = 32, /* 256 bits as defined in 10.2.1 */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 16,
 		.cra_name = "ctr_aes128",
 		.backend_cra_name = "ecb(aes)",
 	}, {
 		.flags = DRBG_CTR | DRBG_STRENGTH192,
 		.statelen = 40, /* 320 bits as defined in 10.2.1 */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 16,
 		.cra_name = "ctr_aes192",
 		.backend_cra_name = "ecb(aes)",
 	}, {
 		.flags = DRBG_CTR | DRBG_STRENGTH256,
 		.statelen = 48, /* 384 bits as defined in 10.2.1 */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 16,
 		.cra_name = "ctr_aes256",
 		.backend_cra_name = "ecb(aes)",
@@ -147,36 +138,24 @@ static const struct drbg_core drbg_cores[] = {
 	{
 		.flags = DRBG_HASH | DRBG_STRENGTH128,
 		.statelen = 55, /* 440 bits */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 20,
 		.cra_name = "sha1",
 		.backend_cra_name = "sha1",
 	}, {
 		.flags = DRBG_HASH | DRBG_STRENGTH256,
 		.statelen = 111, /* 888 bits */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 48,
 		.cra_name = "sha384",
 		.backend_cra_name = "sha384",
 	}, {
 		.flags = DRBG_HASH | DRBG_STRENGTH256,
 		.statelen = 111, /* 888 bits */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 64,
 		.cra_name = "sha512",
 		.backend_cra_name = "sha512",
 	}, {
 		.flags = DRBG_HASH | DRBG_STRENGTH256,
 		.statelen = 55, /* 440 bits */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 32,
 		.cra_name = "sha256",
 		.backend_cra_name = "sha256",
@@ -186,36 +165,24 @@ static const struct drbg_core drbg_cores[] = {
 	{
 		.flags = DRBG_HMAC | DRBG_STRENGTH128,
 		.statelen = 20, /* block length of cipher */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 20,
 		.cra_name = "hmac_sha1",
 		.backend_cra_name = "hmac(sha1)",
 	}, {
 		.flags = DRBG_HMAC | DRBG_STRENGTH256,
 		.statelen = 48, /* block length of cipher */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 48,
 		.cra_name = "hmac_sha384",
 		.backend_cra_name = "hmac(sha384)",
 	}, {
 		.flags = DRBG_HMAC | DRBG_STRENGTH256,
 		.statelen = 64, /* block length of cipher */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 64,
 		.cra_name = "hmac_sha512",
 		.backend_cra_name = "hmac(sha512)",
 	}, {
 		.flags = DRBG_HMAC | DRBG_STRENGTH256,
 		.statelen = 32, /* block length of cipher */
-		.max_addtllen = 35,
-		.max_bits = 19,
-		.max_req = 48,
 		.blocklen_bytes = 32,
 		.cra_name = "hmac_sha256",
 		.backend_cra_name = "hmac(sha256)",
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index 831d786976c5..3d8e73a1a1c7 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -82,15 +82,6 @@ typedef uint32_t drbg_flag_t;
 struct drbg_core {
 	drbg_flag_t flags;	/* flags for the cipher */
 	__u8 statelen;		/* maximum state length */
-	/*
-	 * maximum length of personalization string or additional input
-	 * string -- exponent for base 2
-	 */
-	__u8 max_addtllen;
-	/* maximum bits per RNG request -- exponent for base 2*/
-	__u8 max_bits;
-	/* maximum number of requests -- exponent for base 2 */
-	__u8 max_req;
 	__u8 blocklen_bytes;	/* block size of output in bytes */
 	char cra_name[CRYPTO_MAX_ALG_NAME]; /* mapping to kernel crypto API */
 	 /* kernel crypto API backend cipher name */
@@ -156,18 +147,20 @@ static inline __u8 drbg_keylen(struct drbg_state *drbg)
 
 static inline size_t drbg_max_request_bytes(struct drbg_state *drbg)
 {
-	/* max_bits is in bits, but buflen is in bytes */
-	return (1 << (drbg->core->max_bits - 3));
+	/* SP800-90A requires the limit 2**19 bits, but we return bytes */
+	return (1 << 16);
 }
 
 static inline size_t drbg_max_addtl(struct drbg_state *drbg)
 {
-	return (1UL<<(drbg->core->max_addtllen));
+	/* SP800-90A requires 2**35 bytes additional info str / pers str */
+	return (1UL<<35);
 }
 
 static inline size_t drbg_max_requests(struct drbg_state *drbg)
 {
-	return (1UL<<(drbg->core->max_req));
+	/* SP800-90A requires 2**48 maximum requests before reseeding */
+	return (1UL<<48);
 }
 
 /*
-- 
cgit v1.2.3


From 96c2737716d586a218bc795fcb79d2e2b6003081 Mon Sep 17 00:00:00 2001
From: Valentina Manea <valentina.manea.m@gmail.com>
Date: Wed, 20 Aug 2014 07:31:00 +0300
Subject: usbip: move usbip kernel code out of staging

At this point, USB/IP kernel code is fully functional
and can be moved out of staging.

Signed-off-by: Valentina Manea <valentina.manea.m@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/Kconfig                  |    2 -
 drivers/staging/Makefile                 |    1 -
 drivers/staging/usbip/Kconfig            |   41 --
 drivers/staging/usbip/Makefile           |   10 -
 drivers/staging/usbip/README             |    7 -
 drivers/staging/usbip/stub.h             |  113 ---
 drivers/staging/usbip/stub_dev.c         |  525 --------------
 drivers/staging/usbip/stub_main.c        |  335 ---------
 drivers/staging/usbip/stub_rx.c          |  594 ---------------
 drivers/staging/usbip/stub_tx.c          |  398 ----------
 drivers/staging/usbip/uapi/usbip.h       |   26 -
 drivers/staging/usbip/usbip_common.c     |  776 --------------------
 drivers/staging/usbip/usbip_common.h     |  335 ---------
 drivers/staging/usbip/usbip_event.c      |  128 ----
 drivers/staging/usbip/usbip_protocol.txt |  358 ---------
 drivers/staging/usbip/vhci.h             |  129 ----
 drivers/staging/usbip/vhci_hcd.c         | 1171 ------------------------------
 drivers/staging/usbip/vhci_rx.c          |  268 -------
 drivers/staging/usbip/vhci_sysfs.c       |  252 -------
 drivers/staging/usbip/vhci_tx.c          |  224 ------
 drivers/usb/Kconfig                      |    2 +
 drivers/usb/Makefile                     |    2 +
 drivers/usb/usbip/Kconfig                |   41 ++
 drivers/usb/usbip/Makefile               |   10 +
 drivers/usb/usbip/README                 |    7 +
 drivers/usb/usbip/stub.h                 |  113 +++
 drivers/usb/usbip/stub_dev.c             |  525 ++++++++++++++
 drivers/usb/usbip/stub_main.c            |  335 +++++++++
 drivers/usb/usbip/stub_rx.c              |  594 +++++++++++++++
 drivers/usb/usbip/stub_tx.c              |  398 ++++++++++
 drivers/usb/usbip/usbip_common.c         |  776 ++++++++++++++++++++
 drivers/usb/usbip/usbip_common.h         |  335 +++++++++
 drivers/usb/usbip/usbip_event.c          |  128 ++++
 drivers/usb/usbip/usbip_protocol.txt     |  358 +++++++++
 drivers/usb/usbip/vhci.h                 |  129 ++++
 drivers/usb/usbip/vhci_hcd.c             | 1171 ++++++++++++++++++++++++++++++
 drivers/usb/usbip/vhci_rx.c              |  268 +++++++
 drivers/usb/usbip/vhci_sysfs.c           |  252 +++++++
 drivers/usb/usbip/vhci_tx.c              |  224 ++++++
 include/uapi/linux/usbip.h               |   26 +
 40 files changed, 5694 insertions(+), 5693 deletions(-)
 delete mode 100644 drivers/staging/usbip/Kconfig
 delete mode 100644 drivers/staging/usbip/Makefile
 delete mode 100644 drivers/staging/usbip/README
 delete mode 100644 drivers/staging/usbip/stub.h
 delete mode 100644 drivers/staging/usbip/stub_dev.c
 delete mode 100644 drivers/staging/usbip/stub_main.c
 delete mode 100644 drivers/staging/usbip/stub_rx.c
 delete mode 100644 drivers/staging/usbip/stub_tx.c
 delete mode 100644 drivers/staging/usbip/uapi/usbip.h
 delete mode 100644 drivers/staging/usbip/usbip_common.c
 delete mode 100644 drivers/staging/usbip/usbip_common.h
 delete mode 100644 drivers/staging/usbip/usbip_event.c
 delete mode 100644 drivers/staging/usbip/usbip_protocol.txt
 delete mode 100644 drivers/staging/usbip/vhci.h
 delete mode 100644 drivers/staging/usbip/vhci_hcd.c
 delete mode 100644 drivers/staging/usbip/vhci_rx.c
 delete mode 100644 drivers/staging/usbip/vhci_sysfs.c
 delete mode 100644 drivers/staging/usbip/vhci_tx.c
 create mode 100644 drivers/usb/usbip/Kconfig
 create mode 100644 drivers/usb/usbip/Makefile
 create mode 100644 drivers/usb/usbip/README
 create mode 100644 drivers/usb/usbip/stub.h
 create mode 100644 drivers/usb/usbip/stub_dev.c
 create mode 100644 drivers/usb/usbip/stub_main.c
 create mode 100644 drivers/usb/usbip/stub_rx.c
 create mode 100644 drivers/usb/usbip/stub_tx.c
 create mode 100644 drivers/usb/usbip/usbip_common.c
 create mode 100644 drivers/usb/usbip/usbip_common.h
 create mode 100644 drivers/usb/usbip/usbip_event.c
 create mode 100644 drivers/usb/usbip/usbip_protocol.txt
 create mode 100644 drivers/usb/usbip/vhci.h
 create mode 100644 drivers/usb/usbip/vhci_hcd.c
 create mode 100644 drivers/usb/usbip/vhci_rx.c
 create mode 100644 drivers/usb/usbip/vhci_sysfs.c
 create mode 100644 drivers/usb/usbip/vhci_tx.c
 create mode 100644 include/uapi/linux/usbip.h

(limited to 'include')

diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index 2c486ea6236b..35b494f5667f 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -28,8 +28,6 @@ source "drivers/staging/et131x/Kconfig"
 
 source "drivers/staging/slicoss/Kconfig"
 
-source "drivers/staging/usbip/Kconfig"
-
 source "drivers/staging/wlan-ng/Kconfig"
 
 source "drivers/staging/comedi/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 1e1a3a10faf7..e66a5dbd9b02 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -6,7 +6,6 @@ obj-$(CONFIG_STAGING)		+= staging.o
 obj-y				+= media/
 obj-$(CONFIG_ET131X)		+= et131x/
 obj-$(CONFIG_SLICOSS)		+= slicoss/
-obj-$(CONFIG_USBIP_CORE)	+= usbip/
 obj-$(CONFIG_PRISM2_USB)	+= wlan-ng/
 obj-$(CONFIG_COMEDI)		+= comedi/
 obj-$(CONFIG_FB_OLPC_DCON)	+= olpc_dcon/
diff --git a/drivers/staging/usbip/Kconfig b/drivers/staging/usbip/Kconfig
deleted file mode 100644
index bd99e9e47e50..000000000000
--- a/drivers/staging/usbip/Kconfig
+++ /dev/null
@@ -1,41 +0,0 @@
-config USBIP_CORE
-	tristate "USB/IP support"
-	depends on USB && NET
-	---help---
-	  This enables pushing USB packets over IP to allow remote
-	  machines direct access to USB devices. It provides the
-	  USB/IP core that is required by both drivers.
-
-	  For more details, and to get the userspace utility
-	  programs, please see <http://usbip.sourceforge.net/>.
-
-	  To compile this as a module, choose M here: the module will
-	  be called usbip-core.
-
-	  If unsure, say N.
-
-config USBIP_VHCI_HCD
-	tristate "VHCI hcd"
-	depends on USBIP_CORE
-	---help---
-	  This enables the USB/IP virtual host controller driver,
-	  which is run on the remote machine.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called vhci-hcd.
-
-config USBIP_HOST
-	tristate "Host driver"
-	depends on USBIP_CORE
-	---help---
-	  This enables the USB/IP host driver, which is run on the
-	  machine that is sharing the USB devices.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called usbip-host.
-
-config USBIP_DEBUG
-	bool "Debug messages for USB/IP"
-	depends on USBIP_CORE
-	---help---
-	  This enables the debug messages from the USB/IP drivers.
diff --git a/drivers/staging/usbip/Makefile b/drivers/staging/usbip/Makefile
deleted file mode 100644
index 9ecd61545be1..000000000000
--- a/drivers/staging/usbip/Makefile
+++ /dev/null
@@ -1,10 +0,0 @@
-ccflags-$(CONFIG_USBIP_DEBUG) := -DDEBUG
-
-obj-$(CONFIG_USBIP_CORE) += usbip-core.o
-usbip-core-y := usbip_common.o usbip_event.o
-
-obj-$(CONFIG_USBIP_VHCI_HCD) += vhci-hcd.o
-vhci-hcd-y := vhci_sysfs.o vhci_tx.o vhci_rx.o vhci_hcd.o
-
-obj-$(CONFIG_USBIP_HOST) += usbip-host.o
-usbip-host-y := stub_dev.o stub_main.o stub_rx.o stub_tx.o
diff --git a/drivers/staging/usbip/README b/drivers/staging/usbip/README
deleted file mode 100644
index 41a2cf2e77a6..000000000000
--- a/drivers/staging/usbip/README
+++ /dev/null
@@ -1,7 +0,0 @@
-TODO:
-	- more discussion about the protocol
-	- testing
-	- review of the userspace interface
-	- document the protocol
-
-Please send patches for this code to Greg Kroah-Hartman <greg@kroah.com>
diff --git a/drivers/staging/usbip/stub.h b/drivers/staging/usbip/stub.h
deleted file mode 100644
index 266e2b0ce9a8..000000000000
--- a/drivers/staging/usbip/stub.h
+++ /dev/null
@@ -1,113 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#ifndef __USBIP_STUB_H
-#define __USBIP_STUB_H
-
-#include <linux/list.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-#include <linux/usb.h>
-#include <linux/wait.h>
-
-#define STUB_BUSID_OTHER 0
-#define STUB_BUSID_REMOV 1
-#define STUB_BUSID_ADDED 2
-#define STUB_BUSID_ALLOC 3
-
-struct stub_device {
-	struct usb_interface *interface;
-	struct usb_device *udev;
-
-	struct usbip_device ud;
-	__u32 devid;
-
-	/*
-	 * stub_priv preserves private data of each urb.
-	 * It is allocated as stub_priv_cache and assigned to urb->context.
-	 *
-	 * stub_priv is always linked to any one of 3 lists;
-	 *	priv_init: linked to this until the comletion of a urb.
-	 *	priv_tx  : linked to this after the completion of a urb.
-	 *	priv_free: linked to this after the sending of the result.
-	 *
-	 * Any of these list operations should be locked by priv_lock.
-	 */
-	spinlock_t priv_lock;
-	struct list_head priv_init;
-	struct list_head priv_tx;
-	struct list_head priv_free;
-
-	/* see comments for unlinking in stub_rx.c */
-	struct list_head unlink_tx;
-	struct list_head unlink_free;
-
-	wait_queue_head_t tx_waitq;
-};
-
-/* private data into urb->priv */
-struct stub_priv {
-	unsigned long seqnum;
-	struct list_head list;
-	struct stub_device *sdev;
-	struct urb *urb;
-
-	int unlinking;
-};
-
-struct stub_unlink {
-	unsigned long seqnum;
-	struct list_head list;
-	__u32 status;
-};
-
-/* same as SYSFS_BUS_ID_SIZE */
-#define BUSID_SIZE 32
-
-struct bus_id_priv {
-	char name[BUSID_SIZE];
-	char status;
-	int interf_count;
-	struct stub_device *sdev;
-	struct usb_device *udev;
-	char shutdown_busid;
-};
-
-/* stub_priv is allocated from stub_priv_cache */
-extern struct kmem_cache *stub_priv_cache;
-
-/* stub_dev.c */
-extern struct usb_device_driver stub_driver;
-
-/* stub_main.c */
-struct bus_id_priv *get_busid_priv(const char *busid);
-int del_match_busid(char *busid);
-void stub_device_cleanup_urbs(struct stub_device *sdev);
-
-/* stub_rx.c */
-int stub_rx_loop(void *data);
-
-/* stub_tx.c */
-void stub_enqueue_ret_unlink(struct stub_device *sdev, __u32 seqnum,
-			     __u32 status);
-void stub_complete(struct urb *urb);
-int stub_tx_loop(void *data);
-
-#endif /* __USBIP_STUB_H */
diff --git a/drivers/staging/usbip/stub_dev.c b/drivers/staging/usbip/stub_dev.c
deleted file mode 100644
index 51d0c7188738..000000000000
--- a/drivers/staging/usbip/stub_dev.c
+++ /dev/null
@@ -1,525 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <linux/device.h>
-#include <linux/file.h>
-#include <linux/kthread.h>
-#include <linux/module.h>
-
-#include "usbip_common.h"
-#include "stub.h"
-
-/*
- * Define device IDs here if you want to explicitly limit exportable devices.
- * In most cases, wildcard matching will be okay because driver binding can be
- * changed dynamically by a userland program.
- */
-static struct usb_device_id stub_table[] = {
-#if 0
-	/* just an example */
-	{ USB_DEVICE(0x05ac, 0x0301) },   /* Mac 1 button mouse */
-	{ USB_DEVICE(0x0430, 0x0009) },   /* Plat Home Keyboard */
-	{ USB_DEVICE(0x059b, 0x0001) },   /* Iomega USB Zip 100 */
-	{ USB_DEVICE(0x04b3, 0x4427) },   /* IBM USB CD-ROM */
-	{ USB_DEVICE(0x05a9, 0xa511) },   /* LifeView USB cam */
-	{ USB_DEVICE(0x55aa, 0x0201) },   /* Imation card reader */
-	{ USB_DEVICE(0x046d, 0x0870) },   /* Qcam Express(QV-30) */
-	{ USB_DEVICE(0x04bb, 0x0101) },   /* IO-DATA HD 120GB */
-	{ USB_DEVICE(0x04bb, 0x0904) },   /* IO-DATA USB-ET/TX */
-	{ USB_DEVICE(0x04bb, 0x0201) },   /* IO-DATA USB-ET/TX */
-	{ USB_DEVICE(0x08bb, 0x2702) },   /* ONKYO USB Speaker */
-	{ USB_DEVICE(0x046d, 0x08b2) },   /* Logicool Qcam 4000 Pro */
-#endif
-	/* magic for wild card */
-	{ .driver_info = 1 },
-	{ 0, }                                     /* Terminating entry */
-};
-MODULE_DEVICE_TABLE(usb, stub_table);
-
-/*
- * usbip_status shows the status of usbip-host as long as this driver is bound
- * to the target device.
- */
-static ssize_t usbip_status_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	struct stub_device *sdev = dev_get_drvdata(dev);
-	int status;
-
-	if (!sdev) {
-		dev_err(dev, "sdev is null\n");
-		return -ENODEV;
-	}
-
-	spin_lock_irq(&sdev->ud.lock);
-	status = sdev->ud.status;
-	spin_unlock_irq(&sdev->ud.lock);
-
-	return snprintf(buf, PAGE_SIZE, "%d\n", status);
-}
-static DEVICE_ATTR_RO(usbip_status);
-
-/*
- * usbip_sockfd gets a socket descriptor of an established TCP connection that
- * is used to transfer usbip requests by kernel threads. -1 is a magic number
- * by which usbip connection is finished.
- */
-static ssize_t store_sockfd(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
-{
-	struct stub_device *sdev = dev_get_drvdata(dev);
-	int sockfd = 0;
-	struct socket *socket;
-	int rv;
-
-	if (!sdev) {
-		dev_err(dev, "sdev is null\n");
-		return -ENODEV;
-	}
-
-	rv = sscanf(buf, "%d", &sockfd);
-	if (rv != 1)
-		return -EINVAL;
-
-	if (sockfd != -1) {
-		int err;
-
-		dev_info(dev, "stub up\n");
-
-		spin_lock_irq(&sdev->ud.lock);
-
-		if (sdev->ud.status != SDEV_ST_AVAILABLE) {
-			dev_err(dev, "not ready\n");
-			goto err;
-		}
-
-		socket = sockfd_lookup(sockfd, &err);
-		if (!socket)
-			goto err;
-
-		sdev->ud.tcp_socket = socket;
-
-		spin_unlock_irq(&sdev->ud.lock);
-
-		sdev->ud.tcp_rx = kthread_get_run(stub_rx_loop, &sdev->ud,
-						  "stub_rx");
-		sdev->ud.tcp_tx = kthread_get_run(stub_tx_loop, &sdev->ud,
-						  "stub_tx");
-
-		spin_lock_irq(&sdev->ud.lock);
-		sdev->ud.status = SDEV_ST_USED;
-		spin_unlock_irq(&sdev->ud.lock);
-
-	} else {
-		dev_info(dev, "stub down\n");
-
-		spin_lock_irq(&sdev->ud.lock);
-		if (sdev->ud.status != SDEV_ST_USED)
-			goto err;
-
-		spin_unlock_irq(&sdev->ud.lock);
-
-		usbip_event_add(&sdev->ud, SDEV_EVENT_DOWN);
-	}
-
-	return count;
-
-err:
-	spin_unlock_irq(&sdev->ud.lock);
-	return -EINVAL;
-}
-static DEVICE_ATTR(usbip_sockfd, S_IWUSR, NULL, store_sockfd);
-
-static int stub_add_files(struct device *dev)
-{
-	int err = 0;
-
-	err = device_create_file(dev, &dev_attr_usbip_status);
-	if (err)
-		goto err_status;
-
-	err = device_create_file(dev, &dev_attr_usbip_sockfd);
-	if (err)
-		goto err_sockfd;
-
-	err = device_create_file(dev, &dev_attr_usbip_debug);
-	if (err)
-		goto err_debug;
-
-	return 0;
-
-err_debug:
-	device_remove_file(dev, &dev_attr_usbip_sockfd);
-err_sockfd:
-	device_remove_file(dev, &dev_attr_usbip_status);
-err_status:
-	return err;
-}
-
-static void stub_remove_files(struct device *dev)
-{
-	device_remove_file(dev, &dev_attr_usbip_status);
-	device_remove_file(dev, &dev_attr_usbip_sockfd);
-	device_remove_file(dev, &dev_attr_usbip_debug);
-}
-
-static void stub_shutdown_connection(struct usbip_device *ud)
-{
-	struct stub_device *sdev = container_of(ud, struct stub_device, ud);
-
-	/*
-	 * When removing an exported device, kernel panic sometimes occurred
-	 * and then EIP was sk_wait_data of stub_rx thread. Is this because
-	 * sk_wait_data returned though stub_rx thread was already finished by
-	 * step 1?
-	 */
-	if (ud->tcp_socket) {
-		dev_dbg(&sdev->udev->dev, "shutdown tcp_socket %p\n",
-			ud->tcp_socket);
-		kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
-	}
-
-	/* 1. stop threads */
-	if (ud->tcp_rx) {
-		kthread_stop_put(ud->tcp_rx);
-		ud->tcp_rx = NULL;
-	}
-	if (ud->tcp_tx) {
-		kthread_stop_put(ud->tcp_tx);
-		ud->tcp_tx = NULL;
-	}
-
-	/*
-	 * 2. close the socket
-	 *
-	 * tcp_socket is freed after threads are killed so that usbip_xmit does
-	 * not touch NULL socket.
-	 */
-	if (ud->tcp_socket) {
-		sockfd_put(ud->tcp_socket);
-		ud->tcp_socket = NULL;
-	}
-
-	/* 3. free used data */
-	stub_device_cleanup_urbs(sdev);
-
-	/* 4. free stub_unlink */
-	{
-		unsigned long flags;
-		struct stub_unlink *unlink, *tmp;
-
-		spin_lock_irqsave(&sdev->priv_lock, flags);
-		list_for_each_entry_safe(unlink, tmp, &sdev->unlink_tx, list) {
-			list_del(&unlink->list);
-			kfree(unlink);
-		}
-		list_for_each_entry_safe(unlink, tmp, &sdev->unlink_free,
-					 list) {
-			list_del(&unlink->list);
-			kfree(unlink);
-		}
-		spin_unlock_irqrestore(&sdev->priv_lock, flags);
-	}
-}
-
-static void stub_device_reset(struct usbip_device *ud)
-{
-	struct stub_device *sdev = container_of(ud, struct stub_device, ud);
-	struct usb_device *udev = sdev->udev;
-	int ret;
-
-	dev_dbg(&udev->dev, "device reset");
-
-	ret = usb_lock_device_for_reset(udev, sdev->interface);
-	if (ret < 0) {
-		dev_err(&udev->dev, "lock for reset\n");
-		spin_lock_irq(&ud->lock);
-		ud->status = SDEV_ST_ERROR;
-		spin_unlock_irq(&ud->lock);
-		return;
-	}
-
-	/* try to reset the device */
-	ret = usb_reset_device(udev);
-	usb_unlock_device(udev);
-
-	spin_lock_irq(&ud->lock);
-	if (ret) {
-		dev_err(&udev->dev, "device reset\n");
-		ud->status = SDEV_ST_ERROR;
-	} else {
-		dev_info(&udev->dev, "device reset\n");
-		ud->status = SDEV_ST_AVAILABLE;
-	}
-	spin_unlock_irq(&ud->lock);
-}
-
-static void stub_device_unusable(struct usbip_device *ud)
-{
-	spin_lock_irq(&ud->lock);
-	ud->status = SDEV_ST_ERROR;
-	spin_unlock_irq(&ud->lock);
-}
-
-/**
- * stub_device_alloc - allocate a new stub_device struct
- * @interface: usb_interface of a new device
- *
- * Allocates and initializes a new stub_device struct.
- */
-static struct stub_device *stub_device_alloc(struct usb_device *udev)
-{
-	struct stub_device *sdev;
-	int busnum = udev->bus->busnum;
-	int devnum = udev->devnum;
-
-	dev_dbg(&udev->dev, "allocating stub device");
-
-	/* yes, it's a new device */
-	sdev = kzalloc(sizeof(struct stub_device), GFP_KERNEL);
-	if (!sdev)
-		return NULL;
-
-	sdev->udev = usb_get_dev(udev);
-
-	/*
-	 * devid is defined with devnum when this driver is first allocated.
-	 * devnum may change later if a device is reset. However, devid never
-	 * changes during a usbip connection.
-	 */
-	sdev->devid		= (busnum << 16) | devnum;
-	sdev->ud.side		= USBIP_STUB;
-	sdev->ud.status		= SDEV_ST_AVAILABLE;
-	spin_lock_init(&sdev->ud.lock);
-	sdev->ud.tcp_socket	= NULL;
-
-	INIT_LIST_HEAD(&sdev->priv_init);
-	INIT_LIST_HEAD(&sdev->priv_tx);
-	INIT_LIST_HEAD(&sdev->priv_free);
-	INIT_LIST_HEAD(&sdev->unlink_free);
-	INIT_LIST_HEAD(&sdev->unlink_tx);
-	spin_lock_init(&sdev->priv_lock);
-
-	init_waitqueue_head(&sdev->tx_waitq);
-
-	sdev->ud.eh_ops.shutdown = stub_shutdown_connection;
-	sdev->ud.eh_ops.reset    = stub_device_reset;
-	sdev->ud.eh_ops.unusable = stub_device_unusable;
-
-	usbip_start_eh(&sdev->ud);
-
-	dev_dbg(&udev->dev, "register new device\n");
-
-	return sdev;
-}
-
-static void stub_device_free(struct stub_device *sdev)
-{
-	kfree(sdev);
-}
-
-static int stub_probe(struct usb_device *udev)
-{
-	struct stub_device *sdev = NULL;
-	const char *udev_busid = dev_name(&udev->dev);
-	int err = 0;
-	struct bus_id_priv *busid_priv;
-	int rc;
-
-	dev_dbg(&udev->dev, "Enter\n");
-
-	/* check we should claim or not by busid_table */
-	busid_priv = get_busid_priv(udev_busid);
-	if (!busid_priv || (busid_priv->status == STUB_BUSID_REMOV) ||
-	    (busid_priv->status == STUB_BUSID_OTHER)) {
-		dev_info(&udev->dev,
-			"%s is not in match_busid table... skip!\n",
-			udev_busid);
-
-		/*
-		 * Return value should be ENODEV or ENOXIO to continue trying
-		 * other matched drivers by the driver core.
-		 * See driver_probe_device() in driver/base/dd.c
-		 */
-		return -ENODEV;
-	}
-
-	if (udev->descriptor.bDeviceClass == USB_CLASS_HUB) {
-		dev_dbg(&udev->dev, "%s is a usb hub device... skip!\n",
-			 udev_busid);
-		return -ENODEV;
-	}
-
-	if (!strcmp(udev->bus->bus_name, "vhci_hcd")) {
-		dev_dbg(&udev->dev,
-			"%s is attached on vhci_hcd... skip!\n",
-			udev_busid);
-
-		return -ENODEV;
-	}
-
-	/* ok, this is my device */
-	sdev = stub_device_alloc(udev);
-	if (!sdev)
-		return -ENOMEM;
-
-	dev_info(&udev->dev,
-		"usbip-host: register new device (bus %u dev %u)\n",
-		udev->bus->busnum, udev->devnum);
-
-	busid_priv->shutdown_busid = 0;
-
-	/* set private data to usb_device */
-	dev_set_drvdata(&udev->dev, sdev);
-	busid_priv->sdev = sdev;
-	busid_priv->udev = udev;
-
-	/*
-	 * Claim this hub port.
-	 * It doesn't matter what value we pass as owner
-	 * (struct dev_state) as long as it is unique.
-	 */
-	rc = usb_hub_claim_port(udev->parent, udev->portnum,
-			(struct usb_dev_state *) udev);
-	if (rc) {
-		dev_dbg(&udev->dev, "unable to claim port\n");
-		return rc;
-	}
-
-	err = stub_add_files(&udev->dev);
-	if (err) {
-		dev_err(&udev->dev, "stub_add_files for %s\n", udev_busid);
-		dev_set_drvdata(&udev->dev, NULL);
-		usb_put_dev(udev);
-		kthread_stop_put(sdev->ud.eh);
-
-		busid_priv->sdev = NULL;
-		stub_device_free(sdev);
-		return err;
-	}
-	busid_priv->status = STUB_BUSID_ALLOC;
-
-	return 0;
-}
-
-static void shutdown_busid(struct bus_id_priv *busid_priv)
-{
-	if (busid_priv->sdev && !busid_priv->shutdown_busid) {
-		busid_priv->shutdown_busid = 1;
-		usbip_event_add(&busid_priv->sdev->ud, SDEV_EVENT_REMOVED);
-
-		/* wait for the stop of the event handler */
-		usbip_stop_eh(&busid_priv->sdev->ud);
-	}
-}
-
-/*
- * called in usb_disconnect() or usb_deregister()
- * but only if actconfig(active configuration) exists
- */
-static void stub_disconnect(struct usb_device *udev)
-{
-	struct stub_device *sdev;
-	const char *udev_busid = dev_name(&udev->dev);
-	struct bus_id_priv *busid_priv;
-	int rc;
-
-	dev_dbg(&udev->dev, "Enter\n");
-
-	busid_priv = get_busid_priv(udev_busid);
-	if (!busid_priv) {
-		BUG();
-		return;
-	}
-
-	sdev = dev_get_drvdata(&udev->dev);
-
-	/* get stub_device */
-	if (!sdev) {
-		dev_err(&udev->dev, "could not get device");
-		return;
-	}
-
-	dev_set_drvdata(&udev->dev, NULL);
-
-	/*
-	 * NOTE: rx/tx threads are invoked for each usb_device.
-	 */
-	stub_remove_files(&udev->dev);
-
-	/* release port */
-	rc = usb_hub_release_port(udev->parent, udev->portnum,
-				  (struct usb_dev_state *) udev);
-	if (rc) {
-		dev_dbg(&udev->dev, "unable to release port\n");
-		return;
-	}
-
-	/* If usb reset is called from event handler */
-	if (busid_priv->sdev->ud.eh == current)
-		return;
-
-	/* shutdown the current connection */
-	shutdown_busid(busid_priv);
-
-	usb_put_dev(sdev->udev);
-
-	/* free sdev */
-	busid_priv->sdev = NULL;
-	stub_device_free(sdev);
-
-	if (busid_priv->status == STUB_BUSID_ALLOC) {
-		busid_priv->status = STUB_BUSID_ADDED;
-	} else {
-		busid_priv->status = STUB_BUSID_OTHER;
-		del_match_busid((char *)udev_busid);
-	}
-}
-
-#ifdef CONFIG_PM
-
-/* These functions need usb_port_suspend and usb_port_resume,
- * which reside in drivers/usb/core/usb.h. Skip for now. */
-
-static int stub_suspend(struct usb_device *udev, pm_message_t message)
-{
-	dev_dbg(&udev->dev, "stub_suspend\n");
-
-	return 0;
-}
-
-static int stub_resume(struct usb_device *udev, pm_message_t message)
-{
-	dev_dbg(&udev->dev, "stub_resume\n");
-
-	return 0;
-}
-
-#endif	/* CONFIG_PM */
-
-struct usb_device_driver stub_driver = {
-	.name		= "usbip-host",
-	.probe		= stub_probe,
-	.disconnect	= stub_disconnect,
-#ifdef CONFIG_PM
-	.suspend	= stub_suspend,
-	.resume		= stub_resume,
-#endif
-	.supports_autosuspend	=	0,
-};
diff --git a/drivers/staging/usbip/stub_main.c b/drivers/staging/usbip/stub_main.c
deleted file mode 100644
index 44ab43fc4fcc..000000000000
--- a/drivers/staging/usbip/stub_main.c
+++ /dev/null
@@ -1,335 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <linux/string.h>
-#include <linux/module.h>
-#include <linux/device.h>
-
-#include "usbip_common.h"
-#include "stub.h"
-
-#define DRIVER_AUTHOR "Takahiro Hirofuchi"
-#define DRIVER_DESC "USB/IP Host Driver"
-
-struct kmem_cache *stub_priv_cache;
-/*
- * busid_tables defines matching busids that usbip can grab. A user can change
- * dynamically what device is locally used and what device is exported to a
- * remote host.
- */
-#define MAX_BUSID 16
-static struct bus_id_priv busid_table[MAX_BUSID];
-static spinlock_t busid_table_lock;
-
-static void init_busid_table(void)
-{
-	/*
-	 * This also sets the bus_table[i].status to
-	 * STUB_BUSID_OTHER, which is 0.
-	 */
-	memset(busid_table, 0, sizeof(busid_table));
-
-	spin_lock_init(&busid_table_lock);
-}
-
-/*
- * Find the index of the busid by name.
- * Must be called with busid_table_lock held.
- */
-static int get_busid_idx(const char *busid)
-{
-	int i;
-	int idx = -1;
-
-	for (i = 0; i < MAX_BUSID; i++)
-		if (busid_table[i].name[0])
-			if (!strncmp(busid_table[i].name, busid, BUSID_SIZE)) {
-				idx = i;
-				break;
-			}
-	return idx;
-}
-
-struct bus_id_priv *get_busid_priv(const char *busid)
-{
-	int idx;
-	struct bus_id_priv *bid = NULL;
-
-	spin_lock(&busid_table_lock);
-	idx = get_busid_idx(busid);
-	if (idx >= 0)
-		bid = &(busid_table[idx]);
-	spin_unlock(&busid_table_lock);
-
-	return bid;
-}
-
-static int add_match_busid(char *busid)
-{
-	int i;
-	int ret = -1;
-
-	spin_lock(&busid_table_lock);
-	/* already registered? */
-	if (get_busid_idx(busid) >= 0) {
-		ret = 0;
-		goto out;
-	}
-
-	for (i = 0; i < MAX_BUSID; i++)
-		if (!busid_table[i].name[0]) {
-			strlcpy(busid_table[i].name, busid, BUSID_SIZE);
-			if ((busid_table[i].status != STUB_BUSID_ALLOC) &&
-			    (busid_table[i].status != STUB_BUSID_REMOV))
-				busid_table[i].status = STUB_BUSID_ADDED;
-			ret = 0;
-			break;
-		}
-
-out:
-	spin_unlock(&busid_table_lock);
-
-	return ret;
-}
-
-int del_match_busid(char *busid)
-{
-	int idx;
-	int ret = -1;
-
-	spin_lock(&busid_table_lock);
-	idx = get_busid_idx(busid);
-	if (idx < 0)
-		goto out;
-
-	/* found */
-	ret = 0;
-
-	if (busid_table[idx].status == STUB_BUSID_OTHER)
-		memset(busid_table[idx].name, 0, BUSID_SIZE);
-
-	if ((busid_table[idx].status != STUB_BUSID_OTHER) &&
-	    (busid_table[idx].status != STUB_BUSID_ADDED))
-		busid_table[idx].status = STUB_BUSID_REMOV;
-
-out:
-	spin_unlock(&busid_table_lock);
-
-	return ret;
-}
-
-static ssize_t show_match_busid(struct device_driver *drv, char *buf)
-{
-	int i;
-	char *out = buf;
-
-	spin_lock(&busid_table_lock);
-	for (i = 0; i < MAX_BUSID; i++)
-		if (busid_table[i].name[0])
-			out += sprintf(out, "%s ", busid_table[i].name);
-	spin_unlock(&busid_table_lock);
-	out += sprintf(out, "\n");
-
-	return out - buf;
-}
-
-static ssize_t store_match_busid(struct device_driver *dev, const char *buf,
-				 size_t count)
-{
-	int len;
-	char busid[BUSID_SIZE];
-
-	if (count < 5)
-		return -EINVAL;
-
-	/* busid needs to include \0 termination */
-	len = strlcpy(busid, buf + 4, BUSID_SIZE);
-	if (sizeof(busid) <= len)
-		return -EINVAL;
-
-	if (!strncmp(buf, "add ", 4)) {
-		if (add_match_busid(busid) < 0)
-			return -ENOMEM;
-
-		pr_debug("add busid %s\n", busid);
-		return count;
-	}
-
-	if (!strncmp(buf, "del ", 4)) {
-		if (del_match_busid(busid) < 0)
-			return -ENODEV;
-
-		pr_debug("del busid %s\n", busid);
-		return count;
-	}
-
-	return -EINVAL;
-}
-static DRIVER_ATTR(match_busid, S_IRUSR | S_IWUSR, show_match_busid,
-		   store_match_busid);
-
-static ssize_t rebind_store(struct device_driver *dev, const char *buf,
-				 size_t count)
-{
-	int ret;
-	int len;
-	struct bus_id_priv *bid;
-
-	/* buf length should be less that BUSID_SIZE */
-	len = strnlen(buf, BUSID_SIZE);
-
-	if (!(len < BUSID_SIZE))
-		return -EINVAL;
-
-	bid = get_busid_priv(buf);
-	if (!bid)
-		return -ENODEV;
-
-	ret = device_attach(&bid->udev->dev);
-	if (ret < 0) {
-		dev_err(&bid->udev->dev, "rebind failed\n");
-		return ret;
-	}
-
-	return count;
-}
-
-static DRIVER_ATTR_WO(rebind);
-
-static struct stub_priv *stub_priv_pop_from_listhead(struct list_head *listhead)
-{
-	struct stub_priv *priv, *tmp;
-
-	list_for_each_entry_safe(priv, tmp, listhead, list) {
-		list_del(&priv->list);
-		return priv;
-	}
-
-	return NULL;
-}
-
-static struct stub_priv *stub_priv_pop(struct stub_device *sdev)
-{
-	unsigned long flags;
-	struct stub_priv *priv;
-
-	spin_lock_irqsave(&sdev->priv_lock, flags);
-
-	priv = stub_priv_pop_from_listhead(&sdev->priv_init);
-	if (priv)
-		goto done;
-
-	priv = stub_priv_pop_from_listhead(&sdev->priv_tx);
-	if (priv)
-		goto done;
-
-	priv = stub_priv_pop_from_listhead(&sdev->priv_free);
-
-done:
-	spin_unlock_irqrestore(&sdev->priv_lock, flags);
-
-	return priv;
-}
-
-void stub_device_cleanup_urbs(struct stub_device *sdev)
-{
-	struct stub_priv *priv;
-	struct urb *urb;
-
-	dev_dbg(&sdev->udev->dev, "free sdev %p\n", sdev);
-
-	while ((priv = stub_priv_pop(sdev))) {
-		urb = priv->urb;
-		dev_dbg(&sdev->udev->dev, "free urb %p\n", urb);
-		usb_kill_urb(urb);
-
-		kmem_cache_free(stub_priv_cache, priv);
-
-		kfree(urb->transfer_buffer);
-		kfree(urb->setup_packet);
-		usb_free_urb(urb);
-	}
-}
-
-static int __init usbip_host_init(void)
-{
-	int ret;
-
-	init_busid_table();
-
-	stub_priv_cache = KMEM_CACHE(stub_priv, SLAB_HWCACHE_ALIGN);
-	if (!stub_priv_cache) {
-		pr_err("kmem_cache_create failed\n");
-		return -ENOMEM;
-	}
-
-	ret = usb_register_device_driver(&stub_driver, THIS_MODULE);
-	if (ret) {
-		pr_err("usb_register failed %d\n", ret);
-		goto err_usb_register;
-	}
-
-	ret = driver_create_file(&stub_driver.drvwrap.driver,
-				 &driver_attr_match_busid);
-	if (ret) {
-		pr_err("driver_create_file failed\n");
-		goto err_create_file;
-	}
-
-	ret = driver_create_file(&stub_driver.drvwrap.driver,
-				 &driver_attr_rebind);
-	if (ret) {
-		pr_err("driver_create_file failed\n");
-		goto err_create_file;
-	}
-
-	pr_info(DRIVER_DESC " v" USBIP_VERSION "\n");
-	return ret;
-
-err_create_file:
-	usb_deregister_device_driver(&stub_driver);
-err_usb_register:
-	kmem_cache_destroy(stub_priv_cache);
-	return ret;
-}
-
-static void __exit usbip_host_exit(void)
-{
-	driver_remove_file(&stub_driver.drvwrap.driver,
-			   &driver_attr_match_busid);
-
-	driver_remove_file(&stub_driver.drvwrap.driver,
-			   &driver_attr_rebind);
-
-	/*
-	 * deregister() calls stub_disconnect() for all devices. Device
-	 * specific data is cleared in stub_disconnect().
-	 */
-	usb_deregister_device_driver(&stub_driver);
-
-	kmem_cache_destroy(stub_priv_cache);
-}
-
-module_init(usbip_host_init);
-module_exit(usbip_host_exit);
-
-MODULE_AUTHOR(DRIVER_AUTHOR);
-MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE("GPL");
-MODULE_VERSION(USBIP_VERSION);
diff --git a/drivers/staging/usbip/stub_rx.c b/drivers/staging/usbip/stub_rx.c
deleted file mode 100644
index 00e475c51a12..000000000000
--- a/drivers/staging/usbip/stub_rx.c
+++ /dev/null
@@ -1,594 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <asm/byteorder.h>
-#include <linux/kthread.h>
-#include <linux/usb.h>
-#include <linux/usb/hcd.h>
-
-#include "usbip_common.h"
-#include "stub.h"
-
-static int is_clear_halt_cmd(struct urb *urb)
-{
-	struct usb_ctrlrequest *req;
-
-	req = (struct usb_ctrlrequest *) urb->setup_packet;
-
-	 return (req->bRequest == USB_REQ_CLEAR_FEATURE) &&
-		 (req->bRequestType == USB_RECIP_ENDPOINT) &&
-		 (req->wValue == USB_ENDPOINT_HALT);
-}
-
-static int is_set_interface_cmd(struct urb *urb)
-{
-	struct usb_ctrlrequest *req;
-
-	req = (struct usb_ctrlrequest *) urb->setup_packet;
-
-	return (req->bRequest == USB_REQ_SET_INTERFACE) &&
-		(req->bRequestType == USB_RECIP_INTERFACE);
-}
-
-static int is_set_configuration_cmd(struct urb *urb)
-{
-	struct usb_ctrlrequest *req;
-
-	req = (struct usb_ctrlrequest *) urb->setup_packet;
-
-	return (req->bRequest == USB_REQ_SET_CONFIGURATION) &&
-		(req->bRequestType == USB_RECIP_DEVICE);
-}
-
-static int is_reset_device_cmd(struct urb *urb)
-{
-	struct usb_ctrlrequest *req;
-	__u16 value;
-	__u16 index;
-
-	req = (struct usb_ctrlrequest *) urb->setup_packet;
-	value = le16_to_cpu(req->wValue);
-	index = le16_to_cpu(req->wIndex);
-
-	if ((req->bRequest == USB_REQ_SET_FEATURE) &&
-	    (req->bRequestType == USB_RT_PORT) &&
-	    (value == USB_PORT_FEAT_RESET)) {
-		usbip_dbg_stub_rx("reset_device_cmd, port %u\n", index);
-		return 1;
-	} else
-		return 0;
-}
-
-static int tweak_clear_halt_cmd(struct urb *urb)
-{
-	struct usb_ctrlrequest *req;
-	int target_endp;
-	int target_dir;
-	int target_pipe;
-	int ret;
-
-	req = (struct usb_ctrlrequest *) urb->setup_packet;
-
-	/*
-	 * The stalled endpoint is specified in the wIndex value. The endpoint
-	 * of the urb is the target of this clear_halt request (i.e., control
-	 * endpoint).
-	 */
-	target_endp = le16_to_cpu(req->wIndex) & 0x000f;
-
-	/* the stalled endpoint direction is IN or OUT?. USB_DIR_IN is 0x80.  */
-	target_dir = le16_to_cpu(req->wIndex) & 0x0080;
-
-	if (target_dir)
-		target_pipe = usb_rcvctrlpipe(urb->dev, target_endp);
-	else
-		target_pipe = usb_sndctrlpipe(urb->dev, target_endp);
-
-	ret = usb_clear_halt(urb->dev, target_pipe);
-	if (ret < 0)
-		dev_err(&urb->dev->dev,
-			"usb_clear_halt error: devnum %d endp %d ret %d\n",
-			urb->dev->devnum, target_endp, ret);
-	else
-		dev_info(&urb->dev->dev,
-			 "usb_clear_halt done: devnum %d endp %d\n",
-			 urb->dev->devnum, target_endp);
-
-	return ret;
-}
-
-static int tweak_set_interface_cmd(struct urb *urb)
-{
-	struct usb_ctrlrequest *req;
-	__u16 alternate;
-	__u16 interface;
-	int ret;
-
-	req = (struct usb_ctrlrequest *) urb->setup_packet;
-	alternate = le16_to_cpu(req->wValue);
-	interface = le16_to_cpu(req->wIndex);
-
-	usbip_dbg_stub_rx("set_interface: inf %u alt %u\n",
-			  interface, alternate);
-
-	ret = usb_set_interface(urb->dev, interface, alternate);
-	if (ret < 0)
-		dev_err(&urb->dev->dev,
-			"usb_set_interface error: inf %u alt %u ret %d\n",
-			interface, alternate, ret);
-	else
-		dev_info(&urb->dev->dev,
-			"usb_set_interface done: inf %u alt %u\n",
-			interface, alternate);
-
-	return ret;
-}
-
-static int tweak_set_configuration_cmd(struct urb *urb)
-{
-	struct stub_priv *priv = (struct stub_priv *) urb->context;
-	struct stub_device *sdev = priv->sdev;
-	struct usb_ctrlrequest *req;
-	__u16 config;
-	int err;
-
-	req = (struct usb_ctrlrequest *) urb->setup_packet;
-	config = le16_to_cpu(req->wValue);
-
-	err = usb_set_configuration(sdev->udev, config);
-	if (err && err != -ENODEV)
-		dev_err(&sdev->udev->dev, "can't set config #%d, error %d\n",
-			config, err);
-	return 0;
-}
-
-static int tweak_reset_device_cmd(struct urb *urb)
-{
-	struct stub_priv *priv = (struct stub_priv *) urb->context;
-	struct stub_device *sdev = priv->sdev;
-
-	dev_info(&urb->dev->dev, "usb_queue_reset_device\n");
-
-	/*
-	 * With the implementation of pre_reset and post_reset the driver no
-	 * longer unbinds. This allows the use of synchronous reset.
-	 */
-
-	if (usb_lock_device_for_reset(sdev->udev, sdev->interface) < 0) {
-		dev_err(&urb->dev->dev, "could not obtain lock to reset device\n");
-		return 0;
-	}
-	usb_reset_device(sdev->udev);
-	usb_unlock_device(sdev->udev);
-
-	return 0;
-}
-
-/*
- * clear_halt, set_interface, and set_configuration require special tricks.
- */
-static void tweak_special_requests(struct urb *urb)
-{
-	if (!urb || !urb->setup_packet)
-		return;
-
-	if (usb_pipetype(urb->pipe) != PIPE_CONTROL)
-		return;
-
-	if (is_clear_halt_cmd(urb))
-		/* tweak clear_halt */
-		 tweak_clear_halt_cmd(urb);
-
-	else if (is_set_interface_cmd(urb))
-		/* tweak set_interface */
-		tweak_set_interface_cmd(urb);
-
-	else if (is_set_configuration_cmd(urb))
-		/* tweak set_configuration */
-		tweak_set_configuration_cmd(urb);
-
-	else if (is_reset_device_cmd(urb))
-		tweak_reset_device_cmd(urb);
-	else
-		usbip_dbg_stub_rx("no need to tweak\n");
-}
-
-/*
- * stub_recv_unlink() unlinks the URB by a call to usb_unlink_urb().
- * By unlinking the urb asynchronously, stub_rx can continuously
- * process coming urbs.  Even if the urb is unlinked, its completion
- * handler will be called and stub_tx will send a return pdu.
- *
- * See also comments about unlinking strategy in vhci_hcd.c.
- */
-static int stub_recv_cmd_unlink(struct stub_device *sdev,
-				struct usbip_header *pdu)
-{
-	int ret;
-	unsigned long flags;
-	struct stub_priv *priv;
-
-	spin_lock_irqsave(&sdev->priv_lock, flags);
-
-	list_for_each_entry(priv, &sdev->priv_init, list) {
-		if (priv->seqnum != pdu->u.cmd_unlink.seqnum)
-			continue;
-
-		dev_info(&priv->urb->dev->dev, "unlink urb %p\n",
-			 priv->urb);
-
-		/*
-		 * This matched urb is not completed yet (i.e., be in
-		 * flight in usb hcd hardware/driver). Now we are
-		 * cancelling it. The unlinking flag means that we are
-		 * now not going to return the normal result pdu of a
-		 * submission request, but going to return a result pdu
-		 * of the unlink request.
-		 */
-		priv->unlinking = 1;
-
-		/*
-		 * In the case that unlinking flag is on, prev->seqnum
-		 * is changed from the seqnum of the cancelling urb to
-		 * the seqnum of the unlink request. This will be used
-		 * to make the result pdu of the unlink request.
-		 */
-		priv->seqnum = pdu->base.seqnum;
-
-		spin_unlock_irqrestore(&sdev->priv_lock, flags);
-
-		/*
-		 * usb_unlink_urb() is now out of spinlocking to avoid
-		 * spinlock recursion since stub_complete() is
-		 * sometimes called in this context but not in the
-		 * interrupt context.  If stub_complete() is executed
-		 * before we call usb_unlink_urb(), usb_unlink_urb()
-		 * will return an error value. In this case, stub_tx
-		 * will return the result pdu of this unlink request
-		 * though submission is completed and actual unlinking
-		 * is not executed. OK?
-		 */
-		/* In the above case, urb->status is not -ECONNRESET,
-		 * so a driver in a client host will know the failure
-		 * of the unlink request ?
-		 */
-		ret = usb_unlink_urb(priv->urb);
-		if (ret != -EINPROGRESS)
-			dev_err(&priv->urb->dev->dev,
-				"failed to unlink a urb %p, ret %d\n",
-				priv->urb, ret);
-
-		return 0;
-	}
-
-	usbip_dbg_stub_rx("seqnum %d is not pending\n",
-			  pdu->u.cmd_unlink.seqnum);
-
-	/*
-	 * The urb of the unlink target is not found in priv_init queue. It was
-	 * already completed and its results is/was going to be sent by a
-	 * CMD_RET pdu. In this case, usb_unlink_urb() is not needed. We only
-	 * return the completeness of this unlink request to vhci_hcd.
-	 */
-	stub_enqueue_ret_unlink(sdev, pdu->base.seqnum, 0);
-
-	spin_unlock_irqrestore(&sdev->priv_lock, flags);
-
-	return 0;
-}
-
-static int valid_request(struct stub_device *sdev, struct usbip_header *pdu)
-{
-	struct usbip_device *ud = &sdev->ud;
-	int valid = 0;
-
-	if (pdu->base.devid == sdev->devid) {
-		spin_lock_irq(&ud->lock);
-		if (ud->status == SDEV_ST_USED) {
-			/* A request is valid. */
-			valid = 1;
-		}
-		spin_unlock_irq(&ud->lock);
-	}
-
-	return valid;
-}
-
-static struct stub_priv *stub_priv_alloc(struct stub_device *sdev,
-					 struct usbip_header *pdu)
-{
-	struct stub_priv *priv;
-	struct usbip_device *ud = &sdev->ud;
-	unsigned long flags;
-
-	spin_lock_irqsave(&sdev->priv_lock, flags);
-
-	priv = kmem_cache_zalloc(stub_priv_cache, GFP_ATOMIC);
-	if (!priv) {
-		dev_err(&sdev->interface->dev, "alloc stub_priv\n");
-		spin_unlock_irqrestore(&sdev->priv_lock, flags);
-		usbip_event_add(ud, SDEV_EVENT_ERROR_MALLOC);
-		return NULL;
-	}
-
-	priv->seqnum = pdu->base.seqnum;
-	priv->sdev = sdev;
-
-	/*
-	 * After a stub_priv is linked to a list_head,
-	 * our error handler can free allocated data.
-	 */
-	list_add_tail(&priv->list, &sdev->priv_init);
-
-	spin_unlock_irqrestore(&sdev->priv_lock, flags);
-
-	return priv;
-}
-
-static int get_pipe(struct stub_device *sdev, int epnum, int dir)
-{
-	struct usb_device *udev = sdev->udev;
-	struct usb_host_endpoint *ep;
-	struct usb_endpoint_descriptor *epd = NULL;
-
-	if (dir == USBIP_DIR_IN)
-		ep = udev->ep_in[epnum & 0x7f];
-	else
-		ep = udev->ep_out[epnum & 0x7f];
-	if (!ep) {
-		dev_err(&sdev->interface->dev, "no such endpoint?, %d\n",
-			epnum);
-		BUG();
-	}
-
-	epd = &ep->desc;
-	if (usb_endpoint_xfer_control(epd)) {
-		if (dir == USBIP_DIR_OUT)
-			return usb_sndctrlpipe(udev, epnum);
-		else
-			return usb_rcvctrlpipe(udev, epnum);
-	}
-
-	if (usb_endpoint_xfer_bulk(epd)) {
-		if (dir == USBIP_DIR_OUT)
-			return usb_sndbulkpipe(udev, epnum);
-		else
-			return usb_rcvbulkpipe(udev, epnum);
-	}
-
-	if (usb_endpoint_xfer_int(epd)) {
-		if (dir == USBIP_DIR_OUT)
-			return usb_sndintpipe(udev, epnum);
-		else
-			return usb_rcvintpipe(udev, epnum);
-	}
-
-	if (usb_endpoint_xfer_isoc(epd)) {
-		if (dir == USBIP_DIR_OUT)
-			return usb_sndisocpipe(udev, epnum);
-		else
-			return usb_rcvisocpipe(udev, epnum);
-	}
-
-	/* NOT REACHED */
-	dev_err(&sdev->interface->dev, "get pipe, epnum %d\n", epnum);
-	return 0;
-}
-
-static void masking_bogus_flags(struct urb *urb)
-{
-	int				xfertype;
-	struct usb_device		*dev;
-	struct usb_host_endpoint	*ep;
-	int				is_out;
-	unsigned int	allowed;
-
-	if (!urb || urb->hcpriv || !urb->complete)
-		return;
-	dev = urb->dev;
-	if ((!dev) || (dev->state < USB_STATE_UNAUTHENTICATED))
-		return;
-
-	ep = (usb_pipein(urb->pipe) ? dev->ep_in : dev->ep_out)
-		[usb_pipeendpoint(urb->pipe)];
-	if (!ep)
-		return;
-
-	xfertype = usb_endpoint_type(&ep->desc);
-	if (xfertype == USB_ENDPOINT_XFER_CONTROL) {
-		struct usb_ctrlrequest *setup =
-			(struct usb_ctrlrequest *) urb->setup_packet;
-
-		if (!setup)
-			return;
-		is_out = !(setup->bRequestType & USB_DIR_IN) ||
-			!setup->wLength;
-	} else {
-		is_out = usb_endpoint_dir_out(&ep->desc);
-	}
-
-	/* enforce simple/standard policy */
-	allowed = (URB_NO_TRANSFER_DMA_MAP | URB_NO_INTERRUPT |
-		   URB_DIR_MASK | URB_FREE_BUFFER);
-	switch (xfertype) {
-	case USB_ENDPOINT_XFER_BULK:
-		if (is_out)
-			allowed |= URB_ZERO_PACKET;
-		/* FALLTHROUGH */
-	case USB_ENDPOINT_XFER_CONTROL:
-		allowed |= URB_NO_FSBR;	/* only affects UHCI */
-		/* FALLTHROUGH */
-	default:			/* all non-iso endpoints */
-		if (!is_out)
-			allowed |= URB_SHORT_NOT_OK;
-		break;
-	case USB_ENDPOINT_XFER_ISOC:
-		allowed |= URB_ISO_ASAP;
-		break;
-	}
-	urb->transfer_flags &= allowed;
-}
-
-static void stub_recv_cmd_submit(struct stub_device *sdev,
-				 struct usbip_header *pdu)
-{
-	int ret;
-	struct stub_priv *priv;
-	struct usbip_device *ud = &sdev->ud;
-	struct usb_device *udev = sdev->udev;
-	int pipe = get_pipe(sdev, pdu->base.ep, pdu->base.direction);
-
-	priv = stub_priv_alloc(sdev, pdu);
-	if (!priv)
-		return;
-
-	/* setup a urb */
-	if (usb_pipeisoc(pipe))
-		priv->urb = usb_alloc_urb(pdu->u.cmd_submit.number_of_packets,
-					  GFP_KERNEL);
-	else
-		priv->urb = usb_alloc_urb(0, GFP_KERNEL);
-
-	if (!priv->urb) {
-		dev_err(&sdev->interface->dev, "malloc urb\n");
-		usbip_event_add(ud, SDEV_EVENT_ERROR_MALLOC);
-		return;
-	}
-
-	/* allocate urb transfer buffer, if needed */
-	if (pdu->u.cmd_submit.transfer_buffer_length > 0) {
-		priv->urb->transfer_buffer =
-			kzalloc(pdu->u.cmd_submit.transfer_buffer_length,
-				GFP_KERNEL);
-		if (!priv->urb->transfer_buffer) {
-			usbip_event_add(ud, SDEV_EVENT_ERROR_MALLOC);
-			return;
-		}
-	}
-
-	/* copy urb setup packet */
-	priv->urb->setup_packet = kmemdup(&pdu->u.cmd_submit.setup, 8,
-					  GFP_KERNEL);
-	if (!priv->urb->setup_packet) {
-		dev_err(&sdev->interface->dev, "allocate setup_packet\n");
-		usbip_event_add(ud, SDEV_EVENT_ERROR_MALLOC);
-		return;
-	}
-
-	/* set other members from the base header of pdu */
-	priv->urb->context                = (void *) priv;
-	priv->urb->dev                    = udev;
-	priv->urb->pipe                   = pipe;
-	priv->urb->complete               = stub_complete;
-
-	usbip_pack_pdu(pdu, priv->urb, USBIP_CMD_SUBMIT, 0);
-
-
-	if (usbip_recv_xbuff(ud, priv->urb) < 0)
-		return;
-
-	if (usbip_recv_iso(ud, priv->urb) < 0)
-		return;
-
-	/* no need to submit an intercepted request, but harmless? */
-	tweak_special_requests(priv->urb);
-
-	masking_bogus_flags(priv->urb);
-	/* urb is now ready to submit */
-	ret = usb_submit_urb(priv->urb, GFP_KERNEL);
-
-	if (ret == 0)
-		usbip_dbg_stub_rx("submit urb ok, seqnum %u\n",
-				  pdu->base.seqnum);
-	else {
-		dev_err(&sdev->interface->dev, "submit_urb error, %d\n", ret);
-		usbip_dump_header(pdu);
-		usbip_dump_urb(priv->urb);
-
-		/*
-		 * Pessimistic.
-		 * This connection will be discarded.
-		 */
-		usbip_event_add(ud, SDEV_EVENT_ERROR_SUBMIT);
-	}
-
-	usbip_dbg_stub_rx("Leave\n");
-}
-
-/* recv a pdu */
-static void stub_rx_pdu(struct usbip_device *ud)
-{
-	int ret;
-	struct usbip_header pdu;
-	struct stub_device *sdev = container_of(ud, struct stub_device, ud);
-	struct device *dev = &sdev->udev->dev;
-
-	usbip_dbg_stub_rx("Enter\n");
-
-	memset(&pdu, 0, sizeof(pdu));
-
-	/* receive a pdu header */
-	ret = usbip_recv(ud->tcp_socket, &pdu, sizeof(pdu));
-	if (ret != sizeof(pdu)) {
-		dev_err(dev, "recv a header, %d\n", ret);
-		usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
-		return;
-	}
-
-	usbip_header_correct_endian(&pdu, 0);
-
-	if (usbip_dbg_flag_stub_rx)
-		usbip_dump_header(&pdu);
-
-	if (!valid_request(sdev, &pdu)) {
-		dev_err(dev, "recv invalid request\n");
-		usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
-		return;
-	}
-
-	switch (pdu.base.command) {
-	case USBIP_CMD_UNLINK:
-		stub_recv_cmd_unlink(sdev, &pdu);
-		break;
-
-	case USBIP_CMD_SUBMIT:
-		stub_recv_cmd_submit(sdev, &pdu);
-		break;
-
-	default:
-		/* NOTREACHED */
-		dev_err(dev, "unknown pdu\n");
-		usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
-		break;
-	}
-}
-
-int stub_rx_loop(void *data)
-{
-	struct usbip_device *ud = data;
-
-	while (!kthread_should_stop()) {
-		if (usbip_event_happened(ud))
-			break;
-
-		stub_rx_pdu(ud);
-	}
-
-	return 0;
-}
diff --git a/drivers/staging/usbip/stub_tx.c b/drivers/staging/usbip/stub_tx.c
deleted file mode 100644
index dbcabc9dbe0d..000000000000
--- a/drivers/staging/usbip/stub_tx.c
+++ /dev/null
@@ -1,398 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <linux/kthread.h>
-#include <linux/socket.h>
-
-#include "usbip_common.h"
-#include "stub.h"
-
-static void stub_free_priv_and_urb(struct stub_priv *priv)
-{
-	struct urb *urb = priv->urb;
-
-	kfree(urb->setup_packet);
-	kfree(urb->transfer_buffer);
-	list_del(&priv->list);
-	kmem_cache_free(stub_priv_cache, priv);
-	usb_free_urb(urb);
-}
-
-/* be in spin_lock_irqsave(&sdev->priv_lock, flags) */
-void stub_enqueue_ret_unlink(struct stub_device *sdev, __u32 seqnum,
-			     __u32 status)
-{
-	struct stub_unlink *unlink;
-
-	unlink = kzalloc(sizeof(struct stub_unlink), GFP_ATOMIC);
-	if (!unlink) {
-		usbip_event_add(&sdev->ud, VDEV_EVENT_ERROR_MALLOC);
-		return;
-	}
-
-	unlink->seqnum = seqnum;
-	unlink->status = status;
-
-	list_add_tail(&unlink->list, &sdev->unlink_tx);
-}
-
-/**
- * stub_complete - completion handler of a usbip urb
- * @urb: pointer to the urb completed
- *
- * When a urb has completed, the USB core driver calls this function mostly in
- * the interrupt context. To return the result of a urb, the completed urb is
- * linked to the pending list of returning.
- *
- */
-void stub_complete(struct urb *urb)
-{
-	struct stub_priv *priv = (struct stub_priv *) urb->context;
-	struct stub_device *sdev = priv->sdev;
-	unsigned long flags;
-
-	usbip_dbg_stub_tx("complete! status %d\n", urb->status);
-
-	switch (urb->status) {
-	case 0:
-		/* OK */
-		break;
-	case -ENOENT:
-		dev_info(&urb->dev->dev,
-			 "stopped by a call to usb_kill_urb() because of cleaning up a virtual connection\n");
-		return;
-	case -ECONNRESET:
-		dev_info(&urb->dev->dev,
-			 "unlinked by a call to usb_unlink_urb()\n");
-		break;
-	case -EPIPE:
-		dev_info(&urb->dev->dev, "endpoint %d is stalled\n",
-			 usb_pipeendpoint(urb->pipe));
-		break;
-	case -ESHUTDOWN:
-		dev_info(&urb->dev->dev, "device removed?\n");
-		break;
-	default:
-		dev_info(&urb->dev->dev,
-			 "urb completion with non-zero status %d\n",
-			 urb->status);
-		break;
-	}
-
-	/* link a urb to the queue of tx. */
-	spin_lock_irqsave(&sdev->priv_lock, flags);
-	if (priv->unlinking) {
-		stub_enqueue_ret_unlink(sdev, priv->seqnum, urb->status);
-		stub_free_priv_and_urb(priv);
-	} else {
-		list_move_tail(&priv->list, &sdev->priv_tx);
-	}
-	spin_unlock_irqrestore(&sdev->priv_lock, flags);
-
-	/* wake up tx_thread */
-	wake_up(&sdev->tx_waitq);
-}
-
-static inline void setup_base_pdu(struct usbip_header_basic *base,
-				  __u32 command, __u32 seqnum)
-{
-	base->command	= command;
-	base->seqnum	= seqnum;
-	base->devid	= 0;
-	base->ep	= 0;
-	base->direction = 0;
-}
-
-static void setup_ret_submit_pdu(struct usbip_header *rpdu, struct urb *urb)
-{
-	struct stub_priv *priv = (struct stub_priv *) urb->context;
-
-	setup_base_pdu(&rpdu->base, USBIP_RET_SUBMIT, priv->seqnum);
-	usbip_pack_pdu(rpdu, urb, USBIP_RET_SUBMIT, 1);
-}
-
-static void setup_ret_unlink_pdu(struct usbip_header *rpdu,
-				 struct stub_unlink *unlink)
-{
-	setup_base_pdu(&rpdu->base, USBIP_RET_UNLINK, unlink->seqnum);
-	rpdu->u.ret_unlink.status = unlink->status;
-}
-
-static struct stub_priv *dequeue_from_priv_tx(struct stub_device *sdev)
-{
-	unsigned long flags;
-	struct stub_priv *priv, *tmp;
-
-	spin_lock_irqsave(&sdev->priv_lock, flags);
-
-	list_for_each_entry_safe(priv, tmp, &sdev->priv_tx, list) {
-		list_move_tail(&priv->list, &sdev->priv_free);
-		spin_unlock_irqrestore(&sdev->priv_lock, flags);
-		return priv;
-	}
-
-	spin_unlock_irqrestore(&sdev->priv_lock, flags);
-
-	return NULL;
-}
-
-static int stub_send_ret_submit(struct stub_device *sdev)
-{
-	unsigned long flags;
-	struct stub_priv *priv, *tmp;
-
-	struct msghdr msg;
-	size_t txsize;
-
-	size_t total_size = 0;
-
-	while ((priv = dequeue_from_priv_tx(sdev)) != NULL) {
-		int ret;
-		struct urb *urb = priv->urb;
-		struct usbip_header pdu_header;
-		struct usbip_iso_packet_descriptor *iso_buffer = NULL;
-		struct kvec *iov = NULL;
-		int iovnum = 0;
-
-		txsize = 0;
-		memset(&pdu_header, 0, sizeof(pdu_header));
-		memset(&msg, 0, sizeof(msg));
-
-		if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS)
-			iovnum = 2 + urb->number_of_packets;
-		else
-			iovnum = 2;
-
-		iov = kcalloc(iovnum, sizeof(struct kvec), GFP_KERNEL);
-
-		if (!iov) {
-			usbip_event_add(&sdev->ud, SDEV_EVENT_ERROR_MALLOC);
-			return -1;
-		}
-
-		iovnum = 0;
-
-		/* 1. setup usbip_header */
-		setup_ret_submit_pdu(&pdu_header, urb);
-		usbip_dbg_stub_tx("setup txdata seqnum: %d urb: %p\n",
-				  pdu_header.base.seqnum, urb);
-		usbip_header_correct_endian(&pdu_header, 1);
-
-		iov[iovnum].iov_base = &pdu_header;
-		iov[iovnum].iov_len  = sizeof(pdu_header);
-		iovnum++;
-		txsize += sizeof(pdu_header);
-
-		/* 2. setup transfer buffer */
-		if (usb_pipein(urb->pipe) &&
-		    usb_pipetype(urb->pipe) != PIPE_ISOCHRONOUS &&
-		    urb->actual_length > 0) {
-			iov[iovnum].iov_base = urb->transfer_buffer;
-			iov[iovnum].iov_len  = urb->actual_length;
-			iovnum++;
-			txsize += urb->actual_length;
-		} else if (usb_pipein(urb->pipe) &&
-			   usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) {
-			/*
-			 * For isochronous packets: actual length is the sum of
-			 * the actual length of the individual, packets, but as
-			 * the packet offsets are not changed there will be
-			 * padding between the packets. To optimally use the
-			 * bandwidth the padding is not transmitted.
-			 */
-
-			int i;
-
-			for (i = 0; i < urb->number_of_packets; i++) {
-				iov[iovnum].iov_base = urb->transfer_buffer +
-					urb->iso_frame_desc[i].offset;
-				iov[iovnum].iov_len =
-					urb->iso_frame_desc[i].actual_length;
-				iovnum++;
-				txsize += urb->iso_frame_desc[i].actual_length;
-			}
-
-			if (txsize != sizeof(pdu_header) + urb->actual_length) {
-				dev_err(&sdev->interface->dev,
-					"actual length of urb %d does not match iso packet sizes %zu\n",
-					urb->actual_length,
-					txsize-sizeof(pdu_header));
-				kfree(iov);
-				usbip_event_add(&sdev->ud,
-						SDEV_EVENT_ERROR_TCP);
-			   return -1;
-			}
-		}
-
-		/* 3. setup iso_packet_descriptor */
-		if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) {
-			ssize_t len = 0;
-
-			iso_buffer = usbip_alloc_iso_desc_pdu(urb, &len);
-			if (!iso_buffer) {
-				usbip_event_add(&sdev->ud,
-						SDEV_EVENT_ERROR_MALLOC);
-				kfree(iov);
-				return -1;
-			}
-
-			iov[iovnum].iov_base = iso_buffer;
-			iov[iovnum].iov_len  = len;
-			txsize += len;
-			iovnum++;
-		}
-
-		ret = kernel_sendmsg(sdev->ud.tcp_socket, &msg,
-						iov,  iovnum, txsize);
-		if (ret != txsize) {
-			dev_err(&sdev->interface->dev,
-				"sendmsg failed!, retval %d for %zd\n",
-				ret, txsize);
-			kfree(iov);
-			kfree(iso_buffer);
-			usbip_event_add(&sdev->ud, SDEV_EVENT_ERROR_TCP);
-			return -1;
-		}
-
-		kfree(iov);
-		kfree(iso_buffer);
-
-		total_size += txsize;
-	}
-
-	spin_lock_irqsave(&sdev->priv_lock, flags);
-	list_for_each_entry_safe(priv, tmp, &sdev->priv_free, list) {
-		stub_free_priv_and_urb(priv);
-	}
-	spin_unlock_irqrestore(&sdev->priv_lock, flags);
-
-	return total_size;
-}
-
-static struct stub_unlink *dequeue_from_unlink_tx(struct stub_device *sdev)
-{
-	unsigned long flags;
-	struct stub_unlink *unlink, *tmp;
-
-	spin_lock_irqsave(&sdev->priv_lock, flags);
-
-	list_for_each_entry_safe(unlink, tmp, &sdev->unlink_tx, list) {
-		list_move_tail(&unlink->list, &sdev->unlink_free);
-		spin_unlock_irqrestore(&sdev->priv_lock, flags);
-		return unlink;
-	}
-
-	spin_unlock_irqrestore(&sdev->priv_lock, flags);
-
-	return NULL;
-}
-
-static int stub_send_ret_unlink(struct stub_device *sdev)
-{
-	unsigned long flags;
-	struct stub_unlink *unlink, *tmp;
-
-	struct msghdr msg;
-	struct kvec iov[1];
-	size_t txsize;
-
-	size_t total_size = 0;
-
-	while ((unlink = dequeue_from_unlink_tx(sdev)) != NULL) {
-		int ret;
-		struct usbip_header pdu_header;
-
-		txsize = 0;
-		memset(&pdu_header, 0, sizeof(pdu_header));
-		memset(&msg, 0, sizeof(msg));
-		memset(&iov, 0, sizeof(iov));
-
-		usbip_dbg_stub_tx("setup ret unlink %lu\n", unlink->seqnum);
-
-		/* 1. setup usbip_header */
-		setup_ret_unlink_pdu(&pdu_header, unlink);
-		usbip_header_correct_endian(&pdu_header, 1);
-
-		iov[0].iov_base = &pdu_header;
-		iov[0].iov_len  = sizeof(pdu_header);
-		txsize += sizeof(pdu_header);
-
-		ret = kernel_sendmsg(sdev->ud.tcp_socket, &msg, iov,
-				     1, txsize);
-		if (ret != txsize) {
-			dev_err(&sdev->interface->dev,
-				"sendmsg failed!, retval %d for %zd\n",
-				ret, txsize);
-			usbip_event_add(&sdev->ud, SDEV_EVENT_ERROR_TCP);
-			return -1;
-		}
-
-		usbip_dbg_stub_tx("send txdata\n");
-		total_size += txsize;
-	}
-
-	spin_lock_irqsave(&sdev->priv_lock, flags);
-
-	list_for_each_entry_safe(unlink, tmp, &sdev->unlink_free, list) {
-		list_del(&unlink->list);
-		kfree(unlink);
-	}
-
-	spin_unlock_irqrestore(&sdev->priv_lock, flags);
-
-	return total_size;
-}
-
-int stub_tx_loop(void *data)
-{
-	struct usbip_device *ud = data;
-	struct stub_device *sdev = container_of(ud, struct stub_device, ud);
-
-	while (!kthread_should_stop()) {
-		if (usbip_event_happened(ud))
-			break;
-
-		/*
-		 * send_ret_submit comes earlier than send_ret_unlink.  stub_rx
-		 * looks at only priv_init queue. If the completion of a URB is
-		 * earlier than the receive of CMD_UNLINK, priv is moved to
-		 * priv_tx queue and stub_rx does not find the target priv. In
-		 * this case, vhci_rx receives the result of the submit request
-		 * and then receives the result of the unlink request. The
-		 * result of the submit is given back to the usbcore as the
-		 * completion of the unlink request. The request of the
-		 * unlink is ignored. This is ok because a driver who calls
-		 * usb_unlink_urb() understands the unlink was too late by
-		 * getting the status of the given-backed URB which has the
-		 * status of usb_submit_urb().
-		 */
-		if (stub_send_ret_submit(sdev) < 0)
-			break;
-
-		if (stub_send_ret_unlink(sdev) < 0)
-			break;
-
-		wait_event_interruptible(sdev->tx_waitq,
-					 (!list_empty(&sdev->priv_tx) ||
-					  !list_empty(&sdev->unlink_tx) ||
-					  kthread_should_stop()));
-	}
-
-	return 0;
-}
diff --git a/drivers/staging/usbip/uapi/usbip.h b/drivers/staging/usbip/uapi/usbip.h
deleted file mode 100644
index fa5db30ede36..000000000000
--- a/drivers/staging/usbip/uapi/usbip.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- *	usbip.h
- *
- *	USBIP uapi defines and function prototypes etc.
-*/
-
-#ifndef _UAPI_LINUX_USBIP_H
-#define _UAPI_LINUX_USBIP_H
-
-/* usbip device status - exported in usbip device sysfs status */
-enum usbip_device_status {
-	/* sdev is available. */
-	SDEV_ST_AVAILABLE = 0x01,
-	/* sdev is now used. */
-	SDEV_ST_USED,
-	/* sdev is unusable because of a fatal error. */
-	SDEV_ST_ERROR,
-
-	/* vdev does not connect a remote device. */
-	VDEV_ST_NULL,
-	/* vdev is used, but the USB address is not assigned yet */
-	VDEV_ST_NOTASSIGNED,
-	VDEV_ST_USED,
-	VDEV_ST_ERROR
-};
-#endif /* _UAPI_LINUX_USBIP_H */
diff --git a/drivers/staging/usbip/usbip_common.c b/drivers/staging/usbip/usbip_common.c
deleted file mode 100644
index facaaf003f19..000000000000
--- a/drivers/staging/usbip/usbip_common.c
+++ /dev/null
@@ -1,776 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <asm/byteorder.h>
-#include <linux/file.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/stat.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <net/sock.h>
-
-#include "usbip_common.h"
-
-#define DRIVER_AUTHOR "Takahiro Hirofuchi <hirofuchi@users.sourceforge.net>"
-#define DRIVER_DESC "USB/IP Core"
-
-#ifdef CONFIG_USBIP_DEBUG
-unsigned long usbip_debug_flag = 0xffffffff;
-#else
-unsigned long usbip_debug_flag;
-#endif
-EXPORT_SYMBOL_GPL(usbip_debug_flag);
-module_param(usbip_debug_flag, ulong, S_IRUGO|S_IWUSR);
-MODULE_PARM_DESC(usbip_debug_flag, "debug flags (defined in usbip_common.h)");
-
-/* FIXME */
-struct device_attribute dev_attr_usbip_debug;
-EXPORT_SYMBOL_GPL(dev_attr_usbip_debug);
-
-static ssize_t usbip_debug_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "%lx\n", usbip_debug_flag);
-}
-
-static ssize_t usbip_debug_store(struct device *dev,
-				 struct device_attribute *attr, const char *buf,
-				 size_t count)
-{
-	if (sscanf(buf, "%lx", &usbip_debug_flag) != 1)
-		return -EINVAL;
-	return count;
-}
-DEVICE_ATTR_RW(usbip_debug);
-
-static void usbip_dump_buffer(char *buff, int bufflen)
-{
-	print_hex_dump(KERN_DEBUG, "usbip-core", DUMP_PREFIX_OFFSET, 16, 4,
-		       buff, bufflen, false);
-}
-
-static void usbip_dump_pipe(unsigned int p)
-{
-	unsigned char type = usb_pipetype(p);
-	unsigned char ep   = usb_pipeendpoint(p);
-	unsigned char dev  = usb_pipedevice(p);
-	unsigned char dir  = usb_pipein(p);
-
-	pr_debug("dev(%d) ep(%d) [%s] ", dev, ep, dir ? "IN" : "OUT");
-
-	switch (type) {
-	case PIPE_ISOCHRONOUS:
-		pr_debug("ISO\n");
-		break;
-	case PIPE_INTERRUPT:
-		pr_debug("INT\n");
-		break;
-	case PIPE_CONTROL:
-		pr_debug("CTRL\n");
-		break;
-	case PIPE_BULK:
-		pr_debug("BULK\n");
-		break;
-	default:
-		pr_debug("ERR\n");
-		break;
-	}
-}
-
-static void usbip_dump_usb_device(struct usb_device *udev)
-{
-	struct device *dev = &udev->dev;
-	int i;
-
-	dev_dbg(dev, "       devnum(%d) devpath(%s) usb speed(%s)",
-		udev->devnum, udev->devpath, usb_speed_string(udev->speed));
-
-	pr_debug("tt %p, ttport %d\n", udev->tt, udev->ttport);
-
-	dev_dbg(dev, "                    ");
-	for (i = 0; i < 16; i++)
-		pr_debug(" %2u", i);
-	pr_debug("\n");
-
-	dev_dbg(dev, "       toggle0(IN) :");
-	for (i = 0; i < 16; i++)
-		pr_debug(" %2u", (udev->toggle[0] & (1 << i)) ? 1 : 0);
-	pr_debug("\n");
-
-	dev_dbg(dev, "       toggle1(OUT):");
-	for (i = 0; i < 16; i++)
-		pr_debug(" %2u", (udev->toggle[1] & (1 << i)) ? 1 : 0);
-	pr_debug("\n");
-
-	dev_dbg(dev, "       epmaxp_in   :");
-	for (i = 0; i < 16; i++) {
-		if (udev->ep_in[i])
-			pr_debug(" %2u",
-			    le16_to_cpu(udev->ep_in[i]->desc.wMaxPacketSize));
-	}
-	pr_debug("\n");
-
-	dev_dbg(dev, "       epmaxp_out  :");
-	for (i = 0; i < 16; i++) {
-		if (udev->ep_out[i])
-			pr_debug(" %2u",
-			    le16_to_cpu(udev->ep_out[i]->desc.wMaxPacketSize));
-	}
-	pr_debug("\n");
-
-	dev_dbg(dev, "parent %p, bus %p\n", udev->parent, udev->bus);
-
-	dev_dbg(dev,
-		"descriptor %p, config %p, actconfig %p, rawdescriptors %p\n",
-		&udev->descriptor, udev->config,
-		udev->actconfig, udev->rawdescriptors);
-
-	dev_dbg(dev, "have_langid %d, string_langid %d\n",
-		udev->have_langid, udev->string_langid);
-
-	dev_dbg(dev, "maxchild %d\n", udev->maxchild);
-}
-
-static void usbip_dump_request_type(__u8 rt)
-{
-	switch (rt & USB_RECIP_MASK) {
-	case USB_RECIP_DEVICE:
-		pr_debug("DEVICE");
-		break;
-	case USB_RECIP_INTERFACE:
-		pr_debug("INTERF");
-		break;
-	case USB_RECIP_ENDPOINT:
-		pr_debug("ENDPOI");
-		break;
-	case USB_RECIP_OTHER:
-		pr_debug("OTHER ");
-		break;
-	default:
-		pr_debug("------");
-		break;
-	}
-}
-
-static void usbip_dump_usb_ctrlrequest(struct usb_ctrlrequest *cmd)
-{
-	if (!cmd) {
-		pr_debug("       : null pointer\n");
-		return;
-	}
-
-	pr_debug("       ");
-	pr_debug("bRequestType(%02X) bRequest(%02X) wValue(%04X) wIndex(%04X) wLength(%04X) ",
-		 cmd->bRequestType, cmd->bRequest,
-		 cmd->wValue, cmd->wIndex, cmd->wLength);
-	pr_debug("\n       ");
-
-	if ((cmd->bRequestType & USB_TYPE_MASK) == USB_TYPE_STANDARD) {
-		pr_debug("STANDARD ");
-		switch (cmd->bRequest) {
-		case USB_REQ_GET_STATUS:
-			pr_debug("GET_STATUS\n");
-			break;
-		case USB_REQ_CLEAR_FEATURE:
-			pr_debug("CLEAR_FEAT\n");
-			break;
-		case USB_REQ_SET_FEATURE:
-			pr_debug("SET_FEAT\n");
-			break;
-		case USB_REQ_SET_ADDRESS:
-			pr_debug("SET_ADDRRS\n");
-			break;
-		case USB_REQ_GET_DESCRIPTOR:
-			pr_debug("GET_DESCRI\n");
-			break;
-		case USB_REQ_SET_DESCRIPTOR:
-			pr_debug("SET_DESCRI\n");
-			break;
-		case USB_REQ_GET_CONFIGURATION:
-			pr_debug("GET_CONFIG\n");
-			break;
-		case USB_REQ_SET_CONFIGURATION:
-			pr_debug("SET_CONFIG\n");
-			break;
-		case USB_REQ_GET_INTERFACE:
-			pr_debug("GET_INTERF\n");
-			break;
-		case USB_REQ_SET_INTERFACE:
-			pr_debug("SET_INTERF\n");
-			break;
-		case USB_REQ_SYNCH_FRAME:
-			pr_debug("SYNC_FRAME\n");
-			break;
-		default:
-			pr_debug("REQ(%02X)\n", cmd->bRequest);
-			break;
-		}
-		usbip_dump_request_type(cmd->bRequestType);
-	} else if ((cmd->bRequestType & USB_TYPE_MASK) == USB_TYPE_CLASS) {
-		pr_debug("CLASS\n");
-	} else if ((cmd->bRequestType & USB_TYPE_MASK) == USB_TYPE_VENDOR) {
-		pr_debug("VENDOR\n");
-	} else if ((cmd->bRequestType & USB_TYPE_MASK) == USB_TYPE_RESERVED) {
-		pr_debug("RESERVED\n");
-	}
-}
-
-void usbip_dump_urb(struct urb *urb)
-{
-	struct device *dev;
-
-	if (!urb) {
-		pr_debug("urb: null pointer!!\n");
-		return;
-	}
-
-	if (!urb->dev) {
-		pr_debug("urb->dev: null pointer!!\n");
-		return;
-	}
-
-	dev = &urb->dev->dev;
-
-	dev_dbg(dev, "   urb                   :%p\n", urb);
-	dev_dbg(dev, "   dev                   :%p\n", urb->dev);
-
-	usbip_dump_usb_device(urb->dev);
-
-	dev_dbg(dev, "   pipe                  :%08x ", urb->pipe);
-
-	usbip_dump_pipe(urb->pipe);
-
-	dev_dbg(dev, "   status                :%d\n", urb->status);
-	dev_dbg(dev, "   transfer_flags        :%08X\n", urb->transfer_flags);
-	dev_dbg(dev, "   transfer_buffer       :%p\n", urb->transfer_buffer);
-	dev_dbg(dev, "   transfer_buffer_length:%d\n",
-						urb->transfer_buffer_length);
-	dev_dbg(dev, "   actual_length         :%d\n", urb->actual_length);
-	dev_dbg(dev, "   setup_packet          :%p\n", urb->setup_packet);
-
-	if (urb->setup_packet && usb_pipetype(urb->pipe) == PIPE_CONTROL)
-		usbip_dump_usb_ctrlrequest(
-			(struct usb_ctrlrequest *)urb->setup_packet);
-
-	dev_dbg(dev, "   start_frame           :%d\n", urb->start_frame);
-	dev_dbg(dev, "   number_of_packets     :%d\n", urb->number_of_packets);
-	dev_dbg(dev, "   interval              :%d\n", urb->interval);
-	dev_dbg(dev, "   error_count           :%d\n", urb->error_count);
-	dev_dbg(dev, "   context               :%p\n", urb->context);
-	dev_dbg(dev, "   complete              :%p\n", urb->complete);
-}
-EXPORT_SYMBOL_GPL(usbip_dump_urb);
-
-void usbip_dump_header(struct usbip_header *pdu)
-{
-	pr_debug("BASE: cmd %u seq %u devid %u dir %u ep %u\n",
-		 pdu->base.command,
-		 pdu->base.seqnum,
-		 pdu->base.devid,
-		 pdu->base.direction,
-		 pdu->base.ep);
-
-	switch (pdu->base.command) {
-	case USBIP_CMD_SUBMIT:
-		pr_debug("USBIP_CMD_SUBMIT: x_flags %u x_len %u sf %u #p %d iv %d\n",
-			 pdu->u.cmd_submit.transfer_flags,
-			 pdu->u.cmd_submit.transfer_buffer_length,
-			 pdu->u.cmd_submit.start_frame,
-			 pdu->u.cmd_submit.number_of_packets,
-			 pdu->u.cmd_submit.interval);
-		break;
-	case USBIP_CMD_UNLINK:
-		pr_debug("USBIP_CMD_UNLINK: seq %u\n",
-			 pdu->u.cmd_unlink.seqnum);
-		break;
-	case USBIP_RET_SUBMIT:
-		pr_debug("USBIP_RET_SUBMIT: st %d al %u sf %d #p %d ec %d\n",
-			 pdu->u.ret_submit.status,
-			 pdu->u.ret_submit.actual_length,
-			 pdu->u.ret_submit.start_frame,
-			 pdu->u.ret_submit.number_of_packets,
-			 pdu->u.ret_submit.error_count);
-		break;
-	case USBIP_RET_UNLINK:
-		pr_debug("USBIP_RET_UNLINK: status %d\n",
-			 pdu->u.ret_unlink.status);
-		break;
-	default:
-		/* NOT REACHED */
-		pr_err("unknown command\n");
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(usbip_dump_header);
-
-/* Receive data over TCP/IP. */
-int usbip_recv(struct socket *sock, void *buf, int size)
-{
-	int result;
-	struct msghdr msg;
-	struct kvec iov;
-	int total = 0;
-
-	/* for blocks of if (usbip_dbg_flag_xmit) */
-	char *bp = buf;
-	int osize = size;
-
-	usbip_dbg_xmit("enter\n");
-
-	if (!sock || !buf || !size) {
-		pr_err("invalid arg, sock %p buff %p size %d\n", sock, buf,
-		       size);
-		return -EINVAL;
-	}
-
-	do {
-		sock->sk->sk_allocation = GFP_NOIO;
-		iov.iov_base    = buf;
-		iov.iov_len     = size;
-		msg.msg_name    = NULL;
-		msg.msg_namelen = 0;
-		msg.msg_control = NULL;
-		msg.msg_controllen = 0;
-		msg.msg_flags      = MSG_NOSIGNAL;
-
-		result = kernel_recvmsg(sock, &msg, &iov, 1, size, MSG_WAITALL);
-		if (result <= 0) {
-			pr_debug("receive sock %p buf %p size %u ret %d total %d\n",
-				 sock, buf, size, result, total);
-			goto err;
-		}
-
-		size -= result;
-		buf += result;
-		total += result;
-	} while (size > 0);
-
-	if (usbip_dbg_flag_xmit) {
-		if (!in_interrupt())
-			pr_debug("%-10s:", current->comm);
-		else
-			pr_debug("interrupt  :");
-
-		pr_debug("receiving....\n");
-		usbip_dump_buffer(bp, osize);
-		pr_debug("received, osize %d ret %d size %d total %d\n",
-			 osize, result, size, total);
-	}
-
-	return total;
-
-err:
-	return result;
-}
-EXPORT_SYMBOL_GPL(usbip_recv);
-
-/* there may be more cases to tweak the flags. */
-static unsigned int tweak_transfer_flags(unsigned int flags)
-{
-	flags &= ~URB_NO_TRANSFER_DMA_MAP;
-	return flags;
-}
-
-static void usbip_pack_cmd_submit(struct usbip_header *pdu, struct urb *urb,
-				  int pack)
-{
-	struct usbip_header_cmd_submit *spdu = &pdu->u.cmd_submit;
-
-	/*
-	 * Some members are not still implemented in usbip. I hope this issue
-	 * will be discussed when usbip is ported to other operating systems.
-	 */
-	if (pack) {
-		spdu->transfer_flags =
-			tweak_transfer_flags(urb->transfer_flags);
-		spdu->transfer_buffer_length	= urb->transfer_buffer_length;
-		spdu->start_frame		= urb->start_frame;
-		spdu->number_of_packets		= urb->number_of_packets;
-		spdu->interval			= urb->interval;
-	} else  {
-		urb->transfer_flags         = spdu->transfer_flags;
-		urb->transfer_buffer_length = spdu->transfer_buffer_length;
-		urb->start_frame            = spdu->start_frame;
-		urb->number_of_packets      = spdu->number_of_packets;
-		urb->interval               = spdu->interval;
-	}
-}
-
-static void usbip_pack_ret_submit(struct usbip_header *pdu, struct urb *urb,
-				  int pack)
-{
-	struct usbip_header_ret_submit *rpdu = &pdu->u.ret_submit;
-
-	if (pack) {
-		rpdu->status		= urb->status;
-		rpdu->actual_length	= urb->actual_length;
-		rpdu->start_frame	= urb->start_frame;
-		rpdu->number_of_packets = urb->number_of_packets;
-		rpdu->error_count	= urb->error_count;
-	} else {
-		urb->status		= rpdu->status;
-		urb->actual_length	= rpdu->actual_length;
-		urb->start_frame	= rpdu->start_frame;
-		urb->number_of_packets = rpdu->number_of_packets;
-		urb->error_count	= rpdu->error_count;
-	}
-}
-
-void usbip_pack_pdu(struct usbip_header *pdu, struct urb *urb, int cmd,
-		    int pack)
-{
-	switch (cmd) {
-	case USBIP_CMD_SUBMIT:
-		usbip_pack_cmd_submit(pdu, urb, pack);
-		break;
-	case USBIP_RET_SUBMIT:
-		usbip_pack_ret_submit(pdu, urb, pack);
-		break;
-	default:
-		/* NOT REACHED */
-		pr_err("unknown command\n");
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(usbip_pack_pdu);
-
-static void correct_endian_basic(struct usbip_header_basic *base, int send)
-{
-	if (send) {
-		base->command	= cpu_to_be32(base->command);
-		base->seqnum	= cpu_to_be32(base->seqnum);
-		base->devid	= cpu_to_be32(base->devid);
-		base->direction	= cpu_to_be32(base->direction);
-		base->ep	= cpu_to_be32(base->ep);
-	} else {
-		base->command	= be32_to_cpu(base->command);
-		base->seqnum	= be32_to_cpu(base->seqnum);
-		base->devid	= be32_to_cpu(base->devid);
-		base->direction	= be32_to_cpu(base->direction);
-		base->ep	= be32_to_cpu(base->ep);
-	}
-}
-
-static void correct_endian_cmd_submit(struct usbip_header_cmd_submit *pdu,
-				      int send)
-{
-	if (send) {
-		pdu->transfer_flags = cpu_to_be32(pdu->transfer_flags);
-
-		cpu_to_be32s(&pdu->transfer_buffer_length);
-		cpu_to_be32s(&pdu->start_frame);
-		cpu_to_be32s(&pdu->number_of_packets);
-		cpu_to_be32s(&pdu->interval);
-	} else {
-		pdu->transfer_flags = be32_to_cpu(pdu->transfer_flags);
-
-		be32_to_cpus(&pdu->transfer_buffer_length);
-		be32_to_cpus(&pdu->start_frame);
-		be32_to_cpus(&pdu->number_of_packets);
-		be32_to_cpus(&pdu->interval);
-	}
-}
-
-static void correct_endian_ret_submit(struct usbip_header_ret_submit *pdu,
-				      int send)
-{
-	if (send) {
-		cpu_to_be32s(&pdu->status);
-		cpu_to_be32s(&pdu->actual_length);
-		cpu_to_be32s(&pdu->start_frame);
-		cpu_to_be32s(&pdu->number_of_packets);
-		cpu_to_be32s(&pdu->error_count);
-	} else {
-		be32_to_cpus(&pdu->status);
-		be32_to_cpus(&pdu->actual_length);
-		be32_to_cpus(&pdu->start_frame);
-		be32_to_cpus(&pdu->number_of_packets);
-		be32_to_cpus(&pdu->error_count);
-	}
-}
-
-static void correct_endian_cmd_unlink(struct usbip_header_cmd_unlink *pdu,
-				      int send)
-{
-	if (send)
-		pdu->seqnum = cpu_to_be32(pdu->seqnum);
-	else
-		pdu->seqnum = be32_to_cpu(pdu->seqnum);
-}
-
-static void correct_endian_ret_unlink(struct usbip_header_ret_unlink *pdu,
-				      int send)
-{
-	if (send)
-		cpu_to_be32s(&pdu->status);
-	else
-		be32_to_cpus(&pdu->status);
-}
-
-void usbip_header_correct_endian(struct usbip_header *pdu, int send)
-{
-	__u32 cmd = 0;
-
-	if (send)
-		cmd = pdu->base.command;
-
-	correct_endian_basic(&pdu->base, send);
-
-	if (!send)
-		cmd = pdu->base.command;
-
-	switch (cmd) {
-	case USBIP_CMD_SUBMIT:
-		correct_endian_cmd_submit(&pdu->u.cmd_submit, send);
-		break;
-	case USBIP_RET_SUBMIT:
-		correct_endian_ret_submit(&pdu->u.ret_submit, send);
-		break;
-	case USBIP_CMD_UNLINK:
-		correct_endian_cmd_unlink(&pdu->u.cmd_unlink, send);
-		break;
-	case USBIP_RET_UNLINK:
-		correct_endian_ret_unlink(&pdu->u.ret_unlink, send);
-		break;
-	default:
-		/* NOT REACHED */
-		pr_err("unknown command\n");
-		break;
-	}
-}
-EXPORT_SYMBOL_GPL(usbip_header_correct_endian);
-
-static void usbip_iso_packet_correct_endian(
-		struct usbip_iso_packet_descriptor *iso, int send)
-{
-	/* does not need all members. but copy all simply. */
-	if (send) {
-		iso->offset	= cpu_to_be32(iso->offset);
-		iso->length	= cpu_to_be32(iso->length);
-		iso->status	= cpu_to_be32(iso->status);
-		iso->actual_length = cpu_to_be32(iso->actual_length);
-	} else {
-		iso->offset	= be32_to_cpu(iso->offset);
-		iso->length	= be32_to_cpu(iso->length);
-		iso->status	= be32_to_cpu(iso->status);
-		iso->actual_length = be32_to_cpu(iso->actual_length);
-	}
-}
-
-static void usbip_pack_iso(struct usbip_iso_packet_descriptor *iso,
-			   struct usb_iso_packet_descriptor *uiso, int pack)
-{
-	if (pack) {
-		iso->offset		= uiso->offset;
-		iso->length		= uiso->length;
-		iso->status		= uiso->status;
-		iso->actual_length	= uiso->actual_length;
-	} else {
-		uiso->offset		= iso->offset;
-		uiso->length		= iso->length;
-		uiso->status		= iso->status;
-		uiso->actual_length	= iso->actual_length;
-	}
-}
-
-/* must free buffer */
-struct usbip_iso_packet_descriptor*
-usbip_alloc_iso_desc_pdu(struct urb *urb, ssize_t *bufflen)
-{
-	struct usbip_iso_packet_descriptor *iso;
-	int np = urb->number_of_packets;
-	ssize_t size = np * sizeof(*iso);
-	int i;
-
-	iso = kzalloc(size, GFP_KERNEL);
-	if (!iso)
-		return NULL;
-
-	for (i = 0; i < np; i++) {
-		usbip_pack_iso(&iso[i], &urb->iso_frame_desc[i], 1);
-		usbip_iso_packet_correct_endian(&iso[i], 1);
-	}
-
-	*bufflen = size;
-
-	return iso;
-}
-EXPORT_SYMBOL_GPL(usbip_alloc_iso_desc_pdu);
-
-/* some members of urb must be substituted before. */
-int usbip_recv_iso(struct usbip_device *ud, struct urb *urb)
-{
-	void *buff;
-	struct usbip_iso_packet_descriptor *iso;
-	int np = urb->number_of_packets;
-	int size = np * sizeof(*iso);
-	int i;
-	int ret;
-	int total_length = 0;
-
-	if (!usb_pipeisoc(urb->pipe))
-		return 0;
-
-	/* my Bluetooth dongle gets ISO URBs which are np = 0 */
-	if (np == 0)
-		return 0;
-
-	buff = kzalloc(size, GFP_KERNEL);
-	if (!buff)
-		return -ENOMEM;
-
-	ret = usbip_recv(ud->tcp_socket, buff, size);
-	if (ret != size) {
-		dev_err(&urb->dev->dev, "recv iso_frame_descriptor, %d\n",
-			ret);
-		kfree(buff);
-
-		if (ud->side == USBIP_STUB)
-			usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
-		else
-			usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
-
-		return -EPIPE;
-	}
-
-	iso = (struct usbip_iso_packet_descriptor *) buff;
-	for (i = 0; i < np; i++) {
-		usbip_iso_packet_correct_endian(&iso[i], 0);
-		usbip_pack_iso(&iso[i], &urb->iso_frame_desc[i], 0);
-		total_length += urb->iso_frame_desc[i].actual_length;
-	}
-
-	kfree(buff);
-
-	if (total_length != urb->actual_length) {
-		dev_err(&urb->dev->dev,
-			"total length of iso packets %d not equal to actual length of buffer %d\n",
-			total_length, urb->actual_length);
-
-		if (ud->side == USBIP_STUB)
-			usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
-		else
-			usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
-
-		return -EPIPE;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(usbip_recv_iso);
-
-/*
- * This functions restores the padding which was removed for optimizing
- * the bandwidth during transfer over tcp/ip
- *
- * buffer and iso packets need to be stored and be in propeper endian in urb
- * before calling this function
- */
-void usbip_pad_iso(struct usbip_device *ud, struct urb *urb)
-{
-	int np = urb->number_of_packets;
-	int i;
-	int actualoffset = urb->actual_length;
-
-	if (!usb_pipeisoc(urb->pipe))
-		return;
-
-	/* if no packets or length of data is 0, then nothing to unpack */
-	if (np == 0 || urb->actual_length == 0)
-		return;
-
-	/*
-	 * if actual_length is transfer_buffer_length then no padding is
-	 * present.
-	 */
-	if (urb->actual_length == urb->transfer_buffer_length)
-		return;
-
-	/*
-	 * loop over all packets from last to first (to prevent overwritting
-	 * memory when padding) and move them into the proper place
-	 */
-	for (i = np-1; i > 0; i--) {
-		actualoffset -= urb->iso_frame_desc[i].actual_length;
-		memmove(urb->transfer_buffer + urb->iso_frame_desc[i].offset,
-			urb->transfer_buffer + actualoffset,
-			urb->iso_frame_desc[i].actual_length);
-	}
-}
-EXPORT_SYMBOL_GPL(usbip_pad_iso);
-
-/* some members of urb must be substituted before. */
-int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb)
-{
-	int ret;
-	int size;
-
-	if (ud->side == USBIP_STUB) {
-		/* the direction of urb must be OUT. */
-		if (usb_pipein(urb->pipe))
-			return 0;
-
-		size = urb->transfer_buffer_length;
-	} else {
-		/* the direction of urb must be IN. */
-		if (usb_pipeout(urb->pipe))
-			return 0;
-
-		size = urb->actual_length;
-	}
-
-	/* no need to recv xbuff */
-	if (!(size > 0))
-		return 0;
-
-	ret = usbip_recv(ud->tcp_socket, urb->transfer_buffer, size);
-	if (ret != size) {
-		dev_err(&urb->dev->dev, "recv xbuf, %d\n", ret);
-		if (ud->side == USBIP_STUB) {
-			usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
-		} else {
-			usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
-			return -EPIPE;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(usbip_recv_xbuff);
-
-static int __init usbip_core_init(void)
-{
-	pr_info(DRIVER_DESC " v" USBIP_VERSION "\n");
-	return 0;
-}
-
-static void __exit usbip_core_exit(void)
-{
-	return;
-}
-
-module_init(usbip_core_init);
-module_exit(usbip_core_exit);
-
-MODULE_AUTHOR(DRIVER_AUTHOR);
-MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE("GPL");
-MODULE_VERSION(USBIP_VERSION);
diff --git a/drivers/staging/usbip/usbip_common.h b/drivers/staging/usbip/usbip_common.h
deleted file mode 100644
index 4da3866a037d..000000000000
--- a/drivers/staging/usbip/usbip_common.h
+++ /dev/null
@@ -1,335 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#ifndef __USBIP_COMMON_H
-#define __USBIP_COMMON_H
-
-#include <linux/compiler.h>
-#include <linux/device.h>
-#include <linux/interrupt.h>
-#include <linux/net.h>
-#include <linux/printk.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-#include <linux/usb.h>
-#include <linux/wait.h>
-#include "uapi/usbip.h"
-
-#define USBIP_VERSION "1.0.0"
-
-#undef pr_fmt
-
-#ifdef DEBUG
-#define pr_fmt(fmt)     KBUILD_MODNAME ": %s:%d: " fmt, __func__, __LINE__
-#else
-#define pr_fmt(fmt)     KBUILD_MODNAME ": " fmt
-#endif
-
-enum {
-	usbip_debug_xmit	= (1 << 0),
-	usbip_debug_sysfs	= (1 << 1),
-	usbip_debug_urb		= (1 << 2),
-	usbip_debug_eh		= (1 << 3),
-
-	usbip_debug_stub_cmp	= (1 << 8),
-	usbip_debug_stub_dev	= (1 << 9),
-	usbip_debug_stub_rx	= (1 << 10),
-	usbip_debug_stub_tx	= (1 << 11),
-
-	usbip_debug_vhci_rh	= (1 << 8),
-	usbip_debug_vhci_hc	= (1 << 9),
-	usbip_debug_vhci_rx	= (1 << 10),
-	usbip_debug_vhci_tx	= (1 << 11),
-	usbip_debug_vhci_sysfs  = (1 << 12)
-};
-
-#define usbip_dbg_flag_xmit	(usbip_debug_flag & usbip_debug_xmit)
-#define usbip_dbg_flag_vhci_rh	(usbip_debug_flag & usbip_debug_vhci_rh)
-#define usbip_dbg_flag_vhci_hc	(usbip_debug_flag & usbip_debug_vhci_hc)
-#define usbip_dbg_flag_vhci_rx	(usbip_debug_flag & usbip_debug_vhci_rx)
-#define usbip_dbg_flag_vhci_tx	(usbip_debug_flag & usbip_debug_vhci_tx)
-#define usbip_dbg_flag_stub_rx	(usbip_debug_flag & usbip_debug_stub_rx)
-#define usbip_dbg_flag_stub_tx	(usbip_debug_flag & usbip_debug_stub_tx)
-#define usbip_dbg_flag_vhci_sysfs  (usbip_debug_flag & usbip_debug_vhci_sysfs)
-
-extern unsigned long usbip_debug_flag;
-extern struct device_attribute dev_attr_usbip_debug;
-
-#define usbip_dbg_with_flag(flag, fmt, args...)		\
-	do {						\
-		if (flag & usbip_debug_flag)		\
-			pr_debug(fmt, ##args);		\
-	} while (0)
-
-#define usbip_dbg_sysfs(fmt, args...) \
-	usbip_dbg_with_flag(usbip_debug_sysfs, fmt , ##args)
-#define usbip_dbg_xmit(fmt, args...) \
-	usbip_dbg_with_flag(usbip_debug_xmit, fmt , ##args)
-#define usbip_dbg_urb(fmt, args...) \
-	usbip_dbg_with_flag(usbip_debug_urb, fmt , ##args)
-#define usbip_dbg_eh(fmt, args...) \
-	usbip_dbg_with_flag(usbip_debug_eh, fmt , ##args)
-
-#define usbip_dbg_vhci_rh(fmt, args...)	\
-	usbip_dbg_with_flag(usbip_debug_vhci_rh, fmt , ##args)
-#define usbip_dbg_vhci_hc(fmt, args...)	\
-	usbip_dbg_with_flag(usbip_debug_vhci_hc, fmt , ##args)
-#define usbip_dbg_vhci_rx(fmt, args...)	\
-	usbip_dbg_with_flag(usbip_debug_vhci_rx, fmt , ##args)
-#define usbip_dbg_vhci_tx(fmt, args...)	\
-	usbip_dbg_with_flag(usbip_debug_vhci_tx, fmt , ##args)
-#define usbip_dbg_vhci_sysfs(fmt, args...) \
-	usbip_dbg_with_flag(usbip_debug_vhci_sysfs, fmt , ##args)
-
-#define usbip_dbg_stub_cmp(fmt, args...) \
-	usbip_dbg_with_flag(usbip_debug_stub_cmp, fmt , ##args)
-#define usbip_dbg_stub_rx(fmt, args...) \
-	usbip_dbg_with_flag(usbip_debug_stub_rx, fmt , ##args)
-#define usbip_dbg_stub_tx(fmt, args...) \
-	usbip_dbg_with_flag(usbip_debug_stub_tx, fmt , ##args)
-
-/*
- * USB/IP request headers
- *
- * Each request is transferred across the network to its counterpart, which
- * facilitates the normal USB communication. The values contained in the headers
- * are basically the same as in a URB. Currently, four request types are
- * defined:
- *
- *  - USBIP_CMD_SUBMIT: a USB request block, corresponds to usb_submit_urb()
- *    (client to server)
- *
- *  - USBIP_RET_SUBMIT: the result of USBIP_CMD_SUBMIT
- *    (server to client)
- *
- *  - USBIP_CMD_UNLINK: an unlink request of a pending USBIP_CMD_SUBMIT,
- *    corresponds to usb_unlink_urb()
- *    (client to server)
- *
- *  - USBIP_RET_UNLINK: the result of USBIP_CMD_UNLINK
- *    (server to client)
- *
- */
-#define USBIP_CMD_SUBMIT	0x0001
-#define USBIP_CMD_UNLINK	0x0002
-#define USBIP_RET_SUBMIT	0x0003
-#define USBIP_RET_UNLINK	0x0004
-
-#define USBIP_DIR_OUT	0x00
-#define USBIP_DIR_IN	0x01
-
-/**
- * struct usbip_header_basic - data pertinent to every request
- * @command: the usbip request type
- * @seqnum: sequential number that identifies requests; incremented per
- *	    connection
- * @devid: specifies a remote USB device uniquely instead of busnum and devnum;
- *	   in the stub driver, this value is ((busnum << 16) | devnum)
- * @direction: direction of the transfer
- * @ep: endpoint number
- */
-struct usbip_header_basic {
-	__u32 command;
-	__u32 seqnum;
-	__u32 devid;
-	__u32 direction;
-	__u32 ep;
-} __packed;
-
-/**
- * struct usbip_header_cmd_submit - USBIP_CMD_SUBMIT packet header
- * @transfer_flags: URB flags
- * @transfer_buffer_length: the data size for (in) or (out) transfer
- * @start_frame: initial frame for isochronous or interrupt transfers
- * @number_of_packets: number of isochronous packets
- * @interval: maximum time for the request on the server-side host controller
- * @setup: setup data for a control request
- */
-struct usbip_header_cmd_submit {
-	__u32 transfer_flags;
-	__s32 transfer_buffer_length;
-
-	/* it is difficult for usbip to sync frames (reserved only?) */
-	__s32 start_frame;
-	__s32 number_of_packets;
-	__s32 interval;
-
-	unsigned char setup[8];
-} __packed;
-
-/**
- * struct usbip_header_ret_submit - USBIP_RET_SUBMIT packet header
- * @status: return status of a non-iso request
- * @actual_length: number of bytes transferred
- * @start_frame: initial frame for isochronous or interrupt transfers
- * @number_of_packets: number of isochronous packets
- * @error_count: number of errors for isochronous transfers
- */
-struct usbip_header_ret_submit {
-	__s32 status;
-	__s32 actual_length;
-	__s32 start_frame;
-	__s32 number_of_packets;
-	__s32 error_count;
-} __packed;
-
-/**
- * struct usbip_header_cmd_unlink - USBIP_CMD_UNLINK packet header
- * @seqnum: the URB seqnum to unlink
- */
-struct usbip_header_cmd_unlink {
-	__u32 seqnum;
-} __packed;
-
-/**
- * struct usbip_header_ret_unlink - USBIP_RET_UNLINK packet header
- * @status: return status of the request
- */
-struct usbip_header_ret_unlink {
-	__s32 status;
-} __packed;
-
-/**
- * struct usbip_header - common header for all usbip packets
- * @base: the basic header
- * @u: packet type dependent header
- */
-struct usbip_header {
-	struct usbip_header_basic base;
-
-	union {
-		struct usbip_header_cmd_submit	cmd_submit;
-		struct usbip_header_ret_submit	ret_submit;
-		struct usbip_header_cmd_unlink	cmd_unlink;
-		struct usbip_header_ret_unlink	ret_unlink;
-	} u;
-} __packed;
-
-/*
- * This is the same as usb_iso_packet_descriptor but packed for pdu.
- */
-struct usbip_iso_packet_descriptor {
-	__u32 offset;
-	__u32 length;			/* expected length */
-	__u32 actual_length;
-	__u32 status;
-} __packed;
-
-enum usbip_side {
-	USBIP_VHCI,
-	USBIP_STUB,
-};
-
-/* event handler */
-#define USBIP_EH_SHUTDOWN	(1 << 0)
-#define USBIP_EH_BYE		(1 << 1)
-#define USBIP_EH_RESET		(1 << 2)
-#define USBIP_EH_UNUSABLE	(1 << 3)
-
-#define SDEV_EVENT_REMOVED   (USBIP_EH_SHUTDOWN | USBIP_EH_RESET | USBIP_EH_BYE)
-#define	SDEV_EVENT_DOWN		(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
-#define	SDEV_EVENT_ERROR_TCP	(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
-#define	SDEV_EVENT_ERROR_SUBMIT	(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
-#define	SDEV_EVENT_ERROR_MALLOC	(USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
-
-#define	VDEV_EVENT_REMOVED	(USBIP_EH_SHUTDOWN | USBIP_EH_BYE)
-#define	VDEV_EVENT_DOWN		(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
-#define	VDEV_EVENT_ERROR_TCP	(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
-#define	VDEV_EVENT_ERROR_MALLOC	(USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
-
-/* a common structure for stub_device and vhci_device */
-struct usbip_device {
-	enum usbip_side side;
-	enum usbip_device_status status;
-
-	/* lock for status */
-	spinlock_t lock;
-
-	struct socket *tcp_socket;
-
-	struct task_struct *tcp_rx;
-	struct task_struct *tcp_tx;
-
-	unsigned long event;
-	struct task_struct *eh;
-	wait_queue_head_t eh_waitq;
-
-	struct eh_ops {
-		void (*shutdown)(struct usbip_device *);
-		void (*reset)(struct usbip_device *);
-		void (*unusable)(struct usbip_device *);
-	} eh_ops;
-};
-
-#define kthread_get_run(threadfn, data, namefmt, ...)			   \
-({									   \
-	struct task_struct *__k						   \
-		= kthread_create(threadfn, data, namefmt, ## __VA_ARGS__); \
-	if (!IS_ERR(__k)) {						   \
-		get_task_struct(__k);					   \
-		wake_up_process(__k);					   \
-	}								   \
-	__k;								   \
-})
-
-#define kthread_stop_put(k)		\
-	do {				\
-		kthread_stop(k);	\
-		put_task_struct(k);	\
-	} while (0)
-
-/* usbip_common.c */
-void usbip_dump_urb(struct urb *purb);
-void usbip_dump_header(struct usbip_header *pdu);
-
-int usbip_recv(struct socket *sock, void *buf, int size);
-
-void usbip_pack_pdu(struct usbip_header *pdu, struct urb *urb, int cmd,
-		    int pack);
-void usbip_header_correct_endian(struct usbip_header *pdu, int send);
-
-struct usbip_iso_packet_descriptor*
-usbip_alloc_iso_desc_pdu(struct urb *urb, ssize_t *bufflen);
-
-/* some members of urb must be substituted before. */
-int usbip_recv_iso(struct usbip_device *ud, struct urb *urb);
-void usbip_pad_iso(struct usbip_device *ud, struct urb *urb);
-int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb);
-
-/* usbip_event.c */
-int usbip_start_eh(struct usbip_device *ud);
-void usbip_stop_eh(struct usbip_device *ud);
-void usbip_event_add(struct usbip_device *ud, unsigned long event);
-int usbip_event_happened(struct usbip_device *ud);
-
-static inline int interface_to_busnum(struct usb_interface *interface)
-{
-	struct usb_device *udev = interface_to_usbdev(interface);
-
-	return udev->bus->busnum;
-}
-
-static inline int interface_to_devnum(struct usb_interface *interface)
-{
-	struct usb_device *udev = interface_to_usbdev(interface);
-
-	return udev->devnum;
-}
-
-#endif /* __USBIP_COMMON_H */
diff --git a/drivers/staging/usbip/usbip_event.c b/drivers/staging/usbip/usbip_event.c
deleted file mode 100644
index 64933b993d7a..000000000000
--- a/drivers/staging/usbip/usbip_event.c
+++ /dev/null
@@ -1,128 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <linux/kthread.h>
-#include <linux/export.h>
-
-#include "usbip_common.h"
-
-static int event_handler(struct usbip_device *ud)
-{
-	usbip_dbg_eh("enter\n");
-
-	/*
-	 * Events are handled by only this thread.
-	 */
-	while (usbip_event_happened(ud)) {
-		usbip_dbg_eh("pending event %lx\n", ud->event);
-
-		/*
-		 * NOTE: shutdown must come first.
-		 * Shutdown the device.
-		 */
-		if (ud->event & USBIP_EH_SHUTDOWN) {
-			ud->eh_ops.shutdown(ud);
-			ud->event &= ~USBIP_EH_SHUTDOWN;
-		}
-
-		/* Reset the device. */
-		if (ud->event & USBIP_EH_RESET) {
-			ud->eh_ops.reset(ud);
-			ud->event &= ~USBIP_EH_RESET;
-		}
-
-		/* Mark the device as unusable. */
-		if (ud->event & USBIP_EH_UNUSABLE) {
-			ud->eh_ops.unusable(ud);
-			ud->event &= ~USBIP_EH_UNUSABLE;
-		}
-
-		/* Stop the error handler. */
-		if (ud->event & USBIP_EH_BYE)
-			return -1;
-	}
-
-	return 0;
-}
-
-static int event_handler_loop(void *data)
-{
-	struct usbip_device *ud = data;
-
-	while (!kthread_should_stop()) {
-		wait_event_interruptible(ud->eh_waitq,
-					 usbip_event_happened(ud) ||
-					 kthread_should_stop());
-		usbip_dbg_eh("wakeup\n");
-
-		if (event_handler(ud) < 0)
-			break;
-	}
-
-	return 0;
-}
-
-int usbip_start_eh(struct usbip_device *ud)
-{
-	init_waitqueue_head(&ud->eh_waitq);
-	ud->event = 0;
-
-	ud->eh = kthread_run(event_handler_loop, ud, "usbip_eh");
-	if (IS_ERR(ud->eh)) {
-		pr_warn("Unable to start control thread\n");
-		return PTR_ERR(ud->eh);
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(usbip_start_eh);
-
-void usbip_stop_eh(struct usbip_device *ud)
-{
-	if (ud->eh == current)
-		return; /* do not wait for myself */
-
-	kthread_stop(ud->eh);
-	usbip_dbg_eh("usbip_eh has finished\n");
-}
-EXPORT_SYMBOL_GPL(usbip_stop_eh);
-
-void usbip_event_add(struct usbip_device *ud, unsigned long event)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&ud->lock, flags);
-	ud->event |= event;
-	wake_up(&ud->eh_waitq);
-	spin_unlock_irqrestore(&ud->lock, flags);
-}
-EXPORT_SYMBOL_GPL(usbip_event_add);
-
-int usbip_event_happened(struct usbip_device *ud)
-{
-	int happened = 0;
-
-	spin_lock(&ud->lock);
-	if (ud->event != 0)
-		happened = 1;
-	spin_unlock(&ud->lock);
-
-	return happened;
-}
-EXPORT_SYMBOL_GPL(usbip_event_happened);
diff --git a/drivers/staging/usbip/usbip_protocol.txt b/drivers/staging/usbip/usbip_protocol.txt
deleted file mode 100644
index 16b6fe27284c..000000000000
--- a/drivers/staging/usbip/usbip_protocol.txt
+++ /dev/null
@@ -1,358 +0,0 @@
-PRELIMINARY DRAFT, MAY CONTAIN MISTAKES!
-28 Jun 2011
-
-The USB/IP protocol follows a server/client architecture. The server exports the
-USB devices and the clients imports them. The device driver for the exported
-USB device runs on the client machine.
-
-The client may ask for the list of the exported USB devices. To get the list the
-client opens a TCP/IP connection towards the server, and sends an OP_REQ_DEVLIST
-packet on top of the TCP/IP connection (so the actual OP_REQ_DEVLIST may be sent
-in one or more pieces at the low level transport layer). The server sends back
-the OP_REP_DEVLIST packet which lists the exported USB devices. Finally the
-TCP/IP connection is closed.
-
- virtual host controller                                 usb host
-      "client"                                           "server"
-  (imports USB devices)                             (exports USB devices)
-          |                                                 |
-          |                  OP_REQ_DEVLIST                 |
-          | ----------------------------------------------> |
-          |                                                 |
-          |                  OP_REP_DEVLIST                 |
-          | <---------------------------------------------- |
-          |                                                 |
-
-Once the client knows the list of exported USB devices it may decide to use one
-of them. First the client opens a TCP/IP connection towards the server and
-sends an OP_REQ_IMPORT packet. The server replies with OP_REP_IMPORT. If the
-import was successful the TCP/IP connection remains open and will be used
-to transfer the URB traffic between the client and the server. The client may
-send two types of packets: the USBIP_CMD_SUBMIT to submit an URB, and
-USBIP_CMD_UNLINK to unlink a previously submitted URB. The answers of the
-server may be USBIP_RET_SUBMIT and USBIP_RET_UNLINK respectively.
-
- virtual host controller                                 usb host
-      "client"                                           "server"
-  (imports USB devices)                             (exports USB devices)
-          |                                                 |
-          |                  OP_REQ_IMPORT                  |
-          | ----------------------------------------------> |
-          |                                                 |
-          |                  OP_REP_IMPORT                  |
-          | <---------------------------------------------- |
-          |                                                 |
-          |                                                 |
-          |            USBIP_CMD_SUBMIT(seqnum = n)         |
-          | ----------------------------------------------> |
-          |                                                 |
-          |            USBIP_RET_SUBMIT(seqnum = n)         |
-          | <---------------------------------------------- |
-          |                        .                        |
-          |                        :                        |
-          |                                                 |
-          |            USBIP_CMD_SUBMIT(seqnum = m)         |
-          | ----------------------------------------------> |
-          |                                                 |
-          |            USBIP_CMD_SUBMIT(seqnum = m+1)       |
-          | ----------------------------------------------> |
-          |                                                 |
-          |            USBIP_CMD_SUBMIT(seqnum = m+2)       |
-          | ----------------------------------------------> |
-          |                                                 |
-          |            USBIP_RET_SUBMIT(seqnum = m)         |
-          | <---------------------------------------------- |
-          |                                                 |
-          |            USBIP_CMD_SUBMIT(seqnum = m+3)       |
-          | ----------------------------------------------> |
-          |                                                 |
-          |            USBIP_RET_SUBMIT(seqnum = m+1)       |
-          | <---------------------------------------------- |
-          |                                                 |
-          |            USBIP_CMD_SUBMIT(seqnum = m+4)       |
-          | ----------------------------------------------> |
-          |                                                 |
-          |            USBIP_RET_SUBMIT(seqnum = m+2)       |
-          | <---------------------------------------------- |
-          |                        .                        |
-          |                        :                        |
-          |                                                 |
-          |               USBIP_CMD_UNLINK                  |
-          | ----------------------------------------------> |
-          |                                                 |
-          |               USBIP_RET_UNLINK                  |
-          | <---------------------------------------------- |
-          |                                                 |
-
-The fields are in network (big endian) byte order meaning that the most significant
-byte (MSB) is stored at the lowest address.
-
-
-OP_REQ_DEVLIST: Retrieve the list of exported USB devices.
-
- Offset    | Length | Value      | Description
------------+--------+------------+---------------------------------------------------
- 0         | 2      | 0x0100     | Binary-coded decimal USBIP version number: v1.0.0
------------+--------+------------+---------------------------------------------------
- 2         | 2      | 0x8005     | Command code: Retrieve the list of exported USB
-           |        |            |   devices.
------------+--------+------------+---------------------------------------------------
- 4         | 4      | 0x00000000 | Status: unused, shall be set to 0
-
-OP_REP_DEVLIST: Reply with the list of exported USB devices.
-
- Offset    | Length | Value      | Description
------------+--------+------------+---------------------------------------------------
- 0         | 2      | 0x0100     | Binary-coded decimal USBIP version number: v1.0.0.
------------+--------+------------+---------------------------------------------------
- 2         | 2      | 0x0005     | Reply code: The list of exported USB devices.
------------+--------+------------+---------------------------------------------------
- 4         | 4      | 0x00000000 | Status: 0 for OK
------------+--------+------------+---------------------------------------------------
- 8         | 4      | n          | Number of exported devices: 0 means no exported
-           |        |            |   devices.
------------+--------+------------+---------------------------------------------------
- 0x0C      |        |            | From now on the exported n devices are described,
-           |        |            |   if any. If no devices are exported the message
-           |        |            |   ends with the previous "number of exported
-           |        |            |   devices" field.
------------+--------+------------+---------------------------------------------------
-           | 256    |            | path: Path of the device on the host exporting the
-           |        |            |   USB device, string closed with zero byte, e.g.
-           |        |            |   "/sys/devices/pci0000:00/0000:00:1d.1/usb3/3-2"
-           |        |            |   The unused bytes shall be filled with zero
-           |        |            |   bytes.
------------+--------+------------+---------------------------------------------------
- 0x10C     | 32     |            | busid: Bus ID of the exported device, string
-           |        |            |   closed with zero byte, e.g. "3-2". The unused
-           |        |            |   bytes shall be filled with zero bytes.
------------+--------+------------+---------------------------------------------------
- 0x12C     | 4      |            | busnum
------------+--------+------------+---------------------------------------------------
- 0x130     | 4      |            | devnum
------------+--------+------------+---------------------------------------------------
- 0x134     | 4      |            | speed
------------+--------+------------+---------------------------------------------------
- 0x138     | 2      |            | idVendor
------------+--------+------------+---------------------------------------------------
- 0x13A     | 2      |            | idProduct
------------+--------+------------+---------------------------------------------------
- 0x13C     | 2      |            | bcdDevice
------------+--------+------------+---------------------------------------------------
- 0x13E     | 1      |            | bDeviceClass
------------+--------+------------+---------------------------------------------------
- 0x13F     | 1      |            | bDeviceSubClass
------------+--------+------------+---------------------------------------------------
- 0x140     | 1      |            | bDeviceProtocol
------------+--------+------------+---------------------------------------------------
- 0x141     | 1      |            | bConfigurationValue
------------+--------+------------+---------------------------------------------------
- 0x142     | 1      |            | bNumConfigurations
------------+--------+------------+---------------------------------------------------
- 0x143     | 1      |            | bNumInterfaces
------------+--------+------------+---------------------------------------------------
- 0x144     |        | m_0        | From now on each interface is described, all
-           |        |            |   together bNumInterfaces times, with the
-           |        |            |   the following 4 fields:
------------+--------+------------+---------------------------------------------------
-           | 1      |            | bInterfaceClass
------------+--------+------------+---------------------------------------------------
- 0x145     | 1      |            | bInterfaceSubClass
------------+--------+------------+---------------------------------------------------
- 0x146     | 1      |            | bInterfaceProtocol
------------+--------+------------+---------------------------------------------------
- 0x147     | 1      |            | padding byte for alignment, shall be set to zero
------------+--------+------------+---------------------------------------------------
- 0xC +     |        |            | The second exported USB device starts at i=1
- i*0x138 + |        |            | with the busid field.
- m_(i-1)*4 |        |            |
-
-OP_REQ_IMPORT: Request to import (attach) a remote USB device.
-
- Offset    | Length | Value      | Description
------------+--------+------------+---------------------------------------------------
- 0         | 2      | 0x0100     | Binary-coded decimal USBIP version number: v1.0.0
------------+--------+------------+---------------------------------------------------
- 2         | 2      | 0x8003     | Command code: import a remote USB device.
------------+--------+------------+---------------------------------------------------
- 4         | 4      | 0x00000000 | Status: unused, shall be set to 0
------------+--------+------------+---------------------------------------------------
- 8         | 32     |            | busid: the busid of the exported device on the
-           |        |            |   remote host. The possible values are taken
-           |        |            |   from the message field OP_REP_DEVLIST.busid.
-           |        |            |   A string closed with zero, the unused bytes
-           |        |            |   shall be filled with zeros.
------------+--------+------------+---------------------------------------------------
-
-OP_REP_IMPORT: Reply to import (attach) a remote USB device.
-
- Offset    | Length | Value      | Description
------------+--------+------------+---------------------------------------------------
- 0         | 2      | 0x0100     | Binary-coded decimal USBIP version number: v1.0.0
------------+--------+------------+---------------------------------------------------
- 2         | 2      | 0x0003     | Reply code: Reply to import.
------------+--------+------------+---------------------------------------------------
- 4         | 4      | 0x00000000 | Status: 0 for OK
-           |        |            |         1 for error
------------+--------+------------+---------------------------------------------------
- 8         |        |            | From now on comes the details of the imported
-           |        |            |   device, if the previous status field was OK (0),
-           |        |            |   otherwise the reply ends with the status field.
------------+--------+------------+---------------------------------------------------
-           | 256    |            | path: Path of the device on the host exporting the
-           |        |            |   USB device, string closed with zero byte, e.g.
-           |        |            |   "/sys/devices/pci0000:00/0000:00:1d.1/usb3/3-2"
-           |        |            |   The unused bytes shall be filled with zero
-           |        |            |   bytes.
------------+--------+------------+---------------------------------------------------
- 0x108     | 32     |            | busid: Bus ID of the exported device, string
-           |        |            |   closed with zero byte, e.g. "3-2". The unused
-           |        |            |   bytes shall be filled with zero bytes.
------------+--------+------------+---------------------------------------------------
- 0x128     | 4      |            | busnum
------------+--------+------------+---------------------------------------------------
- 0x12C     | 4      |            | devnum
------------+--------+------------+---------------------------------------------------
- 0x130     | 4      |            | speed
------------+--------+------------+---------------------------------------------------
- 0x134     | 2      |            | idVendor
------------+--------+------------+---------------------------------------------------
- 0x136     | 2      |            | idProduct
------------+--------+------------+---------------------------------------------------
- 0x138     | 2      |            | bcdDevice
------------+--------+------------+---------------------------------------------------
- 0x139     | 1      |            | bDeviceClass
------------+--------+------------+---------------------------------------------------
- 0x13A     | 1      |            | bDeviceSubClass
------------+--------+------------+---------------------------------------------------
- 0x13B     | 1      |            | bDeviceProtocol
------------+--------+------------+---------------------------------------------------
- 0x13C     | 1      |            | bConfigurationValue
------------+--------+------------+---------------------------------------------------
- 0x13D     | 1      |            | bNumConfigurations
------------+--------+------------+---------------------------------------------------
- 0x13E     | 1      |            | bNumInterfaces
-
-USBIP_CMD_SUBMIT: Submit an URB
-
- Offset    | Length | Value      | Description
------------+--------+------------+---------------------------------------------------
- 0         | 4      | 0x00000001 | command: Submit an URB
------------+--------+------------+---------------------------------------------------
- 4         | 4      |            | seqnum: the sequence number of the URB to submit
------------+--------+------------+---------------------------------------------------
- 8         | 4      |            | devid
------------+--------+------------+---------------------------------------------------
- 0xC       | 4      |            | direction: 0: USBIP_DIR_OUT
-           |        |            |            1: USBIP_DIR_IN
------------+--------+------------+---------------------------------------------------
- 0x10      | 4      |            | ep: endpoint number, possible values are: 0...15
------------+--------+------------+---------------------------------------------------
- 0x14      | 4      |            | transfer_flags: possible values depend on the
-           |        |            |   URB transfer type, see below
------------+--------+------------+---------------------------------------------------
- 0x18      | 4      |            | transfer_buffer_length
------------+--------+------------+---------------------------------------------------
- 0x1C      | 4      |            | start_frame: specify the selected frame to
-           |        |            |   transmit an ISO frame, ignored if URB_ISO_ASAP
-           |        |            |   is specified at transfer_flags
------------+--------+------------+---------------------------------------------------
- 0x20      | 4      |            | number_of_packets: number of ISO packets
------------+--------+------------+---------------------------------------------------
- 0x24      | 4      |            | interval: maximum time for the request on the
-           |        |            |   server-side host controller
------------+--------+------------+---------------------------------------------------
- 0x28      | 8      |            | setup: data bytes for USB setup, filled with
-           |        |            |   zeros if not used
------------+--------+------------+---------------------------------------------------
- 0x30      |        |            | URB data. For ISO transfers the padding between
-           |        |            |   each ISO packets is not transmitted.
-
-
-  Allowed transfer_flags  | value      | control | interrupt | bulk     | isochronous
- -------------------------+------------+---------+-----------+----------+-------------
-  URB_SHORT_NOT_OK        | 0x00000001 | only in | only in   | only in  | no
-  URB_ISO_ASAP            | 0x00000002 | no      | no        | no       | yes
-  URB_NO_TRANSFER_DMA_MAP | 0x00000004 | yes     | yes       | yes      | yes
-  URB_NO_FSBR             | 0x00000020 | yes     | no        | no       | no
-  URB_ZERO_PACKET         | 0x00000040 | no      | no        | only out | no
-  URB_NO_INTERRUPT        | 0x00000080 | yes     | yes       | yes      | yes
-  URB_FREE_BUFFER         | 0x00000100 | yes     | yes       | yes      | yes
-  URB_DIR_MASK            | 0x00000200 | yes     | yes       | yes      | yes
-
-
-USBIP_RET_SUBMIT: Reply for submitting an URB
-
- Offset    | Length | Value      | Description
------------+--------+------------+---------------------------------------------------
- 0         | 4      | 0x00000003 | command
------------+--------+------------+---------------------------------------------------
- 4         | 4      |            | seqnum: URB sequence number
------------+--------+------------+---------------------------------------------------
- 8         | 4      |            | devid
------------+--------+------------+---------------------------------------------------
- 0xC       | 4      |            | direction: 0: USBIP_DIR_OUT
-           |        |            |            1: USBIP_DIR_IN
------------+--------+------------+---------------------------------------------------
- 0x10      | 4      |            | ep: endpoint number
------------+--------+------------+---------------------------------------------------
- 0x14      | 4      |            | status: zero for successful URB transaction,
-           |        |            |   otherwise some kind of error happened.
------------+--------+------------+---------------------------------------------------
- 0x18      | 4      | n          | actual_length: number of URB data bytes
------------+--------+------------+---------------------------------------------------
- 0x1C      | 4      |            | start_frame: for an ISO frame the actually
-           |        |            |   selected frame for transmit.
------------+--------+------------+---------------------------------------------------
- 0x20      | 4      |            | number_of_packets
------------+--------+------------+---------------------------------------------------
- 0x24      | 4      |            | error_count
------------+--------+------------+---------------------------------------------------
- 0x28      | 8      |            | setup: data bytes for USB setup, filled with
-           |        |            |   zeros if not used
------------+--------+------------+---------------------------------------------------
- 0x30      | n      |            | URB data bytes. For ISO transfers the padding
-           |        |            |   between each ISO packets is not transmitted.
-
-USBIP_CMD_UNLINK: Unlink an URB
-
- Offset    | Length | Value      | Description
------------+--------+------------+---------------------------------------------------
- 0         | 4      | 0x00000002 | command: URB unlink command
------------+--------+------------+---------------------------------------------------
- 4         | 4      |            | seqnum: URB sequence number to unlink: FIXME: is this so?
------------+--------+------------+---------------------------------------------------
- 8         | 4      |            | devid
------------+--------+------------+---------------------------------------------------
- 0xC       | 4      |            | direction: 0: USBIP_DIR_OUT
-           |        |            |            1: USBIP_DIR_IN
------------+--------+------------+---------------------------------------------------
- 0x10      | 4      |            | ep: endpoint number: zero
------------+--------+------------+---------------------------------------------------
- 0x14      | 4      |            | seqnum: the URB sequence number given previously
-           |        |            |   at USBIP_CMD_SUBMIT.seqnum field
------------+--------+------------+---------------------------------------------------
- 0x30      | n      |            | URB data bytes. For ISO transfers the padding
-           |        |            |   between each ISO packets is not transmitted.
-
-USBIP_RET_UNLINK: Reply for URB unlink
-
- Offset    | Length | Value      | Description
------------+--------+------------+---------------------------------------------------
- 0         | 4      | 0x00000004 | command: reply for the URB unlink command
------------+--------+------------+---------------------------------------------------
- 4         | 4      |            | seqnum: the unlinked URB sequence number
------------+--------+------------+---------------------------------------------------
- 8         | 4      |            | devid
------------+--------+------------+---------------------------------------------------
- 0xC       | 4      |            | direction: 0: USBIP_DIR_OUT
-           |        |            |            1: USBIP_DIR_IN
------------+--------+------------+---------------------------------------------------
- 0x10      | 4      |            | ep: endpoint number
------------+--------+------------+---------------------------------------------------
- 0x14      | 4      |            | status: This is the value contained in the
-           |        |            |   urb->status in the URB completition handler.
-           |        |            |   FIXME: a better explanation needed.
------------+--------+------------+---------------------------------------------------
- 0x30      | n      |            | URB data bytes. For ISO transfers the padding
-           |        |            |   between each ISO packets is not transmitted.
diff --git a/drivers/staging/usbip/vhci.h b/drivers/staging/usbip/vhci.h
deleted file mode 100644
index a863a98a91ce..000000000000
--- a/drivers/staging/usbip/vhci.h
+++ /dev/null
@@ -1,129 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- */
-
-#ifndef __USBIP_VHCI_H
-#define __USBIP_VHCI_H
-
-#include <linux/device.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/sysfs.h>
-#include <linux/types.h>
-#include <linux/usb.h>
-#include <linux/usb/hcd.h>
-#include <linux/wait.h>
-
-struct vhci_device {
-	struct usb_device *udev;
-
-	/*
-	 * devid specifies a remote usb device uniquely instead
-	 * of combination of busnum and devnum.
-	 */
-	__u32 devid;
-
-	/* speed of a remote device */
-	enum usb_device_speed speed;
-
-	/* vhci root-hub port to which this device is attached */
-	__u32 rhport;
-
-	struct usbip_device ud;
-
-	/* lock for the below link lists */
-	spinlock_t priv_lock;
-
-	/* vhci_priv is linked to one of them. */
-	struct list_head priv_tx;
-	struct list_head priv_rx;
-
-	/* vhci_unlink is linked to one of them */
-	struct list_head unlink_tx;
-	struct list_head unlink_rx;
-
-	/* vhci_tx thread sleeps for this queue */
-	wait_queue_head_t waitq_tx;
-};
-
-/* urb->hcpriv, use container_of() */
-struct vhci_priv {
-	unsigned long seqnum;
-	struct list_head list;
-
-	struct vhci_device *vdev;
-	struct urb *urb;
-};
-
-struct vhci_unlink {
-	/* seqnum of this request */
-	unsigned long seqnum;
-
-	struct list_head list;
-
-	/* seqnum of the unlink target */
-	unsigned long unlink_seqnum;
-};
-
-/* Number of supported ports. Value has an upperbound of USB_MAXCHILDREN */
-#define VHCI_NPORTS 8
-
-/* for usb_bus.hcpriv */
-struct vhci_hcd {
-	spinlock_t lock;
-
-	u32 port_status[VHCI_NPORTS];
-
-	unsigned resuming:1;
-	unsigned long re_timeout;
-
-	atomic_t seqnum;
-
-	/*
-	 * NOTE:
-	 * wIndex shows the port number and begins from 1.
-	 * But, the index of this array begins from 0.
-	 */
-	struct vhci_device vdev[VHCI_NPORTS];
-};
-
-extern struct vhci_hcd *the_controller;
-extern const struct attribute_group dev_attr_group;
-
-/* vhci_hcd.c */
-void rh_port_connect(int rhport, enum usb_device_speed speed);
-
-/* vhci_rx.c */
-struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum);
-int vhci_rx_loop(void *data);
-
-/* vhci_tx.c */
-int vhci_tx_loop(void *data);
-
-static inline struct vhci_device *port_to_vdev(__u32 port)
-{
-	return &the_controller->vdev[port];
-}
-
-static inline struct vhci_hcd *hcd_to_vhci(struct usb_hcd *hcd)
-{
-	return (struct vhci_hcd *) (hcd->hcd_priv);
-}
-
-static inline struct usb_hcd *vhci_to_hcd(struct vhci_hcd *vhci)
-{
-	return container_of((void *) vhci, struct usb_hcd, hcd_priv);
-}
-
-static inline struct device *vhci_dev(struct vhci_hcd *vhci)
-{
-	return vhci_to_hcd(vhci)->self.controller;
-}
-
-#endif /* __USBIP_VHCI_H */
diff --git a/drivers/staging/usbip/vhci_hcd.c b/drivers/staging/usbip/vhci_hcd.c
deleted file mode 100644
index c02374b6049c..000000000000
--- a/drivers/staging/usbip/vhci_hcd.c
+++ /dev/null
@@ -1,1171 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <linux/init.h>
-#include <linux/file.h>
-#include <linux/kernel.h>
-#include <linux/kthread.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-
-#include "usbip_common.h"
-#include "vhci.h"
-
-#define DRIVER_AUTHOR "Takahiro Hirofuchi"
-#define DRIVER_DESC "USB/IP 'Virtual' Host Controller (VHCI) Driver"
-
-/*
- * TODO
- *	- update root hub emulation
- *	- move the emulation code to userland ?
- *		porting to other operating systems
- *		minimize kernel code
- *	- add suspend/resume code
- *	- clean up everything
- */
-
-/* See usb gadget dummy hcd */
-
-static int vhci_hub_status(struct usb_hcd *hcd, char *buff);
-static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
-			    u16 wIndex, char *buff, u16 wLength);
-static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
-			    gfp_t mem_flags);
-static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status);
-static int vhci_start(struct usb_hcd *vhci_hcd);
-static void vhci_stop(struct usb_hcd *hcd);
-static int vhci_get_frame_number(struct usb_hcd *hcd);
-
-static const char driver_name[] = "vhci_hcd";
-static const char driver_desc[] = "USB/IP Virtual Host Controller";
-
-struct vhci_hcd *the_controller;
-
-static const char * const bit_desc[] = {
-	"CONNECTION",		/*0*/
-	"ENABLE",		/*1*/
-	"SUSPEND",		/*2*/
-	"OVER_CURRENT",		/*3*/
-	"RESET",		/*4*/
-	"R5",			/*5*/
-	"R6",			/*6*/
-	"R7",			/*7*/
-	"POWER",		/*8*/
-	"LOWSPEED",		/*9*/
-	"HIGHSPEED",		/*10*/
-	"PORT_TEST",		/*11*/
-	"INDICATOR",		/*12*/
-	"R13",			/*13*/
-	"R14",			/*14*/
-	"R15",			/*15*/
-	"C_CONNECTION",		/*16*/
-	"C_ENABLE",		/*17*/
-	"C_SUSPEND",		/*18*/
-	"C_OVER_CURRENT",	/*19*/
-	"C_RESET",		/*20*/
-	"R21",			/*21*/
-	"R22",			/*22*/
-	"R23",			/*23*/
-	"R24",			/*24*/
-	"R25",			/*25*/
-	"R26",			/*26*/
-	"R27",			/*27*/
-	"R28",			/*28*/
-	"R29",			/*29*/
-	"R30",			/*30*/
-	"R31",			/*31*/
-};
-
-static void dump_port_status_diff(u32 prev_status, u32 new_status)
-{
-	int i = 0;
-	u32 bit = 1;
-
-	pr_debug("status prev -> new: %08x -> %08x\n", prev_status, new_status);
-	while (bit) {
-		u32 prev = prev_status & bit;
-		u32 new = new_status & bit;
-		char change;
-
-		if (!prev && new)
-			change = '+';
-		else if (prev && !new)
-			change = '-';
-		else
-			change = ' ';
-
-		if (prev || new)
-			pr_debug(" %c%s\n", change, bit_desc[i]);
-		bit <<= 1;
-		i++;
-	}
-	pr_debug("\n");
-}
-
-void rh_port_connect(int rhport, enum usb_device_speed speed)
-{
-	usbip_dbg_vhci_rh("rh_port_connect %d\n", rhport);
-
-	spin_lock(&the_controller->lock);
-
-	the_controller->port_status[rhport] |= USB_PORT_STAT_CONNECTION
-		| (1 << USB_PORT_FEAT_C_CONNECTION);
-
-	switch (speed) {
-	case USB_SPEED_HIGH:
-		the_controller->port_status[rhport] |= USB_PORT_STAT_HIGH_SPEED;
-		break;
-	case USB_SPEED_LOW:
-		the_controller->port_status[rhport] |= USB_PORT_STAT_LOW_SPEED;
-		break;
-	default:
-		break;
-	}
-
-	spin_unlock(&the_controller->lock);
-
-	usb_hcd_poll_rh_status(vhci_to_hcd(the_controller));
-}
-
-static void rh_port_disconnect(int rhport)
-{
-	usbip_dbg_vhci_rh("rh_port_disconnect %d\n", rhport);
-
-	spin_lock(&the_controller->lock);
-
-	the_controller->port_status[rhport] &= ~USB_PORT_STAT_CONNECTION;
-	the_controller->port_status[rhport] |=
-					(1 << USB_PORT_FEAT_C_CONNECTION);
-
-	spin_unlock(&the_controller->lock);
-	usb_hcd_poll_rh_status(vhci_to_hcd(the_controller));
-}
-
-#define PORT_C_MASK				\
-	((USB_PORT_STAT_C_CONNECTION		\
-	  | USB_PORT_STAT_C_ENABLE		\
-	  | USB_PORT_STAT_C_SUSPEND		\
-	  | USB_PORT_STAT_C_OVERCURRENT		\
-	  | USB_PORT_STAT_C_RESET) << 16)
-
-/*
- * Returns 0 if the status hasn't changed, or the number of bytes in buf.
- * Ports are 0-indexed from the HCD point of view,
- * and 1-indexed from the USB core pointer of view.
- *
- * @buf: a bitmap to show which port status has been changed.
- *  bit  0: reserved
- *  bit  1: the status of port 0 has been changed.
- *  bit  2: the status of port 1 has been changed.
- *  ...
- */
-static int vhci_hub_status(struct usb_hcd *hcd, char *buf)
-{
-	struct vhci_hcd	*vhci;
-	int		retval;
-	int		rhport;
-	int		changed = 0;
-
-	retval = DIV_ROUND_UP(VHCI_NPORTS + 1, 8);
-	memset(buf, 0, retval);
-
-	vhci = hcd_to_vhci(hcd);
-
-	spin_lock(&vhci->lock);
-	if (!HCD_HW_ACCESSIBLE(hcd)) {
-		usbip_dbg_vhci_rh("hw accessible flag not on?\n");
-		goto done;
-	}
-
-	/* check pseudo status register for each port */
-	for (rhport = 0; rhport < VHCI_NPORTS; rhport++) {
-		if ((vhci->port_status[rhport] & PORT_C_MASK)) {
-			/* The status of a port has been changed, */
-			usbip_dbg_vhci_rh("port %d status changed\n", rhport);
-
-			buf[(rhport + 1) / 8] |= 1 << (rhport + 1) % 8;
-			changed = 1;
-		}
-	}
-
-	if ((hcd->state == HC_STATE_SUSPENDED) && (changed == 1))
-		usb_hcd_resume_root_hub(hcd);
-
-done:
-	spin_unlock(&vhci->lock);
-	return changed ? retval : 0;
-}
-
-static inline void hub_descriptor(struct usb_hub_descriptor *desc)
-{
-	memset(desc, 0, sizeof(*desc));
-	desc->bDescriptorType = 0x29;
-	desc->bDescLength = 9;
-	desc->wHubCharacteristics = (__constant_cpu_to_le16(0x0001));
-	desc->bNbrPorts = VHCI_NPORTS;
-	desc->u.hs.DeviceRemovable[0] = 0xff;
-	desc->u.hs.DeviceRemovable[1] = 0xff;
-}
-
-static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
-			    u16 wIndex, char *buf, u16 wLength)
-{
-	struct vhci_hcd	*dum;
-	int             retval = 0;
-	int		rhport;
-
-	u32 prev_port_status[VHCI_NPORTS];
-
-	if (!HCD_HW_ACCESSIBLE(hcd))
-		return -ETIMEDOUT;
-
-	/*
-	 * NOTE:
-	 * wIndex shows the port number and begins from 1.
-	 */
-	usbip_dbg_vhci_rh("typeReq %x wValue %x wIndex %x\n", typeReq, wValue,
-			  wIndex);
-	if (wIndex > VHCI_NPORTS)
-		pr_err("invalid port number %d\n", wIndex);
-	rhport = ((__u8)(wIndex & 0x00ff)) - 1;
-
-	dum = hcd_to_vhci(hcd);
-
-	spin_lock(&dum->lock);
-
-	/* store old status and compare now and old later */
-	if (usbip_dbg_flag_vhci_rh) {
-		memcpy(prev_port_status, dum->port_status,
-			sizeof(prev_port_status));
-	}
-
-	switch (typeReq) {
-	case ClearHubFeature:
-		usbip_dbg_vhci_rh(" ClearHubFeature\n");
-		break;
-	case ClearPortFeature:
-		switch (wValue) {
-		case USB_PORT_FEAT_SUSPEND:
-			if (dum->port_status[rhport] & USB_PORT_STAT_SUSPEND) {
-				/* 20msec signaling */
-				dum->resuming = 1;
-				dum->re_timeout =
-					jiffies + msecs_to_jiffies(20);
-			}
-			break;
-		case USB_PORT_FEAT_POWER:
-			usbip_dbg_vhci_rh(
-				" ClearPortFeature: USB_PORT_FEAT_POWER\n");
-			dum->port_status[rhport] = 0;
-			dum->resuming = 0;
-			break;
-		case USB_PORT_FEAT_C_RESET:
-			usbip_dbg_vhci_rh(
-				" ClearPortFeature: USB_PORT_FEAT_C_RESET\n");
-			switch (dum->vdev[rhport].speed) {
-			case USB_SPEED_HIGH:
-				dum->port_status[rhport] |=
-					USB_PORT_STAT_HIGH_SPEED;
-				break;
-			case USB_SPEED_LOW:
-				dum->port_status[rhport] |=
-					USB_PORT_STAT_LOW_SPEED;
-				break;
-			default:
-				break;
-			}
-		default:
-			usbip_dbg_vhci_rh(" ClearPortFeature: default %x\n",
-					  wValue);
-			dum->port_status[rhport] &= ~(1 << wValue);
-			break;
-		}
-		break;
-	case GetHubDescriptor:
-		usbip_dbg_vhci_rh(" GetHubDescriptor\n");
-		hub_descriptor((struct usb_hub_descriptor *) buf);
-		break;
-	case GetHubStatus:
-		usbip_dbg_vhci_rh(" GetHubStatus\n");
-		*(__le32 *) buf = cpu_to_le32(0);
-		break;
-	case GetPortStatus:
-		usbip_dbg_vhci_rh(" GetPortStatus port %x\n", wIndex);
-		if (wIndex > VHCI_NPORTS || wIndex < 1) {
-			pr_err("invalid port number %d\n", wIndex);
-			retval = -EPIPE;
-		}
-
-		/* we do not care about resume. */
-
-		/* whoever resets or resumes must GetPortStatus to
-		 * complete it!!
-		 */
-		if (dum->resuming && time_after(jiffies, dum->re_timeout)) {
-			dum->port_status[rhport] |=
-				(1 << USB_PORT_FEAT_C_SUSPEND);
-			dum->port_status[rhport] &=
-				~(1 << USB_PORT_FEAT_SUSPEND);
-			dum->resuming = 0;
-			dum->re_timeout = 0;
-		}
-
-		if ((dum->port_status[rhport] & (1 << USB_PORT_FEAT_RESET)) !=
-		    0 && time_after(jiffies, dum->re_timeout)) {
-			dum->port_status[rhport] |=
-				(1 << USB_PORT_FEAT_C_RESET);
-			dum->port_status[rhport] &=
-				~(1 << USB_PORT_FEAT_RESET);
-			dum->re_timeout = 0;
-
-			if (dum->vdev[rhport].ud.status ==
-			    VDEV_ST_NOTASSIGNED) {
-				usbip_dbg_vhci_rh(
-					" enable rhport %d (status %u)\n",
-					rhport,
-					dum->vdev[rhport].ud.status);
-				dum->port_status[rhport] |=
-					USB_PORT_STAT_ENABLE;
-			}
-		}
-		((__le16 *) buf)[0] = cpu_to_le16(dum->port_status[rhport]);
-		((__le16 *) buf)[1] =
-			cpu_to_le16(dum->port_status[rhport] >> 16);
-
-		usbip_dbg_vhci_rh(" GetPortStatus bye %x %x\n", ((u16 *)buf)[0],
-				  ((u16 *)buf)[1]);
-		break;
-	case SetHubFeature:
-		usbip_dbg_vhci_rh(" SetHubFeature\n");
-		retval = -EPIPE;
-		break;
-	case SetPortFeature:
-		switch (wValue) {
-		case USB_PORT_FEAT_SUSPEND:
-			usbip_dbg_vhci_rh(
-				" SetPortFeature: USB_PORT_FEAT_SUSPEND\n");
-			break;
-		case USB_PORT_FEAT_RESET:
-			usbip_dbg_vhci_rh(
-				" SetPortFeature: USB_PORT_FEAT_RESET\n");
-			/* if it's already running, disconnect first */
-			if (dum->port_status[rhport] & USB_PORT_STAT_ENABLE) {
-				dum->port_status[rhport] &=
-					~(USB_PORT_STAT_ENABLE |
-					  USB_PORT_STAT_LOW_SPEED |
-					  USB_PORT_STAT_HIGH_SPEED);
-				/* FIXME test that code path! */
-			}
-			/* 50msec reset signaling */
-			dum->re_timeout = jiffies + msecs_to_jiffies(50);
-
-			/* FALLTHROUGH */
-		default:
-			usbip_dbg_vhci_rh(" SetPortFeature: default %d\n",
-					  wValue);
-			dum->port_status[rhport] |= (1 << wValue);
-			break;
-		}
-		break;
-
-	default:
-		pr_err("default: no such request\n");
-
-		/* "protocol stall" on error */
-		retval = -EPIPE;
-	}
-
-	if (usbip_dbg_flag_vhci_rh) {
-		pr_debug("port %d\n", rhport);
-		/* Only dump valid port status */
-		if (rhport >= 0) {
-			dump_port_status_diff(prev_port_status[rhport],
-					      dum->port_status[rhport]);
-		}
-	}
-	usbip_dbg_vhci_rh(" bye\n");
-
-	spin_unlock(&dum->lock);
-
-	return retval;
-}
-
-static struct vhci_device *get_vdev(struct usb_device *udev)
-{
-	int i;
-
-	if (!udev)
-		return NULL;
-
-	for (i = 0; i < VHCI_NPORTS; i++)
-		if (the_controller->vdev[i].udev == udev)
-			return port_to_vdev(i);
-
-	return NULL;
-}
-
-static void vhci_tx_urb(struct urb *urb)
-{
-	struct vhci_device *vdev = get_vdev(urb->dev);
-	struct vhci_priv *priv;
-
-	if (!vdev) {
-		pr_err("could not get virtual device");
-		return;
-	}
-
-	priv = kzalloc(sizeof(struct vhci_priv), GFP_ATOMIC);
-	if (!priv) {
-		usbip_event_add(&vdev->ud, VDEV_EVENT_ERROR_MALLOC);
-		return;
-	}
-
-	spin_lock(&vdev->priv_lock);
-
-	priv->seqnum = atomic_inc_return(&the_controller->seqnum);
-	if (priv->seqnum == 0xffff)
-		dev_info(&urb->dev->dev, "seqnum max\n");
-
-	priv->vdev = vdev;
-	priv->urb = urb;
-
-	urb->hcpriv = (void *) priv;
-
-	list_add_tail(&priv->list, &vdev->priv_tx);
-
-	wake_up(&vdev->waitq_tx);
-	spin_unlock(&vdev->priv_lock);
-}
-
-static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
-			    gfp_t mem_flags)
-{
-	struct device *dev = &urb->dev->dev;
-	int ret = 0;
-	struct vhci_device *vdev;
-
-	usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n",
-			  hcd, urb, mem_flags);
-
-	/* patch to usb_sg_init() is in 2.5.60 */
-	BUG_ON(!urb->transfer_buffer && urb->transfer_buffer_length);
-
-	spin_lock(&the_controller->lock);
-
-	if (urb->status != -EINPROGRESS) {
-		dev_err(dev, "URB already unlinked!, status %d\n", urb->status);
-		spin_unlock(&the_controller->lock);
-		return urb->status;
-	}
-
-	vdev = port_to_vdev(urb->dev->portnum-1);
-
-	/* refuse enqueue for dead connection */
-	spin_lock(&vdev->ud.lock);
-	if (vdev->ud.status == VDEV_ST_NULL ||
-	    vdev->ud.status == VDEV_ST_ERROR) {
-		dev_err(dev, "enqueue for inactive port %d\n", vdev->rhport);
-		spin_unlock(&vdev->ud.lock);
-		spin_unlock(&the_controller->lock);
-		return -ENODEV;
-	}
-	spin_unlock(&vdev->ud.lock);
-
-	ret = usb_hcd_link_urb_to_ep(hcd, urb);
-	if (ret)
-		goto no_need_unlink;
-
-	/*
-	 * The enumeration process is as follows;
-	 *
-	 *  1. Get_Descriptor request to DevAddrs(0) EndPoint(0)
-	 *     to get max packet length of default pipe
-	 *
-	 *  2. Set_Address request to DevAddr(0) EndPoint(0)
-	 *
-	 */
-	if (usb_pipedevice(urb->pipe) == 0) {
-		__u8 type = usb_pipetype(urb->pipe);
-		struct usb_ctrlrequest *ctrlreq =
-			(struct usb_ctrlrequest *) urb->setup_packet;
-
-		if (type != PIPE_CONTROL || !ctrlreq) {
-			dev_err(dev, "invalid request to devnum 0\n");
-			ret = -EINVAL;
-			goto no_need_xmit;
-		}
-
-		switch (ctrlreq->bRequest) {
-		case USB_REQ_SET_ADDRESS:
-			/* set_address may come when a device is reset */
-			dev_info(dev, "SetAddress Request (%d) to port %d\n",
-				 ctrlreq->wValue, vdev->rhport);
-
-			if (vdev->udev)
-				usb_put_dev(vdev->udev);
-			vdev->udev = usb_get_dev(urb->dev);
-
-			spin_lock(&vdev->ud.lock);
-			vdev->ud.status = VDEV_ST_USED;
-			spin_unlock(&vdev->ud.lock);
-
-			if (urb->status == -EINPROGRESS) {
-				/* This request is successfully completed. */
-				/* If not -EINPROGRESS, possibly unlinked. */
-				urb->status = 0;
-			}
-
-			goto no_need_xmit;
-
-		case USB_REQ_GET_DESCRIPTOR:
-			if (ctrlreq->wValue == cpu_to_le16(USB_DT_DEVICE << 8))
-				usbip_dbg_vhci_hc(
-					"Not yet?:Get_Descriptor to device 0 (get max pipe size)\n");
-
-			if (vdev->udev)
-				usb_put_dev(vdev->udev);
-			vdev->udev = usb_get_dev(urb->dev);
-			goto out;
-
-		default:
-			/* NOT REACHED */
-			dev_err(dev,
-				"invalid request to devnum 0 bRequest %u, wValue %u\n",
-				ctrlreq->bRequest,
-				ctrlreq->wValue);
-			ret =  -EINVAL;
-			goto no_need_xmit;
-		}
-
-	}
-
-out:
-	vhci_tx_urb(urb);
-	spin_unlock(&the_controller->lock);
-
-	return 0;
-
-no_need_xmit:
-	usb_hcd_unlink_urb_from_ep(hcd, urb);
-no_need_unlink:
-	spin_unlock(&the_controller->lock);
-	usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status);
-	return ret;
-}
-
-/*
- * vhci_rx gives back the urb after receiving the reply of the urb.  If an
- * unlink pdu is sent or not, vhci_rx receives a normal return pdu and gives
- * back its urb. For the driver unlinking the urb, the content of the urb is
- * not important, but the calling to its completion handler is important; the
- * completion of unlinking is notified by the completion handler.
- *
- *
- * CLIENT SIDE
- *
- * - When vhci_hcd receives RET_SUBMIT,
- *
- *	- case 1a). the urb of the pdu is not unlinking.
- *		- normal case
- *		=> just give back the urb
- *
- *	- case 1b). the urb of the pdu is unlinking.
- *		- usbip.ko will return a reply of the unlinking request.
- *		=> give back the urb now and go to case 2b).
- *
- * - When vhci_hcd receives RET_UNLINK,
- *
- *	- case 2a). a submit request is still pending in vhci_hcd.
- *		- urb was really pending in usbip.ko and urb_unlink_urb() was
- *		  completed there.
- *		=> free a pending submit request
- *		=> notify unlink completeness by giving back the urb
- *
- *	- case 2b). a submit request is *not* pending in vhci_hcd.
- *		- urb was already given back to the core driver.
- *		=> do not give back the urb
- *
- *
- * SERVER SIDE
- *
- * - When usbip receives CMD_UNLINK,
- *
- *	- case 3a). the urb of the unlink request is now in submission.
- *		=> do usb_unlink_urb().
- *		=> after the unlink is completed, send RET_UNLINK.
- *
- *	- case 3b). the urb of the unlink request is not in submission.
- *		- may be already completed or never be received
- *		=> send RET_UNLINK
- *
- */
-static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
-{
-	struct vhci_priv *priv;
-	struct vhci_device *vdev;
-
-	pr_info("dequeue a urb %p\n", urb);
-
-	spin_lock(&the_controller->lock);
-
-	priv = urb->hcpriv;
-	if (!priv) {
-		/* URB was never linked! or will be soon given back by
-		 * vhci_rx. */
-		spin_unlock(&the_controller->lock);
-		return 0;
-	}
-
-	{
-		int ret = 0;
-
-		ret = usb_hcd_check_unlink_urb(hcd, urb, status);
-		if (ret) {
-			spin_unlock(&the_controller->lock);
-			return ret;
-		}
-	}
-
-	 /* send unlink request here? */
-	vdev = priv->vdev;
-
-	if (!vdev->ud.tcp_socket) {
-		/* tcp connection is closed */
-		spin_lock(&vdev->priv_lock);
-
-		pr_info("device %p seems to be disconnected\n", vdev);
-		list_del(&priv->list);
-		kfree(priv);
-		urb->hcpriv = NULL;
-
-		spin_unlock(&vdev->priv_lock);
-
-		/*
-		 * If tcp connection is alive, we have sent CMD_UNLINK.
-		 * vhci_rx will receive RET_UNLINK and give back the URB.
-		 * Otherwise, we give back it here.
-		 */
-		pr_info("gives back urb %p\n", urb);
-
-		usb_hcd_unlink_urb_from_ep(hcd, urb);
-
-		spin_unlock(&the_controller->lock);
-		usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
-				     urb->status);
-		spin_lock(&the_controller->lock);
-
-	} else {
-		/* tcp connection is alive */
-		struct vhci_unlink *unlink;
-
-		spin_lock(&vdev->priv_lock);
-
-		/* setup CMD_UNLINK pdu */
-		unlink = kzalloc(sizeof(struct vhci_unlink), GFP_ATOMIC);
-		if (!unlink) {
-			spin_unlock(&vdev->priv_lock);
-			spin_unlock(&the_controller->lock);
-			usbip_event_add(&vdev->ud, VDEV_EVENT_ERROR_MALLOC);
-			return -ENOMEM;
-		}
-
-		unlink->seqnum = atomic_inc_return(&the_controller->seqnum);
-		if (unlink->seqnum == 0xffff)
-			pr_info("seqnum max\n");
-
-		unlink->unlink_seqnum = priv->seqnum;
-
-		pr_info("device %p seems to be still connected\n", vdev);
-
-		/* send cmd_unlink and try to cancel the pending URB in the
-		 * peer */
-		list_add_tail(&unlink->list, &vdev->unlink_tx);
-		wake_up(&vdev->waitq_tx);
-
-		spin_unlock(&vdev->priv_lock);
-	}
-
-	spin_unlock(&the_controller->lock);
-
-	usbip_dbg_vhci_hc("leave\n");
-	return 0;
-}
-
-static void vhci_device_unlink_cleanup(struct vhci_device *vdev)
-{
-	struct vhci_unlink *unlink, *tmp;
-
-	spin_lock(&the_controller->lock);
-	spin_lock(&vdev->priv_lock);
-
-	list_for_each_entry_safe(unlink, tmp, &vdev->unlink_tx, list) {
-		pr_info("unlink cleanup tx %lu\n", unlink->unlink_seqnum);
-		list_del(&unlink->list);
-		kfree(unlink);
-	}
-
-	while (!list_empty(&vdev->unlink_rx)) {
-		struct urb *urb;
-
-		unlink = list_first_entry(&vdev->unlink_rx, struct vhci_unlink,
-			list);
-
-		/* give back URB of unanswered unlink request */
-		pr_info("unlink cleanup rx %lu\n", unlink->unlink_seqnum);
-
-		urb = pickup_urb_and_free_priv(vdev, unlink->unlink_seqnum);
-		if (!urb) {
-			pr_info("the urb (seqnum %lu) was already given back\n",
-				unlink->unlink_seqnum);
-			list_del(&unlink->list);
-			kfree(unlink);
-			continue;
-		}
-
-		urb->status = -ENODEV;
-
-		usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
-
-		list_del(&unlink->list);
-
-		spin_unlock(&vdev->priv_lock);
-		spin_unlock(&the_controller->lock);
-
-		usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
-				     urb->status);
-
-		spin_lock(&the_controller->lock);
-		spin_lock(&vdev->priv_lock);
-
-		kfree(unlink);
-	}
-
-	spin_unlock(&vdev->priv_lock);
-	spin_unlock(&the_controller->lock);
-}
-
-/*
- * The important thing is that only one context begins cleanup.
- * This is why error handling and cleanup become simple.
- * We do not want to consider race condition as possible.
- */
-static void vhci_shutdown_connection(struct usbip_device *ud)
-{
-	struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
-
-	/* need this? see stub_dev.c */
-	if (ud->tcp_socket) {
-		pr_debug("shutdown tcp_socket %p\n", ud->tcp_socket);
-		kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
-	}
-
-	/* kill threads related to this sdev */
-	if (vdev->ud.tcp_rx) {
-		kthread_stop_put(vdev->ud.tcp_rx);
-		vdev->ud.tcp_rx = NULL;
-	}
-	if (vdev->ud.tcp_tx) {
-		kthread_stop_put(vdev->ud.tcp_tx);
-		vdev->ud.tcp_tx = NULL;
-	}
-	pr_info("stop threads\n");
-
-	/* active connection is closed */
-	if (vdev->ud.tcp_socket) {
-		sockfd_put(vdev->ud.tcp_socket);
-		vdev->ud.tcp_socket = NULL;
-	}
-	pr_info("release socket\n");
-
-	vhci_device_unlink_cleanup(vdev);
-
-	/*
-	 * rh_port_disconnect() is a trigger of ...
-	 *   usb_disable_device():
-	 *	disable all the endpoints for a USB device.
-	 *   usb_disable_endpoint():
-	 *	disable endpoints. pending urbs are unlinked(dequeued).
-	 *
-	 * NOTE: After calling rh_port_disconnect(), the USB device drivers of a
-	 * detached device should release used urbs in a cleanup function (i.e.
-	 * xxx_disconnect()). Therefore, vhci_hcd does not need to release
-	 * pushed urbs and their private data in this function.
-	 *
-	 * NOTE: vhci_dequeue() must be considered carefully. When shutting down
-	 * a connection, vhci_shutdown_connection() expects vhci_dequeue()
-	 * gives back pushed urbs and frees their private data by request of
-	 * the cleanup function of a USB driver. When unlinking a urb with an
-	 * active connection, vhci_dequeue() does not give back the urb which
-	 * is actually given back by vhci_rx after receiving its return pdu.
-	 *
-	 */
-	rh_port_disconnect(vdev->rhport);
-
-	pr_info("disconnect device\n");
-}
-
-
-static void vhci_device_reset(struct usbip_device *ud)
-{
-	struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
-
-	spin_lock(&ud->lock);
-
-	vdev->speed  = 0;
-	vdev->devid  = 0;
-
-	if (vdev->udev)
-		usb_put_dev(vdev->udev);
-	vdev->udev = NULL;
-
-	if (ud->tcp_socket) {
-		sockfd_put(ud->tcp_socket);
-		ud->tcp_socket = NULL;
-	}
-	ud->status = VDEV_ST_NULL;
-
-	spin_unlock(&ud->lock);
-}
-
-static void vhci_device_unusable(struct usbip_device *ud)
-{
-	spin_lock(&ud->lock);
-	ud->status = VDEV_ST_ERROR;
-	spin_unlock(&ud->lock);
-}
-
-static void vhci_device_init(struct vhci_device *vdev)
-{
-	memset(vdev, 0, sizeof(*vdev));
-
-	vdev->ud.side   = USBIP_VHCI;
-	vdev->ud.status = VDEV_ST_NULL;
-	spin_lock_init(&vdev->ud.lock);
-
-	INIT_LIST_HEAD(&vdev->priv_rx);
-	INIT_LIST_HEAD(&vdev->priv_tx);
-	INIT_LIST_HEAD(&vdev->unlink_tx);
-	INIT_LIST_HEAD(&vdev->unlink_rx);
-	spin_lock_init(&vdev->priv_lock);
-
-	init_waitqueue_head(&vdev->waitq_tx);
-
-	vdev->ud.eh_ops.shutdown = vhci_shutdown_connection;
-	vdev->ud.eh_ops.reset = vhci_device_reset;
-	vdev->ud.eh_ops.unusable = vhci_device_unusable;
-
-	usbip_start_eh(&vdev->ud);
-}
-
-static int vhci_start(struct usb_hcd *hcd)
-{
-	struct vhci_hcd *vhci = hcd_to_vhci(hcd);
-	int rhport;
-	int err = 0;
-
-	usbip_dbg_vhci_hc("enter vhci_start\n");
-
-	/* initialize private data of usb_hcd */
-
-	for (rhport = 0; rhport < VHCI_NPORTS; rhport++) {
-		struct vhci_device *vdev = &vhci->vdev[rhport];
-
-		vhci_device_init(vdev);
-		vdev->rhport = rhport;
-	}
-
-	atomic_set(&vhci->seqnum, 0);
-	spin_lock_init(&vhci->lock);
-
-	hcd->power_budget = 0; /* no limit */
-	hcd->uses_new_polling = 1;
-
-	/* vhci_hcd is now ready to be controlled through sysfs */
-	err = sysfs_create_group(&vhci_dev(vhci)->kobj, &dev_attr_group);
-	if (err) {
-		pr_err("create sysfs files\n");
-		return err;
-	}
-
-	return 0;
-}
-
-static void vhci_stop(struct usb_hcd *hcd)
-{
-	struct vhci_hcd *vhci = hcd_to_vhci(hcd);
-	int rhport = 0;
-
-	usbip_dbg_vhci_hc("stop VHCI controller\n");
-
-	/* 1. remove the userland interface of vhci_hcd */
-	sysfs_remove_group(&vhci_dev(vhci)->kobj, &dev_attr_group);
-
-	/* 2. shutdown all the ports of vhci_hcd */
-	for (rhport = 0; rhport < VHCI_NPORTS; rhport++) {
-		struct vhci_device *vdev = &vhci->vdev[rhport];
-
-		usbip_event_add(&vdev->ud, VDEV_EVENT_REMOVED);
-		usbip_stop_eh(&vdev->ud);
-	}
-}
-
-static int vhci_get_frame_number(struct usb_hcd *hcd)
-{
-	pr_err("Not yet implemented\n");
-	return 0;
-}
-
-#ifdef CONFIG_PM
-
-/* FIXME: suspend/resume */
-static int vhci_bus_suspend(struct usb_hcd *hcd)
-{
-	struct vhci_hcd *vhci = hcd_to_vhci(hcd);
-
-	dev_dbg(&hcd->self.root_hub->dev, "%s\n", __func__);
-
-	spin_lock(&vhci->lock);
-	hcd->state = HC_STATE_SUSPENDED;
-	spin_unlock(&vhci->lock);
-
-	return 0;
-}
-
-static int vhci_bus_resume(struct usb_hcd *hcd)
-{
-	struct vhci_hcd *vhci = hcd_to_vhci(hcd);
-	int rc = 0;
-
-	dev_dbg(&hcd->self.root_hub->dev, "%s\n", __func__);
-
-	spin_lock(&vhci->lock);
-	if (!HCD_HW_ACCESSIBLE(hcd))
-		rc = -ESHUTDOWN;
-	else
-		hcd->state = HC_STATE_RUNNING;
-	spin_unlock(&vhci->lock);
-
-	return rc;
-}
-
-#else
-
-#define vhci_bus_suspend      NULL
-#define vhci_bus_resume       NULL
-#endif
-
-static struct hc_driver vhci_hc_driver = {
-	.description	= driver_name,
-	.product_desc	= driver_desc,
-	.hcd_priv_size	= sizeof(struct vhci_hcd),
-
-	.flags		= HCD_USB2,
-
-	.start		= vhci_start,
-	.stop		= vhci_stop,
-
-	.urb_enqueue	= vhci_urb_enqueue,
-	.urb_dequeue	= vhci_urb_dequeue,
-
-	.get_frame_number = vhci_get_frame_number,
-
-	.hub_status_data = vhci_hub_status,
-	.hub_control    = vhci_hub_control,
-	.bus_suspend	= vhci_bus_suspend,
-	.bus_resume	= vhci_bus_resume,
-};
-
-static int vhci_hcd_probe(struct platform_device *pdev)
-{
-	struct usb_hcd		*hcd;
-	int			ret;
-
-	usbip_dbg_vhci_hc("name %s id %d\n", pdev->name, pdev->id);
-
-	/*
-	 * Allocate and initialize hcd.
-	 * Our private data is also allocated automatically.
-	 */
-	hcd = usb_create_hcd(&vhci_hc_driver, &pdev->dev, dev_name(&pdev->dev));
-	if (!hcd) {
-		pr_err("create hcd failed\n");
-		return -ENOMEM;
-	}
-	hcd->has_tt = 1;
-
-	/* this is private data for vhci_hcd */
-	the_controller = hcd_to_vhci(hcd);
-
-	/*
-	 * Finish generic HCD structure initialization and register.
-	 * Call the driver's reset() and start() routines.
-	 */
-	ret = usb_add_hcd(hcd, 0, 0);
-	if (ret != 0) {
-		pr_err("usb_add_hcd failed %d\n", ret);
-		usb_put_hcd(hcd);
-		the_controller = NULL;
-		return ret;
-	}
-
-	usbip_dbg_vhci_hc("bye\n");
-	return 0;
-}
-
-static int vhci_hcd_remove(struct platform_device *pdev)
-{
-	struct usb_hcd	*hcd;
-
-	hcd = platform_get_drvdata(pdev);
-	if (!hcd)
-		return 0;
-
-	/*
-	 * Disconnects the root hub,
-	 * then reverses the effects of usb_add_hcd(),
-	 * invoking the HCD's stop() methods.
-	 */
-	usb_remove_hcd(hcd);
-	usb_put_hcd(hcd);
-	the_controller = NULL;
-
-	return 0;
-}
-
-#ifdef CONFIG_PM
-
-/* what should happen for USB/IP under suspend/resume? */
-static int vhci_hcd_suspend(struct platform_device *pdev, pm_message_t state)
-{
-	struct usb_hcd *hcd;
-	int rhport = 0;
-	int connected = 0;
-	int ret = 0;
-
-	hcd = platform_get_drvdata(pdev);
-
-	spin_lock(&the_controller->lock);
-
-	for (rhport = 0; rhport < VHCI_NPORTS; rhport++)
-		if (the_controller->port_status[rhport] &
-		    USB_PORT_STAT_CONNECTION)
-			connected += 1;
-
-	spin_unlock(&the_controller->lock);
-
-	if (connected > 0) {
-		dev_info(&pdev->dev,
-			 "We have %d active connection%s. Do not suspend.\n",
-			 connected, (connected == 1 ? "" : "s"));
-		ret =  -EBUSY;
-	} else {
-		dev_info(&pdev->dev, "suspend vhci_hcd");
-		clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
-	}
-
-	return ret;
-}
-
-static int vhci_hcd_resume(struct platform_device *pdev)
-{
-	struct usb_hcd *hcd;
-
-	dev_dbg(&pdev->dev, "%s\n", __func__);
-
-	hcd = platform_get_drvdata(pdev);
-	set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
-	usb_hcd_poll_rh_status(hcd);
-
-	return 0;
-}
-
-#else
-
-#define vhci_hcd_suspend	NULL
-#define vhci_hcd_resume		NULL
-
-#endif
-
-static struct platform_driver vhci_driver = {
-	.probe	= vhci_hcd_probe,
-	.remove	= vhci_hcd_remove,
-	.suspend = vhci_hcd_suspend,
-	.resume	= vhci_hcd_resume,
-	.driver	= {
-		.name = driver_name,
-		.owner = THIS_MODULE,
-	},
-};
-
-/*
- * The VHCI 'device' is 'virtual'; not a real plug&play hardware.
- * We need to add this virtual device as a platform device arbitrarily:
- *	1. platform_device_register()
- */
-static void the_pdev_release(struct device *dev)
-{
-}
-
-static struct platform_device the_pdev = {
-	/* should be the same name as driver_name */
-	.name = driver_name,
-	.id = -1,
-	.dev = {
-		.release = the_pdev_release,
-	},
-};
-
-static int __init vhci_hcd_init(void)
-{
-	int ret;
-
-	if (usb_disabled())
-		return -ENODEV;
-
-	ret = platform_driver_register(&vhci_driver);
-	if (ret)
-		goto err_driver_register;
-
-	ret = platform_device_register(&the_pdev);
-	if (ret)
-		goto err_platform_device_register;
-
-	pr_info(DRIVER_DESC " v" USBIP_VERSION "\n");
-	return ret;
-
-err_platform_device_register:
-	platform_driver_unregister(&vhci_driver);
-err_driver_register:
-	return ret;
-}
-
-static void __exit vhci_hcd_exit(void)
-{
-	platform_device_unregister(&the_pdev);
-	platform_driver_unregister(&vhci_driver);
-}
-
-module_init(vhci_hcd_init);
-module_exit(vhci_hcd_exit);
-
-MODULE_AUTHOR(DRIVER_AUTHOR);
-MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE("GPL");
-MODULE_VERSION(USBIP_VERSION);
diff --git a/drivers/staging/usbip/vhci_rx.c b/drivers/staging/usbip/vhci_rx.c
deleted file mode 100644
index 00e4a54308e4..000000000000
--- a/drivers/staging/usbip/vhci_rx.c
+++ /dev/null
@@ -1,268 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <linux/kthread.h>
-#include <linux/slab.h>
-
-#include "usbip_common.h"
-#include "vhci.h"
-
-/* get URB from transmitted urb queue. caller must hold vdev->priv_lock */
-struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum)
-{
-	struct vhci_priv *priv, *tmp;
-	struct urb *urb = NULL;
-	int status;
-
-	list_for_each_entry_safe(priv, tmp, &vdev->priv_rx, list) {
-		if (priv->seqnum != seqnum)
-			continue;
-
-		urb = priv->urb;
-		status = urb->status;
-
-		usbip_dbg_vhci_rx("find urb %p vurb %p seqnum %u\n",
-				urb, priv, seqnum);
-
-		switch (status) {
-		case -ENOENT:
-			/* fall through */
-		case -ECONNRESET:
-			dev_info(&urb->dev->dev,
-				 "urb %p was unlinked %ssynchronuously.\n", urb,
-				 status == -ENOENT ? "" : "a");
-			break;
-		case -EINPROGRESS:
-			/* no info output */
-			break;
-		default:
-			dev_info(&urb->dev->dev,
-				 "urb %p may be in a error, status %d\n", urb,
-				 status);
-		}
-
-		list_del(&priv->list);
-		kfree(priv);
-		urb->hcpriv = NULL;
-
-		break;
-	}
-
-	return urb;
-}
-
-static void vhci_recv_ret_submit(struct vhci_device *vdev,
-				 struct usbip_header *pdu)
-{
-	struct usbip_device *ud = &vdev->ud;
-	struct urb *urb;
-
-	spin_lock(&vdev->priv_lock);
-	urb = pickup_urb_and_free_priv(vdev, pdu->base.seqnum);
-	spin_unlock(&vdev->priv_lock);
-
-	if (!urb) {
-		pr_err("cannot find a urb of seqnum %u\n", pdu->base.seqnum);
-		pr_info("max seqnum %d\n",
-			atomic_read(&the_controller->seqnum));
-		usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
-		return;
-	}
-
-	/* unpack the pdu to a urb */
-	usbip_pack_pdu(pdu, urb, USBIP_RET_SUBMIT, 0);
-
-	/* recv transfer buffer */
-	if (usbip_recv_xbuff(ud, urb) < 0)
-		return;
-
-	/* recv iso_packet_descriptor */
-	if (usbip_recv_iso(ud, urb) < 0)
-		return;
-
-	/* restore the padding in iso packets */
-	usbip_pad_iso(ud, urb);
-
-	if (usbip_dbg_flag_vhci_rx)
-		usbip_dump_urb(urb);
-
-	usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
-
-	spin_lock(&the_controller->lock);
-	usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
-	spin_unlock(&the_controller->lock);
-
-	usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status);
-
-	usbip_dbg_vhci_rx("Leave\n");
-}
-
-static struct vhci_unlink *dequeue_pending_unlink(struct vhci_device *vdev,
-						  struct usbip_header *pdu)
-{
-	struct vhci_unlink *unlink, *tmp;
-
-	spin_lock(&vdev->priv_lock);
-
-	list_for_each_entry_safe(unlink, tmp, &vdev->unlink_rx, list) {
-		pr_info("unlink->seqnum %lu\n", unlink->seqnum);
-		if (unlink->seqnum == pdu->base.seqnum) {
-			usbip_dbg_vhci_rx("found pending unlink, %lu\n",
-					  unlink->seqnum);
-			list_del(&unlink->list);
-
-			spin_unlock(&vdev->priv_lock);
-			return unlink;
-		}
-	}
-
-	spin_unlock(&vdev->priv_lock);
-
-	return NULL;
-}
-
-static void vhci_recv_ret_unlink(struct vhci_device *vdev,
-				 struct usbip_header *pdu)
-{
-	struct vhci_unlink *unlink;
-	struct urb *urb;
-
-	usbip_dump_header(pdu);
-
-	unlink = dequeue_pending_unlink(vdev, pdu);
-	if (!unlink) {
-		pr_info("cannot find the pending unlink %u\n",
-			pdu->base.seqnum);
-		return;
-	}
-
-	spin_lock(&vdev->priv_lock);
-	urb = pickup_urb_and_free_priv(vdev, unlink->unlink_seqnum);
-	spin_unlock(&vdev->priv_lock);
-
-	if (!urb) {
-		/*
-		 * I get the result of a unlink request. But, it seems that I
-		 * already received the result of its submit result and gave
-		 * back the URB.
-		 */
-		pr_info("the urb (seqnum %d) was already given back\n",
-			pdu->base.seqnum);
-	} else {
-		usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
-
-		/* If unlink is successful, status is -ECONNRESET */
-		urb->status = pdu->u.ret_unlink.status;
-		pr_info("urb->status %d\n", urb->status);
-
-		spin_lock(&the_controller->lock);
-		usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
-		spin_unlock(&the_controller->lock);
-
-		usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
-				     urb->status);
-	}
-
-	kfree(unlink);
-}
-
-static int vhci_priv_tx_empty(struct vhci_device *vdev)
-{
-	int empty = 0;
-
-	spin_lock(&vdev->priv_lock);
-	empty = list_empty(&vdev->priv_rx);
-	spin_unlock(&vdev->priv_lock);
-
-	return empty;
-}
-
-/* recv a pdu */
-static void vhci_rx_pdu(struct usbip_device *ud)
-{
-	int ret;
-	struct usbip_header pdu;
-	struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
-
-	usbip_dbg_vhci_rx("Enter\n");
-
-	memset(&pdu, 0, sizeof(pdu));
-
-	/* receive a pdu header */
-	ret = usbip_recv(ud->tcp_socket, &pdu, sizeof(pdu));
-	if (ret < 0) {
-		if (ret == -ECONNRESET)
-			pr_info("connection reset by peer\n");
-		else if (ret == -EAGAIN) {
-			/* ignore if connection was idle */
-			if (vhci_priv_tx_empty(vdev))
-				return;
-			pr_info("connection timed out with pending urbs\n");
-		} else if (ret != -ERESTARTSYS)
-			pr_info("xmit failed %d\n", ret);
-
-		usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
-		return;
-	}
-	if (ret == 0) {
-		pr_info("connection closed");
-		usbip_event_add(ud, VDEV_EVENT_DOWN);
-		return;
-	}
-	if (ret != sizeof(pdu)) {
-		pr_err("received pdu size is %d, should be %d\n", ret,
-		       (unsigned int)sizeof(pdu));
-		usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
-		return;
-	}
-
-	usbip_header_correct_endian(&pdu, 0);
-
-	if (usbip_dbg_flag_vhci_rx)
-		usbip_dump_header(&pdu);
-
-	switch (pdu.base.command) {
-	case USBIP_RET_SUBMIT:
-		vhci_recv_ret_submit(vdev, &pdu);
-		break;
-	case USBIP_RET_UNLINK:
-		vhci_recv_ret_unlink(vdev, &pdu);
-		break;
-	default:
-		/* NOT REACHED */
-		pr_err("unknown pdu %u\n", pdu.base.command);
-		usbip_dump_header(&pdu);
-		usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
-		break;
-	}
-}
-
-int vhci_rx_loop(void *data)
-{
-	struct usbip_device *ud = data;
-
-	while (!kthread_should_stop()) {
-		if (usbip_event_happened(ud))
-			break;
-
-		vhci_rx_pdu(ud);
-	}
-
-	return 0;
-}
diff --git a/drivers/staging/usbip/vhci_sysfs.c b/drivers/staging/usbip/vhci_sysfs.c
deleted file mode 100644
index 211f43f67ea2..000000000000
--- a/drivers/staging/usbip/vhci_sysfs.c
+++ /dev/null
@@ -1,252 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <linux/kthread.h>
-#include <linux/file.h>
-#include <linux/net.h>
-
-#include "usbip_common.h"
-#include "vhci.h"
-
-/* TODO: refine locking ?*/
-
-/* Sysfs entry to show port status */
-static ssize_t status_show(struct device *dev, struct device_attribute *attr,
-			   char *out)
-{
-	char *s = out;
-	int i = 0;
-
-	BUG_ON(!the_controller || !out);
-
-	spin_lock(&the_controller->lock);
-
-	/*
-	 * output example:
-	 * prt sta spd dev socket           local_busid
-	 * 000 004 000 000         c5a7bb80 1-2.3
-	 * 001 004 000 000         d8cee980 2-3.4
-	 *
-	 * IP address can be retrieved from a socket pointer address by looking
-	 * up /proc/net/{tcp,tcp6}. Also, a userland program may remember a
-	 * port number and its peer IP address.
-	 */
-	out += sprintf(out,
-		       "prt sta spd bus dev socket           local_busid\n");
-
-	for (i = 0; i < VHCI_NPORTS; i++) {
-		struct vhci_device *vdev = port_to_vdev(i);
-
-		spin_lock(&vdev->ud.lock);
-		out += sprintf(out, "%03u %03u ", i, vdev->ud.status);
-
-		if (vdev->ud.status == VDEV_ST_USED) {
-			out += sprintf(out, "%03u %08x ",
-				       vdev->speed, vdev->devid);
-			out += sprintf(out, "%16p ", vdev->ud.tcp_socket);
-			out += sprintf(out, "%s", dev_name(&vdev->udev->dev));
-
-		} else {
-			out += sprintf(out, "000 000 000 0000000000000000 0-0");
-		}
-
-		out += sprintf(out, "\n");
-		spin_unlock(&vdev->ud.lock);
-	}
-
-	spin_unlock(&the_controller->lock);
-
-	return out - s;
-}
-static DEVICE_ATTR_RO(status);
-
-/* Sysfs entry to shutdown a virtual connection */
-static int vhci_port_disconnect(__u32 rhport)
-{
-	struct vhci_device *vdev;
-
-	usbip_dbg_vhci_sysfs("enter\n");
-
-	/* lock */
-	spin_lock(&the_controller->lock);
-
-	vdev = port_to_vdev(rhport);
-
-	spin_lock(&vdev->ud.lock);
-	if (vdev->ud.status == VDEV_ST_NULL) {
-		pr_err("not connected %d\n", vdev->ud.status);
-
-		/* unlock */
-		spin_unlock(&vdev->ud.lock);
-		spin_unlock(&the_controller->lock);
-
-		return -EINVAL;
-	}
-
-	/* unlock */
-	spin_unlock(&vdev->ud.lock);
-	spin_unlock(&the_controller->lock);
-
-	usbip_event_add(&vdev->ud, VDEV_EVENT_DOWN);
-
-	return 0;
-}
-
-static ssize_t store_detach(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
-{
-	int err;
-	__u32 rhport = 0;
-
-	if (sscanf(buf, "%u", &rhport) != 1)
-		return -EINVAL;
-
-	/* check rhport */
-	if (rhport >= VHCI_NPORTS) {
-		dev_err(dev, "invalid port %u\n", rhport);
-		return -EINVAL;
-	}
-
-	err = vhci_port_disconnect(rhport);
-	if (err < 0)
-		return -EINVAL;
-
-	usbip_dbg_vhci_sysfs("Leave\n");
-
-	return count;
-}
-static DEVICE_ATTR(detach, S_IWUSR, NULL, store_detach);
-
-/* Sysfs entry to establish a virtual connection */
-static int valid_args(__u32 rhport, enum usb_device_speed speed)
-{
-	/* check rhport */
-	if (rhport >= VHCI_NPORTS) {
-		pr_err("port %u\n", rhport);
-		return -EINVAL;
-	}
-
-	/* check speed */
-	switch (speed) {
-	case USB_SPEED_LOW:
-	case USB_SPEED_FULL:
-	case USB_SPEED_HIGH:
-	case USB_SPEED_WIRELESS:
-		break;
-	default:
-		pr_err("Failed attach request for unsupported USB speed: %s\n",
-			usb_speed_string(speed));
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/*
- * To start a new USB/IP attachment, a userland program needs to setup a TCP
- * connection and then write its socket descriptor with remote device
- * information into this sysfs file.
- *
- * A remote device is virtually attached to the root-hub port of @rhport with
- * @speed. @devid is embedded into a request to specify the remote device in a
- * server host.
- *
- * write() returns 0 on success, else negative errno.
- */
-static ssize_t store_attach(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
-{
-	struct vhci_device *vdev;
-	struct socket *socket;
-	int sockfd = 0;
-	__u32 rhport = 0, devid = 0, speed = 0;
-	int err;
-
-	/*
-	 * @rhport: port number of vhci_hcd
-	 * @sockfd: socket descriptor of an established TCP connection
-	 * @devid: unique device identifier in a remote host
-	 * @speed: usb device speed in a remote host
-	 */
-	if (sscanf(buf, "%u %u %u %u", &rhport, &sockfd, &devid, &speed) != 4)
-		return -EINVAL;
-
-	usbip_dbg_vhci_sysfs("rhport(%u) sockfd(%u) devid(%u) speed(%u)\n",
-			     rhport, sockfd, devid, speed);
-
-	/* check received parameters */
-	if (valid_args(rhport, speed) < 0)
-		return -EINVAL;
-
-	/* Extract socket from fd. */
-	socket = sockfd_lookup(sockfd, &err);
-	if (!socket)
-		return -EINVAL;
-
-	/* now need lock until setting vdev status as used */
-
-	/* begin a lock */
-	spin_lock(&the_controller->lock);
-	vdev = port_to_vdev(rhport);
-	spin_lock(&vdev->ud.lock);
-
-	if (vdev->ud.status != VDEV_ST_NULL) {
-		/* end of the lock */
-		spin_unlock(&vdev->ud.lock);
-		spin_unlock(&the_controller->lock);
-
-		sockfd_put(socket);
-
-		dev_err(dev, "port %d already used\n", rhport);
-		return -EINVAL;
-	}
-
-	dev_info(dev,
-		 "rhport(%u) sockfd(%d) devid(%u) speed(%u) speed_str(%s)\n",
-		 rhport, sockfd, devid, speed, usb_speed_string(speed));
-
-	vdev->devid         = devid;
-	vdev->speed         = speed;
-	vdev->ud.tcp_socket = socket;
-	vdev->ud.status     = VDEV_ST_NOTASSIGNED;
-
-	spin_unlock(&vdev->ud.lock);
-	spin_unlock(&the_controller->lock);
-	/* end the lock */
-
-	vdev->ud.tcp_rx = kthread_get_run(vhci_rx_loop, &vdev->ud, "vhci_rx");
-	vdev->ud.tcp_tx = kthread_get_run(vhci_tx_loop, &vdev->ud, "vhci_tx");
-
-	rh_port_connect(rhport, speed);
-
-	return count;
-}
-static DEVICE_ATTR(attach, S_IWUSR, NULL, store_attach);
-
-static struct attribute *dev_attrs[] = {
-	&dev_attr_status.attr,
-	&dev_attr_detach.attr,
-	&dev_attr_attach.attr,
-	&dev_attr_usbip_debug.attr,
-	NULL,
-};
-
-const struct attribute_group dev_attr_group = {
-	.attrs = dev_attrs,
-};
diff --git a/drivers/staging/usbip/vhci_tx.c b/drivers/staging/usbip/vhci_tx.c
deleted file mode 100644
index 409fd99f3257..000000000000
--- a/drivers/staging/usbip/vhci_tx.c
+++ /dev/null
@@ -1,224 +0,0 @@
-/*
- * Copyright (C) 2003-2008 Takahiro Hirofuchi
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
- * USA.
- */
-
-#include <linux/kthread.h>
-#include <linux/slab.h>
-
-#include "usbip_common.h"
-#include "vhci.h"
-
-static void setup_cmd_submit_pdu(struct usbip_header *pdup,  struct urb *urb)
-{
-	struct vhci_priv *priv = ((struct vhci_priv *)urb->hcpriv);
-	struct vhci_device *vdev = priv->vdev;
-
-	usbip_dbg_vhci_tx("URB, local devnum %u, remote devid %u\n",
-			  usb_pipedevice(urb->pipe), vdev->devid);
-
-	pdup->base.command   = USBIP_CMD_SUBMIT;
-	pdup->base.seqnum    = priv->seqnum;
-	pdup->base.devid     = vdev->devid;
-	pdup->base.direction = usb_pipein(urb->pipe) ?
-		USBIP_DIR_IN : USBIP_DIR_OUT;
-	pdup->base.ep	     = usb_pipeendpoint(urb->pipe);
-
-	usbip_pack_pdu(pdup, urb, USBIP_CMD_SUBMIT, 1);
-
-	if (urb->setup_packet)
-		memcpy(pdup->u.cmd_submit.setup, urb->setup_packet, 8);
-}
-
-static struct vhci_priv *dequeue_from_priv_tx(struct vhci_device *vdev)
-{
-	struct vhci_priv *priv, *tmp;
-
-	spin_lock(&vdev->priv_lock);
-
-	list_for_each_entry_safe(priv, tmp, &vdev->priv_tx, list) {
-		list_move_tail(&priv->list, &vdev->priv_rx);
-		spin_unlock(&vdev->priv_lock);
-		return priv;
-	}
-
-	spin_unlock(&vdev->priv_lock);
-
-	return NULL;
-}
-
-static int vhci_send_cmd_submit(struct vhci_device *vdev)
-{
-	struct vhci_priv *priv = NULL;
-
-	struct msghdr msg;
-	struct kvec iov[3];
-	size_t txsize;
-
-	size_t total_size = 0;
-
-	while ((priv = dequeue_from_priv_tx(vdev)) != NULL) {
-		int ret;
-		struct urb *urb = priv->urb;
-		struct usbip_header pdu_header;
-		struct usbip_iso_packet_descriptor *iso_buffer = NULL;
-
-		txsize = 0;
-		memset(&pdu_header, 0, sizeof(pdu_header));
-		memset(&msg, 0, sizeof(msg));
-		memset(&iov, 0, sizeof(iov));
-
-		usbip_dbg_vhci_tx("setup txdata urb %p\n", urb);
-
-		/* 1. setup usbip_header */
-		setup_cmd_submit_pdu(&pdu_header, urb);
-		usbip_header_correct_endian(&pdu_header, 1);
-
-		iov[0].iov_base = &pdu_header;
-		iov[0].iov_len  = sizeof(pdu_header);
-		txsize += sizeof(pdu_header);
-
-		/* 2. setup transfer buffer */
-		if (!usb_pipein(urb->pipe) && urb->transfer_buffer_length > 0) {
-			iov[1].iov_base = urb->transfer_buffer;
-			iov[1].iov_len  = urb->transfer_buffer_length;
-			txsize += urb->transfer_buffer_length;
-		}
-
-		/* 3. setup iso_packet_descriptor */
-		if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) {
-			ssize_t len = 0;
-
-			iso_buffer = usbip_alloc_iso_desc_pdu(urb, &len);
-			if (!iso_buffer) {
-				usbip_event_add(&vdev->ud,
-						SDEV_EVENT_ERROR_MALLOC);
-				return -1;
-			}
-
-			iov[2].iov_base = iso_buffer;
-			iov[2].iov_len  = len;
-			txsize += len;
-		}
-
-		ret = kernel_sendmsg(vdev->ud.tcp_socket, &msg, iov, 3, txsize);
-		if (ret != txsize) {
-			pr_err("sendmsg failed!, ret=%d for %zd\n", ret,
-			       txsize);
-			kfree(iso_buffer);
-			usbip_event_add(&vdev->ud, VDEV_EVENT_ERROR_TCP);
-			return -1;
-		}
-
-		kfree(iso_buffer);
-		usbip_dbg_vhci_tx("send txdata\n");
-
-		total_size += txsize;
-	}
-
-	return total_size;
-}
-
-static struct vhci_unlink *dequeue_from_unlink_tx(struct vhci_device *vdev)
-{
-	struct vhci_unlink *unlink, *tmp;
-
-	spin_lock(&vdev->priv_lock);
-
-	list_for_each_entry_safe(unlink, tmp, &vdev->unlink_tx, list) {
-		list_move_tail(&unlink->list, &vdev->unlink_rx);
-		spin_unlock(&vdev->priv_lock);
-		return unlink;
-	}
-
-	spin_unlock(&vdev->priv_lock);
-
-	return NULL;
-}
-
-static int vhci_send_cmd_unlink(struct vhci_device *vdev)
-{
-	struct vhci_unlink *unlink = NULL;
-
-	struct msghdr msg;
-	struct kvec iov[3];
-	size_t txsize;
-
-	size_t total_size = 0;
-
-	while ((unlink = dequeue_from_unlink_tx(vdev)) != NULL) {
-		int ret;
-		struct usbip_header pdu_header;
-
-		txsize = 0;
-		memset(&pdu_header, 0, sizeof(pdu_header));
-		memset(&msg, 0, sizeof(msg));
-		memset(&iov, 0, sizeof(iov));
-
-		usbip_dbg_vhci_tx("setup cmd unlink, %lu\n", unlink->seqnum);
-
-		/* 1. setup usbip_header */
-		pdu_header.base.command = USBIP_CMD_UNLINK;
-		pdu_header.base.seqnum  = unlink->seqnum;
-		pdu_header.base.devid	= vdev->devid;
-		pdu_header.base.ep	= 0;
-		pdu_header.u.cmd_unlink.seqnum = unlink->unlink_seqnum;
-
-		usbip_header_correct_endian(&pdu_header, 1);
-
-		iov[0].iov_base = &pdu_header;
-		iov[0].iov_len  = sizeof(pdu_header);
-		txsize += sizeof(pdu_header);
-
-		ret = kernel_sendmsg(vdev->ud.tcp_socket, &msg, iov, 1, txsize);
-		if (ret != txsize) {
-			pr_err("sendmsg failed!, ret=%d for %zd\n", ret,
-			       txsize);
-			usbip_event_add(&vdev->ud, VDEV_EVENT_ERROR_TCP);
-			return -1;
-		}
-
-		usbip_dbg_vhci_tx("send txdata\n");
-
-		total_size += txsize;
-	}
-
-	return total_size;
-}
-
-int vhci_tx_loop(void *data)
-{
-	struct usbip_device *ud = data;
-	struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
-
-	while (!kthread_should_stop()) {
-		if (vhci_send_cmd_submit(vdev) < 0)
-			break;
-
-		if (vhci_send_cmd_unlink(vdev) < 0)
-			break;
-
-		wait_event_interruptible(vdev->waitq_tx,
-					 (!list_empty(&vdev->priv_tx) ||
-					  !list_empty(&vdev->unlink_tx) ||
-					  kthread_should_stop()));
-
-		usbip_dbg_vhci_tx("pending urbs ?, now wake up\n");
-	}
-
-	return 0;
-}
diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index e0cad4418085..cf1b19bca306 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -92,6 +92,8 @@ source "drivers/usb/storage/Kconfig"
 
 source "drivers/usb/image/Kconfig"
 
+source "drivers/usb/usbip/Kconfig"
+
 endif
 
 source "drivers/usb/musb/Kconfig"
diff --git a/drivers/usb/Makefile b/drivers/usb/Makefile
index 3cba892b83a2..d7be71778059 100644
--- a/drivers/usb/Makefile
+++ b/drivers/usb/Makefile
@@ -60,3 +60,5 @@ obj-$(CONFIG_USB_RENESAS_USBHS)	+= renesas_usbhs/
 obj-$(CONFIG_USB_GADGET)	+= gadget/
 
 obj-$(CONFIG_USB_COMMON)	+= common/
+
+obj-$(CONFIG_USBIP_CORE)	+= usbip/
diff --git a/drivers/usb/usbip/Kconfig b/drivers/usb/usbip/Kconfig
new file mode 100644
index 000000000000..bd99e9e47e50
--- /dev/null
+++ b/drivers/usb/usbip/Kconfig
@@ -0,0 +1,41 @@
+config USBIP_CORE
+	tristate "USB/IP support"
+	depends on USB && NET
+	---help---
+	  This enables pushing USB packets over IP to allow remote
+	  machines direct access to USB devices. It provides the
+	  USB/IP core that is required by both drivers.
+
+	  For more details, and to get the userspace utility
+	  programs, please see <http://usbip.sourceforge.net/>.
+
+	  To compile this as a module, choose M here: the module will
+	  be called usbip-core.
+
+	  If unsure, say N.
+
+config USBIP_VHCI_HCD
+	tristate "VHCI hcd"
+	depends on USBIP_CORE
+	---help---
+	  This enables the USB/IP virtual host controller driver,
+	  which is run on the remote machine.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called vhci-hcd.
+
+config USBIP_HOST
+	tristate "Host driver"
+	depends on USBIP_CORE
+	---help---
+	  This enables the USB/IP host driver, which is run on the
+	  machine that is sharing the USB devices.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called usbip-host.
+
+config USBIP_DEBUG
+	bool "Debug messages for USB/IP"
+	depends on USBIP_CORE
+	---help---
+	  This enables the debug messages from the USB/IP drivers.
diff --git a/drivers/usb/usbip/Makefile b/drivers/usb/usbip/Makefile
new file mode 100644
index 000000000000..9ecd61545be1
--- /dev/null
+++ b/drivers/usb/usbip/Makefile
@@ -0,0 +1,10 @@
+ccflags-$(CONFIG_USBIP_DEBUG) := -DDEBUG
+
+obj-$(CONFIG_USBIP_CORE) += usbip-core.o
+usbip-core-y := usbip_common.o usbip_event.o
+
+obj-$(CONFIG_USBIP_VHCI_HCD) += vhci-hcd.o
+vhci-hcd-y := vhci_sysfs.o vhci_tx.o vhci_rx.o vhci_hcd.o
+
+obj-$(CONFIG_USBIP_HOST) += usbip-host.o
+usbip-host-y := stub_dev.o stub_main.o stub_rx.o stub_tx.o
diff --git a/drivers/usb/usbip/README b/drivers/usb/usbip/README
new file mode 100644
index 000000000000..41a2cf2e77a6
--- /dev/null
+++ b/drivers/usb/usbip/README
@@ -0,0 +1,7 @@
+TODO:
+	- more discussion about the protocol
+	- testing
+	- review of the userspace interface
+	- document the protocol
+
+Please send patches for this code to Greg Kroah-Hartman <greg@kroah.com>
diff --git a/drivers/usb/usbip/stub.h b/drivers/usb/usbip/stub.h
new file mode 100644
index 000000000000..266e2b0ce9a8
--- /dev/null
+++ b/drivers/usb/usbip/stub.h
@@ -0,0 +1,113 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#ifndef __USBIP_STUB_H
+#define __USBIP_STUB_H
+
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+#include <linux/wait.h>
+
+#define STUB_BUSID_OTHER 0
+#define STUB_BUSID_REMOV 1
+#define STUB_BUSID_ADDED 2
+#define STUB_BUSID_ALLOC 3
+
+struct stub_device {
+	struct usb_interface *interface;
+	struct usb_device *udev;
+
+	struct usbip_device ud;
+	__u32 devid;
+
+	/*
+	 * stub_priv preserves private data of each urb.
+	 * It is allocated as stub_priv_cache and assigned to urb->context.
+	 *
+	 * stub_priv is always linked to any one of 3 lists;
+	 *	priv_init: linked to this until the comletion of a urb.
+	 *	priv_tx  : linked to this after the completion of a urb.
+	 *	priv_free: linked to this after the sending of the result.
+	 *
+	 * Any of these list operations should be locked by priv_lock.
+	 */
+	spinlock_t priv_lock;
+	struct list_head priv_init;
+	struct list_head priv_tx;
+	struct list_head priv_free;
+
+	/* see comments for unlinking in stub_rx.c */
+	struct list_head unlink_tx;
+	struct list_head unlink_free;
+
+	wait_queue_head_t tx_waitq;
+};
+
+/* private data into urb->priv */
+struct stub_priv {
+	unsigned long seqnum;
+	struct list_head list;
+	struct stub_device *sdev;
+	struct urb *urb;
+
+	int unlinking;
+};
+
+struct stub_unlink {
+	unsigned long seqnum;
+	struct list_head list;
+	__u32 status;
+};
+
+/* same as SYSFS_BUS_ID_SIZE */
+#define BUSID_SIZE 32
+
+struct bus_id_priv {
+	char name[BUSID_SIZE];
+	char status;
+	int interf_count;
+	struct stub_device *sdev;
+	struct usb_device *udev;
+	char shutdown_busid;
+};
+
+/* stub_priv is allocated from stub_priv_cache */
+extern struct kmem_cache *stub_priv_cache;
+
+/* stub_dev.c */
+extern struct usb_device_driver stub_driver;
+
+/* stub_main.c */
+struct bus_id_priv *get_busid_priv(const char *busid);
+int del_match_busid(char *busid);
+void stub_device_cleanup_urbs(struct stub_device *sdev);
+
+/* stub_rx.c */
+int stub_rx_loop(void *data);
+
+/* stub_tx.c */
+void stub_enqueue_ret_unlink(struct stub_device *sdev, __u32 seqnum,
+			     __u32 status);
+void stub_complete(struct urb *urb);
+int stub_tx_loop(void *data);
+
+#endif /* __USBIP_STUB_H */
diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
new file mode 100644
index 000000000000..51d0c7188738
--- /dev/null
+++ b/drivers/usb/usbip/stub_dev.c
@@ -0,0 +1,525 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+
+#include "usbip_common.h"
+#include "stub.h"
+
+/*
+ * Define device IDs here if you want to explicitly limit exportable devices.
+ * In most cases, wildcard matching will be okay because driver binding can be
+ * changed dynamically by a userland program.
+ */
+static struct usb_device_id stub_table[] = {
+#if 0
+	/* just an example */
+	{ USB_DEVICE(0x05ac, 0x0301) },   /* Mac 1 button mouse */
+	{ USB_DEVICE(0x0430, 0x0009) },   /* Plat Home Keyboard */
+	{ USB_DEVICE(0x059b, 0x0001) },   /* Iomega USB Zip 100 */
+	{ USB_DEVICE(0x04b3, 0x4427) },   /* IBM USB CD-ROM */
+	{ USB_DEVICE(0x05a9, 0xa511) },   /* LifeView USB cam */
+	{ USB_DEVICE(0x55aa, 0x0201) },   /* Imation card reader */
+	{ USB_DEVICE(0x046d, 0x0870) },   /* Qcam Express(QV-30) */
+	{ USB_DEVICE(0x04bb, 0x0101) },   /* IO-DATA HD 120GB */
+	{ USB_DEVICE(0x04bb, 0x0904) },   /* IO-DATA USB-ET/TX */
+	{ USB_DEVICE(0x04bb, 0x0201) },   /* IO-DATA USB-ET/TX */
+	{ USB_DEVICE(0x08bb, 0x2702) },   /* ONKYO USB Speaker */
+	{ USB_DEVICE(0x046d, 0x08b2) },   /* Logicool Qcam 4000 Pro */
+#endif
+	/* magic for wild card */
+	{ .driver_info = 1 },
+	{ 0, }                                     /* Terminating entry */
+};
+MODULE_DEVICE_TABLE(usb, stub_table);
+
+/*
+ * usbip_status shows the status of usbip-host as long as this driver is bound
+ * to the target device.
+ */
+static ssize_t usbip_status_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct stub_device *sdev = dev_get_drvdata(dev);
+	int status;
+
+	if (!sdev) {
+		dev_err(dev, "sdev is null\n");
+		return -ENODEV;
+	}
+
+	spin_lock_irq(&sdev->ud.lock);
+	status = sdev->ud.status;
+	spin_unlock_irq(&sdev->ud.lock);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", status);
+}
+static DEVICE_ATTR_RO(usbip_status);
+
+/*
+ * usbip_sockfd gets a socket descriptor of an established TCP connection that
+ * is used to transfer usbip requests by kernel threads. -1 is a magic number
+ * by which usbip connection is finished.
+ */
+static ssize_t store_sockfd(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	struct stub_device *sdev = dev_get_drvdata(dev);
+	int sockfd = 0;
+	struct socket *socket;
+	int rv;
+
+	if (!sdev) {
+		dev_err(dev, "sdev is null\n");
+		return -ENODEV;
+	}
+
+	rv = sscanf(buf, "%d", &sockfd);
+	if (rv != 1)
+		return -EINVAL;
+
+	if (sockfd != -1) {
+		int err;
+
+		dev_info(dev, "stub up\n");
+
+		spin_lock_irq(&sdev->ud.lock);
+
+		if (sdev->ud.status != SDEV_ST_AVAILABLE) {
+			dev_err(dev, "not ready\n");
+			goto err;
+		}
+
+		socket = sockfd_lookup(sockfd, &err);
+		if (!socket)
+			goto err;
+
+		sdev->ud.tcp_socket = socket;
+
+		spin_unlock_irq(&sdev->ud.lock);
+
+		sdev->ud.tcp_rx = kthread_get_run(stub_rx_loop, &sdev->ud,
+						  "stub_rx");
+		sdev->ud.tcp_tx = kthread_get_run(stub_tx_loop, &sdev->ud,
+						  "stub_tx");
+
+		spin_lock_irq(&sdev->ud.lock);
+		sdev->ud.status = SDEV_ST_USED;
+		spin_unlock_irq(&sdev->ud.lock);
+
+	} else {
+		dev_info(dev, "stub down\n");
+
+		spin_lock_irq(&sdev->ud.lock);
+		if (sdev->ud.status != SDEV_ST_USED)
+			goto err;
+
+		spin_unlock_irq(&sdev->ud.lock);
+
+		usbip_event_add(&sdev->ud, SDEV_EVENT_DOWN);
+	}
+
+	return count;
+
+err:
+	spin_unlock_irq(&sdev->ud.lock);
+	return -EINVAL;
+}
+static DEVICE_ATTR(usbip_sockfd, S_IWUSR, NULL, store_sockfd);
+
+static int stub_add_files(struct device *dev)
+{
+	int err = 0;
+
+	err = device_create_file(dev, &dev_attr_usbip_status);
+	if (err)
+		goto err_status;
+
+	err = device_create_file(dev, &dev_attr_usbip_sockfd);
+	if (err)
+		goto err_sockfd;
+
+	err = device_create_file(dev, &dev_attr_usbip_debug);
+	if (err)
+		goto err_debug;
+
+	return 0;
+
+err_debug:
+	device_remove_file(dev, &dev_attr_usbip_sockfd);
+err_sockfd:
+	device_remove_file(dev, &dev_attr_usbip_status);
+err_status:
+	return err;
+}
+
+static void stub_remove_files(struct device *dev)
+{
+	device_remove_file(dev, &dev_attr_usbip_status);
+	device_remove_file(dev, &dev_attr_usbip_sockfd);
+	device_remove_file(dev, &dev_attr_usbip_debug);
+}
+
+static void stub_shutdown_connection(struct usbip_device *ud)
+{
+	struct stub_device *sdev = container_of(ud, struct stub_device, ud);
+
+	/*
+	 * When removing an exported device, kernel panic sometimes occurred
+	 * and then EIP was sk_wait_data of stub_rx thread. Is this because
+	 * sk_wait_data returned though stub_rx thread was already finished by
+	 * step 1?
+	 */
+	if (ud->tcp_socket) {
+		dev_dbg(&sdev->udev->dev, "shutdown tcp_socket %p\n",
+			ud->tcp_socket);
+		kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
+	}
+
+	/* 1. stop threads */
+	if (ud->tcp_rx) {
+		kthread_stop_put(ud->tcp_rx);
+		ud->tcp_rx = NULL;
+	}
+	if (ud->tcp_tx) {
+		kthread_stop_put(ud->tcp_tx);
+		ud->tcp_tx = NULL;
+	}
+
+	/*
+	 * 2. close the socket
+	 *
+	 * tcp_socket is freed after threads are killed so that usbip_xmit does
+	 * not touch NULL socket.
+	 */
+	if (ud->tcp_socket) {
+		sockfd_put(ud->tcp_socket);
+		ud->tcp_socket = NULL;
+	}
+
+	/* 3. free used data */
+	stub_device_cleanup_urbs(sdev);
+
+	/* 4. free stub_unlink */
+	{
+		unsigned long flags;
+		struct stub_unlink *unlink, *tmp;
+
+		spin_lock_irqsave(&sdev->priv_lock, flags);
+		list_for_each_entry_safe(unlink, tmp, &sdev->unlink_tx, list) {
+			list_del(&unlink->list);
+			kfree(unlink);
+		}
+		list_for_each_entry_safe(unlink, tmp, &sdev->unlink_free,
+					 list) {
+			list_del(&unlink->list);
+			kfree(unlink);
+		}
+		spin_unlock_irqrestore(&sdev->priv_lock, flags);
+	}
+}
+
+static void stub_device_reset(struct usbip_device *ud)
+{
+	struct stub_device *sdev = container_of(ud, struct stub_device, ud);
+	struct usb_device *udev = sdev->udev;
+	int ret;
+
+	dev_dbg(&udev->dev, "device reset");
+
+	ret = usb_lock_device_for_reset(udev, sdev->interface);
+	if (ret < 0) {
+		dev_err(&udev->dev, "lock for reset\n");
+		spin_lock_irq(&ud->lock);
+		ud->status = SDEV_ST_ERROR;
+		spin_unlock_irq(&ud->lock);
+		return;
+	}
+
+	/* try to reset the device */
+	ret = usb_reset_device(udev);
+	usb_unlock_device(udev);
+
+	spin_lock_irq(&ud->lock);
+	if (ret) {
+		dev_err(&udev->dev, "device reset\n");
+		ud->status = SDEV_ST_ERROR;
+	} else {
+		dev_info(&udev->dev, "device reset\n");
+		ud->status = SDEV_ST_AVAILABLE;
+	}
+	spin_unlock_irq(&ud->lock);
+}
+
+static void stub_device_unusable(struct usbip_device *ud)
+{
+	spin_lock_irq(&ud->lock);
+	ud->status = SDEV_ST_ERROR;
+	spin_unlock_irq(&ud->lock);
+}
+
+/**
+ * stub_device_alloc - allocate a new stub_device struct
+ * @interface: usb_interface of a new device
+ *
+ * Allocates and initializes a new stub_device struct.
+ */
+static struct stub_device *stub_device_alloc(struct usb_device *udev)
+{
+	struct stub_device *sdev;
+	int busnum = udev->bus->busnum;
+	int devnum = udev->devnum;
+
+	dev_dbg(&udev->dev, "allocating stub device");
+
+	/* yes, it's a new device */
+	sdev = kzalloc(sizeof(struct stub_device), GFP_KERNEL);
+	if (!sdev)
+		return NULL;
+
+	sdev->udev = usb_get_dev(udev);
+
+	/*
+	 * devid is defined with devnum when this driver is first allocated.
+	 * devnum may change later if a device is reset. However, devid never
+	 * changes during a usbip connection.
+	 */
+	sdev->devid		= (busnum << 16) | devnum;
+	sdev->ud.side		= USBIP_STUB;
+	sdev->ud.status		= SDEV_ST_AVAILABLE;
+	spin_lock_init(&sdev->ud.lock);
+	sdev->ud.tcp_socket	= NULL;
+
+	INIT_LIST_HEAD(&sdev->priv_init);
+	INIT_LIST_HEAD(&sdev->priv_tx);
+	INIT_LIST_HEAD(&sdev->priv_free);
+	INIT_LIST_HEAD(&sdev->unlink_free);
+	INIT_LIST_HEAD(&sdev->unlink_tx);
+	spin_lock_init(&sdev->priv_lock);
+
+	init_waitqueue_head(&sdev->tx_waitq);
+
+	sdev->ud.eh_ops.shutdown = stub_shutdown_connection;
+	sdev->ud.eh_ops.reset    = stub_device_reset;
+	sdev->ud.eh_ops.unusable = stub_device_unusable;
+
+	usbip_start_eh(&sdev->ud);
+
+	dev_dbg(&udev->dev, "register new device\n");
+
+	return sdev;
+}
+
+static void stub_device_free(struct stub_device *sdev)
+{
+	kfree(sdev);
+}
+
+static int stub_probe(struct usb_device *udev)
+{
+	struct stub_device *sdev = NULL;
+	const char *udev_busid = dev_name(&udev->dev);
+	int err = 0;
+	struct bus_id_priv *busid_priv;
+	int rc;
+
+	dev_dbg(&udev->dev, "Enter\n");
+
+	/* check we should claim or not by busid_table */
+	busid_priv = get_busid_priv(udev_busid);
+	if (!busid_priv || (busid_priv->status == STUB_BUSID_REMOV) ||
+	    (busid_priv->status == STUB_BUSID_OTHER)) {
+		dev_info(&udev->dev,
+			"%s is not in match_busid table... skip!\n",
+			udev_busid);
+
+		/*
+		 * Return value should be ENODEV or ENOXIO to continue trying
+		 * other matched drivers by the driver core.
+		 * See driver_probe_device() in driver/base/dd.c
+		 */
+		return -ENODEV;
+	}
+
+	if (udev->descriptor.bDeviceClass == USB_CLASS_HUB) {
+		dev_dbg(&udev->dev, "%s is a usb hub device... skip!\n",
+			 udev_busid);
+		return -ENODEV;
+	}
+
+	if (!strcmp(udev->bus->bus_name, "vhci_hcd")) {
+		dev_dbg(&udev->dev,
+			"%s is attached on vhci_hcd... skip!\n",
+			udev_busid);
+
+		return -ENODEV;
+	}
+
+	/* ok, this is my device */
+	sdev = stub_device_alloc(udev);
+	if (!sdev)
+		return -ENOMEM;
+
+	dev_info(&udev->dev,
+		"usbip-host: register new device (bus %u dev %u)\n",
+		udev->bus->busnum, udev->devnum);
+
+	busid_priv->shutdown_busid = 0;
+
+	/* set private data to usb_device */
+	dev_set_drvdata(&udev->dev, sdev);
+	busid_priv->sdev = sdev;
+	busid_priv->udev = udev;
+
+	/*
+	 * Claim this hub port.
+	 * It doesn't matter what value we pass as owner
+	 * (struct dev_state) as long as it is unique.
+	 */
+	rc = usb_hub_claim_port(udev->parent, udev->portnum,
+			(struct usb_dev_state *) udev);
+	if (rc) {
+		dev_dbg(&udev->dev, "unable to claim port\n");
+		return rc;
+	}
+
+	err = stub_add_files(&udev->dev);
+	if (err) {
+		dev_err(&udev->dev, "stub_add_files for %s\n", udev_busid);
+		dev_set_drvdata(&udev->dev, NULL);
+		usb_put_dev(udev);
+		kthread_stop_put(sdev->ud.eh);
+
+		busid_priv->sdev = NULL;
+		stub_device_free(sdev);
+		return err;
+	}
+	busid_priv->status = STUB_BUSID_ALLOC;
+
+	return 0;
+}
+
+static void shutdown_busid(struct bus_id_priv *busid_priv)
+{
+	if (busid_priv->sdev && !busid_priv->shutdown_busid) {
+		busid_priv->shutdown_busid = 1;
+		usbip_event_add(&busid_priv->sdev->ud, SDEV_EVENT_REMOVED);
+
+		/* wait for the stop of the event handler */
+		usbip_stop_eh(&busid_priv->sdev->ud);
+	}
+}
+
+/*
+ * called in usb_disconnect() or usb_deregister()
+ * but only if actconfig(active configuration) exists
+ */
+static void stub_disconnect(struct usb_device *udev)
+{
+	struct stub_device *sdev;
+	const char *udev_busid = dev_name(&udev->dev);
+	struct bus_id_priv *busid_priv;
+	int rc;
+
+	dev_dbg(&udev->dev, "Enter\n");
+
+	busid_priv = get_busid_priv(udev_busid);
+	if (!busid_priv) {
+		BUG();
+		return;
+	}
+
+	sdev = dev_get_drvdata(&udev->dev);
+
+	/* get stub_device */
+	if (!sdev) {
+		dev_err(&udev->dev, "could not get device");
+		return;
+	}
+
+	dev_set_drvdata(&udev->dev, NULL);
+
+	/*
+	 * NOTE: rx/tx threads are invoked for each usb_device.
+	 */
+	stub_remove_files(&udev->dev);
+
+	/* release port */
+	rc = usb_hub_release_port(udev->parent, udev->portnum,
+				  (struct usb_dev_state *) udev);
+	if (rc) {
+		dev_dbg(&udev->dev, "unable to release port\n");
+		return;
+	}
+
+	/* If usb reset is called from event handler */
+	if (busid_priv->sdev->ud.eh == current)
+		return;
+
+	/* shutdown the current connection */
+	shutdown_busid(busid_priv);
+
+	usb_put_dev(sdev->udev);
+
+	/* free sdev */
+	busid_priv->sdev = NULL;
+	stub_device_free(sdev);
+
+	if (busid_priv->status == STUB_BUSID_ALLOC) {
+		busid_priv->status = STUB_BUSID_ADDED;
+	} else {
+		busid_priv->status = STUB_BUSID_OTHER;
+		del_match_busid((char *)udev_busid);
+	}
+}
+
+#ifdef CONFIG_PM
+
+/* These functions need usb_port_suspend and usb_port_resume,
+ * which reside in drivers/usb/core/usb.h. Skip for now. */
+
+static int stub_suspend(struct usb_device *udev, pm_message_t message)
+{
+	dev_dbg(&udev->dev, "stub_suspend\n");
+
+	return 0;
+}
+
+static int stub_resume(struct usb_device *udev, pm_message_t message)
+{
+	dev_dbg(&udev->dev, "stub_resume\n");
+
+	return 0;
+}
+
+#endif	/* CONFIG_PM */
+
+struct usb_device_driver stub_driver = {
+	.name		= "usbip-host",
+	.probe		= stub_probe,
+	.disconnect	= stub_disconnect,
+#ifdef CONFIG_PM
+	.suspend	= stub_suspend,
+	.resume		= stub_resume,
+#endif
+	.supports_autosuspend	=	0,
+};
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
new file mode 100644
index 000000000000..44ab43fc4fcc
--- /dev/null
+++ b/drivers/usb/usbip/stub_main.c
@@ -0,0 +1,335 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/device.h>
+
+#include "usbip_common.h"
+#include "stub.h"
+
+#define DRIVER_AUTHOR "Takahiro Hirofuchi"
+#define DRIVER_DESC "USB/IP Host Driver"
+
+struct kmem_cache *stub_priv_cache;
+/*
+ * busid_tables defines matching busids that usbip can grab. A user can change
+ * dynamically what device is locally used and what device is exported to a
+ * remote host.
+ */
+#define MAX_BUSID 16
+static struct bus_id_priv busid_table[MAX_BUSID];
+static spinlock_t busid_table_lock;
+
+static void init_busid_table(void)
+{
+	/*
+	 * This also sets the bus_table[i].status to
+	 * STUB_BUSID_OTHER, which is 0.
+	 */
+	memset(busid_table, 0, sizeof(busid_table));
+
+	spin_lock_init(&busid_table_lock);
+}
+
+/*
+ * Find the index of the busid by name.
+ * Must be called with busid_table_lock held.
+ */
+static int get_busid_idx(const char *busid)
+{
+	int i;
+	int idx = -1;
+
+	for (i = 0; i < MAX_BUSID; i++)
+		if (busid_table[i].name[0])
+			if (!strncmp(busid_table[i].name, busid, BUSID_SIZE)) {
+				idx = i;
+				break;
+			}
+	return idx;
+}
+
+struct bus_id_priv *get_busid_priv(const char *busid)
+{
+	int idx;
+	struct bus_id_priv *bid = NULL;
+
+	spin_lock(&busid_table_lock);
+	idx = get_busid_idx(busid);
+	if (idx >= 0)
+		bid = &(busid_table[idx]);
+	spin_unlock(&busid_table_lock);
+
+	return bid;
+}
+
+static int add_match_busid(char *busid)
+{
+	int i;
+	int ret = -1;
+
+	spin_lock(&busid_table_lock);
+	/* already registered? */
+	if (get_busid_idx(busid) >= 0) {
+		ret = 0;
+		goto out;
+	}
+
+	for (i = 0; i < MAX_BUSID; i++)
+		if (!busid_table[i].name[0]) {
+			strlcpy(busid_table[i].name, busid, BUSID_SIZE);
+			if ((busid_table[i].status != STUB_BUSID_ALLOC) &&
+			    (busid_table[i].status != STUB_BUSID_REMOV))
+				busid_table[i].status = STUB_BUSID_ADDED;
+			ret = 0;
+			break;
+		}
+
+out:
+	spin_unlock(&busid_table_lock);
+
+	return ret;
+}
+
+int del_match_busid(char *busid)
+{
+	int idx;
+	int ret = -1;
+
+	spin_lock(&busid_table_lock);
+	idx = get_busid_idx(busid);
+	if (idx < 0)
+		goto out;
+
+	/* found */
+	ret = 0;
+
+	if (busid_table[idx].status == STUB_BUSID_OTHER)
+		memset(busid_table[idx].name, 0, BUSID_SIZE);
+
+	if ((busid_table[idx].status != STUB_BUSID_OTHER) &&
+	    (busid_table[idx].status != STUB_BUSID_ADDED))
+		busid_table[idx].status = STUB_BUSID_REMOV;
+
+out:
+	spin_unlock(&busid_table_lock);
+
+	return ret;
+}
+
+static ssize_t show_match_busid(struct device_driver *drv, char *buf)
+{
+	int i;
+	char *out = buf;
+
+	spin_lock(&busid_table_lock);
+	for (i = 0; i < MAX_BUSID; i++)
+		if (busid_table[i].name[0])
+			out += sprintf(out, "%s ", busid_table[i].name);
+	spin_unlock(&busid_table_lock);
+	out += sprintf(out, "\n");
+
+	return out - buf;
+}
+
+static ssize_t store_match_busid(struct device_driver *dev, const char *buf,
+				 size_t count)
+{
+	int len;
+	char busid[BUSID_SIZE];
+
+	if (count < 5)
+		return -EINVAL;
+
+	/* busid needs to include \0 termination */
+	len = strlcpy(busid, buf + 4, BUSID_SIZE);
+	if (sizeof(busid) <= len)
+		return -EINVAL;
+
+	if (!strncmp(buf, "add ", 4)) {
+		if (add_match_busid(busid) < 0)
+			return -ENOMEM;
+
+		pr_debug("add busid %s\n", busid);
+		return count;
+	}
+
+	if (!strncmp(buf, "del ", 4)) {
+		if (del_match_busid(busid) < 0)
+			return -ENODEV;
+
+		pr_debug("del busid %s\n", busid);
+		return count;
+	}
+
+	return -EINVAL;
+}
+static DRIVER_ATTR(match_busid, S_IRUSR | S_IWUSR, show_match_busid,
+		   store_match_busid);
+
+static ssize_t rebind_store(struct device_driver *dev, const char *buf,
+				 size_t count)
+{
+	int ret;
+	int len;
+	struct bus_id_priv *bid;
+
+	/* buf length should be less that BUSID_SIZE */
+	len = strnlen(buf, BUSID_SIZE);
+
+	if (!(len < BUSID_SIZE))
+		return -EINVAL;
+
+	bid = get_busid_priv(buf);
+	if (!bid)
+		return -ENODEV;
+
+	ret = device_attach(&bid->udev->dev);
+	if (ret < 0) {
+		dev_err(&bid->udev->dev, "rebind failed\n");
+		return ret;
+	}
+
+	return count;
+}
+
+static DRIVER_ATTR_WO(rebind);
+
+static struct stub_priv *stub_priv_pop_from_listhead(struct list_head *listhead)
+{
+	struct stub_priv *priv, *tmp;
+
+	list_for_each_entry_safe(priv, tmp, listhead, list) {
+		list_del(&priv->list);
+		return priv;
+	}
+
+	return NULL;
+}
+
+static struct stub_priv *stub_priv_pop(struct stub_device *sdev)
+{
+	unsigned long flags;
+	struct stub_priv *priv;
+
+	spin_lock_irqsave(&sdev->priv_lock, flags);
+
+	priv = stub_priv_pop_from_listhead(&sdev->priv_init);
+	if (priv)
+		goto done;
+
+	priv = stub_priv_pop_from_listhead(&sdev->priv_tx);
+	if (priv)
+		goto done;
+
+	priv = stub_priv_pop_from_listhead(&sdev->priv_free);
+
+done:
+	spin_unlock_irqrestore(&sdev->priv_lock, flags);
+
+	return priv;
+}
+
+void stub_device_cleanup_urbs(struct stub_device *sdev)
+{
+	struct stub_priv *priv;
+	struct urb *urb;
+
+	dev_dbg(&sdev->udev->dev, "free sdev %p\n", sdev);
+
+	while ((priv = stub_priv_pop(sdev))) {
+		urb = priv->urb;
+		dev_dbg(&sdev->udev->dev, "free urb %p\n", urb);
+		usb_kill_urb(urb);
+
+		kmem_cache_free(stub_priv_cache, priv);
+
+		kfree(urb->transfer_buffer);
+		kfree(urb->setup_packet);
+		usb_free_urb(urb);
+	}
+}
+
+static int __init usbip_host_init(void)
+{
+	int ret;
+
+	init_busid_table();
+
+	stub_priv_cache = KMEM_CACHE(stub_priv, SLAB_HWCACHE_ALIGN);
+	if (!stub_priv_cache) {
+		pr_err("kmem_cache_create failed\n");
+		return -ENOMEM;
+	}
+
+	ret = usb_register_device_driver(&stub_driver, THIS_MODULE);
+	if (ret) {
+		pr_err("usb_register failed %d\n", ret);
+		goto err_usb_register;
+	}
+
+	ret = driver_create_file(&stub_driver.drvwrap.driver,
+				 &driver_attr_match_busid);
+	if (ret) {
+		pr_err("driver_create_file failed\n");
+		goto err_create_file;
+	}
+
+	ret = driver_create_file(&stub_driver.drvwrap.driver,
+				 &driver_attr_rebind);
+	if (ret) {
+		pr_err("driver_create_file failed\n");
+		goto err_create_file;
+	}
+
+	pr_info(DRIVER_DESC " v" USBIP_VERSION "\n");
+	return ret;
+
+err_create_file:
+	usb_deregister_device_driver(&stub_driver);
+err_usb_register:
+	kmem_cache_destroy(stub_priv_cache);
+	return ret;
+}
+
+static void __exit usbip_host_exit(void)
+{
+	driver_remove_file(&stub_driver.drvwrap.driver,
+			   &driver_attr_match_busid);
+
+	driver_remove_file(&stub_driver.drvwrap.driver,
+			   &driver_attr_rebind);
+
+	/*
+	 * deregister() calls stub_disconnect() for all devices. Device
+	 * specific data is cleared in stub_disconnect().
+	 */
+	usb_deregister_device_driver(&stub_driver);
+
+	kmem_cache_destroy(stub_priv_cache);
+}
+
+module_init(usbip_host_init);
+module_exit(usbip_host_exit);
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+MODULE_VERSION(USBIP_VERSION);
diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
new file mode 100644
index 000000000000..00e475c51a12
--- /dev/null
+++ b/drivers/usb/usbip/stub_rx.c
@@ -0,0 +1,594 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <asm/byteorder.h>
+#include <linux/kthread.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
+
+#include "usbip_common.h"
+#include "stub.h"
+
+static int is_clear_halt_cmd(struct urb *urb)
+{
+	struct usb_ctrlrequest *req;
+
+	req = (struct usb_ctrlrequest *) urb->setup_packet;
+
+	 return (req->bRequest == USB_REQ_CLEAR_FEATURE) &&
+		 (req->bRequestType == USB_RECIP_ENDPOINT) &&
+		 (req->wValue == USB_ENDPOINT_HALT);
+}
+
+static int is_set_interface_cmd(struct urb *urb)
+{
+	struct usb_ctrlrequest *req;
+
+	req = (struct usb_ctrlrequest *) urb->setup_packet;
+
+	return (req->bRequest == USB_REQ_SET_INTERFACE) &&
+		(req->bRequestType == USB_RECIP_INTERFACE);
+}
+
+static int is_set_configuration_cmd(struct urb *urb)
+{
+	struct usb_ctrlrequest *req;
+
+	req = (struct usb_ctrlrequest *) urb->setup_packet;
+
+	return (req->bRequest == USB_REQ_SET_CONFIGURATION) &&
+		(req->bRequestType == USB_RECIP_DEVICE);
+}
+
+static int is_reset_device_cmd(struct urb *urb)
+{
+	struct usb_ctrlrequest *req;
+	__u16 value;
+	__u16 index;
+
+	req = (struct usb_ctrlrequest *) urb->setup_packet;
+	value = le16_to_cpu(req->wValue);
+	index = le16_to_cpu(req->wIndex);
+
+	if ((req->bRequest == USB_REQ_SET_FEATURE) &&
+	    (req->bRequestType == USB_RT_PORT) &&
+	    (value == USB_PORT_FEAT_RESET)) {
+		usbip_dbg_stub_rx("reset_device_cmd, port %u\n", index);
+		return 1;
+	} else
+		return 0;
+}
+
+static int tweak_clear_halt_cmd(struct urb *urb)
+{
+	struct usb_ctrlrequest *req;
+	int target_endp;
+	int target_dir;
+	int target_pipe;
+	int ret;
+
+	req = (struct usb_ctrlrequest *) urb->setup_packet;
+
+	/*
+	 * The stalled endpoint is specified in the wIndex value. The endpoint
+	 * of the urb is the target of this clear_halt request (i.e., control
+	 * endpoint).
+	 */
+	target_endp = le16_to_cpu(req->wIndex) & 0x000f;
+
+	/* the stalled endpoint direction is IN or OUT?. USB_DIR_IN is 0x80.  */
+	target_dir = le16_to_cpu(req->wIndex) & 0x0080;
+
+	if (target_dir)
+		target_pipe = usb_rcvctrlpipe(urb->dev, target_endp);
+	else
+		target_pipe = usb_sndctrlpipe(urb->dev, target_endp);
+
+	ret = usb_clear_halt(urb->dev, target_pipe);
+	if (ret < 0)
+		dev_err(&urb->dev->dev,
+			"usb_clear_halt error: devnum %d endp %d ret %d\n",
+			urb->dev->devnum, target_endp, ret);
+	else
+		dev_info(&urb->dev->dev,
+			 "usb_clear_halt done: devnum %d endp %d\n",
+			 urb->dev->devnum, target_endp);
+
+	return ret;
+}
+
+static int tweak_set_interface_cmd(struct urb *urb)
+{
+	struct usb_ctrlrequest *req;
+	__u16 alternate;
+	__u16 interface;
+	int ret;
+
+	req = (struct usb_ctrlrequest *) urb->setup_packet;
+	alternate = le16_to_cpu(req->wValue);
+	interface = le16_to_cpu(req->wIndex);
+
+	usbip_dbg_stub_rx("set_interface: inf %u alt %u\n",
+			  interface, alternate);
+
+	ret = usb_set_interface(urb->dev, interface, alternate);
+	if (ret < 0)
+		dev_err(&urb->dev->dev,
+			"usb_set_interface error: inf %u alt %u ret %d\n",
+			interface, alternate, ret);
+	else
+		dev_info(&urb->dev->dev,
+			"usb_set_interface done: inf %u alt %u\n",
+			interface, alternate);
+
+	return ret;
+}
+
+static int tweak_set_configuration_cmd(struct urb *urb)
+{
+	struct stub_priv *priv = (struct stub_priv *) urb->context;
+	struct stub_device *sdev = priv->sdev;
+	struct usb_ctrlrequest *req;
+	__u16 config;
+	int err;
+
+	req = (struct usb_ctrlrequest *) urb->setup_packet;
+	config = le16_to_cpu(req->wValue);
+
+	err = usb_set_configuration(sdev->udev, config);
+	if (err && err != -ENODEV)
+		dev_err(&sdev->udev->dev, "can't set config #%d, error %d\n",
+			config, err);
+	return 0;
+}
+
+static int tweak_reset_device_cmd(struct urb *urb)
+{
+	struct stub_priv *priv = (struct stub_priv *) urb->context;
+	struct stub_device *sdev = priv->sdev;
+
+	dev_info(&urb->dev->dev, "usb_queue_reset_device\n");
+
+	/*
+	 * With the implementation of pre_reset and post_reset the driver no
+	 * longer unbinds. This allows the use of synchronous reset.
+	 */
+
+	if (usb_lock_device_for_reset(sdev->udev, sdev->interface) < 0) {
+		dev_err(&urb->dev->dev, "could not obtain lock to reset device\n");
+		return 0;
+	}
+	usb_reset_device(sdev->udev);
+	usb_unlock_device(sdev->udev);
+
+	return 0;
+}
+
+/*
+ * clear_halt, set_interface, and set_configuration require special tricks.
+ */
+static void tweak_special_requests(struct urb *urb)
+{
+	if (!urb || !urb->setup_packet)
+		return;
+
+	if (usb_pipetype(urb->pipe) != PIPE_CONTROL)
+		return;
+
+	if (is_clear_halt_cmd(urb))
+		/* tweak clear_halt */
+		 tweak_clear_halt_cmd(urb);
+
+	else if (is_set_interface_cmd(urb))
+		/* tweak set_interface */
+		tweak_set_interface_cmd(urb);
+
+	else if (is_set_configuration_cmd(urb))
+		/* tweak set_configuration */
+		tweak_set_configuration_cmd(urb);
+
+	else if (is_reset_device_cmd(urb))
+		tweak_reset_device_cmd(urb);
+	else
+		usbip_dbg_stub_rx("no need to tweak\n");
+}
+
+/*
+ * stub_recv_unlink() unlinks the URB by a call to usb_unlink_urb().
+ * By unlinking the urb asynchronously, stub_rx can continuously
+ * process coming urbs.  Even if the urb is unlinked, its completion
+ * handler will be called and stub_tx will send a return pdu.
+ *
+ * See also comments about unlinking strategy in vhci_hcd.c.
+ */
+static int stub_recv_cmd_unlink(struct stub_device *sdev,
+				struct usbip_header *pdu)
+{
+	int ret;
+	unsigned long flags;
+	struct stub_priv *priv;
+
+	spin_lock_irqsave(&sdev->priv_lock, flags);
+
+	list_for_each_entry(priv, &sdev->priv_init, list) {
+		if (priv->seqnum != pdu->u.cmd_unlink.seqnum)
+			continue;
+
+		dev_info(&priv->urb->dev->dev, "unlink urb %p\n",
+			 priv->urb);
+
+		/*
+		 * This matched urb is not completed yet (i.e., be in
+		 * flight in usb hcd hardware/driver). Now we are
+		 * cancelling it. The unlinking flag means that we are
+		 * now not going to return the normal result pdu of a
+		 * submission request, but going to return a result pdu
+		 * of the unlink request.
+		 */
+		priv->unlinking = 1;
+
+		/*
+		 * In the case that unlinking flag is on, prev->seqnum
+		 * is changed from the seqnum of the cancelling urb to
+		 * the seqnum of the unlink request. This will be used
+		 * to make the result pdu of the unlink request.
+		 */
+		priv->seqnum = pdu->base.seqnum;
+
+		spin_unlock_irqrestore(&sdev->priv_lock, flags);
+
+		/*
+		 * usb_unlink_urb() is now out of spinlocking to avoid
+		 * spinlock recursion since stub_complete() is
+		 * sometimes called in this context but not in the
+		 * interrupt context.  If stub_complete() is executed
+		 * before we call usb_unlink_urb(), usb_unlink_urb()
+		 * will return an error value. In this case, stub_tx
+		 * will return the result pdu of this unlink request
+		 * though submission is completed and actual unlinking
+		 * is not executed. OK?
+		 */
+		/* In the above case, urb->status is not -ECONNRESET,
+		 * so a driver in a client host will know the failure
+		 * of the unlink request ?
+		 */
+		ret = usb_unlink_urb(priv->urb);
+		if (ret != -EINPROGRESS)
+			dev_err(&priv->urb->dev->dev,
+				"failed to unlink a urb %p, ret %d\n",
+				priv->urb, ret);
+
+		return 0;
+	}
+
+	usbip_dbg_stub_rx("seqnum %d is not pending\n",
+			  pdu->u.cmd_unlink.seqnum);
+
+	/*
+	 * The urb of the unlink target is not found in priv_init queue. It was
+	 * already completed and its results is/was going to be sent by a
+	 * CMD_RET pdu. In this case, usb_unlink_urb() is not needed. We only
+	 * return the completeness of this unlink request to vhci_hcd.
+	 */
+	stub_enqueue_ret_unlink(sdev, pdu->base.seqnum, 0);
+
+	spin_unlock_irqrestore(&sdev->priv_lock, flags);
+
+	return 0;
+}
+
+static int valid_request(struct stub_device *sdev, struct usbip_header *pdu)
+{
+	struct usbip_device *ud = &sdev->ud;
+	int valid = 0;
+
+	if (pdu->base.devid == sdev->devid) {
+		spin_lock_irq(&ud->lock);
+		if (ud->status == SDEV_ST_USED) {
+			/* A request is valid. */
+			valid = 1;
+		}
+		spin_unlock_irq(&ud->lock);
+	}
+
+	return valid;
+}
+
+static struct stub_priv *stub_priv_alloc(struct stub_device *sdev,
+					 struct usbip_header *pdu)
+{
+	struct stub_priv *priv;
+	struct usbip_device *ud = &sdev->ud;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sdev->priv_lock, flags);
+
+	priv = kmem_cache_zalloc(stub_priv_cache, GFP_ATOMIC);
+	if (!priv) {
+		dev_err(&sdev->interface->dev, "alloc stub_priv\n");
+		spin_unlock_irqrestore(&sdev->priv_lock, flags);
+		usbip_event_add(ud, SDEV_EVENT_ERROR_MALLOC);
+		return NULL;
+	}
+
+	priv->seqnum = pdu->base.seqnum;
+	priv->sdev = sdev;
+
+	/*
+	 * After a stub_priv is linked to a list_head,
+	 * our error handler can free allocated data.
+	 */
+	list_add_tail(&priv->list, &sdev->priv_init);
+
+	spin_unlock_irqrestore(&sdev->priv_lock, flags);
+
+	return priv;
+}
+
+static int get_pipe(struct stub_device *sdev, int epnum, int dir)
+{
+	struct usb_device *udev = sdev->udev;
+	struct usb_host_endpoint *ep;
+	struct usb_endpoint_descriptor *epd = NULL;
+
+	if (dir == USBIP_DIR_IN)
+		ep = udev->ep_in[epnum & 0x7f];
+	else
+		ep = udev->ep_out[epnum & 0x7f];
+	if (!ep) {
+		dev_err(&sdev->interface->dev, "no such endpoint?, %d\n",
+			epnum);
+		BUG();
+	}
+
+	epd = &ep->desc;
+	if (usb_endpoint_xfer_control(epd)) {
+		if (dir == USBIP_DIR_OUT)
+			return usb_sndctrlpipe(udev, epnum);
+		else
+			return usb_rcvctrlpipe(udev, epnum);
+	}
+
+	if (usb_endpoint_xfer_bulk(epd)) {
+		if (dir == USBIP_DIR_OUT)
+			return usb_sndbulkpipe(udev, epnum);
+		else
+			return usb_rcvbulkpipe(udev, epnum);
+	}
+
+	if (usb_endpoint_xfer_int(epd)) {
+		if (dir == USBIP_DIR_OUT)
+			return usb_sndintpipe(udev, epnum);
+		else
+			return usb_rcvintpipe(udev, epnum);
+	}
+
+	if (usb_endpoint_xfer_isoc(epd)) {
+		if (dir == USBIP_DIR_OUT)
+			return usb_sndisocpipe(udev, epnum);
+		else
+			return usb_rcvisocpipe(udev, epnum);
+	}
+
+	/* NOT REACHED */
+	dev_err(&sdev->interface->dev, "get pipe, epnum %d\n", epnum);
+	return 0;
+}
+
+static void masking_bogus_flags(struct urb *urb)
+{
+	int				xfertype;
+	struct usb_device		*dev;
+	struct usb_host_endpoint	*ep;
+	int				is_out;
+	unsigned int	allowed;
+
+	if (!urb || urb->hcpriv || !urb->complete)
+		return;
+	dev = urb->dev;
+	if ((!dev) || (dev->state < USB_STATE_UNAUTHENTICATED))
+		return;
+
+	ep = (usb_pipein(urb->pipe) ? dev->ep_in : dev->ep_out)
+		[usb_pipeendpoint(urb->pipe)];
+	if (!ep)
+		return;
+
+	xfertype = usb_endpoint_type(&ep->desc);
+	if (xfertype == USB_ENDPOINT_XFER_CONTROL) {
+		struct usb_ctrlrequest *setup =
+			(struct usb_ctrlrequest *) urb->setup_packet;
+
+		if (!setup)
+			return;
+		is_out = !(setup->bRequestType & USB_DIR_IN) ||
+			!setup->wLength;
+	} else {
+		is_out = usb_endpoint_dir_out(&ep->desc);
+	}
+
+	/* enforce simple/standard policy */
+	allowed = (URB_NO_TRANSFER_DMA_MAP | URB_NO_INTERRUPT |
+		   URB_DIR_MASK | URB_FREE_BUFFER);
+	switch (xfertype) {
+	case USB_ENDPOINT_XFER_BULK:
+		if (is_out)
+			allowed |= URB_ZERO_PACKET;
+		/* FALLTHROUGH */
+	case USB_ENDPOINT_XFER_CONTROL:
+		allowed |= URB_NO_FSBR;	/* only affects UHCI */
+		/* FALLTHROUGH */
+	default:			/* all non-iso endpoints */
+		if (!is_out)
+			allowed |= URB_SHORT_NOT_OK;
+		break;
+	case USB_ENDPOINT_XFER_ISOC:
+		allowed |= URB_ISO_ASAP;
+		break;
+	}
+	urb->transfer_flags &= allowed;
+}
+
+static void stub_recv_cmd_submit(struct stub_device *sdev,
+				 struct usbip_header *pdu)
+{
+	int ret;
+	struct stub_priv *priv;
+	struct usbip_device *ud = &sdev->ud;
+	struct usb_device *udev = sdev->udev;
+	int pipe = get_pipe(sdev, pdu->base.ep, pdu->base.direction);
+
+	priv = stub_priv_alloc(sdev, pdu);
+	if (!priv)
+		return;
+
+	/* setup a urb */
+	if (usb_pipeisoc(pipe))
+		priv->urb = usb_alloc_urb(pdu->u.cmd_submit.number_of_packets,
+					  GFP_KERNEL);
+	else
+		priv->urb = usb_alloc_urb(0, GFP_KERNEL);
+
+	if (!priv->urb) {
+		dev_err(&sdev->interface->dev, "malloc urb\n");
+		usbip_event_add(ud, SDEV_EVENT_ERROR_MALLOC);
+		return;
+	}
+
+	/* allocate urb transfer buffer, if needed */
+	if (pdu->u.cmd_submit.transfer_buffer_length > 0) {
+		priv->urb->transfer_buffer =
+			kzalloc(pdu->u.cmd_submit.transfer_buffer_length,
+				GFP_KERNEL);
+		if (!priv->urb->transfer_buffer) {
+			usbip_event_add(ud, SDEV_EVENT_ERROR_MALLOC);
+			return;
+		}
+	}
+
+	/* copy urb setup packet */
+	priv->urb->setup_packet = kmemdup(&pdu->u.cmd_submit.setup, 8,
+					  GFP_KERNEL);
+	if (!priv->urb->setup_packet) {
+		dev_err(&sdev->interface->dev, "allocate setup_packet\n");
+		usbip_event_add(ud, SDEV_EVENT_ERROR_MALLOC);
+		return;
+	}
+
+	/* set other members from the base header of pdu */
+	priv->urb->context                = (void *) priv;
+	priv->urb->dev                    = udev;
+	priv->urb->pipe                   = pipe;
+	priv->urb->complete               = stub_complete;
+
+	usbip_pack_pdu(pdu, priv->urb, USBIP_CMD_SUBMIT, 0);
+
+
+	if (usbip_recv_xbuff(ud, priv->urb) < 0)
+		return;
+
+	if (usbip_recv_iso(ud, priv->urb) < 0)
+		return;
+
+	/* no need to submit an intercepted request, but harmless? */
+	tweak_special_requests(priv->urb);
+
+	masking_bogus_flags(priv->urb);
+	/* urb is now ready to submit */
+	ret = usb_submit_urb(priv->urb, GFP_KERNEL);
+
+	if (ret == 0)
+		usbip_dbg_stub_rx("submit urb ok, seqnum %u\n",
+				  pdu->base.seqnum);
+	else {
+		dev_err(&sdev->interface->dev, "submit_urb error, %d\n", ret);
+		usbip_dump_header(pdu);
+		usbip_dump_urb(priv->urb);
+
+		/*
+		 * Pessimistic.
+		 * This connection will be discarded.
+		 */
+		usbip_event_add(ud, SDEV_EVENT_ERROR_SUBMIT);
+	}
+
+	usbip_dbg_stub_rx("Leave\n");
+}
+
+/* recv a pdu */
+static void stub_rx_pdu(struct usbip_device *ud)
+{
+	int ret;
+	struct usbip_header pdu;
+	struct stub_device *sdev = container_of(ud, struct stub_device, ud);
+	struct device *dev = &sdev->udev->dev;
+
+	usbip_dbg_stub_rx("Enter\n");
+
+	memset(&pdu, 0, sizeof(pdu));
+
+	/* receive a pdu header */
+	ret = usbip_recv(ud->tcp_socket, &pdu, sizeof(pdu));
+	if (ret != sizeof(pdu)) {
+		dev_err(dev, "recv a header, %d\n", ret);
+		usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
+		return;
+	}
+
+	usbip_header_correct_endian(&pdu, 0);
+
+	if (usbip_dbg_flag_stub_rx)
+		usbip_dump_header(&pdu);
+
+	if (!valid_request(sdev, &pdu)) {
+		dev_err(dev, "recv invalid request\n");
+		usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
+		return;
+	}
+
+	switch (pdu.base.command) {
+	case USBIP_CMD_UNLINK:
+		stub_recv_cmd_unlink(sdev, &pdu);
+		break;
+
+	case USBIP_CMD_SUBMIT:
+		stub_recv_cmd_submit(sdev, &pdu);
+		break;
+
+	default:
+		/* NOTREACHED */
+		dev_err(dev, "unknown pdu\n");
+		usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
+		break;
+	}
+}
+
+int stub_rx_loop(void *data)
+{
+	struct usbip_device *ud = data;
+
+	while (!kthread_should_stop()) {
+		if (usbip_event_happened(ud))
+			break;
+
+		stub_rx_pdu(ud);
+	}
+
+	return 0;
+}
diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c
new file mode 100644
index 000000000000..dbcabc9dbe0d
--- /dev/null
+++ b/drivers/usb/usbip/stub_tx.c
@@ -0,0 +1,398 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <linux/kthread.h>
+#include <linux/socket.h>
+
+#include "usbip_common.h"
+#include "stub.h"
+
+static void stub_free_priv_and_urb(struct stub_priv *priv)
+{
+	struct urb *urb = priv->urb;
+
+	kfree(urb->setup_packet);
+	kfree(urb->transfer_buffer);
+	list_del(&priv->list);
+	kmem_cache_free(stub_priv_cache, priv);
+	usb_free_urb(urb);
+}
+
+/* be in spin_lock_irqsave(&sdev->priv_lock, flags) */
+void stub_enqueue_ret_unlink(struct stub_device *sdev, __u32 seqnum,
+			     __u32 status)
+{
+	struct stub_unlink *unlink;
+
+	unlink = kzalloc(sizeof(struct stub_unlink), GFP_ATOMIC);
+	if (!unlink) {
+		usbip_event_add(&sdev->ud, VDEV_EVENT_ERROR_MALLOC);
+		return;
+	}
+
+	unlink->seqnum = seqnum;
+	unlink->status = status;
+
+	list_add_tail(&unlink->list, &sdev->unlink_tx);
+}
+
+/**
+ * stub_complete - completion handler of a usbip urb
+ * @urb: pointer to the urb completed
+ *
+ * When a urb has completed, the USB core driver calls this function mostly in
+ * the interrupt context. To return the result of a urb, the completed urb is
+ * linked to the pending list of returning.
+ *
+ */
+void stub_complete(struct urb *urb)
+{
+	struct stub_priv *priv = (struct stub_priv *) urb->context;
+	struct stub_device *sdev = priv->sdev;
+	unsigned long flags;
+
+	usbip_dbg_stub_tx("complete! status %d\n", urb->status);
+
+	switch (urb->status) {
+	case 0:
+		/* OK */
+		break;
+	case -ENOENT:
+		dev_info(&urb->dev->dev,
+			 "stopped by a call to usb_kill_urb() because of cleaning up a virtual connection\n");
+		return;
+	case -ECONNRESET:
+		dev_info(&urb->dev->dev,
+			 "unlinked by a call to usb_unlink_urb()\n");
+		break;
+	case -EPIPE:
+		dev_info(&urb->dev->dev, "endpoint %d is stalled\n",
+			 usb_pipeendpoint(urb->pipe));
+		break;
+	case -ESHUTDOWN:
+		dev_info(&urb->dev->dev, "device removed?\n");
+		break;
+	default:
+		dev_info(&urb->dev->dev,
+			 "urb completion with non-zero status %d\n",
+			 urb->status);
+		break;
+	}
+
+	/* link a urb to the queue of tx. */
+	spin_lock_irqsave(&sdev->priv_lock, flags);
+	if (priv->unlinking) {
+		stub_enqueue_ret_unlink(sdev, priv->seqnum, urb->status);
+		stub_free_priv_and_urb(priv);
+	} else {
+		list_move_tail(&priv->list, &sdev->priv_tx);
+	}
+	spin_unlock_irqrestore(&sdev->priv_lock, flags);
+
+	/* wake up tx_thread */
+	wake_up(&sdev->tx_waitq);
+}
+
+static inline void setup_base_pdu(struct usbip_header_basic *base,
+				  __u32 command, __u32 seqnum)
+{
+	base->command	= command;
+	base->seqnum	= seqnum;
+	base->devid	= 0;
+	base->ep	= 0;
+	base->direction = 0;
+}
+
+static void setup_ret_submit_pdu(struct usbip_header *rpdu, struct urb *urb)
+{
+	struct stub_priv *priv = (struct stub_priv *) urb->context;
+
+	setup_base_pdu(&rpdu->base, USBIP_RET_SUBMIT, priv->seqnum);
+	usbip_pack_pdu(rpdu, urb, USBIP_RET_SUBMIT, 1);
+}
+
+static void setup_ret_unlink_pdu(struct usbip_header *rpdu,
+				 struct stub_unlink *unlink)
+{
+	setup_base_pdu(&rpdu->base, USBIP_RET_UNLINK, unlink->seqnum);
+	rpdu->u.ret_unlink.status = unlink->status;
+}
+
+static struct stub_priv *dequeue_from_priv_tx(struct stub_device *sdev)
+{
+	unsigned long flags;
+	struct stub_priv *priv, *tmp;
+
+	spin_lock_irqsave(&sdev->priv_lock, flags);
+
+	list_for_each_entry_safe(priv, tmp, &sdev->priv_tx, list) {
+		list_move_tail(&priv->list, &sdev->priv_free);
+		spin_unlock_irqrestore(&sdev->priv_lock, flags);
+		return priv;
+	}
+
+	spin_unlock_irqrestore(&sdev->priv_lock, flags);
+
+	return NULL;
+}
+
+static int stub_send_ret_submit(struct stub_device *sdev)
+{
+	unsigned long flags;
+	struct stub_priv *priv, *tmp;
+
+	struct msghdr msg;
+	size_t txsize;
+
+	size_t total_size = 0;
+
+	while ((priv = dequeue_from_priv_tx(sdev)) != NULL) {
+		int ret;
+		struct urb *urb = priv->urb;
+		struct usbip_header pdu_header;
+		struct usbip_iso_packet_descriptor *iso_buffer = NULL;
+		struct kvec *iov = NULL;
+		int iovnum = 0;
+
+		txsize = 0;
+		memset(&pdu_header, 0, sizeof(pdu_header));
+		memset(&msg, 0, sizeof(msg));
+
+		if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS)
+			iovnum = 2 + urb->number_of_packets;
+		else
+			iovnum = 2;
+
+		iov = kcalloc(iovnum, sizeof(struct kvec), GFP_KERNEL);
+
+		if (!iov) {
+			usbip_event_add(&sdev->ud, SDEV_EVENT_ERROR_MALLOC);
+			return -1;
+		}
+
+		iovnum = 0;
+
+		/* 1. setup usbip_header */
+		setup_ret_submit_pdu(&pdu_header, urb);
+		usbip_dbg_stub_tx("setup txdata seqnum: %d urb: %p\n",
+				  pdu_header.base.seqnum, urb);
+		usbip_header_correct_endian(&pdu_header, 1);
+
+		iov[iovnum].iov_base = &pdu_header;
+		iov[iovnum].iov_len  = sizeof(pdu_header);
+		iovnum++;
+		txsize += sizeof(pdu_header);
+
+		/* 2. setup transfer buffer */
+		if (usb_pipein(urb->pipe) &&
+		    usb_pipetype(urb->pipe) != PIPE_ISOCHRONOUS &&
+		    urb->actual_length > 0) {
+			iov[iovnum].iov_base = urb->transfer_buffer;
+			iov[iovnum].iov_len  = urb->actual_length;
+			iovnum++;
+			txsize += urb->actual_length;
+		} else if (usb_pipein(urb->pipe) &&
+			   usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) {
+			/*
+			 * For isochronous packets: actual length is the sum of
+			 * the actual length of the individual, packets, but as
+			 * the packet offsets are not changed there will be
+			 * padding between the packets. To optimally use the
+			 * bandwidth the padding is not transmitted.
+			 */
+
+			int i;
+
+			for (i = 0; i < urb->number_of_packets; i++) {
+				iov[iovnum].iov_base = urb->transfer_buffer +
+					urb->iso_frame_desc[i].offset;
+				iov[iovnum].iov_len =
+					urb->iso_frame_desc[i].actual_length;
+				iovnum++;
+				txsize += urb->iso_frame_desc[i].actual_length;
+			}
+
+			if (txsize != sizeof(pdu_header) + urb->actual_length) {
+				dev_err(&sdev->interface->dev,
+					"actual length of urb %d does not match iso packet sizes %zu\n",
+					urb->actual_length,
+					txsize-sizeof(pdu_header));
+				kfree(iov);
+				usbip_event_add(&sdev->ud,
+						SDEV_EVENT_ERROR_TCP);
+			   return -1;
+			}
+		}
+
+		/* 3. setup iso_packet_descriptor */
+		if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) {
+			ssize_t len = 0;
+
+			iso_buffer = usbip_alloc_iso_desc_pdu(urb, &len);
+			if (!iso_buffer) {
+				usbip_event_add(&sdev->ud,
+						SDEV_EVENT_ERROR_MALLOC);
+				kfree(iov);
+				return -1;
+			}
+
+			iov[iovnum].iov_base = iso_buffer;
+			iov[iovnum].iov_len  = len;
+			txsize += len;
+			iovnum++;
+		}
+
+		ret = kernel_sendmsg(sdev->ud.tcp_socket, &msg,
+						iov,  iovnum, txsize);
+		if (ret != txsize) {
+			dev_err(&sdev->interface->dev,
+				"sendmsg failed!, retval %d for %zd\n",
+				ret, txsize);
+			kfree(iov);
+			kfree(iso_buffer);
+			usbip_event_add(&sdev->ud, SDEV_EVENT_ERROR_TCP);
+			return -1;
+		}
+
+		kfree(iov);
+		kfree(iso_buffer);
+
+		total_size += txsize;
+	}
+
+	spin_lock_irqsave(&sdev->priv_lock, flags);
+	list_for_each_entry_safe(priv, tmp, &sdev->priv_free, list) {
+		stub_free_priv_and_urb(priv);
+	}
+	spin_unlock_irqrestore(&sdev->priv_lock, flags);
+
+	return total_size;
+}
+
+static struct stub_unlink *dequeue_from_unlink_tx(struct stub_device *sdev)
+{
+	unsigned long flags;
+	struct stub_unlink *unlink, *tmp;
+
+	spin_lock_irqsave(&sdev->priv_lock, flags);
+
+	list_for_each_entry_safe(unlink, tmp, &sdev->unlink_tx, list) {
+		list_move_tail(&unlink->list, &sdev->unlink_free);
+		spin_unlock_irqrestore(&sdev->priv_lock, flags);
+		return unlink;
+	}
+
+	spin_unlock_irqrestore(&sdev->priv_lock, flags);
+
+	return NULL;
+}
+
+static int stub_send_ret_unlink(struct stub_device *sdev)
+{
+	unsigned long flags;
+	struct stub_unlink *unlink, *tmp;
+
+	struct msghdr msg;
+	struct kvec iov[1];
+	size_t txsize;
+
+	size_t total_size = 0;
+
+	while ((unlink = dequeue_from_unlink_tx(sdev)) != NULL) {
+		int ret;
+		struct usbip_header pdu_header;
+
+		txsize = 0;
+		memset(&pdu_header, 0, sizeof(pdu_header));
+		memset(&msg, 0, sizeof(msg));
+		memset(&iov, 0, sizeof(iov));
+
+		usbip_dbg_stub_tx("setup ret unlink %lu\n", unlink->seqnum);
+
+		/* 1. setup usbip_header */
+		setup_ret_unlink_pdu(&pdu_header, unlink);
+		usbip_header_correct_endian(&pdu_header, 1);
+
+		iov[0].iov_base = &pdu_header;
+		iov[0].iov_len  = sizeof(pdu_header);
+		txsize += sizeof(pdu_header);
+
+		ret = kernel_sendmsg(sdev->ud.tcp_socket, &msg, iov,
+				     1, txsize);
+		if (ret != txsize) {
+			dev_err(&sdev->interface->dev,
+				"sendmsg failed!, retval %d for %zd\n",
+				ret, txsize);
+			usbip_event_add(&sdev->ud, SDEV_EVENT_ERROR_TCP);
+			return -1;
+		}
+
+		usbip_dbg_stub_tx("send txdata\n");
+		total_size += txsize;
+	}
+
+	spin_lock_irqsave(&sdev->priv_lock, flags);
+
+	list_for_each_entry_safe(unlink, tmp, &sdev->unlink_free, list) {
+		list_del(&unlink->list);
+		kfree(unlink);
+	}
+
+	spin_unlock_irqrestore(&sdev->priv_lock, flags);
+
+	return total_size;
+}
+
+int stub_tx_loop(void *data)
+{
+	struct usbip_device *ud = data;
+	struct stub_device *sdev = container_of(ud, struct stub_device, ud);
+
+	while (!kthread_should_stop()) {
+		if (usbip_event_happened(ud))
+			break;
+
+		/*
+		 * send_ret_submit comes earlier than send_ret_unlink.  stub_rx
+		 * looks at only priv_init queue. If the completion of a URB is
+		 * earlier than the receive of CMD_UNLINK, priv is moved to
+		 * priv_tx queue and stub_rx does not find the target priv. In
+		 * this case, vhci_rx receives the result of the submit request
+		 * and then receives the result of the unlink request. The
+		 * result of the submit is given back to the usbcore as the
+		 * completion of the unlink request. The request of the
+		 * unlink is ignored. This is ok because a driver who calls
+		 * usb_unlink_urb() understands the unlink was too late by
+		 * getting the status of the given-backed URB which has the
+		 * status of usb_submit_urb().
+		 */
+		if (stub_send_ret_submit(sdev) < 0)
+			break;
+
+		if (stub_send_ret_unlink(sdev) < 0)
+			break;
+
+		wait_event_interruptible(sdev->tx_waitq,
+					 (!list_empty(&sdev->priv_tx) ||
+					  !list_empty(&sdev->unlink_tx) ||
+					  kthread_should_stop()));
+	}
+
+	return 0;
+}
diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
new file mode 100644
index 000000000000..facaaf003f19
--- /dev/null
+++ b/drivers/usb/usbip/usbip_common.c
@@ -0,0 +1,776 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <asm/byteorder.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <net/sock.h>
+
+#include "usbip_common.h"
+
+#define DRIVER_AUTHOR "Takahiro Hirofuchi <hirofuchi@users.sourceforge.net>"
+#define DRIVER_DESC "USB/IP Core"
+
+#ifdef CONFIG_USBIP_DEBUG
+unsigned long usbip_debug_flag = 0xffffffff;
+#else
+unsigned long usbip_debug_flag;
+#endif
+EXPORT_SYMBOL_GPL(usbip_debug_flag);
+module_param(usbip_debug_flag, ulong, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(usbip_debug_flag, "debug flags (defined in usbip_common.h)");
+
+/* FIXME */
+struct device_attribute dev_attr_usbip_debug;
+EXPORT_SYMBOL_GPL(dev_attr_usbip_debug);
+
+static ssize_t usbip_debug_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%lx\n", usbip_debug_flag);
+}
+
+static ssize_t usbip_debug_store(struct device *dev,
+				 struct device_attribute *attr, const char *buf,
+				 size_t count)
+{
+	if (sscanf(buf, "%lx", &usbip_debug_flag) != 1)
+		return -EINVAL;
+	return count;
+}
+DEVICE_ATTR_RW(usbip_debug);
+
+static void usbip_dump_buffer(char *buff, int bufflen)
+{
+	print_hex_dump(KERN_DEBUG, "usbip-core", DUMP_PREFIX_OFFSET, 16, 4,
+		       buff, bufflen, false);
+}
+
+static void usbip_dump_pipe(unsigned int p)
+{
+	unsigned char type = usb_pipetype(p);
+	unsigned char ep   = usb_pipeendpoint(p);
+	unsigned char dev  = usb_pipedevice(p);
+	unsigned char dir  = usb_pipein(p);
+
+	pr_debug("dev(%d) ep(%d) [%s] ", dev, ep, dir ? "IN" : "OUT");
+
+	switch (type) {
+	case PIPE_ISOCHRONOUS:
+		pr_debug("ISO\n");
+		break;
+	case PIPE_INTERRUPT:
+		pr_debug("INT\n");
+		break;
+	case PIPE_CONTROL:
+		pr_debug("CTRL\n");
+		break;
+	case PIPE_BULK:
+		pr_debug("BULK\n");
+		break;
+	default:
+		pr_debug("ERR\n");
+		break;
+	}
+}
+
+static void usbip_dump_usb_device(struct usb_device *udev)
+{
+	struct device *dev = &udev->dev;
+	int i;
+
+	dev_dbg(dev, "       devnum(%d) devpath(%s) usb speed(%s)",
+		udev->devnum, udev->devpath, usb_speed_string(udev->speed));
+
+	pr_debug("tt %p, ttport %d\n", udev->tt, udev->ttport);
+
+	dev_dbg(dev, "                    ");
+	for (i = 0; i < 16; i++)
+		pr_debug(" %2u", i);
+	pr_debug("\n");
+
+	dev_dbg(dev, "       toggle0(IN) :");
+	for (i = 0; i < 16; i++)
+		pr_debug(" %2u", (udev->toggle[0] & (1 << i)) ? 1 : 0);
+	pr_debug("\n");
+
+	dev_dbg(dev, "       toggle1(OUT):");
+	for (i = 0; i < 16; i++)
+		pr_debug(" %2u", (udev->toggle[1] & (1 << i)) ? 1 : 0);
+	pr_debug("\n");
+
+	dev_dbg(dev, "       epmaxp_in   :");
+	for (i = 0; i < 16; i++) {
+		if (udev->ep_in[i])
+			pr_debug(" %2u",
+			    le16_to_cpu(udev->ep_in[i]->desc.wMaxPacketSize));
+	}
+	pr_debug("\n");
+
+	dev_dbg(dev, "       epmaxp_out  :");
+	for (i = 0; i < 16; i++) {
+		if (udev->ep_out[i])
+			pr_debug(" %2u",
+			    le16_to_cpu(udev->ep_out[i]->desc.wMaxPacketSize));
+	}
+	pr_debug("\n");
+
+	dev_dbg(dev, "parent %p, bus %p\n", udev->parent, udev->bus);
+
+	dev_dbg(dev,
+		"descriptor %p, config %p, actconfig %p, rawdescriptors %p\n",
+		&udev->descriptor, udev->config,
+		udev->actconfig, udev->rawdescriptors);
+
+	dev_dbg(dev, "have_langid %d, string_langid %d\n",
+		udev->have_langid, udev->string_langid);
+
+	dev_dbg(dev, "maxchild %d\n", udev->maxchild);
+}
+
+static void usbip_dump_request_type(__u8 rt)
+{
+	switch (rt & USB_RECIP_MASK) {
+	case USB_RECIP_DEVICE:
+		pr_debug("DEVICE");
+		break;
+	case USB_RECIP_INTERFACE:
+		pr_debug("INTERF");
+		break;
+	case USB_RECIP_ENDPOINT:
+		pr_debug("ENDPOI");
+		break;
+	case USB_RECIP_OTHER:
+		pr_debug("OTHER ");
+		break;
+	default:
+		pr_debug("------");
+		break;
+	}
+}
+
+static void usbip_dump_usb_ctrlrequest(struct usb_ctrlrequest *cmd)
+{
+	if (!cmd) {
+		pr_debug("       : null pointer\n");
+		return;
+	}
+
+	pr_debug("       ");
+	pr_debug("bRequestType(%02X) bRequest(%02X) wValue(%04X) wIndex(%04X) wLength(%04X) ",
+		 cmd->bRequestType, cmd->bRequest,
+		 cmd->wValue, cmd->wIndex, cmd->wLength);
+	pr_debug("\n       ");
+
+	if ((cmd->bRequestType & USB_TYPE_MASK) == USB_TYPE_STANDARD) {
+		pr_debug("STANDARD ");
+		switch (cmd->bRequest) {
+		case USB_REQ_GET_STATUS:
+			pr_debug("GET_STATUS\n");
+			break;
+		case USB_REQ_CLEAR_FEATURE:
+			pr_debug("CLEAR_FEAT\n");
+			break;
+		case USB_REQ_SET_FEATURE:
+			pr_debug("SET_FEAT\n");
+			break;
+		case USB_REQ_SET_ADDRESS:
+			pr_debug("SET_ADDRRS\n");
+			break;
+		case USB_REQ_GET_DESCRIPTOR:
+			pr_debug("GET_DESCRI\n");
+			break;
+		case USB_REQ_SET_DESCRIPTOR:
+			pr_debug("SET_DESCRI\n");
+			break;
+		case USB_REQ_GET_CONFIGURATION:
+			pr_debug("GET_CONFIG\n");
+			break;
+		case USB_REQ_SET_CONFIGURATION:
+			pr_debug("SET_CONFIG\n");
+			break;
+		case USB_REQ_GET_INTERFACE:
+			pr_debug("GET_INTERF\n");
+			break;
+		case USB_REQ_SET_INTERFACE:
+			pr_debug("SET_INTERF\n");
+			break;
+		case USB_REQ_SYNCH_FRAME:
+			pr_debug("SYNC_FRAME\n");
+			break;
+		default:
+			pr_debug("REQ(%02X)\n", cmd->bRequest);
+			break;
+		}
+		usbip_dump_request_type(cmd->bRequestType);
+	} else if ((cmd->bRequestType & USB_TYPE_MASK) == USB_TYPE_CLASS) {
+		pr_debug("CLASS\n");
+	} else if ((cmd->bRequestType & USB_TYPE_MASK) == USB_TYPE_VENDOR) {
+		pr_debug("VENDOR\n");
+	} else if ((cmd->bRequestType & USB_TYPE_MASK) == USB_TYPE_RESERVED) {
+		pr_debug("RESERVED\n");
+	}
+}
+
+void usbip_dump_urb(struct urb *urb)
+{
+	struct device *dev;
+
+	if (!urb) {
+		pr_debug("urb: null pointer!!\n");
+		return;
+	}
+
+	if (!urb->dev) {
+		pr_debug("urb->dev: null pointer!!\n");
+		return;
+	}
+
+	dev = &urb->dev->dev;
+
+	dev_dbg(dev, "   urb                   :%p\n", urb);
+	dev_dbg(dev, "   dev                   :%p\n", urb->dev);
+
+	usbip_dump_usb_device(urb->dev);
+
+	dev_dbg(dev, "   pipe                  :%08x ", urb->pipe);
+
+	usbip_dump_pipe(urb->pipe);
+
+	dev_dbg(dev, "   status                :%d\n", urb->status);
+	dev_dbg(dev, "   transfer_flags        :%08X\n", urb->transfer_flags);
+	dev_dbg(dev, "   transfer_buffer       :%p\n", urb->transfer_buffer);
+	dev_dbg(dev, "   transfer_buffer_length:%d\n",
+						urb->transfer_buffer_length);
+	dev_dbg(dev, "   actual_length         :%d\n", urb->actual_length);
+	dev_dbg(dev, "   setup_packet          :%p\n", urb->setup_packet);
+
+	if (urb->setup_packet && usb_pipetype(urb->pipe) == PIPE_CONTROL)
+		usbip_dump_usb_ctrlrequest(
+			(struct usb_ctrlrequest *)urb->setup_packet);
+
+	dev_dbg(dev, "   start_frame           :%d\n", urb->start_frame);
+	dev_dbg(dev, "   number_of_packets     :%d\n", urb->number_of_packets);
+	dev_dbg(dev, "   interval              :%d\n", urb->interval);
+	dev_dbg(dev, "   error_count           :%d\n", urb->error_count);
+	dev_dbg(dev, "   context               :%p\n", urb->context);
+	dev_dbg(dev, "   complete              :%p\n", urb->complete);
+}
+EXPORT_SYMBOL_GPL(usbip_dump_urb);
+
+void usbip_dump_header(struct usbip_header *pdu)
+{
+	pr_debug("BASE: cmd %u seq %u devid %u dir %u ep %u\n",
+		 pdu->base.command,
+		 pdu->base.seqnum,
+		 pdu->base.devid,
+		 pdu->base.direction,
+		 pdu->base.ep);
+
+	switch (pdu->base.command) {
+	case USBIP_CMD_SUBMIT:
+		pr_debug("USBIP_CMD_SUBMIT: x_flags %u x_len %u sf %u #p %d iv %d\n",
+			 pdu->u.cmd_submit.transfer_flags,
+			 pdu->u.cmd_submit.transfer_buffer_length,
+			 pdu->u.cmd_submit.start_frame,
+			 pdu->u.cmd_submit.number_of_packets,
+			 pdu->u.cmd_submit.interval);
+		break;
+	case USBIP_CMD_UNLINK:
+		pr_debug("USBIP_CMD_UNLINK: seq %u\n",
+			 pdu->u.cmd_unlink.seqnum);
+		break;
+	case USBIP_RET_SUBMIT:
+		pr_debug("USBIP_RET_SUBMIT: st %d al %u sf %d #p %d ec %d\n",
+			 pdu->u.ret_submit.status,
+			 pdu->u.ret_submit.actual_length,
+			 pdu->u.ret_submit.start_frame,
+			 pdu->u.ret_submit.number_of_packets,
+			 pdu->u.ret_submit.error_count);
+		break;
+	case USBIP_RET_UNLINK:
+		pr_debug("USBIP_RET_UNLINK: status %d\n",
+			 pdu->u.ret_unlink.status);
+		break;
+	default:
+		/* NOT REACHED */
+		pr_err("unknown command\n");
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(usbip_dump_header);
+
+/* Receive data over TCP/IP. */
+int usbip_recv(struct socket *sock, void *buf, int size)
+{
+	int result;
+	struct msghdr msg;
+	struct kvec iov;
+	int total = 0;
+
+	/* for blocks of if (usbip_dbg_flag_xmit) */
+	char *bp = buf;
+	int osize = size;
+
+	usbip_dbg_xmit("enter\n");
+
+	if (!sock || !buf || !size) {
+		pr_err("invalid arg, sock %p buff %p size %d\n", sock, buf,
+		       size);
+		return -EINVAL;
+	}
+
+	do {
+		sock->sk->sk_allocation = GFP_NOIO;
+		iov.iov_base    = buf;
+		iov.iov_len     = size;
+		msg.msg_name    = NULL;
+		msg.msg_namelen = 0;
+		msg.msg_control = NULL;
+		msg.msg_controllen = 0;
+		msg.msg_flags      = MSG_NOSIGNAL;
+
+		result = kernel_recvmsg(sock, &msg, &iov, 1, size, MSG_WAITALL);
+		if (result <= 0) {
+			pr_debug("receive sock %p buf %p size %u ret %d total %d\n",
+				 sock, buf, size, result, total);
+			goto err;
+		}
+
+		size -= result;
+		buf += result;
+		total += result;
+	} while (size > 0);
+
+	if (usbip_dbg_flag_xmit) {
+		if (!in_interrupt())
+			pr_debug("%-10s:", current->comm);
+		else
+			pr_debug("interrupt  :");
+
+		pr_debug("receiving....\n");
+		usbip_dump_buffer(bp, osize);
+		pr_debug("received, osize %d ret %d size %d total %d\n",
+			 osize, result, size, total);
+	}
+
+	return total;
+
+err:
+	return result;
+}
+EXPORT_SYMBOL_GPL(usbip_recv);
+
+/* there may be more cases to tweak the flags. */
+static unsigned int tweak_transfer_flags(unsigned int flags)
+{
+	flags &= ~URB_NO_TRANSFER_DMA_MAP;
+	return flags;
+}
+
+static void usbip_pack_cmd_submit(struct usbip_header *pdu, struct urb *urb,
+				  int pack)
+{
+	struct usbip_header_cmd_submit *spdu = &pdu->u.cmd_submit;
+
+	/*
+	 * Some members are not still implemented in usbip. I hope this issue
+	 * will be discussed when usbip is ported to other operating systems.
+	 */
+	if (pack) {
+		spdu->transfer_flags =
+			tweak_transfer_flags(urb->transfer_flags);
+		spdu->transfer_buffer_length	= urb->transfer_buffer_length;
+		spdu->start_frame		= urb->start_frame;
+		spdu->number_of_packets		= urb->number_of_packets;
+		spdu->interval			= urb->interval;
+	} else  {
+		urb->transfer_flags         = spdu->transfer_flags;
+		urb->transfer_buffer_length = spdu->transfer_buffer_length;
+		urb->start_frame            = spdu->start_frame;
+		urb->number_of_packets      = spdu->number_of_packets;
+		urb->interval               = spdu->interval;
+	}
+}
+
+static void usbip_pack_ret_submit(struct usbip_header *pdu, struct urb *urb,
+				  int pack)
+{
+	struct usbip_header_ret_submit *rpdu = &pdu->u.ret_submit;
+
+	if (pack) {
+		rpdu->status		= urb->status;
+		rpdu->actual_length	= urb->actual_length;
+		rpdu->start_frame	= urb->start_frame;
+		rpdu->number_of_packets = urb->number_of_packets;
+		rpdu->error_count	= urb->error_count;
+	} else {
+		urb->status		= rpdu->status;
+		urb->actual_length	= rpdu->actual_length;
+		urb->start_frame	= rpdu->start_frame;
+		urb->number_of_packets = rpdu->number_of_packets;
+		urb->error_count	= rpdu->error_count;
+	}
+}
+
+void usbip_pack_pdu(struct usbip_header *pdu, struct urb *urb, int cmd,
+		    int pack)
+{
+	switch (cmd) {
+	case USBIP_CMD_SUBMIT:
+		usbip_pack_cmd_submit(pdu, urb, pack);
+		break;
+	case USBIP_RET_SUBMIT:
+		usbip_pack_ret_submit(pdu, urb, pack);
+		break;
+	default:
+		/* NOT REACHED */
+		pr_err("unknown command\n");
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(usbip_pack_pdu);
+
+static void correct_endian_basic(struct usbip_header_basic *base, int send)
+{
+	if (send) {
+		base->command	= cpu_to_be32(base->command);
+		base->seqnum	= cpu_to_be32(base->seqnum);
+		base->devid	= cpu_to_be32(base->devid);
+		base->direction	= cpu_to_be32(base->direction);
+		base->ep	= cpu_to_be32(base->ep);
+	} else {
+		base->command	= be32_to_cpu(base->command);
+		base->seqnum	= be32_to_cpu(base->seqnum);
+		base->devid	= be32_to_cpu(base->devid);
+		base->direction	= be32_to_cpu(base->direction);
+		base->ep	= be32_to_cpu(base->ep);
+	}
+}
+
+static void correct_endian_cmd_submit(struct usbip_header_cmd_submit *pdu,
+				      int send)
+{
+	if (send) {
+		pdu->transfer_flags = cpu_to_be32(pdu->transfer_flags);
+
+		cpu_to_be32s(&pdu->transfer_buffer_length);
+		cpu_to_be32s(&pdu->start_frame);
+		cpu_to_be32s(&pdu->number_of_packets);
+		cpu_to_be32s(&pdu->interval);
+	} else {
+		pdu->transfer_flags = be32_to_cpu(pdu->transfer_flags);
+
+		be32_to_cpus(&pdu->transfer_buffer_length);
+		be32_to_cpus(&pdu->start_frame);
+		be32_to_cpus(&pdu->number_of_packets);
+		be32_to_cpus(&pdu->interval);
+	}
+}
+
+static void correct_endian_ret_submit(struct usbip_header_ret_submit *pdu,
+				      int send)
+{
+	if (send) {
+		cpu_to_be32s(&pdu->status);
+		cpu_to_be32s(&pdu->actual_length);
+		cpu_to_be32s(&pdu->start_frame);
+		cpu_to_be32s(&pdu->number_of_packets);
+		cpu_to_be32s(&pdu->error_count);
+	} else {
+		be32_to_cpus(&pdu->status);
+		be32_to_cpus(&pdu->actual_length);
+		be32_to_cpus(&pdu->start_frame);
+		be32_to_cpus(&pdu->number_of_packets);
+		be32_to_cpus(&pdu->error_count);
+	}
+}
+
+static void correct_endian_cmd_unlink(struct usbip_header_cmd_unlink *pdu,
+				      int send)
+{
+	if (send)
+		pdu->seqnum = cpu_to_be32(pdu->seqnum);
+	else
+		pdu->seqnum = be32_to_cpu(pdu->seqnum);
+}
+
+static void correct_endian_ret_unlink(struct usbip_header_ret_unlink *pdu,
+				      int send)
+{
+	if (send)
+		cpu_to_be32s(&pdu->status);
+	else
+		be32_to_cpus(&pdu->status);
+}
+
+void usbip_header_correct_endian(struct usbip_header *pdu, int send)
+{
+	__u32 cmd = 0;
+
+	if (send)
+		cmd = pdu->base.command;
+
+	correct_endian_basic(&pdu->base, send);
+
+	if (!send)
+		cmd = pdu->base.command;
+
+	switch (cmd) {
+	case USBIP_CMD_SUBMIT:
+		correct_endian_cmd_submit(&pdu->u.cmd_submit, send);
+		break;
+	case USBIP_RET_SUBMIT:
+		correct_endian_ret_submit(&pdu->u.ret_submit, send);
+		break;
+	case USBIP_CMD_UNLINK:
+		correct_endian_cmd_unlink(&pdu->u.cmd_unlink, send);
+		break;
+	case USBIP_RET_UNLINK:
+		correct_endian_ret_unlink(&pdu->u.ret_unlink, send);
+		break;
+	default:
+		/* NOT REACHED */
+		pr_err("unknown command\n");
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(usbip_header_correct_endian);
+
+static void usbip_iso_packet_correct_endian(
+		struct usbip_iso_packet_descriptor *iso, int send)
+{
+	/* does not need all members. but copy all simply. */
+	if (send) {
+		iso->offset	= cpu_to_be32(iso->offset);
+		iso->length	= cpu_to_be32(iso->length);
+		iso->status	= cpu_to_be32(iso->status);
+		iso->actual_length = cpu_to_be32(iso->actual_length);
+	} else {
+		iso->offset	= be32_to_cpu(iso->offset);
+		iso->length	= be32_to_cpu(iso->length);
+		iso->status	= be32_to_cpu(iso->status);
+		iso->actual_length = be32_to_cpu(iso->actual_length);
+	}
+}
+
+static void usbip_pack_iso(struct usbip_iso_packet_descriptor *iso,
+			   struct usb_iso_packet_descriptor *uiso, int pack)
+{
+	if (pack) {
+		iso->offset		= uiso->offset;
+		iso->length		= uiso->length;
+		iso->status		= uiso->status;
+		iso->actual_length	= uiso->actual_length;
+	} else {
+		uiso->offset		= iso->offset;
+		uiso->length		= iso->length;
+		uiso->status		= iso->status;
+		uiso->actual_length	= iso->actual_length;
+	}
+}
+
+/* must free buffer */
+struct usbip_iso_packet_descriptor*
+usbip_alloc_iso_desc_pdu(struct urb *urb, ssize_t *bufflen)
+{
+	struct usbip_iso_packet_descriptor *iso;
+	int np = urb->number_of_packets;
+	ssize_t size = np * sizeof(*iso);
+	int i;
+
+	iso = kzalloc(size, GFP_KERNEL);
+	if (!iso)
+		return NULL;
+
+	for (i = 0; i < np; i++) {
+		usbip_pack_iso(&iso[i], &urb->iso_frame_desc[i], 1);
+		usbip_iso_packet_correct_endian(&iso[i], 1);
+	}
+
+	*bufflen = size;
+
+	return iso;
+}
+EXPORT_SYMBOL_GPL(usbip_alloc_iso_desc_pdu);
+
+/* some members of urb must be substituted before. */
+int usbip_recv_iso(struct usbip_device *ud, struct urb *urb)
+{
+	void *buff;
+	struct usbip_iso_packet_descriptor *iso;
+	int np = urb->number_of_packets;
+	int size = np * sizeof(*iso);
+	int i;
+	int ret;
+	int total_length = 0;
+
+	if (!usb_pipeisoc(urb->pipe))
+		return 0;
+
+	/* my Bluetooth dongle gets ISO URBs which are np = 0 */
+	if (np == 0)
+		return 0;
+
+	buff = kzalloc(size, GFP_KERNEL);
+	if (!buff)
+		return -ENOMEM;
+
+	ret = usbip_recv(ud->tcp_socket, buff, size);
+	if (ret != size) {
+		dev_err(&urb->dev->dev, "recv iso_frame_descriptor, %d\n",
+			ret);
+		kfree(buff);
+
+		if (ud->side == USBIP_STUB)
+			usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
+		else
+			usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+
+		return -EPIPE;
+	}
+
+	iso = (struct usbip_iso_packet_descriptor *) buff;
+	for (i = 0; i < np; i++) {
+		usbip_iso_packet_correct_endian(&iso[i], 0);
+		usbip_pack_iso(&iso[i], &urb->iso_frame_desc[i], 0);
+		total_length += urb->iso_frame_desc[i].actual_length;
+	}
+
+	kfree(buff);
+
+	if (total_length != urb->actual_length) {
+		dev_err(&urb->dev->dev,
+			"total length of iso packets %d not equal to actual length of buffer %d\n",
+			total_length, urb->actual_length);
+
+		if (ud->side == USBIP_STUB)
+			usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
+		else
+			usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+
+		return -EPIPE;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(usbip_recv_iso);
+
+/*
+ * This functions restores the padding which was removed for optimizing
+ * the bandwidth during transfer over tcp/ip
+ *
+ * buffer and iso packets need to be stored and be in propeper endian in urb
+ * before calling this function
+ */
+void usbip_pad_iso(struct usbip_device *ud, struct urb *urb)
+{
+	int np = urb->number_of_packets;
+	int i;
+	int actualoffset = urb->actual_length;
+
+	if (!usb_pipeisoc(urb->pipe))
+		return;
+
+	/* if no packets or length of data is 0, then nothing to unpack */
+	if (np == 0 || urb->actual_length == 0)
+		return;
+
+	/*
+	 * if actual_length is transfer_buffer_length then no padding is
+	 * present.
+	 */
+	if (urb->actual_length == urb->transfer_buffer_length)
+		return;
+
+	/*
+	 * loop over all packets from last to first (to prevent overwritting
+	 * memory when padding) and move them into the proper place
+	 */
+	for (i = np-1; i > 0; i--) {
+		actualoffset -= urb->iso_frame_desc[i].actual_length;
+		memmove(urb->transfer_buffer + urb->iso_frame_desc[i].offset,
+			urb->transfer_buffer + actualoffset,
+			urb->iso_frame_desc[i].actual_length);
+	}
+}
+EXPORT_SYMBOL_GPL(usbip_pad_iso);
+
+/* some members of urb must be substituted before. */
+int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb)
+{
+	int ret;
+	int size;
+
+	if (ud->side == USBIP_STUB) {
+		/* the direction of urb must be OUT. */
+		if (usb_pipein(urb->pipe))
+			return 0;
+
+		size = urb->transfer_buffer_length;
+	} else {
+		/* the direction of urb must be IN. */
+		if (usb_pipeout(urb->pipe))
+			return 0;
+
+		size = urb->actual_length;
+	}
+
+	/* no need to recv xbuff */
+	if (!(size > 0))
+		return 0;
+
+	ret = usbip_recv(ud->tcp_socket, urb->transfer_buffer, size);
+	if (ret != size) {
+		dev_err(&urb->dev->dev, "recv xbuf, %d\n", ret);
+		if (ud->side == USBIP_STUB) {
+			usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
+		} else {
+			usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+			return -EPIPE;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(usbip_recv_xbuff);
+
+static int __init usbip_core_init(void)
+{
+	pr_info(DRIVER_DESC " v" USBIP_VERSION "\n");
+	return 0;
+}
+
+static void __exit usbip_core_exit(void)
+{
+	return;
+}
+
+module_init(usbip_core_init);
+module_exit(usbip_core_exit);
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+MODULE_VERSION(USBIP_VERSION);
diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h
new file mode 100644
index 000000000000..86b08475c254
--- /dev/null
+++ b/drivers/usb/usbip/usbip_common.h
@@ -0,0 +1,335 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#ifndef __USBIP_COMMON_H
+#define __USBIP_COMMON_H
+
+#include <linux/compiler.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/net.h>
+#include <linux/printk.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+#include <linux/wait.h>
+#include <uapi/linux/usbip.h>
+
+#define USBIP_VERSION "1.0.0"
+
+#undef pr_fmt
+
+#ifdef DEBUG
+#define pr_fmt(fmt)     KBUILD_MODNAME ": %s:%d: " fmt, __func__, __LINE__
+#else
+#define pr_fmt(fmt)     KBUILD_MODNAME ": " fmt
+#endif
+
+enum {
+	usbip_debug_xmit	= (1 << 0),
+	usbip_debug_sysfs	= (1 << 1),
+	usbip_debug_urb		= (1 << 2),
+	usbip_debug_eh		= (1 << 3),
+
+	usbip_debug_stub_cmp	= (1 << 8),
+	usbip_debug_stub_dev	= (1 << 9),
+	usbip_debug_stub_rx	= (1 << 10),
+	usbip_debug_stub_tx	= (1 << 11),
+
+	usbip_debug_vhci_rh	= (1 << 8),
+	usbip_debug_vhci_hc	= (1 << 9),
+	usbip_debug_vhci_rx	= (1 << 10),
+	usbip_debug_vhci_tx	= (1 << 11),
+	usbip_debug_vhci_sysfs  = (1 << 12)
+};
+
+#define usbip_dbg_flag_xmit	(usbip_debug_flag & usbip_debug_xmit)
+#define usbip_dbg_flag_vhci_rh	(usbip_debug_flag & usbip_debug_vhci_rh)
+#define usbip_dbg_flag_vhci_hc	(usbip_debug_flag & usbip_debug_vhci_hc)
+#define usbip_dbg_flag_vhci_rx	(usbip_debug_flag & usbip_debug_vhci_rx)
+#define usbip_dbg_flag_vhci_tx	(usbip_debug_flag & usbip_debug_vhci_tx)
+#define usbip_dbg_flag_stub_rx	(usbip_debug_flag & usbip_debug_stub_rx)
+#define usbip_dbg_flag_stub_tx	(usbip_debug_flag & usbip_debug_stub_tx)
+#define usbip_dbg_flag_vhci_sysfs  (usbip_debug_flag & usbip_debug_vhci_sysfs)
+
+extern unsigned long usbip_debug_flag;
+extern struct device_attribute dev_attr_usbip_debug;
+
+#define usbip_dbg_with_flag(flag, fmt, args...)		\
+	do {						\
+		if (flag & usbip_debug_flag)		\
+			pr_debug(fmt, ##args);		\
+	} while (0)
+
+#define usbip_dbg_sysfs(fmt, args...) \
+	usbip_dbg_with_flag(usbip_debug_sysfs, fmt , ##args)
+#define usbip_dbg_xmit(fmt, args...) \
+	usbip_dbg_with_flag(usbip_debug_xmit, fmt , ##args)
+#define usbip_dbg_urb(fmt, args...) \
+	usbip_dbg_with_flag(usbip_debug_urb, fmt , ##args)
+#define usbip_dbg_eh(fmt, args...) \
+	usbip_dbg_with_flag(usbip_debug_eh, fmt , ##args)
+
+#define usbip_dbg_vhci_rh(fmt, args...)	\
+	usbip_dbg_with_flag(usbip_debug_vhci_rh, fmt , ##args)
+#define usbip_dbg_vhci_hc(fmt, args...)	\
+	usbip_dbg_with_flag(usbip_debug_vhci_hc, fmt , ##args)
+#define usbip_dbg_vhci_rx(fmt, args...)	\
+	usbip_dbg_with_flag(usbip_debug_vhci_rx, fmt , ##args)
+#define usbip_dbg_vhci_tx(fmt, args...)	\
+	usbip_dbg_with_flag(usbip_debug_vhci_tx, fmt , ##args)
+#define usbip_dbg_vhci_sysfs(fmt, args...) \
+	usbip_dbg_with_flag(usbip_debug_vhci_sysfs, fmt , ##args)
+
+#define usbip_dbg_stub_cmp(fmt, args...) \
+	usbip_dbg_with_flag(usbip_debug_stub_cmp, fmt , ##args)
+#define usbip_dbg_stub_rx(fmt, args...) \
+	usbip_dbg_with_flag(usbip_debug_stub_rx, fmt , ##args)
+#define usbip_dbg_stub_tx(fmt, args...) \
+	usbip_dbg_with_flag(usbip_debug_stub_tx, fmt , ##args)
+
+/*
+ * USB/IP request headers
+ *
+ * Each request is transferred across the network to its counterpart, which
+ * facilitates the normal USB communication. The values contained in the headers
+ * are basically the same as in a URB. Currently, four request types are
+ * defined:
+ *
+ *  - USBIP_CMD_SUBMIT: a USB request block, corresponds to usb_submit_urb()
+ *    (client to server)
+ *
+ *  - USBIP_RET_SUBMIT: the result of USBIP_CMD_SUBMIT
+ *    (server to client)
+ *
+ *  - USBIP_CMD_UNLINK: an unlink request of a pending USBIP_CMD_SUBMIT,
+ *    corresponds to usb_unlink_urb()
+ *    (client to server)
+ *
+ *  - USBIP_RET_UNLINK: the result of USBIP_CMD_UNLINK
+ *    (server to client)
+ *
+ */
+#define USBIP_CMD_SUBMIT	0x0001
+#define USBIP_CMD_UNLINK	0x0002
+#define USBIP_RET_SUBMIT	0x0003
+#define USBIP_RET_UNLINK	0x0004
+
+#define USBIP_DIR_OUT	0x00
+#define USBIP_DIR_IN	0x01
+
+/**
+ * struct usbip_header_basic - data pertinent to every request
+ * @command: the usbip request type
+ * @seqnum: sequential number that identifies requests; incremented per
+ *	    connection
+ * @devid: specifies a remote USB device uniquely instead of busnum and devnum;
+ *	   in the stub driver, this value is ((busnum << 16) | devnum)
+ * @direction: direction of the transfer
+ * @ep: endpoint number
+ */
+struct usbip_header_basic {
+	__u32 command;
+	__u32 seqnum;
+	__u32 devid;
+	__u32 direction;
+	__u32 ep;
+} __packed;
+
+/**
+ * struct usbip_header_cmd_submit - USBIP_CMD_SUBMIT packet header
+ * @transfer_flags: URB flags
+ * @transfer_buffer_length: the data size for (in) or (out) transfer
+ * @start_frame: initial frame for isochronous or interrupt transfers
+ * @number_of_packets: number of isochronous packets
+ * @interval: maximum time for the request on the server-side host controller
+ * @setup: setup data for a control request
+ */
+struct usbip_header_cmd_submit {
+	__u32 transfer_flags;
+	__s32 transfer_buffer_length;
+
+	/* it is difficult for usbip to sync frames (reserved only?) */
+	__s32 start_frame;
+	__s32 number_of_packets;
+	__s32 interval;
+
+	unsigned char setup[8];
+} __packed;
+
+/**
+ * struct usbip_header_ret_submit - USBIP_RET_SUBMIT packet header
+ * @status: return status of a non-iso request
+ * @actual_length: number of bytes transferred
+ * @start_frame: initial frame for isochronous or interrupt transfers
+ * @number_of_packets: number of isochronous packets
+ * @error_count: number of errors for isochronous transfers
+ */
+struct usbip_header_ret_submit {
+	__s32 status;
+	__s32 actual_length;
+	__s32 start_frame;
+	__s32 number_of_packets;
+	__s32 error_count;
+} __packed;
+
+/**
+ * struct usbip_header_cmd_unlink - USBIP_CMD_UNLINK packet header
+ * @seqnum: the URB seqnum to unlink
+ */
+struct usbip_header_cmd_unlink {
+	__u32 seqnum;
+} __packed;
+
+/**
+ * struct usbip_header_ret_unlink - USBIP_RET_UNLINK packet header
+ * @status: return status of the request
+ */
+struct usbip_header_ret_unlink {
+	__s32 status;
+} __packed;
+
+/**
+ * struct usbip_header - common header for all usbip packets
+ * @base: the basic header
+ * @u: packet type dependent header
+ */
+struct usbip_header {
+	struct usbip_header_basic base;
+
+	union {
+		struct usbip_header_cmd_submit	cmd_submit;
+		struct usbip_header_ret_submit	ret_submit;
+		struct usbip_header_cmd_unlink	cmd_unlink;
+		struct usbip_header_ret_unlink	ret_unlink;
+	} u;
+} __packed;
+
+/*
+ * This is the same as usb_iso_packet_descriptor but packed for pdu.
+ */
+struct usbip_iso_packet_descriptor {
+	__u32 offset;
+	__u32 length;			/* expected length */
+	__u32 actual_length;
+	__u32 status;
+} __packed;
+
+enum usbip_side {
+	USBIP_VHCI,
+	USBIP_STUB,
+};
+
+/* event handler */
+#define USBIP_EH_SHUTDOWN	(1 << 0)
+#define USBIP_EH_BYE		(1 << 1)
+#define USBIP_EH_RESET		(1 << 2)
+#define USBIP_EH_UNUSABLE	(1 << 3)
+
+#define SDEV_EVENT_REMOVED   (USBIP_EH_SHUTDOWN | USBIP_EH_RESET | USBIP_EH_BYE)
+#define	SDEV_EVENT_DOWN		(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
+#define	SDEV_EVENT_ERROR_TCP	(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
+#define	SDEV_EVENT_ERROR_SUBMIT	(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
+#define	SDEV_EVENT_ERROR_MALLOC	(USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
+
+#define	VDEV_EVENT_REMOVED	(USBIP_EH_SHUTDOWN | USBIP_EH_BYE)
+#define	VDEV_EVENT_DOWN		(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
+#define	VDEV_EVENT_ERROR_TCP	(USBIP_EH_SHUTDOWN | USBIP_EH_RESET)
+#define	VDEV_EVENT_ERROR_MALLOC	(USBIP_EH_SHUTDOWN | USBIP_EH_UNUSABLE)
+
+/* a common structure for stub_device and vhci_device */
+struct usbip_device {
+	enum usbip_side side;
+	enum usbip_device_status status;
+
+	/* lock for status */
+	spinlock_t lock;
+
+	struct socket *tcp_socket;
+
+	struct task_struct *tcp_rx;
+	struct task_struct *tcp_tx;
+
+	unsigned long event;
+	struct task_struct *eh;
+	wait_queue_head_t eh_waitq;
+
+	struct eh_ops {
+		void (*shutdown)(struct usbip_device *);
+		void (*reset)(struct usbip_device *);
+		void (*unusable)(struct usbip_device *);
+	} eh_ops;
+};
+
+#define kthread_get_run(threadfn, data, namefmt, ...)			   \
+({									   \
+	struct task_struct *__k						   \
+		= kthread_create(threadfn, data, namefmt, ## __VA_ARGS__); \
+	if (!IS_ERR(__k)) {						   \
+		get_task_struct(__k);					   \
+		wake_up_process(__k);					   \
+	}								   \
+	__k;								   \
+})
+
+#define kthread_stop_put(k)		\
+	do {				\
+		kthread_stop(k);	\
+		put_task_struct(k);	\
+	} while (0)
+
+/* usbip_common.c */
+void usbip_dump_urb(struct urb *purb);
+void usbip_dump_header(struct usbip_header *pdu);
+
+int usbip_recv(struct socket *sock, void *buf, int size);
+
+void usbip_pack_pdu(struct usbip_header *pdu, struct urb *urb, int cmd,
+		    int pack);
+void usbip_header_correct_endian(struct usbip_header *pdu, int send);
+
+struct usbip_iso_packet_descriptor*
+usbip_alloc_iso_desc_pdu(struct urb *urb, ssize_t *bufflen);
+
+/* some members of urb must be substituted before. */
+int usbip_recv_iso(struct usbip_device *ud, struct urb *urb);
+void usbip_pad_iso(struct usbip_device *ud, struct urb *urb);
+int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb);
+
+/* usbip_event.c */
+int usbip_start_eh(struct usbip_device *ud);
+void usbip_stop_eh(struct usbip_device *ud);
+void usbip_event_add(struct usbip_device *ud, unsigned long event);
+int usbip_event_happened(struct usbip_device *ud);
+
+static inline int interface_to_busnum(struct usb_interface *interface)
+{
+	struct usb_device *udev = interface_to_usbdev(interface);
+
+	return udev->bus->busnum;
+}
+
+static inline int interface_to_devnum(struct usb_interface *interface)
+{
+	struct usb_device *udev = interface_to_usbdev(interface);
+
+	return udev->devnum;
+}
+
+#endif /* __USBIP_COMMON_H */
diff --git a/drivers/usb/usbip/usbip_event.c b/drivers/usb/usbip/usbip_event.c
new file mode 100644
index 000000000000..64933b993d7a
--- /dev/null
+++ b/drivers/usb/usbip/usbip_event.c
@@ -0,0 +1,128 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <linux/kthread.h>
+#include <linux/export.h>
+
+#include "usbip_common.h"
+
+static int event_handler(struct usbip_device *ud)
+{
+	usbip_dbg_eh("enter\n");
+
+	/*
+	 * Events are handled by only this thread.
+	 */
+	while (usbip_event_happened(ud)) {
+		usbip_dbg_eh("pending event %lx\n", ud->event);
+
+		/*
+		 * NOTE: shutdown must come first.
+		 * Shutdown the device.
+		 */
+		if (ud->event & USBIP_EH_SHUTDOWN) {
+			ud->eh_ops.shutdown(ud);
+			ud->event &= ~USBIP_EH_SHUTDOWN;
+		}
+
+		/* Reset the device. */
+		if (ud->event & USBIP_EH_RESET) {
+			ud->eh_ops.reset(ud);
+			ud->event &= ~USBIP_EH_RESET;
+		}
+
+		/* Mark the device as unusable. */
+		if (ud->event & USBIP_EH_UNUSABLE) {
+			ud->eh_ops.unusable(ud);
+			ud->event &= ~USBIP_EH_UNUSABLE;
+		}
+
+		/* Stop the error handler. */
+		if (ud->event & USBIP_EH_BYE)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int event_handler_loop(void *data)
+{
+	struct usbip_device *ud = data;
+
+	while (!kthread_should_stop()) {
+		wait_event_interruptible(ud->eh_waitq,
+					 usbip_event_happened(ud) ||
+					 kthread_should_stop());
+		usbip_dbg_eh("wakeup\n");
+
+		if (event_handler(ud) < 0)
+			break;
+	}
+
+	return 0;
+}
+
+int usbip_start_eh(struct usbip_device *ud)
+{
+	init_waitqueue_head(&ud->eh_waitq);
+	ud->event = 0;
+
+	ud->eh = kthread_run(event_handler_loop, ud, "usbip_eh");
+	if (IS_ERR(ud->eh)) {
+		pr_warn("Unable to start control thread\n");
+		return PTR_ERR(ud->eh);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(usbip_start_eh);
+
+void usbip_stop_eh(struct usbip_device *ud)
+{
+	if (ud->eh == current)
+		return; /* do not wait for myself */
+
+	kthread_stop(ud->eh);
+	usbip_dbg_eh("usbip_eh has finished\n");
+}
+EXPORT_SYMBOL_GPL(usbip_stop_eh);
+
+void usbip_event_add(struct usbip_device *ud, unsigned long event)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ud->lock, flags);
+	ud->event |= event;
+	wake_up(&ud->eh_waitq);
+	spin_unlock_irqrestore(&ud->lock, flags);
+}
+EXPORT_SYMBOL_GPL(usbip_event_add);
+
+int usbip_event_happened(struct usbip_device *ud)
+{
+	int happened = 0;
+
+	spin_lock(&ud->lock);
+	if (ud->event != 0)
+		happened = 1;
+	spin_unlock(&ud->lock);
+
+	return happened;
+}
+EXPORT_SYMBOL_GPL(usbip_event_happened);
diff --git a/drivers/usb/usbip/usbip_protocol.txt b/drivers/usb/usbip/usbip_protocol.txt
new file mode 100644
index 000000000000..16b6fe27284c
--- /dev/null
+++ b/drivers/usb/usbip/usbip_protocol.txt
@@ -0,0 +1,358 @@
+PRELIMINARY DRAFT, MAY CONTAIN MISTAKES!
+28 Jun 2011
+
+The USB/IP protocol follows a server/client architecture. The server exports the
+USB devices and the clients imports them. The device driver for the exported
+USB device runs on the client machine.
+
+The client may ask for the list of the exported USB devices. To get the list the
+client opens a TCP/IP connection towards the server, and sends an OP_REQ_DEVLIST
+packet on top of the TCP/IP connection (so the actual OP_REQ_DEVLIST may be sent
+in one or more pieces at the low level transport layer). The server sends back
+the OP_REP_DEVLIST packet which lists the exported USB devices. Finally the
+TCP/IP connection is closed.
+
+ virtual host controller                                 usb host
+      "client"                                           "server"
+  (imports USB devices)                             (exports USB devices)
+          |                                                 |
+          |                  OP_REQ_DEVLIST                 |
+          | ----------------------------------------------> |
+          |                                                 |
+          |                  OP_REP_DEVLIST                 |
+          | <---------------------------------------------- |
+          |                                                 |
+
+Once the client knows the list of exported USB devices it may decide to use one
+of them. First the client opens a TCP/IP connection towards the server and
+sends an OP_REQ_IMPORT packet. The server replies with OP_REP_IMPORT. If the
+import was successful the TCP/IP connection remains open and will be used
+to transfer the URB traffic between the client and the server. The client may
+send two types of packets: the USBIP_CMD_SUBMIT to submit an URB, and
+USBIP_CMD_UNLINK to unlink a previously submitted URB. The answers of the
+server may be USBIP_RET_SUBMIT and USBIP_RET_UNLINK respectively.
+
+ virtual host controller                                 usb host
+      "client"                                           "server"
+  (imports USB devices)                             (exports USB devices)
+          |                                                 |
+          |                  OP_REQ_IMPORT                  |
+          | ----------------------------------------------> |
+          |                                                 |
+          |                  OP_REP_IMPORT                  |
+          | <---------------------------------------------- |
+          |                                                 |
+          |                                                 |
+          |            USBIP_CMD_SUBMIT(seqnum = n)         |
+          | ----------------------------------------------> |
+          |                                                 |
+          |            USBIP_RET_SUBMIT(seqnum = n)         |
+          | <---------------------------------------------- |
+          |                        .                        |
+          |                        :                        |
+          |                                                 |
+          |            USBIP_CMD_SUBMIT(seqnum = m)         |
+          | ----------------------------------------------> |
+          |                                                 |
+          |            USBIP_CMD_SUBMIT(seqnum = m+1)       |
+          | ----------------------------------------------> |
+          |                                                 |
+          |            USBIP_CMD_SUBMIT(seqnum = m+2)       |
+          | ----------------------------------------------> |
+          |                                                 |
+          |            USBIP_RET_SUBMIT(seqnum = m)         |
+          | <---------------------------------------------- |
+          |                                                 |
+          |            USBIP_CMD_SUBMIT(seqnum = m+3)       |
+          | ----------------------------------------------> |
+          |                                                 |
+          |            USBIP_RET_SUBMIT(seqnum = m+1)       |
+          | <---------------------------------------------- |
+          |                                                 |
+          |            USBIP_CMD_SUBMIT(seqnum = m+4)       |
+          | ----------------------------------------------> |
+          |                                                 |
+          |            USBIP_RET_SUBMIT(seqnum = m+2)       |
+          | <---------------------------------------------- |
+          |                        .                        |
+          |                        :                        |
+          |                                                 |
+          |               USBIP_CMD_UNLINK                  |
+          | ----------------------------------------------> |
+          |                                                 |
+          |               USBIP_RET_UNLINK                  |
+          | <---------------------------------------------- |
+          |                                                 |
+
+The fields are in network (big endian) byte order meaning that the most significant
+byte (MSB) is stored at the lowest address.
+
+
+OP_REQ_DEVLIST: Retrieve the list of exported USB devices.
+
+ Offset    | Length | Value      | Description
+-----------+--------+------------+---------------------------------------------------
+ 0         | 2      | 0x0100     | Binary-coded decimal USBIP version number: v1.0.0
+-----------+--------+------------+---------------------------------------------------
+ 2         | 2      | 0x8005     | Command code: Retrieve the list of exported USB
+           |        |            |   devices.
+-----------+--------+------------+---------------------------------------------------
+ 4         | 4      | 0x00000000 | Status: unused, shall be set to 0
+
+OP_REP_DEVLIST: Reply with the list of exported USB devices.
+
+ Offset    | Length | Value      | Description
+-----------+--------+------------+---------------------------------------------------
+ 0         | 2      | 0x0100     | Binary-coded decimal USBIP version number: v1.0.0.
+-----------+--------+------------+---------------------------------------------------
+ 2         | 2      | 0x0005     | Reply code: The list of exported USB devices.
+-----------+--------+------------+---------------------------------------------------
+ 4         | 4      | 0x00000000 | Status: 0 for OK
+-----------+--------+------------+---------------------------------------------------
+ 8         | 4      | n          | Number of exported devices: 0 means no exported
+           |        |            |   devices.
+-----------+--------+------------+---------------------------------------------------
+ 0x0C      |        |            | From now on the exported n devices are described,
+           |        |            |   if any. If no devices are exported the message
+           |        |            |   ends with the previous "number of exported
+           |        |            |   devices" field.
+-----------+--------+------------+---------------------------------------------------
+           | 256    |            | path: Path of the device on the host exporting the
+           |        |            |   USB device, string closed with zero byte, e.g.
+           |        |            |   "/sys/devices/pci0000:00/0000:00:1d.1/usb3/3-2"
+           |        |            |   The unused bytes shall be filled with zero
+           |        |            |   bytes.
+-----------+--------+------------+---------------------------------------------------
+ 0x10C     | 32     |            | busid: Bus ID of the exported device, string
+           |        |            |   closed with zero byte, e.g. "3-2". The unused
+           |        |            |   bytes shall be filled with zero bytes.
+-----------+--------+------------+---------------------------------------------------
+ 0x12C     | 4      |            | busnum
+-----------+--------+------------+---------------------------------------------------
+ 0x130     | 4      |            | devnum
+-----------+--------+------------+---------------------------------------------------
+ 0x134     | 4      |            | speed
+-----------+--------+------------+---------------------------------------------------
+ 0x138     | 2      |            | idVendor
+-----------+--------+------------+---------------------------------------------------
+ 0x13A     | 2      |            | idProduct
+-----------+--------+------------+---------------------------------------------------
+ 0x13C     | 2      |            | bcdDevice
+-----------+--------+------------+---------------------------------------------------
+ 0x13E     | 1      |            | bDeviceClass
+-----------+--------+------------+---------------------------------------------------
+ 0x13F     | 1      |            | bDeviceSubClass
+-----------+--------+------------+---------------------------------------------------
+ 0x140     | 1      |            | bDeviceProtocol
+-----------+--------+------------+---------------------------------------------------
+ 0x141     | 1      |            | bConfigurationValue
+-----------+--------+------------+---------------------------------------------------
+ 0x142     | 1      |            | bNumConfigurations
+-----------+--------+------------+---------------------------------------------------
+ 0x143     | 1      |            | bNumInterfaces
+-----------+--------+------------+---------------------------------------------------
+ 0x144     |        | m_0        | From now on each interface is described, all
+           |        |            |   together bNumInterfaces times, with the
+           |        |            |   the following 4 fields:
+-----------+--------+------------+---------------------------------------------------
+           | 1      |            | bInterfaceClass
+-----------+--------+------------+---------------------------------------------------
+ 0x145     | 1      |            | bInterfaceSubClass
+-----------+--------+------------+---------------------------------------------------
+ 0x146     | 1      |            | bInterfaceProtocol
+-----------+--------+------------+---------------------------------------------------
+ 0x147     | 1      |            | padding byte for alignment, shall be set to zero
+-----------+--------+------------+---------------------------------------------------
+ 0xC +     |        |            | The second exported USB device starts at i=1
+ i*0x138 + |        |            | with the busid field.
+ m_(i-1)*4 |        |            |
+
+OP_REQ_IMPORT: Request to import (attach) a remote USB device.
+
+ Offset    | Length | Value      | Description
+-----------+--------+------------+---------------------------------------------------
+ 0         | 2      | 0x0100     | Binary-coded decimal USBIP version number: v1.0.0
+-----------+--------+------------+---------------------------------------------------
+ 2         | 2      | 0x8003     | Command code: import a remote USB device.
+-----------+--------+------------+---------------------------------------------------
+ 4         | 4      | 0x00000000 | Status: unused, shall be set to 0
+-----------+--------+------------+---------------------------------------------------
+ 8         | 32     |            | busid: the busid of the exported device on the
+           |        |            |   remote host. The possible values are taken
+           |        |            |   from the message field OP_REP_DEVLIST.busid.
+           |        |            |   A string closed with zero, the unused bytes
+           |        |            |   shall be filled with zeros.
+-----------+--------+------------+---------------------------------------------------
+
+OP_REP_IMPORT: Reply to import (attach) a remote USB device.
+
+ Offset    | Length | Value      | Description
+-----------+--------+------------+---------------------------------------------------
+ 0         | 2      | 0x0100     | Binary-coded decimal USBIP version number: v1.0.0
+-----------+--------+------------+---------------------------------------------------
+ 2         | 2      | 0x0003     | Reply code: Reply to import.
+-----------+--------+------------+---------------------------------------------------
+ 4         | 4      | 0x00000000 | Status: 0 for OK
+           |        |            |         1 for error
+-----------+--------+------------+---------------------------------------------------
+ 8         |        |            | From now on comes the details of the imported
+           |        |            |   device, if the previous status field was OK (0),
+           |        |            |   otherwise the reply ends with the status field.
+-----------+--------+------------+---------------------------------------------------
+           | 256    |            | path: Path of the device on the host exporting the
+           |        |            |   USB device, string closed with zero byte, e.g.
+           |        |            |   "/sys/devices/pci0000:00/0000:00:1d.1/usb3/3-2"
+           |        |            |   The unused bytes shall be filled with zero
+           |        |            |   bytes.
+-----------+--------+------------+---------------------------------------------------
+ 0x108     | 32     |            | busid: Bus ID of the exported device, string
+           |        |            |   closed with zero byte, e.g. "3-2". The unused
+           |        |            |   bytes shall be filled with zero bytes.
+-----------+--------+------------+---------------------------------------------------
+ 0x128     | 4      |            | busnum
+-----------+--------+------------+---------------------------------------------------
+ 0x12C     | 4      |            | devnum
+-----------+--------+------------+---------------------------------------------------
+ 0x130     | 4      |            | speed
+-----------+--------+------------+---------------------------------------------------
+ 0x134     | 2      |            | idVendor
+-----------+--------+------------+---------------------------------------------------
+ 0x136     | 2      |            | idProduct
+-----------+--------+------------+---------------------------------------------------
+ 0x138     | 2      |            | bcdDevice
+-----------+--------+------------+---------------------------------------------------
+ 0x139     | 1      |            | bDeviceClass
+-----------+--------+------------+---------------------------------------------------
+ 0x13A     | 1      |            | bDeviceSubClass
+-----------+--------+------------+---------------------------------------------------
+ 0x13B     | 1      |            | bDeviceProtocol
+-----------+--------+------------+---------------------------------------------------
+ 0x13C     | 1      |            | bConfigurationValue
+-----------+--------+------------+---------------------------------------------------
+ 0x13D     | 1      |            | bNumConfigurations
+-----------+--------+------------+---------------------------------------------------
+ 0x13E     | 1      |            | bNumInterfaces
+
+USBIP_CMD_SUBMIT: Submit an URB
+
+ Offset    | Length | Value      | Description
+-----------+--------+------------+---------------------------------------------------
+ 0         | 4      | 0x00000001 | command: Submit an URB
+-----------+--------+------------+---------------------------------------------------
+ 4         | 4      |            | seqnum: the sequence number of the URB to submit
+-----------+--------+------------+---------------------------------------------------
+ 8         | 4      |            | devid
+-----------+--------+------------+---------------------------------------------------
+ 0xC       | 4      |            | direction: 0: USBIP_DIR_OUT
+           |        |            |            1: USBIP_DIR_IN
+-----------+--------+------------+---------------------------------------------------
+ 0x10      | 4      |            | ep: endpoint number, possible values are: 0...15
+-----------+--------+------------+---------------------------------------------------
+ 0x14      | 4      |            | transfer_flags: possible values depend on the
+           |        |            |   URB transfer type, see below
+-----------+--------+------------+---------------------------------------------------
+ 0x18      | 4      |            | transfer_buffer_length
+-----------+--------+------------+---------------------------------------------------
+ 0x1C      | 4      |            | start_frame: specify the selected frame to
+           |        |            |   transmit an ISO frame, ignored if URB_ISO_ASAP
+           |        |            |   is specified at transfer_flags
+-----------+--------+------------+---------------------------------------------------
+ 0x20      | 4      |            | number_of_packets: number of ISO packets
+-----------+--------+------------+---------------------------------------------------
+ 0x24      | 4      |            | interval: maximum time for the request on the
+           |        |            |   server-side host controller
+-----------+--------+------------+---------------------------------------------------
+ 0x28      | 8      |            | setup: data bytes for USB setup, filled with
+           |        |            |   zeros if not used
+-----------+--------+------------+---------------------------------------------------
+ 0x30      |        |            | URB data. For ISO transfers the padding between
+           |        |            |   each ISO packets is not transmitted.
+
+
+  Allowed transfer_flags  | value      | control | interrupt | bulk     | isochronous
+ -------------------------+------------+---------+-----------+----------+-------------
+  URB_SHORT_NOT_OK        | 0x00000001 | only in | only in   | only in  | no
+  URB_ISO_ASAP            | 0x00000002 | no      | no        | no       | yes
+  URB_NO_TRANSFER_DMA_MAP | 0x00000004 | yes     | yes       | yes      | yes
+  URB_NO_FSBR             | 0x00000020 | yes     | no        | no       | no
+  URB_ZERO_PACKET         | 0x00000040 | no      | no        | only out | no
+  URB_NO_INTERRUPT        | 0x00000080 | yes     | yes       | yes      | yes
+  URB_FREE_BUFFER         | 0x00000100 | yes     | yes       | yes      | yes
+  URB_DIR_MASK            | 0x00000200 | yes     | yes       | yes      | yes
+
+
+USBIP_RET_SUBMIT: Reply for submitting an URB
+
+ Offset    | Length | Value      | Description
+-----------+--------+------------+---------------------------------------------------
+ 0         | 4      | 0x00000003 | command
+-----------+--------+------------+---------------------------------------------------
+ 4         | 4      |            | seqnum: URB sequence number
+-----------+--------+------------+---------------------------------------------------
+ 8         | 4      |            | devid
+-----------+--------+------------+---------------------------------------------------
+ 0xC       | 4      |            | direction: 0: USBIP_DIR_OUT
+           |        |            |            1: USBIP_DIR_IN
+-----------+--------+------------+---------------------------------------------------
+ 0x10      | 4      |            | ep: endpoint number
+-----------+--------+------------+---------------------------------------------------
+ 0x14      | 4      |            | status: zero for successful URB transaction,
+           |        |            |   otherwise some kind of error happened.
+-----------+--------+------------+---------------------------------------------------
+ 0x18      | 4      | n          | actual_length: number of URB data bytes
+-----------+--------+------------+---------------------------------------------------
+ 0x1C      | 4      |            | start_frame: for an ISO frame the actually
+           |        |            |   selected frame for transmit.
+-----------+--------+------------+---------------------------------------------------
+ 0x20      | 4      |            | number_of_packets
+-----------+--------+------------+---------------------------------------------------
+ 0x24      | 4      |            | error_count
+-----------+--------+------------+---------------------------------------------------
+ 0x28      | 8      |            | setup: data bytes for USB setup, filled with
+           |        |            |   zeros if not used
+-----------+--------+------------+---------------------------------------------------
+ 0x30      | n      |            | URB data bytes. For ISO transfers the padding
+           |        |            |   between each ISO packets is not transmitted.
+
+USBIP_CMD_UNLINK: Unlink an URB
+
+ Offset    | Length | Value      | Description
+-----------+--------+------------+---------------------------------------------------
+ 0         | 4      | 0x00000002 | command: URB unlink command
+-----------+--------+------------+---------------------------------------------------
+ 4         | 4      |            | seqnum: URB sequence number to unlink: FIXME: is this so?
+-----------+--------+------------+---------------------------------------------------
+ 8         | 4      |            | devid
+-----------+--------+------------+---------------------------------------------------
+ 0xC       | 4      |            | direction: 0: USBIP_DIR_OUT
+           |        |            |            1: USBIP_DIR_IN
+-----------+--------+------------+---------------------------------------------------
+ 0x10      | 4      |            | ep: endpoint number: zero
+-----------+--------+------------+---------------------------------------------------
+ 0x14      | 4      |            | seqnum: the URB sequence number given previously
+           |        |            |   at USBIP_CMD_SUBMIT.seqnum field
+-----------+--------+------------+---------------------------------------------------
+ 0x30      | n      |            | URB data bytes. For ISO transfers the padding
+           |        |            |   between each ISO packets is not transmitted.
+
+USBIP_RET_UNLINK: Reply for URB unlink
+
+ Offset    | Length | Value      | Description
+-----------+--------+------------+---------------------------------------------------
+ 0         | 4      | 0x00000004 | command: reply for the URB unlink command
+-----------+--------+------------+---------------------------------------------------
+ 4         | 4      |            | seqnum: the unlinked URB sequence number
+-----------+--------+------------+---------------------------------------------------
+ 8         | 4      |            | devid
+-----------+--------+------------+---------------------------------------------------
+ 0xC       | 4      |            | direction: 0: USBIP_DIR_OUT
+           |        |            |            1: USBIP_DIR_IN
+-----------+--------+------------+---------------------------------------------------
+ 0x10      | 4      |            | ep: endpoint number
+-----------+--------+------------+---------------------------------------------------
+ 0x14      | 4      |            | status: This is the value contained in the
+           |        |            |   urb->status in the URB completition handler.
+           |        |            |   FIXME: a better explanation needed.
+-----------+--------+------------+---------------------------------------------------
+ 0x30      | n      |            | URB data bytes. For ISO transfers the padding
+           |        |            |   between each ISO packets is not transmitted.
diff --git a/drivers/usb/usbip/vhci.h b/drivers/usb/usbip/vhci.h
new file mode 100644
index 000000000000..a863a98a91ce
--- /dev/null
+++ b/drivers/usb/usbip/vhci.h
@@ -0,0 +1,129 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __USBIP_VHCI_H
+#define __USBIP_VHCI_H
+
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
+#include <linux/wait.h>
+
+struct vhci_device {
+	struct usb_device *udev;
+
+	/*
+	 * devid specifies a remote usb device uniquely instead
+	 * of combination of busnum and devnum.
+	 */
+	__u32 devid;
+
+	/* speed of a remote device */
+	enum usb_device_speed speed;
+
+	/* vhci root-hub port to which this device is attached */
+	__u32 rhport;
+
+	struct usbip_device ud;
+
+	/* lock for the below link lists */
+	spinlock_t priv_lock;
+
+	/* vhci_priv is linked to one of them. */
+	struct list_head priv_tx;
+	struct list_head priv_rx;
+
+	/* vhci_unlink is linked to one of them */
+	struct list_head unlink_tx;
+	struct list_head unlink_rx;
+
+	/* vhci_tx thread sleeps for this queue */
+	wait_queue_head_t waitq_tx;
+};
+
+/* urb->hcpriv, use container_of() */
+struct vhci_priv {
+	unsigned long seqnum;
+	struct list_head list;
+
+	struct vhci_device *vdev;
+	struct urb *urb;
+};
+
+struct vhci_unlink {
+	/* seqnum of this request */
+	unsigned long seqnum;
+
+	struct list_head list;
+
+	/* seqnum of the unlink target */
+	unsigned long unlink_seqnum;
+};
+
+/* Number of supported ports. Value has an upperbound of USB_MAXCHILDREN */
+#define VHCI_NPORTS 8
+
+/* for usb_bus.hcpriv */
+struct vhci_hcd {
+	spinlock_t lock;
+
+	u32 port_status[VHCI_NPORTS];
+
+	unsigned resuming:1;
+	unsigned long re_timeout;
+
+	atomic_t seqnum;
+
+	/*
+	 * NOTE:
+	 * wIndex shows the port number and begins from 1.
+	 * But, the index of this array begins from 0.
+	 */
+	struct vhci_device vdev[VHCI_NPORTS];
+};
+
+extern struct vhci_hcd *the_controller;
+extern const struct attribute_group dev_attr_group;
+
+/* vhci_hcd.c */
+void rh_port_connect(int rhport, enum usb_device_speed speed);
+
+/* vhci_rx.c */
+struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum);
+int vhci_rx_loop(void *data);
+
+/* vhci_tx.c */
+int vhci_tx_loop(void *data);
+
+static inline struct vhci_device *port_to_vdev(__u32 port)
+{
+	return &the_controller->vdev[port];
+}
+
+static inline struct vhci_hcd *hcd_to_vhci(struct usb_hcd *hcd)
+{
+	return (struct vhci_hcd *) (hcd->hcd_priv);
+}
+
+static inline struct usb_hcd *vhci_to_hcd(struct vhci_hcd *vhci)
+{
+	return container_of((void *) vhci, struct usb_hcd, hcd_priv);
+}
+
+static inline struct device *vhci_dev(struct vhci_hcd *vhci)
+{
+	return vhci_to_hcd(vhci)->self.controller;
+}
+
+#endif /* __USBIP_VHCI_H */
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
new file mode 100644
index 000000000000..c02374b6049c
--- /dev/null
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -0,0 +1,1171 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <linux/init.h>
+#include <linux/file.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "usbip_common.h"
+#include "vhci.h"
+
+#define DRIVER_AUTHOR "Takahiro Hirofuchi"
+#define DRIVER_DESC "USB/IP 'Virtual' Host Controller (VHCI) Driver"
+
+/*
+ * TODO
+ *	- update root hub emulation
+ *	- move the emulation code to userland ?
+ *		porting to other operating systems
+ *		minimize kernel code
+ *	- add suspend/resume code
+ *	- clean up everything
+ */
+
+/* See usb gadget dummy hcd */
+
+static int vhci_hub_status(struct usb_hcd *hcd, char *buff);
+static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
+			    u16 wIndex, char *buff, u16 wLength);
+static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
+			    gfp_t mem_flags);
+static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status);
+static int vhci_start(struct usb_hcd *vhci_hcd);
+static void vhci_stop(struct usb_hcd *hcd);
+static int vhci_get_frame_number(struct usb_hcd *hcd);
+
+static const char driver_name[] = "vhci_hcd";
+static const char driver_desc[] = "USB/IP Virtual Host Controller";
+
+struct vhci_hcd *the_controller;
+
+static const char * const bit_desc[] = {
+	"CONNECTION",		/*0*/
+	"ENABLE",		/*1*/
+	"SUSPEND",		/*2*/
+	"OVER_CURRENT",		/*3*/
+	"RESET",		/*4*/
+	"R5",			/*5*/
+	"R6",			/*6*/
+	"R7",			/*7*/
+	"POWER",		/*8*/
+	"LOWSPEED",		/*9*/
+	"HIGHSPEED",		/*10*/
+	"PORT_TEST",		/*11*/
+	"INDICATOR",		/*12*/
+	"R13",			/*13*/
+	"R14",			/*14*/
+	"R15",			/*15*/
+	"C_CONNECTION",		/*16*/
+	"C_ENABLE",		/*17*/
+	"C_SUSPEND",		/*18*/
+	"C_OVER_CURRENT",	/*19*/
+	"C_RESET",		/*20*/
+	"R21",			/*21*/
+	"R22",			/*22*/
+	"R23",			/*23*/
+	"R24",			/*24*/
+	"R25",			/*25*/
+	"R26",			/*26*/
+	"R27",			/*27*/
+	"R28",			/*28*/
+	"R29",			/*29*/
+	"R30",			/*30*/
+	"R31",			/*31*/
+};
+
+static void dump_port_status_diff(u32 prev_status, u32 new_status)
+{
+	int i = 0;
+	u32 bit = 1;
+
+	pr_debug("status prev -> new: %08x -> %08x\n", prev_status, new_status);
+	while (bit) {
+		u32 prev = prev_status & bit;
+		u32 new = new_status & bit;
+		char change;
+
+		if (!prev && new)
+			change = '+';
+		else if (prev && !new)
+			change = '-';
+		else
+			change = ' ';
+
+		if (prev || new)
+			pr_debug(" %c%s\n", change, bit_desc[i]);
+		bit <<= 1;
+		i++;
+	}
+	pr_debug("\n");
+}
+
+void rh_port_connect(int rhport, enum usb_device_speed speed)
+{
+	usbip_dbg_vhci_rh("rh_port_connect %d\n", rhport);
+
+	spin_lock(&the_controller->lock);
+
+	the_controller->port_status[rhport] |= USB_PORT_STAT_CONNECTION
+		| (1 << USB_PORT_FEAT_C_CONNECTION);
+
+	switch (speed) {
+	case USB_SPEED_HIGH:
+		the_controller->port_status[rhport] |= USB_PORT_STAT_HIGH_SPEED;
+		break;
+	case USB_SPEED_LOW:
+		the_controller->port_status[rhport] |= USB_PORT_STAT_LOW_SPEED;
+		break;
+	default:
+		break;
+	}
+
+	spin_unlock(&the_controller->lock);
+
+	usb_hcd_poll_rh_status(vhci_to_hcd(the_controller));
+}
+
+static void rh_port_disconnect(int rhport)
+{
+	usbip_dbg_vhci_rh("rh_port_disconnect %d\n", rhport);
+
+	spin_lock(&the_controller->lock);
+
+	the_controller->port_status[rhport] &= ~USB_PORT_STAT_CONNECTION;
+	the_controller->port_status[rhport] |=
+					(1 << USB_PORT_FEAT_C_CONNECTION);
+
+	spin_unlock(&the_controller->lock);
+	usb_hcd_poll_rh_status(vhci_to_hcd(the_controller));
+}
+
+#define PORT_C_MASK				\
+	((USB_PORT_STAT_C_CONNECTION		\
+	  | USB_PORT_STAT_C_ENABLE		\
+	  | USB_PORT_STAT_C_SUSPEND		\
+	  | USB_PORT_STAT_C_OVERCURRENT		\
+	  | USB_PORT_STAT_C_RESET) << 16)
+
+/*
+ * Returns 0 if the status hasn't changed, or the number of bytes in buf.
+ * Ports are 0-indexed from the HCD point of view,
+ * and 1-indexed from the USB core pointer of view.
+ *
+ * @buf: a bitmap to show which port status has been changed.
+ *  bit  0: reserved
+ *  bit  1: the status of port 0 has been changed.
+ *  bit  2: the status of port 1 has been changed.
+ *  ...
+ */
+static int vhci_hub_status(struct usb_hcd *hcd, char *buf)
+{
+	struct vhci_hcd	*vhci;
+	int		retval;
+	int		rhport;
+	int		changed = 0;
+
+	retval = DIV_ROUND_UP(VHCI_NPORTS + 1, 8);
+	memset(buf, 0, retval);
+
+	vhci = hcd_to_vhci(hcd);
+
+	spin_lock(&vhci->lock);
+	if (!HCD_HW_ACCESSIBLE(hcd)) {
+		usbip_dbg_vhci_rh("hw accessible flag not on?\n");
+		goto done;
+	}
+
+	/* check pseudo status register for each port */
+	for (rhport = 0; rhport < VHCI_NPORTS; rhport++) {
+		if ((vhci->port_status[rhport] & PORT_C_MASK)) {
+			/* The status of a port has been changed, */
+			usbip_dbg_vhci_rh("port %d status changed\n", rhport);
+
+			buf[(rhport + 1) / 8] |= 1 << (rhport + 1) % 8;
+			changed = 1;
+		}
+	}
+
+	if ((hcd->state == HC_STATE_SUSPENDED) && (changed == 1))
+		usb_hcd_resume_root_hub(hcd);
+
+done:
+	spin_unlock(&vhci->lock);
+	return changed ? retval : 0;
+}
+
+static inline void hub_descriptor(struct usb_hub_descriptor *desc)
+{
+	memset(desc, 0, sizeof(*desc));
+	desc->bDescriptorType = 0x29;
+	desc->bDescLength = 9;
+	desc->wHubCharacteristics = (__constant_cpu_to_le16(0x0001));
+	desc->bNbrPorts = VHCI_NPORTS;
+	desc->u.hs.DeviceRemovable[0] = 0xff;
+	desc->u.hs.DeviceRemovable[1] = 0xff;
+}
+
+static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
+			    u16 wIndex, char *buf, u16 wLength)
+{
+	struct vhci_hcd	*dum;
+	int             retval = 0;
+	int		rhport;
+
+	u32 prev_port_status[VHCI_NPORTS];
+
+	if (!HCD_HW_ACCESSIBLE(hcd))
+		return -ETIMEDOUT;
+
+	/*
+	 * NOTE:
+	 * wIndex shows the port number and begins from 1.
+	 */
+	usbip_dbg_vhci_rh("typeReq %x wValue %x wIndex %x\n", typeReq, wValue,
+			  wIndex);
+	if (wIndex > VHCI_NPORTS)
+		pr_err("invalid port number %d\n", wIndex);
+	rhport = ((__u8)(wIndex & 0x00ff)) - 1;
+
+	dum = hcd_to_vhci(hcd);
+
+	spin_lock(&dum->lock);
+
+	/* store old status and compare now and old later */
+	if (usbip_dbg_flag_vhci_rh) {
+		memcpy(prev_port_status, dum->port_status,
+			sizeof(prev_port_status));
+	}
+
+	switch (typeReq) {
+	case ClearHubFeature:
+		usbip_dbg_vhci_rh(" ClearHubFeature\n");
+		break;
+	case ClearPortFeature:
+		switch (wValue) {
+		case USB_PORT_FEAT_SUSPEND:
+			if (dum->port_status[rhport] & USB_PORT_STAT_SUSPEND) {
+				/* 20msec signaling */
+				dum->resuming = 1;
+				dum->re_timeout =
+					jiffies + msecs_to_jiffies(20);
+			}
+			break;
+		case USB_PORT_FEAT_POWER:
+			usbip_dbg_vhci_rh(
+				" ClearPortFeature: USB_PORT_FEAT_POWER\n");
+			dum->port_status[rhport] = 0;
+			dum->resuming = 0;
+			break;
+		case USB_PORT_FEAT_C_RESET:
+			usbip_dbg_vhci_rh(
+				" ClearPortFeature: USB_PORT_FEAT_C_RESET\n");
+			switch (dum->vdev[rhport].speed) {
+			case USB_SPEED_HIGH:
+				dum->port_status[rhport] |=
+					USB_PORT_STAT_HIGH_SPEED;
+				break;
+			case USB_SPEED_LOW:
+				dum->port_status[rhport] |=
+					USB_PORT_STAT_LOW_SPEED;
+				break;
+			default:
+				break;
+			}
+		default:
+			usbip_dbg_vhci_rh(" ClearPortFeature: default %x\n",
+					  wValue);
+			dum->port_status[rhport] &= ~(1 << wValue);
+			break;
+		}
+		break;
+	case GetHubDescriptor:
+		usbip_dbg_vhci_rh(" GetHubDescriptor\n");
+		hub_descriptor((struct usb_hub_descriptor *) buf);
+		break;
+	case GetHubStatus:
+		usbip_dbg_vhci_rh(" GetHubStatus\n");
+		*(__le32 *) buf = cpu_to_le32(0);
+		break;
+	case GetPortStatus:
+		usbip_dbg_vhci_rh(" GetPortStatus port %x\n", wIndex);
+		if (wIndex > VHCI_NPORTS || wIndex < 1) {
+			pr_err("invalid port number %d\n", wIndex);
+			retval = -EPIPE;
+		}
+
+		/* we do not care about resume. */
+
+		/* whoever resets or resumes must GetPortStatus to
+		 * complete it!!
+		 */
+		if (dum->resuming && time_after(jiffies, dum->re_timeout)) {
+			dum->port_status[rhport] |=
+				(1 << USB_PORT_FEAT_C_SUSPEND);
+			dum->port_status[rhport] &=
+				~(1 << USB_PORT_FEAT_SUSPEND);
+			dum->resuming = 0;
+			dum->re_timeout = 0;
+		}
+
+		if ((dum->port_status[rhport] & (1 << USB_PORT_FEAT_RESET)) !=
+		    0 && time_after(jiffies, dum->re_timeout)) {
+			dum->port_status[rhport] |=
+				(1 << USB_PORT_FEAT_C_RESET);
+			dum->port_status[rhport] &=
+				~(1 << USB_PORT_FEAT_RESET);
+			dum->re_timeout = 0;
+
+			if (dum->vdev[rhport].ud.status ==
+			    VDEV_ST_NOTASSIGNED) {
+				usbip_dbg_vhci_rh(
+					" enable rhport %d (status %u)\n",
+					rhport,
+					dum->vdev[rhport].ud.status);
+				dum->port_status[rhport] |=
+					USB_PORT_STAT_ENABLE;
+			}
+		}
+		((__le16 *) buf)[0] = cpu_to_le16(dum->port_status[rhport]);
+		((__le16 *) buf)[1] =
+			cpu_to_le16(dum->port_status[rhport] >> 16);
+
+		usbip_dbg_vhci_rh(" GetPortStatus bye %x %x\n", ((u16 *)buf)[0],
+				  ((u16 *)buf)[1]);
+		break;
+	case SetHubFeature:
+		usbip_dbg_vhci_rh(" SetHubFeature\n");
+		retval = -EPIPE;
+		break;
+	case SetPortFeature:
+		switch (wValue) {
+		case USB_PORT_FEAT_SUSPEND:
+			usbip_dbg_vhci_rh(
+				" SetPortFeature: USB_PORT_FEAT_SUSPEND\n");
+			break;
+		case USB_PORT_FEAT_RESET:
+			usbip_dbg_vhci_rh(
+				" SetPortFeature: USB_PORT_FEAT_RESET\n");
+			/* if it's already running, disconnect first */
+			if (dum->port_status[rhport] & USB_PORT_STAT_ENABLE) {
+				dum->port_status[rhport] &=
+					~(USB_PORT_STAT_ENABLE |
+					  USB_PORT_STAT_LOW_SPEED |
+					  USB_PORT_STAT_HIGH_SPEED);
+				/* FIXME test that code path! */
+			}
+			/* 50msec reset signaling */
+			dum->re_timeout = jiffies + msecs_to_jiffies(50);
+
+			/* FALLTHROUGH */
+		default:
+			usbip_dbg_vhci_rh(" SetPortFeature: default %d\n",
+					  wValue);
+			dum->port_status[rhport] |= (1 << wValue);
+			break;
+		}
+		break;
+
+	default:
+		pr_err("default: no such request\n");
+
+		/* "protocol stall" on error */
+		retval = -EPIPE;
+	}
+
+	if (usbip_dbg_flag_vhci_rh) {
+		pr_debug("port %d\n", rhport);
+		/* Only dump valid port status */
+		if (rhport >= 0) {
+			dump_port_status_diff(prev_port_status[rhport],
+					      dum->port_status[rhport]);
+		}
+	}
+	usbip_dbg_vhci_rh(" bye\n");
+
+	spin_unlock(&dum->lock);
+
+	return retval;
+}
+
+static struct vhci_device *get_vdev(struct usb_device *udev)
+{
+	int i;
+
+	if (!udev)
+		return NULL;
+
+	for (i = 0; i < VHCI_NPORTS; i++)
+		if (the_controller->vdev[i].udev == udev)
+			return port_to_vdev(i);
+
+	return NULL;
+}
+
+static void vhci_tx_urb(struct urb *urb)
+{
+	struct vhci_device *vdev = get_vdev(urb->dev);
+	struct vhci_priv *priv;
+
+	if (!vdev) {
+		pr_err("could not get virtual device");
+		return;
+	}
+
+	priv = kzalloc(sizeof(struct vhci_priv), GFP_ATOMIC);
+	if (!priv) {
+		usbip_event_add(&vdev->ud, VDEV_EVENT_ERROR_MALLOC);
+		return;
+	}
+
+	spin_lock(&vdev->priv_lock);
+
+	priv->seqnum = atomic_inc_return(&the_controller->seqnum);
+	if (priv->seqnum == 0xffff)
+		dev_info(&urb->dev->dev, "seqnum max\n");
+
+	priv->vdev = vdev;
+	priv->urb = urb;
+
+	urb->hcpriv = (void *) priv;
+
+	list_add_tail(&priv->list, &vdev->priv_tx);
+
+	wake_up(&vdev->waitq_tx);
+	spin_unlock(&vdev->priv_lock);
+}
+
+static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
+			    gfp_t mem_flags)
+{
+	struct device *dev = &urb->dev->dev;
+	int ret = 0;
+	struct vhci_device *vdev;
+
+	usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n",
+			  hcd, urb, mem_flags);
+
+	/* patch to usb_sg_init() is in 2.5.60 */
+	BUG_ON(!urb->transfer_buffer && urb->transfer_buffer_length);
+
+	spin_lock(&the_controller->lock);
+
+	if (urb->status != -EINPROGRESS) {
+		dev_err(dev, "URB already unlinked!, status %d\n", urb->status);
+		spin_unlock(&the_controller->lock);
+		return urb->status;
+	}
+
+	vdev = port_to_vdev(urb->dev->portnum-1);
+
+	/* refuse enqueue for dead connection */
+	spin_lock(&vdev->ud.lock);
+	if (vdev->ud.status == VDEV_ST_NULL ||
+	    vdev->ud.status == VDEV_ST_ERROR) {
+		dev_err(dev, "enqueue for inactive port %d\n", vdev->rhport);
+		spin_unlock(&vdev->ud.lock);
+		spin_unlock(&the_controller->lock);
+		return -ENODEV;
+	}
+	spin_unlock(&vdev->ud.lock);
+
+	ret = usb_hcd_link_urb_to_ep(hcd, urb);
+	if (ret)
+		goto no_need_unlink;
+
+	/*
+	 * The enumeration process is as follows;
+	 *
+	 *  1. Get_Descriptor request to DevAddrs(0) EndPoint(0)
+	 *     to get max packet length of default pipe
+	 *
+	 *  2. Set_Address request to DevAddr(0) EndPoint(0)
+	 *
+	 */
+	if (usb_pipedevice(urb->pipe) == 0) {
+		__u8 type = usb_pipetype(urb->pipe);
+		struct usb_ctrlrequest *ctrlreq =
+			(struct usb_ctrlrequest *) urb->setup_packet;
+
+		if (type != PIPE_CONTROL || !ctrlreq) {
+			dev_err(dev, "invalid request to devnum 0\n");
+			ret = -EINVAL;
+			goto no_need_xmit;
+		}
+
+		switch (ctrlreq->bRequest) {
+		case USB_REQ_SET_ADDRESS:
+			/* set_address may come when a device is reset */
+			dev_info(dev, "SetAddress Request (%d) to port %d\n",
+				 ctrlreq->wValue, vdev->rhport);
+
+			if (vdev->udev)
+				usb_put_dev(vdev->udev);
+			vdev->udev = usb_get_dev(urb->dev);
+
+			spin_lock(&vdev->ud.lock);
+			vdev->ud.status = VDEV_ST_USED;
+			spin_unlock(&vdev->ud.lock);
+
+			if (urb->status == -EINPROGRESS) {
+				/* This request is successfully completed. */
+				/* If not -EINPROGRESS, possibly unlinked. */
+				urb->status = 0;
+			}
+
+			goto no_need_xmit;
+
+		case USB_REQ_GET_DESCRIPTOR:
+			if (ctrlreq->wValue == cpu_to_le16(USB_DT_DEVICE << 8))
+				usbip_dbg_vhci_hc(
+					"Not yet?:Get_Descriptor to device 0 (get max pipe size)\n");
+
+			if (vdev->udev)
+				usb_put_dev(vdev->udev);
+			vdev->udev = usb_get_dev(urb->dev);
+			goto out;
+
+		default:
+			/* NOT REACHED */
+			dev_err(dev,
+				"invalid request to devnum 0 bRequest %u, wValue %u\n",
+				ctrlreq->bRequest,
+				ctrlreq->wValue);
+			ret =  -EINVAL;
+			goto no_need_xmit;
+		}
+
+	}
+
+out:
+	vhci_tx_urb(urb);
+	spin_unlock(&the_controller->lock);
+
+	return 0;
+
+no_need_xmit:
+	usb_hcd_unlink_urb_from_ep(hcd, urb);
+no_need_unlink:
+	spin_unlock(&the_controller->lock);
+	usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status);
+	return ret;
+}
+
+/*
+ * vhci_rx gives back the urb after receiving the reply of the urb.  If an
+ * unlink pdu is sent or not, vhci_rx receives a normal return pdu and gives
+ * back its urb. For the driver unlinking the urb, the content of the urb is
+ * not important, but the calling to its completion handler is important; the
+ * completion of unlinking is notified by the completion handler.
+ *
+ *
+ * CLIENT SIDE
+ *
+ * - When vhci_hcd receives RET_SUBMIT,
+ *
+ *	- case 1a). the urb of the pdu is not unlinking.
+ *		- normal case
+ *		=> just give back the urb
+ *
+ *	- case 1b). the urb of the pdu is unlinking.
+ *		- usbip.ko will return a reply of the unlinking request.
+ *		=> give back the urb now and go to case 2b).
+ *
+ * - When vhci_hcd receives RET_UNLINK,
+ *
+ *	- case 2a). a submit request is still pending in vhci_hcd.
+ *		- urb was really pending in usbip.ko and urb_unlink_urb() was
+ *		  completed there.
+ *		=> free a pending submit request
+ *		=> notify unlink completeness by giving back the urb
+ *
+ *	- case 2b). a submit request is *not* pending in vhci_hcd.
+ *		- urb was already given back to the core driver.
+ *		=> do not give back the urb
+ *
+ *
+ * SERVER SIDE
+ *
+ * - When usbip receives CMD_UNLINK,
+ *
+ *	- case 3a). the urb of the unlink request is now in submission.
+ *		=> do usb_unlink_urb().
+ *		=> after the unlink is completed, send RET_UNLINK.
+ *
+ *	- case 3b). the urb of the unlink request is not in submission.
+ *		- may be already completed or never be received
+ *		=> send RET_UNLINK
+ *
+ */
+static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
+{
+	struct vhci_priv *priv;
+	struct vhci_device *vdev;
+
+	pr_info("dequeue a urb %p\n", urb);
+
+	spin_lock(&the_controller->lock);
+
+	priv = urb->hcpriv;
+	if (!priv) {
+		/* URB was never linked! or will be soon given back by
+		 * vhci_rx. */
+		spin_unlock(&the_controller->lock);
+		return 0;
+	}
+
+	{
+		int ret = 0;
+
+		ret = usb_hcd_check_unlink_urb(hcd, urb, status);
+		if (ret) {
+			spin_unlock(&the_controller->lock);
+			return ret;
+		}
+	}
+
+	 /* send unlink request here? */
+	vdev = priv->vdev;
+
+	if (!vdev->ud.tcp_socket) {
+		/* tcp connection is closed */
+		spin_lock(&vdev->priv_lock);
+
+		pr_info("device %p seems to be disconnected\n", vdev);
+		list_del(&priv->list);
+		kfree(priv);
+		urb->hcpriv = NULL;
+
+		spin_unlock(&vdev->priv_lock);
+
+		/*
+		 * If tcp connection is alive, we have sent CMD_UNLINK.
+		 * vhci_rx will receive RET_UNLINK and give back the URB.
+		 * Otherwise, we give back it here.
+		 */
+		pr_info("gives back urb %p\n", urb);
+
+		usb_hcd_unlink_urb_from_ep(hcd, urb);
+
+		spin_unlock(&the_controller->lock);
+		usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
+				     urb->status);
+		spin_lock(&the_controller->lock);
+
+	} else {
+		/* tcp connection is alive */
+		struct vhci_unlink *unlink;
+
+		spin_lock(&vdev->priv_lock);
+
+		/* setup CMD_UNLINK pdu */
+		unlink = kzalloc(sizeof(struct vhci_unlink), GFP_ATOMIC);
+		if (!unlink) {
+			spin_unlock(&vdev->priv_lock);
+			spin_unlock(&the_controller->lock);
+			usbip_event_add(&vdev->ud, VDEV_EVENT_ERROR_MALLOC);
+			return -ENOMEM;
+		}
+
+		unlink->seqnum = atomic_inc_return(&the_controller->seqnum);
+		if (unlink->seqnum == 0xffff)
+			pr_info("seqnum max\n");
+
+		unlink->unlink_seqnum = priv->seqnum;
+
+		pr_info("device %p seems to be still connected\n", vdev);
+
+		/* send cmd_unlink and try to cancel the pending URB in the
+		 * peer */
+		list_add_tail(&unlink->list, &vdev->unlink_tx);
+		wake_up(&vdev->waitq_tx);
+
+		spin_unlock(&vdev->priv_lock);
+	}
+
+	spin_unlock(&the_controller->lock);
+
+	usbip_dbg_vhci_hc("leave\n");
+	return 0;
+}
+
+static void vhci_device_unlink_cleanup(struct vhci_device *vdev)
+{
+	struct vhci_unlink *unlink, *tmp;
+
+	spin_lock(&the_controller->lock);
+	spin_lock(&vdev->priv_lock);
+
+	list_for_each_entry_safe(unlink, tmp, &vdev->unlink_tx, list) {
+		pr_info("unlink cleanup tx %lu\n", unlink->unlink_seqnum);
+		list_del(&unlink->list);
+		kfree(unlink);
+	}
+
+	while (!list_empty(&vdev->unlink_rx)) {
+		struct urb *urb;
+
+		unlink = list_first_entry(&vdev->unlink_rx, struct vhci_unlink,
+			list);
+
+		/* give back URB of unanswered unlink request */
+		pr_info("unlink cleanup rx %lu\n", unlink->unlink_seqnum);
+
+		urb = pickup_urb_and_free_priv(vdev, unlink->unlink_seqnum);
+		if (!urb) {
+			pr_info("the urb (seqnum %lu) was already given back\n",
+				unlink->unlink_seqnum);
+			list_del(&unlink->list);
+			kfree(unlink);
+			continue;
+		}
+
+		urb->status = -ENODEV;
+
+		usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
+
+		list_del(&unlink->list);
+
+		spin_unlock(&vdev->priv_lock);
+		spin_unlock(&the_controller->lock);
+
+		usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
+				     urb->status);
+
+		spin_lock(&the_controller->lock);
+		spin_lock(&vdev->priv_lock);
+
+		kfree(unlink);
+	}
+
+	spin_unlock(&vdev->priv_lock);
+	spin_unlock(&the_controller->lock);
+}
+
+/*
+ * The important thing is that only one context begins cleanup.
+ * This is why error handling and cleanup become simple.
+ * We do not want to consider race condition as possible.
+ */
+static void vhci_shutdown_connection(struct usbip_device *ud)
+{
+	struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
+
+	/* need this? see stub_dev.c */
+	if (ud->tcp_socket) {
+		pr_debug("shutdown tcp_socket %p\n", ud->tcp_socket);
+		kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
+	}
+
+	/* kill threads related to this sdev */
+	if (vdev->ud.tcp_rx) {
+		kthread_stop_put(vdev->ud.tcp_rx);
+		vdev->ud.tcp_rx = NULL;
+	}
+	if (vdev->ud.tcp_tx) {
+		kthread_stop_put(vdev->ud.tcp_tx);
+		vdev->ud.tcp_tx = NULL;
+	}
+	pr_info("stop threads\n");
+
+	/* active connection is closed */
+	if (vdev->ud.tcp_socket) {
+		sockfd_put(vdev->ud.tcp_socket);
+		vdev->ud.tcp_socket = NULL;
+	}
+	pr_info("release socket\n");
+
+	vhci_device_unlink_cleanup(vdev);
+
+	/*
+	 * rh_port_disconnect() is a trigger of ...
+	 *   usb_disable_device():
+	 *	disable all the endpoints for a USB device.
+	 *   usb_disable_endpoint():
+	 *	disable endpoints. pending urbs are unlinked(dequeued).
+	 *
+	 * NOTE: After calling rh_port_disconnect(), the USB device drivers of a
+	 * detached device should release used urbs in a cleanup function (i.e.
+	 * xxx_disconnect()). Therefore, vhci_hcd does not need to release
+	 * pushed urbs and their private data in this function.
+	 *
+	 * NOTE: vhci_dequeue() must be considered carefully. When shutting down
+	 * a connection, vhci_shutdown_connection() expects vhci_dequeue()
+	 * gives back pushed urbs and frees their private data by request of
+	 * the cleanup function of a USB driver. When unlinking a urb with an
+	 * active connection, vhci_dequeue() does not give back the urb which
+	 * is actually given back by vhci_rx after receiving its return pdu.
+	 *
+	 */
+	rh_port_disconnect(vdev->rhport);
+
+	pr_info("disconnect device\n");
+}
+
+
+static void vhci_device_reset(struct usbip_device *ud)
+{
+	struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
+
+	spin_lock(&ud->lock);
+
+	vdev->speed  = 0;
+	vdev->devid  = 0;
+
+	if (vdev->udev)
+		usb_put_dev(vdev->udev);
+	vdev->udev = NULL;
+
+	if (ud->tcp_socket) {
+		sockfd_put(ud->tcp_socket);
+		ud->tcp_socket = NULL;
+	}
+	ud->status = VDEV_ST_NULL;
+
+	spin_unlock(&ud->lock);
+}
+
+static void vhci_device_unusable(struct usbip_device *ud)
+{
+	spin_lock(&ud->lock);
+	ud->status = VDEV_ST_ERROR;
+	spin_unlock(&ud->lock);
+}
+
+static void vhci_device_init(struct vhci_device *vdev)
+{
+	memset(vdev, 0, sizeof(*vdev));
+
+	vdev->ud.side   = USBIP_VHCI;
+	vdev->ud.status = VDEV_ST_NULL;
+	spin_lock_init(&vdev->ud.lock);
+
+	INIT_LIST_HEAD(&vdev->priv_rx);
+	INIT_LIST_HEAD(&vdev->priv_tx);
+	INIT_LIST_HEAD(&vdev->unlink_tx);
+	INIT_LIST_HEAD(&vdev->unlink_rx);
+	spin_lock_init(&vdev->priv_lock);
+
+	init_waitqueue_head(&vdev->waitq_tx);
+
+	vdev->ud.eh_ops.shutdown = vhci_shutdown_connection;
+	vdev->ud.eh_ops.reset = vhci_device_reset;
+	vdev->ud.eh_ops.unusable = vhci_device_unusable;
+
+	usbip_start_eh(&vdev->ud);
+}
+
+static int vhci_start(struct usb_hcd *hcd)
+{
+	struct vhci_hcd *vhci = hcd_to_vhci(hcd);
+	int rhport;
+	int err = 0;
+
+	usbip_dbg_vhci_hc("enter vhci_start\n");
+
+	/* initialize private data of usb_hcd */
+
+	for (rhport = 0; rhport < VHCI_NPORTS; rhport++) {
+		struct vhci_device *vdev = &vhci->vdev[rhport];
+
+		vhci_device_init(vdev);
+		vdev->rhport = rhport;
+	}
+
+	atomic_set(&vhci->seqnum, 0);
+	spin_lock_init(&vhci->lock);
+
+	hcd->power_budget = 0; /* no limit */
+	hcd->uses_new_polling = 1;
+
+	/* vhci_hcd is now ready to be controlled through sysfs */
+	err = sysfs_create_group(&vhci_dev(vhci)->kobj, &dev_attr_group);
+	if (err) {
+		pr_err("create sysfs files\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static void vhci_stop(struct usb_hcd *hcd)
+{
+	struct vhci_hcd *vhci = hcd_to_vhci(hcd);
+	int rhport = 0;
+
+	usbip_dbg_vhci_hc("stop VHCI controller\n");
+
+	/* 1. remove the userland interface of vhci_hcd */
+	sysfs_remove_group(&vhci_dev(vhci)->kobj, &dev_attr_group);
+
+	/* 2. shutdown all the ports of vhci_hcd */
+	for (rhport = 0; rhport < VHCI_NPORTS; rhport++) {
+		struct vhci_device *vdev = &vhci->vdev[rhport];
+
+		usbip_event_add(&vdev->ud, VDEV_EVENT_REMOVED);
+		usbip_stop_eh(&vdev->ud);
+	}
+}
+
+static int vhci_get_frame_number(struct usb_hcd *hcd)
+{
+	pr_err("Not yet implemented\n");
+	return 0;
+}
+
+#ifdef CONFIG_PM
+
+/* FIXME: suspend/resume */
+static int vhci_bus_suspend(struct usb_hcd *hcd)
+{
+	struct vhci_hcd *vhci = hcd_to_vhci(hcd);
+
+	dev_dbg(&hcd->self.root_hub->dev, "%s\n", __func__);
+
+	spin_lock(&vhci->lock);
+	hcd->state = HC_STATE_SUSPENDED;
+	spin_unlock(&vhci->lock);
+
+	return 0;
+}
+
+static int vhci_bus_resume(struct usb_hcd *hcd)
+{
+	struct vhci_hcd *vhci = hcd_to_vhci(hcd);
+	int rc = 0;
+
+	dev_dbg(&hcd->self.root_hub->dev, "%s\n", __func__);
+
+	spin_lock(&vhci->lock);
+	if (!HCD_HW_ACCESSIBLE(hcd))
+		rc = -ESHUTDOWN;
+	else
+		hcd->state = HC_STATE_RUNNING;
+	spin_unlock(&vhci->lock);
+
+	return rc;
+}
+
+#else
+
+#define vhci_bus_suspend      NULL
+#define vhci_bus_resume       NULL
+#endif
+
+static struct hc_driver vhci_hc_driver = {
+	.description	= driver_name,
+	.product_desc	= driver_desc,
+	.hcd_priv_size	= sizeof(struct vhci_hcd),
+
+	.flags		= HCD_USB2,
+
+	.start		= vhci_start,
+	.stop		= vhci_stop,
+
+	.urb_enqueue	= vhci_urb_enqueue,
+	.urb_dequeue	= vhci_urb_dequeue,
+
+	.get_frame_number = vhci_get_frame_number,
+
+	.hub_status_data = vhci_hub_status,
+	.hub_control    = vhci_hub_control,
+	.bus_suspend	= vhci_bus_suspend,
+	.bus_resume	= vhci_bus_resume,
+};
+
+static int vhci_hcd_probe(struct platform_device *pdev)
+{
+	struct usb_hcd		*hcd;
+	int			ret;
+
+	usbip_dbg_vhci_hc("name %s id %d\n", pdev->name, pdev->id);
+
+	/*
+	 * Allocate and initialize hcd.
+	 * Our private data is also allocated automatically.
+	 */
+	hcd = usb_create_hcd(&vhci_hc_driver, &pdev->dev, dev_name(&pdev->dev));
+	if (!hcd) {
+		pr_err("create hcd failed\n");
+		return -ENOMEM;
+	}
+	hcd->has_tt = 1;
+
+	/* this is private data for vhci_hcd */
+	the_controller = hcd_to_vhci(hcd);
+
+	/*
+	 * Finish generic HCD structure initialization and register.
+	 * Call the driver's reset() and start() routines.
+	 */
+	ret = usb_add_hcd(hcd, 0, 0);
+	if (ret != 0) {
+		pr_err("usb_add_hcd failed %d\n", ret);
+		usb_put_hcd(hcd);
+		the_controller = NULL;
+		return ret;
+	}
+
+	usbip_dbg_vhci_hc("bye\n");
+	return 0;
+}
+
+static int vhci_hcd_remove(struct platform_device *pdev)
+{
+	struct usb_hcd	*hcd;
+
+	hcd = platform_get_drvdata(pdev);
+	if (!hcd)
+		return 0;
+
+	/*
+	 * Disconnects the root hub,
+	 * then reverses the effects of usb_add_hcd(),
+	 * invoking the HCD's stop() methods.
+	 */
+	usb_remove_hcd(hcd);
+	usb_put_hcd(hcd);
+	the_controller = NULL;
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+
+/* what should happen for USB/IP under suspend/resume? */
+static int vhci_hcd_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct usb_hcd *hcd;
+	int rhport = 0;
+	int connected = 0;
+	int ret = 0;
+
+	hcd = platform_get_drvdata(pdev);
+
+	spin_lock(&the_controller->lock);
+
+	for (rhport = 0; rhport < VHCI_NPORTS; rhport++)
+		if (the_controller->port_status[rhport] &
+		    USB_PORT_STAT_CONNECTION)
+			connected += 1;
+
+	spin_unlock(&the_controller->lock);
+
+	if (connected > 0) {
+		dev_info(&pdev->dev,
+			 "We have %d active connection%s. Do not suspend.\n",
+			 connected, (connected == 1 ? "" : "s"));
+		ret =  -EBUSY;
+	} else {
+		dev_info(&pdev->dev, "suspend vhci_hcd");
+		clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
+	}
+
+	return ret;
+}
+
+static int vhci_hcd_resume(struct platform_device *pdev)
+{
+	struct usb_hcd *hcd;
+
+	dev_dbg(&pdev->dev, "%s\n", __func__);
+
+	hcd = platform_get_drvdata(pdev);
+	set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
+	usb_hcd_poll_rh_status(hcd);
+
+	return 0;
+}
+
+#else
+
+#define vhci_hcd_suspend	NULL
+#define vhci_hcd_resume		NULL
+
+#endif
+
+static struct platform_driver vhci_driver = {
+	.probe	= vhci_hcd_probe,
+	.remove	= vhci_hcd_remove,
+	.suspend = vhci_hcd_suspend,
+	.resume	= vhci_hcd_resume,
+	.driver	= {
+		.name = driver_name,
+		.owner = THIS_MODULE,
+	},
+};
+
+/*
+ * The VHCI 'device' is 'virtual'; not a real plug&play hardware.
+ * We need to add this virtual device as a platform device arbitrarily:
+ *	1. platform_device_register()
+ */
+static void the_pdev_release(struct device *dev)
+{
+}
+
+static struct platform_device the_pdev = {
+	/* should be the same name as driver_name */
+	.name = driver_name,
+	.id = -1,
+	.dev = {
+		.release = the_pdev_release,
+	},
+};
+
+static int __init vhci_hcd_init(void)
+{
+	int ret;
+
+	if (usb_disabled())
+		return -ENODEV;
+
+	ret = platform_driver_register(&vhci_driver);
+	if (ret)
+		goto err_driver_register;
+
+	ret = platform_device_register(&the_pdev);
+	if (ret)
+		goto err_platform_device_register;
+
+	pr_info(DRIVER_DESC " v" USBIP_VERSION "\n");
+	return ret;
+
+err_platform_device_register:
+	platform_driver_unregister(&vhci_driver);
+err_driver_register:
+	return ret;
+}
+
+static void __exit vhci_hcd_exit(void)
+{
+	platform_device_unregister(&the_pdev);
+	platform_driver_unregister(&vhci_driver);
+}
+
+module_init(vhci_hcd_init);
+module_exit(vhci_hcd_exit);
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
+MODULE_VERSION(USBIP_VERSION);
diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c
new file mode 100644
index 000000000000..00e4a54308e4
--- /dev/null
+++ b/drivers/usb/usbip/vhci_rx.c
@@ -0,0 +1,268 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <linux/kthread.h>
+#include <linux/slab.h>
+
+#include "usbip_common.h"
+#include "vhci.h"
+
+/* get URB from transmitted urb queue. caller must hold vdev->priv_lock */
+struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum)
+{
+	struct vhci_priv *priv, *tmp;
+	struct urb *urb = NULL;
+	int status;
+
+	list_for_each_entry_safe(priv, tmp, &vdev->priv_rx, list) {
+		if (priv->seqnum != seqnum)
+			continue;
+
+		urb = priv->urb;
+		status = urb->status;
+
+		usbip_dbg_vhci_rx("find urb %p vurb %p seqnum %u\n",
+				urb, priv, seqnum);
+
+		switch (status) {
+		case -ENOENT:
+			/* fall through */
+		case -ECONNRESET:
+			dev_info(&urb->dev->dev,
+				 "urb %p was unlinked %ssynchronuously.\n", urb,
+				 status == -ENOENT ? "" : "a");
+			break;
+		case -EINPROGRESS:
+			/* no info output */
+			break;
+		default:
+			dev_info(&urb->dev->dev,
+				 "urb %p may be in a error, status %d\n", urb,
+				 status);
+		}
+
+		list_del(&priv->list);
+		kfree(priv);
+		urb->hcpriv = NULL;
+
+		break;
+	}
+
+	return urb;
+}
+
+static void vhci_recv_ret_submit(struct vhci_device *vdev,
+				 struct usbip_header *pdu)
+{
+	struct usbip_device *ud = &vdev->ud;
+	struct urb *urb;
+
+	spin_lock(&vdev->priv_lock);
+	urb = pickup_urb_and_free_priv(vdev, pdu->base.seqnum);
+	spin_unlock(&vdev->priv_lock);
+
+	if (!urb) {
+		pr_err("cannot find a urb of seqnum %u\n", pdu->base.seqnum);
+		pr_info("max seqnum %d\n",
+			atomic_read(&the_controller->seqnum));
+		usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+		return;
+	}
+
+	/* unpack the pdu to a urb */
+	usbip_pack_pdu(pdu, urb, USBIP_RET_SUBMIT, 0);
+
+	/* recv transfer buffer */
+	if (usbip_recv_xbuff(ud, urb) < 0)
+		return;
+
+	/* recv iso_packet_descriptor */
+	if (usbip_recv_iso(ud, urb) < 0)
+		return;
+
+	/* restore the padding in iso packets */
+	usbip_pad_iso(ud, urb);
+
+	if (usbip_dbg_flag_vhci_rx)
+		usbip_dump_urb(urb);
+
+	usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+
+	spin_lock(&the_controller->lock);
+	usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
+	spin_unlock(&the_controller->lock);
+
+	usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status);
+
+	usbip_dbg_vhci_rx("Leave\n");
+}
+
+static struct vhci_unlink *dequeue_pending_unlink(struct vhci_device *vdev,
+						  struct usbip_header *pdu)
+{
+	struct vhci_unlink *unlink, *tmp;
+
+	spin_lock(&vdev->priv_lock);
+
+	list_for_each_entry_safe(unlink, tmp, &vdev->unlink_rx, list) {
+		pr_info("unlink->seqnum %lu\n", unlink->seqnum);
+		if (unlink->seqnum == pdu->base.seqnum) {
+			usbip_dbg_vhci_rx("found pending unlink, %lu\n",
+					  unlink->seqnum);
+			list_del(&unlink->list);
+
+			spin_unlock(&vdev->priv_lock);
+			return unlink;
+		}
+	}
+
+	spin_unlock(&vdev->priv_lock);
+
+	return NULL;
+}
+
+static void vhci_recv_ret_unlink(struct vhci_device *vdev,
+				 struct usbip_header *pdu)
+{
+	struct vhci_unlink *unlink;
+	struct urb *urb;
+
+	usbip_dump_header(pdu);
+
+	unlink = dequeue_pending_unlink(vdev, pdu);
+	if (!unlink) {
+		pr_info("cannot find the pending unlink %u\n",
+			pdu->base.seqnum);
+		return;
+	}
+
+	spin_lock(&vdev->priv_lock);
+	urb = pickup_urb_and_free_priv(vdev, unlink->unlink_seqnum);
+	spin_unlock(&vdev->priv_lock);
+
+	if (!urb) {
+		/*
+		 * I get the result of a unlink request. But, it seems that I
+		 * already received the result of its submit result and gave
+		 * back the URB.
+		 */
+		pr_info("the urb (seqnum %d) was already given back\n",
+			pdu->base.seqnum);
+	} else {
+		usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+
+		/* If unlink is successful, status is -ECONNRESET */
+		urb->status = pdu->u.ret_unlink.status;
+		pr_info("urb->status %d\n", urb->status);
+
+		spin_lock(&the_controller->lock);
+		usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
+		spin_unlock(&the_controller->lock);
+
+		usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
+				     urb->status);
+	}
+
+	kfree(unlink);
+}
+
+static int vhci_priv_tx_empty(struct vhci_device *vdev)
+{
+	int empty = 0;
+
+	spin_lock(&vdev->priv_lock);
+	empty = list_empty(&vdev->priv_rx);
+	spin_unlock(&vdev->priv_lock);
+
+	return empty;
+}
+
+/* recv a pdu */
+static void vhci_rx_pdu(struct usbip_device *ud)
+{
+	int ret;
+	struct usbip_header pdu;
+	struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
+
+	usbip_dbg_vhci_rx("Enter\n");
+
+	memset(&pdu, 0, sizeof(pdu));
+
+	/* receive a pdu header */
+	ret = usbip_recv(ud->tcp_socket, &pdu, sizeof(pdu));
+	if (ret < 0) {
+		if (ret == -ECONNRESET)
+			pr_info("connection reset by peer\n");
+		else if (ret == -EAGAIN) {
+			/* ignore if connection was idle */
+			if (vhci_priv_tx_empty(vdev))
+				return;
+			pr_info("connection timed out with pending urbs\n");
+		} else if (ret != -ERESTARTSYS)
+			pr_info("xmit failed %d\n", ret);
+
+		usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+		return;
+	}
+	if (ret == 0) {
+		pr_info("connection closed");
+		usbip_event_add(ud, VDEV_EVENT_DOWN);
+		return;
+	}
+	if (ret != sizeof(pdu)) {
+		pr_err("received pdu size is %d, should be %d\n", ret,
+		       (unsigned int)sizeof(pdu));
+		usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+		return;
+	}
+
+	usbip_header_correct_endian(&pdu, 0);
+
+	if (usbip_dbg_flag_vhci_rx)
+		usbip_dump_header(&pdu);
+
+	switch (pdu.base.command) {
+	case USBIP_RET_SUBMIT:
+		vhci_recv_ret_submit(vdev, &pdu);
+		break;
+	case USBIP_RET_UNLINK:
+		vhci_recv_ret_unlink(vdev, &pdu);
+		break;
+	default:
+		/* NOT REACHED */
+		pr_err("unknown pdu %u\n", pdu.base.command);
+		usbip_dump_header(&pdu);
+		usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+		break;
+	}
+}
+
+int vhci_rx_loop(void *data)
+{
+	struct usbip_device *ud = data;
+
+	while (!kthread_should_stop()) {
+		if (usbip_event_happened(ud))
+			break;
+
+		vhci_rx_pdu(ud);
+	}
+
+	return 0;
+}
diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c
new file mode 100644
index 000000000000..211f43f67ea2
--- /dev/null
+++ b/drivers/usb/usbip/vhci_sysfs.c
@@ -0,0 +1,252 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <linux/kthread.h>
+#include <linux/file.h>
+#include <linux/net.h>
+
+#include "usbip_common.h"
+#include "vhci.h"
+
+/* TODO: refine locking ?*/
+
+/* Sysfs entry to show port status */
+static ssize_t status_show(struct device *dev, struct device_attribute *attr,
+			   char *out)
+{
+	char *s = out;
+	int i = 0;
+
+	BUG_ON(!the_controller || !out);
+
+	spin_lock(&the_controller->lock);
+
+	/*
+	 * output example:
+	 * prt sta spd dev socket           local_busid
+	 * 000 004 000 000         c5a7bb80 1-2.3
+	 * 001 004 000 000         d8cee980 2-3.4
+	 *
+	 * IP address can be retrieved from a socket pointer address by looking
+	 * up /proc/net/{tcp,tcp6}. Also, a userland program may remember a
+	 * port number and its peer IP address.
+	 */
+	out += sprintf(out,
+		       "prt sta spd bus dev socket           local_busid\n");
+
+	for (i = 0; i < VHCI_NPORTS; i++) {
+		struct vhci_device *vdev = port_to_vdev(i);
+
+		spin_lock(&vdev->ud.lock);
+		out += sprintf(out, "%03u %03u ", i, vdev->ud.status);
+
+		if (vdev->ud.status == VDEV_ST_USED) {
+			out += sprintf(out, "%03u %08x ",
+				       vdev->speed, vdev->devid);
+			out += sprintf(out, "%16p ", vdev->ud.tcp_socket);
+			out += sprintf(out, "%s", dev_name(&vdev->udev->dev));
+
+		} else {
+			out += sprintf(out, "000 000 000 0000000000000000 0-0");
+		}
+
+		out += sprintf(out, "\n");
+		spin_unlock(&vdev->ud.lock);
+	}
+
+	spin_unlock(&the_controller->lock);
+
+	return out - s;
+}
+static DEVICE_ATTR_RO(status);
+
+/* Sysfs entry to shutdown a virtual connection */
+static int vhci_port_disconnect(__u32 rhport)
+{
+	struct vhci_device *vdev;
+
+	usbip_dbg_vhci_sysfs("enter\n");
+
+	/* lock */
+	spin_lock(&the_controller->lock);
+
+	vdev = port_to_vdev(rhport);
+
+	spin_lock(&vdev->ud.lock);
+	if (vdev->ud.status == VDEV_ST_NULL) {
+		pr_err("not connected %d\n", vdev->ud.status);
+
+		/* unlock */
+		spin_unlock(&vdev->ud.lock);
+		spin_unlock(&the_controller->lock);
+
+		return -EINVAL;
+	}
+
+	/* unlock */
+	spin_unlock(&vdev->ud.lock);
+	spin_unlock(&the_controller->lock);
+
+	usbip_event_add(&vdev->ud, VDEV_EVENT_DOWN);
+
+	return 0;
+}
+
+static ssize_t store_detach(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	int err;
+	__u32 rhport = 0;
+
+	if (sscanf(buf, "%u", &rhport) != 1)
+		return -EINVAL;
+
+	/* check rhport */
+	if (rhport >= VHCI_NPORTS) {
+		dev_err(dev, "invalid port %u\n", rhport);
+		return -EINVAL;
+	}
+
+	err = vhci_port_disconnect(rhport);
+	if (err < 0)
+		return -EINVAL;
+
+	usbip_dbg_vhci_sysfs("Leave\n");
+
+	return count;
+}
+static DEVICE_ATTR(detach, S_IWUSR, NULL, store_detach);
+
+/* Sysfs entry to establish a virtual connection */
+static int valid_args(__u32 rhport, enum usb_device_speed speed)
+{
+	/* check rhport */
+	if (rhport >= VHCI_NPORTS) {
+		pr_err("port %u\n", rhport);
+		return -EINVAL;
+	}
+
+	/* check speed */
+	switch (speed) {
+	case USB_SPEED_LOW:
+	case USB_SPEED_FULL:
+	case USB_SPEED_HIGH:
+	case USB_SPEED_WIRELESS:
+		break;
+	default:
+		pr_err("Failed attach request for unsupported USB speed: %s\n",
+			usb_speed_string(speed));
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * To start a new USB/IP attachment, a userland program needs to setup a TCP
+ * connection and then write its socket descriptor with remote device
+ * information into this sysfs file.
+ *
+ * A remote device is virtually attached to the root-hub port of @rhport with
+ * @speed. @devid is embedded into a request to specify the remote device in a
+ * server host.
+ *
+ * write() returns 0 on success, else negative errno.
+ */
+static ssize_t store_attach(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	struct vhci_device *vdev;
+	struct socket *socket;
+	int sockfd = 0;
+	__u32 rhport = 0, devid = 0, speed = 0;
+	int err;
+
+	/*
+	 * @rhport: port number of vhci_hcd
+	 * @sockfd: socket descriptor of an established TCP connection
+	 * @devid: unique device identifier in a remote host
+	 * @speed: usb device speed in a remote host
+	 */
+	if (sscanf(buf, "%u %u %u %u", &rhport, &sockfd, &devid, &speed) != 4)
+		return -EINVAL;
+
+	usbip_dbg_vhci_sysfs("rhport(%u) sockfd(%u) devid(%u) speed(%u)\n",
+			     rhport, sockfd, devid, speed);
+
+	/* check received parameters */
+	if (valid_args(rhport, speed) < 0)
+		return -EINVAL;
+
+	/* Extract socket from fd. */
+	socket = sockfd_lookup(sockfd, &err);
+	if (!socket)
+		return -EINVAL;
+
+	/* now need lock until setting vdev status as used */
+
+	/* begin a lock */
+	spin_lock(&the_controller->lock);
+	vdev = port_to_vdev(rhport);
+	spin_lock(&vdev->ud.lock);
+
+	if (vdev->ud.status != VDEV_ST_NULL) {
+		/* end of the lock */
+		spin_unlock(&vdev->ud.lock);
+		spin_unlock(&the_controller->lock);
+
+		sockfd_put(socket);
+
+		dev_err(dev, "port %d already used\n", rhport);
+		return -EINVAL;
+	}
+
+	dev_info(dev,
+		 "rhport(%u) sockfd(%d) devid(%u) speed(%u) speed_str(%s)\n",
+		 rhport, sockfd, devid, speed, usb_speed_string(speed));
+
+	vdev->devid         = devid;
+	vdev->speed         = speed;
+	vdev->ud.tcp_socket = socket;
+	vdev->ud.status     = VDEV_ST_NOTASSIGNED;
+
+	spin_unlock(&vdev->ud.lock);
+	spin_unlock(&the_controller->lock);
+	/* end the lock */
+
+	vdev->ud.tcp_rx = kthread_get_run(vhci_rx_loop, &vdev->ud, "vhci_rx");
+	vdev->ud.tcp_tx = kthread_get_run(vhci_tx_loop, &vdev->ud, "vhci_tx");
+
+	rh_port_connect(rhport, speed);
+
+	return count;
+}
+static DEVICE_ATTR(attach, S_IWUSR, NULL, store_attach);
+
+static struct attribute *dev_attrs[] = {
+	&dev_attr_status.attr,
+	&dev_attr_detach.attr,
+	&dev_attr_attach.attr,
+	&dev_attr_usbip_debug.attr,
+	NULL,
+};
+
+const struct attribute_group dev_attr_group = {
+	.attrs = dev_attrs,
+};
diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c
new file mode 100644
index 000000000000..409fd99f3257
--- /dev/null
+++ b/drivers/usb/usbip/vhci_tx.c
@@ -0,0 +1,224 @@
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
+ * USA.
+ */
+
+#include <linux/kthread.h>
+#include <linux/slab.h>
+
+#include "usbip_common.h"
+#include "vhci.h"
+
+static void setup_cmd_submit_pdu(struct usbip_header *pdup,  struct urb *urb)
+{
+	struct vhci_priv *priv = ((struct vhci_priv *)urb->hcpriv);
+	struct vhci_device *vdev = priv->vdev;
+
+	usbip_dbg_vhci_tx("URB, local devnum %u, remote devid %u\n",
+			  usb_pipedevice(urb->pipe), vdev->devid);
+
+	pdup->base.command   = USBIP_CMD_SUBMIT;
+	pdup->base.seqnum    = priv->seqnum;
+	pdup->base.devid     = vdev->devid;
+	pdup->base.direction = usb_pipein(urb->pipe) ?
+		USBIP_DIR_IN : USBIP_DIR_OUT;
+	pdup->base.ep	     = usb_pipeendpoint(urb->pipe);
+
+	usbip_pack_pdu(pdup, urb, USBIP_CMD_SUBMIT, 1);
+
+	if (urb->setup_packet)
+		memcpy(pdup->u.cmd_submit.setup, urb->setup_packet, 8);
+}
+
+static struct vhci_priv *dequeue_from_priv_tx(struct vhci_device *vdev)
+{
+	struct vhci_priv *priv, *tmp;
+
+	spin_lock(&vdev->priv_lock);
+
+	list_for_each_entry_safe(priv, tmp, &vdev->priv_tx, list) {
+		list_move_tail(&priv->list, &vdev->priv_rx);
+		spin_unlock(&vdev->priv_lock);
+		return priv;
+	}
+
+	spin_unlock(&vdev->priv_lock);
+
+	return NULL;
+}
+
+static int vhci_send_cmd_submit(struct vhci_device *vdev)
+{
+	struct vhci_priv *priv = NULL;
+
+	struct msghdr msg;
+	struct kvec iov[3];
+	size_t txsize;
+
+	size_t total_size = 0;
+
+	while ((priv = dequeue_from_priv_tx(vdev)) != NULL) {
+		int ret;
+		struct urb *urb = priv->urb;
+		struct usbip_header pdu_header;
+		struct usbip_iso_packet_descriptor *iso_buffer = NULL;
+
+		txsize = 0;
+		memset(&pdu_header, 0, sizeof(pdu_header));
+		memset(&msg, 0, sizeof(msg));
+		memset(&iov, 0, sizeof(iov));
+
+		usbip_dbg_vhci_tx("setup txdata urb %p\n", urb);
+
+		/* 1. setup usbip_header */
+		setup_cmd_submit_pdu(&pdu_header, urb);
+		usbip_header_correct_endian(&pdu_header, 1);
+
+		iov[0].iov_base = &pdu_header;
+		iov[0].iov_len  = sizeof(pdu_header);
+		txsize += sizeof(pdu_header);
+
+		/* 2. setup transfer buffer */
+		if (!usb_pipein(urb->pipe) && urb->transfer_buffer_length > 0) {
+			iov[1].iov_base = urb->transfer_buffer;
+			iov[1].iov_len  = urb->transfer_buffer_length;
+			txsize += urb->transfer_buffer_length;
+		}
+
+		/* 3. setup iso_packet_descriptor */
+		if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) {
+			ssize_t len = 0;
+
+			iso_buffer = usbip_alloc_iso_desc_pdu(urb, &len);
+			if (!iso_buffer) {
+				usbip_event_add(&vdev->ud,
+						SDEV_EVENT_ERROR_MALLOC);
+				return -1;
+			}
+
+			iov[2].iov_base = iso_buffer;
+			iov[2].iov_len  = len;
+			txsize += len;
+		}
+
+		ret = kernel_sendmsg(vdev->ud.tcp_socket, &msg, iov, 3, txsize);
+		if (ret != txsize) {
+			pr_err("sendmsg failed!, ret=%d for %zd\n", ret,
+			       txsize);
+			kfree(iso_buffer);
+			usbip_event_add(&vdev->ud, VDEV_EVENT_ERROR_TCP);
+			return -1;
+		}
+
+		kfree(iso_buffer);
+		usbip_dbg_vhci_tx("send txdata\n");
+
+		total_size += txsize;
+	}
+
+	return total_size;
+}
+
+static struct vhci_unlink *dequeue_from_unlink_tx(struct vhci_device *vdev)
+{
+	struct vhci_unlink *unlink, *tmp;
+
+	spin_lock(&vdev->priv_lock);
+
+	list_for_each_entry_safe(unlink, tmp, &vdev->unlink_tx, list) {
+		list_move_tail(&unlink->list, &vdev->unlink_rx);
+		spin_unlock(&vdev->priv_lock);
+		return unlink;
+	}
+
+	spin_unlock(&vdev->priv_lock);
+
+	return NULL;
+}
+
+static int vhci_send_cmd_unlink(struct vhci_device *vdev)
+{
+	struct vhci_unlink *unlink = NULL;
+
+	struct msghdr msg;
+	struct kvec iov[3];
+	size_t txsize;
+
+	size_t total_size = 0;
+
+	while ((unlink = dequeue_from_unlink_tx(vdev)) != NULL) {
+		int ret;
+		struct usbip_header pdu_header;
+
+		txsize = 0;
+		memset(&pdu_header, 0, sizeof(pdu_header));
+		memset(&msg, 0, sizeof(msg));
+		memset(&iov, 0, sizeof(iov));
+
+		usbip_dbg_vhci_tx("setup cmd unlink, %lu\n", unlink->seqnum);
+
+		/* 1. setup usbip_header */
+		pdu_header.base.command = USBIP_CMD_UNLINK;
+		pdu_header.base.seqnum  = unlink->seqnum;
+		pdu_header.base.devid	= vdev->devid;
+		pdu_header.base.ep	= 0;
+		pdu_header.u.cmd_unlink.seqnum = unlink->unlink_seqnum;
+
+		usbip_header_correct_endian(&pdu_header, 1);
+
+		iov[0].iov_base = &pdu_header;
+		iov[0].iov_len  = sizeof(pdu_header);
+		txsize += sizeof(pdu_header);
+
+		ret = kernel_sendmsg(vdev->ud.tcp_socket, &msg, iov, 1, txsize);
+		if (ret != txsize) {
+			pr_err("sendmsg failed!, ret=%d for %zd\n", ret,
+			       txsize);
+			usbip_event_add(&vdev->ud, VDEV_EVENT_ERROR_TCP);
+			return -1;
+		}
+
+		usbip_dbg_vhci_tx("send txdata\n");
+
+		total_size += txsize;
+	}
+
+	return total_size;
+}
+
+int vhci_tx_loop(void *data)
+{
+	struct usbip_device *ud = data;
+	struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
+
+	while (!kthread_should_stop()) {
+		if (vhci_send_cmd_submit(vdev) < 0)
+			break;
+
+		if (vhci_send_cmd_unlink(vdev) < 0)
+			break;
+
+		wait_event_interruptible(vdev->waitq_tx,
+					 (!list_empty(&vdev->priv_tx) ||
+					  !list_empty(&vdev->unlink_tx) ||
+					  kthread_should_stop()));
+
+		usbip_dbg_vhci_tx("pending urbs ?, now wake up\n");
+	}
+
+	return 0;
+}
diff --git a/include/uapi/linux/usbip.h b/include/uapi/linux/usbip.h
new file mode 100644
index 000000000000..fa5db30ede36
--- /dev/null
+++ b/include/uapi/linux/usbip.h
@@ -0,0 +1,26 @@
+/*
+ *	usbip.h
+ *
+ *	USBIP uapi defines and function prototypes etc.
+*/
+
+#ifndef _UAPI_LINUX_USBIP_H
+#define _UAPI_LINUX_USBIP_H
+
+/* usbip device status - exported in usbip device sysfs status */
+enum usbip_device_status {
+	/* sdev is available. */
+	SDEV_ST_AVAILABLE = 0x01,
+	/* sdev is now used. */
+	SDEV_ST_USED,
+	/* sdev is unusable because of a fatal error. */
+	SDEV_ST_ERROR,
+
+	/* vdev does not connect a remote device. */
+	VDEV_ST_NULL,
+	/* vdev is used, but the USB address is not assigned yet */
+	VDEV_ST_NOTASSIGNED,
+	VDEV_ST_USED,
+	VDEV_ST_ERROR
+};
+#endif /* _UAPI_LINUX_USBIP_H */
-- 
cgit v1.2.3


From f153566570fb9e32c2f59182883f4f66048788fb Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Fri, 22 Aug 2014 21:48:00 +0100
Subject: iio:trigger: modify return value for iio_trigger_get

Instead of a void function, return the trigger pointer.

Whilst not in of itself a fix, this makes the following set of
7 fixes cleaner than they would otherwise be.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Cc: Stable@vger.kernel.org
---
 include/linux/iio/trigger.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h
index 4b79ffe7b188..fa76c79a52a1 100644
--- a/include/linux/iio/trigger.h
+++ b/include/linux/iio/trigger.h
@@ -84,10 +84,12 @@ static inline void iio_trigger_put(struct iio_trigger *trig)
 	put_device(&trig->dev);
 }
 
-static inline void iio_trigger_get(struct iio_trigger *trig)
+static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig)
 {
 	get_device(&trig->dev);
 	__module_get(trig->ops->owner);
+
+	return trig;
 }
 
 /**
-- 
cgit v1.2.3


From 48ea526a6877d605c961aa37fae33f3227b29424 Mon Sep 17 00:00:00 2001
From: Amir Vadai <amirv@mellanox.com>
Date: Mon, 25 Aug 2014 16:06:53 +0300
Subject: net/mlx4: Use is_kdump_kernel() to detect kdump kernel

Use is_kdump_kernel() to detect kdump kernel, instead of reset_devices.

Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mlx4/device.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 071f6b234604..783dd099abd1 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -38,6 +38,7 @@
 #include <linux/completion.h>
 #include <linux/radix-tree.h>
 #include <linux/cpu_rmap.h>
+#include <linux/crash_dump.h>
 
 #include <linux/atomic.h>
 
@@ -1275,7 +1276,7 @@ int mlx4_mr_rereg_mem_write(struct mlx4_dev *dev, struct mlx4_mr *mr,
 /* Returns true if running in low memory profile (kdump kernel) */
 static inline bool mlx4_low_memory_profile(void)
 {
-	return reset_devices;
+	return is_kdump_kernel();
 }
 
 #endif /* MLX4_DEVICE_H */
-- 
cgit v1.2.3


From 7d5929c1f34304ca5a970cfde8044053e56aa8c9 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Mon, 25 Aug 2014 16:15:32 -0700
Subject: mtd: nand: omap: Revert to using software ECC by default

For v3.12 and prior, 1-bit Hamming code ECC via software was the
default choice. Commit c66d039197e4 in v3.13 changed the behaviour
to use 1-bit Hamming code via Hardware using a different ECC layout
i.e. (ROM code layout) than what is used by software ECC.

This ECC layout change causes NAND filesystems created in v3.12
and prior to be unusable in v3.13 and later. So revert back to
using software ECC by default if an ECC scheme is not explicitely
specified.

This defect can be observed on the following boards during legacy boot

-omap3beagle
-omap3touchbook
-overo
-am3517crane
-devkit8000
-ldp
-3430sdp

Signed-off-by: Roger Quadros <rogerq@ti.com>
Tested-by: Grazvydas Ignotas <notasas@gmail.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/board-flash.c            |  2 +-
 arch/arm/mach-omap2/gpmc-nand.c              |  3 ++-
 drivers/mtd/nand/omap2.c                     | 14 +++++++++++---
 include/linux/platform_data/mtd-nand-omap2.h | 13 +++++++++++--
 4 files changed, 25 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c
index e87f2a83d6bf..2d245c2e641c 100644
--- a/arch/arm/mach-omap2/board-flash.c
+++ b/arch/arm/mach-omap2/board-flash.c
@@ -142,7 +142,7 @@ __init board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs,
 	board_nand_data.nr_parts	= nr_parts;
 	board_nand_data.devsize		= nand_type;
 
-	board_nand_data.ecc_opt = OMAP_ECC_HAM1_CODE_HW;
+	board_nand_data.ecc_opt = OMAP_ECC_HAM1_CODE_SW;
 	gpmc_nand_init(&board_nand_data, gpmc_t);
 }
 #endif /* CONFIG_MTD_NAND_OMAP2 || CONFIG_MTD_NAND_OMAP2_MODULE */
diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c
index 8897ad7035fd..cb7764314f17 100644
--- a/arch/arm/mach-omap2/gpmc-nand.c
+++ b/arch/arm/mach-omap2/gpmc-nand.c
@@ -49,7 +49,8 @@ static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt)
 		return 0;
 
 	/* legacy platforms support only HAM1 (1-bit Hamming) ECC scheme */
-	if (ecc_opt == OMAP_ECC_HAM1_CODE_HW)
+	if (ecc_opt == OMAP_ECC_HAM1_CODE_HW ||
+	    ecc_opt == OMAP_ECC_HAM1_CODE_SW)
 		return 1;
 	else
 		return 0;
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index f0ed92e210a1..4dd617897eee 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1794,9 +1794,12 @@ static int omap_nand_probe(struct platform_device *pdev)
 	}
 
 	/* populate MTD interface based on ECC scheme */
-	nand_chip->ecc.layout	= &omap_oobinfo;
 	ecclayout		= &omap_oobinfo;
 	switch (info->ecc_opt) {
+	case OMAP_ECC_HAM1_CODE_SW:
+		nand_chip->ecc.mode = NAND_ECC_SOFT;
+		break;
+
 	case OMAP_ECC_HAM1_CODE_HW:
 		pr_info("nand: using OMAP_ECC_HAM1_CODE_HW\n");
 		nand_chip->ecc.mode             = NAND_ECC_HW;
@@ -1848,7 +1851,7 @@ static int omap_nand_probe(struct platform_device *pdev)
 		nand_chip->ecc.priv		= nand_bch_init(mtd,
 							nand_chip->ecc.size,
 							nand_chip->ecc.bytes,
-							&nand_chip->ecc.layout);
+							&ecclayout);
 		if (!nand_chip->ecc.priv) {
 			pr_err("nand: error: unable to use s/w BCH library\n");
 			err = -EINVAL;
@@ -1923,7 +1926,7 @@ static int omap_nand_probe(struct platform_device *pdev)
 		nand_chip->ecc.priv		= nand_bch_init(mtd,
 							nand_chip->ecc.size,
 							nand_chip->ecc.bytes,
-							&nand_chip->ecc.layout);
+							&ecclayout);
 		if (!nand_chip->ecc.priv) {
 			pr_err("nand: error: unable to use s/w BCH library\n");
 			err = -EINVAL;
@@ -2012,6 +2015,9 @@ static int omap_nand_probe(struct platform_device *pdev)
 		goto return_error;
 	}
 
+	if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW)
+		goto scan_tail;
+
 	/* all OOB bytes from oobfree->offset till end off OOB are free */
 	ecclayout->oobfree->length = mtd->oobsize - ecclayout->oobfree->offset;
 	/* check if NAND device's OOB is enough to store ECC signatures */
@@ -2021,7 +2027,9 @@ static int omap_nand_probe(struct platform_device *pdev)
 		err = -EINVAL;
 		goto return_error;
 	}
+	nand_chip->ecc.layout = ecclayout;
 
+scan_tail:
 	/* second phase scan */
 	if (nand_scan_tail(mtd)) {
 		err = -ENXIO;
diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h
index 660c029d694f..16ec262dfcc8 100644
--- a/include/linux/platform_data/mtd-nand-omap2.h
+++ b/include/linux/platform_data/mtd-nand-omap2.h
@@ -21,8 +21,17 @@ enum nand_io {
 };
 
 enum omap_ecc {
-	/* 1-bit  ECC calculation by GPMC, Error detection by Software */
-	OMAP_ECC_HAM1_CODE_HW = 0,
+	/*
+	 * 1-bit ECC: calculation and correction by SW
+	 * ECC stored at end of spare area
+	 */
+	OMAP_ECC_HAM1_CODE_SW = 0,
+
+	/*
+	 * 1-bit ECC: calculation by GPMC, Error detection by Software
+	 * ECC layout compatible with ROM code layout
+	 */
+	OMAP_ECC_HAM1_CODE_HW,
 	/* 4-bit  ECC calculation by GPMC, Error detection by Software */
 	OMAP_ECC_BCH4_CODE_HW_DETECTION_SW,
 	/* 4-bit  ECC calculation by GPMC, Error detection by ELM */
-- 
cgit v1.2.3


From 0b725a2ca61bedc33a2a63d0451d528b268cf975 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 25 Aug 2014 15:51:53 -0700
Subject: net: Remove ndo_xmit_flush netdev operation, use signalling instead.

As reported by Jesper Dangaard Brouer, for high packet rates the
overhead of having another indirect call in the TX path is
non-trivial.

There is the indirect call itself, and then there is all of the
reloading of the state to refetch the tail pointer value and
then write the device register.

Move to a more passive scheme, which requires very light modifications
to the device drivers.

The signal is a new skb->xmit_more value, if it is non-zero it means
that more SKBs are pending to be transmitted on the same queue as the
current SKB.  And therefore, the driver may elide the tail pointer
update.

Right now skb->xmit_more is always zero.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 36 +++++++++++--------------------
 drivers/net/virtio_net.c                  | 12 +++--------
 include/linux/netdevice.h                 | 25 ++-------------------
 include/linux/skbuff.h                    |  2 ++
 4 files changed, 19 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index b9c020a05fb8..89c29b40d61c 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -136,7 +136,6 @@ static void igb_update_phy_info(unsigned long);
 static void igb_watchdog(unsigned long);
 static void igb_watchdog_task(struct work_struct *);
 static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *);
-static void igb_xmit_flush(struct net_device *netdev, u16 queue);
 static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *dev,
 					  struct rtnl_link_stats64 *stats);
 static int igb_change_mtu(struct net_device *, int);
@@ -2076,7 +2075,6 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_open		= igb_open,
 	.ndo_stop		= igb_close,
 	.ndo_start_xmit		= igb_xmit_frame,
-	.ndo_xmit_flush		= igb_xmit_flush,
 	.ndo_get_stats64	= igb_get_stats64,
 	.ndo_set_rx_mode	= igb_set_rx_mode,
 	.ndo_set_mac_address	= igb_set_mac,
@@ -4917,6 +4915,14 @@ static void igb_tx_map(struct igb_ring *tx_ring,
 
 	tx_ring->next_to_use = i;
 
+	if (!skb->xmit_more) {
+		writel(i, tx_ring->tail);
+
+		/* we need this if more than one processor can write to our tail
+		 * at a time, it synchronizes IO on IA64/Altix systems
+		 */
+		mmiowb();
+	}
 	return;
 
 dma_error:
@@ -5052,20 +5058,17 @@ out_drop:
 	return NETDEV_TX_OK;
 }
 
-static struct igb_ring *__igb_tx_queue_mapping(struct igb_adapter *adapter, unsigned int r_idx)
+static inline struct igb_ring *igb_tx_queue_mapping(struct igb_adapter *adapter,
+						    struct sk_buff *skb)
 {
+	unsigned int r_idx = skb->queue_mapping;
+
 	if (r_idx >= adapter->num_tx_queues)
 		r_idx = r_idx % adapter->num_tx_queues;
 
 	return adapter->tx_ring[r_idx];
 }
 
-static inline struct igb_ring *igb_tx_queue_mapping(struct igb_adapter *adapter,
-						    struct sk_buff *skb)
-{
-	return __igb_tx_queue_mapping(adapter, skb->queue_mapping);
-}
-
 static netdev_tx_t igb_xmit_frame(struct sk_buff *skb,
 				  struct net_device *netdev)
 {
@@ -5094,21 +5097,6 @@ static netdev_tx_t igb_xmit_frame(struct sk_buff *skb,
 	return igb_xmit_frame_ring(skb, igb_tx_queue_mapping(adapter, skb));
 }
 
-static void igb_xmit_flush(struct net_device *netdev, u16 queue)
-{
-	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct igb_ring *tx_ring;
-
-	tx_ring = __igb_tx_queue_mapping(adapter, queue);
-
-	writel(tx_ring->next_to_use, tx_ring->tail);
-
-	/* we need this if more than one processor can write to our tail
-	 * at a time, it synchronizes IO on IA64/Altix systems
-	 */
-	mmiowb();
-}
-
 /**
  *  igb_tx_timeout - Respond to a Tx Hang
  *  @netdev: network interface device structure
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 62421086d3e6..f0c2824f5e0f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -953,15 +953,10 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	return NETDEV_TX_OK;
-}
+	if (!skb->xmit_more)
+		virtqueue_kick(sq->vq);
 
-static void xmit_flush(struct net_device *dev, u16 qnum)
-{
-	struct virtnet_info *vi = netdev_priv(dev);
-	struct send_queue *sq = &vi->sq[qnum];
-
-	virtqueue_kick(sq->vq);
+	return NETDEV_TX_OK;
 }
 
 /*
@@ -1393,7 +1388,6 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
 	.ndo_start_xmit      = start_xmit,
-	.ndo_xmit_flush      = xmit_flush,
 	.ndo_validate_addr   = eth_validate_addr,
 	.ndo_set_mac_address = virtnet_set_mac_address,
 	.ndo_set_rx_mode     = virtnet_set_rx_mode,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 220c50984688..039b23786c22 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -782,19 +782,6 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
  *	Required can not be NULL.
  *
- * void (*ndo_xmit_flush)(struct net_device *dev, u16 queue);
- *	A driver implements this function when it wishes to support
- *	deferred TX queue flushing.  The idea is that the expensive
- *	operation to trigger TX queue processing can be done after
- *	N calls to ndo_start_xmit rather than being done every single
- *	time.  In this regime ndo_start_xmit will be called one or more
- *	times, and then a final ndo_xmit_flush call will be made to
- *	have the driver tell the device about the new pending TX queue
- *	entries.  The kernel keeps track of which queues need flushing
- *	by monitoring skb->queue_mapping of the packets it submits to
- *	ndo_start_xmit.  This is the queue value that will be passed
- *	to ndo_xmit_flush.
- *
  * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
  *                         void *accel_priv, select_queue_fallback_t fallback);
  *	Called to decide which queue to when device supports multiple
@@ -1018,7 +1005,6 @@ struct net_device_ops {
 	int			(*ndo_stop)(struct net_device *dev);
 	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
 						   struct net_device *dev);
-	void			(*ndo_xmit_flush)(struct net_device *dev, u16 queue);
 	u16			(*ndo_select_queue)(struct net_device *dev,
 						    struct sk_buff *skb,
 						    void *accel_priv,
@@ -3447,15 +3433,8 @@ int __init dev_proc_init(void);
 static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
 					      struct sk_buff *skb, struct net_device *dev)
 {
-	netdev_tx_t ret;
-	u16 q;
-
-	q = skb->queue_mapping;
-	ret = ops->ndo_start_xmit(skb, dev);
-	if (dev_xmit_complete(ret) && ops->ndo_xmit_flush)
-		ops->ndo_xmit_flush(dev, q);
-
-	return ret;
+	skb->xmit_more = 0;
+	return ops->ndo_start_xmit(skb, dev);
 }
 
 static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 18ddf9684a27..9b3802a197a8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -452,6 +452,7 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
  *	@tc_verd: traffic control verdict
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
+ *	@xmit_more: More SKBs are pending for this queue
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
  *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
@@ -558,6 +559,7 @@ struct sk_buff {
 
 	__u16			queue_mapping;
 	kmemcheck_bitfield_begin(flags2);
+	__u8			xmit_more:1;
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
-- 
cgit v1.2.3


From 453a940ea725d692282f9e66475cec0d1b1e12f2 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 25 Aug 2014 17:03:47 -0700
Subject: net: make skb an optional parameter for__skb_flow_dissect()

Fixes: commit 690e36e726d00d2 (net: Allow raw buffers to be passed into the flow dissector)
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_keys.h   |  4 ++--
 net/core/flow_dissector.c | 18 +++++++++++++++---
 2 files changed, 17 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index 4040f63932c5..9a03f73c4974 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -28,10 +28,10 @@ struct flow_keys {
 };
 
 bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
-			void *data, int hlen);
+			void *data, __be16 proto, int nhoff, int hlen);
 static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
 {
-	return __skb_flow_dissect(skb, flow, NULL, 0);
+	return __skb_flow_dissect(skb, flow, NULL, 0, 0, 0);
 }
 __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
 			    void *data, int hlen_proto);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index ae8f0db67aed..12f48ca7a0b0 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -59,14 +59,26 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
 }
 EXPORT_SYMBOL(__skb_flow_get_ports);
 
-bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, void *data, int hlen)
+/**
+ * __skb_flow_dissect - extract the flow_keys struct and return it
+ * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
+ * @data: raw buffer pointer to the packet, if NULL use skb->data
+ * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol
+ * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb)
+ * @hlen: packet header length, if @data is NULL use skb_headlen(skb)
+ *
+ * The function will try to retrieve the struct flow_keys from either the skbuff
+ * or a raw buffer specified by the rest parameters
+ */
+bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
+			void *data, __be16 proto, int nhoff, int hlen)
 {
-	int nhoff = skb_network_offset(skb);
 	u8 ip_proto;
-	__be16 proto = skb->protocol;
 
 	if (!data) {
 		data = skb->data;
+		proto = skb->protocol;
+		nhoff = skb_network_offset(skb);
 		hlen = skb_headlen(skb);
 	}
 
-- 
cgit v1.2.3


From b4bbb107d73bbc0d92c9ae7fd8e69580aa9381e7 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 27 Jun 2014 11:56:58 +0200
Subject: dma-mapping: Provide write-combine allocations

Provide an implementation for dma_{alloc,free,mmap}_writecombine() when
the architecture supports DMA attributes.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 arch/arm/include/asm/dma-mapping.h       | 16 ----------------
 include/asm-generic/dma-mapping-common.h |  8 --------
 include/linux/dma-mapping.h              | 26 ++++++++++++++++++++++++++
 3 files changed, 26 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index c45b61a4b4a5..85738b200023 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -265,22 +265,6 @@ extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 			void *cpu_addr, dma_addr_t dma_addr, size_t size,
 			struct dma_attrs *attrs);
 
-static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
-{
-	DEFINE_DMA_ATTRS(attrs);
-	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
-	return dma_alloc_attrs(dev, size, dma_handle, flag, &attrs);
-}
-
-static inline void dma_free_writecombine(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
-{
-	DEFINE_DMA_ATTRS(attrs);
-	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
-	return dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs);
-}
-
 /*
  * This can be called during early boot to increase the size of the atomic
  * coherent DMA pool above the default value of 256KiB. It must be called
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index de8bf89940f8..d137431bf26f 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -205,14 +205,6 @@ dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr,
 
 #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL)
 
-static inline int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
-		      void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
-	DEFINE_DMA_ATTRS(attrs);
-	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
-	return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
-}
-
 int
 dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
 		       void *cpu_addr, dma_addr_t dma_addr, size_t size);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 931b70986272..d5d388160f42 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -263,6 +263,32 @@ struct dma_attrs;
 #define dma_unmap_sg_attrs(dev, sgl, nents, dir, attrs) \
 	dma_unmap_sg(dev, sgl, nents, dir)
 
+#else
+static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
+					   dma_addr_t *dma_addr, gfp_t gfp)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_alloc_attrs(dev, size, dma_addr, gfp, &attrs);
+}
+
+static inline void dma_free_writecombine(struct device *dev, size_t size,
+					 void *cpu_addr, dma_addr_t dma_addr)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_free_attrs(dev, size, cpu_addr, dma_addr, &attrs);
+}
+
+static inline int dma_mmap_writecombine(struct device *dev,
+					struct vm_area_struct *vma,
+					void *cpu_addr, dma_addr_t dma_addr,
+					size_t size)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
+}
 #endif /* CONFIG_HAVE_DMA_ATTRS */
 
 #ifdef CONFIG_NEED_DMA_MAP_STATE
-- 
cgit v1.2.3


From 50d8a189013cef83eef771c45787cee68ecdf8fe Mon Sep 17 00:00:00 2001
From: "Raymond L. Rivera" <ray.l.rivera@gmail.com>
Date: Thu, 24 Jul 2014 02:39:45 -0700
Subject: linux/pagemap.h: Fixed a typo in a code comment.

Corrected a minor typo in a code comment where 'be' was missing.

Signed-off-by: Raymond L. Rivera <ray.l.rivera@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/pagemap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e1474ae18c88..bf657ff3208c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -96,7 +96,7 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 }
 
 /*
- * The page cache can done in larger chunks than
+ * The page cache can be done in larger chunks than
  * one page, because it allows for more efficient
  * throughput (it can then be mapped into user
  * space in smaller chunks for same flexibility).
-- 
cgit v1.2.3


From b9347aff91ce4789619168539f08202d8d6a1177 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Tue, 26 Aug 2014 10:29:45 +0200
Subject: crypto: drbg - fix maximum value checks on 32 bit systems

The maximum values for additional input string or generated blocks is
larger than 1<<32. To ensure a sensible value on 32 bit systems, return
SIZE_MAX on 32 bit systems. This value is lower than the maximum
allowed values defined in SP800-90A. The standard allow lower maximum
values, but not larger values.

SIZE_MAX - 1 is used for drbg_max_addtl to allow
drbg_healthcheck_sanity to check the enforcement of the variable
without wrapping.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/drbg.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index 3d8e73a1a1c7..5186f750c713 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -154,13 +154,26 @@ static inline size_t drbg_max_request_bytes(struct drbg_state *drbg)
 static inline size_t drbg_max_addtl(struct drbg_state *drbg)
 {
 	/* SP800-90A requires 2**35 bytes additional info str / pers str */
+#if (__BITS_PER_LONG == 32)
+	/*
+	 * SP800-90A allows smaller maximum numbers to be returned -- we
+	 * return SIZE_MAX - 1 to allow the verification of the enforcement
+	 * of this value in drbg_healthcheck_sanity.
+	 */
+	return (SIZE_MAX - 1);
+#else
 	return (1UL<<35);
+#endif
 }
 
 static inline size_t drbg_max_requests(struct drbg_state *drbg)
 {
 	/* SP800-90A requires 2**48 maximum requests before reseeding */
+#if (__BITS_PER_LONG == 32)
+	return SIZE_MAX;
+#else
 	return (1UL<<48);
+#endif
 }
 
 /*
-- 
cgit v1.2.3


From 970fdfa89babb5a6f1a3d345e8cb54d92c1e3a8f Mon Sep 17 00:00:00 2001
From: Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
Date: Mon, 11 Aug 2014 03:29:57 -0700
Subject: cfg80211: remove @gfp parameter from cfg80211_rx_mgmt()

In the cfg80211_rx_mgmt(), parameter @gfp was used for the memory allocation.
But, memory get allocated under spin_lock_bh(), this implies atomic context.
So, one can't use GFP_KERNEL, only variants with no __GFP_WAIT. Actually, in all
occurrences GFP_ATOMIC is used (wil6210 use GFP_KERNEL by mistake),
and it should be this way or warning triggered in the memory allocation code.

Remove @gfp parameter as no actual choice exist, and use hard coded
GFP_ATOMIC for memory allocation.

Signed-off-by: Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/wmi.c             | 5 ++---
 drivers/net/wireless/ath/wil6210/wmi.c            | 2 +-
 drivers/net/wireless/brcm80211/brcmfmac/p2p.c     | 6 ++----
 drivers/net/wireless/mwifiex/util.c               | 2 +-
 drivers/staging/rtl8723au/core/rtw_mlme_ext.c     | 2 +-
 drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c | 4 ++--
 include/net/cfg80211.h                            | 3 +--
 net/mac80211/rx.c                                 | 2 +-
 net/wireless/mlme.c                               | 4 ++--
 9 files changed, 13 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index 94df345d08c2..77fcca1f5bd6 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -619,8 +619,7 @@ static int ath6kl_wmi_rx_probe_req_event_rx(struct wmi *wmi, u8 *datap, int len,
 		   dlen, freq, vif->probe_req_report);
 
 	if (vif->probe_req_report || vif->nw_type == AP_NETWORK)
-		cfg80211_rx_mgmt(&vif->wdev, freq, 0, ev->data, dlen, 0,
-				 GFP_ATOMIC);
+		cfg80211_rx_mgmt(&vif->wdev, freq, 0, ev->data, dlen, 0);
 
 	return 0;
 }
@@ -659,7 +658,7 @@ static int ath6kl_wmi_rx_action_event_rx(struct wmi *wmi, u8 *datap, int len,
 		return -EINVAL;
 	}
 	ath6kl_dbg(ATH6KL_DBG_WMI, "rx_action: len=%u freq=%u\n", dlen, freq);
-	cfg80211_rx_mgmt(&vif->wdev, freq, 0, ev->data, dlen, 0, GFP_ATOMIC);
+	cfg80211_rx_mgmt(&vif->wdev, freq, 0, ev->data, dlen, 0);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 1d1d0afdd2e1..335bc38325db 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -350,7 +350,7 @@ static void wmi_evt_rx_mgmt(struct wil6210_priv *wil, int id, void *d, int len)
 		}
 	} else {
 		cfg80211_rx_mgmt(wil->wdev, freq, signal,
-				 (void *)rx_mgmt_frame, d_len, 0, GFP_KERNEL);
+				 (void *)rx_mgmt_frame, d_len, 0);
 	}
 }
 
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/brcm80211/brcmfmac/p2p.c
index 057b982ea8b3..1d78a91db594 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/p2p.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/p2p.c
@@ -1431,8 +1431,7 @@ int brcmf_p2p_notify_action_frame_rx(struct brcmf_if *ifp,
 					      IEEE80211_BAND_5GHZ);
 
 	wdev = &ifp->vif->wdev;
-	cfg80211_rx_mgmt(wdev, freq, 0, (u8 *)mgmt_frame, mgmt_frame_len, 0,
-			 GFP_ATOMIC);
+	cfg80211_rx_mgmt(wdev, freq, 0, (u8 *)mgmt_frame, mgmt_frame_len, 0);
 
 	kfree(mgmt_frame);
 	return 0;
@@ -1896,8 +1895,7 @@ s32 brcmf_p2p_notify_rx_mgmt_p2p_probereq(struct brcmf_if *ifp,
 					      IEEE80211_BAND_2GHZ :
 					      IEEE80211_BAND_5GHZ);
 
-	cfg80211_rx_mgmt(&vif->wdev, freq, 0, mgmt_frame, mgmt_frame_len, 0,
-			 GFP_ATOMIC);
+	cfg80211_rx_mgmt(&vif->wdev, freq, 0, mgmt_frame, mgmt_frame_len, 0);
 
 	brcmf_dbg(INFO, "mgmt_frame_len (%d) , e->datalen (%d), chanspec (%04x), freq (%d)\n",
 		  mgmt_frame_len, e->datalen, chanspec, freq);
diff --git a/drivers/net/wireless/mwifiex/util.c b/drivers/net/wireless/mwifiex/util.c
index cee028321a9a..ec79c49de097 100644
--- a/drivers/net/wireless/mwifiex/util.c
+++ b/drivers/net/wireless/mwifiex/util.c
@@ -172,7 +172,7 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv,
 
 	cfg80211_rx_mgmt(priv->wdev, priv->roc_cfg.chan.center_freq,
 			 CAL_RSSI(rx_pd->snr, rx_pd->nf), skb->data, pkt_len,
-			 0, GFP_ATOMIC);
+			 0);
 
 	return 0;
 }
diff --git a/drivers/staging/rtl8723au/core/rtw_mlme_ext.c b/drivers/staging/rtl8723au/core/rtw_mlme_ext.c
index c5fdcb89dacd..2a1502f351f8 100644
--- a/drivers/staging/rtl8723au/core/rtw_mlme_ext.c
+++ b/drivers/staging/rtl8723au/core/rtw_mlme_ext.c
@@ -2128,7 +2128,7 @@ static int on_action_public23a(struct rtw_adapter *padapter,
 						      IEEE80211_BAND_5GHZ);
 
 	if (cfg80211_rx_mgmt(padapter->rtw_wdev, freq, 0, pframe,
-			     skb->len, 0, GFP_ATOMIC))
+			     skb->len, 0))
 		return _SUCCESS;
 
 	return _FAIL;
diff --git a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
index 93dc844a10b3..2d6d7d1a5b7d 100644
--- a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
+++ b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
@@ -2379,7 +2379,7 @@ void rtw_cfg80211_indicate_sta_assoc(struct rtw_adapter *padapter,
 						      IEEE80211_BAND_5GHZ);
 
 	cfg80211_rx_mgmt(padapter->rtw_wdev, freq, 0, pmgmt_frame, frame_len,
-			 0, GFP_ATOMIC);
+			 0);
 #endif /* defined(RTW_USE_CFG80211_STA_EVENT) */
 }
 
@@ -2425,7 +2425,7 @@ void rtw_cfg80211_indicate_sta_disassoc(struct rtw_adapter *padapter,
 	frame_len = sizeof(struct ieee80211_hdr_3addr) + 2;
 
 	cfg80211_rx_mgmt(padapter->rtw_wdev, freq, 0, (u8 *)&mgmt, frame_len,
-			 0, GFP_ATOMIC);
+			 0);
 #endif /* defined(RTW_USE_CFG80211_STA_EVENT) */
 }
 
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 0a080c4de275..7b8dac3efe8f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4412,7 +4412,6 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr,
  * @buf: Management frame (header + body)
  * @len: length of the frame data
  * @flags: flags, as defined in enum nl80211_rxmgmt_flags
- * @gfp: context flags
  *
  * This function is called whenever an Action frame is received for a station
  * mode interface, but is not processed in kernel.
@@ -4423,7 +4422,7 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr,
  * driver is responsible for rejecting the frame.
  */
 bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_dbm,
-		      const u8 *buf, size_t len, u32 flags, gfp_t gfp);
+		      const u8 *buf, size_t len, u32 flags);
 
 /**
  * cfg80211_mgmt_tx_status - notification of TX status for management frame
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index bd2c9b22c945..a8d862f9183c 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2725,7 +2725,7 @@ ieee80211_rx_h_userspace_mgmt(struct ieee80211_rx_data *rx)
 		sig = status->signal;
 
 	if (cfg80211_rx_mgmt(&rx->sdata->wdev, status->freq, sig,
-			     rx->skb->data, rx->skb->len, 0, GFP_ATOMIC)) {
+			     rx->skb->data, rx->skb->len, 0)) {
 		if (rx->sta)
 			rx->sta->rx_packets++;
 		dev_kfree_skb(rx->skb);
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 266766b8d80b..369fc334fdad 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -605,7 +605,7 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev,
 }
 
 bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm,
-		      const u8 *buf, size_t len, u32 flags, gfp_t gfp)
+		      const u8 *buf, size_t len, u32 flags)
 {
 	struct wiphy *wiphy = wdev->wiphy;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
@@ -648,7 +648,7 @@ bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm,
 		/* Indicate the received Action frame to user space */
 		if (nl80211_send_mgmt(rdev, wdev, reg->nlportid,
 				      freq, sig_mbm,
-				      buf, len, flags, gfp))
+				      buf, len, flags, GFP_ATOMIC))
 			continue;
 
 		result = true;
-- 
cgit v1.2.3


From 170fd0b1f6108b48df4369afa0ee29a83e922748 Mon Sep 17 00:00:00 2001
From: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Date: Wed, 30 Jul 2014 14:36:18 +0300
Subject: ieee80211: Support parsing TPC report element in action frames

TPC report element is contained in spectrum management's tpc report
action frames and in radio measurement's link measurement report
action frames. Add a function which checks whether an action frame
contains this element. This may be needed by the drivers in order
to set the correct tx power value in these frames.

Signed-off-by: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 65 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 63ab3873c5ed..8018c915ee63 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -838,6 +838,16 @@ enum ieee80211_vht_opmode_bits {
 
 #define WLAN_SA_QUERY_TR_ID_LEN 2
 
+/**
+ * struct ieee80211_tpc_report_ie
+ *
+ * This structure refers to "TPC Report element"
+ */
+struct ieee80211_tpc_report_ie {
+	u8 tx_power;
+	u8 link_margin;
+} __packed;
+
 struct ieee80211_mgmt {
 	__le16 frame_control;
 	__le16 duration;
@@ -973,6 +983,13 @@ struct ieee80211_mgmt {
 					u8 action_code;
 					u8 operating_mode;
 				} __packed vht_opmode_notif;
+				struct {
+					u8 action_code;
+					u8 dialog_token;
+					u8 tpc_elem_id;
+					u8 tpc_elem_length;
+					struct ieee80211_tpc_report_ie tpc;
+				} __packed tpc_report;
 			} u;
 		} __packed action;
 	} u;
@@ -1865,6 +1882,7 @@ enum ieee80211_category {
 	WLAN_CATEGORY_DLS = 2,
 	WLAN_CATEGORY_BACK = 3,
 	WLAN_CATEGORY_PUBLIC = 4,
+	WLAN_CATEGORY_RADIO_MEASUREMENT = 5,
 	WLAN_CATEGORY_HT = 7,
 	WLAN_CATEGORY_SA_QUERY = 8,
 	WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9,
@@ -2378,4 +2396,51 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim,
 #define TU_TO_JIFFIES(x)	(usecs_to_jiffies((x) * 1024))
 #define TU_TO_EXP_TIME(x)	(jiffies + TU_TO_JIFFIES(x))
 
+/**
+ * ieee80211_action_contains_tpc - checks if the frame contains TPC element
+ * @skb: the skb containing the frame, length will be checked
+ *
+ * This function checks if it's either TPC report action frame or Link
+ * Measurement report action frame as defined in IEEE Std. 802.11-2012 8.5.2.5
+ * and 8.5.7.5 accordingly.
+ */
+static inline bool ieee80211_action_contains_tpc(struct sk_buff *skb)
+{
+	struct ieee80211_mgmt *mgmt = (void *)skb->data;
+
+	if (!ieee80211_is_action(mgmt->frame_control))
+		return false;
+
+	if (skb->len < IEEE80211_MIN_ACTION_SIZE +
+		       sizeof(mgmt->u.action.u.tpc_report))
+		return false;
+
+	/*
+	 * TPC report - check that:
+	 * category = 0 (Spectrum Management) or 5 (Radio Measurement)
+	 * spectrum management action = 3 (TPC/Link Measurement report)
+	 * TPC report EID = 35
+	 * TPC report element length = 2
+	 *
+	 * The spectrum management's tpc_report struct is used here both for
+	 * parsing tpc_report and radio measurement's link measurement report
+	 * frame, since the relevant part is identical in both frames.
+	 */
+	if (mgmt->u.action.category != WLAN_CATEGORY_SPECTRUM_MGMT &&
+	    mgmt->u.action.category != WLAN_CATEGORY_RADIO_MEASUREMENT)
+		return false;
+
+	/* both spectrum mgmt and link measurement have same action code */
+	if (mgmt->u.action.u.tpc_report.action_code !=
+	    WLAN_ACTION_SPCT_TPC_RPRT)
+		return false;
+
+	if (mgmt->u.action.u.tpc_report.tpc_elem_id != WLAN_EID_TPC_REPORT ||
+	    mgmt->u.action.u.tpc_report.tpc_elem_length !=
+	    sizeof(struct ieee80211_tpc_report_ie))
+		return false;
+
+	return true;
+}
+
 #endif /* LINUX_IEEE80211_H */
-- 
cgit v1.2.3


From ca34e3b5c808385b175650605faa29e71e91991b Mon Sep 17 00:00:00 2001
From: Ido Yariv <ido@wizery.com>
Date: Tue, 29 Jul 2014 15:38:53 +0300
Subject: mac80211: Fix accounting of the tailroom-needed counter

When hw acceleration is enabled, the GENERATE_IV or PUT_IV_SPACE flags
will only require headroom space. Consequently, the tailroom-needed
counter can safely be decremented.

Signed-off-by: Ido Yariv <idox.yariv@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  7 +++++--
 net/mac80211/key.c     | 12 +++---------
 2 files changed, 8 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 1cd84444665c..1fbed0a6d556 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1226,7 +1226,8 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  *
  * @IEEE80211_KEY_FLAG_GENERATE_IV: This flag should be set by the
  *	driver to indicate that it requires IV generation for this
- *	particular key.
+ *	particular key. Setting this flag does not necessarily mean that SKBs
+ *	will have sufficient tailroom for ICV or MIC.
  * @IEEE80211_KEY_FLAG_GENERATE_MMIC: This flag should be set by
  *	the driver for a TKIP key if it requires Michael MIC
  *	generation in software.
@@ -1238,7 +1239,9 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  * @IEEE80211_KEY_FLAG_PUT_IV_SPACE: This flag should be set by the driver
  *	if space should be prepared for the IV, but the IV
  *	itself should not be generated. Do not set together with
- *	@IEEE80211_KEY_FLAG_GENERATE_IV on the same key.
+ *	@IEEE80211_KEY_FLAG_GENERATE_IV on the same key. Setting this flag does
+ *	not necessarily mean that SKBs will have sufficient tailroom for ICV or
+ *	MIC.
  * @IEEE80211_KEY_FLAG_RX_MGMT: This key will be used to decrypt received
  *	management frames. The flag can help drivers that have a hardware
  *	crypto implementation that doesn't deal with management frames
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index d808cff80153..6429d0e1d4a1 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -130,9 +130,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	if (!ret) {
 		key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE;
 
-		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
-		      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
-		      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
+		if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
 			sdata->crypto_tx_tailroom_needed_cnt--;
 
 		WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
@@ -180,9 +178,7 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key)
 	sta = key->sta;
 	sdata = key->sdata;
 
-	if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
-	      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
-	      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
+	if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
 		increment_tailroom_need_count(sdata);
 
 	ret = drv_set_key(key->local, DISABLE_KEY, sdata,
@@ -878,9 +874,7 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf)
 	if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) {
 		key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE;
 
-		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
-		      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
-		      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
+		if (!(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC))
 			increment_tailroom_need_count(key->sdata);
 	}
 
-- 
cgit v1.2.3


From c70f59a2a007c57843195a93c3b7308204e0a5ab Mon Sep 17 00:00:00 2001
From: Ido Yariv <ido@wizery.com>
Date: Tue, 29 Jul 2014 15:39:14 +0300
Subject: mac80211: don't resize skbs needlessly

Header-less cloned skbs with sufficient headroom need not be cloned
unless the tailroom is going to be modified.

Fix ieee80211_skb_resize so it would only resize cloned skbs if either
the header isn't released or the tailroom is going to be modified.

Some drivers might have assumed that skbs are never cloned, so add a HW
flag that explicitly permits cloned TX skbs. Drivers which do not modify
TX skbs should set this flag to avoid copying skbs.

Signed-off-by: Ido Yariv <idox.yariv@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 5 ++++-
 net/mac80211/tx.c      | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 1fbed0a6d556..c9b2bec8db47 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1609,6 +1609,9 @@ struct ieee80211_tx_control {
  *	is not enabled the default action is to disconnect when getting the
  *	CSA frame.
  *
+ * @IEEE80211_HW_SUPPORTS_CLONED_SKBS: The driver will never modify the payload
+ *	or tailroom of TX skbs without copying them first.
+ *
  * @IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS: The HW supports scanning on all bands
  *	in one command, mac80211 doesn't have to run separate scans per band.
  */
@@ -1642,7 +1645,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_TIMING_BEACON_ONLY			= 1<<26,
 	IEEE80211_HW_SUPPORTS_HT_CCK_RATES		= 1<<27,
 	IEEE80211_HW_CHANCTX_STA_CSA			= 1<<28,
-	/* bit 29 unused */
+	IEEE80211_HW_SUPPORTS_CLONED_SKBS		= 1<<29,
 	IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS		= 1<<30,
 };
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 2051cc60f8ce..925c39f4099e 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1478,7 +1478,10 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
 		tail_need = max_t(int, tail_need, 0);
 	}
 
-	if (skb_cloned(skb))
+	if (skb_cloned(skb) &&
+	    (!(local->hw.flags & IEEE80211_HW_SUPPORTS_CLONED_SKBS) ||
+	     !skb_clone_writable(skb, ETH_HLEN) ||
+	     sdata->crypto_tx_tailroom_needed_cnt))
 		I802_DEBUG_INC(local->tx_expand_skb_head_cloned);
 	else if (head_need || tail_need)
 		I802_DEBUG_INC(local->tx_expand_skb_head);
-- 
cgit v1.2.3


From 0e227084aee36b3ba27b4fc9cd9e425be6ce2ab8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 12 Aug 2014 20:34:30 +0200
Subject: cfg80211: clarify BSS probe response vs. beacon data

There are a few possible cases of where BSS data came from:
 1) only a beacon has been received
 2) only a probe response has been received
 3) the driver didn't report what it received (this happens when
    using cfg80211_inform_bss[_width]())
 4) both probe response and beacon data has been received

Unfortunately, in the userspace API, a few things weren't there:
 a) there was no way to differentiate cases 1) and 4) above
    without comparing the data of the IEs
 b) the TSF was always from the last frame, instead of being
    exposed for beacon/probe response separately like IEs

Fix this by
   i) exporting a new flag attribute that indicates whether or
      not probe response data has been received - this addresses (a)
  ii) exporting a BEACON_TSF attribute that holds the beacon's TSF
      if a beacon has been received
 iii) not exporting the beacon attributes in case (3) above as that
      would just lead userspace into thinking the data actually came
      from a beacon when that isn't clear

To implement this, track inside the IEs struct whether or not it
(definitely) came from a beacon.

Reported-by: William Seto
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  2 ++
 include/uapi/linux/nl80211.h | 16 ++++++++++++++--
 net/wireless/nl80211.c       | 16 ++++++++++++----
 net/wireless/scan.c          |  6 ++++--
 4 files changed, 32 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 7b8dac3efe8f..77b85a89abca 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1503,12 +1503,14 @@ enum cfg80211_signal_type {
  * @tsf: TSF contained in the frame that carried these IEs
  * @rcu_head: internal use, for freeing
  * @len: length of the IEs
+ * @from_beacon: these IEs are known to come from a beacon
  * @data: IE data
  */
 struct cfg80211_bss_ies {
 	u64 tsf;
 	struct rcu_head rcu_head;
 	int len;
+	bool from_beacon;
 	u8 data[];
 };
 
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index f1db15b9c041..d097568da690 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3055,14 +3055,20 @@ enum nl80211_bss_scan_width {
  * @NL80211_BSS_BSSID: BSSID of the BSS (6 octets)
  * @NL80211_BSS_FREQUENCY: frequency in MHz (u32)
  * @NL80211_BSS_TSF: TSF of the received probe response/beacon (u64)
+ *	(if @NL80211_BSS_PRESP_DATA is present then this is known to be
+ *	from a probe response, otherwise it may be from the same beacon
+ *	that the NL80211_BSS_BEACON_TSF will be from)
  * @NL80211_BSS_BEACON_INTERVAL: beacon interval of the (I)BSS (u16)
  * @NL80211_BSS_CAPABILITY: capability field (CPU order, u16)
  * @NL80211_BSS_INFORMATION_ELEMENTS: binary attribute containing the
  *	raw information elements from the probe response/beacon (bin);
- *	if the %NL80211_BSS_BEACON_IES attribute is present, the IEs here are
- *	from a Probe Response frame; otherwise they are from a Beacon frame.
+ *	if the %NL80211_BSS_BEACON_IES attribute is present and the data is
+ *	different then the IEs here are from a Probe Response frame; otherwise
+ *	they are from a Beacon frame.
  *	However, if the driver does not indicate the source of the IEs, these
  *	IEs may be from either frame subtype.
+ *	If present, the @NL80211_BSS_PRESP_DATA attribute indicates that the
+ *	data here is known to be from a probe response, without any heuristics.
  * @NL80211_BSS_SIGNAL_MBM: signal strength of probe response/beacon
  *	in mBm (100 * dBm) (s32)
  * @NL80211_BSS_SIGNAL_UNSPEC: signal strength of the probe response/beacon
@@ -3074,6 +3080,10 @@ enum nl80211_bss_scan_width {
  *	yet been received
  * @NL80211_BSS_CHAN_WIDTH: channel width of the control channel
  *	(u32, enum nl80211_bss_scan_width)
+ * @NL80211_BSS_BEACON_TSF: TSF of the last received beacon (u64)
+ *	(not present if no beacon frame has been received yet)
+ * @NL80211_BSS_PRESP_DATA: the data in @NL80211_BSS_INFORMATION_ELEMENTS and
+ *	@NL80211_BSS_TSF is known to be from a probe response (flag attribute)
  * @__NL80211_BSS_AFTER_LAST: internal
  * @NL80211_BSS_MAX: highest BSS attribute
  */
@@ -3091,6 +3101,8 @@ enum nl80211_bss {
 	NL80211_BSS_SEEN_MS_AGO,
 	NL80211_BSS_BEACON_IES,
 	NL80211_BSS_CHAN_WIDTH,
+	NL80211_BSS_BEACON_TSF,
+	NL80211_BSS_PRESP_DATA,
 
 	/* keep last */
 	__NL80211_BSS_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index df7b1332a1ec..3011401f52c0 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6033,7 +6033,6 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 	const struct cfg80211_bss_ies *ies;
 	void *hdr;
 	struct nlattr *bss;
-	bool tsf = false;
 
 	ASSERT_WDEV_LOCK(wdev);
 
@@ -6060,18 +6059,27 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 		goto nla_put_failure;
 
 	rcu_read_lock();
+	/* indicate whether we have probe response data or not */
+	if (rcu_access_pointer(res->proberesp_ies) &&
+	    nla_put_flag(msg, NL80211_BSS_PRESP_DATA))
+		goto fail_unlock_rcu;
+
+	/* this pointer prefers to be pointed to probe response data
+	 * but is always valid
+	 */
 	ies = rcu_dereference(res->ies);
 	if (ies) {
 		if (nla_put_u64(msg, NL80211_BSS_TSF, ies->tsf))
 			goto fail_unlock_rcu;
-		tsf = true;
 		if (ies->len && nla_put(msg, NL80211_BSS_INFORMATION_ELEMENTS,
 					ies->len, ies->data))
 			goto fail_unlock_rcu;
 	}
+
+	/* and this pointer is always (unless driver didn't know) beacon data */
 	ies = rcu_dereference(res->beacon_ies);
-	if (ies) {
-		if (!tsf && nla_put_u64(msg, NL80211_BSS_TSF, ies->tsf))
+	if (ies && ies->from_beacon) {
+		if (nla_put_u64(msg, NL80211_BSS_BEACON_TSF, ies->tsf))
 			goto fail_unlock_rcu;
 		if (ies->len && nla_put(msg, NL80211_BSS_BEACON_IES,
 					ies->len, ies->data))
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 0798c62e6085..ad1a1a2808d3 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -918,11 +918,12 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 	 * override the IEs pointer should we have received an earlier
 	 * indication of Probe Response data.
 	 */
-	ies = kmalloc(sizeof(*ies) + ielen, gfp);
+	ies = kzalloc(sizeof(*ies) + ielen, gfp);
 	if (!ies)
 		return NULL;
 	ies->len = ielen;
 	ies->tsf = tsf;
+	ies->from_beacon = false;
 	memcpy(ies->data, ie, ielen);
 
 	rcu_assign_pointer(tmp.pub.beacon_ies, ies);
@@ -982,11 +983,12 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy,
 	if (!channel)
 		return NULL;
 
-	ies = kmalloc(sizeof(*ies) + ielen, gfp);
+	ies = kzalloc(sizeof(*ies) + ielen, gfp);
 	if (!ies)
 		return NULL;
 	ies->len = ielen;
 	ies->tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp);
+	ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control);
 	memcpy(ies->data, mgmt->u.probe_resp.variable, ielen);
 
 	if (ieee80211_is_probe_resp(mgmt->frame_control))
-- 
cgit v1.2.3


From 5bc8c1f2b070bab82ed738f98ecfac725e33c57f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 12 Aug 2014 21:01:28 +0200
Subject: cfg80211: allow passing frame type to cfg80211_inform_bss()

When using the cfg80211_inform_bss[_width]() functions drivers
cannot currently indicate whether the data was received in a
beacon or probe response. Fix that by passing a new enum that
indicates such (or unknown).

For good measure, use it in ath6kl.

Acked-by: Kalle Valo <kvalo@qca.qualcomm.com> [ath6kl]
Acked-by: Arend van Spriel <arend@broadcom.com> [brcmfmac]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c         |  1 +
 drivers/net/wireless/ath/ath6kl/wmi.c              | 43 +++++-----------------
 drivers/net/wireless/ath/wil6210/wmi.c             |  2 +-
 .../net/wireless/brcm80211/brcmfmac/wl_cfg80211.c  | 18 ++++++---
 drivers/net/wireless/libertas/cfg.c                |  2 +
 drivers/net/wireless/mwifiex/cfg80211.c            |  1 +
 drivers/net/wireless/mwifiex/scan.c                |  3 +-
 drivers/net/wireless/orinoco/scan.c                | 14 ++++---
 drivers/net/wireless/rndis_wlan.c                  | 14 ++++---
 drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c  |  1 +
 drivers/staging/wlan-ng/cfg80211.c                 |  1 +
 include/net/cfg80211.h                             | 20 +++++++++-
 net/wireless/scan.c                                | 15 +++++++-
 13 files changed, 77 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index e535807c3d89..ba60e37213eb 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -717,6 +717,7 @@ ath6kl_add_bss_if_needed(struct ath6kl_vif *vif,
 		memcpy(ie + 2, vif->ssid, vif->ssid_len);
 		memcpy(ie + 2 + vif->ssid_len, beacon_ie, beacon_ie_len);
 		bss = cfg80211_inform_bss(ar->wiphy, chan,
+					  CFG80211_BSS_FTYPE_UNKNOWN,
 					  bssid, 0, cap_val, 100,
 					  ie, 2 + vif->ssid_len + beacon_ie_len,
 					  0, GFP_KERNEL);
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index 77fcca1f5bd6..b921005ad7ee 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -1092,7 +1092,6 @@ static int ath6kl_wmi_bssinfo_event_rx(struct wmi *wmi, u8 *datap, int len,
 	u8 *buf;
 	struct ieee80211_channel *channel;
 	struct ath6kl *ar = wmi->parent_dev;
-	struct ieee80211_mgmt *mgmt;
 	struct cfg80211_bss *bss;
 
 	if (len <= sizeof(struct wmi_bss_info_hdr2))
@@ -1138,39 +1137,15 @@ static int ath6kl_wmi_bssinfo_event_rx(struct wmi *wmi, u8 *datap, int len,
 		}
 	}
 
-	/*
-	 * In theory, use of cfg80211_inform_bss() would be more natural here
-	 * since we do not have the full frame. However, at least for now,
-	 * cfg80211 can only distinguish Beacon and Probe Response frames from
-	 * each other when using cfg80211_inform_bss_frame(), so let's build a
-	 * fake IEEE 802.11 header to be able to take benefit of this.
-	 */
-	mgmt = kmalloc(24 + len, GFP_ATOMIC);
-	if (mgmt == NULL)
-		return -EINVAL;
-
-	if (bih->frame_type == BEACON_FTYPE) {
-		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
-						  IEEE80211_STYPE_BEACON);
-		memset(mgmt->da, 0xff, ETH_ALEN);
-	} else {
-		struct net_device *dev = vif->ndev;
-
-		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
-						  IEEE80211_STYPE_PROBE_RESP);
-		memcpy(mgmt->da, dev->dev_addr, ETH_ALEN);
-	}
-	mgmt->duration = cpu_to_le16(0);
-	memcpy(mgmt->sa, bih->bssid, ETH_ALEN);
-	memcpy(mgmt->bssid, bih->bssid, ETH_ALEN);
-	mgmt->seq_ctrl = cpu_to_le16(0);
-
-	memcpy(&mgmt->u.beacon, buf, len);
-
-	bss = cfg80211_inform_bss_frame(ar->wiphy, channel, mgmt,
-					24 + len, (bih->snr - 95) * 100,
-					GFP_ATOMIC);
-	kfree(mgmt);
+	bss = cfg80211_inform_bss(ar->wiphy, channel,
+				  bih->frame_type == BEACON_FTYPE ?
+					CFG80211_BSS_FTYPE_BEACON :
+					CFG80211_BSS_FTYPE_PRESP,
+				  bih->bssid, get_unaligned_le64((__le64 *)buf),
+				  get_unaligned_le16(((__le16 *)buf) + 5),
+				  get_unaligned_le16(((__le16 *)buf) + 4),
+				  buf + 8 + 2 + 2, len - 8 - 2 - 2,
+				  (bih->snr - 95) * 100, GFP_ATOMIC);
 	if (bss == NULL)
 		return -ENOMEM;
 	cfg80211_put_bss(ar->wiphy, bss);
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 335bc38325db..960b66fc1430 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -346,7 +346,7 @@ static void wmi_evt_rx_mgmt(struct wil6210_priv *wil, int id, void *d, int len)
 				    rx_mgmt_frame->bssid);
 			cfg80211_put_bss(wiphy, bss);
 		} else {
-			wil_err(wil, "cfg80211_inform_bss() failed\n");
+			wil_err(wil, "cfg80211_inform_bss_frame() failed\n");
 		}
 	} else {
 		cfg80211_rx_mgmt(wil->wdev, freq, signal,
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
index 02fe706fc9ec..12a60ca1462a 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
@@ -2394,9 +2394,13 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg,
 	brcmf_dbg(CONN, "Beacon interval: %d\n", notify_interval);
 	brcmf_dbg(CONN, "Signal: %d\n", notify_signal);
 
-	bss = cfg80211_inform_bss(wiphy, notify_channel, (const u8 *)bi->BSSID,
-		0, notify_capability, notify_interval, notify_ie,
-		notify_ielen, notify_signal, GFP_KERNEL);
+	bss = cfg80211_inform_bss(wiphy, notify_channel,
+				  CFG80211_BSS_FTYPE_UNKNOWN,
+				  (const u8 *)bi->BSSID,
+				  0, notify_capability,
+				  notify_interval, notify_ie,
+				  notify_ielen, notify_signal,
+				  GFP_KERNEL);
 
 	if (!bss)
 		return -ENOMEM;
@@ -2498,9 +2502,11 @@ static s32 wl_inform_ibss(struct brcmf_cfg80211_info *cfg,
 	brcmf_dbg(CONN, "beacon interval: %d\n", notify_interval);
 	brcmf_dbg(CONN, "signal: %d\n", notify_signal);
 
-	bss = cfg80211_inform_bss(wiphy, notify_channel, bssid,
-		0, notify_capability, notify_interval,
-		notify_ie, notify_ielen, notify_signal, GFP_KERNEL);
+	bss = cfg80211_inform_bss(wiphy, notify_channel,
+				  CFG80211_BSS_FTYPE_UNKNOWN, bssid, 0,
+				  notify_capability, notify_interval,
+				  notify_ie, notify_ielen, notify_signal,
+				  GFP_KERNEL);
 
 	if (!bss) {
 		err = -ENOMEM;
diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c
index 47a998d8f99e..22884ba7d6cc 100644
--- a/drivers/net/wireless/libertas/cfg.c
+++ b/drivers/net/wireless/libertas/cfg.c
@@ -653,6 +653,7 @@ static int lbs_ret_scan(struct lbs_private *priv, unsigned long dummy,
 			if (channel &&
 			    !(channel->flags & IEEE80211_CHAN_DISABLED)) {
 				bss = cfg80211_inform_bss(wiphy, channel,
+					CFG80211_BSS_FTYPE_UNKNOWN,
 					bssid, get_unaligned_le64(tsfdesc),
 					capa, intvl, ie, ielen,
 					LBS_SCAN_RSSI_TO_MBM(rssi),
@@ -1754,6 +1755,7 @@ static void lbs_join_post(struct lbs_private *priv,
 
 	bss = cfg80211_inform_bss(priv->wdev->wiphy,
 				  params->chandef.chan,
+				  CFG80211_BSS_FTYPE_UNKNOWN,
 				  bssid,
 				  0,
 				  capability,
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index e2e6bf13c2d8..15f994f3b4ce 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -1557,6 +1557,7 @@ static int mwifiex_cfg80211_inform_ibss_bss(struct mwifiex_private *priv)
 						       band));
 
 	bss = cfg80211_inform_bss(priv->wdev->wiphy, chan,
+				  CFG80211_BSS_FTYPE_UNKNOWN,
 				  bss_info.bssid, 0, WLAN_CAPABILITY_IBSS,
 				  0, ie_buf, ie_len, 0, GFP_KERNEL);
 	cfg80211_put_bss(priv->wdev->wiphy, bss);
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index dee717a19ddb..195ef0ca343f 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -1719,7 +1719,8 @@ mwifiex_parse_single_response_buf(struct mwifiex_private *priv, u8 **bss_info,
 
 		if (chan && !(chan->flags & IEEE80211_CHAN_DISABLED)) {
 			bss = cfg80211_inform_bss(priv->wdev->wiphy,
-					    chan, bssid, timestamp,
+					    chan, CFG80211_BSS_FTYPE_UNKNOWN,
+					    bssid, timestamp,
 					    cap_info_bitmap, beacon_period,
 					    ie_buf, ie_len, rssi, GFP_KERNEL);
 			bss_priv = (struct mwifiex_bss_priv *)bss->priv;
diff --git a/drivers/net/wireless/orinoco/scan.c b/drivers/net/wireless/orinoco/scan.c
index e175b9b8561b..2c66166add70 100644
--- a/drivers/net/wireless/orinoco/scan.c
+++ b/drivers/net/wireless/orinoco/scan.c
@@ -123,9 +123,10 @@ static void orinoco_add_hostscan_result(struct orinoco_private *priv,
 	beacon_interval = le16_to_cpu(bss->a.beacon_interv);
 	signal = SIGNAL_TO_MBM(le16_to_cpu(bss->a.level));
 
-	cbss = cfg80211_inform_bss(wiphy, channel, bss->a.bssid, timestamp,
-				   capability, beacon_interval, ie_buf, ie_len,
-				   signal, GFP_KERNEL);
+	cbss = cfg80211_inform_bss(wiphy, channel, CFG80211_BSS_FTYPE_UNKNOWN,
+				   bss->a.bssid, timestamp, capability,
+				   beacon_interval, ie_buf, ie_len, signal,
+				   GFP_KERNEL);
 	cfg80211_put_bss(wiphy, cbss);
 }
 
@@ -156,9 +157,10 @@ void orinoco_add_extscan_result(struct orinoco_private *priv,
 	ie = bss->data;
 	signal = SIGNAL_TO_MBM(bss->level);
 
-	cbss = cfg80211_inform_bss(wiphy, channel, bss->bssid, timestamp,
-				   capability, beacon_interval, ie, ie_len,
-				   signal, GFP_KERNEL);
+	cbss = cfg80211_inform_bss(wiphy, channel, CFG80211_BSS_FTYPE_UNKNOWN,
+				   bss->bssid, timestamp, capability,
+				   beacon_interval, ie, ie_len, signal,
+				   GFP_KERNEL);
 	cfg80211_put_bss(wiphy, cbss);
 }
 
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index d2a9a08210be..1a4facd1fbf3 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -2022,9 +2022,10 @@ static bool rndis_bss_info_update(struct usbnet *usbdev,
 	capability = le16_to_cpu(fixed->capabilities);
 	beacon_interval = le16_to_cpu(fixed->beacon_interval);
 
-	bss = cfg80211_inform_bss(priv->wdev.wiphy, channel, bssid->mac,
-		timestamp, capability, beacon_interval, ie, ie_len, signal,
-		GFP_KERNEL);
+	bss = cfg80211_inform_bss(priv->wdev.wiphy, channel,
+				  CFG80211_BSS_FTYPE_UNKNOWN, bssid->mac,
+				  timestamp, capability, beacon_interval,
+				  ie, ie_len, signal, GFP_KERNEL);
 	cfg80211_put_bss(priv->wdev.wiphy, bss);
 
 	return (bss != NULL);
@@ -2711,9 +2712,10 @@ static void rndis_wlan_craft_connected_bss(struct usbnet *usbdev, u8 *bssid,
 		bssid, (u32)timestamp, capability, beacon_period, ie_len,
 		ssid.essid, signal);
 
-	bss = cfg80211_inform_bss(priv->wdev.wiphy, channel, bssid,
-		timestamp, capability, beacon_period, ie_buf, ie_len,
-		signal, GFP_KERNEL);
+	bss = cfg80211_inform_bss(priv->wdev.wiphy, channel,
+				  CFG80211_BSS_FTYPE_UNKNOWN, bssid,
+				  timestamp, capability, beacon_period,
+				  ie_buf, ie_len, signal, GFP_KERNEL);
 	cfg80211_put_bss(priv->wdev.wiphy, bss);
 }
 
diff --git a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
index 2d6d7d1a5b7d..8b0ccb5c5fc4 100644
--- a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
+++ b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
@@ -279,6 +279,7 @@ static int rtw_cfg80211_inform_bss(struct rtw_adapter *padapter,
 	}
 
 	bss = cfg80211_inform_bss(wiphy, notify_channel,
+				  CFG80211_BSS_FTYPE_UNKNOWN,
 				  pnetwork->network.MacAddress,
 				  pnetwork->network.tsf,
 				  pnetwork->network.capability,
diff --git a/drivers/staging/wlan-ng/cfg80211.c b/drivers/staging/wlan-ng/cfg80211.c
index 3727f6d25cf1..8942dcb44180 100644
--- a/drivers/staging/wlan-ng/cfg80211.c
+++ b/drivers/staging/wlan-ng/cfg80211.c
@@ -422,6 +422,7 @@ static int prism2_scan(struct wiphy *wiphy,
 						      IEEE80211_BAND_2GHZ);
 		bss = cfg80211_inform_bss(wiphy,
 			ieee80211_get_channel(wiphy, freq),
+			CFG80211_BSS_FTYPE_UNKNOWN,
 			(const u8 *) &(msg2.bssid.data.data),
 			msg2.timestamp.data, msg2.capinfo.data,
 			msg2.beaconperiod.data,
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 77b85a89abca..ab21299c8f4d 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3767,11 +3767,25 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy,
 }
 
 /**
- * cfg80211_inform_bss - inform cfg80211 of a new BSS
+ * enum cfg80211_bss_frame_type - frame type that the BSS data came from
+ * @CFG80211_BSS_FTYPE_UNKNOWN: driver doesn't know whether the data is
+ *	from a beacon or probe response
+ * @CFG80211_BSS_FTYPE_BEACON: data comes from a beacon
+ * @CFG80211_BSS_FTYPE_PRESP: data comes from a probe response
+ */
+enum cfg80211_bss_frame_type {
+	CFG80211_BSS_FTYPE_UNKNOWN,
+	CFG80211_BSS_FTYPE_BEACON,
+	CFG80211_BSS_FTYPE_PRESP,
+};
+
+/**
+ * cfg80211_inform_bss_width - inform cfg80211 of a new BSS
  *
  * @wiphy: the wiphy reporting the BSS
  * @rx_channel: The channel the frame was received on
  * @scan_width: width of the control channel
+ * @ftype: frame type (if known)
  * @bssid: the BSSID of the BSS
  * @tsf: the TSF sent by the peer in the beacon/probe response (or 0)
  * @capability: the capability field sent by the peer
@@ -3791,6 +3805,7 @@ struct cfg80211_bss * __must_check
 cfg80211_inform_bss_width(struct wiphy *wiphy,
 			  struct ieee80211_channel *rx_channel,
 			  enum nl80211_bss_scan_width scan_width,
+			  enum cfg80211_bss_frame_type ftype,
 			  const u8 *bssid, u64 tsf, u16 capability,
 			  u16 beacon_interval, const u8 *ie, size_t ielen,
 			  s32 signal, gfp_t gfp);
@@ -3798,12 +3813,13 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 static inline struct cfg80211_bss * __must_check
 cfg80211_inform_bss(struct wiphy *wiphy,
 		    struct ieee80211_channel *rx_channel,
+		    enum cfg80211_bss_frame_type ftype,
 		    const u8 *bssid, u64 tsf, u16 capability,
 		    u16 beacon_interval, const u8 *ie, size_t ielen,
 		    s32 signal, gfp_t gfp)
 {
 	return cfg80211_inform_bss_width(wiphy, rx_channel,
-					 NL80211_BSS_CHAN_WIDTH_20,
+					 NL80211_BSS_CHAN_WIDTH_20, ftype,
 					 bssid, tsf, capability,
 					 beacon_interval, ie, ielen, signal,
 					 gfp);
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index ad1a1a2808d3..620a4b40d466 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -884,6 +884,7 @@ struct cfg80211_bss*
 cfg80211_inform_bss_width(struct wiphy *wiphy,
 			  struct ieee80211_channel *rx_channel,
 			  enum nl80211_bss_scan_width scan_width,
+			  enum cfg80211_bss_frame_type ftype,
 			  const u8 *bssid, u64 tsf, u16 capability,
 			  u16 beacon_interval, const u8 *ie, size_t ielen,
 			  s32 signal, gfp_t gfp)
@@ -911,7 +912,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 	tmp.pub.beacon_interval = beacon_interval;
 	tmp.pub.capability = capability;
 	/*
-	 * Since we do not know here whether the IEs are from a Beacon or Probe
+	 * If we do not know here whether the IEs are from a Beacon or Probe
 	 * Response frame, we need to pick one of the options and only use it
 	 * with the driver that does not provide the full Beacon/Probe Response
 	 * frame. Use Beacon frame pointer to avoid indicating that this should
@@ -926,7 +927,17 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 	ies->from_beacon = false;
 	memcpy(ies->data, ie, ielen);
 
-	rcu_assign_pointer(tmp.pub.beacon_ies, ies);
+	switch (ftype) {
+	case CFG80211_BSS_FTYPE_BEACON:
+		ies->from_beacon = true;
+		/* fall through to assign */
+	case CFG80211_BSS_FTYPE_UNKNOWN:
+		rcu_assign_pointer(tmp.pub.beacon_ies, ies);
+		break;
+	case CFG80211_BSS_FTYPE_PRESP:
+		rcu_assign_pointer(tmp.pub.proberesp_ies, ies);
+		break;
+	}
 	rcu_assign_pointer(tmp.pub.ies, ies);
 
 	signal_valid = abs(rx_channel->center_freq - channel->center_freq) <=
-- 
cgit v1.2.3


From 4a32fea9d78f2d2315c0072757b197d5a304dc8b Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Sun, 17 Aug 2014 12:30:27 -0500
Subject: scheduler: Replace __get_cpu_var with this_cpu_ptr

Convert all uses of __get_cpu_var for address calculation to use
this_cpu_ptr instead.

[Uses of __get_cpu_var with cpumask_var_t are no longer
handled by this patch]

Cc: Peter Zijlstra <peterz@infradead.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/kernel_stat.h   |  4 ++--
 kernel/events/callchain.c     |  4 ++--
 kernel/events/core.c          | 24 ++++++++++++------------
 kernel/sched/sched.h          |  4 ++--
 kernel/taskstats.c            |  2 +-
 kernel/time/tick-sched.c      |  4 ++--
 kernel/user-return-notifier.c |  4 ++--
 7 files changed, 23 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index ecbc52f9ff77..8422b4ed6882 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -44,8 +44,8 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 
 /* Must have preemption disabled for this to be meaningful. */
-#define kstat_this_cpu (&__get_cpu_var(kstat))
-#define kcpustat_this_cpu (&__get_cpu_var(kernel_cpustat))
+#define kstat_this_cpu this_cpu_ptr(&kstat)
+#define kcpustat_this_cpu this_cpu_ptr(&kernel_cpustat)
 #define kstat_cpu(cpu) per_cpu(kstat, cpu)
 #define kcpustat_cpu(cpu) per_cpu(kernel_cpustat, cpu)
 
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 97b67df8fbfe..c4f63e68a35c 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -137,7 +137,7 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 	int cpu;
 	struct callchain_cpus_entries *entries;
 
-	*rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
+	*rctx = get_recursion_context(this_cpu_ptr(callchain_recursion));
 	if (*rctx == -1)
 		return NULL;
 
@@ -153,7 +153,7 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 static void
 put_callchain_entry(int rctx)
 {
-	put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
+	put_recursion_context(this_cpu_ptr(callchain_recursion), rctx);
 }
 
 struct perf_callchain_entry *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cf24b3e42ec..4d44e40a0483 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -239,7 +239,7 @@ static void perf_duration_warn(struct irq_work *w)
 	u64 avg_local_sample_len;
 	u64 local_samples_len;
 
-	local_samples_len = __get_cpu_var(running_sample_length);
+	local_samples_len = __this_cpu_read(running_sample_length);
 	avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
 
 	printk_ratelimited(KERN_WARNING
@@ -261,10 +261,10 @@ void perf_sample_event_took(u64 sample_len_ns)
 		return;
 
 	/* decay the counter by 1 average sample */
-	local_samples_len = __get_cpu_var(running_sample_length);
+	local_samples_len = __this_cpu_read(running_sample_length);
 	local_samples_len -= local_samples_len/NR_ACCUMULATED_SAMPLES;
 	local_samples_len += sample_len_ns;
-	__get_cpu_var(running_sample_length) = local_samples_len;
+	__this_cpu_write(running_sample_length, local_samples_len);
 
 	/*
 	 * note: this will be biased artifically low until we have
@@ -877,7 +877,7 @@ static DEFINE_PER_CPU(struct list_head, rotation_list);
 static void perf_pmu_rotate_start(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-	struct list_head *head = &__get_cpu_var(rotation_list);
+	struct list_head *head = this_cpu_ptr(&rotation_list);
 
 	WARN_ON(!irqs_disabled());
 
@@ -2389,7 +2389,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
 	 * to check if we have to switch out PMU state.
 	 * cgroup event are system-wide mode only
 	 */
-	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
 		perf_cgroup_sched_out(task, next);
 }
 
@@ -2632,11 +2632,11 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	 * to check if we have to switch in PMU state.
 	 * cgroup event are system-wide mode only
 	 */
-	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
 		perf_cgroup_sched_in(prev, task);
 
 	/* check for system-wide branch_stack events */
-	if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
+	if (atomic_read(this_cpu_ptr(&perf_branch_stack_events)))
 		perf_branch_stack_sched_in(prev, task);
 }
 
@@ -2891,7 +2891,7 @@ bool perf_event_can_stop_tick(void)
 
 void perf_event_task_tick(void)
 {
-	struct list_head *head = &__get_cpu_var(rotation_list);
+	struct list_head *head = this_cpu_ptr(&rotation_list);
 	struct perf_cpu_context *cpuctx, *tmp;
 	struct perf_event_context *ctx;
 	int throttled;
@@ -5671,7 +5671,7 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
 				    struct perf_sample_data *data,
 				    struct pt_regs *regs)
 {
-	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 	struct perf_event *event;
 	struct hlist_head *head;
 
@@ -5690,7 +5690,7 @@ end:
 
 int perf_swevent_get_recursion_context(void)
 {
-	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 
 	return get_recursion_context(swhash->recursion);
 }
@@ -5698,7 +5698,7 @@ EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
 inline void perf_swevent_put_recursion_context(int rctx)
 {
-	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 
 	put_recursion_context(swhash->recursion, rctx);
 }
@@ -5727,7 +5727,7 @@ static void perf_swevent_read(struct perf_event *event)
 
 static int perf_swevent_add(struct perf_event *event, int flags)
 {
-	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 	struct hw_perf_event *hwc = &event->hw;
 	struct hlist_head *head;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 579712f4e9d5..77d92f8130e8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -650,10 +650,10 @@ static inline int cpu_of(struct rq *rq)
 DECLARE_PER_CPU(struct rq, runqueues);
 
 #define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
-#define this_rq()		(&__get_cpu_var(runqueues))
+#define this_rq()		this_cpu_ptr(&runqueues)
 #define task_rq(p)		cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
-#define raw_rq()		(&__raw_get_cpu_var(runqueues))
+#define raw_rq()		raw_cpu_ptr(&runqueues)
 
 static inline u64 rq_clock(struct rq *rq)
 {
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13d2f7cd65db..b312fcc73024 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -638,7 +638,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
 		fill_tgid_exit(tsk);
 	}
 
-	listeners = __this_cpu_ptr(&listener_array);
+	listeners = raw_cpu_ptr(&listener_array);
 	if (list_empty(&listeners->list))
 		return;
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 73f90932282b..3cadc112519f 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -924,7 +924,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
  */
 void tick_nohz_idle_exit(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t now;
 
 	local_irq_disable();
@@ -1041,7 +1041,7 @@ static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
 
 static inline void tick_nohz_irq_enter(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t now;
 
 	if (!ts->idle_active && !ts->tick_stopped)
diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c
index 394f70b17162..9586b670a5b2 100644
--- a/kernel/user-return-notifier.c
+++ b/kernel/user-return-notifier.c
@@ -14,7 +14,7 @@ static DEFINE_PER_CPU(struct hlist_head, return_notifier_list);
 void user_return_notifier_register(struct user_return_notifier *urn)
 {
 	set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
-	hlist_add_head(&urn->link, &__get_cpu_var(return_notifier_list));
+	hlist_add_head(&urn->link, this_cpu_ptr(&return_notifier_list));
 }
 EXPORT_SYMBOL_GPL(user_return_notifier_register);
 
@@ -25,7 +25,7 @@ EXPORT_SYMBOL_GPL(user_return_notifier_register);
 void user_return_notifier_unregister(struct user_return_notifier *urn)
 {
 	hlist_del(&urn->link);
-	if (hlist_empty(&__get_cpu_var(return_notifier_list)))
+	if (hlist_empty(this_cpu_ptr(&return_notifier_list)))
 		clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
 }
 EXPORT_SYMBOL_GPL(user_return_notifier_unregister);
-- 
cgit v1.2.3


From 903ceff7ca7b4d80c083a80ee5163b74e9fa359f Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Sun, 17 Aug 2014 12:30:35 -0500
Subject: net: Replace get_cpu_var through this_cpu_ptr

Replace uses of get_cpu_var for address calculation through this_cpu_ptr.

Cc: netdev@vger.kernel.org
Cc: Eric Dumazet <edumazet@google.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/net/netfilter/nf_conntrack.h |  2 +-
 include/net/snmp.h                   |  6 +++---
 net/core/dev.c                       | 14 +++++++-------
 net/core/drop_monitor.c              |  2 +-
 net/core/skbuff.c                    |  2 +-
 net/ipv4/route.c                     |  4 ++--
 net/ipv4/syncookies.c                |  2 +-
 net/ipv4/tcp.c                       |  2 +-
 net/ipv4/tcp_output.c                |  2 +-
 net/ipv6/syncookies.c                |  2 +-
 net/rds/ib_rdma.c                    |  2 +-
 11 files changed, 20 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 37252f71a380..c8a7db605e03 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -242,7 +242,7 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
 DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
 static inline struct nf_conn *nf_ct_untracked_get(void)
 {
-	return &__raw_get_cpu_var(nf_conntrack_untracked);
+	return raw_cpu_ptr(&nf_conntrack_untracked);
 }
 void nf_ct_untracked_status_or(unsigned long bits);
 
diff --git a/include/net/snmp.h b/include/net/snmp.h
index f1f27fdbb0d5..e154133877a2 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -168,7 +168,7 @@ struct linux_xfrm_mib {
 
 #define SNMP_ADD_STATS64_BH(mib, field, addend) 			\
 	do {								\
-		__typeof__(*mib) *ptr = __this_cpu_ptr(mib);		\
+		__typeof__(*mib) *ptr = raw_cpu_ptr(mib);		\
 		u64_stats_update_begin(&ptr->syncp);			\
 		ptr->mibs[field] += addend;				\
 		u64_stats_update_end(&ptr->syncp);			\
@@ -189,8 +189,8 @@ struct linux_xfrm_mib {
 #define SNMP_INC_STATS64(mib, field) SNMP_ADD_STATS64(mib, field, 1)
 #define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend)			\
 	do {								\
-		__typeof__(*mib) *ptr;					\
-		ptr = __this_cpu_ptr(mib);				\
+		__typeof__(*mib) *ptr;				\
+		ptr = raw_cpu_ptr((mib));				\
 		u64_stats_update_begin(&ptr->syncp);			\
 		ptr->mibs[basefield##PKTS]++;				\
 		ptr->mibs[basefield##OCTETS] += addend;			\
diff --git a/net/core/dev.c b/net/core/dev.c
index b65a5051361f..9ef13ff354fe 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2153,7 +2153,7 @@ static inline void __netif_reschedule(struct Qdisc *q)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	sd = &__get_cpu_var(softnet_data);
+	sd = this_cpu_ptr(&softnet_data);
 	q->next_sched = NULL;
 	*sd->output_queue_tailp = q;
 	sd->output_queue_tailp = &q->next_sched;
@@ -3195,7 +3195,7 @@ static void rps_trigger_softirq(void *data)
 static int rps_ipi_queued(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-	struct softnet_data *mysd = &__get_cpu_var(softnet_data);
+	struct softnet_data *mysd = this_cpu_ptr(&softnet_data);
 
 	if (sd != mysd) {
 		sd->rps_ipi_next = mysd->rps_ipi_list;
@@ -3222,7 +3222,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 	if (qlen < (netdev_max_backlog >> 1))
 		return false;
 
-	sd = &__get_cpu_var(softnet_data);
+	sd = this_cpu_ptr(&softnet_data);
 
 	rcu_read_lock();
 	fl = rcu_dereference(sd->flow_limit);
@@ -3369,7 +3369,7 @@ EXPORT_SYMBOL(netif_rx_ni);
 
 static void net_tx_action(struct softirq_action *h)
 {
-	struct softnet_data *sd = &__get_cpu_var(softnet_data);
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 
 	if (sd->completion_queue) {
 		struct sk_buff *clist;
@@ -3794,7 +3794,7 @@ EXPORT_SYMBOL(netif_receive_skb);
 static void flush_backlog(void *arg)
 {
 	struct net_device *dev = arg;
-	struct softnet_data *sd = &__get_cpu_var(softnet_data);
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	struct sk_buff *skb, *tmp;
 
 	rps_lock(sd);
@@ -4301,7 +4301,7 @@ void __napi_schedule(struct napi_struct *n)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	____napi_schedule(&__get_cpu_var(softnet_data), n);
+	____napi_schedule(this_cpu_ptr(&softnet_data), n);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(__napi_schedule);
@@ -4422,7 +4422,7 @@ EXPORT_SYMBOL(netif_napi_del);
 
 static void net_rx_action(struct softirq_action *h)
 {
-	struct softnet_data *sd = &__get_cpu_var(softnet_data);
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	unsigned long time_limit = jiffies + 2;
 	int budget = netdev_budget;
 	void *have;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 50f9a9db5792..252e155c837b 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -146,7 +146,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	data = &__get_cpu_var(dm_cpu_data);
+	data = this_cpu_ptr(&dm_cpu_data);
 	spin_lock(&data->lock);
 	dskb = data->skb;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 163b673f9e62..adfc7ee1acf2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -345,7 +345,7 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	nc = &__get_cpu_var(netdev_alloc_cache);
+	nc = this_cpu_ptr(&netdev_alloc_cache);
 	if (unlikely(!nc->frag.page)) {
 refill:
 		for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index eaa4b000c7b4..7d6f4e021846 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1311,7 +1311,7 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	if (rt_is_input_route(rt)) {
 		p = (struct rtable **)&nh->nh_rth_input;
 	} else {
-		p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
+		p = (struct rtable **)raw_cpu_ptr(nh->nh_pcpu_rth_output);
 	}
 	orig = *p;
 
@@ -1939,7 +1939,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 				do_cache = false;
 				goto add;
 			}
-			prth = __this_cpu_ptr(nh->nh_pcpu_rth_output);
+			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
 		rth = rcu_dereference(*prth);
 		if (rt_cache_valid(rth)) {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index c0c75688896e..f83391bfdd76 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -40,7 +40,7 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 
 	net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
 
-	tmp  = __get_cpu_var(ipv4_cookie_scratch);
+	tmp  = this_cpu_ptr(ipv4_cookie_scratch);
 	memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c]));
 	tmp[0] = (__force u32)saddr;
 	tmp[1] = (__force u32)daddr;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 541f26a67ba2..b2cab7770a11 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3058,7 +3058,7 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 	local_bh_disable();
 	p = ACCESS_ONCE(tcp_md5sig_pool);
 	if (p)
-		return __this_cpu_ptr(p);
+		return raw_cpu_ptr(p);
 
 	local_bh_enable();
 	return NULL;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5a7c41fbc6d3..d145f7ef78f3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -842,7 +842,7 @@ void tcp_wfree(struct sk_buff *skb)
 
 		/* queue this socket to tasklet queue */
 		local_irq_save(flags);
-		tsq = &__get_cpu_var(tsq_tasklet);
+		tsq = this_cpu_ptr(&tsq_tasklet);
 		list_add(&tp->tsq_node, &tsq->head);
 		tasklet_schedule(&tsq->tasklet);
 		local_irq_restore(flags);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 83cea1d39466..637de5b87589 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -67,7 +67,7 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd
 
 	net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
 
-	tmp  = __get_cpu_var(ipv6_cookie_scratch);
+	tmp  = this_cpu_ptr(ipv6_cookie_scratch);
 
 	/*
 	 * we have 320 bits of information to hash, copy in the remaining
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index e8fdb172adbb..273b8bff6ba4 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -267,7 +267,7 @@ static inline struct rds_ib_mr *rds_ib_reuse_fmr(struct rds_ib_mr_pool *pool)
 	unsigned long *flag;
 
 	preempt_disable();
-	flag = &__get_cpu_var(clean_list_grace);
+	flag = this_cpu_ptr(&clean_list_grace);
 	set_bit(CLEAN_LIST_BUSY_BIT, flag);
 	ret = llist_del_first(&pool->clean_list);
 	if (ret)
-- 
cgit v1.2.3


From 47405a253da4d8ca4b18ad537423083fdd790440 Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Sun, 17 Aug 2014 12:30:56 -0500
Subject: percpu: Remove __this_cpu_ptr

The __this_cpu_ptr macro is no longer in use so drop it.

Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/percpu-defs.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index cfd56046ecec..420032d41d27 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -257,9 +257,6 @@ do {									\
 #define __raw_get_cpu_var(var)	(*raw_cpu_ptr(&(var)))
 #define __get_cpu_var(var)	(*this_cpu_ptr(&(var)))
 
-/* keep until we have removed all uses of __this_cpu_ptr */
-#define __this_cpu_ptr(ptr)	raw_cpu_ptr(ptr)
-
 /*
  * Must be an lvalue. Since @var must be a simple identifier,
  * we force a syntax error here if it isn't.
-- 
cgit v1.2.3


From f111f780ae1abf4cdc464f24293be90c010a04f6 Mon Sep 17 00:00:00 2001
From: Alexey Perevalov <a.perevalov@samsung.com>
Date: Wed, 20 Aug 2014 22:03:18 +0400
Subject: netfilter: nfnetlink_acct: add filter support to nfacct counter
 list/reset

You can use this to skip accounting objects when listing/resetting
via NFNL_MSG_ACCT_GET/NFNL_MSG_ACCT_GET_CTRZERO messages with the
NLM_F_DUMP netlink flag. The filtering covers the following cases:

1. No filter specified. In this case, the client will get old behaviour,
2. List/reset counter object only: In this case, you have to use
   NFACCT_F_QUOTA as mask and value 0.
3. List/reset quota objects only: You have to use NFACCT_F_QUOTA_PKTS
   as mask and value - the same, for byte based quota mask should be
   NFACCT_F_QUOTA_BYTES and value - the same.

If you want to obtain the object with any quota type
(ie. NFACCT_F_QUOTA_PKTS|NFACCT_F_QUOTA_BYTES), you need to perform
two dump requests, one to obtain NFACCT_F_QUOTA_PKTS objects and
another for NFACCT_F_QUOTA_BYTES.

Signed-off-by: Alexey Perevalov <a.perevalov@samsung.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nfnetlink_acct.h |  8 ++++
 net/netfilter/nfnetlink_acct.c                | 54 +++++++++++++++++++++++++++
 2 files changed, 62 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nfnetlink_acct.h b/include/uapi/linux/netfilter/nfnetlink_acct.h
index 51404ec19022..f3e34dbbf966 100644
--- a/include/uapi/linux/netfilter/nfnetlink_acct.h
+++ b/include/uapi/linux/netfilter/nfnetlink_acct.h
@@ -28,9 +28,17 @@ enum nfnl_acct_type {
 	NFACCT_USE,
 	NFACCT_FLAGS,
 	NFACCT_QUOTA,
+	NFACCT_FILTER,
 	__NFACCT_MAX
 };
 #define NFACCT_MAX (__NFACCT_MAX - 1)
 
+enum nfnl_attr_filter_type {
+	NFACCT_FILTER_UNSPEC,
+	NFACCT_FILTER_MASK,
+	NFACCT_FILTER_VALUE,
+	__NFACCT_FILTER_MAX
+};
+#define NFACCT_FILTER_MAX (__NFACCT_FILTER_MAX - 1)
 
 #endif /* _UAPI_NFNL_ACCT_H_ */
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 3ea0eacbd970..c18af2f63eef 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -40,6 +40,11 @@ struct nf_acct {
 	char			data[0];
 };
 
+struct nfacct_filter {
+	u32 value;
+	u32 mask;
+};
+
 #define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES)
 #define NFACCT_OVERQUOTA_BIT	2	/* NFACCT_F_OVERQUOTA */
 
@@ -181,6 +186,7 @@ static int
 nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct nf_acct *cur, *last;
+	const struct nfacct_filter *filter = cb->data;
 
 	if (cb->args[2])
 		return 0;
@@ -197,6 +203,10 @@ nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 			last = NULL;
 		}
+
+		if (filter && (cur->flags & filter->mask) != filter->value)
+			continue;
+
 		if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).portid,
 				       cb->nlh->nlmsg_seq,
 				       NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
@@ -211,6 +221,38 @@ nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+static int nfnl_acct_done(struct netlink_callback *cb)
+{
+	kfree(cb->data);
+	return 0;
+}
+
+static const struct nla_policy filter_policy[NFACCT_FILTER_MAX + 1] = {
+	[NFACCT_FILTER_MASK]	= { .type = NLA_U32 },
+	[NFACCT_FILTER_VALUE]	= { .type = NLA_U32 },
+};
+
+static struct nfacct_filter *
+nfacct_filter_alloc(const struct nlattr * const attr)
+{
+	struct nfacct_filter *filter;
+	struct nlattr *tb[NFACCT_FILTER_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, NFACCT_FILTER_MAX, attr, filter_policy);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	filter = kzalloc(sizeof(struct nfacct_filter), GFP_KERNEL);
+	if (!filter)
+		return ERR_PTR(-ENOMEM);
+
+	filter->mask = ntohl(nla_get_be32(tb[NFACCT_FILTER_MASK]));
+	filter->value = ntohl(nla_get_be32(tb[NFACCT_FILTER_VALUE]));
+
+	return filter;
+}
+
 static int
 nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb,
 	     const struct nlmsghdr *nlh, const struct nlattr * const tb[])
@@ -222,7 +264,18 @@ nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb,
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
 			.dump = nfnl_acct_dump,
+			.done = nfnl_acct_done,
 		};
+
+		if (tb[NFACCT_FILTER]) {
+			struct nfacct_filter *filter;
+
+			filter = nfacct_filter_alloc(tb[NFACCT_FILTER]);
+			if (IS_ERR(filter))
+				return PTR_ERR(filter);
+
+			c.data = filter;
+		}
 		return netlink_dump_start(nfnl, skb, nlh, &c);
 	}
 
@@ -314,6 +367,7 @@ static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = {
 	[NFACCT_PKTS] = { .type = NLA_U64 },
 	[NFACCT_FLAGS] = { .type = NLA_U32 },
 	[NFACCT_QUOTA] = { .type = NLA_U64 },
+	[NFACCT_FILTER] = {.type = NLA_NESTED },
 };
 
 static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = {
-- 
cgit v1.2.3


From 8dece35daf098e5d086b50724119ffbb24ceca7f Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <m.chehab@samsung.com>
Date: Fri, 22 Aug 2014 07:00:42 -0500
Subject: [media] dm644x_ccdc: use unsigned long for fpc_table_addr

The fpc_table_addr is used as an unsigned integer that stores
an address. At the Kernel, the proper type for such integers
is unsigned long.

This generates lots of warnings when compiling on 64 bits.

Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/platform/davinci/dm644x_ccdc.c | 4 ++--
 include/media/davinci/dm644x_ccdc.h          | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/davinci/dm644x_ccdc.c b/drivers/media/platform/davinci/dm644x_ccdc.c
index b0b9cd54e9e9..62a0ebb01056 100644
--- a/drivers/media/platform/davinci/dm644x_ccdc.c
+++ b/drivers/media/platform/davinci/dm644x_ccdc.c
@@ -291,7 +291,7 @@ static int ccdc_update_raw_params(struct ccdc_config_params_raw *raw_params)
 		dev_dbg(ccdc_cfg.dev, "\n copy_from_user failed");
 		return -EFAULT;
 	}
-	config_params->fault_pxl.fpc_table_addr = (unsigned int)fpc_physaddr;
+	config_params->fault_pxl.fpc_table_addr = (unsigned long)fpc_physaddr;
 	return 0;
 }
 
@@ -506,7 +506,7 @@ static void ccdc_config_fpc(struct ccdc_fault_pixel *fpc)
 
 	/* Configure Fault pixel if needed */
 	regw(fpc->fpc_table_addr, CCDC_FPC_ADDR);
-	dev_dbg(ccdc_cfg.dev, "\nWriting 0x%x to FPC_ADDR...\n",
+	dev_dbg(ccdc_cfg.dev, "\nWriting 0x%lx to FPC_ADDR...\n",
 		       (fpc->fpc_table_addr));
 	/* Write the FPC params with FPC disable */
 	val = fpc->fp_num & CCDC_FPC_FPC_NUM_MASK;
diff --git a/include/media/davinci/dm644x_ccdc.h b/include/media/davinci/dm644x_ccdc.h
index 852e96c4bb46..984fb79031de 100644
--- a/include/media/davinci/dm644x_ccdc.h
+++ b/include/media/davinci/dm644x_ccdc.h
@@ -114,7 +114,7 @@ struct ccdc_fault_pixel {
 	/* Number of fault pixel */
 	unsigned short fp_num;
 	/* Address of fault pixel table */
-	unsigned int fpc_table_addr;
+	unsigned long fpc_table_addr;
 };
 
 /* Structure for CCDC configuration parameters for raw capture mode passed
-- 
cgit v1.2.3


From bf3baca6c54ce8a2f51687296f868dfe20d33f13 Mon Sep 17 00:00:00 2001
From: James Ban <james.ban.opensource@diasemi.com>
Date: Wed, 27 Aug 2014 11:47:07 +0900
Subject: regulator: da9211: support device tree

This is a patch for supporting device tree of DA9211/DA9213.

Signed-off-by: James Ban <james.ban.opensource@diasemi.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 .../devicetree/bindings/regulator/da9211.txt       | 63 ++++++++++++++++
 drivers/regulator/da9211-regulator.c               | 85 ++++++++++++++++++++--
 include/linux/regulator/da9211.h                   |  2 +-
 3 files changed, 142 insertions(+), 8 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/regulator/da9211.txt

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/regulator/da9211.txt b/Documentation/devicetree/bindings/regulator/da9211.txt
new file mode 100644
index 000000000000..240019a82f9a
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/da9211.txt
@@ -0,0 +1,63 @@
+* Dialog Semiconductor DA9211/DA9213 Voltage Regulator
+
+Required properties:
+- compatible: "dlg,da9211" or "dlg,da9213".
+- reg: I2C slave address, usually 0x68.
+- interrupts: the interrupt outputs of the controller
+- regulators: A node that houses a sub-node for each regulator within the
+  device. Each sub-node is identified using the node's name, with valid
+  values listed below. The content of each sub-node is defined by the
+  standard binding for regulators; see regulator.txt.
+  BUCKA and BUCKB.
+
+Optional properties:
+- Any optional property defined in regulator.txt
+
+Example 1) DA9211
+
+	pmic: da9211@68 {
+		compatible = "dlg,da9211";
+		reg = <0x68>;
+		interrupts = <3 27>;
+
+		regulators {
+			BUCKA {
+				regulator-name = "VBUCKA";
+				regulator-min-microvolt = < 300000>;
+				regulator-max-microvolt = <1570000>;
+				regulator-min-microamp 	= <2000000>;
+				regulator-max-microamp 	= <5000000>;
+			};
+			BUCKB {
+				regulator-name = "VBUCKB";
+				regulator-min-microvolt = < 300000>;
+				regulator-max-microvolt = <1570000>;
+				regulator-min-microamp 	= <2000000>;
+				regulator-max-microamp 	= <5000000>;
+			};
+		};
+	};
+
+Example 2) DA92113
+	pmic: da9213@68 {
+		compatible = "dlg,da9213";
+		reg = <0x68>;
+		interrupts = <3 27>;
+
+		regulators {
+			BUCKA {
+				regulator-name = "VBUCKA";
+				regulator-min-microvolt = < 300000>;
+				regulator-max-microvolt = <1570000>;
+				regulator-min-microamp 	= <3000000>;
+				regulator-max-microamp 	= <6000000>;
+			};
+			BUCKB {
+				regulator-name = "VBUCKB";
+				regulator-min-microvolt = < 300000>;
+				regulator-max-microvolt = <1570000>;
+				regulator-min-microamp 	= <3000000>;
+				regulator-max-microamp 	= <6000000>;
+			};
+		};
+	};
diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c
index a26f1d283c57..5aabbac1b524 100644
--- a/drivers/regulator/da9211-regulator.c
+++ b/drivers/regulator/da9211-regulator.c
@@ -24,6 +24,7 @@
 #include <linux/regmap.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
+#include <linux/regulator/of_regulator.h>
 #include <linux/regulator/da9211.h>
 #include "da9211-regulator.h"
 
@@ -236,6 +237,59 @@ static struct regulator_desc da9211_regulators[] = {
 	DA9211_BUCK(BUCKB),
 };
 
+#ifdef CONFIG_OF
+static struct of_regulator_match da9211_matches[] = {
+	[DA9211_ID_BUCKA] = { .name = "BUCKA" },
+	[DA9211_ID_BUCKB] = { .name = "BUCKB" },
+	};
+
+static struct da9211_pdata *da9211_parse_regulators_dt(
+		struct device *dev)
+{
+	struct da9211_pdata *pdata;
+	struct device_node *node;
+	int i, num, n;
+
+	node = of_get_child_by_name(dev->of_node, "regulators");
+	if (!node) {
+		dev_err(dev, "regulators node not found\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	num = of_regulator_match(dev, node, da9211_matches,
+				 ARRAY_SIZE(da9211_matches));
+	of_node_put(node);
+	if (num < 0) {
+		dev_err(dev, "Failed to match regulators\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	pdata->num_buck = num;
+
+	n = 0;
+	for (i = 0; i < ARRAY_SIZE(da9211_matches); i++) {
+		if (!da9211_matches[i].init_data)
+			continue;
+
+		pdata->init_data[n] = da9211_matches[i].init_data;
+
+		n++;
+	};
+
+	return pdata;
+}
+#else
+static struct da9211_pdata *da9211_parse_regulators_dt(
+		struct device *dev)
+{
+	return ERR_PTR(-ENODEV);
+}
+#endif
+
 static irqreturn_t da9211_irq_handler(int irq, void *data)
 {
 	struct da9211 *chip = data;
@@ -306,7 +360,7 @@ static int da9211_regulator_init(struct da9211 *chip)
 	}
 
 	for (i = 0; i < chip->num_regulator; i++) {
-		config.init_data = &(chip->pdata->init_data[i]);
+		config.init_data = chip->pdata->init_data[i];
 		config.dev = chip->dev;
 		config.driver_data = chip;
 		config.regmap = chip->regmap;
@@ -332,6 +386,21 @@ static int da9211_regulator_init(struct da9211 *chip)
 
 	return 0;
 }
+
+static const struct i2c_device_id da9211_i2c_id[] = {
+	{"da9211", DA9211},
+	{"da9213", DA9213},
+	{},
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id da9211_dt_ids[] = {
+	{ .compatible = "dlg,da9211", .data = &da9211_i2c_id[0] },
+	{ .compatible = "dlg,da9213", .data = &da9211_i2c_id[1] },
+	{},
+};
+#endif
+
 /*
  * I2C driver interface functions
  */
@@ -377,6 +446,14 @@ static int da9211_i2c_probe(struct i2c_client *i2c,
 		return -ENODEV;
 	}
 
+	if (!chip->pdata)
+		chip->pdata = da9211_parse_regulators_dt(chip->dev);
+
+	if (IS_ERR(chip->pdata)) {
+		dev_err(chip->dev, "No regulators defined for the platform\n");
+		return PTR_ERR(chip->pdata);
+	}
+
 	chip->chip_irq = i2c->irq;
 
 	if (chip->chip_irq != 0) {
@@ -401,12 +478,6 @@ static int da9211_i2c_probe(struct i2c_client *i2c,
 	return ret;
 }
 
-static const struct i2c_device_id da9211_i2c_id[] = {
-	{"da9211", DA9211},
-	{"da9213", DA9213},
-	{},
-};
-
 MODULE_DEVICE_TABLE(i2c, da9211_i2c_id);
 
 static struct i2c_driver da9211_regulator_driver = {
diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h
index 658c3c33f4c0..5479394fefce 100644
--- a/include/linux/regulator/da9211.h
+++ b/include/linux/regulator/da9211.h
@@ -32,6 +32,6 @@ struct da9211_pdata {
 	 * 2 : 2 phase 2 buck
 	 */
 	int num_buck;
-	struct regulator_init_data *init_data;
+	struct regulator_init_data *init_data[DA9211_MAX_REGULATORS];
 };
 #endif
-- 
cgit v1.2.3


From f1217ed09f827e42a49ffa6a5aab672aa6f57a65 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 27 Aug 2014 13:16:04 +0200
Subject: drm/ttm: move fpfn and lpfn into each placement v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This allows us to more fine grained specify where to place the buffer object.

v2: rebased on drm-next, add bochs changes as well

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ast/ast_drv.h                 |   2 +-
 drivers/gpu/drm/ast/ast_ttm.c                 |  20 ++--
 drivers/gpu/drm/bochs/bochs.h                 |   2 +-
 drivers/gpu/drm/bochs/bochs_mm.c              |  20 ++--
 drivers/gpu/drm/cirrus/cirrus_drv.h           |   2 +-
 drivers/gpu/drm/cirrus/cirrus_ttm.c           |  17 ++--
 drivers/gpu/drm/mgag200/mgag200_drv.h         |   2 +-
 drivers/gpu/drm/mgag200/mgag200_ttm.c         |  20 ++--
 drivers/gpu/drm/nouveau/nouveau_bo.c          |  52 +++++++---
 drivers/gpu/drm/nouveau/nouveau_bo.h          |   4 +-
 drivers/gpu/drm/nouveau/nouveau_ttm.c         |   9 +-
 drivers/gpu/drm/qxl/qxl_drv.h                 |   2 +-
 drivers/gpu/drm/qxl/qxl_object.c              |  17 ++--
 drivers/gpu/drm/qxl/qxl_ttm.c                 |   8 +-
 drivers/gpu/drm/radeon/radeon.h               |   2 +-
 drivers/gpu/drm/radeon/radeon_object.c        |  71 +++++++++-----
 drivers/gpu/drm/radeon/radeon_ttm.c           |  25 ++---
 drivers/gpu/drm/radeon/radeon_uvd.c           |   8 +-
 drivers/gpu/drm/ttm/ttm_bo.c                  |  93 ++++++++----------
 drivers/gpu/drm/ttm/ttm_bo_manager.c          |   9 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c        | 136 ++++++++++++++++----------
 drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c        |  22 +++--
 drivers/gpu/drm/vmwgfx/vmwgfx_fb.c            |  10 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c |   3 +-
 include/drm/ttm/ttm_bo_api.h                  |  40 ++++----
 include/drm/ttm/ttm_bo_driver.h               |   3 +-
 26 files changed, 346 insertions(+), 253 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 957d4fabf1e1..cb91c2acc3cb 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -316,7 +316,7 @@ struct ast_bo {
 	struct ttm_placement placement;
 	struct ttm_bo_kmap_obj kmap;
 	struct drm_gem_object gem;
-	u32 placements[3];
+	struct ttm_place placements[3];
 	int pin_count;
 };
 #define gem_to_ast_bo(gobj) container_of((gobj), struct ast_bo, gem)
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index b8246227bab0..8008ea0bc76c 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -293,18 +293,22 @@ void ast_mm_fini(struct ast_private *ast)
 void ast_ttm_placement(struct ast_bo *bo, int domain)
 {
 	u32 c = 0;
-	bo->placement.fpfn = 0;
-	bo->placement.lpfn = 0;
+	unsigned i;
+
 	bo->placement.placement = bo->placements;
 	bo->placement.busy_placement = bo->placements;
 	if (domain & TTM_PL_FLAG_VRAM)
-		bo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
+		bo->placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
 	if (domain & TTM_PL_FLAG_SYSTEM)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	if (!c)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	bo->placement.num_placement = c;
 	bo->placement.num_busy_placement = c;
+	for (i = 0; i < c; ++i) {
+		bo->placements[i].fpfn = 0;
+		bo->placements[i].lpfn = 0;
+	}
 }
 
 int ast_bo_create(struct drm_device *dev, int size, int align,
@@ -360,7 +364,7 @@ int ast_bo_pin(struct ast_bo *bo, u32 pl_flag, u64 *gpu_addr)
 
 	ast_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -383,7 +387,7 @@ int ast_bo_unpin(struct ast_bo *bo)
 		return 0;
 
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -407,7 +411,7 @@ int ast_bo_push_sysram(struct ast_bo *bo)
 
 	ast_ttm_placement(bo, TTM_PL_FLAG_SYSTEM);
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret) {
diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h
index 7eb52dd44b01..4f6e7b3a3635 100644
--- a/drivers/gpu/drm/bochs/bochs.h
+++ b/drivers/gpu/drm/bochs/bochs.h
@@ -99,7 +99,7 @@ struct bochs_bo {
 	struct ttm_placement placement;
 	struct ttm_bo_kmap_obj kmap;
 	struct drm_gem_object gem;
-	u32 placements[3];
+	struct ttm_place placements[3];
 	int pin_count;
 };
 
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
index 1728a1b0b813..2af30e7607d7 100644
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ b/drivers/gpu/drm/bochs/bochs_mm.c
@@ -257,20 +257,26 @@ void bochs_mm_fini(struct bochs_device *bochs)
 
 static void bochs_ttm_placement(struct bochs_bo *bo, int domain)
 {
+	unsigned i;
 	u32 c = 0;
-	bo->placement.fpfn = 0;
-	bo->placement.lpfn = 0;
 	bo->placement.placement = bo->placements;
 	bo->placement.busy_placement = bo->placements;
 	if (domain & TTM_PL_FLAG_VRAM) {
-		bo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED
+		bo->placements[c++].flags = TTM_PL_FLAG_WC
+			| TTM_PL_FLAG_UNCACHED
 			| TTM_PL_FLAG_VRAM;
 	}
 	if (domain & TTM_PL_FLAG_SYSTEM) {
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING
+			| TTM_PL_FLAG_SYSTEM;
 	}
 	if (!c) {
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING
+			| TTM_PL_FLAG_SYSTEM;
+	}
+	for (i = 0; i < c; ++i) {
+		bo->placements[i].fpfn = 0;
+		bo->placements[i].lpfn = 0;
 	}
 	bo->placement.num_placement = c;
 	bo->placement.num_busy_placement = c;
@@ -294,7 +300,7 @@ int bochs_bo_pin(struct bochs_bo *bo, u32 pl_flag, u64 *gpu_addr)
 
 	bochs_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -319,7 +325,7 @@ int bochs_bo_unpin(struct bochs_bo *bo)
 		return 0;
 
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index 401c890b6c6a..dd2cfc9024aa 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -163,7 +163,7 @@ struct cirrus_bo {
 	struct ttm_placement placement;
 	struct ttm_bo_kmap_obj kmap;
 	struct drm_gem_object gem;
-	u32 placements[3];
+	struct ttm_place placements[3];
 	int pin_count;
 };
 #define gem_to_cirrus_bo(gobj) container_of((gobj), struct cirrus_bo, gem)
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 92e6b7786097..3e7d758330a9 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -298,18 +298,21 @@ void cirrus_mm_fini(struct cirrus_device *cirrus)
 void cirrus_ttm_placement(struct cirrus_bo *bo, int domain)
 {
 	u32 c = 0;
-	bo->placement.fpfn = 0;
-	bo->placement.lpfn = 0;
+	unsigned i;
 	bo->placement.placement = bo->placements;
 	bo->placement.busy_placement = bo->placements;
 	if (domain & TTM_PL_FLAG_VRAM)
-		bo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
+		bo->placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
 	if (domain & TTM_PL_FLAG_SYSTEM)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	if (!c)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	bo->placement.num_placement = c;
 	bo->placement.num_busy_placement = c;
+	for (i = 0; i < c; ++i) {
+		bo->placements[i].fpfn = 0;
+		bo->placements[i].lpfn = 0;
+	}
 }
 
 int cirrus_bo_create(struct drm_device *dev, int size, int align,
@@ -365,7 +368,7 @@ int cirrus_bo_pin(struct cirrus_bo *bo, u32 pl_flag, u64 *gpu_addr)
 
 	cirrus_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -392,7 +395,7 @@ int cirrus_bo_push_sysram(struct cirrus_bo *bo)
 
 	cirrus_ttm_placement(bo, TTM_PL_FLAG_SYSTEM);
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret) {
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 80de23d9b9c9..2e2b76aa4e17 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -224,7 +224,7 @@ struct mgag200_bo {
 	struct ttm_placement placement;
 	struct ttm_bo_kmap_obj kmap;
 	struct drm_gem_object gem;
-	u32 placements[3];
+	struct ttm_place placements[3];
 	int pin_count;
 };
 #define gem_to_mga_bo(gobj) container_of((gobj), struct mgag200_bo, gem)
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 5a00e90696de..be883ef5a1d3 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -293,18 +293,22 @@ void mgag200_mm_fini(struct mga_device *mdev)
 void mgag200_ttm_placement(struct mgag200_bo *bo, int domain)
 {
 	u32 c = 0;
-	bo->placement.fpfn = 0;
-	bo->placement.lpfn = 0;
+	unsigned i;
+
 	bo->placement.placement = bo->placements;
 	bo->placement.busy_placement = bo->placements;
 	if (domain & TTM_PL_FLAG_VRAM)
-		bo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
+		bo->placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
 	if (domain & TTM_PL_FLAG_SYSTEM)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	if (!c)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	bo->placement.num_placement = c;
 	bo->placement.num_busy_placement = c;
+	for (i = 0; i < c; ++i) {
+		bo->placements[i].fpfn = 0;
+		bo->placements[i].lpfn = 0;
+	}
 }
 
 int mgag200_bo_create(struct drm_device *dev, int size, int align,
@@ -361,7 +365,7 @@ int mgag200_bo_pin(struct mgag200_bo *bo, u32 pl_flag, u64 *gpu_addr)
 
 	mgag200_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -384,7 +388,7 @@ int mgag200_bo_unpin(struct mgag200_bo *bo)
 		return 0;
 
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -408,7 +412,7 @@ int mgag200_bo_push_sysram(struct mgag200_bo *bo)
 
 	mgag200_ttm_placement(bo, TTM_PL_FLAG_SYSTEM);
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 01da508625f2..0591ca0734e3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -241,16 +241,16 @@ nouveau_bo_new(struct drm_device *dev, int size, int align,
 }
 
 static void
-set_placement_list(uint32_t *pl, unsigned *n, uint32_t type, uint32_t flags)
+set_placement_list(struct ttm_place *pl, unsigned *n, uint32_t type, uint32_t flags)
 {
 	*n = 0;
 
 	if (type & TTM_PL_FLAG_VRAM)
-		pl[(*n)++] = TTM_PL_FLAG_VRAM | flags;
+		pl[(*n)++].flags = TTM_PL_FLAG_VRAM | flags;
 	if (type & TTM_PL_FLAG_TT)
-		pl[(*n)++] = TTM_PL_FLAG_TT | flags;
+		pl[(*n)++].flags = TTM_PL_FLAG_TT | flags;
 	if (type & TTM_PL_FLAG_SYSTEM)
-		pl[(*n)++] = TTM_PL_FLAG_SYSTEM | flags;
+		pl[(*n)++].flags = TTM_PL_FLAG_SYSTEM | flags;
 }
 
 static void
@@ -258,6 +258,7 @@ set_placement_range(struct nouveau_bo *nvbo, uint32_t type)
 {
 	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
 	u32 vram_pages = drm->device.info.ram_size >> PAGE_SHIFT;
+	unsigned i, fpfn, lpfn;
 
 	if (drm->device.info.family == NV_DEVICE_INFO_V0_CELSIUS &&
 	    nvbo->tile_mode && (type & TTM_PL_FLAG_VRAM) &&
@@ -269,11 +270,19 @@ set_placement_range(struct nouveau_bo *nvbo, uint32_t type)
 		 * at the same time.
 		 */
 		if (nvbo->tile_flags & NOUVEAU_GEM_TILE_ZETA) {
-			nvbo->placement.fpfn = vram_pages / 2;
-			nvbo->placement.lpfn = ~0;
+			fpfn = vram_pages / 2;
+			lpfn = ~0;
 		} else {
-			nvbo->placement.fpfn = 0;
-			nvbo->placement.lpfn = vram_pages / 2;
+			fpfn = 0;
+			lpfn = vram_pages / 2;
+		}
+		for (i = 0; i < nvbo->placement.num_placement; ++i) {
+			nvbo->placements[i].fpfn = fpfn;
+			nvbo->placements[i].lpfn = lpfn;
+		}
+		for (i = 0; i < nvbo->placement.num_busy_placement; ++i) {
+			nvbo->busy_placements[i].fpfn = fpfn;
+			nvbo->busy_placements[i].lpfn = lpfn;
 		}
 	}
 }
@@ -1041,12 +1050,15 @@ static int
 nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 		      bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
-	u32 placement_memtype = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
+	struct ttm_place placement_memtype = {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING
+	};
 	struct ttm_placement placement;
 	struct ttm_mem_reg tmp_mem;
 	int ret;
 
-	placement.fpfn = placement.lpfn = 0;
 	placement.num_placement = placement.num_busy_placement = 1;
 	placement.placement = placement.busy_placement = &placement_memtype;
 
@@ -1074,12 +1086,15 @@ static int
 nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
 		      bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
-	u32 placement_memtype = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
+	struct ttm_place placement_memtype = {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING
+	};
 	struct ttm_placement placement;
 	struct ttm_mem_reg tmp_mem;
 	int ret;
 
-	placement.fpfn = placement.lpfn = 0;
 	placement.num_placement = placement.num_busy_placement = 1;
 	placement.placement = placement.busy_placement = &placement_memtype;
 
@@ -1294,7 +1309,7 @@ nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nvif_device *device = &drm->device;
 	u32 mappable = nv_device_resource_len(nvkm_device(device), 1) >> PAGE_SHIFT;
-	int ret;
+	int i, ret;
 
 	/* as long as the bo isn't in vram, and isn't tiled, we've got
 	 * nothing to do here.
@@ -1319,9 +1334,16 @@ nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
 	    bo->mem.start + bo->mem.num_pages < mappable)
 		return 0;
 
+	for (i = 0; i < nvbo->placement.num_placement; ++i) {
+		nvbo->placements[i].fpfn = 0;
+		nvbo->placements[i].lpfn = mappable;
+	}
+
+	for (i = 0; i < nvbo->placement.num_busy_placement; ++i) {
+		nvbo->busy_placements[i].fpfn = 0;
+		nvbo->busy_placements[i].lpfn = mappable;
+	}
 
-	nvbo->placement.fpfn = 0;
-	nvbo->placement.lpfn = mappable;
 	nouveau_bo_placement_set(nvbo, TTM_PL_FLAG_VRAM, 0);
 	return nouveau_bo_validate(nvbo, false, false);
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h
index ff17c1f432fc..4ef88e84a694 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.h
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.h
@@ -9,8 +9,8 @@ struct nouveau_bo {
 	struct ttm_buffer_object bo;
 	struct ttm_placement placement;
 	u32 valid_domains;
-	u32 placements[3];
-	u32 busy_placements[3];
+	struct ttm_place placements[3];
+	struct ttm_place busy_placements[3];
 	struct ttm_bo_kmap_obj kmap;
 	struct list_head head;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 53874b76b031..e81d086577ce 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -71,8 +71,7 @@ nouveau_vram_manager_del(struct ttm_mem_type_manager *man,
 static int
 nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
 			 struct ttm_buffer_object *bo,
-			 struct ttm_placement *placement,
-			 uint32_t flags,
+			 const struct ttm_place *place,
 			 struct ttm_mem_reg *mem)
 {
 	struct nouveau_drm *drm = nouveau_bdev(man->bdev);
@@ -158,8 +157,7 @@ nouveau_gart_manager_del(struct ttm_mem_type_manager *man,
 static int
 nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
 			 struct ttm_buffer_object *bo,
-			 struct ttm_placement *placement,
-			 uint32_t flags,
+			 const struct ttm_place *place,
 			 struct ttm_mem_reg *mem)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
@@ -239,8 +237,7 @@ nv04_gart_manager_del(struct ttm_mem_type_manager *man, struct ttm_mem_reg *mem)
 static int
 nv04_gart_manager_new(struct ttm_mem_type_manager *man,
 		      struct ttm_buffer_object *bo,
-		      struct ttm_placement *placement,
-		      uint32_t flags,
+		      const struct ttm_place *place,
 		      struct ttm_mem_reg *mem)
 {
 	struct nouveau_mem *node;
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 36ed40ba773f..f6022b703645 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -106,7 +106,7 @@ struct qxl_bo {
 	/* Protected by gem.mutex */
 	struct list_head		list;
 	/* Protected by tbo.reserved */
-	u32				placements[3];
+	struct ttm_place		placements[3];
 	struct ttm_placement		placement;
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index b95f144f0b49..adad12d30372 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -55,21 +55,24 @@ void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain, bool pinned)
 {
 	u32 c = 0;
 	u32 pflag = pinned ? TTM_PL_FLAG_NO_EVICT : 0;
+	unsigned i;
 
-	qbo->placement.fpfn = 0;
-	qbo->placement.lpfn = 0;
 	qbo->placement.placement = qbo->placements;
 	qbo->placement.busy_placement = qbo->placements;
 	if (domain == QXL_GEM_DOMAIN_VRAM)
-		qbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_VRAM | pflag;
+		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_VRAM | pflag;
 	if (domain == QXL_GEM_DOMAIN_SURFACE)
-		qbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_PRIV0 | pflag;
+		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_PRIV0 | pflag;
 	if (domain == QXL_GEM_DOMAIN_CPU)
-		qbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM | pflag;
+		qbo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM | pflag;
 	if (!c)
-		qbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		qbo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	qbo->placement.num_placement = c;
 	qbo->placement.num_busy_placement = c;
+	for (i = 0; i < c; ++i) {
+		qbo->placements[i].fpfn = 0;
+		qbo->placements[i].lpfn = 0;
+	}
 }
 
 
@@ -259,7 +262,7 @@ int qxl_bo_unpin(struct qxl_bo *bo)
 	if (bo->pin_count)
 		return 0;
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
 	if (unlikely(r != 0))
 		dev_err(qdev->dev, "%p validate failed for unpin\n", bo);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 71a1baeac14e..f66c59b222f1 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -188,11 +188,13 @@ static void qxl_evict_flags(struct ttm_buffer_object *bo,
 				struct ttm_placement *placement)
 {
 	struct qxl_bo *qbo;
-	static u32 placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+	static struct ttm_place placements = {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM
+	};
 
 	if (!qxl_ttm_bo_is_qxl_bo(bo)) {
-		placement->fpfn = 0;
-		placement->lpfn = 0;
 		placement->placement = &placements;
 		placement->busy_placement = &placements;
 		placement->num_placement = 1;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b321ad4dcafd..bb01dab513dd 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -469,7 +469,7 @@ struct radeon_bo {
 	struct list_head		list;
 	/* Protected by tbo.reserved */
 	u32				initial_domain;
-	u32				placements[3];
+	struct ttm_place		placements[3];
 	struct ttm_placement		placement;
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 287523807989..0129c7efae3b 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -97,40 +97,56 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 {
 	u32 c = 0, i;
 
-	rbo->placement.fpfn = 0;
-	rbo->placement.lpfn = 0;
 	rbo->placement.placement = rbo->placements;
 	rbo->placement.busy_placement = rbo->placements;
 	if (domain & RADEON_GEM_DOMAIN_VRAM)
-		rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
-					TTM_PL_FLAG_VRAM;
+		rbo->placements[c++].flags = TTM_PL_FLAG_WC |
+					     TTM_PL_FLAG_UNCACHED |
+					     TTM_PL_FLAG_VRAM;
+
 	if (domain & RADEON_GEM_DOMAIN_GTT) {
 		if (rbo->flags & RADEON_GEM_GTT_UC) {
-			rbo->placements[c++] = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_TT;
+			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED |
+				TTM_PL_FLAG_TT;
+
 		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
 			   (rbo->rdev->flags & RADEON_IS_AGP)) {
-			rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
+			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
+				TTM_PL_FLAG_UNCACHED |
 				TTM_PL_FLAG_TT;
 		} else {
-			rbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_TT;
+			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED |
+						     TTM_PL_FLAG_TT;
 		}
 	}
+
 	if (domain & RADEON_GEM_DOMAIN_CPU) {
 		if (rbo->flags & RADEON_GEM_GTT_UC) {
-			rbo->placements[c++] = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_SYSTEM;
+			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED |
+				TTM_PL_FLAG_SYSTEM;
+
 		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
 		    rbo->rdev->flags & RADEON_IS_AGP) {
-			rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
+			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
+				TTM_PL_FLAG_UNCACHED |
 				TTM_PL_FLAG_SYSTEM;
 		} else {
-			rbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM;
+			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED |
+						     TTM_PL_FLAG_SYSTEM;
 		}
 	}
 	if (!c)
-		rbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		rbo->placements[c++].flags = TTM_PL_MASK_CACHING |
+					     TTM_PL_FLAG_SYSTEM;
+
 	rbo->placement.num_placement = c;
 	rbo->placement.num_busy_placement = c;
 
+	for (i = 0; i < c; ++i) {
+		rbo->placements[i].fpfn = 0;
+		rbo->placements[i].lpfn = 0;
+	}
+
 	/*
 	 * Use two-ended allocation depending on the buffer size to
 	 * improve fragmentation quality.
@@ -138,7 +154,7 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 	 */
 	if (rbo->tbo.mem.size > 512 * 1024) {
 		for (i = 0; i < c; i++) {
-			rbo->placements[i] |= TTM_PL_FLAG_TOPDOWN;
+			rbo->placements[i].flags |= TTM_PL_FLAG_TOPDOWN;
 		}
 	}
 }
@@ -287,21 +303,22 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 		return 0;
 	}
 	radeon_ttm_placement_from_domain(bo, domain);
-	if (domain == RADEON_GEM_DOMAIN_VRAM) {
+	for (i = 0; i < bo->placement.num_placement; i++) {
+		unsigned lpfn = 0;
+
 		/* force to pin into visible video ram */
-		bo->placement.lpfn = bo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
-	}
-	if (max_offset) {
-		u64 lpfn = max_offset >> PAGE_SHIFT;
+		if (bo->placements[i].flags & TTM_PL_FLAG_VRAM)
+			lpfn = bo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
+		else
+			lpfn = bo->rdev->mc.gtt_size >> PAGE_SHIFT; /* ??? */
 
-		if (!bo->placement.lpfn)
-			bo->placement.lpfn = bo->rdev->mc.gtt_size >> PAGE_SHIFT;
+		if (max_offset)
+			lpfn = min (lpfn, (unsigned)(max_offset >> PAGE_SHIFT));
 
-		if (lpfn < bo->placement.lpfn)
-			bo->placement.lpfn = lpfn;
+		bo->placements[i].lpfn = lpfn;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	}
-	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
 	if (likely(r == 0)) {
 		bo->pin_count = 1;
@@ -333,8 +350,10 @@ int radeon_bo_unpin(struct radeon_bo *bo)
 	bo->pin_count--;
 	if (bo->pin_count)
 		return 0;
-	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+	for (i = 0; i < bo->placement.num_placement; i++) {
+		bo->placements[i].lpfn = 0;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
+	}
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
 	if (likely(r == 0)) {
 		if (bo->tbo.mem.mem_type == TTM_PL_VRAM)
@@ -735,7 +754,7 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 
 	/* hurrah the memory is not visible ! */
 	radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
-	rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
+	rbo->placements[0].lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
 	r = ttm_bo_validate(bo, &rbo->placement, false, false);
 	if (unlikely(r == -ENOMEM)) {
 		radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 12e37b1ddc40..822eb3630045 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -178,12 +178,15 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 static void radeon_evict_flags(struct ttm_buffer_object *bo,
 				struct ttm_placement *placement)
 {
+	static struct ttm_place placements = {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM
+	};
+
 	struct radeon_bo *rbo;
-	static u32 placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 
 	if (!radeon_ttm_bo_is_radeon_bo(bo)) {
-		placement->fpfn = 0;
-		placement->lpfn = 0;
 		placement->placement = &placements;
 		placement->busy_placement = &placements;
 		placement->num_placement = 1;
@@ -286,20 +289,20 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 	struct radeon_device *rdev;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg tmp_mem;
-	u32 placements;
+	struct ttm_place placements;
 	struct ttm_placement placement;
 	int r;
 
 	rdev = radeon_get_rdev(bo->bdev);
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
-	placement.fpfn = 0;
-	placement.lpfn = 0;
 	placement.num_placement = 1;
 	placement.placement = &placements;
 	placement.num_busy_placement = 1;
 	placement.busy_placement = &placements;
-	placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
+	placements.fpfn = 0;
+	placements.lpfn = 0;
+	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
 			     interruptible, no_wait_gpu);
 	if (unlikely(r)) {
@@ -334,19 +337,19 @@ static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg tmp_mem;
 	struct ttm_placement placement;
-	u32 placements;
+	struct ttm_place placements;
 	int r;
 
 	rdev = radeon_get_rdev(bo->bdev);
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
-	placement.fpfn = 0;
-	placement.lpfn = 0;
 	placement.num_placement = 1;
 	placement.placement = &placements;
 	placement.num_busy_placement = 1;
 	placement.busy_placement = &placements;
-	placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
+	placements.fpfn = 0;
+	placements.lpfn = 0;
+	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
 			     interruptible, no_wait_gpu);
 	if (unlikely(r)) {
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 341848a14376..25c8a1fd152c 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -233,8 +233,12 @@ int radeon_uvd_resume(struct radeon_device *rdev)
 
 void radeon_uvd_force_into_uvd_segment(struct radeon_bo *rbo)
 {
-	rbo->placement.fpfn = 0 >> PAGE_SHIFT;
-	rbo->placement.lpfn = (256 * 1024 * 1024) >> PAGE_SHIFT;
+	int i;
+
+	for (i = 0; i < rbo->placement.num_placement; ++i) {
+		rbo->placements[i].fpfn = 0 >> PAGE_SHIFT;
+		rbo->placements[i].lpfn = (256 * 1024 * 1024) >> PAGE_SHIFT;
+	}
 }
 
 void radeon_uvd_free_handles(struct radeon_device *rdev, struct drm_file *filp)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 3da89d5dab60..b992ec3c318a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -53,12 +53,13 @@ static struct attribute ttm_bo_count = {
 	.mode = S_IRUGO
 };
 
-static inline int ttm_mem_type_from_flags(uint32_t flags, uint32_t *mem_type)
+static inline int ttm_mem_type_from_place(const struct ttm_place *place,
+					  uint32_t *mem_type)
 {
 	int i;
 
 	for (i = 0; i <= TTM_PL_PRIV5; i++)
-		if (flags & (1 << i)) {
+		if (place->flags & (1 << i)) {
 			*mem_type = i;
 			return 0;
 		}
@@ -89,12 +90,12 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 	       bo, bo->mem.num_pages, bo->mem.size >> 10,
 	       bo->mem.size >> 20);
 	for (i = 0; i < placement->num_placement; i++) {
-		ret = ttm_mem_type_from_flags(placement->placement[i],
+		ret = ttm_mem_type_from_place(&placement->placement[i],
 						&mem_type);
 		if (ret)
 			return;
 		pr_err("  placement[%d]=0x%08X (%d)\n",
-		       i, placement->placement[i], mem_type);
+		       i, placement->placement[i].flags, mem_type);
 		ttm_mem_type_debug(bo->bdev, mem_type);
 	}
 }
@@ -685,8 +686,6 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	evict_mem.bus.io_reserved_vm = false;
 	evict_mem.bus.io_reserved_count = 0;
 
-	placement.fpfn = 0;
-	placement.lpfn = 0;
 	placement.num_placement = 0;
 	placement.num_busy_placement = 0;
 	bdev->driver->evict_flags(bo, &placement);
@@ -774,7 +773,7 @@ EXPORT_SYMBOL(ttm_bo_mem_put);
  */
 static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 					uint32_t mem_type,
-					struct ttm_placement *placement,
+					const struct ttm_place *place,
 					struct ttm_mem_reg *mem,
 					bool interruptible,
 					bool no_wait_gpu)
@@ -784,7 +783,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 	int ret;
 
 	do {
-		ret = (*man->func->get_node)(man, bo, placement, 0, mem);
+		ret = (*man->func->get_node)(man, bo, place, mem);
 		if (unlikely(ret != 0))
 			return ret;
 		if (mem->mm_node)
@@ -827,18 +826,18 @@ static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
 
 static bool ttm_bo_mt_compatible(struct ttm_mem_type_manager *man,
 				 uint32_t mem_type,
-				 uint32_t proposed_placement,
+				 const struct ttm_place *place,
 				 uint32_t *masked_placement)
 {
 	uint32_t cur_flags = ttm_bo_type_flags(mem_type);
 
-	if ((cur_flags & proposed_placement & TTM_PL_MASK_MEM) == 0)
+	if ((cur_flags & place->flags & TTM_PL_MASK_MEM) == 0)
 		return false;
 
-	if ((proposed_placement & man->available_caching) == 0)
+	if ((place->flags & man->available_caching) == 0)
 		return false;
 
-	cur_flags |= (proposed_placement & man->available_caching);
+	cur_flags |= (place->flags & man->available_caching);
 
 	*masked_placement = cur_flags;
 	return true;
@@ -869,15 +868,14 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 
 	mem->mm_node = NULL;
 	for (i = 0; i < placement->num_placement; ++i) {
-		ret = ttm_mem_type_from_flags(placement->placement[i],
-						&mem_type);
+		const struct ttm_place *place = &placement->placement[i];
+
+		ret = ttm_mem_type_from_place(place, &mem_type);
 		if (ret)
 			return ret;
 		man = &bdev->man[mem_type];
 
-		type_ok = ttm_bo_mt_compatible(man,
-						mem_type,
-						placement->placement[i],
+		type_ok = ttm_bo_mt_compatible(man, mem_type, place,
 						&cur_flags);
 
 		if (!type_ok)
@@ -889,7 +887,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		 * Use the access and other non-mapping-related flag bits from
 		 * the memory placement flags to the current flags
 		 */
-		ttm_flag_masked(&cur_flags, placement->placement[i],
+		ttm_flag_masked(&cur_flags, place->flags,
 				~TTM_PL_MASK_MEMTYPE);
 
 		if (mem_type == TTM_PL_SYSTEM)
@@ -897,8 +895,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 
 		if (man->has_type && man->use_type) {
 			type_found = true;
-			ret = (*man->func->get_node)(man, bo, placement,
-						     cur_flags, mem);
+			ret = (*man->func->get_node)(man, bo, place, mem);
 			if (unlikely(ret))
 				return ret;
 		}
@@ -916,17 +913,15 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		return -EINVAL;
 
 	for (i = 0; i < placement->num_busy_placement; ++i) {
-		ret = ttm_mem_type_from_flags(placement->busy_placement[i],
-						&mem_type);
+		const struct ttm_place *place = &placement->busy_placement[i];
+
+		ret = ttm_mem_type_from_place(place, &mem_type);
 		if (ret)
 			return ret;
 		man = &bdev->man[mem_type];
 		if (!man->has_type)
 			continue;
-		if (!ttm_bo_mt_compatible(man,
-						mem_type,
-						placement->busy_placement[i],
-						&cur_flags))
+		if (!ttm_bo_mt_compatible(man, mem_type, place, &cur_flags))
 			continue;
 
 		cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
@@ -935,7 +930,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		 * Use the access and other non-mapping-related flag bits from
 		 * the memory placement flags to the current flags
 		 */
-		ttm_flag_masked(&cur_flags, placement->busy_placement[i],
+		ttm_flag_masked(&cur_flags, place->flags,
 				~TTM_PL_MASK_MEMTYPE);
 
 		if (mem_type == TTM_PL_SYSTEM) {
@@ -945,7 +940,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 			return 0;
 		}
 
-		ret = ttm_bo_mem_force_space(bo, mem_type, placement, mem,
+		ret = ttm_bo_mem_force_space(bo, mem_type, place, mem,
 						interruptible, no_wait_gpu);
 		if (ret == 0 && mem->mm_node) {
 			mem->placement = cur_flags;
@@ -1006,20 +1001,27 @@ static bool ttm_bo_mem_compat(struct ttm_placement *placement,
 {
 	int i;
 
-	if (mem->mm_node && placement->lpfn != 0 &&
-	    (mem->start < placement->fpfn ||
-	     mem->start + mem->num_pages > placement->lpfn))
-		return false;
-
 	for (i = 0; i < placement->num_placement; i++) {
-		*new_flags = placement->placement[i];
+		const struct ttm_place *heap = &placement->placement[i];
+		if (mem->mm_node && heap->lpfn != 0 &&
+		    (mem->start < heap->fpfn ||
+		     mem->start + mem->num_pages > heap->lpfn))
+			continue;
+
+		*new_flags = heap->flags;
 		if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) &&
 		    (*new_flags & mem->placement & TTM_PL_MASK_MEM))
 			return true;
 	}
 
 	for (i = 0; i < placement->num_busy_placement; i++) {
-		*new_flags = placement->busy_placement[i];
+		const struct ttm_place *heap = &placement->busy_placement[i];
+		if (mem->mm_node && heap->lpfn != 0 &&
+		    (mem->start < heap->fpfn ||
+		     mem->start + mem->num_pages > heap->lpfn))
+			continue;
+
+		*new_flags = heap->flags;
 		if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) &&
 		    (*new_flags & mem->placement & TTM_PL_MASK_MEM))
 			return true;
@@ -1037,11 +1039,6 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	uint32_t new_flags;
 
 	lockdep_assert_held(&bo->resv->lock.base);
-	/* Check that range is valid */
-	if (placement->lpfn || placement->fpfn)
-		if (placement->fpfn > placement->lpfn ||
-			(placement->lpfn - placement->fpfn) < bo->num_pages)
-			return -EINVAL;
 	/*
 	 * Check whether we need to move buffer.
 	 */
@@ -1070,15 +1067,6 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_validate);
 
-int ttm_bo_check_placement(struct ttm_buffer_object *bo,
-				struct ttm_placement *placement)
-{
-	BUG_ON((placement->fpfn || placement->lpfn) &&
-	       (bo->mem.num_pages > (placement->lpfn - placement->fpfn)));
-
-	return 0;
-}
-
 int ttm_bo_init(struct ttm_bo_device *bdev,
 		struct ttm_buffer_object *bo,
 		unsigned long size,
@@ -1147,15 +1135,12 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	atomic_inc(&bo->glob->bo_count);
 	drm_vma_node_reset(&bo->vma_node);
 
-	ret = ttm_bo_check_placement(bo, placement);
-
 	/*
 	 * For ttm_bo_type_device buffers, allocate
 	 * address space from the device.
 	 */
-	if (likely(!ret) &&
-	    (bo->type == ttm_bo_type_device ||
-	     bo->type == ttm_bo_type_sg))
+	if (bo->type == ttm_bo_type_device ||
+	    bo->type == ttm_bo_type_sg)
 		ret = drm_vma_offset_add(&bdev->vma_manager, &bo->vma_node,
 					 bo->mem.num_pages);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index 9e103a4875c8..964387fc5c8f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -49,8 +49,7 @@ struct ttm_range_manager {
 
 static int ttm_bo_man_get_node(struct ttm_mem_type_manager *man,
 			       struct ttm_buffer_object *bo,
-			       struct ttm_placement *placement,
-			       uint32_t flags,
+			       const struct ttm_place *place,
 			       struct ttm_mem_reg *mem)
 {
 	struct ttm_range_manager *rman = (struct ttm_range_manager *) man->priv;
@@ -60,7 +59,7 @@ static int ttm_bo_man_get_node(struct ttm_mem_type_manager *man,
 	unsigned long lpfn;
 	int ret;
 
-	lpfn = placement->lpfn;
+	lpfn = place->lpfn;
 	if (!lpfn)
 		lpfn = man->size;
 
@@ -68,13 +67,13 @@ static int ttm_bo_man_get_node(struct ttm_mem_type_manager *man,
 	if (!node)
 		return -ENOMEM;
 
-	if (flags & TTM_PL_FLAG_TOPDOWN)
+	if (place->flags & TTM_PL_FLAG_TOPDOWN)
 		aflags = DRM_MM_CREATE_TOP;
 
 	spin_lock(&rman->lock);
 	ret = drm_mm_insert_node_in_range_generic(mm, node, mem->num_pages,
 					  mem->page_alignment, 0,
-					  placement->fpfn, lpfn,
+					  place->fpfn, lpfn,
 					  DRM_MM_SEARCH_BEST,
 					  aflags);
 	spin_unlock(&rman->lock);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
index 6327cfc36805..37c093c0c7b8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
@@ -30,66 +30,101 @@
 #include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_page_alloc.h>
 
-static uint32_t vram_placement_flags = TTM_PL_FLAG_VRAM |
-	TTM_PL_FLAG_CACHED;
-
-static uint32_t vram_ne_placement_flags = TTM_PL_FLAG_VRAM |
-	TTM_PL_FLAG_CACHED |
-	TTM_PL_FLAG_NO_EVICT;
+static struct ttm_place vram_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+};
 
-static uint32_t sys_placement_flags = TTM_PL_FLAG_SYSTEM |
-	TTM_PL_FLAG_CACHED;
+static struct ttm_place vram_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
 
-static uint32_t sys_ne_placement_flags = TTM_PL_FLAG_SYSTEM |
-	TTM_PL_FLAG_CACHED |
-	TTM_PL_FLAG_NO_EVICT;
+static struct ttm_place sys_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+};
 
-static uint32_t gmr_placement_flags = VMW_PL_FLAG_GMR |
-	TTM_PL_FLAG_CACHED;
+static struct ttm_place sys_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
 
-static uint32_t gmr_ne_placement_flags = VMW_PL_FLAG_GMR |
-	TTM_PL_FLAG_CACHED |
-	TTM_PL_FLAG_NO_EVICT;
+static struct ttm_place gmr_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+};
 
-static uint32_t mob_placement_flags = VMW_PL_FLAG_MOB |
-	TTM_PL_FLAG_CACHED;
+static struct ttm_place gmr_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
 
-struct ttm_placement vmw_vram_placement = {
+static struct ttm_place mob_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
+	.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+};
+
+struct ttm_placement vmw_vram_placement = {
 	.num_placement = 1,
 	.placement = &vram_placement_flags,
 	.num_busy_placement = 1,
 	.busy_placement = &vram_placement_flags
 };
 
-static uint32_t vram_gmr_placement_flags[] = {
-	TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED,
-	VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+static struct ttm_place vram_gmr_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}
 };
 
-static uint32_t gmr_vram_placement_flags[] = {
-	VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED,
-	TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+static struct ttm_place gmr_vram_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	}
 };
 
 struct ttm_placement vmw_vram_gmr_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 2,
 	.placement = vram_gmr_placement_flags,
 	.num_busy_placement = 1,
 	.busy_placement = &gmr_placement_flags
 };
 
-static uint32_t vram_gmr_ne_placement_flags[] = {
-	TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT,
-	VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+static struct ttm_place vram_gmr_ne_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED |
+			 TTM_PL_FLAG_NO_EVICT
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED |
+			 TTM_PL_FLAG_NO_EVICT
+	}
 };
 
 struct ttm_placement vmw_vram_gmr_ne_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 2,
 	.placement = vram_gmr_ne_placement_flags,
 	.num_busy_placement = 1,
@@ -97,8 +132,6 @@ struct ttm_placement vmw_vram_gmr_ne_placement = {
 };
 
 struct ttm_placement vmw_vram_sys_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.placement = &vram_placement_flags,
 	.num_busy_placement = 1,
@@ -106,8 +139,6 @@ struct ttm_placement vmw_vram_sys_placement = {
 };
 
 struct ttm_placement vmw_vram_ne_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.placement = &vram_ne_placement_flags,
 	.num_busy_placement = 1,
@@ -115,8 +146,6 @@ struct ttm_placement vmw_vram_ne_placement = {
 };
 
 struct ttm_placement vmw_sys_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.placement = &sys_placement_flags,
 	.num_busy_placement = 1,
@@ -124,24 +153,33 @@ struct ttm_placement vmw_sys_placement = {
 };
 
 struct ttm_placement vmw_sys_ne_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.placement = &sys_ne_placement_flags,
 	.num_busy_placement = 1,
 	.busy_placement = &sys_ne_placement_flags
 };
 
-static uint32_t evictable_placement_flags[] = {
-	TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED,
-	TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED,
-	VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED,
-	VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+static struct ttm_place evictable_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+	}
 };
 
 struct ttm_placement vmw_evictable_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 4,
 	.placement = evictable_placement_flags,
 	.num_busy_placement = 1,
@@ -149,8 +187,6 @@ struct ttm_placement vmw_evictable_placement = {
 };
 
 struct ttm_placement vmw_srf_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.num_busy_placement = 2,
 	.placement = &gmr_placement_flags,
@@ -158,8 +194,6 @@ struct ttm_placement vmw_srf_placement = {
 };
 
 struct ttm_placement vmw_mob_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.num_busy_placement = 1,
 	.placement = &mob_placement_flags,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
index ed1d51006ab1..914b375763dc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
@@ -198,13 +198,19 @@ int vmw_dmabuf_to_start_of_vram(struct vmw_private *dev_priv,
 {
 	struct ttm_buffer_object *bo = &buf->base;
 	struct ttm_placement placement;
+	struct ttm_place place;
 	int ret = 0;
 
 	if (pin)
-		placement = vmw_vram_ne_placement;
+		place = vmw_vram_ne_placement.placement[0];
 	else
-		placement = vmw_vram_placement;
-	placement.lpfn = bo->num_pages;
+		place = vmw_vram_placement.placement[0];
+	place.lpfn = bo->num_pages;
+
+	placement.num_placement = 1;
+	placement.placement = &place;
+	placement.num_busy_placement = 1;
+	placement.busy_placement = &place;
 
 	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
 	if (unlikely(ret != 0))
@@ -293,21 +299,23 @@ void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo,
  */
 void vmw_bo_pin(struct ttm_buffer_object *bo, bool pin)
 {
-	uint32_t pl_flags;
+	struct ttm_place pl;
 	struct ttm_placement placement;
 	uint32_t old_mem_type = bo->mem.mem_type;
 	int ret;
 
 	lockdep_assert_held(&bo->resv->lock.base);
 
-	pl_flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
+	pl.fpfn = 0;
+	pl.lpfn = 0;
+	pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
 		| TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED;
 	if (pin)
-		pl_flags |= TTM_PL_FLAG_NO_EVICT;
+		pl.flags |= TTM_PL_FLAG_NO_EVICT;
 
 	memset(&placement, 0, sizeof(placement));
 	placement.num_placement = 1;
-	placement.placement = &pl_flags;
+	placement.placement = &pl;
 
 	ret = ttm_bo_validate(bo, &placement, false, true);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index b031b48dbb3c..0a474f391fad 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -374,10 +374,16 @@ static int vmw_fb_create_bo(struct vmw_private *vmw_priv,
 			    size_t size, struct vmw_dma_buffer **out)
 {
 	struct vmw_dma_buffer *vmw_bo;
-	struct ttm_placement ne_placement = vmw_vram_ne_placement;
+	struct ttm_place ne_place = vmw_vram_ne_placement.placement[0];
+	struct ttm_placement ne_placement;
 	int ret;
 
-	ne_placement.lpfn = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	ne_placement.num_placement = 1;
+	ne_placement.placement = &ne_place;
+	ne_placement.num_busy_placement = 1;
+	ne_placement.busy_placement = &ne_place;
+
+	ne_place.lpfn = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	(void) ttm_write_lock(&vmw_priv->reservation_sem, false);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index 26f8bdde3529..170b61be1e4e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -46,8 +46,7 @@ struct vmwgfx_gmrid_man {
 
 static int vmw_gmrid_man_get_node(struct ttm_mem_type_manager *man,
 				  struct ttm_buffer_object *bo,
-				  struct ttm_placement *placement,
-				  uint32_t flags,
+				  const struct ttm_place *place,
 				  struct ttm_mem_reg *mem)
 {
 	struct vmwgfx_gmrid_man *gman =
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 7526c5bf5610..e3d39c80a091 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -45,12 +45,24 @@ struct ttm_bo_device;
 
 struct drm_mm_node;
 
+/**
+ * struct ttm_place
+ *
+ * @fpfn:	first valid page frame number to put the object
+ * @lpfn:	last valid page frame number to put the object
+ * @flags:	memory domain and caching flags for the object
+ *
+ * Structure indicating a possible place to put an object.
+ */
+struct ttm_place {
+	unsigned	fpfn;
+	unsigned	lpfn;
+	uint32_t	flags;
+};
 
 /**
  * struct ttm_placement
  *
- * @fpfn:		first valid page frame number to put the object
- * @lpfn:		last valid page frame number to put the object
  * @num_placement:	number of preferred placements
  * @placement:		preferred placements
  * @num_busy_placement:	number of preferred placements when need to evict buffer
@@ -59,12 +71,10 @@ struct drm_mm_node;
  * Structure indicating the placement you request for an object.
  */
 struct ttm_placement {
-	unsigned	fpfn;
-	unsigned	lpfn;
-	unsigned	num_placement;
-	const uint32_t	*placement;
-	unsigned	num_busy_placement;
-	const uint32_t	*busy_placement;
+	unsigned		num_placement;
+	const struct ttm_place	*placement;
+	unsigned		num_busy_placement;
+	const struct ttm_place	*busy_placement;
 };
 
 /**
@@ -518,20 +528,6 @@ extern int ttm_bo_create(struct ttm_bo_device *bdev,
 				struct file *persistent_swap_storage,
 				struct ttm_buffer_object **p_bo);
 
-/**
- * ttm_bo_check_placement
- *
- * @bo:		the buffer object.
- * @placement:	placements
- *
- * Performs minimal validity checking on an intended change of
- * placement flags.
- * Returns
- * -EINVAL: Intended change is invalid or not allowed.
- */
-extern int ttm_bo_check_placement(struct ttm_buffer_object *bo,
-					struct ttm_placement *placement);
-
 /**
  * ttm_bo_init_mm
  *
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 1d9f0f1ff52d..5c8bb5699a6f 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -208,8 +208,7 @@ struct ttm_mem_type_manager_func {
 	 */
 	int  (*get_node)(struct ttm_mem_type_manager *man,
 			 struct ttm_buffer_object *bo,
-			 struct ttm_placement *placement,
-			 uint32_t flags,
+			 const struct ttm_place *place,
 			 struct ttm_mem_reg *mem);
 
 	/**
-- 
cgit v1.2.3


From 6a4c264313c4ae32dc53821a9c57e0dc9696fb81 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 27 Aug 2014 06:21:23 +0930
Subject: module: rename KERNEL_PARAM_FL_NOARG to avoid confusion

Make it clear this is about kernel_param_ops, not kernel_param (which
will soon have a flags field of its own). No functional changes.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jean Delvare <khali@linux-fr.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Jon Mason <jon.mason@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/moduleparam.h | 2 +-
 kernel/module.c             | 2 +-
 kernel/params.c             | 6 +++---
 security/apparmor/lsm.c     | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 494f99e852da..16fdddab856a 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -42,7 +42,7 @@ struct kernel_param;
  * NOARG - the parameter allows for no argument (foo instead of foo=1)
  */
 enum {
-	KERNEL_PARAM_FL_NOARG = (1 << 0)
+	KERNEL_PARAM_OPS_FL_NOARG = (1 << 0)
 };
 
 struct kernel_param_ops {
diff --git a/kernel/module.c b/kernel/module.c
index 03214bd288e9..8a0dc91eddbc 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -135,7 +135,7 @@ static int param_set_bool_enable_only(const char *val,
 }
 
 static const struct kernel_param_ops param_ops_bool_enable_only = {
-	.flags = KERNEL_PARAM_FL_NOARG,
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_bool_enable_only,
 	.get = param_get_bool,
 };
diff --git a/kernel/params.c b/kernel/params.c
index 34f527023794..8a484fc8bde8 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -104,7 +104,7 @@ static int parse_one(char *param,
 				return 0;
 			/* No one handled NULL, so do it here. */
 			if (!val &&
-			    !(params[i].ops->flags & KERNEL_PARAM_FL_NOARG))
+			    !(params[i].ops->flags & KERNEL_PARAM_OPS_FL_NOARG))
 				return -EINVAL;
 			pr_debug("handling %s with %p\n", param,
 				params[i].ops->set);
@@ -318,7 +318,7 @@ int param_get_bool(char *buffer, const struct kernel_param *kp)
 EXPORT_SYMBOL(param_get_bool);
 
 struct kernel_param_ops param_ops_bool = {
-	.flags = KERNEL_PARAM_FL_NOARG,
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_bool,
 	.get = param_get_bool,
 };
@@ -369,7 +369,7 @@ int param_set_bint(const char *val, const struct kernel_param *kp)
 EXPORT_SYMBOL(param_set_bint);
 
 struct kernel_param_ops param_ops_bint = {
-	.flags = KERNEL_PARAM_FL_NOARG,
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_bint,
 	.get = param_get_int,
 };
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 998100093332..65ca451a764d 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -668,7 +668,7 @@ static int param_set_aabool(const char *val, const struct kernel_param *kp);
 static int param_get_aabool(char *buffer, const struct kernel_param *kp);
 #define param_check_aabool param_check_bool
 static struct kernel_param_ops param_ops_aabool = {
-	.flags = KERNEL_PARAM_FL_NOARG,
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_aabool,
 	.get = param_get_aabool
 };
@@ -685,7 +685,7 @@ static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp
 static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp);
 #define param_check_aalockpolicy param_check_bool
 static struct kernel_param_ops param_ops_aalockpolicy = {
-	.flags = KERNEL_PARAM_FL_NOARG,
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
 	.set = param_set_aalockpolicy,
 	.get = param_get_aalockpolicy
 };
-- 
cgit v1.2.3


From 91f9d330cc14932084c37751997213cb0e7ea882 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 27 Aug 2014 06:22:23 +0930
Subject: module: make it possible to have unsafe, tainting module params

Add flags field to struct kernel_params, and add the first flag: unsafe
parameter. Modifying a kernel parameter with the unsafe flag set, either
via the kernel command line or sysfs, will issue a warning and taint the
kernel.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jean Delvare <khali@linux-fr.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Jon Mason <jon.mason@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/tty/serial/8250/8250_core.c |  2 +-
 include/linux/moduleparam.h         | 44 +++++++++++++++++++++++++++++--------
 kernel/params.c                     | 11 ++++++++++
 3 files changed, 47 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 1d42dba6121d..bd672948f2f1 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -3587,7 +3587,7 @@ static void __used s8250_options(void)
 #ifdef CONFIG_SERIAL_8250_RSA
 	__module_param_call(MODULE_PARAM_PREFIX, probe_rsa,
 		&param_array_ops, .arr = &__param_arr_probe_rsa,
-		0444, -1);
+		0444, -1, 0);
 #endif
 }
 #else
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 16fdddab856a..1e3ffb839daa 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -56,11 +56,21 @@ struct kernel_param_ops {
 	void (*free)(void *arg);
 };
 
+/*
+ * Flags available for kernel_param
+ *
+ * UNSAFE - the parameter is dangerous and setting it will taint the kernel
+ */
+enum {
+	KERNEL_PARAM_FL_UNSAFE = (1 << 0)
+};
+
 struct kernel_param {
 	const char *name;
 	const struct kernel_param_ops *ops;
 	u16 perm;
-	s16 level;
+	s8 level;
+	u8 flags;
 	union {
 		void *arg;
 		const struct kparam_string *str;
@@ -137,7 +147,7 @@ struct kparam_array
  * The ops can have NULL set or get functions.
  */
 #define module_param_cb(name, ops, arg, perm)				      \
-	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, -1)
+	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, -1, 0)
 
 /**
  * <level>_param_cb - general callback for a module/cmdline parameter
@@ -149,7 +159,7 @@ struct kparam_array
  * The ops can have NULL set or get functions.
  */
 #define __level_param_cb(name, ops, arg, perm, level)			\
-	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, level)
+	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, level, 0)
 
 #define core_param_cb(name, ops, arg, perm)		\
 	__level_param_cb(name, ops, arg, perm, 1)
@@ -184,14 +194,14 @@ struct kparam_array
 
 /* This is the fundamental function for registering boot/module
    parameters. */
-#define __module_param_call(prefix, name, ops, arg, perm, level)	\
+#define __module_param_call(prefix, name, ops, arg, perm, level, flags)	\
 	/* Default value instead of permissions? */			\
 	static const char __param_str_##name[] = prefix #name; \
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used								\
     __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \
 	= { __param_str_##name, ops, VERIFY_OCTAL_PERMISSIONS(perm),	\
-	    level, { arg } }
+	    level, flags, { arg } }
 
 /* Obsolete - use module_param_cb() */
 #define module_param_call(name, set, get, arg, perm)			\
@@ -199,7 +209,7 @@ struct kparam_array
 		{ 0, (void *)set, (void *)get };			\
 	__module_param_call(MODULE_PARAM_PREFIX,			\
 			    name, &__param_ops_##name, arg,		\
-			    (perm) + sizeof(__check_old_set_param(set))*0, -1)
+			    (perm) + sizeof(__check_old_set_param(set))*0, -1, 0)
 
 /* We don't get oldget: it's often a new-style param_get_uint, etc. */
 static inline int
@@ -279,7 +289,7 @@ static inline void __kernel_param_unlock(void)
  */
 #define core_param(name, var, type, perm)				\
 	param_check_##type(name, &(var));				\
-	__module_param_call("", name, &param_ops_##type, &var, perm, -1)
+	__module_param_call("", name, &param_ops_##type, &var, perm, -1, 0)
 #endif /* !MODULE */
 
 /**
@@ -297,7 +307,7 @@ static inline void __kernel_param_unlock(void)
 		= { len, string };					\
 	__module_param_call(MODULE_PARAM_PREFIX, name,			\
 			    &param_ops_string,				\
-			    .str = &__param_string_##name, perm, -1);	\
+			    .str = &__param_string_##name, perm, -1, 0);\
 	__MODULE_PARM_TYPE(name, "string")
 
 /**
@@ -346,6 +356,22 @@ static inline void destroy_params(const struct kernel_param *params,
 #define __param_check(name, p, type) \
 	static inline type __always_unused *__check_##name(void) { return(p); }
 
+/**
+ * param_check_unsafe - Warn and taint the kernel if setting dangerous options.
+ *
+ * This gets called from all the standard param setters, but can be used from
+ * custom setters as well.
+ */
+static inline void
+param_check_unsafe(const struct kernel_param *kp)
+{
+	if (kp->flags & KERNEL_PARAM_FL_UNSAFE) {
+		pr_warn("Setting dangerous option %s - tainting kernel\n",
+			kp->name);
+		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+	}
+}
+
 extern struct kernel_param_ops param_ops_byte;
 extern int param_set_byte(const char *val, const struct kernel_param *kp);
 extern int param_get_byte(char *buffer, const struct kernel_param *kp);
@@ -444,7 +470,7 @@ extern int param_set_bint(const char *val, const struct kernel_param *kp);
 	__module_param_call(MODULE_PARAM_PREFIX, name,			\
 			    &param_array_ops,				\
 			    .arr = &__param_arr_##name,			\
-			    perm, -1);					\
+			    perm, -1, 0);				\
 	__MODULE_PARM_TYPE(name, "array of " #type)
 
 extern struct kernel_param_ops param_array_ops;
diff --git a/kernel/params.c b/kernel/params.c
index 8a484fc8bde8..ad8d04563c3a 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -233,6 +233,7 @@ char *parse_args(const char *doing,
 #define STANDARD_PARAM_DEF(name, type, format, strtolfn)      		\
 	int param_set_##name(const char *val, const struct kernel_param *kp) \
 	{								\
+		param_check_unsafe(kp);					\
 		return strtolfn(val, 0, (type *)kp->arg);		\
 	}								\
 	int param_get_##name(char *buffer, const struct kernel_param *kp) \
@@ -265,6 +266,8 @@ int param_set_charp(const char *val, const struct kernel_param *kp)
 		return -ENOSPC;
 	}
 
+	param_check_unsafe(kp);
+
 	maybe_kfree_parameter(*(char **)kp->arg);
 
 	/* This is a hack.  We can't kmalloc in early boot, and we
@@ -302,6 +305,8 @@ EXPORT_SYMBOL(param_ops_charp);
 /* Actually could be a bool or an int, for historical reasons. */
 int param_set_bool(const char *val, const struct kernel_param *kp)
 {
+	param_check_unsafe(kp);
+
 	/* No equals means "set"... */
 	if (!val) val = "1";
 
@@ -331,6 +336,8 @@ int param_set_invbool(const char *val, const struct kernel_param *kp)
 	bool boolval;
 	struct kernel_param dummy;
 
+	param_check_unsafe(kp);
+
 	dummy.arg = &boolval;
 	ret = param_set_bool(val, &dummy);
 	if (ret == 0)
@@ -357,6 +364,8 @@ int param_set_bint(const char *val, const struct kernel_param *kp)
 	bool v;
 	int ret;
 
+	param_check_unsafe(kp);
+
 	/* Match bool exactly, by re-using it. */
 	boolkp = *kp;
 	boolkp.arg = &v;
@@ -476,6 +485,8 @@ int param_set_copystring(const char *val, const struct kernel_param *kp)
 {
 	const struct kparam_string *kps = kp->str;
 
+	param_check_unsafe(kp);
+
 	if (strlen(val)+1 > kps->maxlen) {
 		pr_err("%s: string doesn't fit in %u chars.\n",
 		       kp->name, kps->maxlen-1);
-- 
cgit v1.2.3


From 3baee201b06cfaff84c2c5ddc551b192bb3eaed3 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 27 Aug 2014 06:23:23 +0930
Subject: module: add module_param_unsafe and module_param_named_unsafe

Add the helpers to be used by modules wishing to expose unsafe debugging
or testing module parameters that taint the kernel when set.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jean Delvare <khali@linux-fr.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Jon Mason <jon.mason@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/moduleparam.h | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 1e3ffb839daa..9531f9f9729e 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -122,6 +122,12 @@ struct kparam_array
 #define module_param(name, type, perm)				\
 	module_param_named(name, name, type, perm)
 
+/**
+ * module_param_unsafe - same as module_param but taints kernel
+ */
+#define module_param_unsafe(name, type, perm)			\
+	module_param_named_unsafe(name, name, type, perm)
+
 /**
  * module_param_named - typesafe helper for a renamed module/cmdline parameter
  * @name: a valid C identifier which is the parameter name.
@@ -138,6 +144,14 @@ struct kparam_array
 	module_param_cb(name, &param_ops_##type, &value, perm);		   \
 	__MODULE_PARM_TYPE(name, #type)
 
+/**
+ * module_param_named_unsafe - same as module_param_named but taints kernel
+ */
+#define module_param_named_unsafe(name, value, type, perm)		\
+	param_check_##type(name, &(value));				\
+	module_param_cb_unsafe(name, &param_ops_##type, &value, perm);	\
+	__MODULE_PARM_TYPE(name, #type)
+
 /**
  * module_param_cb - general callback for a module/cmdline parameter
  * @name: a valid C identifier which is the parameter name.
@@ -149,6 +163,10 @@ struct kparam_array
 #define module_param_cb(name, ops, arg, perm)				      \
 	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, -1, 0)
 
+#define module_param_cb_unsafe(name, ops, arg, perm)			      \
+	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, -1,    \
+			    KERNEL_PARAM_FL_UNSAFE)
+
 /**
  * <level>_param_cb - general callback for a module/cmdline parameter
  *                    to be evaluated before certain initcall level
-- 
cgit v1.2.3


From 7a486d3781295b5298cbf9556928a76d26896863 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Wed, 27 Aug 2014 06:25:23 +0930
Subject: param: check for tainting before calling set op.

This means every set op doesn't need to call it, and it can move into
params.c.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/moduleparam.h | 16 ----------------
 kernel/params.c             | 22 +++++++++++-----------
 2 files changed, 11 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 9531f9f9729e..593501996574 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -374,22 +374,6 @@ static inline void destroy_params(const struct kernel_param *params,
 #define __param_check(name, p, type) \
 	static inline type __always_unused *__check_##name(void) { return(p); }
 
-/**
- * param_check_unsafe - Warn and taint the kernel if setting dangerous options.
- *
- * This gets called from all the standard param setters, but can be used from
- * custom setters as well.
- */
-static inline void
-param_check_unsafe(const struct kernel_param *kp)
-{
-	if (kp->flags & KERNEL_PARAM_FL_UNSAFE) {
-		pr_warn("Setting dangerous option %s - tainting kernel\n",
-			kp->name);
-		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
-	}
-}
-
 extern struct kernel_param_ops param_ops_byte;
 extern int param_set_byte(const char *val, const struct kernel_param *kp);
 extern int param_get_byte(char *buffer, const struct kernel_param *kp);
diff --git a/kernel/params.c b/kernel/params.c
index ad8d04563c3a..041b5899d5e2 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -83,6 +83,15 @@ bool parameq(const char *a, const char *b)
 	return parameqn(a, b, strlen(a)+1);
 }
 
+static void param_check_unsafe(const struct kernel_param *kp)
+{
+	if (kp->flags & KERNEL_PARAM_FL_UNSAFE) {
+		pr_warn("Setting dangerous option %s - tainting kernel\n",
+			kp->name);
+		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+	}
+}
+
 static int parse_one(char *param,
 		     char *val,
 		     const char *doing,
@@ -109,6 +118,7 @@ static int parse_one(char *param,
 			pr_debug("handling %s with %p\n", param,
 				params[i].ops->set);
 			mutex_lock(&param_lock);
+			param_check_unsafe(&params[i]);
 			err = params[i].ops->set(val, &params[i]);
 			mutex_unlock(&param_lock);
 			return err;
@@ -233,7 +243,6 @@ char *parse_args(const char *doing,
 #define STANDARD_PARAM_DEF(name, type, format, strtolfn)      		\
 	int param_set_##name(const char *val, const struct kernel_param *kp) \
 	{								\
-		param_check_unsafe(kp);					\
 		return strtolfn(val, 0, (type *)kp->arg);		\
 	}								\
 	int param_get_##name(char *buffer, const struct kernel_param *kp) \
@@ -266,8 +275,6 @@ int param_set_charp(const char *val, const struct kernel_param *kp)
 		return -ENOSPC;
 	}
 
-	param_check_unsafe(kp);
-
 	maybe_kfree_parameter(*(char **)kp->arg);
 
 	/* This is a hack.  We can't kmalloc in early boot, and we
@@ -305,8 +312,6 @@ EXPORT_SYMBOL(param_ops_charp);
 /* Actually could be a bool or an int, for historical reasons. */
 int param_set_bool(const char *val, const struct kernel_param *kp)
 {
-	param_check_unsafe(kp);
-
 	/* No equals means "set"... */
 	if (!val) val = "1";
 
@@ -336,8 +341,6 @@ int param_set_invbool(const char *val, const struct kernel_param *kp)
 	bool boolval;
 	struct kernel_param dummy;
 
-	param_check_unsafe(kp);
-
 	dummy.arg = &boolval;
 	ret = param_set_bool(val, &dummy);
 	if (ret == 0)
@@ -364,8 +367,6 @@ int param_set_bint(const char *val, const struct kernel_param *kp)
 	bool v;
 	int ret;
 
-	param_check_unsafe(kp);
-
 	/* Match bool exactly, by re-using it. */
 	boolkp = *kp;
 	boolkp.arg = &v;
@@ -485,8 +486,6 @@ int param_set_copystring(const char *val, const struct kernel_param *kp)
 {
 	const struct kparam_string *kps = kp->str;
 
-	param_check_unsafe(kp);
-
 	if (strlen(val)+1 > kps->maxlen) {
 		pr_err("%s: string doesn't fit in %u chars.\n",
 		       kp->name, kps->maxlen-1);
@@ -563,6 +562,7 @@ static ssize_t param_attr_store(struct module_attribute *mattr,
 		return -EPERM;
 
 	mutex_lock(&param_lock);
+	param_check_unsafe(attribute->param);
 	err = attribute->param->ops->set(buf, attribute->param);
 	mutex_unlock(&param_lock);
 	if (!err)
-- 
cgit v1.2.3


From 2d15d974618db4ed3adafe9b9fe092db0f5076a0 Mon Sep 17 00:00:00 2001
From: Bard Liao <bardliao@realtek.com>
Date: Wed, 27 Aug 2014 19:50:34 +0800
Subject: ASoC: rt5677: Add DMIC2 clock selection

There are two pins can be used for rt5677's DMIC2 clock. This patch
add the select options for it.

Signed-off-by: Bard Liao <bardliao@realtek.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/rt5677.h    |  8 +++++++
 sound/soc/codecs/rt5677.c | 57 ++++++++++++++++++++++++++++++++++++++++-------
 sound/soc/codecs/rt5677.h | 10 +++++++++
 3 files changed, 67 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/sound/rt5677.h b/include/sound/rt5677.h
index 3da14313bcfc..a676717f74f4 100644
--- a/include/sound/rt5677.h
+++ b/include/sound/rt5677.h
@@ -12,10 +12,18 @@
 #ifndef __LINUX_SND_RT5677_H
 #define __LINUX_SND_RT5677_H
 
+enum rt5677_dmic2_clk {
+	RT5677_DMIC_CLK1 = 0,
+	RT5677_DMIC_CLK2 = 1,
+};
+
+
 struct rt5677_platform_data {
 	/* IN1 IN2 can optionally be differential */
 	bool in1_diff;
 	bool in2_diff;
+	/* DMIC2 clock source selection */
+	enum rt5677_dmic2_clk dmic2_clk_pin;
 };
 
 #endif
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 67f14556462f..f0b751bf1d6c 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -1700,14 +1700,19 @@ static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = {
 
 	SND_SOC_DAPM_INPUT("Haptic Generator"),
 
-	SND_SOC_DAPM_PGA("DMIC1", RT5677_DMIC_CTRL1, RT5677_DMIC_1_EN_SFT, 0,
-		NULL, 0),
-	SND_SOC_DAPM_PGA("DMIC2", RT5677_DMIC_CTRL1, RT5677_DMIC_2_EN_SFT, 0,
-		NULL, 0),
-	SND_SOC_DAPM_PGA("DMIC3", RT5677_DMIC_CTRL1, RT5677_DMIC_3_EN_SFT, 0,
-		NULL, 0),
-	SND_SOC_DAPM_PGA("DMIC4", RT5677_DMIC_CTRL2, RT5677_DMIC_4_EN_SFT, 0,
-		NULL, 0),
+	SND_SOC_DAPM_PGA("DMIC1", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("DMIC2", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("DMIC3", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("DMIC4", SND_SOC_NOPM, 0, 0, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("DMIC1 power", RT5677_DMIC_CTRL1,
+		RT5677_DMIC_1_EN_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DMIC2 power", RT5677_DMIC_CTRL1,
+		RT5677_DMIC_2_EN_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DMIC3 power", RT5677_DMIC_CTRL1,
+		RT5677_DMIC_3_EN_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DMIC4 power", RT5677_DMIC_CTRL2,
+		RT5677_DMIC_4_EN_SFT, 0, NULL, 0),
 
 	SND_SOC_DAPM_SUPPLY("DMIC CLK", SND_SOC_NOPM, 0, 0,
 		set_dmic_clk, SND_SOC_DAPM_PRE_PMU),
@@ -2130,6 +2135,13 @@ static const struct snd_soc_dapm_route rt5677_dapm_routes[] = {
 	{ "DMIC L4", NULL, "DMIC CLK" },
 	{ "DMIC R4", NULL, "DMIC CLK" },
 
+	{ "DMIC L1", NULL, "DMIC1 power" },
+	{ "DMIC R1", NULL, "DMIC1 power" },
+	{ "DMIC L3", NULL, "DMIC3 power" },
+	{ "DMIC R3", NULL, "DMIC3 power" },
+	{ "DMIC L4", NULL, "DMIC4 power" },
+	{ "DMIC R4", NULL, "DMIC4 power" },
+
 	{ "BST1", NULL, "IN1P" },
 	{ "BST1", NULL, "IN1N" },
 	{ "BST2", NULL, "IN2P" },
@@ -2793,6 +2805,16 @@ static const struct snd_soc_dapm_route rt5677_dapm_routes[] = {
 	{ "PDM2R", NULL, "PDM2 R Mux" },
 };
 
+static const struct snd_soc_dapm_route rt5677_dmic2_clk_1[] = {
+	{ "DMIC L2", NULL, "DMIC1 power" },
+	{ "DMIC R2", NULL, "DMIC1 power" },
+};
+
+static const struct snd_soc_dapm_route rt5677_dmic2_clk_2[] = {
+	{ "DMIC L2", NULL, "DMIC2 power" },
+	{ "DMIC R2", NULL, "DMIC2 power" },
+};
+
 static int rt5677_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_hw_params *params, struct snd_soc_dai *dai)
 {
@@ -3144,6 +3166,16 @@ static int rt5677_probe(struct snd_soc_codec *codec)
 
 	rt5677->codec = codec;
 
+	if (rt5677->pdata.dmic2_clk_pin == RT5677_DMIC_CLK2) {
+		snd_soc_dapm_add_routes(&codec->dapm,
+			rt5677_dmic2_clk_2,
+			ARRAY_SIZE(rt5677_dmic2_clk_2));
+	} else { /*use dmic1 clock by default*/
+		snd_soc_dapm_add_routes(&codec->dapm,
+			rt5677_dmic2_clk_1,
+			ARRAY_SIZE(rt5677_dmic2_clk_1));
+	}
+
 	rt5677_set_bias_level(codec, SND_SOC_BIAS_OFF);
 
 	regmap_write(rt5677->regmap, RT5677_DIG_MISC, 0x0020);
@@ -3381,6 +3413,15 @@ static int rt5677_i2c_probe(struct i2c_client *i2c,
 		regmap_update_bits(rt5677->regmap, RT5677_IN1,
 					RT5677_IN_DF2, RT5677_IN_DF2);
 
+	if (rt5677->pdata.dmic2_clk_pin == RT5677_DMIC_CLK2) {
+		regmap_update_bits(rt5677->regmap, RT5677_GEN_CTRL2,
+					RT5677_GPIO5_FUNC_MASK,
+					RT5677_GPIO5_FUNC_DMIC);
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL2,
+					RT5677_GPIO5_DIR_MASK,
+					RT5677_GPIO5_DIR_OUT);
+	}
+
 	return snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5677,
 				      rt5677_dai, ARRAY_SIZE(rt5677_dai));
 }
diff --git a/sound/soc/codecs/rt5677.h b/sound/soc/codecs/rt5677.h
index 863393e62096..8791ab9637f3 100644
--- a/sound/soc/codecs/rt5677.h
+++ b/sound/soc/codecs/rt5677.h
@@ -1363,6 +1363,11 @@
 #define RT5677_SEL_SRC_IB01			(0x1 << 0)
 #define RT5677_SEL_SRC_IB01_SFT			0
 
+/* GPIO Control 2 (0xc1) */
+#define RT5677_GPIO5_DIR_MASK			(0x1 << 14)
+#define RT5677_GPIO5_DIR_IN			(0x0 << 14)
+#define RT5677_GPIO5_DIR_OUT			(0x1 << 14)
+
 /* Virtual DSP Mixer Control (0xf7 0xf8 0xf9) */
 #define RT5677_DSP_IB_01_H			(0x1 << 15)
 #define RT5677_DSP_IB_01_H_SFT			15
@@ -1393,6 +1398,11 @@
 #define RT5677_DSP_IB_9_L			(0x1 << 1)
 #define RT5677_DSP_IB_9_L_SFT			1
 
+/* General Control2 (0xfc)*/
+#define RT5677_GPIO5_FUNC_MASK			(0x1 << 9)
+#define RT5677_GPIO5_FUNC_GPIO			(0x0 << 9)
+#define RT5677_GPIO5_FUNC_DMIC			(0x1 << 9)
+
 /* System Clock Source */
 enum {
 	RT5677_SCLK_S_MCLK,
-- 
cgit v1.2.3


From 64d831269ccbca1fc6d739a0f3c8aa24afb43a5e Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Tue, 19 Aug 2014 12:15:00 +0200
Subject: KVM: Introduce gfn_to_hva_memslot_prot

To support read-only memory regions on arm and arm64, we have a need to
resolve a gfn to an hva given a pointer to a memslot to avoid looping
through the memslots twice and to reuse the hva error checking of
gfn_to_hva_prot(), add a new gfn_to_hva_memslot_prot() function and
refactor gfn_to_hva_prot() to use this function.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 include/linux/kvm_host.h |  2 ++
 virt/kvm/kvm_main.c      | 11 +++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ebd723676633..6d8a658ec174 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -528,6 +528,8 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
 unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
+				      bool *writable);
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
 void kvm_set_page_accessed(struct page *page);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5a0817ee996e..76c92a7249c4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1076,9 +1076,9 @@ EXPORT_SYMBOL_GPL(gfn_to_hva);
  * If writable is set to false, the hva returned by this function is only
  * allowed to be read.
  */
-unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
+				      gfn_t gfn, bool *writable)
 {
-	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
 	unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false);
 
 	if (!kvm_is_error_hva(hva) && writable)
@@ -1087,6 +1087,13 @@ unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
 	return hva;
 }
 
+unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
+{
+	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+
+	return gfn_to_hva_memslot_prot(slot, gfn, writable);
+}
+
 static int kvm_read_hva(void *data, void __user *hva, int len)
 {
 	return __copy_from_user(data, hva, len);
-- 
cgit v1.2.3


From 5c21403d74af2c9cd635a34c2f9199681a5b813e Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 27 Aug 2014 14:39:04 -0700
Subject: net: Update sk_buff flag bit availability comment.

We lost one when xmit_more was added.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9b3802a197a8..b69b7b512c06 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -580,7 +580,7 @@ struct sk_buff {
 	__u8			encap_hdr_csum:1;
 	__u8			csum_valid:1;
 	__u8			csum_complete_sw:1;
-	/* 2/4 bit hole (depending on ndisc_nodetype presence) */
+	/* 1/3 bit hole (depending on ndisc_nodetype presence) */
 	kmemcheck_bitfield_end(flags2);
 
 #if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL
-- 
cgit v1.2.3


From 3e8a72d1dae374cf6fc1dba97cec663585845ff9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 27 Aug 2014 17:04:46 -0700
Subject: net: dsa: reduce number of protocol hooks

DSA is currently registering one packet_type function per EtherType it
needs to intercept in the receive path of a DSA-enabled Ethernet device.
Right now we have three of them: trailer, DSA and eDSA, and there might
be more in the future, this will not scale to the addition of new
protocols.

This patch proceeds with adding a new layer of abstraction and two new
functions:

dsa_switch_rcv() which will dispatch into the tag-protocol specific
receive function implemented by net/dsa/tag_*.c

dsa_slave_xmit() which will dispatch into the tag-protocol specific
transmit function implemented by net/dsa/tag_*.c

When we do create the per-port slave network devices, we iterate over
the switch protocol to assign the DSA-specific receive and transmit
operations.

A new fake ethertype value is used: ETH_P_XDSA to illustrate the fact
that this is no longer going to look like ETH_P_DSA or ETH_P_TRAILER
like it used to be.

This allows us to greatly simplify the check in eth_type_trans() and
always override the skb->protocol with ETH_P_XDSA for Ethernet switches
tagged protocol, while also reducing the number repetitive slave
netdevice_ops assignments.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h     | 28 ++++++++++++---------------
 include/net/dsa.h             | 20 +++----------------
 include/uapi/linux/if_ether.h |  1 +
 net/dsa/dsa.c                 | 39 ++++++++++++++++++++-----------------
 net/dsa/dsa_priv.h            |  9 +++------
 net/dsa/slave.c               | 45 ++++++++++++++-----------------------------
 net/dsa/tag_dsa.c             |  8 ++++----
 net/dsa/tag_edsa.c            |  8 ++++----
 net/dsa/tag_trailer.c         |  8 ++++----
 net/ethernet/eth.c            |  7 ++-----
 10 files changed, 68 insertions(+), 105 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 039b23786c22..1875dc71422a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1781,24 +1781,13 @@ void dev_net_set(struct net_device *dev, struct net *net)
 #endif
 }
 
-static inline bool netdev_uses_dsa_tags(struct net_device *dev)
+static inline bool netdev_uses_dsa(struct net_device *dev)
 {
-#ifdef CONFIG_NET_DSA_TAG_DSA
-	if (dev->dsa_ptr != NULL)
-		return dsa_uses_dsa_tags(dev->dsa_ptr);
-#endif
-
-	return 0;
-}
-
-static inline bool netdev_uses_trailer_tags(struct net_device *dev)
-{
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
-	if (dev->dsa_ptr != NULL)
-		return dsa_uses_trailer_tags(dev->dsa_ptr);
+#ifdef CONFIG_NET_DSA
+	return dev->dsa_ptr != NULL;
+#else
+	return false;
 #endif
-
-	return 0;
 }
 
 /**
@@ -1933,6 +1922,13 @@ struct udp_offload {
 	struct offload_callbacks callbacks;
 };
 
+struct dsa_device_ops {
+	netdev_tx_t (*xmit)(struct sk_buff *skb, struct net_device *dev);
+	int (*rcv)(struct sk_buff *skb, struct net_device *dev,
+		   struct packet_type *pt, struct net_device *orig_dev);
+};
+
+
 /* often modified stats are per cpu, other are shared (netdev->stats) */
 struct pcpu_sw_netstats {
 	u64     rx_packets;
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 6efce384451e..6e26f1e4d8ce 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -59,6 +59,8 @@ struct dsa_platform_data {
 	struct dsa_chip_data	*chip;
 };
 
+struct dsa_device_ops;
+
 struct dsa_switch_tree {
 	/*
 	 * Configuration data for the platform device that owns
@@ -71,6 +73,7 @@ struct dsa_switch_tree {
 	 * protocol to use.
 	 */
 	struct net_device	*master_netdev;
+	const struct dsa_device_ops	*ops;
 	__be16			tag_protocol;
 
 	/*
@@ -186,21 +189,4 @@ static inline void *ds_to_priv(struct dsa_switch *ds)
 	return (void *)(ds + 1);
 }
 
-/*
- * The original DSA tag format and some other tag formats have no
- * ethertype, which means that we need to add a little hack to the
- * networking receive path to make sure that received frames get
- * the right ->protocol assigned to them when one of those tag
- * formats is in use.
- */
-static inline bool dsa_uses_dsa_tags(struct dsa_switch_tree *dst)
-{
-	return !!(dst->tag_protocol == htons(ETH_P_DSA));
-}
-
-static inline bool dsa_uses_trailer_tags(struct dsa_switch_tree *dst)
-{
-	return !!(dst->tag_protocol == htons(ETH_P_TRAILER));
-}
-
 #endif
diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index 0f8210b8e0bc..aa63ed023c2b 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -128,6 +128,7 @@
 #define ETH_P_PHONET	0x00F5		/* Nokia Phonet frames          */
 #define ETH_P_IEEE802154 0x00F6		/* IEEE802.15.4 frame		*/
 #define ETH_P_CAIF	0x00F7		/* ST-Ericsson CAIF protocol	*/
+#define ETH_P_XDSA	0x00F8		/* Multiplexed DSA protocol	*/
 
 /*
  *	This is an Ethernet frame header.
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 0a49632fac47..92e71d2a2ccd 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -608,6 +608,24 @@ static void dsa_shutdown(struct platform_device *pdev)
 {
 }
 
+static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
+			  struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct dsa_switch_tree *dst = dev->dsa_ptr;
+
+	if (unlikely(dst == NULL)) {
+		kfree_skb(skb);
+		return 0;
+	}
+
+	return dst->ops->rcv(skb, dev, pt, orig_dev);
+}
+
+struct packet_type dsa_pack_type __read_mostly = {
+	.type	= cpu_to_be16(ETH_P_XDSA),
+	.func	= dsa_switch_rcv,
+};
+
 static const struct of_device_id dsa_of_match_table[] = {
 	{ .compatible = "marvell,dsa", },
 	{}
@@ -633,30 +651,15 @@ static int __init dsa_init_module(void)
 	if (rc)
 		return rc;
 
-#ifdef CONFIG_NET_DSA_TAG_DSA
-	dev_add_pack(&dsa_packet_type);
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
-	dev_add_pack(&edsa_packet_type);
-#endif
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
-	dev_add_pack(&trailer_packet_type);
-#endif
+	dev_add_pack(&dsa_pack_type);
+
 	return 0;
 }
 module_init(dsa_init_module);
 
 static void __exit dsa_cleanup_module(void)
 {
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
-	dev_remove_pack(&trailer_packet_type);
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
-	dev_remove_pack(&edsa_packet_type);
-#endif
-#ifdef CONFIG_NET_DSA_TAG_DSA
-	dev_remove_pack(&dsa_packet_type);
-#endif
+	dev_remove_pack(&dsa_pack_type);
 	platform_driver_unregister(&dsa_driver);
 }
 module_exit(dsa_cleanup_module);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index d4cf5cc747e3..218d75d16f6f 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -45,16 +45,13 @@ struct net_device *dsa_slave_create(struct dsa_switch *ds,
 				    int port, char *name);
 
 /* tag_dsa.c */
-netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev);
-extern struct packet_type dsa_packet_type;
+extern const struct dsa_device_ops dsa_netdev_ops;
 
 /* tag_edsa.c */
-netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev);
-extern struct packet_type edsa_packet_type;
+extern const struct dsa_device_ops edsa_netdev_ops;
 
 /* tag_trailer.c */
-netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev);
-extern struct packet_type trailer_packet_type;
+extern const struct dsa_device_ops trailer_netdev_ops;
 
 
 #endif
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 45a1e34c89e0..ad1a913533aa 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -171,6 +171,14 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return -EOPNOTSUPP;
 }
 
+static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch_tree *dst = p->parent->dst;
+
+	return dst->ops->xmit(skb, dev);
+}
+
 
 /* ethtool operations *******************************************************/
 static int
@@ -293,42 +301,16 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_sset_count		= dsa_slave_get_sset_count,
 };
 
-#ifdef CONFIG_NET_DSA_TAG_DSA
-static const struct net_device_ops dsa_netdev_ops = {
+static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_init		= dsa_slave_init,
 	.ndo_open	 	= dsa_slave_open,
 	.ndo_stop		= dsa_slave_close,
-	.ndo_start_xmit		= dsa_xmit,
+	.ndo_start_xmit		= dsa_slave_xmit,
 	.ndo_change_rx_flags	= dsa_slave_change_rx_flags,
 	.ndo_set_rx_mode	= dsa_slave_set_rx_mode,
 	.ndo_set_mac_address	= dsa_slave_set_mac_address,
 	.ndo_do_ioctl		= dsa_slave_ioctl,
 };
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
-static const struct net_device_ops edsa_netdev_ops = {
-	.ndo_init		= dsa_slave_init,
-	.ndo_open	 	= dsa_slave_open,
-	.ndo_stop		= dsa_slave_close,
-	.ndo_start_xmit		= edsa_xmit,
-	.ndo_change_rx_flags	= dsa_slave_change_rx_flags,
-	.ndo_set_rx_mode	= dsa_slave_set_rx_mode,
-	.ndo_set_mac_address	= dsa_slave_set_mac_address,
-	.ndo_do_ioctl		= dsa_slave_ioctl,
-};
-#endif
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
-static const struct net_device_ops trailer_netdev_ops = {
-	.ndo_init		= dsa_slave_init,
-	.ndo_open	 	= dsa_slave_open,
-	.ndo_stop		= dsa_slave_close,
-	.ndo_start_xmit		= trailer_xmit,
-	.ndo_change_rx_flags	= dsa_slave_change_rx_flags,
-	.ndo_set_rx_mode	= dsa_slave_set_rx_mode,
-	.ndo_set_mac_address	= dsa_slave_set_mac_address,
-	.ndo_do_ioctl		= dsa_slave_ioctl,
-};
-#endif
 
 /* slave device setup *******************************************************/
 struct net_device *
@@ -349,21 +331,22 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
 	eth_hw_addr_inherit(slave_dev, master);
 	slave_dev->tx_queue_len = 0;
+	slave_dev->netdev_ops = &dsa_slave_netdev_ops;
 
 	switch (ds->dst->tag_protocol) {
 #ifdef CONFIG_NET_DSA_TAG_DSA
 	case htons(ETH_P_DSA):
-		slave_dev->netdev_ops = &dsa_netdev_ops;
+		ds->dst->ops = &dsa_netdev_ops;
 		break;
 #endif
 #ifdef CONFIG_NET_DSA_TAG_EDSA
 	case htons(ETH_P_EDSA):
-		slave_dev->netdev_ops = &edsa_netdev_ops;
+		ds->dst->ops = &edsa_netdev_ops;
 		break;
 #endif
 #ifdef CONFIG_NET_DSA_TAG_TRAILER
 	case htons(ETH_P_TRAILER):
-		slave_dev->netdev_ops = &trailer_netdev_ops;
+		ds->dst->ops = &trailer_netdev_ops;
 		break;
 #endif
 	default:
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index cacce1e22f9c..d7dbc5bda5c0 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -16,7 +16,7 @@
 
 #define DSA_HLEN	4
 
-netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	u8 *dsa_header;
@@ -186,7 +186,7 @@ out:
 	return 0;
 }
 
-struct packet_type dsa_packet_type __read_mostly = {
-	.type	= cpu_to_be16(ETH_P_DSA),
-	.func	= dsa_rcv,
+const struct dsa_device_ops dsa_netdev_ops = {
+	.xmit	= dsa_xmit,
+	.rcv	= dsa_rcv,
 };
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index e70c43c25e64..6b30abe89183 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -17,7 +17,7 @@
 #define DSA_HLEN	4
 #define EDSA_HLEN	8
 
-netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	u8 *edsa_header;
@@ -205,7 +205,7 @@ out:
 	return 0;
 }
 
-struct packet_type edsa_packet_type __read_mostly = {
-	.type	= cpu_to_be16(ETH_P_EDSA),
-	.func	= edsa_rcv,
+const struct dsa_device_ops edsa_netdev_ops = {
+	.xmit	= edsa_xmit,
+	.rcv	= edsa_rcv,
 };
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 94bc260d015d..5fe9444842c5 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -14,7 +14,7 @@
 #include <linux/slab.h>
 #include "dsa_priv.h"
 
-netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct sk_buff *nskb;
@@ -114,7 +114,7 @@ out:
 	return 0;
 }
 
-struct packet_type trailer_packet_type __read_mostly = {
-	.type	= cpu_to_be16(ETH_P_TRAILER),
-	.func	= trailer_rcv,
+const struct dsa_device_ops trailer_netdev_ops = {
+	.xmit	= trailer_xmit,
+	.rcv	= trailer_rcv,
 };
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index f405e0592407..5cebca134585 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -181,11 +181,8 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
 	 * variants has been configured on the receiving interface,
 	 * and if so, set skb->protocol without looking at the packet.
 	 */
-	if (unlikely(netdev_uses_dsa_tags(dev)))
-		return htons(ETH_P_DSA);
-
-	if (unlikely(netdev_uses_trailer_tags(dev)))
-		return htons(ETH_P_TRAILER);
+	if (unlikely(netdev_uses_dsa(dev)))
+		return htons(ETH_P_XDSA);
 
 	if (likely(ntohs(eth->h_proto) >= ETH_P_802_3_MIN))
 		return eth->h_proto;
-- 
cgit v1.2.3


From 464c3668f065baeacfffa9d421959d21069389fe Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 27 Aug 2014 17:04:48 -0700
Subject: net: phy: provide stub for fixed_phy_set_link_update

In preparation for updating the DSA code and avoid using ifdefs there,
provide an empty stub for fixed_phy_set_link_update when
CONFIG_FIXED_PHY is not selected.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy_fixed.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index ae612acebb53..941138664c1d 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -18,6 +18,9 @@ extern int fixed_phy_register(unsigned int irq,
 			      struct fixed_phy_status *status,
 			      struct device_node *np);
 extern void fixed_phy_del(int phy_addr);
+extern int fixed_phy_set_link_update(struct phy_device *phydev,
+			int (*link_update)(struct net_device *,
+					   struct fixed_phy_status *));
 #else
 static inline int fixed_phy_add(unsigned int irq, int phy_id,
 				struct fixed_phy_status *status)
@@ -34,14 +37,12 @@ static inline int fixed_phy_del(int phy_addr)
 {
 	return -ENODEV;
 }
-#endif /* CONFIG_FIXED_PHY */
-
-/*
- * This function issued only by fixed_phy-aware drivers, no need
- * protect it with #ifdef
- */
-extern int fixed_phy_set_link_update(struct phy_device *phydev,
+static inline int fixed_phy_set_link_update(struct phy_device *phydev,
 			int (*link_update)(struct net_device *,
-					   struct fixed_phy_status *));
+					   struct fixed_phy_status *))
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_FIXED_PHY */
 
 #endif /* __PHY_FIXED_H */
-- 
cgit v1.2.3


From fa981d9af82e08f316ed25ed43078f995cc4be0a Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 27 Aug 2014 17:04:49 -0700
Subject: net: dsa: provide a switch device device tree node pointer

We might need to fetch additional resources from the device tree node
pointer, such as register ranges or other properties. Keep a device_node
pointer around for this.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 7 +++++++
 net/dsa/dsa.c     | 1 +
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 6e26f1e4d8ce..decc62709acd 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
+#include <linux/of.h>
 
 #define DSA_MAX_SWITCHES	4
 #define DSA_MAX_PORTS		12
@@ -26,6 +27,12 @@ struct dsa_chip_data {
 	struct device	*mii_bus;
 	int		sw_addr;
 
+	/* Device tree node pointer for this specific switch chip
+	 * used during switch setup in case additional properties
+	 * and resources needs to be used
+	 */
+	struct device_node *of_node;
+
 	/*
 	 * The names of the switch's ports.  Use "cpu" to
 	 * designate the switch port that the cpu is connected to,
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 92e71d2a2ccd..a28ef432d016 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -410,6 +410,7 @@ static int dsa_of_probe(struct platform_device *pdev)
 		chip_index++;
 		cd = &pd->chip[chip_index];
 
+		cd->of_node = child;
 		cd->mii_bus = &mdio_bus->dev;
 
 		sw_addr = of_get_property(child, "reg", NULL);
-- 
cgit v1.2.3


From bd47497a0171b96264927e3377254db13b9fe3e3 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 27 Aug 2014 17:04:50 -0700
Subject: net: dsa: retain a per-port device_node pointer

We will later use the per-port device_node pointer to fetch a bunch of
port-specific properties.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 1 +
 net/dsa/dsa.c     | 2 ++
 net/dsa/slave.c   | 1 +
 3 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index decc62709acd..597875d3f69e 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -41,6 +41,7 @@ struct dsa_chip_data {
 	 * or any other string to indicate this is a physical port.
 	 */
 	char		*port_names[DSA_MAX_PORTS];
+	struct device_node *port_dn[DSA_MAX_PORTS];
 
 	/*
 	 * An array (with nr_chips elements) of which element [a]
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index a28ef432d016..6a5bae673037 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -432,6 +432,8 @@ static int dsa_of_probe(struct platform_device *pdev)
 			if (!port_name)
 				continue;
 
+			cd->port_dn[port_index] = port;
+
 			cd->port_names[port_index] = kstrdup(port_name,
 					GFP_KERNEL);
 			if (!cd->port_names[port_index]) {
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ad1a913533aa..5688c34253e5 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -354,6 +354,7 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	}
 
 	SET_NETDEV_DEV(slave_dev, parent);
+	slave_dev->dev.of_node = ds->pd->port_dn[port];
 	slave_dev->vlan_features = master->vlan_features;
 
 	p = netdev_priv(slave_dev);
-- 
cgit v1.2.3


From 0d8bcdd383b8865e752a7e8edb4712c2e3902052 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 27 Aug 2014 17:04:51 -0700
Subject: net: dsa: allow for more complex PHY setups

Modify the DSA slave interface to be bound to an arbitray PHY, not just
the ones that are available as child PHY devices of the switch MDIO bus.

This allows us for instance to have external PHYs connected to a
separate MDIO bus, but yet also connected to a given switch port.

Under certain configurations, the physical port mask might not be a 1:1
mapping to the MII PHYs mask. This is the case, if e.g: Port 1 of the
switch is used and connects to a PHY at a MDIO address different than 1.

Introduce a phys_mii_mask variable which allows driver to implement and
divert their own MDIO read/writes operations for a subset of the MDIO
PHY addresses.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h  |  1 +
 net/dsa/dsa.c      |  5 ++++
 net/dsa/dsa_priv.h |  4 +++
 net/dsa/slave.c    | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++---
 4 files changed, 83 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 597875d3f69e..dc357454ae3b 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -130,6 +130,7 @@ struct dsa_switch {
 	 */
 	u32			dsa_port_mask;
 	u32			phys_port_mask;
+	u32			phys_mii_mask;
 	struct mii_bus		*slave_mii_bus;
 	struct net_device	*ports[DSA_MAX_PORTS];
 };
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 6a5bae673037..4dc2a16b72cf 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -144,6 +144,11 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
 		goto out;
 	}
 
+	/* Make the built-in MII bus mask match the number of ports,
+	 * switch drivers can override this later
+	 */
+	ds->phys_mii_mask = ds->phys_port_mask;
+
 	/*
 	 * If the CPU connects to this switch, set the switch tree
 	 * tagging protocol to the preferred tagging format of this
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 218d75d16f6f..d20364ac1574 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -33,6 +33,10 @@ struct dsa_slave_priv {
 	 * to this port.
 	 */
 	struct phy_device	*phy;
+	phy_interface_t		phy_interface;
+	int			old_link;
+	int			old_pause;
+	int			old_duplex;
 };
 
 /* dsa.c */
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 5688c34253e5..03d2894a0f8a 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -12,6 +12,8 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/phy.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
 #include "dsa_priv.h"
 
 /* slave mii_bus handling ***************************************************/
@@ -19,7 +21,7 @@ static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg)
 {
 	struct dsa_switch *ds = bus->priv;
 
-	if (ds->phys_port_mask & (1 << addr))
+	if (ds->phys_mii_mask & (1 << addr))
 		return ds->drv->phy_read(ds, addr, reg);
 
 	return 0xffff;
@@ -29,7 +31,7 @@ static int dsa_slave_phy_write(struct mii_bus *bus, int addr, int reg, u16 val)
 {
 	struct dsa_switch *ds = bus->priv;
 
-	if (ds->phys_port_mask & (1 << addr))
+	if (ds->phys_mii_mask & (1 << addr))
 		return ds->drv->phy_write(ds, addr, reg, val);
 
 	return 0;
@@ -312,7 +314,70 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_do_ioctl		= dsa_slave_ioctl,
 };
 
+static void dsa_slave_adjust_link(struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	unsigned int status_changed = 0;
+
+	if (p->old_link != p->phy->link) {
+		status_changed = 1;
+		p->old_link = p->phy->link;
+	}
+
+	if (p->old_duplex != p->phy->duplex) {
+		status_changed = 1;
+		p->old_duplex = p->phy->duplex;
+	}
+
+	if (p->old_pause != p->phy->pause) {
+		status_changed = 1;
+		p->old_pause = p->phy->pause;
+	}
+
+	if (status_changed)
+		phy_print_status(p->phy);
+}
+
 /* slave device setup *******************************************************/
+static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
+				struct net_device *slave_dev)
+{
+	struct dsa_switch *ds = p->parent;
+	struct dsa_chip_data *cd = ds->pd;
+	struct device_node *phy_dn, *port_dn;
+	int ret;
+
+	port_dn = cd->port_dn[p->port];
+	p->phy_interface = of_get_phy_mode(port_dn);
+
+	phy_dn = of_parse_phandle(port_dn, "phy-handle", 0);
+	if (of_phy_is_fixed_link(port_dn)) {
+		/* In the case of a fixed PHY, the DT node associated
+		 * to the fixed PHY is the Port DT node
+		 */
+		ret = of_phy_register_fixed_link(port_dn);
+		if (ret) {
+			pr_err("failed to register fixed PHY\n");
+			return;
+		}
+		phy_dn = port_dn;
+	}
+
+	if (phy_dn)
+		p->phy = of_phy_connect(slave_dev, phy_dn,
+					dsa_slave_adjust_link, 0,
+					p->phy_interface);
+
+	/* We could not connect to a designated PHY, so use the switch internal
+	 * MDIO bus instead
+	 */
+	if (!p->phy)
+		p->phy = ds->slave_mii_bus->phy_map[p->port];
+	else
+		pr_info("attached PHY at address %d [%s]\n",
+			p->phy->addr, p->phy->drv->name);
+}
+
 struct net_device *
 dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 		 int port, char *name)
@@ -361,7 +426,12 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	p->dev = slave_dev;
 	p->parent = ds;
 	p->port = port;
-	p->phy = ds->slave_mii_bus->phy_map[port];
+
+	p->old_pause = -1;
+	p->old_link = -1;
+	p->old_duplex = -1;
+
+	dsa_slave_phy_setup(p, slave_dev);
 
 	ret = register_netdev(slave_dev);
 	if (ret) {
-- 
cgit v1.2.3


From 5aed85cec29882d1c4b4b2a01cb75a99efdbe4ed Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 27 Aug 2014 17:04:52 -0700
Subject: net: dsa: allow switches to work without tagging

In case switch port tagging is disabled (voluntarily, or the switch just
does not support it), allow us to continue using the defined set of
dsa_device_ops in net/dsa/slave.c.

We introduce dsa_protocol_is_tagged() to check whether we need to
override skb->protocol and go through the DSA-specifif packet_type
function, or if we just go on and receive the SKB through the normal
path.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  6 +++---
 include/net/dsa.h         |  5 +++++
 net/dsa/slave.c           | 19 ++++++++++++++++++-
 3 files changed, 26 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1875dc71422a..429801370d0c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1784,10 +1784,10 @@ void dev_net_set(struct net_device *dev, struct net *net)
 static inline bool netdev_uses_dsa(struct net_device *dev)
 {
 #ifdef CONFIG_NET_DSA
-	return dev->dsa_ptr != NULL;
-#else
-	return false;
+	if (dev->dsa_ptr != NULL)
+		return dsa_uses_tagged_protocol(dev->dsa_ptr);
 #endif
+	return false;
 }
 
 /**
diff --git a/include/net/dsa.h b/include/net/dsa.h
index dc357454ae3b..1035f6452d79 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -198,4 +198,9 @@ static inline void *ds_to_priv(struct dsa_switch *ds)
 	return (void *)(ds + 1);
 }
 
+static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst)
+{
+	return dst->tag_protocol != 0;
+}
+
 #endif
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 03d2894a0f8a..241c2a1684cb 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -181,6 +181,17 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 	return dst->ops->xmit(skb, dev);
 }
 
+static netdev_tx_t dsa_slave_notag_xmit(struct sk_buff *skb,
+					struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+
+	skb->dev = p->parent->dst->master_netdev;
+	dev_queue_xmit(skb);
+
+	return NETDEV_TX_OK;
+}
+
 
 /* ethtool operations *******************************************************/
 static int
@@ -314,6 +325,11 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_do_ioctl		= dsa_slave_ioctl,
 };
 
+static const struct dsa_device_ops notag_netdev_ops = {
+	.xmit	= dsa_slave_notag_xmit,
+	.rcv	= NULL,
+};
+
 static void dsa_slave_adjust_link(struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -415,7 +431,8 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 		break;
 #endif
 	default:
-		BUG();
+		ds->dst->ops = &notag_netdev_ops;
+		break;
 	}
 
 	SET_NETDEV_DEV(slave_dev, parent);
-- 
cgit v1.2.3


From ec9436baedb689668c409cfc8b69eb9573b0d661 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 27 Aug 2014 17:04:53 -0700
Subject: net: dsa: allow drivers to do link adjustment

Whenever libphy determines that the link status of a given PHY/port has
changed, allow to call into the switch driver link adjustment callback
so proper actions can be taken care of by the switch driver upon link
notification.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 7 +++++++
 net/dsa/slave.c   | 4 ++++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 1035f6452d79..2d3835924dd2 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -16,6 +16,7 @@
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/of.h>
+#include <linux/phy.h>
 
 #define DSA_MAX_SWITCHES	4
 #define DSA_MAX_PORTS		12
@@ -181,6 +182,12 @@ struct dsa_switch_driver {
 	 */
 	void	(*poll_link)(struct dsa_switch *ds);
 
+	/*
+	 * Link state adjustment (called from libphy)
+	 */
+	void	(*adjust_link)(struct dsa_switch *ds, int port,
+				struct phy_device *phydev);
+
 	/*
 	 * ethtool hardware statistics.
 	 */
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 241c2a1684cb..398d0663d3dd 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -333,6 +333,7 @@ static const struct dsa_device_ops notag_netdev_ops = {
 static void dsa_slave_adjust_link(struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
 	unsigned int status_changed = 0;
 
 	if (p->old_link != p->phy->link) {
@@ -350,6 +351,9 @@ static void dsa_slave_adjust_link(struct net_device *dev)
 		p->old_pause = p->phy->pause;
 	}
 
+	if (ds->drv->adjust_link && status_changed)
+		ds->drv->adjust_link(ds, p->port, p->phy);
+
 	if (status_changed)
 		phy_print_status(p->phy);
 }
-- 
cgit v1.2.3


From ce31b31c68e7e39f29b1257581fbd08ce3ca5589 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 27 Aug 2014 17:04:54 -0700
Subject: net: dsa: allow updating fixed PHY link information

Allow switch drivers to hook a PHY link update callback to perform
port-specific link work.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  3 +++
 net/dsa/slave.c   | 17 +++++++++++++++++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 2d3835924dd2..2c9563f0b2f4 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -17,6 +17,7 @@
 #include <linux/workqueue.h>
 #include <linux/of.h>
 #include <linux/phy.h>
+#include <linux/phy_fixed.h>
 
 #define DSA_MAX_SWITCHES	4
 #define DSA_MAX_PORTS		12
@@ -187,6 +188,8 @@ struct dsa_switch_driver {
 	 */
 	void	(*adjust_link)(struct dsa_switch *ds, int port,
 				struct phy_device *phydev);
+	void	(*fixed_link_update)(struct dsa_switch *ds, int port,
+				struct fixed_phy_status *st);
 
 	/*
 	 * ethtool hardware statistics.
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 398d0663d3dd..18ff53836fe3 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -358,6 +358,18 @@ static void dsa_slave_adjust_link(struct net_device *dev)
 		phy_print_status(p->phy);
 }
 
+static int dsa_slave_fixed_link_update(struct net_device *dev,
+				       struct fixed_phy_status *status)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->fixed_link_update)
+		ds->drv->fixed_link_update(ds, p->port, status);
+
+	return 0;
+}
+
 /* slave device setup *******************************************************/
 static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 				struct net_device *slave_dev)
@@ -365,6 +377,7 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 	struct dsa_switch *ds = p->parent;
 	struct dsa_chip_data *cd = ds->pd;
 	struct device_node *phy_dn, *port_dn;
+	bool phy_is_fixed = false;
 	int ret;
 
 	port_dn = cd->port_dn[p->port];
@@ -380,6 +393,7 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 			pr_err("failed to register fixed PHY\n");
 			return;
 		}
+		phy_is_fixed = true;
 		phy_dn = port_dn;
 	}
 
@@ -388,6 +402,9 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 					dsa_slave_adjust_link, 0,
 					p->phy_interface);
 
+	if (p->phy && phy_is_fixed)
+		fixed_phy_set_link_update(p->phy, dsa_slave_fixed_link_update);
+
 	/* We could not connect to a designated PHY, so use the switch internal
 	 * MDIO bus instead
 	 */
-- 
cgit v1.2.3


From 5037d532b83d7325a2743dffe82882a64697a8e8 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 27 Aug 2014 17:04:55 -0700
Subject: net: dsa: add Broadcom tag RX/TX handler

Add support for the 4-bytes Broadcom tag that built-in switches such as
the Starfighter 2 might insert when receiving packets, or that we need
to insert while targetting specific switch ports. We use a fake local
EtherType value for this 4-bytes switch tag: ETH_P_BRCMTAG to make sure
we can assign DSA-specific network operations within the DSA drivers.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h  |   5 ++
 net/dsa/Kconfig    |   3 +
 net/dsa/Makefile   |   1 +
 net/dsa/dsa_priv.h |   3 +
 net/dsa/slave.c    |   5 ++
 net/dsa/tag_brcm.c | 173 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 190 insertions(+)
 create mode 100644 net/dsa/tag_brcm.c

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 2c9563f0b2f4..97712927a9d2 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -19,6 +19,11 @@
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
 
+/* Not an official ethertype value, used only internally for DSA
+ * demultiplexing
+ */
+#define ETH_P_BRCMTAG		(ETH_P_XDSA + 1)
+
 #define DSA_MAX_SWITCHES	4
 #define DSA_MAX_PORTS		12
 
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index f5eede1d6cb8..a585fd6352eb 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -12,6 +12,9 @@ config NET_DSA
 if NET_DSA
 
 # tagging formats
+config NET_DSA_TAG_BRCM
+	bool
+
 config NET_DSA_TAG_DSA
 	bool
 
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 7b9fcbbeda5d..da06ed1df620 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_NET_DSA) += dsa_core.o
 dsa_core-y += dsa.o slave.o
 
 # tagging formats
+dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o
 dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
 dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
 dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index d20364ac1574..98afed4d92ba 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -57,5 +57,8 @@ extern const struct dsa_device_ops edsa_netdev_ops;
 /* tag_trailer.c */
 extern const struct dsa_device_ops trailer_netdev_ops;
 
+/* tag_brcm.c */
+extern const struct dsa_device_ops brcm_netdev_ops;
+
 
 #endif
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 18ff53836fe3..7333a4aebb7d 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -450,6 +450,11 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	case htons(ETH_P_TRAILER):
 		ds->dst->ops = &trailer_netdev_ops;
 		break;
+#endif
+#ifdef CONFIG_NET_DSA_TAG_BRCM
+	case htons(ETH_P_BRCMTAG):
+		ds->dst->ops = &brcm_netdev_ops;
+		break;
 #endif
 	default:
 		ds->dst->ops = &notag_netdev_ops;
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
new file mode 100644
index 000000000000..e0b759ec209e
--- /dev/null
+++ b/net/dsa/tag_brcm.c
@@ -0,0 +1,173 @@
+/*
+ * Broadcom tag support
+ *
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include "dsa_priv.h"
+
+/* This tag length is 4 bytes, older ones were 6 bytes, we do not
+ * handle them
+ */
+#define BRCM_TAG_LEN	4
+
+/* Tag is constructed and desconstructed using byte by byte access
+ * because the tag is placed after the MAC Source Address, which does
+ * not make it 4-bytes aligned, so this might cause unaligned accesses
+ * on most systems where this is used.
+ */
+
+/* Ingress and egress opcodes */
+#define BRCM_OPCODE_SHIFT	5
+#define BRCM_OPCODE_MASK	0x7
+
+/* Ingress fields */
+/* 1st byte in the tag */
+#define BRCM_IG_TC_SHIFT	2
+#define BRCM_IG_TC_MASK		0x7
+/* 2nd byte in the tag */
+#define BRCM_IG_TE_MASK		0x3
+#define BRCM_IG_TS_SHIFT	7
+/* 3rd byte in the tag */
+#define BRCM_IG_DSTMAP2_MASK	1
+#define BRCM_IG_DSTMAP1_MASK	0xff
+
+/* Egress fields */
+
+/* 2nd byte in the tag */
+#define BRCM_EG_CID_MASK	0xff
+
+/* 3rd byte in the tag */
+#define BRCM_EG_RC_MASK		0xff
+#define  BRCM_EG_RC_RSVD	(3 << 6)
+#define  BRCM_EG_RC_EXCEPTION	(1 << 5)
+#define  BRCM_EG_RC_PROT_SNOOP	(1 << 4)
+#define  BRCM_EG_RC_PROT_TERM	(1 << 3)
+#define  BRCM_EG_RC_SWITCH	(1 << 2)
+#define  BRCM_EG_RC_MAC_LEARN	(1 << 1)
+#define  BRCM_EG_RC_MIRROR	(1 << 0)
+#define BRCM_EG_TC_SHIFT	5
+#define BRCM_EG_TC_MASK		0x7
+#define BRCM_EG_PID_MASK	0x1f
+
+static netdev_tx_t brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	u8 *brcm_tag;
+
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+
+	if (skb_cow_head(skb, BRCM_TAG_LEN) < 0)
+		goto out_free;
+
+	skb_push(skb, BRCM_TAG_LEN);
+
+	memmove(skb->data, skb->data + BRCM_TAG_LEN, 2 * ETH_ALEN);
+
+	/* Build the tag after the MAC Source Address */
+	brcm_tag = skb->data + 2 * ETH_ALEN;
+
+	/* Set the ingress opcode, traffic class, tag enforcment is
+	 * deprecated
+	 */
+	brcm_tag[0] = (1 << BRCM_OPCODE_SHIFT) |
+			((skb->priority << BRCM_IG_TC_SHIFT) & BRCM_IG_TC_MASK);
+	brcm_tag[1] = 0;
+	brcm_tag[2] = 0;
+	if (p->port == 8)
+		brcm_tag[2] = BRCM_IG_DSTMAP2_MASK;
+	brcm_tag[3] = (1 << p->port) & BRCM_IG_DSTMAP1_MASK;
+
+	/* Queue the SKB for transmission on the parent interface, but
+	 * do not modify its EtherType
+	 */
+	skb->protocol = htons(ETH_P_BRCMTAG);
+	skb->dev = p->parent->dst->master_netdev;
+	dev_queue_xmit(skb);
+
+	return NETDEV_TX_OK;
+
+out_free:
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
+			struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct dsa_switch_tree *dst = dev->dsa_ptr;
+	struct dsa_switch *ds;
+	int source_port;
+	u8 *brcm_tag;
+
+	if (unlikely(dst == NULL))
+		goto out_drop;
+
+	ds = dst->ds[0];
+
+	skb = skb_unshare(skb, GFP_ATOMIC);
+	if (skb == NULL)
+		goto out;
+
+	if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN)))
+		goto out_drop;
+
+	/* skb->data points to the EtherType, the tag is right before it */
+	brcm_tag = skb->data - 2;
+
+	/* The opcode should never be different than 0b000 */
+	if (unlikely((brcm_tag[0] >> BRCM_OPCODE_SHIFT) & BRCM_OPCODE_MASK))
+		goto out_drop;
+
+	/* We should never see a reserved reason code without knowing how to
+	 * handle it
+	 */
+	WARN_ON(brcm_tag[2] & BRCM_EG_RC_RSVD);
+
+	/* Locate which port this is coming from */
+	source_port = brcm_tag[3] & BRCM_EG_PID_MASK;
+
+	/* Validate port against switch setup, either the port is totally */
+	if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL)
+		goto out_drop;
+
+	/* Remove Broadcom tag and update checksum */
+	skb_pull_rcsum(skb, BRCM_TAG_LEN);
+
+	/* Move the Ethernet DA and SA */
+	memmove(skb->data - ETH_HLEN,
+		skb->data - ETH_HLEN - BRCM_TAG_LEN,
+		2 * ETH_ALEN);
+
+	skb_push(skb, ETH_HLEN);
+	skb->pkt_type = PACKET_HOST;
+	skb->dev = ds->ports[source_port];
+	skb->protocol = eth_type_trans(skb, skb->dev);
+
+	skb->dev->stats.rx_packets++;
+	skb->dev->stats.rx_bytes += skb->len;
+
+	netif_receive_skb(skb);
+
+	return 0;
+
+out_drop:
+	kfree_skb(skb);
+out:
+	return 0;
+}
+
+const struct dsa_device_ops brcm_netdev_ops = {
+	.xmit	= brcm_tag_xmit,
+	.rcv	= brcm_tag_rcv,
+};
-- 
cgit v1.2.3


From 97fdaab4699de3a2a91001efef60bb0622de1c53 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 26 Aug 2014 13:15:25 -0700
Subject: net: phy: broadcom: fix PHY_BCM_OUI_4

PHY_BCM_OUI_4 is missing two significant digits that actually make it an
OUI, add those missing bits so it becomes usable again for matching.

Fixes: b560a58c45c6 ("net: phy: add Broadcom BCM7xxx internal PHY driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/brcmphy.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index ee1431d976fa..921f17ca4c26 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -21,7 +21,7 @@
 #define PHY_BCM_OUI_1			0x00206000
 #define PHY_BCM_OUI_2			0x0143bc00
 #define PHY_BCM_OUI_3			0x03625c00
-#define PHY_BCM_OUI_4			0x600d0000
+#define PHY_BCM_OUI_4			0x600d8400
 #define PHY_BCM_OUI_5			0x03625e00
 
 
-- 
cgit v1.2.3


From 11bf2bbd596add62a86a74fc7aedc0b86c6ec154 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 26 Aug 2014 13:15:26 -0700
Subject: net: phy: broadcom: add new Broadcom OUI

Broadcom started to use a new OUI for its 2013 and newer products:
D4-01-29 which translates into 0xae025000 for a 32-bits OUI, add its
definition.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/brcmphy.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 921f17ca4c26..cbcfad36d4c0 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -23,7 +23,7 @@
 #define PHY_BCM_OUI_3			0x03625c00
 #define PHY_BCM_OUI_4			0x600d8400
 #define PHY_BCM_OUI_5			0x03625e00
-
+#define PHY_BCM_OUI_6			0xae025000
 
 #define PHY_BCM_FLAGS_MODE_COPPER	0x00000001
 #define PHY_BCM_FLAGS_MODE_1000BX	0x00000002
-- 
cgit v1.2.3


From 430ad68ffb5fa632a277162e5995cd6f7a39fb78 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 26 Aug 2014 13:15:27 -0700
Subject: net: phy: bcm7xxx: add BCM7250 and BCM7364 PHY entries

Add two new entries to the Broadcom BCM7xxx internal PHY driver for
BCM7250 and BCM7364 chips. Those chips share the usual 28nm process
Gigabit PHY sequence and require the same workarounds so far.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 4 ++++
 include/linux/brcmphy.h   | 2 ++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 948c7086679a..09dd6e1dc6e1 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -335,6 +335,8 @@ static int bcm7xxx_dummy_config_init(struct phy_device *phydev)
 }
 
 static struct phy_driver bcm7xxx_driver[] = {
+	BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"),
+	BCM7XXX_28NM_GPHY(PHY_ID_BCM7364, "Broadcom BCM7364"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7366, "Broadcom BCM7366"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7439, "Broadcom BCM7439"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7445, "Broadcom BCM7445"),
@@ -367,6 +369,8 @@ static struct phy_driver bcm7xxx_driver[] = {
 } };
 
 static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
+	{ PHY_ID_BCM7250, 0xfffffff0, },
+	{ PHY_ID_BCM7364, 0xfffffff0, },
 	{ PHY_ID_BCM7366, 0xfffffff0, },
 	{ PHY_ID_BCM7439, 0xfffffff0, },
 	{ PHY_ID_BCM7445, 0xfffffff0, },
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index cbcfad36d4c0..5bd35cc0d471 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -13,6 +13,8 @@
 #define PHY_ID_BCM5461			0x002060c0
 #define PHY_ID_BCM57780			0x03625d90
 
+#define PHY_ID_BCM7250			0xae025280
+#define PHY_ID_BCM7364			0xae025260
 #define PHY_ID_BCM7366			0x600d8490
 #define PHY_ID_BCM7439			0x600d8480
 #define PHY_ID_BCM7445			0x600d8510
-- 
cgit v1.2.3


From 1f58d9465c568eb47cab939bbc4f30ae51863295 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 8 Aug 2014 13:06:30 +0200
Subject: dma-buf/fence: Fix one more kerneldoc warning

The seqno_fence_init() function's cond argument isn't described in the
kerneldoc comment. Fix that to silence a warning when building DocBook
documentation.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
---
 include/linux/seqno-fence.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h
index 3d6003de4b0d..a1ba6a5ccdd6 100644
--- a/include/linux/seqno-fence.h
+++ b/include/linux/seqno-fence.h
@@ -62,6 +62,7 @@ to_seqno_fence(struct fence *fence)
  * @context: the execution context this fence is a part of
  * @seqno_ofs: the offset within @sync_buf
  * @seqno: the sequence # to signal on
+ * @cond: fence wait condition
  * @ops: the fence_ops for operations on this seqno fence
  *
  * This function initializes a struct seqno_fence with passed parameters,
-- 
cgit v1.2.3


From a8dbfeedfe47a19a4712749eb2444b1d7ea1150e Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 27 Aug 2014 14:31:24 -0700
Subject: regulator: fix kernel-doc warnings in header files

Fix kernel-doc warnings in regulator header files:

Warning(..//include/linux/regulator/machine.h:140): No description found for parameter 'ramp_disable'
Warning(..//include/linux/regulator/driver.h:279): No description found for parameter 'linear_ranges'
Warning(..//include/linux/regulator/driver.h:279): No description found for parameter 'n_linear_ranges'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/regulator/driver.h  | 2 ++
 include/linux/regulator/machine.h | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index bbe03a1924c0..4efa1ed8a2b0 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -218,6 +218,8 @@ enum regulator_type {
  * @linear_min_sel: Minimal selector for starting linear mapping
  * @fixed_uV: Fixed voltage of rails.
  * @ramp_delay: Time to settle down after voltage change (unit: uV/us)
+ * @linear_ranges: A constant table of possible voltage ranges.
+ * @n_linear_ranges: Number of entries in the @linear_ranges table.
  * @volt_table: Voltage mapping table (if table based mapping)
  *
  * @vsel_reg: Register for selector when using regulator_regmap_X_voltage_
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 730e638c5589..0b08d05d470b 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -85,6 +85,7 @@ struct regulator_state {
  *           bootloader then it will be enabled when the constraints are
  *           applied.
  * @apply_uV: Apply the voltage constraint when initialising.
+ * @ramp_disable: Disable ramp delay when initialising or when setting voltage.
  *
  * @input_uV: Input voltage for regulator when supplied by another regulator.
  *
-- 
cgit v1.2.3


From 4ba2968420fa9d0604b6a6a5c61bfa8d0fa84ae0 Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Tue, 26 Aug 2014 19:12:21 -0500
Subject: percpu: Resolve ambiguities in __get_cpu_var/cpumask_var_t

__get_cpu_var can paper over differences in the definitions of
cpumask_var_t and either use the address of the cpumask variable
directly or perform a fetch of the address of the struct cpumask
allocated elsewhere. This is important particularly when using per cpu
cpumask_var_t declarations because in one case we have an offset into
a per cpu area to handle and in the other case we need to fetch a
pointer from the offset.

This patch introduces a new macro

this_cpu_cpumask_var_ptr()

that is defined where cpumask_var_t is defined and performs the proper
actions. All use cases where __get_cpu_var is used with cpumask_var_t
are converted to the use of this_cpu_cpumask_var_ptr().

Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 arch/x86/include/asm/perf_event_p4.h  |  2 +-
 arch/x86/kernel/apic/x2apic_cluster.c |  3 +--
 arch/x86/oprofile/op_model_p4.c       |  2 +-
 include/linux/cpumask.h               | 11 +++++++++++
 kernel/sched/deadline.c               |  2 +-
 kernel/sched/fair.c                   |  2 +-
 kernel/sched/rt.c                     |  2 +-
 7 files changed, 17 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 85e13ccf15c4..d725382c2ae0 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -189,7 +189,7 @@ static inline int p4_ht_thread(int cpu)
 {
 #ifdef CONFIG_SMP
 	if (smp_num_siblings == 2)
-		return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+		return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 6ce600f9bc78..1f5d5f2ffae6 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -42,8 +42,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 	 * We are to modify mask, so we need an own copy
 	 * and be sure it's manipulated with irq off.
 	 */
-	ipi_mask_ptr = __raw_get_cpu_var(ipi_mask);
-	cpumask_copy(ipi_mask_ptr, mask);
+	ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask);
 
 	/*
 	 * The idea is to send one IPI per cluster.
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 98ab13058f89..ad1d91f475ab 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -372,7 +372,7 @@ static unsigned int get_stagger(void)
 {
 #ifdef CONFIG_SMP
 	int cpu = smp_processor_id();
-	return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+	return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 2997af6d2ccd..0a9a6da21e74 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -666,10 +666,19 @@ static inline size_t cpumask_size(void)
  *
  * This code makes NR_CPUS length memcopy and brings to a memory corruption.
  * cpumask_copy() provide safe copy functionality.
+ *
+ * Note that there is another evil here: If you define a cpumask_var_t
+ * as a percpu variable then the way to obtain the address of the cpumask
+ * structure differently influences what this_cpu_* operation needs to be
+ * used. Please use this_cpu_cpumask_var_t in those cases. The direct use
+ * of this_cpu_ptr() or this_cpu_read() will lead to failures when the
+ * other type of cpumask_var_t implementation is configured.
  */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 typedef struct cpumask *cpumask_var_t;
 
+#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x)
+
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
 bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
@@ -681,6 +690,8 @@ void free_bootmem_cpumask_var(cpumask_var_t mask);
 #else
 typedef struct cpumask cpumask_var_t[1];
 
+#define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
+
 static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return true;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 255ce138b652..4a608cfaecbd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1158,7 +1158,7 @@ static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
 static int find_later_rq(struct task_struct *task)
 {
 	struct sched_domain *sd;
-	struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl);
+	struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
 	int this_cpu = smp_processor_id();
 	int best_cpu, cpu = task_cpu(task);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bfa3c86d0d68..197d659c144c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6539,7 +6539,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	struct sched_group *group;
 	struct rq *busiest;
 	unsigned long flags;
-	struct cpumask *cpus = __get_cpu_var(load_balance_mask);
+	struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);
 
 	struct lb_env env = {
 		.sd		= sd,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 5f6edca4fafd..a4c50fce9b90 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1526,7 +1526,7 @@ static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 static int find_lowest_rq(struct task_struct *task)
 {
 	struct sched_domain *sd;
-	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
+	struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
 
-- 
cgit v1.2.3


From d7cdb968081727746c8d2fb31b12ea6d1694888e Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 20 Jun 2014 17:19:06 +0200
Subject: treewide: fix synchronize_rcu() in comments

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/percpu-refcount.h | 2 +-
 net/rds/af_rds.c                | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 3dfbf237cd8f..652fd64cab5e 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -29,7 +29,7 @@
  * calls io_destroy() or the process exits.
  *
  * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it
- * calls percpu_ref_kill(), then hlist_del_rcu() and sychronize_rcu() to remove
+ * calls percpu_ref_kill(), then hlist_del_rcu() and synchronize_rcu() to remove
  * the kioctx from the proccess's list of kioctxs - after that, there can't be
  * any new users of the kioctx (from lookup_ioctx()) and it's then safe to drop
  * the initial ref with percpu_ref_put().
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 424ff622ab5f..10443377fb9d 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -83,7 +83,7 @@ static int rds_release(struct socket *sock)
 
 	/*
 	 * the binding lookup hash uses rcu, we need to
-	 * make sure we sychronize_rcu before we free our
+	 * make sure we synchronize_rcu before we free our
 	 * entry
 	 */
 	rds_remove_bound(rs);
-- 
cgit v1.2.3


From f3ababa8ba2ace6668a24803910577a49dc146dd Mon Sep 17 00:00:00 2001
From: Doug Anderson <dianders@chromium.org>
Date: Fri, 8 Aug 2014 15:29:09 -0700
Subject: pinctrl: Add mux options 3 and 4 for rockchip pinctrl

Newer Rockchip SoCs have more muxing slots.  Add slots 3 and 4 since
the rk3288 table goes all the way up to 4.

Signed-off-by: Doug Anderson <dianders@chromium.org>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt | 6 +++---
 include/dt-bindings/pinctrl/rockchip.h                         | 2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
index 4658b69d4f4d..388b213249fd 100644
--- a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
@@ -2,8 +2,8 @@
 
 The Rockchip Pinmux Controller, enables the IC
 to share one PAD to several functional blocks. The sharing is done by
-multiplexing the PAD input/output signals. For each PAD there are up to
-4 muxing options with option 0 being the use as a GPIO.
+multiplexing the PAD input/output signals. For each PAD there are several
+muxing options with option 0 being the use as a GPIO.
 
 Please refer to pinctrl-bindings.txt in this directory for details of the
 common pinctrl bindings used by client devices, including the meaning of the
@@ -58,7 +58,7 @@ Deprecated properties for gpio sub nodes:
 Required properties for pin configuration node:
   - rockchip,pins: 3 integers array, represents a group of pins mux and config
     setting. The format is rockchip,pins = <PIN_BANK PIN_BANK_IDX MUX &phandle>.
-    The MUX 0 means gpio and MUX 1 to 3 mean the specific device function.
+    The MUX 0 means gpio and MUX 1 to N mean the specific device function.
     The phandle of a node containing the generic pinconfig options
     to use, as described in pinctrl-bindings.txt in this directory.
 
diff --git a/include/dt-bindings/pinctrl/rockchip.h b/include/dt-bindings/pinctrl/rockchip.h
index cd5788be82ce..743e66a95e13 100644
--- a/include/dt-bindings/pinctrl/rockchip.h
+++ b/include/dt-bindings/pinctrl/rockchip.h
@@ -28,5 +28,7 @@
 #define RK_FUNC_GPIO	0
 #define RK_FUNC_1	1
 #define RK_FUNC_2	2
+#define RK_FUNC_3	3
+#define RK_FUNC_4	4
 
 #endif
-- 
cgit v1.2.3


From d37aba521379203b740a2929e6e6f6bd2485f5d7 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 28 Aug 2014 13:54:18 +0200
Subject: ARM: tegra: remove unused tegra_emc.h

The header file include/linux/platform_data/tegra_emc.h does not seem
to be used anywhere. It was orphaned by a7cbe92c "ARM: tegra: remove
tegra EMC scaling driver". Remove it.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Stephen Warren <swarren@nvidia.com>
---
 include/linux/platform_data/tegra_emc.h | 34 ---------------------------------
 1 file changed, 34 deletions(-)
 delete mode 100644 include/linux/platform_data/tegra_emc.h

(limited to 'include')

diff --git a/include/linux/platform_data/tegra_emc.h b/include/linux/platform_data/tegra_emc.h
deleted file mode 100644
index df67505e98f8..000000000000
--- a/include/linux/platform_data/tegra_emc.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- * Copyright (C) 2011 Google, Inc.
- *
- * Author:
- *	Colin Cross <ccross@android.com>
- *	Olof Johansson <olof@lixom.net>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef __TEGRA_EMC_H_
-#define __TEGRA_EMC_H_
-
-#define TEGRA_EMC_NUM_REGS 46
-
-struct tegra_emc_table {
-	unsigned long rate;
-	u32 regs[TEGRA_EMC_NUM_REGS];
-};
-
-struct tegra_emc_pdata {
-	int num_tables;
-	struct tegra_emc_table *tables;
-};
-
-#endif
-- 
cgit v1.2.3


From b792346fa8660a22a06f118cebe47709f507914f Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Thu, 28 Aug 2014 14:07:11 +0300
Subject: ASoC: Remove unused cache_only from struct snd_soc_codec

There are no real users for cache_only in "struct snd_soc_codec" so remove
it and needless debugfs node.

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h  | 1 -
 sound/soc/soc-core.c | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index edbb0d72ab38..ce09302bfd6d 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -792,7 +792,6 @@ struct snd_soc_codec {
 	unsigned int ac97_registered:1; /* Codec has been AC97 registered */
 	unsigned int ac97_created:1; /* Codec has been created by SoC */
 	unsigned int cache_init:1; /* codec cache has been initialized */
-	u32 cache_only;  /* Suppress writes to hardware */
 	u32 cache_sync; /* Cache needs to be synced to hardware */
 
 	/* codec IO */
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 419682693886..1b422c5c36c8 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -311,8 +311,6 @@ static void soc_init_codec_debugfs(struct snd_soc_component *component)
 
 	debugfs_create_bool("cache_sync", 0444, codec->component.debugfs_root,
 			    &codec->cache_sync);
-	debugfs_create_bool("cache_only", 0444, codec->component.debugfs_root,
-			    &codec->cache_only);
 
 	codec->debugfs_reg = debugfs_create_file("codec_reg", 0644,
 						 codec->component.debugfs_root,
-- 
cgit v1.2.3


From 2b8941b962a9f24d61c2b3c2e889928e6cf3d82b Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Wed, 27 Aug 2014 11:17:56 -0400
Subject: NFSD: Update some as-yet unused 4.2 error codes

Recent NFS v4.2 drafts have removed NFS4ERR_METADATA_NOTSUPP and
reassigned the error code to NFS4ERR_UNION_NOTSUPP.

I also add in the NFS4ERR_OFFLOAD_NO_REQS error code.

We're not using any of these yet, so there's no harm done.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfsd.h       | 2 +-
 include/linux/nfs4.h | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 847daf37e566..747f3b95bd11 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -251,7 +251,7 @@ void		nfsd_lockd_shutdown(void);
 #define nfserr_deleg_revoked		cpu_to_be32(NFS4ERR_DELEG_REVOKED)
 #define nfserr_partner_notsupp		cpu_to_be32(NFS4ERR_PARTNER_NOTSUPP)
 #define nfserr_partner_no_auth		cpu_to_be32(NFS4ERR_PARTNER_NO_AUTH)
-#define nfserr_metadata_notsupp		cpu_to_be32(NFS4ERR_METADATA_NOTSUPP)
+#define nfserr_union_notsupp		cpu_to_be32(NFS4ERR_UNION_NOTSUPP)
 #define nfserr_offload_denied		cpu_to_be32(NFS4ERR_OFFLOAD_DENIED)
 #define nfserr_wrong_lfs		cpu_to_be32(NFS4ERR_WRONG_LFS)
 #define nfserr_badlabel		cpu_to_be32(NFS4ERR_BADLABEL)
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index a1e3064a8d99..79b2a0f5c318 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -235,10 +235,11 @@ enum nfsstat4 {
 	/* nfs42 */
 	NFS4ERR_PARTNER_NOTSUPP	= 10088,
 	NFS4ERR_PARTNER_NO_AUTH	= 10089,
-	NFS4ERR_METADATA_NOTSUPP = 10090,
+	NFS4ERR_UNION_NOTSUPP = 10090,
 	NFS4ERR_OFFLOAD_DENIED = 10091,
 	NFS4ERR_WRONG_LFS = 10092,
 	NFS4ERR_BADLABEL = 10093,
+	NFS4ERR_OFFLOAD_NO_REQS = 10094,
 };
 
 static inline bool seqid_mutating_err(u32 err)
-- 
cgit v1.2.3


From db9ee220361de03ee86388f9ea5e529eaad5323c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 27 Aug 2014 18:40:07 -0400
Subject: jbd2: fix descriptor block size handling errors with journal_csum

It turns out that there are some serious problems with the on-disk
format of journal checksum v2.  The foremost is that the function to
calculate descriptor tag size returns sizes that are too big.  This
causes alignment issues on some architectures and is compounded by the
fact that some parts of jbd2 use the structure size (incorrectly) to
determine the presence of a 64bit journal instead of checking the
feature flags.

Therefore, introduce journal checksum v3, which enlarges the
descriptor block tag format to allow for full 32-bit checksums of
journal blocks, fix the journal tag function to return the correct
sizes, and fix the jbd2 recovery code to use feature flags to
determine 64bitness.

Add a few function helpers so we don't have to open-code quite so
many pieces.

Switching to a 16-byte block size was found to increase journal size
overhead by a maximum of 0.1%, to convert a 32-bit journal with no
checksumming to a 32-bit journal with checksum v3 enabled.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reported-by: TR Reardon <thomas_reardon@hotmail.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
---
 fs/ext4/super.c      |  5 +++--
 fs/jbd2/commit.c     | 21 +++++++++++---------
 fs/jbd2/journal.c    | 56 ++++++++++++++++++++++++++++++++++------------------
 fs/jbd2/recovery.c   | 26 +++++++++++++-----------
 fs/jbd2/revoke.c     |  6 +++---
 include/linux/jbd2.h | 30 +++++++++++++++++++++++-----
 6 files changed, 95 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 32b43ad154b9..0b28b36e7915 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3181,9 +3181,9 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
-		/* journal checksum v2 */
+		/* journal checksum v3 */
 		compat = 0;
-		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3;
 	} else {
 		/* journal checksum v1 */
 		compat = JBD2_FEATURE_COMPAT_CHECKSUM;
@@ -3205,6 +3205,7 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 		jbd2_journal_clear_features(sbi->s_journal,
 				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
 				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
+				JBD2_FEATURE_INCOMPAT_CSUM_V3 |
 				JBD2_FEATURE_INCOMPAT_CSUM_V2);
 	}
 
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6fac74349856..b73e0215baa7 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -97,7 +97,7 @@ static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh)
 	struct commit_header *h;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	h = (struct commit_header *)(bh->b_data);
@@ -313,11 +313,11 @@ static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
 	return checksum;
 }
 
-static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
+static void write_tag_block(journal_t *j, journal_block_tag_t *tag,
 				   unsigned long long block)
 {
 	tag->t_blocknr = cpu_to_be32(block & (u32)~0);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT))
 		tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
 }
 
@@ -327,7 +327,7 @@ static void jbd2_descr_block_csum_set(journal_t *j,
 	struct jbd2_journal_block_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
@@ -340,12 +340,13 @@ static void jbd2_descr_block_csum_set(journal_t *j,
 static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 				    struct buffer_head *bh, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	struct page *page = bh->b_page;
 	__u8 *addr;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	seq = cpu_to_be32(sequence);
@@ -355,8 +356,10 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 			     bh->b_size);
 	kunmap_atomic(addr);
 
-	/* We only have space to store the lower 16 bits of the crc32c. */
-	tag->t_checksum = cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		tag3->t_checksum = cpu_to_be32(csum32);
+	else
+		tag->t_checksum = cpu_to_be16(csum32);
 }
 /*
  * jbd2_journal_commit_transaction
@@ -396,7 +399,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	LIST_HEAD(io_bufs);
 	LIST_HEAD(log_bufs);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_block_tail);
 
 	/*
@@ -690,7 +693,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			tag_flag |= JBD2_FLAG_SAME_UUID;
 
 		tag = (journal_block_tag_t *) tagp;
-		write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr);
+		write_tag_block(journal, tag, jh2bh(jh)->b_blocknr);
 		tag->t_flags = cpu_to_be16(tag_flag);
 		jbd2_block_tag_csum_set(journal, tag, wbuf[bufs],
 					commit_transaction->t_tid);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 67b8e303946c..19d74d86d99c 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -124,7 +124,7 @@ EXPORT_SYMBOL(__jbd2_debug);
 /* Checksumming functions */
 static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum_type == JBD2_CRC32C_CHKSUM;
@@ -145,7 +145,7 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
 
 static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum == jbd2_superblock_csum(j, sb);
@@ -153,7 +153,7 @@ static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 
 static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	sb->s_checksum = jbd2_superblock_csum(j, sb);
@@ -1522,21 +1522,29 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
-	if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) &&
-	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal) &&
+	    JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) {
 		/* Can't have checksum v1 and v2 on at the same time! */
 		printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 "
 		       "at the same time!\n");
 		goto out;
 	}
 
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) &&
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
+		/* Can't have checksum v2 and v3 at the same time! */
+		printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 "
+		       "at the same time!\n");
+		goto out;
+	}
+
 	if (!jbd2_verify_csum_type(journal, sb)) {
 		printk(KERN_ERR "JBD2: Unknown checksum type\n");
 		goto out;
 	}
 
 	/* Load the checksum driver */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal)) {
 		journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(journal->j_chksum_driver)) {
 			printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
@@ -1553,7 +1561,7 @@ static int journal_get_superblock(journal_t *journal)
 	}
 
 	/* Precompute checksum seed for all metadata */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
 						   sizeof(sb->s_uuid));
 
@@ -1813,8 +1821,14 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 	if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
 		return 0;
 
-	/* Asking for checksumming v2 and v1?  Only give them v2. */
-	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 &&
+	/* If enabling v2 checksums, turn on v3 instead */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) {
+		incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3;
+	}
+
+	/* Asking for checksumming v3 and v1?  Only give them v3. */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 &&
 	    compat & JBD2_FEATURE_COMPAT_CHECKSUM)
 		compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM;
 
@@ -1823,8 +1837,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 
 	sb = journal->j_superblock;
 
-	/* If enabling v2 checksums, update superblock */
-	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	/* If enabling v3 checksums, update superblock */
+	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
 		sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
 		sb->s_feature_compat &=
 			~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
@@ -1842,8 +1856,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 		}
 
 		/* Precompute checksum seed for all metadata */
-		if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					      JBD2_FEATURE_INCOMPAT_CSUM_V2))
+		if (jbd2_journal_has_csum_v2or3(journal))
 			journal->j_csum_seed = jbd2_chksum(journal, ~0,
 							   sb->s_uuid,
 							   sizeof(sb->s_uuid));
@@ -1852,7 +1865,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 	/* If enabling v1 checksums, downgrade superblock */
 	if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM))
 		sb->s_feature_incompat &=
-			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2);
+			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 |
+				     JBD2_FEATURE_INCOMPAT_CSUM_V3);
 
 	sb->s_feature_compat    |= cpu_to_be32(compat);
 	sb->s_feature_ro_compat |= cpu_to_be32(ro);
@@ -2165,16 +2179,20 @@ int jbd2_journal_blocks_per_page(struct inode *inode)
  */
 size_t journal_tag_bytes(journal_t *journal)
 {
-	journal_block_tag_t tag;
-	size_t x = 0;
+	size_t sz;
+
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return sizeof(journal_block_tag3_t);
+
+	sz = sizeof(journal_block_tag_t);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
-		x += sizeof(tag.t_checksum);
+		sz += sizeof(__u16);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
-		return x + JBD2_TAG_SIZE64;
+		return sz;
 	else
-		return x + JBD2_TAG_SIZE32;
+		return sz - sizeof(__u32);
 }
 
 /*
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 00e9703d7dc6..9b329b55ffe3 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -181,7 +181,7 @@ static int jbd2_descr_block_csum_verify(journal_t *j,
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize -
@@ -205,7 +205,7 @@ static int count_tags(journal_t *journal, struct buffer_head *bh)
 	int			nr = 0, size = journal->j_blocksize;
 	int			tag_bytes = journal_tag_bytes(journal);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		size -= sizeof(struct jbd2_journal_block_tail);
 
 	tagp = &bh->b_data[sizeof(journal_header_t)];
@@ -338,10 +338,11 @@ int jbd2_journal_skip_recovery(journal_t *journal)
 	return err;
 }
 
-static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag)
+static inline unsigned long long read_tag_block(journal_t *journal,
+						journal_block_tag_t *tag)
 {
 	unsigned long long block = be32_to_cpu(tag->t_blocknr);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
 		block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32;
 	return block;
 }
@@ -384,7 +385,7 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	h = buf;
@@ -399,17 +400,21 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
 				      void *buf, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	seq = cpu_to_be32(sequence);
 	csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
 	csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize);
 
-	return tag->t_checksum == cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return tag3->t_checksum == cpu_to_be32(csum32);
+	else
+		return tag->t_checksum == cpu_to_be16(csum32);
 }
 
 static int do_one_pass(journal_t *journal,
@@ -513,8 +518,7 @@ static int do_one_pass(journal_t *journal,
 		switch(blocktype) {
 		case JBD2_DESCRIPTOR_BLOCK:
 			/* Verify checksum first */
-			if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					JBD2_FEATURE_INCOMPAT_CSUM_V2))
+			if (jbd2_journal_has_csum_v2or3(journal))
 				descr_csum_size =
 					sizeof(struct jbd2_journal_block_tail);
 			if (descr_csum_size > 0 &&
@@ -575,7 +579,7 @@ static int do_one_pass(journal_t *journal,
 					unsigned long long blocknr;
 
 					J_ASSERT(obh != NULL);
-					blocknr = read_tag_block(tag_bytes,
+					blocknr = read_tag_block(journal,
 								 tag);
 
 					/* If the block has been
@@ -814,7 +818,7 @@ static int jbd2_revoke_block_csum_verify(journal_t *j,
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize -
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 198c9c10276d..d5e95a175c92 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -91,8 +91,8 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/bio.h>
-#endif
 #include <linux/log2.h>
+#endif
 
 static struct kmem_cache *jbd2_revoke_record_cache;
 static struct kmem_cache *jbd2_revoke_table_cache;
@@ -597,7 +597,7 @@ static void write_one_revoke_record(journal_t *journal,
 	offset = *offsetp;
 
 	/* Do we need to leave space at the end for a checksum? */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_revoke_tail);
 
 	/* Make sure we have a descriptor with space left for the record */
@@ -644,7 +644,7 @@ static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
 	struct jbd2_journal_revoke_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize -
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d5b50a19463c..0dae71e9971c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -159,7 +159,11 @@ typedef struct journal_header_s
  * journal_block_tag (in the descriptor).  The other h_chksum* fields are
  * not used.
  *
- * Checksum v1 and v2 are mutually exclusive features.
+ * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses
+ * journal_block_tag3_t to store a full 32-bit checksum.  Everything else
+ * is the same as v2.
+ *
+ * Checksum v1, v2, and v3 are mutually exclusive features.
  */
 struct commit_header {
 	__be32		h_magic;
@@ -179,6 +183,14 @@ struct commit_header {
  * raw struct shouldn't be used for pointer math or sizeof() - use
  * journal_tag_bytes(journal) instead to compute this.
  */
+typedef struct journal_block_tag3_s
+{
+	__be32		t_blocknr;	/* The on-disk block number */
+	__be32		t_flags;	/* See below */
+	__be32		t_blocknr_high; /* most-significant high 32bits. */
+	__be32		t_checksum;	/* crc32c(uuid+seq+block) */
+} journal_block_tag3_t;
+
 typedef struct journal_block_tag_s
 {
 	__be32		t_blocknr;	/* The on-disk block number */
@@ -187,9 +199,6 @@ typedef struct journal_block_tag_s
 	__be32		t_blocknr_high; /* most-significant high 32bits. */
 } journal_block_tag_t;
 
-#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high))
-#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t))
-
 /* Tail of descriptor block, for checksumming */
 struct jbd2_journal_block_tail {
 	__be32		t_checksum;	/* crc32c(uuid+descr_block) */
@@ -284,6 +293,7 @@ typedef struct journal_superblock_s
 #define JBD2_FEATURE_INCOMPAT_64BIT		0x00000002
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
 #define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
+#define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
 
 /* Features known to this kernel version: */
 #define JBD2_KNOWN_COMPAT_FEATURES	JBD2_FEATURE_COMPAT_CHECKSUM
@@ -291,7 +301,8 @@ typedef struct journal_superblock_s
 #define JBD2_KNOWN_INCOMPAT_FEATURES	(JBD2_FEATURE_INCOMPAT_REVOKE | \
 					JBD2_FEATURE_INCOMPAT_64BIT | \
 					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
-					JBD2_FEATURE_INCOMPAT_CSUM_V2)
+					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
+					JBD2_FEATURE_INCOMPAT_CSUM_V3)
 
 #ifdef __KERNEL__
 
@@ -1296,6 +1307,15 @@ static inline int tid_geq(tid_t x, tid_t y)
 extern int jbd2_journal_blocks_per_page(struct inode *inode);
 extern size_t journal_tag_bytes(journal_t *journal);
 
+static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
+{
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) ||
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return 1;
+
+	return 0;
+}
+
 /*
  * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for
  * transaction control blocks.
-- 
cgit v1.2.3


From abdc08a3a263a20e49534a36291d657bf53dda5b Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Tue, 19 Aug 2014 10:06:09 -0700
Subject: gpio: change gpiochip_request_own_desc() prototype

The current prototype of gpiochip_request_own_desc() requires to obtain
a pointer to a descriptor. This is in contradiction to all other GPIO
request schemes, and imposes an extra step of obtaining a descriptor to
drivers. Most drivers actually cannot even perform that step since the
function that does it (gpichip_get_desc()) is gpiolib-private.

Change gpiochip_request_own_desc() to return a descriptor from a
(chip, hwnum) tuple and update users of this function (currently
gpiolib-acpi only).

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/gpio/driver.txt |  3 ++-
 drivers/gpio/gpiolib-acpi.c   | 20 +++-----------------
 drivers/gpio/gpiolib.c        | 18 ++++++++++++++----
 include/linux/gpio/driver.h   |  3 ++-
 4 files changed, 21 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/Documentation/gpio/driver.txt b/Documentation/gpio/driver.txt
index 18790c237977..23b751a10d7b 100644
--- a/Documentation/gpio/driver.txt
+++ b/Documentation/gpio/driver.txt
@@ -178,7 +178,8 @@ does not help since it pins the module to the kernel forever (it calls
 try_module_get()). A GPIO driver can use the following functions instead
 to request and free descriptors without being pinned to the kernel forever.
 
-	int gpiochip_request_own_desc(struct gpio_desc *desc, const char *label)
+	struct gpio_desc *gpiochip_request_own_desc(struct gpio_desc *desc,
+						    const char *label)
 
 	void gpiochip_free_own_desc(struct gpio_desc *desc)
 
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 84540025aa08..f9103e72e2a4 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -145,14 +145,8 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 	if (!handler)
 		return AE_BAD_PARAMETER;
 
-	desc = gpiochip_get_desc(chip, pin);
+	desc = gpiochip_request_own_desc(chip, pin, "ACPI:Event");
 	if (IS_ERR(desc)) {
-		dev_err(chip->dev, "Failed to get GPIO descriptor\n");
-		return AE_ERROR;
-	}
-
-	ret = gpiochip_request_own_desc(desc, "ACPI:Event");
-	if (ret) {
 		dev_err(chip->dev, "Failed to request GPIO\n");
 		return AE_ERROR;
 	}
@@ -420,22 +414,14 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address,
 			}
 		}
 		if (!found) {
-			int ret;
-
-			desc = gpiochip_get_desc(chip, pin);
+			desc = gpiochip_request_own_desc(chip, pin,
+							 "ACPI:OpRegion");
 			if (IS_ERR(desc)) {
 				status = AE_ERROR;
 				mutex_unlock(&achip->conn_lock);
 				goto out;
 			}
 
-			ret = gpiochip_request_own_desc(desc, "ACPI:OpRegion");
-			if (ret) {
-				status = AE_ERROR;
-				mutex_unlock(&achip->conn_lock);
-				goto out;
-			}
-
 			switch (agpio->io_restriction) {
 			case ACPI_IO_RESTRICT_INPUT:
 				gpiod_direction_input(desc);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 15cc0bb65dda..a5831d6a9b91 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -895,12 +895,22 @@ EXPORT_SYMBOL_GPL(gpiochip_is_requested);
  * allows the GPIO chip module to be unloaded as needed (we assume that the
  * GPIO chip driver handles freeing the GPIOs it has requested).
  */
-int gpiochip_request_own_desc(struct gpio_desc *desc, const char *label)
+struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *chip, u16 hwnum,
+					    const char *label)
 {
-	if (!desc || !desc->chip)
-		return -EINVAL;
+	struct gpio_desc *desc = gpiochip_get_desc(chip, hwnum);
+	int err;
+
+	if (IS_ERR(desc)) {
+		chip_err(chip, "failed to get GPIO descriptor\n");
+		return desc;
+	}
+
+	err = __gpiod_request(desc, label);
+	if (err < 0)
+		return ERR_PTR(err);
 
-	return __gpiod_request(desc, label);
+	return desc;
 }
 EXPORT_SYMBOL_GPL(gpiochip_request_own_desc);
 
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index e78a2373e374..a2de58fffd19 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -166,7 +166,8 @@ int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
 
 #endif /* CONFIG_GPIO_IRQCHIP */
 
-int gpiochip_request_own_desc(struct gpio_desc *desc, const char *label);
+struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *chip, u16 hwnum,
+					    const char *label);
 void gpiochip_free_own_desc(struct gpio_desc *desc);
 
 #else /* CONFIG_GPIOLIB */
-- 
cgit v1.2.3


From 7179569aeb52197fd2a9909ba226c4c9cc0e2e2a Mon Sep 17 00:00:00 2001
From: Heiko Stübner <heiko@sntech.de>
Date: Thu, 28 Aug 2014 12:36:04 -0700
Subject: regulator: core: Add REGULATOR_EVENT_PRE_VOLTAGE_CHANGE (and ABORT)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In some cases we need to know when a regulator is about to be changed.
Add a way for clients to be notified.  Note that for set_voltage() we
don't necessarily know what voltage we'll end up with, so we tell the
client what the range will be so they can prepare.

Signed-off-by: Heiko Stübner <heiko@sntech.de>
Signed-off-by: Doug Anderson <dianders@chromium.org>
Signed-off-by: Mark Brown <broonie+linaro@kernel.org>
---
 drivers/regulator/core.c           | 63 +++++++++++++++++++++++++++++++++-----
 include/linux/regulator/consumer.h | 20 ++++++++++++
 2 files changed, 76 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a3c3785901f5..dabc8e8862c8 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -102,7 +102,7 @@ static int _regulator_disable(struct regulator_dev *rdev);
 static int _regulator_get_voltage(struct regulator_dev *rdev);
 static int _regulator_get_current_limit(struct regulator_dev *rdev);
 static unsigned int _regulator_get_mode(struct regulator_dev *rdev);
-static void _notifier_call_chain(struct regulator_dev *rdev,
+static int _notifier_call_chain(struct regulator_dev *rdev,
 				  unsigned long event, void *data);
 static int _regulator_do_set_voltage(struct regulator_dev *rdev,
 				     int min_uV, int max_uV);
@@ -2369,6 +2369,55 @@ int regulator_is_supported_voltage(struct regulator *regulator,
 }
 EXPORT_SYMBOL_GPL(regulator_is_supported_voltage);
 
+static int _regulator_call_set_voltage(struct regulator_dev *rdev,
+				       int min_uV, int max_uV,
+				       unsigned *selector)
+{
+	struct pre_voltage_change_data data;
+	int ret;
+
+	data.old_uV = _regulator_get_voltage(rdev);
+	data.min_uV = min_uV;
+	data.max_uV = max_uV;
+	ret = _notifier_call_chain(rdev, REGULATOR_EVENT_PRE_VOLTAGE_CHANGE,
+				   &data);
+	if (ret & NOTIFY_STOP_MASK)
+		return -EINVAL;
+
+	ret = rdev->desc->ops->set_voltage(rdev, min_uV, max_uV, selector);
+	if (ret >= 0)
+		return ret;
+
+	_notifier_call_chain(rdev, REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE,
+			     (void *)data.old_uV);
+
+	return ret;
+}
+
+static int _regulator_call_set_voltage_sel(struct regulator_dev *rdev,
+					   int uV, unsigned selector)
+{
+	struct pre_voltage_change_data data;
+	int ret;
+
+	data.old_uV = _regulator_get_voltage(rdev);
+	data.min_uV = uV;
+	data.max_uV = uV;
+	ret = _notifier_call_chain(rdev, REGULATOR_EVENT_PRE_VOLTAGE_CHANGE,
+				   &data);
+	if (ret & NOTIFY_STOP_MASK)
+		return -EINVAL;
+
+	ret = rdev->desc->ops->set_voltage_sel(rdev, selector);
+	if (ret >= 0)
+		return ret;
+
+	_notifier_call_chain(rdev, REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE,
+			     (void *)data.old_uV);
+
+	return ret;
+}
+
 static int _regulator_do_set_voltage(struct regulator_dev *rdev,
 				     int min_uV, int max_uV)
 {
@@ -2396,8 +2445,8 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev,
 	}
 
 	if (rdev->desc->ops->set_voltage) {
-		ret = rdev->desc->ops->set_voltage(rdev, min_uV, max_uV,
-						   &selector);
+		ret = _regulator_call_set_voltage(rdev, min_uV, max_uV,
+						  &selector);
 
 		if (ret >= 0) {
 			if (rdev->desc->ops->list_voltage)
@@ -2432,8 +2481,8 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev,
 				if (old_selector == selector)
 					ret = 0;
 				else
-					ret = rdev->desc->ops->set_voltage_sel(
-								rdev, ret);
+					ret = _regulator_call_set_voltage_sel(
+						rdev, best_val, selector);
 			} else {
 				ret = -EINVAL;
 			}
@@ -3079,11 +3128,11 @@ EXPORT_SYMBOL_GPL(regulator_unregister_notifier);
 /* notify regulator consumers and downstream regulator consumers.
  * Note mutex must be held by caller.
  */
-static void _notifier_call_chain(struct regulator_dev *rdev,
+static int _notifier_call_chain(struct regulator_dev *rdev,
 				  unsigned long event, void *data)
 {
 	/* call rdev chain first */
-	blocking_notifier_call_chain(&rdev->notifier, event, data);
+	return blocking_notifier_call_chain(&rdev->notifier, event, data);
 }
 
 /**
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index f8a8733068a7..d347c805f923 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -93,7 +93,12 @@ struct regmap;
  * OVER_TEMP      Regulator over temp.
  * FORCE_DISABLE  Regulator forcibly shut down by software.
  * VOLTAGE_CHANGE Regulator voltage changed.
+ *                Data passed is old voltage cast to (void *).
  * DISABLE        Regulator was disabled.
+ * PRE_VOLTAGE_CHANGE   Regulator is about to have voltage changed.
+ *                      Data passed is "struct pre_voltage_change_data"
+ * ABORT_VOLTAGE_CHANGE Regulator voltage change failed for some reason.
+ *                      Data passed is old voltage cast to (void *).
  *
  * NOTE: These events can be OR'ed together when passed into handler.
  */
@@ -106,6 +111,21 @@ struct regmap;
 #define REGULATOR_EVENT_FORCE_DISABLE		0x20
 #define REGULATOR_EVENT_VOLTAGE_CHANGE		0x40
 #define REGULATOR_EVENT_DISABLE 		0x80
+#define REGULATOR_EVENT_PRE_VOLTAGE_CHANGE	0x100
+#define REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE	0x200
+
+/**
+ * struct pre_voltage_change_data - Data sent with PRE_VOLTAGE_CHANGE event
+ *
+ * @old_uV: Current voltage before change.
+ * @min_uV: Min voltage we'll change to.
+ * @max_uV: Max voltage we'll change to.
+ */
+struct pre_voltage_change_data {
+	unsigned long old_uV;
+	unsigned long min_uV;
+	unsigned long max_uV;
+};
 
 struct regulator;
 
-- 
cgit v1.2.3


From 0f8a4de3e088797576ac76200b634b802e5c7781 Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Tue, 26 Aug 2014 14:00:37 +0200
Subject: KVM: Unconditionally export KVM_CAP_READONLY_MEM

The idea between capabilities and the KVM_CHECK_EXTENSION ioctl is that
userspace can, at run-time, determine if a feature is supported or not.
This allows KVM to being supporting a new feature with a new kernel
version without any need to update user space.  Unfortunately, since the
definition of KVM_CAP_READONLY_MEM was guarded by #ifdef
__KVM_HAVE_READONLY_MEM, such discovery still required a user space
update.

Therefore, unconditionally export KVM_CAP_READONLY_MEM and change the
in-kernel conditional to rely on __KVM_HAVE_READONLY_MEM.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/uapi/linux/kvm.h | 2 --
 virt/kvm/kvm_main.c      | 2 +-
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index cf3a2ff440e4..90d3edab839c 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -738,9 +738,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_GET_SMMU_INFO 78
 #define KVM_CAP_S390_COW 79
 #define KVM_CAP_PPC_ALLOC_HTAB 80
-#ifdef __KVM_HAVE_READONLY_MEM
 #define KVM_CAP_READONLY_MEM 81
-#endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 #define KVM_CAP_PPC_HTAB_FD 84
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5a0817ee996e..1d03967def40 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -708,7 +708,7 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
-#ifdef KVM_CAP_READONLY_MEM
+#ifdef __KVM_HAVE_READONLY_MEM
 	valid_flags |= KVM_MEM_READONLY;
 #endif
 
-- 
cgit v1.2.3


From 44b5ce73c99c389817be71b9161bceb197d40ecb Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Tue, 26 Aug 2014 14:00:38 +0200
Subject: KVM: Unconditionally export KVM_CAP_USER_NMI

The idea between capabilities and the KVM_CHECK_EXTENSION ioctl is that
userspace can, at run-time, determine if a feature is supported or not.
This allows KVM to being supporting a new feature with a new kernel
version without any need to update user space.  Unfortunately, since the
definition of KVM_CAP_USER_NMI was guarded by #ifdef
__KVM_HAVE_USER_NMI, such discovery still required a user space update.

Therefore, unconditionally export KVM_CAP_USER_NMI and change the
the typo in the comment for the IOCTL number definition as well.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/uapi/linux/kvm.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 90d3edab839c..0695a1e3e332 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -654,9 +654,7 @@ struct kvm_ppc_smmu_info {
 #endif
 /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
-#ifdef __KVM_HAVE_USER_NMI
 #define KVM_CAP_USER_NMI 22
-#endif
 #ifdef __KVM_HAVE_GUEST_DEBUG
 #define KVM_CAP_SET_GUEST_DEBUG 23
 #endif
@@ -1091,7 +1089,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_S390_INITIAL_RESET    _IO(KVMIO,   0x97)
 #define KVM_GET_MP_STATE          _IOR(KVMIO,  0x98, struct kvm_mp_state)
 #define KVM_SET_MP_STATE          _IOW(KVMIO,  0x99, struct kvm_mp_state)
-/* Available with KVM_CAP_NMI */
+/* Available with KVM_CAP_USER_NMI */
 #define KVM_NMI                   _IO(KVMIO,   0x9a)
 /* Available with KVM_CAP_SET_GUEST_DEBUG */
 #define KVM_SET_GUEST_DEBUG       _IOW(KVMIO,  0x9b, struct kvm_guest_debug)
-- 
cgit v1.2.3


From 656473003bc7e056c3bbd4a4d9832dad01e86f76 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 29 Aug 2014 14:01:17 +0200
Subject: KVM: forward declare structs in kvm_types.h

Opaque KVM structs are useful for prototypes in asm/kvm_host.h, to avoid
"'struct foo' declared inside parameter list" warnings (and consequent
breakage due to conflicting types).

Move them from individual files to a generic place in linux/kvm_types.h.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm/include/asm/kvm_host.h     |  7 ++-----
 arch/arm64/include/asm/kvm_host.h   |  6 ++----
 arch/ia64/include/asm/kvm_host.h    |  3 ---
 arch/mips/include/asm/kvm_host.h    |  5 -----
 arch/powerpc/include/asm/kvm_host.h |  5 -----
 arch/s390/include/asm/kvm_host.h    |  5 +++--
 arch/x86/include/asm/kvm_host.h     |  4 ----
 include/linux/kvm_host.h            |  6 ------
 include/linux/kvm_types.h           | 14 ++++++++++++++
 9 files changed, 21 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 6dfb404f6c46..4843397b812c 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -19,6 +19,8 @@
 #ifndef __ARM_KVM_HOST_H__
 #define __ARM_KVM_HOST_H__
 
+#include <linux/types.h>
+#include <linux/kvm_types.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -40,7 +42,6 @@
 
 #include <kvm/arm_vgic.h>
 
-struct kvm_vcpu;
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
 int kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -149,20 +150,17 @@ struct kvm_vcpu_stat {
 	u32 halt_wakeup;
 };
 
-struct kvm_vcpu_init;
 int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 			const struct kvm_vcpu_init *init);
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
-struct kvm_one_reg;
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 u64 kvm_call_hyp(void *hypfn, ...);
 void force_vm_exit(const cpumask_t *mask);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-struct kvm;
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end);
@@ -187,7 +185,6 @@ struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
 
 int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
 unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu);
-struct kvm_one_reg;
 int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e10c45a578e3..766147baae0b 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -22,6 +22,8 @@
 #ifndef __ARM64_KVM_HOST_H__
 #define __ARM64_KVM_HOST_H__
 
+#include <linux/types.h>
+#include <linux/kvm_types.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -41,7 +43,6 @@
 
 #define KVM_VCPU_MAX_FEATURES 3
 
-struct kvm_vcpu;
 int kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_dev_ioctl_check_extension(long ext);
@@ -164,18 +165,15 @@ struct kvm_vcpu_stat {
 	u32 halt_wakeup;
 };
 
-struct kvm_vcpu_init;
 int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 			const struct kvm_vcpu_init *init);
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
-struct kvm_one_reg;
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-struct kvm;
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end);
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index db95f570705f..fccc09d04649 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -234,9 +234,6 @@ struct kvm_vm_data {
 #define KVM_REQ_PTC_G		32
 #define KVM_REQ_RESUME		33
 
-struct kvm;
-struct kvm_vcpu;
-
 struct kvm_mmio_req {
 	uint64_t addr;          /*  physical address		*/
 	uint64_t size;          /*  size in bytes		*/
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 7a3fc67bd7f9..b93bc80ed7e7 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -96,11 +96,6 @@
 #define CAUSEB_DC			27
 #define CAUSEF_DC			(_ULCAST_(1) << 27)
 
-struct kvm;
-struct kvm_run;
-struct kvm_vcpu;
-struct kvm_interrupt;
-
 extern atomic_t kvm_mips_instance;
 extern pfn_t(*kvm_mips_gfn_to_pfn) (struct kvm *kvm, gfn_t gfn);
 extern void (*kvm_mips_release_pfn_clean) (pfn_t pfn);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 98d9dd50d063..0e597283c5c6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -53,7 +53,6 @@
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 
-struct kvm;
 extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 extern int kvm_unmap_hva_range(struct kvm *kvm,
 			       unsigned long start, unsigned long end);
@@ -76,10 +75,6 @@ extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 /* Physical Address Mask - allowed range of real mode RAM access */
 #define KVM_PAM			0x0fffffffffffffffULL
 
-struct kvm;
-struct kvm_run;
-struct kvm_vcpu;
-
 struct lppaca;
 struct slb_shadow;
 struct dtl_entry;
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 773bef7614d8..d71291d3fb6f 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -13,8 +13,11 @@
 
 #ifndef ASM_KVM_HOST_H
 #define ASM_KVM_HOST_H
+
+#include <linux/types.h>
 #include <linux/hrtimer.h>
 #include <linux/interrupt.h>
+#include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
 #include <linux/kvm.h>
 #include <asm/debug.h>
@@ -431,8 +434,6 @@ static inline bool kvm_is_error_hva(unsigned long addr)
 }
 
 #define ASYNC_PF_PER_VCPU	64
-struct kvm_vcpu;
-struct kvm_async_pf;
 struct kvm_arch_async_pf {
 	unsigned long pfault_token;
 };
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ac0f90e26a0b..567fface45f8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -99,10 +99,6 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 
 #define ASYNC_PF_PER_VCPU 64
 
-struct kvm_vcpu;
-struct kvm;
-struct kvm_async_pf;
-
 enum kvm_reg {
 	VCPU_REGS_RAX = 0,
 	VCPU_REGS_RCX = 1,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ebd723676633..e1cb915a1096 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -140,8 +140,6 @@ static inline bool is_error_page(struct page *page)
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
 
-struct kvm;
-struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
 extern spinlock_t kvm_lock;
@@ -325,8 +323,6 @@ struct kvm_kernel_irq_routing_entry {
 	struct hlist_node link;
 };
 
-struct kvm_irq_routing_table;
-
 #ifndef KVM_PRIVATE_MEM_SLOTS
 #define KVM_PRIVATE_MEM_SLOTS 0
 #endif
@@ -1036,8 +1032,6 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 
 extern bool kvm_rebooting;
 
-struct kvm_device_ops;
-
 struct kvm_device {
 	struct kvm_device_ops *ops;
 	struct kvm *kvm;
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index b0bcce0ddc95..b606bb689a3e 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -17,6 +17,20 @@
 #ifndef __KVM_TYPES_H__
 #define __KVM_TYPES_H__
 
+struct kvm;
+struct kvm_async_pf;
+struct kvm_device_ops;
+struct kvm_interrupt;
+struct kvm_irq_routing_table;
+struct kvm_memory_slot;
+struct kvm_one_reg;
+struct kvm_run;
+struct kvm_userspace_memory_region;
+struct kvm_vcpu;
+struct kvm_vcpu_init;
+
+enum kvm_mr_change;
+
 #include <asm/types.h>
 
 /*
-- 
cgit v1.2.3


From 13a34e067eab24fec882e1834fbf2cc31911d474 Mon Sep 17 00:00:00 2001
From: Radim Krčmář <rkrcmar@redhat.com>
Date: Thu, 28 Aug 2014 15:13:03 +0200
Subject: KVM: remove garbage arg to *hardware_{en,dis}able
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the beggining was on_each_cpu(), which required an unused argument to
kvm_arch_ops.hardware_{en,dis}able, but this was soon forgotten.

Remove unnecessary arguments that stem from this.

Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm/include/asm/kvm_host.h     |  2 +-
 arch/arm/kvm/arm.c                  |  2 +-
 arch/arm64/include/asm/kvm_host.h   |  2 +-
 arch/ia64/kvm/kvm-ia64.c            |  4 ++--
 arch/mips/include/asm/kvm_host.h    |  2 +-
 arch/mips/kvm/mips.c                |  2 +-
 arch/powerpc/include/asm/kvm_host.h |  2 +-
 arch/powerpc/kvm/powerpc.c          |  2 +-
 arch/s390/include/asm/kvm_host.h    |  2 +-
 arch/s390/kvm/kvm-s390.c            |  2 +-
 arch/x86/include/asm/kvm_host.h     |  4 ++--
 arch/x86/kvm/svm.c                  |  4 ++--
 arch/x86/kvm/vmx.c                  |  4 ++--
 arch/x86/kvm/x86.c                  | 12 ++++++------
 include/linux/kvm_host.h            |  4 ++--
 virt/kvm/kvm_main.c                 |  4 ++--
 16 files changed, 27 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index aea259e9431f..032a8538318a 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -230,7 +230,7 @@ static inline void vgic_arch_setup(const struct vgic_params *vgic)
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 132bb0d9c5ad..005a7b5fd0aa 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -87,7 +87,7 @@ struct kvm_vcpu __percpu **kvm_get_running_vcpus(void)
 	return &kvm_arm_running_vcpu;
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	return 0;
 }
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index b5045e3e05f8..be9970a59497 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -242,7 +242,7 @@ static inline void vgic_arch_setup(const struct vgic_params *vgic)
 	}
 }
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 5e14dcaf844e..ec6b9acb6bea 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -125,7 +125,7 @@ long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler)
 
 static  DEFINE_SPINLOCK(vp_lock);
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	long  status;
 	long  tmp_base;
@@ -160,7 +160,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
 {
 
 	long status;
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 0b24d6622ec1..f2c249796ea8 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -762,7 +762,7 @@ extern int kvm_mips_trans_mtc0(uint32_t inst, uint32_t *opc,
 extern void kvm_mips_dump_stats(struct kvm_vcpu *vcpu);
 extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm);
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 0ec7490d70bd..e3b21e51ff7e 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -77,7 +77,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	return 0;
 }
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 237cc0cc80a2..604000882352 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -682,7 +682,7 @@ struct kvm_vcpu_arch {
 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 72c3fc085207..da505237a664 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -384,7 +384,7 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 }
 EXPORT_SYMBOL_GPL(kvmppc_ld);
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	return 0;
 }
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index f6dd90684b97..a76a124dff48 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -452,7 +452,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 extern char sie_exit;
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_check_processor_compat(void *rtn) {}
 static inline void kvm_arch_exit(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b8fe1ae777db..628e992eeded 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -100,7 +100,7 @@ int test_vfacility(unsigned long nr)
 }
 
 /* Section: not file related */
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	/* every s390 is virtualization enabled ;-) */
 	return 0;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 567fface45f8..73e4149eda33 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -661,8 +661,8 @@ struct msr_data {
 struct kvm_x86_ops {
 	int (*cpu_has_kvm_support)(void);          /* __init */
 	int (*disabled_by_bios)(void);             /* __init */
-	int (*hardware_enable)(void *dummy);
-	void (*hardware_disable)(void *dummy);
+	int (*hardware_enable)(void);
+	void (*hardware_disable)(void);
 	void (*check_processor_compatibility)(void *rtn);
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 7cd230e55118..8ef704037370 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -622,7 +622,7 @@ static int has_svm(void)
 	return 1;
 }
 
-static void svm_hardware_disable(void *garbage)
+static void svm_hardware_disable(void)
 {
 	/* Make sure we clean up behind us */
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
@@ -633,7 +633,7 @@ static void svm_hardware_disable(void *garbage)
 	amd_pmu_disable_virt();
 }
 
-static int svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void)
 {
 
 	struct svm_cpu_data *sd;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d70550d0bcff..671ca5edc709 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2728,7 +2728,7 @@ static void kvm_cpu_vmxon(u64 addr)
 			: "memory", "cc");
 }
 
-static int hardware_enable(void *garbage)
+static int hardware_enable(void)
 {
 	int cpu = raw_smp_processor_id();
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2792,7 +2792,7 @@ static void kvm_cpu_vmxoff(void)
 	asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
 }
 
-static void hardware_disable(void *garbage)
+static void hardware_disable(void)
 {
 	if (vmm_exclusive) {
 		vmclear_local_loaded_vmcss();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c10408ef9ab1..a375dfc42f6a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -246,7 +246,7 @@ void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 }
 EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
 
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -6959,7 +6959,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
 	kvm_rip_write(vcpu, 0);
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
@@ -6970,7 +6970,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	bool stable, backwards_tsc = false;
 
 	kvm_shared_msr_cpu_online();
-	ret = kvm_x86_ops->hardware_enable(garbage);
+	ret = kvm_x86_ops->hardware_enable();
 	if (ret != 0)
 		return ret;
 
@@ -7051,10 +7051,10 @@ int kvm_arch_hardware_enable(void *garbage)
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
 {
-	kvm_x86_ops->hardware_disable(garbage);
-	drop_user_return_notifiers(garbage);
+	kvm_x86_ops->hardware_disable();
+	drop_user_return_notifiers();
 }
 
 int kvm_arch_hardware_setup(void)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e1cb915a1096..e098dce179df 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -630,8 +630,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
-int kvm_arch_hardware_enable(void *garbage);
-void kvm_arch_hardware_disable(void *garbage);
+int kvm_arch_hardware_enable(void);
+void kvm_arch_hardware_disable(void);
 int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1d03967def40..7176929a4cda 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2669,7 +2669,7 @@ static void hardware_enable_nolock(void *junk)
 
 	cpumask_set_cpu(cpu, cpus_hardware_enabled);
 
-	r = kvm_arch_hardware_enable(NULL);
+	r = kvm_arch_hardware_enable();
 
 	if (r) {
 		cpumask_clear_cpu(cpu, cpus_hardware_enabled);
@@ -2694,7 +2694,7 @@ static void hardware_disable_nolock(void *junk)
 	if (!cpumask_test_cpu(cpu, cpus_hardware_enabled))
 		return;
 	cpumask_clear_cpu(cpu, cpus_hardware_enabled);
-	kvm_arch_hardware_disable(NULL);
+	kvm_arch_hardware_disable();
 }
 
 static void hardware_disable(void)
-- 
cgit v1.2.3


From bfcfd44cce2774f19daeb59fb4e43fc9aa80e7b8 Mon Sep 17 00:00:00 2001
From: Filipe Brandenburger <filbranden@google.com>
Date: Fri, 29 Aug 2014 15:18:51 -0700
Subject: xattr: fix check for simultaneous glibc header inclusion

The guard was introduced in commit ea1a8217b06b ("xattr: guard against
simultaneous glibc header inclusion") but it is using #ifdef to check
for a define that is either set to 1 or 0.  Fix it to use #if instead.

* Without this patch:

  $ { echo "#include <sys/xattr.h>"; echo "#include <linux/xattr.h>"; } | gcc -E -Iinclude/uapi - >/dev/null
  include/uapi/linux/xattr.h:19:0: warning: "XATTR_CREATE" redefined [enabled by default]
   #define XATTR_CREATE 0x1 /* set value, fail if attr already exists */
   ^
  /usr/include/x86_64-linux-gnu/sys/xattr.h:32:0: note: this is the location of the previous definition
   #define XATTR_CREATE XATTR_CREATE
   ^

* With this patch:

  $ { echo "#include <sys/xattr.h>"; echo "#include <linux/xattr.h>"; } | gcc -E -Iinclude/uapi - >/dev/null
  (no warnings)

Signed-off-by: Filipe Brandenburger <filbranden@google.com>
Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Cc: Allan McRae <allan@archlinux.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/xattr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h
index c38355c1f3c9..1590c49cae57 100644
--- a/include/uapi/linux/xattr.h
+++ b/include/uapi/linux/xattr.h
@@ -13,7 +13,7 @@
 #ifndef _UAPI_LINUX_XATTR_H
 #define _UAPI_LINUX_XATTR_H
 
-#ifdef __UAPI_DEF_XATTR
+#if __UAPI_DEF_XATTR
 #define __USE_KERNEL_XATTR_DEFS
 
 #define XATTR_CREATE	0x1	/* set value, fail if attr already exists */
-- 
cgit v1.2.3


From 10c51b56232d24f150e39884a9e749fd99cbc60c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Wed, 27 Aug 2014 11:11:27 +0200
Subject: net: add skb_get_tx_queue() helper

Replace occurences of skb_get_queue_mapping() and follow-up
netdev_get_tx_queue() with an actual helper function.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 6 ++++++
 net/core/netpoll.c        | 2 +-
 net/core/pktgen.c         | 4 +---
 net/packet/af_packet.c    | 4 +---
 net/sched/sch_generic.c   | 6 ++++--
 5 files changed, 13 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 429801370d0c..dfc1d8b8bd0f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1747,6 +1747,12 @@ struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
 	return &dev->_tx[index];
 }
 
+static inline struct netdev_queue *skb_get_tx_queue(const struct net_device *dev,
+						    const struct sk_buff *skb)
+{
+	return netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+}
+
 static inline void netdev_for_each_tx_queue(struct net_device *dev,
 					    void (*f)(struct net_device *,
 						      struct netdev_queue *,
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index a5ad06828d67..12b1df976562 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -115,7 +115,7 @@ static void queue_process(struct work_struct *work)
 			continue;
 		}
 
-		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+		txq = skb_get_tx_queue(dev, skb);
 
 		local_irq_save(flags);
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 83e2b4b19eb7..d81b540096c3 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3286,7 +3286,6 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 {
 	struct net_device *odev = pkt_dev->odev;
 	struct netdev_queue *txq;
-	u16 queue_map;
 	int ret;
 
 	/* If device is offline, then don't send */
@@ -3324,8 +3323,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 	if (pkt_dev->delay && pkt_dev->last_ok)
 		spin(pkt_dev, pkt_dev->next_tx);
 
-	queue_map = skb_get_queue_mapping(pkt_dev->skb);
-	txq = netdev_get_tx_queue(odev, queue_map);
+	txq = skb_get_tx_queue(odev, pkt_dev->skb);
 
 	local_bh_disable();
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 0dfa990d4eaa..b7a7f5a721bd 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -243,7 +243,6 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	netdev_features_t features;
 	struct netdev_queue *txq;
 	int ret = NETDEV_TX_BUSY;
-	u16 queue_map;
 
 	if (unlikely(!netif_running(dev) ||
 		     !netif_carrier_ok(dev)))
@@ -254,8 +253,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	    __skb_linearize(skb))
 		goto drop;
 
-	queue_map = skb_get_queue_mapping(skb);
-	txq = netdev_get_tx_queue(dev, queue_map);
+	txq = skb_get_tx_queue(dev, skb);
 
 	local_bh_disable();
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index fc04fe93c2da..05b3f5d104af 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -63,7 +63,7 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 
 	if (unlikely(skb)) {
 		/* check the reason of requeuing without tx lock first */
-		txq = netdev_get_tx_queue(txq->dev, skb_get_queue_mapping(skb));
+		txq = skb_get_tx_queue(txq->dev, skb);
 		if (!netif_xmit_frozen_or_stopped(txq)) {
 			q->gso_skb = NULL;
 			q->q.qlen--;
@@ -183,10 +183,12 @@ static inline int qdisc_restart(struct Qdisc *q)
 	skb = dequeue_skb(q);
 	if (unlikely(!skb))
 		return 0;
+
 	WARN_ON_ONCE(skb_dst_is_noref(skb));
+
 	root_lock = qdisc_lock(q);
 	dev = qdisc_dev(q);
-	txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+	txq = skb_get_tx_queue(dev, skb);
 
 	return sch_direct_xmit(skb, q, dev, txq, root_lock);
 }
-- 
cgit v1.2.3


From b95089d00c04712a9d4655d5c638930ac24b7bd3 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Wed, 27 Aug 2014 16:47:48 +0300
Subject: net/mlx4: Move the tunnel steering helper function to mlx4_core

Move the function which we use to set VXLAN DMFS (flow-steering) rules
from mlx4_en to mlx4_core. This refactoring will allow the mlx4_ib driver
to call the helper for the use case of user-space RAW Ethernet QPs, such
that they can serve VXLAN traffic too.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 31 ++-------------------
 drivers/net/ethernet/mellanox/mlx4/mcg.c       | 38 ++++++++++++++++++++++++++
 include/linux/mlx4/device.h                    |  3 ++
 3 files changed, 43 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index bb536aa613f4..abddcf8c40aa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -474,39 +474,12 @@ static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, unsigned char *ad
 				    int qpn, u64 *reg_id)
 {
 	int err;
-	struct mlx4_spec_list spec_eth_outer = { {NULL} };
-	struct mlx4_spec_list spec_vxlan     = { {NULL} };
-	struct mlx4_spec_list spec_eth_inner = { {NULL} };
-
-	struct mlx4_net_trans_rule rule = {
-		.queue_mode = MLX4_NET_TRANS_Q_FIFO,
-		.exclusive = 0,
-		.allow_loopback = 1,
-		.promisc_mode = MLX4_FS_REGULAR,
-		.priority = MLX4_DOMAIN_NIC,
-	};
-
-	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
 
 	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return 0; /* do nothing */
 
-	rule.port = priv->port;
-	rule.qpn = qpn;
-	INIT_LIST_HEAD(&rule.list);
-
-	spec_eth_outer.id = MLX4_NET_TRANS_RULE_ID_ETH;
-	memcpy(spec_eth_outer.eth.dst_mac, addr, ETH_ALEN);
-	memcpy(spec_eth_outer.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
-
-	spec_vxlan.id = MLX4_NET_TRANS_RULE_ID_VXLAN;    /* any vxlan header */
-	spec_eth_inner.id = MLX4_NET_TRANS_RULE_ID_ETH;	 /* any inner eth header */
-
-	list_add_tail(&spec_eth_outer.list, &rule.list);
-	list_add_tail(&spec_vxlan.list,     &rule.list);
-	list_add_tail(&spec_eth_inner.list, &rule.list);
-
-	err = mlx4_flow_attach(priv->mdev->dev, &rule, reg_id);
+	err = mlx4_tunnel_steer_add(priv->mdev->dev, addr, priv->port, qpn,
+				    MLX4_DOMAIN_NIC, reg_id);
 	if (err) {
 		en_err(priv, "failed to add vxlan steering rule, err %d\n", err);
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index d80e7a6fac74..ca0f98c95105 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1020,6 +1020,44 @@ int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id)
 }
 EXPORT_SYMBOL_GPL(mlx4_flow_detach);
 
+int mlx4_tunnel_steer_add(struct mlx4_dev *dev, unsigned char *addr,
+			  int port, int qpn, u16 prio, u64 *reg_id)
+{
+	int err;
+	struct mlx4_spec_list spec_eth_outer = { {NULL} };
+	struct mlx4_spec_list spec_vxlan     = { {NULL} };
+	struct mlx4_spec_list spec_eth_inner = { {NULL} };
+
+	struct mlx4_net_trans_rule rule = {
+		.queue_mode = MLX4_NET_TRANS_Q_FIFO,
+		.exclusive = 0,
+		.allow_loopback = 1,
+		.promisc_mode = MLX4_FS_REGULAR,
+	};
+
+	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
+
+	rule.port = port;
+	rule.qpn = qpn;
+	rule.priority = prio;
+	INIT_LIST_HEAD(&rule.list);
+
+	spec_eth_outer.id = MLX4_NET_TRANS_RULE_ID_ETH;
+	memcpy(spec_eth_outer.eth.dst_mac, addr, ETH_ALEN);
+	memcpy(spec_eth_outer.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
+
+	spec_vxlan.id = MLX4_NET_TRANS_RULE_ID_VXLAN;    /* any vxlan header */
+	spec_eth_inner.id = MLX4_NET_TRANS_RULE_ID_ETH;	 /* any inner eth header */
+
+	list_add_tail(&spec_eth_outer.list, &rule.list);
+	list_add_tail(&spec_vxlan.list,     &rule.list);
+	list_add_tail(&spec_eth_inner.list, &rule.list);
+
+	err = mlx4_flow_attach(dev, &rule, reg_id);
+	return err;
+}
+EXPORT_SYMBOL(mlx4_tunnel_steer_add);
+
 int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
 				      u32 max_range_qpn)
 {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 071f6b234604..511c6e0d21a9 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1196,6 +1196,9 @@ int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev,
 				  enum mlx4_net_trans_rule_id id);
 int mlx4_hw_rule_sz(struct mlx4_dev *dev, enum mlx4_net_trans_rule_id id);
 
+int mlx4_tunnel_steer_add(struct mlx4_dev *dev, unsigned char *addr,
+			  int port, int qpn, u16 prio, u64 *reg_id);
+
 void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port,
 			  int i, int val);
 
-- 
cgit v1.2.3


From 38ab1fa981d543e1b00f4ffbce4ddb480cd2effe Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Thu, 28 Aug 2014 15:28:26 +0200
Subject: net: sctp: fix ABI mismatch through sctp_assoc_to_state helper

Since SCTP day 1, that is, 19b55a2af145 ("Initial commit") from lksctp
tree, the official <netinet/sctp.h> header carries a copy of enum
sctp_sstat_state that looks like (compared to the current in-kernel
enumeration):

  User definition:                     Kernel definition:

  enum sctp_sstat_state {              typedef enum {
    SCTP_EMPTY             = 0,          <removed>
    SCTP_CLOSED            = 1,          SCTP_STATE_CLOSED            = 0,
    SCTP_COOKIE_WAIT       = 2,          SCTP_STATE_COOKIE_WAIT       = 1,
    SCTP_COOKIE_ECHOED     = 3,          SCTP_STATE_COOKIE_ECHOED     = 2,
    SCTP_ESTABLISHED       = 4,          SCTP_STATE_ESTABLISHED       = 3,
    SCTP_SHUTDOWN_PENDING  = 5,          SCTP_STATE_SHUTDOWN_PENDING  = 4,
    SCTP_SHUTDOWN_SENT     = 6,          SCTP_STATE_SHUTDOWN_SENT     = 5,
    SCTP_SHUTDOWN_RECEIVED = 7,          SCTP_STATE_SHUTDOWN_RECEIVED = 6,
    SCTP_SHUTDOWN_ACK_SENT = 8,          SCTP_STATE_SHUTDOWN_ACK_SENT = 7,
  };                                   } sctp_state_t;

This header was later on also placed into the uapi, so that user space
programs can compile without having <netinet/sctp.h>, but the shipped
with <linux/sctp.h> instead.

While RFC6458 under 8.2.1.Association Status (SCTP_STATUS) says that
sstat_state can range from SCTP_CLOSED to SCTP_SHUTDOWN_ACK_SENT, we
nevertheless have a what it appears to be dummy SCTP_EMPTY state from
the very early days.

While it seems to do just nothing, commit 0b8f9e25b0aa ("sctp: remove
completely unsed EMPTY state") did the right thing and removed this dead
code. That however, causes an off-by-one when the user asks the SCTP
stack via SCTP_STATUS API and checks for the current socket state thus
yielding possibly undefined behaviour in applications as they expect
the kernel to tell the right thing.

The enumeration had to be changed however as based on the current socket
state, we access a function pointer lookup-table through this. Therefore,
I think the best way to deal with this is just to add a helper function
sctp_assoc_to_state() to encapsulate the off-by-one quirk.

Reported-by: Tristan Su <sooqing@gmail.com>
Fixes: 0b8f9e25b0aa ("sctp: remove completely unsed EMPTY state")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 13 +++++++++++++
 net/sctp/socket.c       |  2 +-
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index f6e7397e799d..9fbd856e6713 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -320,6 +320,19 @@ static inline sctp_assoc_t sctp_assoc2id(const struct sctp_association *asoc)
 	return asoc ? asoc->assoc_id : 0;
 }
 
+static inline enum sctp_sstat_state
+sctp_assoc_to_state(const struct sctp_association *asoc)
+{
+	/* SCTP's uapi always had SCTP_EMPTY(=0) as a dummy state, but we
+	 * got rid of it in kernel space. Therefore SCTP_CLOSED et al
+	 * start at =1 in user space, but actually as =0 in kernel space.
+	 * Now that we can not break user space and SCTP_EMPTY is exposed
+	 * there, we need to fix it up with an ugly offset not to break
+	 * applications. :(
+	 */
+	return asoc->state + 1;
+}
+
 /* Look up the association by its id.  */
 struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id);
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index eb71d49e7653..634a2abb5f3a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4243,7 +4243,7 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len,
 	transport = asoc->peer.primary_path;
 
 	status.sstat_assoc_id = sctp_assoc2id(asoc);
-	status.sstat_state = asoc->state;
+	status.sstat_state = sctp_assoc_to_state(asoc);
 	status.sstat_rwnd =  asoc->peer.rwnd;
 	status.sstat_unackdata = asoc->unack_data;
 
-- 
cgit v1.2.3


From 18fe8db5f2b53e4ac67b47048f24f50c57a2a759 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 28 Aug 2014 13:44:31 +0200
Subject: include/linux/cycx_x25.h: Remove unused header

The header file include/linux/cycx_x25.h does not seem to be used
anywhere. It was orphaned by 6fcdf4facb "wanrouter: delete now
orphaned header content, files/drivers". Remove it.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cycx_x25.h | 125 -----------------------------------------------
 1 file changed, 125 deletions(-)
 delete mode 100644 include/linux/cycx_x25.h

(limited to 'include')

diff --git a/include/linux/cycx_x25.h b/include/linux/cycx_x25.h
deleted file mode 100644
index 362bf19d6cf1..000000000000
--- a/include/linux/cycx_x25.h
+++ /dev/null
@@ -1,125 +0,0 @@
-#ifndef	_CYCX_X25_H
-#define	_CYCX_X25_H
-/*
-* cycx_x25.h	Cyclom X.25 firmware API definitions.
-*
-* Author:	Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-*
-* Copyright:	(c) 1998-2003 Arnaldo Carvalho de Melo
-*
-* Based on sdla_x25.h by Gene Kozin <74604.152@compuserve.com>
-*
-*		This program is free software; you can redistribute it and/or
-*		modify it under the terms of the GNU General Public License
-*		as published by the Free Software Foundation; either version
-*		2 of the License, or (at your option) any later version.
-* ============================================================================
-* 2000/04/02	acme		dprintk and cycx_debug
-* 1999/01/03	acme		judicious use of data types
-* 1999/01/02	acme		#define X25_ACK_N3	0x4411
-* 1998/12/28	acme		cleanup: lot'o'things removed
-*					 commands listed,
-*					 TX25Cmd & TX25Config structs
-*					 typedef'ed
-*/
-#ifndef PACKED
-#define PACKED __attribute__((packed))
-#endif 
-
-/* X.25 shared memory layout. */
-#define	X25_MBOX_OFFS	0x300	/* general mailbox block */
-#define	X25_RXMBOX_OFFS	0x340	/* receive mailbox */
-
-/* Debug */
-#define dprintk(level, format, a...) if (cycx_debug >= level) printk(format, ##a)
-
-extern unsigned int cycx_debug;
-
-/* Data Structures */
-/* X.25 Command Block. */
-struct cycx_x25_cmd {
-	u16 command;
-	u16 link;	/* values: 0 or 1 */
-	u16 len;	/* values: 0 thru 0x205 (517) */
-	u32 buf;
-} PACKED;
-
-/* Defines for the 'command' field. */
-#define X25_CONNECT_REQUEST             0x4401
-#define X25_CONNECT_RESPONSE            0x4402
-#define X25_DISCONNECT_REQUEST          0x4403
-#define X25_DISCONNECT_RESPONSE         0x4404
-#define X25_DATA_REQUEST                0x4405
-#define X25_ACK_TO_VC			0x4406
-#define X25_INTERRUPT_RESPONSE          0x4407
-#define X25_CONFIG                      0x4408
-#define X25_CONNECT_INDICATION          0x4409
-#define X25_CONNECT_CONFIRM             0x440A
-#define X25_DISCONNECT_INDICATION       0x440B
-#define X25_DISCONNECT_CONFIRM          0x440C
-#define X25_DATA_INDICATION             0x440E
-#define X25_INTERRUPT_INDICATION        0x440F
-#define X25_ACK_FROM_VC			0x4410
-#define X25_ACK_N3			0x4411
-#define X25_CONNECT_COLLISION           0x4413
-#define X25_N3WIN                       0x4414
-#define X25_LINE_ON                     0x4415
-#define X25_LINE_OFF                    0x4416
-#define X25_RESET_REQUEST               0x4417
-#define X25_LOG                         0x4500
-#define X25_STATISTIC                   0x4600
-#define X25_TRACE                       0x4700
-#define X25_N2TRACEXC                   0x4702
-#define X25_N3TRACEXC                   0x4703
-
-/**
- *	struct cycx_x25_config - cyclom2x x25 firmware configuration
- *	@link - link number
- *	@speed - line speed
- *	@clock - internal/external
- *	@n2 - # of level 2 retransm.(values: 1 thru FF)
- *	@n2win - level 2 window (values: 1 thru 7)
- *	@n3win - level 3 window (values: 1 thru 7)
- *	@nvc - # of logical channels (values: 1 thru 64)
- *	@pktlen - level 3 packet length - log base 2 of size
- *	@locaddr - my address
- *	@remaddr - remote address
- *	@t1 - time, in seconds
- *	@t2 - time, in seconds
- *	@t21 - time, in seconds
- *	@npvc - # of permanent virt. circuits (1 thru nvc)
- *	@t23 - time, in seconds
- *	@flags - see dosx25.doc, in portuguese, for details
- */
-struct cycx_x25_config {
-	u8  link;
-	u8  speed;
-	u8  clock;
-	u8  n2;
-	u8  n2win;
-	u8  n3win;
-	u8  nvc;
-	u8  pktlen;
-	u8  locaddr;
-	u8  remaddr;
-	u16 t1;
-	u16 t2;
-	u8  t21;
-	u8  npvc;
-	u8  t23;
-	u8  flags;
-} PACKED;
-
-struct cycx_x25_stats {
-	u16 rx_crc_errors;
-	u16 rx_over_errors;
-	u16 n2_tx_frames;
-	u16 n2_rx_frames;
-	u16 tx_timeouts;
-	u16 rx_timeouts;
-	u16 n3_tx_packets;
-	u16 n3_rx_packets;
-	u16 tx_aborts;
-	u16 rx_aborts;
-} PACKED;
-#endif	/* _CYCX_X25_H */
-- 
cgit v1.2.3


From fbd74659d4513816a6249b0db491e8d831803520 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 28 Aug 2014 13:44:32 +0200
Subject: include/linux/i82593.h: Remove unused header

The header file include/linux/i82593.h does not seem to be used
anywhere. It was orphaned by 8a594170 "drivers/net: delete intel
i825xx based znet notebook driver". Remove it.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/i82593.h | 229 -------------------------------------------------
 1 file changed, 229 deletions(-)
 delete mode 100644 include/linux/i82593.h

(limited to 'include')

diff --git a/include/linux/i82593.h b/include/linux/i82593.h
deleted file mode 100644
index afac5c7a323d..000000000000
--- a/include/linux/i82593.h
+++ /dev/null
@@ -1,229 +0,0 @@
-/*
- * Definitions for Intel 82593 CSMA/CD Core LAN Controller
- * The definitions are taken from the 1992 users manual with Intel
- * order number 297125-001.
- *
- * /usr/src/pc/RCS/i82593.h,v 1.1 1996/07/17 15:23:12 root Exp
- *
- * Copyright 1994, Anders Klemets <klemets@it.kth.se>
- *
- * HISTORY
- * i82593.h,v
- * Revision 1.4  2005/11/4  09:15:00  baroniunas
- * Modified copyright with permission of author as follows:
- *
- *   "If I82539.H is the only file with my copyright statement
- *    that is included in the Source Forge project, then you have
- *    my approval to change the copyright statement to be a GPL
- *    license, in the way you proposed on October 10."
- *
- * Revision 1.1  1996/07/17 15:23:12  root
- * Initial revision
- *
- * Revision 1.3  1995/04/05  15:13:58  adj
- * Initial alpha release
- *
- * Revision 1.2  1994/06/16  23:57:31  klemets
- * Mirrored all the fields in the configuration block.
- *
- * Revision 1.1  1994/06/02  20:25:34  klemets
- * Initial revision
- *
- *
- */
-#ifndef	_I82593_H
-#define	_I82593_H
-
-/* Intel 82593 CSMA/CD Core LAN Controller */
-
-/* Port 0 Command Register definitions */
-
-/* Execution operations */
-#define OP0_NOP			0	/* CHNL = 0 */
-#define OP0_SWIT_TO_PORT_1	0	/* CHNL = 1 */
-#define OP0_IA_SETUP		1
-#define OP0_CONFIGURE		2
-#define OP0_MC_SETUP		3
-#define OP0_TRANSMIT		4
-#define OP0_TDR			5
-#define OP0_DUMP		6
-#define OP0_DIAGNOSE		7
-#define OP0_TRANSMIT_NO_CRC	9
-#define OP0_RETRANSMIT		12
-#define OP0_ABORT		13
-/* Reception operations */
-#define OP0_RCV_ENABLE		8
-#define OP0_RCV_DISABLE		10
-#define OP0_STOP_RCV		11
-/* Status pointer control operations */
-#define OP0_FIX_PTR		15	/* CHNL = 1 */
-#define OP0_RLS_PTR		15	/* CHNL = 0 */
-#define OP0_RESET		14
-
-#define CR0_CHNL		(1 << 4)	/* 0=Channel 0, 1=Channel 1 */
-#define CR0_STATUS_0		0x00
-#define CR0_STATUS_1		0x20
-#define CR0_STATUS_2		0x40
-#define CR0_STATUS_3		0x60
-#define CR0_INT_ACK		(1 << 7)	/* 0=No ack, 1=acknowledge */
-
-/* Port 0 Status Register definitions */
-
-#define SR0_NO_RESULT		0		/* dummy */
-#define SR0_EVENT_MASK		0x0f
-#define SR0_IA_SETUP_DONE	1
-#define SR0_CONFIGURE_DONE	2
-#define SR0_MC_SETUP_DONE	3
-#define SR0_TRANSMIT_DONE	4
-#define SR0_TDR_DONE		5
-#define SR0_DUMP_DONE		6
-#define SR0_DIAGNOSE_PASSED	7
-#define SR0_TRANSMIT_NO_CRC_DONE 9
-#define SR0_RETRANSMIT_DONE	12
-#define SR0_EXECUTION_ABORTED	13
-#define SR0_END_OF_FRAME	8
-#define SR0_RECEPTION_ABORTED	10
-#define SR0_DIAGNOSE_FAILED	15
-#define SR0_STOP_REG_HIT	11
-
-#define SR0_CHNL		(1 << 4)
-#define SR0_EXECUTION		(1 << 5)
-#define SR0_RECEPTION		(1 << 6)
-#define SR0_INTERRUPT		(1 << 7)
-#define SR0_BOTH_RX_TX		(SR0_EXECUTION | SR0_RECEPTION)
-
-#define SR3_EXEC_STATE_MASK	0x03
-#define SR3_EXEC_IDLE		0
-#define SR3_TX_ABORT_IN_PROGRESS 1
-#define SR3_EXEC_ACTIVE		2
-#define SR3_ABORT_IN_PROGRESS	3
-#define SR3_EXEC_CHNL		(1 << 2)
-#define SR3_STP_ON_NO_RSRC	(1 << 3)
-#define SR3_RCVING_NO_RSRC	(1 << 4)
-#define SR3_RCV_STATE_MASK	0x60
-#define SR3_RCV_IDLE		0x00
-#define SR3_RCV_READY		0x20
-#define SR3_RCV_ACTIVE		0x40
-#define SR3_RCV_STOP_IN_PROG	0x60
-#define SR3_RCV_CHNL		(1 << 7)
-
-/* Port 1 Command Register definitions */
-
-#define OP1_NOP			0
-#define OP1_SWIT_TO_PORT_0	1
-#define OP1_INT_DISABLE		2
-#define OP1_INT_ENABLE		3
-#define OP1_SET_TS		5
-#define OP1_RST_TS		7
-#define OP1_POWER_DOWN		8
-#define OP1_RESET_RING_MNGMT	11
-#define OP1_RESET		14
-#define OP1_SEL_RST		15
-
-#define CR1_STATUS_4		0x00
-#define CR1_STATUS_5		0x20
-#define CR1_STATUS_6		0x40
-#define CR1_STOP_REG_UPDATE	(1 << 7)
-
-/* Receive frame status bits */
-
-#define	RX_RCLD			(1 << 0)
-#define RX_IA_MATCH		(1 << 1)
-#define	RX_NO_AD_MATCH		(1 << 2)
-#define RX_NO_SFD		(1 << 3)
-#define RX_SRT_FRM		(1 << 7)
-#define RX_OVRRUN		(1 << 8)
-#define RX_ALG_ERR		(1 << 10)
-#define RX_CRC_ERR		(1 << 11)
-#define RX_LEN_ERR		(1 << 12)
-#define RX_RCV_OK		(1 << 13)
-#define RX_TYP_LEN		(1 << 15)
-
-/* Transmit status bits */
-
-#define TX_NCOL_MASK		0x0f
-#define TX_FRTL			(1 << 4)
-#define TX_MAX_COL		(1 << 5)
-#define TX_HRT_BEAT		(1 << 6)
-#define TX_DEFER		(1 << 7)
-#define TX_UND_RUN		(1 << 8)
-#define TX_LOST_CTS		(1 << 9)
-#define TX_LOST_CRS		(1 << 10)
-#define TX_LTCOL		(1 << 11)
-#define TX_OK			(1 << 13)
-#define TX_COLL			(1 << 15)
-
-struct i82593_conf_block {
-  u_char fifo_limit : 4,
-  	 forgnesi   : 1,
-  	 fifo_32    : 1,
-  	 d6mod      : 1,
-  	 throttle_enb : 1;
-  u_char throttle   : 6,
-	 cntrxint   : 1,
-	 contin	    : 1;
-  u_char addr_len   : 3,
-  	 acloc 	    : 1,
- 	 preamb_len : 2,
-  	 loopback   : 2;
-  u_char lin_prio   : 3,
-	 tbofstop   : 1,
-	 exp_prio   : 3,
-	 bof_met    : 1;
-  u_char	    : 4,
-	 ifrm_spc   : 4;
-  u_char	    : 5,
-	 slottim_low : 3;
-  u_char slottim_hi : 3,
-		    : 1,
-	 max_retr   : 4;
-  u_char prmisc     : 1,
-	 bc_dis     : 1,
-  		    : 1,
-	 crs_1	    : 1,
-	 nocrc_ins  : 1,
-	 crc_1632   : 1,
-  	 	    : 1,
-  	 crs_cdt    : 1;
-  u_char cs_filter  : 3,
-	 crs_src    : 1,
-	 cd_filter  : 3,
-		    : 1;
-  u_char	    : 2,
-  	 min_fr_len : 6;
-  u_char lng_typ    : 1,
-	 lng_fld    : 1,
-	 rxcrc_xf   : 1,
-	 artx	    : 1,
-	 sarec	    : 1,
-	 tx_jabber  : 1,	/* why is this called max_len in the manual? */
-	 hash_1	    : 1,
-  	 lbpkpol    : 1;
-  u_char	    : 6,
-  	 fdx	    : 1,
-  	  	    : 1;
-  u_char dummy_6    : 6,	/* supposed to be ones */
-  	 mult_ia    : 1,
-  	 dis_bof    : 1;
-  u_char dummy_1    : 1,	/* supposed to be one */
-	 tx_ifs_retrig : 2,
-	 mc_all     : 1,
-	 rcv_mon    : 2,
-	 frag_acpt  : 1,
-  	 tstrttrs   : 1;
-  u_char fretx	    : 1,
-	 runt_eop   : 1,
-	 hw_sw_pin  : 1,
-	 big_endn   : 1,
-	 syncrqs    : 1,
-	 sttlen     : 1,
-	 tx_eop     : 1,
-  	 rx_eop	    : 1;
-  u_char rbuf_size  : 5,
-	 rcvstop    : 1,
-  	 	    : 2;
-};
-
-#define I82593_MAX_MULTICAST_ADDRESSES	128	/* Hardware hashed filter */
-
-#endif /* _I82593_H */
-- 
cgit v1.2.3


From 6fb7c3778f0fba0bad099c30e834c413c4f8bcb5 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 28 Aug 2014 13:44:33 +0200
Subject: include/linux/phonedev.h: Remove unused header

The header file include/linux/phonedev.h does not seem to be used
anywhere. It was orphaned by 7326446c "Staging: remove telephony
drivers". Remove it.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phonedev.h | 25 -------------------------
 1 file changed, 25 deletions(-)
 delete mode 100644 include/linux/phonedev.h

(limited to 'include')

diff --git a/include/linux/phonedev.h b/include/linux/phonedev.h
deleted file mode 100644
index 4269de99e320..000000000000
--- a/include/linux/phonedev.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __LINUX_PHONEDEV_H
-#define __LINUX_PHONEDEV_H
-
-#include <linux/types.h>
-
-#ifdef __KERNEL__
-
-#include <linux/poll.h>
-
-struct phone_device {
-	struct phone_device *next;
-	const struct file_operations *f_op;
-	int (*open) (struct phone_device *, struct file *);
-	int board;		/* Device private index */
-	int minor;
-};
-
-extern int phonedev_init(void);
-#define PHONE_MAJOR	100
-extern int phone_register_device(struct phone_device *, int unit);
-#define PHONE_UNIT_ANY	-1
-extern void phone_unregister_device(struct phone_device *);
-
-#endif
-#endif
-- 
cgit v1.2.3


From 918bbc4ffdb84e9d2696315e427a6c43de65bc01 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 28 Aug 2014 13:44:34 +0200
Subject: include/rxrpc/types.h: Remove unused header

The header file include/rxrpc/types.h does not seem to be used
anywhere. It was orphaned by 63b6be55 "[AF_RXRPC]: Delete the old
RxRPC code.". Remove it.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/rxrpc/types.h | 41 -----------------------------------------
 1 file changed, 41 deletions(-)
 delete mode 100644 include/rxrpc/types.h

(limited to 'include')

diff --git a/include/rxrpc/types.h b/include/rxrpc/types.h
deleted file mode 100644
index 30d48f6da228..000000000000
--- a/include/rxrpc/types.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* types.h: Rx types
- *
- * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifndef _LINUX_RXRPC_TYPES_H
-#define _LINUX_RXRPC_TYPES_H
-
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/socket.h>
-#include <linux/in.h>
-#include <linux/spinlock.h>
-#include <linux/atomic.h>
-
-typedef uint32_t	rxrpc_seq_t;	/* Rx message sequence number */
-typedef uint32_t	rxrpc_serial_t;	/* Rx message serial number */
-typedef __be32	rxrpc_seq_net_t; /* on-the-wire Rx message sequence number */
-typedef __be32	rxrpc_serial_net_t; /* on-the-wire Rx message serial number */
-
-struct rxrpc_call;
-struct rxrpc_connection;
-struct rxrpc_header;
-struct rxrpc_message;
-struct rxrpc_operation;
-struct rxrpc_peer;
-struct rxrpc_service;
-typedef struct rxrpc_timer rxrpc_timer_t;
-struct rxrpc_transport;
-
-typedef void (*rxrpc_call_attn_func_t)(struct rxrpc_call *call);
-typedef void (*rxrpc_call_error_func_t)(struct rxrpc_call *call);
-typedef void (*rxrpc_call_aemap_func_t)(struct rxrpc_call *call);
-
-#endif /* _LINUX_RXRPC_TYPES_H */
-- 
cgit v1.2.3


From de20fe8e2cc3c4ca13fdb529e6720d9d199333fe Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Wed, 27 Aug 2014 21:26:35 -0700
Subject: net: Allocate a new 16 bits for flags in skbuff

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b69b7b512c06..3c9574c80933 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -598,6 +598,10 @@ struct sk_buff {
 		__u32		reserved_tailroom;
 	};
 
+	kmemcheck_bitfield_begin(flags3);
+	/* 16 bit hole */
+	kmemcheck_bitfield_end(flags3);
+
 	__be16			inner_protocol;
 	__u16			inner_transport_header;
 	__u16			inner_network_header;
-- 
cgit v1.2.3


From 77cffe23c1f88835f6bd7b47bfa0c060c2969828 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Wed, 27 Aug 2014 21:26:46 -0700
Subject: net: Clarification of CHECKSUM_UNNECESSARY

This patch:
 - Clarifies the specific requirements of devices returning
   CHECKSUM_UNNECESSARY (comments in skbuff.h).
 - Adds csum_level field to skbuff. This is used to express how
   many checksums are covered by CHECKSUM_UNNECESSARY (stores n - 1).
   This replaces the overloading of skb->encapsulation, that field is
   is now only used to indicate inner headers are valid.
 - Change __skb_checksum_validate_needed to "consume" each checksum
   as indicated by csum_level as layers of the the packet are parsed.
 - Remove skb_pop_rcv_encapsulation, no longer needed in the new
   csum_level model.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c    |  2 --
 include/linux/skbuff.h | 74 ++++++++++++++++++++++++++++++++++----------------
 net/ipv4/gre_demux.c   |  1 -
 3 files changed, 51 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index beb377b2d4b7..67527f3d3be2 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1158,8 +1158,6 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	if (!vs)
 		goto drop;
 
-	skb_pop_rcv_encapsulation(skb);
-
 	vs->rcv(vs, skb, vxh->vx_vni);
 	return 0;
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3c9574c80933..c93b5859a772 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -47,11 +47,29 @@
  *
  *   The hardware you're dealing with doesn't calculate the full checksum
  *   (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums
- *   for specific protocols e.g. TCP/UDP/SCTP, then, for such packets it will
- *   set CHECKSUM_UNNECESSARY if their checksums are okay. skb->csum is still
- *   undefined in this case though. It is a bad option, but, unfortunately,
- *   nowadays most vendors do this. Apparently with the secret goal to sell
- *   you new devices, when you will add new protocol to your host, f.e. IPv6 8)
+ *   for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY
+ *   if their checksums are okay. skb->csum is still undefined in this case
+ *   though. It is a bad option, but, unfortunately, nowadays most vendors do
+ *   this. Apparently with the secret goal to sell you new devices, when you
+ *   will add new protocol to your host, f.e. IPv6 8)
+ *
+ *   CHECKSUM_UNNECESSARY is applicable to following protocols:
+ *     TCP: IPv6 and IPv4.
+ *     UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a
+ *       zero UDP checksum for either IPv4 or IPv6, the networking stack
+ *       may perform further validation in this case.
+ *     GRE: only if the checksum is present in the header.
+ *     SCTP: indicates the CRC in SCTP header has been validated.
+ *
+ *   skb->csum_level indicates the number of consecutive checksums found in
+ *   the packet minus one that have been verified as CHECKSUM_UNNECESSARY.
+ *   For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet
+ *   and a device is able to verify the checksums for UDP (possibly zero),
+ *   GRE (checksum flag is set), and TCP-- skb->csum_level would be set to
+ *   two. If the device were only able to verify the UDP checksum and not
+ *   GRE, either because it doesn't support GRE checksum of because GRE
+ *   checksum is bad, skb->csum_level would be set to zero (TCP checksum is
+ *   not considered in this case).
  *
  * CHECKSUM_COMPLETE:
  *
@@ -112,6 +130,9 @@
 #define CHECKSUM_COMPLETE	2
 #define CHECKSUM_PARTIAL	3
 
+/* Maximum value in skb->csum_level */
+#define SKB_MAX_CSUM_LEVEL	3
+
 #define SKB_DATA_ALIGN(X)	ALIGN(X, SMP_CACHE_BYTES)
 #define SKB_WITH_OVERHEAD(X)	\
 	((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
@@ -571,11 +592,7 @@ struct sk_buff {
 	__u8			wifi_acked:1;
 	__u8			no_fcs:1;
 	__u8			head_frag:1;
-	/* Encapsulation protocol and NIC drivers should use
-	 * this flag to indicate to each other if the skb contains
-	 * encapsulated packet or not and maybe use the inner packet
-	 * headers if needed
-	 */
+	/* Indicates the inner headers are valid in the skbuff. */
 	__u8			encapsulation:1;
 	__u8			encap_hdr_csum:1;
 	__u8			csum_valid:1;
@@ -599,7 +616,8 @@ struct sk_buff {
 	};
 
 	kmemcheck_bitfield_begin(flags3);
-	/* 16 bit hole */
+	__u8			csum_level:2;
+	/* 14 bit hole */
 	kmemcheck_bitfield_end(flags3);
 
 	__be16			inner_protocol;
@@ -1866,18 +1884,6 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
 	return pskb_may_pull(skb, skb_network_offset(skb) + len);
 }
 
-static inline void skb_pop_rcv_encapsulation(struct sk_buff *skb)
-{
-	/* Only continue with checksum unnecessary if device indicated
-	 * it is valid across encapsulation (skb->encapsulation was set).
-	 */
-	if (skb->ip_summed == CHECKSUM_UNNECESSARY && !skb->encapsulation)
-		skb->ip_summed = CHECKSUM_NONE;
-
-	skb->encapsulation = 0;
-	skb->csum_valid = 0;
-}
-
 /*
  * CPUs often take a performance hit when accessing unaligned memory
  * locations. The actual performance hit varies, it can be small if the
@@ -2798,6 +2804,27 @@ static inline __sum16 skb_checksum_complete(struct sk_buff *skb)
 	       0 : __skb_checksum_complete(skb);
 }
 
+static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb)
+{
+	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+		if (skb->csum_level == 0)
+			skb->ip_summed = CHECKSUM_NONE;
+		else
+			skb->csum_level--;
+	}
+}
+
+static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb)
+{
+	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+		if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
+			skb->csum_level++;
+	} else if (skb->ip_summed == CHECKSUM_NONE) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->csum_level = 0;
+	}
+}
+
 /* Check if we need to perform checksum complete validation.
  *
  * Returns true if checksum complete is needed, false otherwise
@@ -2809,6 +2836,7 @@ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb,
 {
 	if (skb_csum_unnecessary(skb) || (zero_okay && !check)) {
 		skb->csum_valid = 1;
+		__skb_decr_checksum_unnecessary(skb);
 		return false;
 	}
 
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 7c1a8ff974dd..0485bf7f8f03 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -125,7 +125,6 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			*csum_err = true;
 			return -EINVAL;
 		}
-		skb_pop_rcv_encapsulation(skb);
 		options++;
 	}
 
-- 
cgit v1.2.3


From 662880f4420340aad4f9a62a349c6c9d4faa1a5d Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Wed, 27 Aug 2014 21:26:56 -0700
Subject: net: Allow GRO to use and set levels of checksum unnecessary

Allow GRO path to "consume" checksums provided in CHECKSUM_UNNECESSARY
and to report new checksums verfied for use in fallback to normal
path.

Change GRO checksum path to track csum_level using a csum_cnt field
in NAPI_GRO_CB. On GRO initialization, if ip_summed is
CHECKSUM_UNNECESSARY set NAPI_GRO_CB(skb)->csum_cnt to
skb->csum_level + 1. For each checksum verified, decrement
NAPI_GRO_CB(skb)->csum_cnt while its greater than zero. If a checksum
is verfied and NAPI_GRO_CB(skb)->csum_cnt == 0, we have verified a
deeper checksum than originally indicated in skbuf so increment
csum_level (or initialize to CHECKSUM_UNNECESSARY if ip_summed is
CHECKSUM_NONE or CHECKSUM_COMPLETE).

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 26 ++++++++++++--------------
 net/core/dev.c            | 24 ++++++++++++++++--------
 net/ipv4/gre_offload.c    |  7 ++-----
 net/ipv4/udp_offload.c    |  5 +++--
 4 files changed, 33 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dfc1d8b8bd0f..456eb1fe51e8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1883,8 +1883,8 @@ struct napi_gro_cb {
 	/* GRO checksum is valid */
 	u8	csum_valid:1;
 
-	/* Number encapsulation layers crossed */
-	u8	encapsulation;
+	/* Number of checksums via CHECKSUM_UNNECESSARY */
+	u8	csum_cnt:3;
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
@@ -2179,8 +2179,7 @@ static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb,
 						      __sum16 check)
 {
 	return (skb->ip_summed != CHECKSUM_PARTIAL &&
-		(skb->ip_summed != CHECKSUM_UNNECESSARY ||
-		 (NAPI_GRO_CB(skb)->encapsulation > skb->encapsulation)) &&
+		NAPI_GRO_CB(skb)->csum_cnt == 0 &&
 		(!zero_okay || check));
 }
 
@@ -2196,18 +2195,17 @@ static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb,
 	return __skb_gro_checksum_complete(skb);
 }
 
-/* Update skb for CHECKSUM_UNNECESSARY when we verified a top level
- * checksum or an encapsulated one during GRO. This saves work
- * if we fallback to normal path with the packet.
- */
 static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb)
 {
-	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-		if (NAPI_GRO_CB(skb)->encapsulation)
-			skb->encapsulation = 1;
-	} else if (skb->ip_summed != CHECKSUM_PARTIAL) {
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		skb->encapsulation = 0;
+	if (NAPI_GRO_CB(skb)->csum_cnt > 0) {
+		/* Consume a checksum from CHECKSUM_UNNECESSARY */
+		NAPI_GRO_CB(skb)->csum_cnt--;
+	} else {
+		/* Update skb for CHECKSUM_UNNECESSARY and csum_level when we
+		 * verified a new top level checksum or an encapsulated one
+		 * during GRO. This saves work if we fallback to normal path.
+		 */
+		__skb_incr_checksum_unnecessary(skb);
 	}
 }
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 26d296c2447c..a6077ef56345 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3962,13 +3962,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 
 	gro_list_prepare(napi, skb);
 
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		NAPI_GRO_CB(skb)->csum = skb->csum;
-		NAPI_GRO_CB(skb)->csum_valid = 1;
-	} else {
-		NAPI_GRO_CB(skb)->csum_valid = 0;
-	}
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
 		if (ptype->type != type || !ptype->callbacks.gro_receive)
@@ -3980,7 +3973,22 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->udp_mark = 0;
-		NAPI_GRO_CB(skb)->encapsulation = 0;
+
+		/* Setup for GRO checksum validation */
+		switch (skb->ip_summed) {
+		case CHECKSUM_COMPLETE:
+			NAPI_GRO_CB(skb)->csum = skb->csum;
+			NAPI_GRO_CB(skb)->csum_valid = 1;
+			NAPI_GRO_CB(skb)->csum_cnt = 0;
+			break;
+		case CHECKSUM_UNNECESSARY:
+			NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1;
+			NAPI_GRO_CB(skb)->csum_valid = 0;
+			break;
+		default:
+			NAPI_GRO_CB(skb)->csum_cnt = 0;
+			NAPI_GRO_CB(skb)->csum_valid = 0;
+		}
 
 		pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
 		break;
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index d1bd16937d93..a4d7965fb880 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -172,12 +172,9 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 	}
 
 	/* Don't bother verifying checksum if we're going to flush anyway. */
-	if (greh->flags & GRE_CSUM) {
-		if (!NAPI_GRO_CB(skb)->flush &&
-		    skb_gro_checksum_simple_validate(skb))
+	if ((greh->flags & GRE_CSUM) && !NAPI_GRO_CB(skb)->flush &&
+	    skb_gro_checksum_simple_validate(skb))
 			goto out_unlock;
-		NAPI_GRO_CB(skb)->encapsulation++;
-	}
 
 	flush = 0;
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 8ed460e3753c..a6adff98382a 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -238,12 +238,13 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 	int flush = 1;
 
 	if (NAPI_GRO_CB(skb)->udp_mark ||
-	    (!skb->encapsulation && !NAPI_GRO_CB(skb)->csum_valid))
+	    (skb->ip_summed != CHECKSUM_PARTIAL &&
+	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
+	     !NAPI_GRO_CB(skb)->csum_valid))
 		goto out;
 
 	/* mark that this skb passed once through the udp gro layer */
 	NAPI_GRO_CB(skb)->udp_mark = 1;
-	NAPI_GRO_CB(skb)->encapsulation++;
 
 	rcu_read_lock();
 	uo_priv = rcu_dereference(udp_offload_base);
-- 
cgit v1.2.3


From dd7cfd641228abb2669d8d047d5ec377b1835900 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Date: Tue, 21 Jan 2014 13:07:31 +0100
Subject: drm/ttm: kill fence_lock

No users are left, kill it off! :D
Conversion to the reservation api is next on the list, after
that the functionality can be restored with rcu.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
---
 drivers/gpu/drm/nouveau/nouveau_bo.c      | 25 ++++-------
 drivers/gpu/drm/nouveau/nouveau_display.c |  6 +--
 drivers/gpu/drm/nouveau/nouveau_gem.c     | 16 +------
 drivers/gpu/drm/qxl/qxl_cmd.c             |  2 -
 drivers/gpu/drm/qxl/qxl_fence.c           |  4 --
 drivers/gpu/drm/qxl/qxl_object.h          |  2 -
 drivers/gpu/drm/qxl/qxl_release.c         |  2 -
 drivers/gpu/drm/radeon/radeon_display.c   |  7 +--
 drivers/gpu/drm/radeon/radeon_object.c    |  2 -
 drivers/gpu/drm/ttm/ttm_bo.c              | 75 ++++++++-----------------------
 drivers/gpu/drm/ttm/ttm_bo_util.c         |  5 ---
 drivers/gpu/drm/ttm/ttm_bo_vm.c           |  3 --
 drivers/gpu/drm/ttm/ttm_execbuf_util.c    |  2 -
 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c    |  4 --
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c  | 16 +++----
 include/drm/ttm/ttm_bo_api.h              |  5 +--
 include/drm/ttm/ttm_bo_driver.h           |  3 --
 17 files changed, 37 insertions(+), 142 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index ed966f51e29b..8d8e5f6340d0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1212,9 +1212,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr,
 	}
 
 	/* Fallback to software copy. */
-	spin_lock(&bo->bdev->fence_lock);
 	ret = ttm_bo_wait(bo, true, intr, no_wait_gpu);
-	spin_unlock(&bo->bdev->fence_lock);
 	if (ret == 0)
 		ret = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 
@@ -1457,26 +1455,19 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	ttm_pool_unpopulate(ttm);
 }
 
+static void
+nouveau_bo_fence_unref(void **sync_obj)
+{
+	nouveau_fence_unref((struct nouveau_fence **)sync_obj);
+}
+
 void
 nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence)
 {
-	struct nouveau_fence *new_fence = nouveau_fence_ref(fence);
-	struct nouveau_fence *old_fence = NULL;
-
 	lockdep_assert_held(&nvbo->bo.resv->lock.base);
 
-	spin_lock(&nvbo->bo.bdev->fence_lock);
-	old_fence = nvbo->bo.sync_obj;
-	nvbo->bo.sync_obj = new_fence;
-	spin_unlock(&nvbo->bo.bdev->fence_lock);
-
-	nouveau_fence_unref(&old_fence);
-}
-
-static void
-nouveau_bo_fence_unref(void **sync_obj)
-{
-	nouveau_fence_unref((struct nouveau_fence **)sync_obj);
+	nouveau_bo_fence_unref(&nvbo->bo.sync_obj);
+	nvbo->bo.sync_obj = nouveau_fence_ref(fence);
 }
 
 static void *
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 54b1f3d8fc7f..e6867b9ebb46 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -722,11 +722,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		goto fail_unpin;
 
 	/* synchronise rendering channel with the kernel's channel */
-	spin_lock(&new_bo->bo.bdev->fence_lock);
-	fence = nouveau_fence_ref(new_bo->bo.sync_obj);
-	spin_unlock(&new_bo->bo.bdev->fence_lock);
-	ret = nouveau_fence_sync(fence, chan);
-	nouveau_fence_unref(&fence);
+	ret = nouveau_fence_sync(new_bo->bo.sync_obj, chan);
 	if (ret) {
 		ttm_bo_unreserve(&new_bo->bo);
 		goto fail_unpin;
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 0054315eb879..1650c0bdb0fc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -103,9 +103,7 @@ nouveau_gem_object_unmap(struct nouveau_bo *nvbo, struct nouveau_vma *vma)
 	list_del(&vma->head);
 
 	if (mapped) {
-		spin_lock(&nvbo->bo.bdev->fence_lock);
 		fence = nouveau_fence_ref(nvbo->bo.sync_obj);
-		spin_unlock(&nvbo->bo.bdev->fence_lock);
 	}
 
 	if (fence) {
@@ -430,17 +428,11 @@ retry:
 static int
 validate_sync(struct nouveau_channel *chan, struct nouveau_bo *nvbo)
 {
-	struct nouveau_fence *fence = NULL;
+	struct nouveau_fence *fence = nvbo->bo.sync_obj;
 	int ret = 0;
 
-	spin_lock(&nvbo->bo.bdev->fence_lock);
-	fence = nouveau_fence_ref(nvbo->bo.sync_obj);
-	spin_unlock(&nvbo->bo.bdev->fence_lock);
-
-	if (fence) {
+	if (fence)
 		ret = nouveau_fence_sync(fence, chan);
-		nouveau_fence_unref(&fence);
-	}
 
 	return ret;
 }
@@ -659,9 +651,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				data |= r->vor;
 		}
 
-		spin_lock(&nvbo->bo.bdev->fence_lock);
 		ret = ttm_bo_wait(&nvbo->bo, false, false, false);
-		spin_unlock(&nvbo->bo.bdev->fence_lock);
 		if (ret) {
 			NV_PRINTK(error, cli, "reloc wait_idle failed: %d\n", ret);
 			break;
@@ -894,11 +884,9 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
 
 	ret = ttm_bo_reserve(&nvbo->bo, true, false, false, NULL);
 	if (!ret) {
-		spin_lock(&nvbo->bo.bdev->fence_lock);
 		ret = ttm_bo_wait(&nvbo->bo, true, true, true);
 		if (!no_wait && ret)
 			fence = nouveau_fence_ref(nvbo->bo.sync_obj);
-		spin_unlock(&nvbo->bo.bdev->fence_lock);
 
 		ttm_bo_unreserve(&nvbo->bo);
 	}
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index eb89653a7a17..45fad7b45486 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -628,9 +628,7 @@ static int qxl_reap_surf(struct qxl_device *qdev, struct qxl_bo *surf, bool stal
 	if (stall)
 		mutex_unlock(&qdev->surf_evict_mutex);
 
-	spin_lock(&surf->tbo.bdev->fence_lock);
 	ret = ttm_bo_wait(&surf->tbo, true, true, !stall);
-	spin_unlock(&surf->tbo.bdev->fence_lock);
 
 	if (stall)
 		mutex_lock(&qdev->surf_evict_mutex);
diff --git a/drivers/gpu/drm/qxl/qxl_fence.c b/drivers/gpu/drm/qxl/qxl_fence.c
index ae59e91cfb9a..c7248418117d 100644
--- a/drivers/gpu/drm/qxl/qxl_fence.c
+++ b/drivers/gpu/drm/qxl/qxl_fence.c
@@ -60,9 +60,6 @@ int qxl_fence_remove_release(struct qxl_fence *qfence, uint32_t rel_id)
 {
 	void *ret;
 	int retval = 0;
-	struct qxl_bo *bo = container_of(qfence, struct qxl_bo, fence);
-
-	spin_lock(&bo->tbo.bdev->fence_lock);
 
 	ret = radix_tree_delete(&qfence->tree, rel_id);
 	if (ret == qfence)
@@ -71,7 +68,6 @@ int qxl_fence_remove_release(struct qxl_fence *qfence, uint32_t rel_id)
 		DRM_DEBUG("didn't find fence in radix tree for %d\n", rel_id);
 		retval = -ENOENT;
 	}
-	spin_unlock(&bo->tbo.bdev->fence_lock);
 	return retval;
 }
 
diff --git a/drivers/gpu/drm/qxl/qxl_object.h b/drivers/gpu/drm/qxl/qxl_object.h
index 83a423293afd..1edaf5768086 100644
--- a/drivers/gpu/drm/qxl/qxl_object.h
+++ b/drivers/gpu/drm/qxl/qxl_object.h
@@ -76,12 +76,10 @@ static inline int qxl_bo_wait(struct qxl_bo *bo, u32 *mem_type,
 		}
 		return r;
 	}
-	spin_lock(&bo->tbo.bdev->fence_lock);
 	if (mem_type)
 		*mem_type = bo->tbo.mem.mem_type;
 	if (bo->tbo.sync_obj)
 		r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
-	spin_unlock(&bo->tbo.bdev->fence_lock);
 	ttm_bo_unreserve(&bo->tbo);
 	return r;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 14e776f1d14e..2e5e38fee9b2 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -337,7 +337,6 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release)
 	glob = bo->glob;
 
 	spin_lock(&glob->lru_lock);
-	spin_lock(&bdev->fence_lock);
 
 	list_for_each_entry(entry, &release->bos, head) {
 		bo = entry->bo;
@@ -352,7 +351,6 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release)
 		__ttm_bo_unreserve(bo);
 		entry->reserved = false;
 	}
-	spin_unlock(&bdev->fence_lock);
 	spin_unlock(&glob->lru_lock);
 	ww_acquire_fini(&release->ticket);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index bd0d687379ee..7d0a7abdab2a 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -476,11 +476,6 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	obj = new_radeon_fb->obj;
 	new_rbo = gem_to_radeon_bo(obj);
 
-	spin_lock(&new_rbo->tbo.bdev->fence_lock);
-	if (new_rbo->tbo.sync_obj)
-		work->fence = radeon_fence_ref(new_rbo->tbo.sync_obj);
-	spin_unlock(&new_rbo->tbo.bdev->fence_lock);
-
 	/* pin the new buffer */
 	DRM_DEBUG_DRIVER("flip-ioctl() cur_rbo = %p, new_rbo = %p\n",
 			 work->old_rbo, new_rbo);
@@ -499,6 +494,7 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 		DRM_ERROR("failed to pin new rbo buffer before flip\n");
 		goto cleanup;
 	}
+	work->fence = radeon_fence_ref(new_rbo->tbo.sync_obj);
 	radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL);
 	radeon_bo_unreserve(new_rbo);
 
@@ -582,7 +578,6 @@ cleanup:
 	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
 	radeon_fence_unref(&work->fence);
 	kfree(work);
-
 	return r;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index c97a42432e2b..cbac963571c0 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -779,12 +779,10 @@ int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type, bool no_wait)
 	r = ttm_bo_reserve(&bo->tbo, true, no_wait, false, NULL);
 	if (unlikely(r != 0))
 		return r;
-	spin_lock(&bo->tbo.bdev->fence_lock);
 	if (mem_type)
 		*mem_type = bo->tbo.mem.mem_type;
 	if (bo->tbo.sync_obj)
 		r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
-	spin_unlock(&bo->tbo.bdev->fence_lock);
 	ttm_bo_unreserve(&bo->tbo);
 	return r;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 4f1bc948bda0..195386f16ca4 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -415,24 +415,20 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	spin_lock(&glob->lru_lock);
 	ret = __ttm_bo_reserve(bo, false, true, false, NULL);
 
-	spin_lock(&bdev->fence_lock);
-	(void) ttm_bo_wait(bo, false, false, true);
-	if (!ret && !bo->sync_obj) {
-		spin_unlock(&bdev->fence_lock);
-		put_count = ttm_bo_del_from_lru(bo);
+	if (!ret) {
+		(void) ttm_bo_wait(bo, false, false, true);
 
-		spin_unlock(&glob->lru_lock);
-		ttm_bo_cleanup_memtype_use(bo);
+		if (!bo->sync_obj) {
+			put_count = ttm_bo_del_from_lru(bo);
 
-		ttm_bo_list_ref_sub(bo, put_count, true);
+			spin_unlock(&glob->lru_lock);
+			ttm_bo_cleanup_memtype_use(bo);
 
-		return;
-	}
-	if (bo->sync_obj)
-		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-	spin_unlock(&bdev->fence_lock);
+			ttm_bo_list_ref_sub(bo, put_count, true);
 
-	if (!ret) {
+			return;
+		}
+		sync_obj = driver->sync_obj_ref(bo->sync_obj);
 
 		/*
 		 * Make NO_EVICT bos immediately available to
@@ -481,7 +477,6 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 	int put_count;
 	int ret;
 
-	spin_lock(&bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, false, true);
 
 	if (ret && !no_wait_gpu) {
@@ -493,7 +488,6 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 		 * no new sync objects can be attached.
 		 */
 		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-		spin_unlock(&bdev->fence_lock);
 
 		__ttm_bo_unreserve(bo);
 		spin_unlock(&glob->lru_lock);
@@ -523,11 +517,9 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 		 * remove sync_obj with ttm_bo_wait, the wait should be
 		 * finished, and no new wait object should have been added.
 		 */
-		spin_lock(&bdev->fence_lock);
 		ret = ttm_bo_wait(bo, false, false, true);
 		WARN_ON(ret);
 	}
-	spin_unlock(&bdev->fence_lock);
 
 	if (ret || unlikely(list_empty(&bo->ddestroy))) {
 		__ttm_bo_unreserve(bo);
@@ -665,9 +657,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	struct ttm_placement placement;
 	int ret = 0;
 
-	spin_lock(&bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu);
-	spin_unlock(&bdev->fence_lock);
 
 	if (unlikely(ret != 0)) {
 		if (ret != -ERESTARTSYS) {
@@ -958,7 +948,6 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 {
 	int ret = 0;
 	struct ttm_mem_reg mem;
-	struct ttm_bo_device *bdev = bo->bdev;
 
 	lockdep_assert_held(&bo->resv->lock.base);
 
@@ -967,9 +956,7 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	 * Have the driver move function wait for idle when necessary,
 	 * instead of doing it here.
 	 */
-	spin_lock(&bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu);
-	spin_unlock(&bdev->fence_lock);
 	if (ret)
 		return ret;
 	mem.num_pages = bo->num_pages;
@@ -1459,7 +1446,6 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 	bdev->glob = glob;
 	bdev->need_dma32 = need_dma32;
 	bdev->val_seq = 0;
-	spin_lock_init(&bdev->fence_lock);
 	mutex_lock(&glob->device_list_mutex);
 	list_add_tail(&bdev->device_list, &glob->device_list);
 	mutex_unlock(&glob->device_list_mutex);
@@ -1517,7 +1503,6 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 		bool lazy, bool interruptible, bool no_wait)
 {
 	struct ttm_bo_driver *driver = bo->bdev->driver;
-	struct ttm_bo_device *bdev = bo->bdev;
 	void *sync_obj;
 	int ret = 0;
 
@@ -1526,53 +1511,33 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 	if (likely(bo->sync_obj == NULL))
 		return 0;
 
-	while (bo->sync_obj) {
-
+	if (bo->sync_obj) {
 		if (driver->sync_obj_signaled(bo->sync_obj)) {
-			void *tmp_obj = bo->sync_obj;
-			bo->sync_obj = NULL;
+			driver->sync_obj_unref(&bo->sync_obj);
 			clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
-			spin_unlock(&bdev->fence_lock);
-			driver->sync_obj_unref(&tmp_obj);
-			spin_lock(&bdev->fence_lock);
-			continue;
+			return 0;
 		}
 
 		if (no_wait)
 			return -EBUSY;
 
 		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-		spin_unlock(&bdev->fence_lock);
 		ret = driver->sync_obj_wait(sync_obj,
 					    lazy, interruptible);
-		if (unlikely(ret != 0)) {
-			driver->sync_obj_unref(&sync_obj);
-			spin_lock(&bdev->fence_lock);
-			return ret;
-		}
-		spin_lock(&bdev->fence_lock);
-		if (likely(bo->sync_obj == sync_obj)) {
-			void *tmp_obj = bo->sync_obj;
-			bo->sync_obj = NULL;
+
+		if (likely(ret == 0)) {
 			clear_bit(TTM_BO_PRIV_FLAG_MOVING,
 				  &bo->priv_flags);
-			spin_unlock(&bdev->fence_lock);
-			driver->sync_obj_unref(&sync_obj);
-			driver->sync_obj_unref(&tmp_obj);
-			spin_lock(&bdev->fence_lock);
-		} else {
-			spin_unlock(&bdev->fence_lock);
-			driver->sync_obj_unref(&sync_obj);
-			spin_lock(&bdev->fence_lock);
+			driver->sync_obj_unref(&bo->sync_obj);
 		}
+		driver->sync_obj_unref(&sync_obj);
 	}
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(ttm_bo_wait);
 
 int ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait)
 {
-	struct ttm_bo_device *bdev = bo->bdev;
 	int ret = 0;
 
 	/*
@@ -1582,9 +1547,7 @@ int ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait)
 	ret = ttm_bo_reserve(bo, true, no_wait, false, NULL);
 	if (unlikely(ret != 0))
 		return ret;
-	spin_lock(&bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, true, no_wait);
-	spin_unlock(&bdev->fence_lock);
 	if (likely(ret == 0))
 		atomic_inc(&bo->cpu_writers);
 	ttm_bo_unreserve(bo);
@@ -1641,9 +1604,7 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 	 * Wait for GPU, then move to system cached.
 	 */
 
-	spin_lock(&bo->bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, false, false);
-	spin_unlock(&bo->bdev->fence_lock);
 
 	if (unlikely(ret != 0))
 		goto out;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 30e5d90cb7bc..495aebf0f9c3 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -466,12 +466,10 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	drm_vma_node_reset(&fbo->vma_node);
 	atomic_set(&fbo->cpu_writers, 0);
 
-	spin_lock(&bdev->fence_lock);
 	if (bo->sync_obj)
 		fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj);
 	else
 		fbo->sync_obj = NULL;
-	spin_unlock(&bdev->fence_lock);
 	kref_init(&fbo->list_kref);
 	kref_init(&fbo->kref);
 	fbo->destroy = &ttm_transfered_destroy;
@@ -657,7 +655,6 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 	struct ttm_buffer_object *ghost_obj;
 	void *tmp_obj = NULL;
 
-	spin_lock(&bdev->fence_lock);
 	if (bo->sync_obj) {
 		tmp_obj = bo->sync_obj;
 		bo->sync_obj = NULL;
@@ -665,7 +662,6 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 	bo->sync_obj = driver->sync_obj_ref(sync_obj);
 	if (evict) {
 		ret = ttm_bo_wait(bo, false, false, false);
-		spin_unlock(&bdev->fence_lock);
 		if (tmp_obj)
 			driver->sync_obj_unref(&tmp_obj);
 		if (ret)
@@ -688,7 +684,6 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		 */
 
 		set_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
-		spin_unlock(&bdev->fence_lock);
 		if (tmp_obj)
 			driver->sync_obj_unref(&tmp_obj);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 0ce48e5a9cb4..d05437f219e9 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -45,10 +45,8 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 				struct vm_area_struct *vma,
 				struct vm_fault *vmf)
 {
-	struct ttm_bo_device *bdev = bo->bdev;
 	int ret = 0;
 
-	spin_lock(&bdev->fence_lock);
 	if (likely(!test_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags)))
 		goto out_unlock;
 
@@ -82,7 +80,6 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 			VM_FAULT_NOPAGE;
 
 out_unlock:
-	spin_unlock(&bdev->fence_lock);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index e8dac8758528..0fbbbbd67afc 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -217,7 +217,6 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 	glob = bo->glob;
 
 	spin_lock(&glob->lru_lock);
-	spin_lock(&bdev->fence_lock);
 
 	list_for_each_entry(entry, list, head) {
 		bo = entry->bo;
@@ -227,7 +226,6 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 		__ttm_bo_unreserve(bo);
 		entry->reserved = false;
 	}
-	spin_unlock(&bdev->fence_lock);
 	spin_unlock(&glob->lru_lock);
 	if (ticket)
 		ww_acquire_fini(ticket);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
index 37c093c0c7b8..c133b3d10de8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
@@ -863,11 +863,7 @@ static void vmw_move_notify(struct ttm_buffer_object *bo,
  */
 static void vmw_swap_notify(struct ttm_buffer_object *bo)
 {
-	struct ttm_bo_device *bdev = bo->bdev;
-
-	spin_lock(&bdev->fence_lock);
 	ttm_bo_wait(bo, false, false, false);
-	spin_unlock(&bdev->fence_lock);
 }
 
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index a432c0db257c..1ee86bf82750 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -567,12 +567,13 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
 	int ret;
 
 	if (flags & drm_vmw_synccpu_allow_cs) {
-		struct ttm_bo_device *bdev = bo->bdev;
+		bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
 
-		spin_lock(&bdev->fence_lock);
-		ret = ttm_bo_wait(bo, false, true,
-				  !!(flags & drm_vmw_synccpu_dontblock));
-		spin_unlock(&bdev->fence_lock);
+		ret = ttm_bo_reserve(bo, true, nonblock, false, NULL);
+		if (!ret) {
+			ret = ttm_bo_wait(bo, false, true, nonblock);
+			ttm_bo_unreserve(bo);
+		}
 		return ret;
 	}
 
@@ -1429,12 +1430,10 @@ void vmw_fence_single_bo(struct ttm_buffer_object *bo,
 	else
 		driver->sync_obj_ref(fence);
 
-	spin_lock(&bdev->fence_lock);
 
 	old_fence_obj = bo->sync_obj;
 	bo->sync_obj = fence;
 
-	spin_unlock(&bdev->fence_lock);
 
 	if (old_fence_obj)
 		vmw_fence_obj_unreference(&old_fence_obj);
@@ -1475,7 +1474,6 @@ void vmw_resource_move_notify(struct ttm_buffer_object *bo,
 
 	if (mem->mem_type != VMW_PL_MOB) {
 		struct vmw_resource *res, *n;
-		struct ttm_bo_device *bdev = bo->bdev;
 		struct ttm_validate_buffer val_buf;
 
 		val_buf.bo = bo;
@@ -1491,9 +1489,7 @@ void vmw_resource_move_notify(struct ttm_buffer_object *bo,
 			list_del_init(&res->mob_head);
 		}
 
-		spin_lock(&bdev->fence_lock);
 		(void) ttm_bo_wait(bo, false, false, false);
-		spin_unlock(&bdev->fence_lock);
 	}
 }
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index e3d39c80a091..5805f4a49478 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -237,10 +237,7 @@ struct ttm_buffer_object {
 	struct list_head io_reserve_lru;
 
 	/**
-	 * Members protected by struct buffer_object_device::fence_lock
-	 * In addition, setting sync_obj to anything else
-	 * than NULL requires bo::reserved to be held. This allows for
-	 * checking NULL while reserved but not holding the mentioned lock.
+	 * Members protected by a bo reservation.
 	 */
 
 	void *sync_obj;
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 5c8bb5699a6f..e1ee141e26cc 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -521,8 +521,6 @@ struct ttm_bo_global {
  *
  * @driver: Pointer to a struct ttm_bo_driver struct setup by the driver.
  * @man: An array of mem_type_managers.
- * @fence_lock: Protects the synchronizing members on *all* bos belonging
- * to this device.
  * @vma_manager: Address space manager
  * lru_lock: Spinlock that protects the buffer+device lru lists and
  * ddestroy lists.
@@ -542,7 +540,6 @@ struct ttm_bo_device {
 	struct ttm_bo_global *glob;
 	struct ttm_bo_driver *driver;
 	struct ttm_mem_type_manager man[TTM_NUM_MEM_TYPES];
-	spinlock_t fence_lock;
 
 	/*
 	 * Protected by internal locks.
-- 
cgit v1.2.3


From 58b4d720c1620bbf09e42b4f218dcb2d0d8cdf3e Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Date: Thu, 9 Jan 2014 11:03:08 +0100
Subject: drm/ttm: add interruptible parameter to ttm_eu_reserve_buffers

It seems some drivers really want this as a parameter,
like vmwgfx.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
---
 drivers/gpu/drm/qxl/qxl_release.c        |  2 +-
 drivers/gpu/drm/radeon/radeon_object.c   |  2 +-
 drivers/gpu/drm/radeon/radeon_vm.c       |  2 +-
 drivers/gpu/drm/ttm/ttm_execbuf_util.c   | 22 +++++++++++++---------
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c  |  7 ++-----
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c |  2 +-
 include/drm/ttm/ttm_execbuf_util.h       |  9 +++++----
 7 files changed, 24 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 2e5e38fee9b2..656f9d3a946d 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -159,7 +159,7 @@ int qxl_release_reserve_list(struct qxl_release *release, bool no_intr)
 	if (list_is_singular(&release->bos))
 		return 0;
 
-	ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos);
+	ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos, !no_intr);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index cbac963571c0..378fe9ea4d44 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -482,7 +482,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 	u64 bytes_moved = 0, initial_bytes_moved;
 	u64 bytes_moved_threshold = radeon_bo_get_threshold_for_moves(rdev);
 
-	r = ttm_eu_reserve_buffers(ticket, head);
+	r = ttm_eu_reserve_buffers(ticket, head, true);
 	if (unlikely(r != 0)) {
 		return r;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 4751c6728fe9..3d9a6a036f8a 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -399,7 +399,7 @@ static int radeon_vm_clear_bo(struct radeon_device *rdev,
         INIT_LIST_HEAD(&head);
         list_add(&tv.head, &head);
 
-        r = ttm_eu_reserve_buffers(&ticket, &head);
+        r = ttm_eu_reserve_buffers(&ticket, &head, true);
         if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 0fbbbbd67afc..87d7deefc806 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -112,7 +112,7 @@ EXPORT_SYMBOL(ttm_eu_backoff_reservation);
  */
 
 int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
-			   struct list_head *list)
+			   struct list_head *list, bool intr)
 {
 	struct ttm_bo_global *glob;
 	struct ttm_validate_buffer *entry;
@@ -140,7 +140,7 @@ retry:
 		if (entry->reserved)
 			continue;
 
-		ret = __ttm_bo_reserve(bo, true, (ticket == NULL), true,
+		ret = __ttm_bo_reserve(bo, intr, (ticket == NULL), true,
 				       ticket);
 
 		if (ret == -EDEADLK) {
@@ -153,13 +153,17 @@ retry:
 			ttm_eu_backoff_reservation_locked(list);
 			spin_unlock(&glob->lru_lock);
 			ttm_eu_list_ref_sub(list);
-			ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
-							       ticket);
-			if (unlikely(ret != 0)) {
-				if (ret == -EINTR)
-					ret = -ERESTARTSYS;
-				goto err_fini;
-			}
+
+			if (intr) {
+				ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
+								       ticket);
+				if (unlikely(ret != 0)) {
+					if (ret == -EINTR)
+						ret = -ERESTARTSYS;
+					goto err_fini;
+				}
+			} else
+				ww_mutex_lock_slow(&bo->resv->lock, ticket);
 
 			entry->reserved = true;
 			if (unlikely(atomic_read(&bo->cpu_writers) > 0)) {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 7bfdaa163a33..24f067bf438d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2496,7 +2496,7 @@ int vmw_execbuf_process(struct drm_file *file_priv,
 	if (unlikely(ret != 0))
 		goto out_err_nores;
 
-	ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes);
+	ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes, true);
 	if (unlikely(ret != 0))
 		goto out_err;
 
@@ -2684,10 +2684,7 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv,
 	query_val.bo = ttm_bo_reference(dev_priv->dummy_query_bo);
 	list_add_tail(&query_val.head, &validate_list);
 
-	do {
-		ret = ttm_eu_reserve_buffers(&ticket, &validate_list);
-	} while (ret == -ERESTARTSYS);
-
+	ret = ttm_eu_reserve_buffers(&ticket, &validate_list, false);
 	if (unlikely(ret != 0)) {
 		vmw_execbuf_unpin_panic(dev_priv);
 		goto out_no_reserve;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 1ee86bf82750..23169362bca8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -1216,7 +1216,7 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 	INIT_LIST_HEAD(&val_list);
 	val_buf->bo = ttm_bo_reference(&res->backup->base);
 	list_add_tail(&val_buf->head, &val_list);
-	ret = ttm_eu_reserve_buffers(NULL, &val_list);
+	ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible);
 	if (unlikely(ret != 0))
 		goto out_no_reserve;
 
diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index 16db7d01a336..fd95fd569ca3 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -73,6 +73,7 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  * @ticket:  [out] ww_acquire_ctx filled in by call, or NULL if only
  *           non-blocking reserves should be tried.
  * @list:    thread private list of ttm_validate_buffer structs.
+ * @intr:    should the wait be interruptible
  *
  * Tries to reserve bos pointed to by the list entries for validation.
  * If the function returns 0, all buffers are marked as "unfenced",
@@ -84,9 +85,9 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  * CPU write reservations to be cleared, and for other threads to
  * unreserve their buffers.
  *
- * This function may return -ERESTART or -EAGAIN if the calling process
- * receives a signal while waiting. In that case, no buffers on the list
- * will be reserved upon return.
+ * If intr is set to true, this function may return -ERESTARTSYS if the
+ * calling process receives a signal while waiting. In that case, no
+ * buffers on the list will be reserved upon return.
  *
  * Buffers reserved by this function should be unreserved by
  * a call to either ttm_eu_backoff_reservation() or
@@ -95,7 +96,7 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  */
 
 extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
-				  struct list_head *list);
+				  struct list_head *list, bool intr);
 
 /**
  * function ttm_eu_fence_buffer_objects.
-- 
cgit v1.2.3


From 1f0dc9a59afeccb96a35ebec36661266260f5eee Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Date: Thu, 9 Jan 2014 11:03:08 +0100
Subject: drm/ttm: kill off some members to ttm_validate_buffer

This reorders the list to keep track of what buffers are reserved,
so previous members are always unreserved.

This gets rid of some bookkeeping that's no longer needed,
while simplifying the code some.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
---
 drivers/gpu/drm/qxl/qxl_release.c       |   1 -
 drivers/gpu/drm/ttm/ttm_execbuf_util.c  | 142 +++++++++++---------------------
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c |   1 -
 include/drm/ttm/ttm_execbuf_util.h      |   3 -
 4 files changed, 50 insertions(+), 97 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 656f9d3a946d..4045ba873ab8 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -349,7 +349,6 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release)
 
 		ttm_bo_add_to_lru(bo);
 		__ttm_bo_unreserve(bo);
-		entry->reserved = false;
 	}
 	spin_unlock(&glob->lru_lock);
 	ww_acquire_fini(&release->ticket);
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 87d7deefc806..108730e9147b 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -32,20 +32,12 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 
-static void ttm_eu_backoff_reservation_locked(struct list_head *list)
+static void ttm_eu_backoff_reservation_reverse(struct list_head *list,
+					      struct ttm_validate_buffer *entry)
 {
-	struct ttm_validate_buffer *entry;
-
-	list_for_each_entry(entry, list, head) {
+	list_for_each_entry_continue_reverse(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
-		if (!entry->reserved)
-			continue;
 
-		entry->reserved = false;
-		if (entry->removed) {
-			ttm_bo_add_to_lru(bo);
-			entry->removed = false;
-		}
 		__ttm_bo_unreserve(bo);
 	}
 }
@@ -56,27 +48,9 @@ static void ttm_eu_del_from_lru_locked(struct list_head *list)
 
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
-		if (!entry->reserved)
-			continue;
+		unsigned put_count = ttm_bo_del_from_lru(bo);
 
-		if (!entry->removed) {
-			entry->put_count = ttm_bo_del_from_lru(bo);
-			entry->removed = true;
-		}
-	}
-}
-
-static void ttm_eu_list_ref_sub(struct list_head *list)
-{
-	struct ttm_validate_buffer *entry;
-
-	list_for_each_entry(entry, list, head) {
-		struct ttm_buffer_object *bo = entry->bo;
-
-		if (entry->put_count) {
-			ttm_bo_list_ref_sub(bo, entry->put_count, true);
-			entry->put_count = 0;
-		}
+		ttm_bo_list_ref_sub(bo, put_count, true);
 	}
 }
 
@@ -91,11 +65,18 @@ void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
 
 	entry = list_first_entry(list, struct ttm_validate_buffer, head);
 	glob = entry->bo->glob;
+
 	spin_lock(&glob->lru_lock);
-	ttm_eu_backoff_reservation_locked(list);
+	list_for_each_entry(entry, list, head) {
+		struct ttm_buffer_object *bo = entry->bo;
+
+		ttm_bo_add_to_lru(bo);
+		__ttm_bo_unreserve(bo);
+	}
+	spin_unlock(&glob->lru_lock);
+
 	if (ticket)
 		ww_acquire_fini(ticket);
-	spin_unlock(&glob->lru_lock);
 }
 EXPORT_SYMBOL(ttm_eu_backoff_reservation);
 
@@ -121,64 +102,55 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 	if (list_empty(list))
 		return 0;
 
-	list_for_each_entry(entry, list, head) {
-		entry->reserved = false;
-		entry->put_count = 0;
-		entry->removed = false;
-	}
-
 	entry = list_first_entry(list, struct ttm_validate_buffer, head);
 	glob = entry->bo->glob;
 
 	if (ticket)
 		ww_acquire_init(ticket, &reservation_ww_class);
-retry:
+
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
 
-		/* already slowpath reserved? */
-		if (entry->reserved)
-			continue;
-
 		ret = __ttm_bo_reserve(bo, intr, (ticket == NULL), true,
 				       ticket);
+		if (!ret && unlikely(atomic_read(&bo->cpu_writers) > 0)) {
+			__ttm_bo_unreserve(bo);
 
-		if (ret == -EDEADLK) {
-			/* uh oh, we lost out, drop every reservation and try
-			 * to only reserve this buffer, then start over if
-			 * this succeeds.
-			 */
-			BUG_ON(ticket == NULL);
-			spin_lock(&glob->lru_lock);
-			ttm_eu_backoff_reservation_locked(list);
-			spin_unlock(&glob->lru_lock);
-			ttm_eu_list_ref_sub(list);
-
-			if (intr) {
-				ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
-								       ticket);
-				if (unlikely(ret != 0)) {
-					if (ret == -EINTR)
-						ret = -ERESTARTSYS;
-					goto err_fini;
-				}
-			} else
-				ww_mutex_lock_slow(&bo->resv->lock, ticket);
-
-			entry->reserved = true;
-			if (unlikely(atomic_read(&bo->cpu_writers) > 0)) {
-				ret = -EBUSY;
-				goto err;
-			}
-			goto retry;
-		} else if (ret)
-			goto err;
-
-		entry->reserved = true;
-		if (unlikely(atomic_read(&bo->cpu_writers) > 0)) {
 			ret = -EBUSY;
-			goto err;
 		}
+
+		if (!ret)
+			continue;
+
+		/* uh oh, we lost out, drop every reservation and try
+		 * to only reserve this buffer, then start over if
+		 * this succeeds.
+		 */
+		ttm_eu_backoff_reservation_reverse(list, entry);
+
+		if (ret == -EDEADLK && intr) {
+			ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
+							       ticket);
+		} else if (ret == -EDEADLK) {
+			ww_mutex_lock_slow(&bo->resv->lock, ticket);
+			ret = 0;
+		}
+
+		if (unlikely(ret != 0)) {
+			if (ret == -EINTR)
+				ret = -ERESTARTSYS;
+			if (ticket) {
+				ww_acquire_done(ticket);
+				ww_acquire_fini(ticket);
+			}
+			return ret;
+		}
+
+		/* move this item to the front of the list,
+		 * forces correct iteration of the loop without keeping track
+		 */
+		list_del(&entry->head);
+		list_add(&entry->head, list);
 	}
 
 	if (ticket)
@@ -186,20 +158,7 @@ retry:
 	spin_lock(&glob->lru_lock);
 	ttm_eu_del_from_lru_locked(list);
 	spin_unlock(&glob->lru_lock);
-	ttm_eu_list_ref_sub(list);
 	return 0;
-
-err:
-	spin_lock(&glob->lru_lock);
-	ttm_eu_backoff_reservation_locked(list);
-	spin_unlock(&glob->lru_lock);
-	ttm_eu_list_ref_sub(list);
-err_fini:
-	if (ticket) {
-		ww_acquire_done(ticket);
-		ww_acquire_fini(ticket);
-	}
-	return ret;
 }
 EXPORT_SYMBOL(ttm_eu_reserve_buffers);
 
@@ -228,7 +187,6 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 		bo->sync_obj = driver->sync_obj_ref(sync_obj);
 		ttm_bo_add_to_lru(bo);
 		__ttm_bo_unreserve(bo);
-		entry->reserved = false;
 	}
 	spin_unlock(&glob->lru_lock);
 	if (ticket)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 24f067bf438d..b19b2b980cb4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -346,7 +346,6 @@ static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
 		++sw_context->cur_val_buf;
 		val_buf = &vval_buf->base;
 		val_buf->bo = ttm_bo_reference(bo);
-		val_buf->reserved = false;
 		list_add_tail(&val_buf->head, &sw_context->validate_nodes);
 		vval_buf->validate_as_mob = validate_as_mob;
 	}
diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index fd95fd569ca3..8490cb8ee0d8 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -48,9 +48,6 @@
 struct ttm_validate_buffer {
 	struct list_head head;
 	struct ttm_buffer_object *bo;
-	bool reserved;
-	bool removed;
-	int put_count;
 	void *old_sync_obj;
 };
 
-- 
cgit v1.2.3


From 4e00517945bed110f1b8de580cce97626e9ef0b5 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 31 Aug 2014 21:10:51 +0200
Subject: regulator: max1586: add device-tree support

Add device-tree support to max1586.
The driver can still be used with the legacy platform data, or the new
device-tree way.

This work is heavily inspired by the device-tree support of its cousin
max8660 driver.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/max1586.c       | 81 ++++++++++++++++++++++++++++++++++++++-
 include/linux/regulator/max1586.h |  2 +-
 2 files changed, 80 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/max1586.c b/drivers/regulator/max1586.c
index d23d0577754b..5c04a7159baa 100644
--- a/drivers/regulator/max1586.c
+++ b/drivers/regulator/max1586.c
@@ -24,6 +24,8 @@
 #include <linux/regulator/driver.h>
 #include <linux/slab.h>
 #include <linux/regulator/max1586.h>
+#include <linux/of_device.h>
+#include <linux/regulator/of_regulator.h>
 
 #define MAX1586_V3_MAX_VSEL 31
 #define MAX1586_V6_MAX_VSEL 3
@@ -157,13 +159,87 @@ static struct regulator_desc max1586_reg[] = {
 	},
 };
 
+int of_get_max1586_platform_data(struct device *dev,
+				 struct max1586_platform_data *pdata)
+{
+	struct max1586_subdev_data *sub;
+	struct of_regulator_match rmatch[ARRAY_SIZE(max1586_reg)];
+	struct device_node *np = dev->of_node;
+	int i, matched;
+
+	if (of_property_read_u32(np, "v3-gain",
+				 &pdata->v3_gain) < 0) {
+		dev_err(dev, "%s has no 'v3-gain' property\n", np->full_name);
+		return -EINVAL;
+	}
+
+	np = of_get_child_by_name(np, "regulators");
+	if (!np) {
+		dev_err(dev, "missing 'regulators' subnode in DT\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(rmatch); i++)
+		rmatch[i].name = max1586_reg[i].name;
+
+	matched = of_regulator_match(dev, np, rmatch, ARRAY_SIZE(rmatch));
+	of_node_put(np);
+	/*
+	 * If matched is 0, ie. neither Output_V3 nor Output_V6 have been found,
+	 * return 0, which signals the normal situation where no subregulator is
+	 * available. This is normal because the max1586 doesn't provide any
+	 * readback support, so the subregulators can't report any status
+	 * anyway.  If matched < 0, return the error.
+	 */
+	if (matched <= 0)
+		return matched;
+
+	pdata->subdevs = devm_kzalloc(dev, sizeof(struct max1586_subdev_data) *
+						matched, GFP_KERNEL);
+	if (!pdata->subdevs)
+		return -ENOMEM;
+
+	pdata->num_subdevs = matched;
+	sub = pdata->subdevs;
+
+	for (i = 0; i < matched; i++) {
+		sub->id = i;
+		sub->name = rmatch[i].of_node->name;
+		sub->platform_data = rmatch[i].init_data;
+		sub++;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id max1586_of_match[] = {
+	{ .compatible = "maxim,max1586", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, max1586_of_match);
+
 static int max1586_pmic_probe(struct i2c_client *client,
 					const struct i2c_device_id *i2c_id)
 {
-	struct max1586_platform_data *pdata = dev_get_platdata(&client->dev);
+	struct max1586_platform_data *pdata, pdata_of;
 	struct regulator_config config = { };
 	struct max1586_data *max1586;
-	int i, id;
+	int i, id, ret;
+	const struct of_device_id *match;
+
+	pdata = dev_get_platdata(&client->dev);
+	if (client->dev.of_node && !pdata) {
+		match = of_match_device(of_match_ptr(max1586_of_match),
+					&client->dev);
+		if (!match) {
+			dev_err(&client->dev, "Error: No device match found\n");
+			return -ENODEV;
+		}
+		ret = of_get_max1586_platform_data(&client->dev, &pdata_of);
+		if (ret < 0)
+			return ret;
+		pdata = &pdata_of;
+	}
 
 	max1586 = devm_kzalloc(&client->dev, sizeof(struct max1586_data),
 			GFP_KERNEL);
@@ -229,6 +305,7 @@ static struct i2c_driver max1586_pmic_driver = {
 	.driver		= {
 		.name	= "max1586",
 		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(max1586_of_match),
 	},
 	.id_table	= max1586_id,
 };
diff --git a/include/linux/regulator/max1586.h b/include/linux/regulator/max1586.h
index de9a7fae20be..cedd0febe882 100644
--- a/include/linux/regulator/max1586.h
+++ b/include/linux/regulator/max1586.h
@@ -40,7 +40,7 @@
  */
 struct max1586_subdev_data {
 	int				id;
-	char				*name;
+	const char			*name;
 	struct regulator_init_data	*platform_data;
 };
 
-- 
cgit v1.2.3


From 068765ba7987e73d4381edfe47b70aa121c7155c Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 1 Sep 2014 13:47:49 +0200
Subject: PM / sleep: Mechanism for aborting system suspends unconditionally

It sometimes may be necessary to abort a system suspend in
progress or wake up the system from suspend-to-idle even if the
pm_wakeup_event()/pm_stay_awake() mechanism is not enabled.

For this purpose, introduce a new global variable pm_abort_suspend
and make pm_wakeup_pending() check its value.  Also add routines
for manipulating that variable.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/wakeup.c | 16 +++++++++++++++-
 include/linux/suspend.h     |  4 ++++
 kernel/power/process.c      |  1 +
 3 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index eb1bd2ecad8b..c2744b30d5d9 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -24,6 +24,9 @@
  */
 bool events_check_enabled __read_mostly;
 
+/* If set and the system is suspending, terminate the suspend. */
+static bool pm_abort_suspend __read_mostly;
+
 /*
  * Combined counters of registered wakeup events and wakeup events in progress.
  * They need to be modified together atomically, so it's better to use one
@@ -719,7 +722,18 @@ bool pm_wakeup_pending(void)
 		pm_print_active_wakeup_sources();
 	}
 
-	return ret;
+	return ret || pm_abort_suspend;
+}
+
+void pm_system_wakeup(void)
+{
+	pm_abort_suspend = true;
+	freeze_wake();
+}
+
+void pm_wakeup_clear(void)
+{
+	pm_abort_suspend = false;
 }
 
 /**
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 519064e0c943..06a9910827c2 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -371,6 +371,8 @@ extern int unregister_pm_notifier(struct notifier_block *nb);
 extern bool events_check_enabled;
 
 extern bool pm_wakeup_pending(void);
+extern void pm_system_wakeup(void);
+extern void pm_wakeup_clear(void);
 extern bool pm_get_wakeup_count(unsigned int *count, bool block);
 extern bool pm_save_wakeup_count(unsigned int count);
 extern void pm_wakep_autosleep_enabled(bool set);
@@ -418,6 +420,8 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
 
 static inline bool pm_wakeup_pending(void) { return false; }
+static inline void pm_system_wakeup(void) {}
+static inline void pm_wakeup_clear(void) {}
 
 static inline void lock_system_sleep(void) {}
 static inline void unlock_system_sleep(void) {}
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 4ee194eb524b..7b323221b9ee 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -129,6 +129,7 @@ int freeze_processes(void)
 	if (!pm_freezing)
 		atomic_inc(&system_freezing_cnt);
 
+	pm_wakeup_clear();
 	printk("Freezing user space processes ... ");
 	pm_freezing = true;
 	error = try_to_freeze_tasks(true);
-- 
cgit v1.2.3


From cab303be91dc47942bc25de33dc1140123540800 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 28 Aug 2014 11:44:31 +0200
Subject: genirq: Add sanity checks for PM options on shared interrupt lines

Account the IRQF_NO_SUSPEND and IRQF_RESUME_EARLY actions on shared
interrupt lines and yell loudly if there is a mismatch.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/irqdesc.h | 10 ++++++++++
 kernel/irq/internals.h  | 10 ++++++++++
 kernel/irq/manage.c     |  4 ++++
 kernel/irq/pm.c         | 36 ++++++++++++++++++++++++++++++++++++
 4 files changed, 60 insertions(+)

(limited to 'include')

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 472c021a2d4f..cb1a31e448ae 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -36,6 +36,11 @@ struct irq_desc;
  * @threads_oneshot:	bitfield to handle shared oneshot threads
  * @threads_active:	number of irqaction threads currently running
  * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
+ * @nr_actions:		number of installed actions on this descriptor
+ * @no_suspend_depth:	number of irqactions on a irq descriptor with
+ *			IRQF_NO_SUSPEND set
+ * @force_resume_depth:	number of irqactions on a irq descriptor with
+ *			IRQF_FORCE_RESUME set
  * @dir:		/proc/irq/ procfs entry
  * @name:		flow handler name for /proc/interrupts output
  */
@@ -68,6 +73,11 @@ struct irq_desc {
 	unsigned long		threads_oneshot;
 	atomic_t		threads_active;
 	wait_queue_head_t       wait_for_threads;
+#ifdef CONFIG_PM_SLEEP
+	unsigned int		nr_actions;
+	unsigned int		no_suspend_depth;
+	unsigned int		force_resume_depth;
+#endif
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
 #endif
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index af2821178900..c402502a5111 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -194,3 +194,13 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *d
 	__this_cpu_inc(*desc->kstat_irqs);
 	__this_cpu_inc(kstat.irqs_sum);
 }
+
+#ifdef CONFIG_PM_SLEEP
+void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action);
+void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action);
+#else
+static inline void
+irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { }
+static inline void
+irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { }
+#endif
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index fa564e8db996..0a9104b4608b 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1200,6 +1200,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	new->irq = irq;
 	*old_ptr = new;
 
+	irq_pm_install_action(desc, new);
+
 	/* Reset broken irq detection when installing new handler */
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
@@ -1318,6 +1320,8 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 	/* Found it - now remove it from the list of entries: */
 	*action_ptr = action->next;
 
+	irq_pm_remove_action(desc, action);
+
 	/* If this was the last handler, shut down the IRQ line: */
 	if (!desc->action) {
 		irq_shutdown(desc);
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index b84141dcee5e..1b1b67a73218 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -13,6 +13,42 @@
 
 #include "internals.h"
 
+/*
+ * Called from __setup_irq() with desc->lock held after @action has
+ * been installed in the action chain.
+ */
+void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action)
+{
+	desc->nr_actions++;
+
+	if (action->flags & IRQF_FORCE_RESUME)
+		desc->force_resume_depth++;
+
+	WARN_ON_ONCE(desc->force_resume_depth &&
+		     desc->force_resume_depth != desc->nr_actions);
+
+	if (action->flags & IRQF_NO_SUSPEND)
+		desc->no_suspend_depth++;
+
+	WARN_ON_ONCE(desc->no_suspend_depth &&
+		     desc->no_suspend_depth != desc->nr_actions);
+}
+
+/*
+ * Called from __free_irq() with desc->lock held after @action has
+ * been removed from the action chain.
+ */
+void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action)
+{
+	desc->nr_actions--;
+
+	if (action->flags & IRQF_FORCE_RESUME)
+		desc->force_resume_depth--;
+
+	if (action->flags & IRQF_NO_SUSPEND)
+		desc->no_suspend_depth--;
+}
+
 static void suspend_device_irq(struct irq_desc *desc, int irq)
 {
 	if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND))
-- 
cgit v1.2.3


From b76f16748fa61801b1a1fd3ffb6f25ee228a35e0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 29 Aug 2014 13:54:09 +0200
Subject: genirq: Mark wakeup sources as armed on suspend

This allows us to utilize this information in the irq_may_run() check
without adding another conditional to the fast path.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/irq.h | 8 ++++++++
 kernel/irq/pm.c     | 5 +++++
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 62af59242ddc..03f48d936f66 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -173,6 +173,7 @@ struct irq_data {
  * IRQD_IRQ_DISABLED		- Disabled state of the interrupt
  * IRQD_IRQ_MASKED		- Masked state of the interrupt
  * IRQD_IRQ_INPROGRESS		- In progress state of the interrupt
+ * IRQD_WAKEUP_ARMED		- Wakeup mode armed
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -186,6 +187,7 @@ enum {
 	IRQD_IRQ_DISABLED		= (1 << 16),
 	IRQD_IRQ_MASKED			= (1 << 17),
 	IRQD_IRQ_INPROGRESS		= (1 << 18),
+	IRQD_WAKEUP_ARMED		= (1 << 19),
 };
 
 static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
@@ -257,6 +259,12 @@ static inline bool irqd_irq_inprogress(struct irq_data *d)
 	return d->state_use_accessors & IRQD_IRQ_INPROGRESS;
 }
 
+static inline bool irqd_is_wakeup_armed(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_WAKEUP_ARMED;
+}
+
+
 /*
  * Functions for chained handlers which can be enabled/disabled by the
  * standard disable_irq/enable_irq calls. Must be called with
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index cf0ce0163db9..766930eaeed9 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -54,6 +54,9 @@ static bool suspend_device_irq(struct irq_desc *desc, int irq)
 	if (!desc->action || desc->no_suspend_depth)
 		return false;
 
+	if (irqd_is_wakeup_set(&desc->irq_data))
+		irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
+
 	desc->istate |= IRQS_SUSPENDED;
 	__disable_irq(desc, irq);
 
@@ -101,6 +104,8 @@ EXPORT_SYMBOL_GPL(suspend_device_irqs);
 
 static void resume_irq(struct irq_desc *desc, int irq)
 {
+	irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED);
+
 	if (desc->istate & IRQS_SUSPENDED)
 		goto resume;
 
-- 
cgit v1.2.3


From 9ce7a25849e80cfb264f4995f832b932c1987e1a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 29 Aug 2014 14:00:16 +0200
Subject: genirq: Simplify wakeup mechanism

Currently we suspend wakeup interrupts by lazy disabling them and
check later whether the interrupt has fired, but that's not sufficient
for suspend to idle as there is no way to check that once we
transitioned into the CPU idle state.

So we change the mechanism in the following way:

1) Leave the wakeup interrupts enabled across suspend

2) Add a check to irq_may_run() which is called at the beginning of
   each flow handler whether the interrupt is an armed wakeup source.

   This check is basically free as it just extends the existing check
   for IRQD_IRQ_INPROGRESS. So no new conditional in the hot path.

   If the IRQD_WAKEUP_ARMED flag is set, then the interrupt is
   disabled, marked as pending/suspended and the pm core is notified
   about the wakeup event.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[ rjw: syscore.c and put irq_pm_check_wakeup() into pm.c ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/syscore.c    |  7 +++---
 include/linux/interrupt.h |  5 -----
 kernel/irq/chip.c         | 20 ++++++++++++++++-
 kernel/irq/internals.h    |  2 ++
 kernel/irq/pm.c           | 55 +++++++++++++++++++++++++----------------------
 5 files changed, 53 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
index dbb8350ea8dc..8d98a329f6ea 100644
--- a/drivers/base/syscore.c
+++ b/drivers/base/syscore.c
@@ -9,7 +9,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
-#include <linux/interrupt.h>
+#include <linux/suspend.h>
 #include <trace/events/power.h>
 
 static LIST_HEAD(syscore_ops_list);
@@ -54,9 +54,8 @@ int syscore_suspend(void)
 	pr_debug("Checking wakeup interrupts\n");
 
 	/* Return error code if there are any wakeup interrupts pending. */
-	ret = check_wakeup_irqs();
-	if (ret)
-		return ret;
+	if (pm_wakeup_pending())
+		return -EBUSY;
 
 	WARN_ONCE(!irqs_disabled(),
 		"Interrupts enabled before system core suspend.\n");
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 698ad053d064..69517a24bc50 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -193,11 +193,6 @@ extern void irq_wake_thread(unsigned int irq, void *dev_id);
 /* The following three functions are for the core kernel use only. */
 extern void suspend_device_irqs(void);
 extern void resume_device_irqs(void);
-#ifdef CONFIG_PM_SLEEP
-extern int check_wakeup_irqs(void);
-#else
-static inline int check_wakeup_irqs(void) { return 0; }
-#endif
 
 /**
  * struct irq_affinity_notify - context for notification of IRQ affinity changes
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 6baf86085571..e7917ff8a486 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -344,8 +344,26 @@ static bool irq_check_poll(struct irq_desc *desc)
 
 static bool irq_may_run(struct irq_desc *desc)
 {
-	if (!irqd_irq_inprogress(&desc->irq_data))
+	unsigned int mask = IRQD_IRQ_INPROGRESS | IRQD_WAKEUP_ARMED;
+
+	/*
+	 * If the interrupt is not in progress and is not an armed
+	 * wakeup interrupt, proceed.
+	 */
+	if (!irqd_has_set(&desc->irq_data, mask))
 		return true;
+
+	/*
+	 * If the interrupt is an armed wakeup source, mark it pending
+	 * and suspended, disable it and notify the pm core about the
+	 * event.
+	 */
+	if (irq_pm_check_wakeup(desc))
+		return false;
+
+	/*
+	 * Handle a potential concurrent poll on a different core.
+	 */
 	return irq_check_poll(desc);
 }
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index c402502a5111..4332d766619d 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -196,9 +196,11 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *d
 }
 
 #ifdef CONFIG_PM_SLEEP
+bool irq_pm_check_wakeup(struct irq_desc *desc);
 void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action);
 void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action);
 #else
+static inline bool irq_pm_check_wakeup(struct irq_desc *desc) { return false; }
 static inline void
 irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { }
 static inline void
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 766930eaeed9..3ca532592704 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -9,10 +9,24 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 
 #include "internals.h"
 
+bool irq_pm_check_wakeup(struct irq_desc *desc)
+{
+	if (irqd_is_wakeup_armed(&desc->irq_data)) {
+		irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED);
+		desc->istate |= IRQS_SUSPENDED | IRQS_PENDING;
+		desc->depth++;
+		irq_disable(desc);
+		pm_system_wakeup();
+		return true;
+	}
+	return false;
+}
+
 /*
  * Called from __setup_irq() with desc->lock held after @action has
  * been installed in the action chain.
@@ -54,8 +68,16 @@ static bool suspend_device_irq(struct irq_desc *desc, int irq)
 	if (!desc->action || desc->no_suspend_depth)
 		return false;
 
-	if (irqd_is_wakeup_set(&desc->irq_data))
+	if (irqd_is_wakeup_set(&desc->irq_data)) {
 		irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
+		/*
+		 * We return true here to force the caller to issue
+		 * synchronize_irq(). We need to make sure that the
+		 * IRQD_WAKEUP_ARMED is visible before we return from
+		 * suspend_device_irqs().
+		 */
+		return true;
+	}
 
 	desc->istate |= IRQS_SUSPENDED;
 	__disable_irq(desc, irq);
@@ -79,9 +101,13 @@ static bool suspend_device_irq(struct irq_desc *desc, int irq)
  * for this purpose.
  *
  * So we disable all interrupts and mark them IRQS_SUSPENDED except
- * for those which are unused and those which are marked as not
+ * for those which are unused, those which are marked as not
  * suspendable via an interrupt request with the flag IRQF_NO_SUSPEND
- * set.
+ * set and those which are marked as active wakeup sources.
+ *
+ * The active wakeup sources are handled by the flow handler entry
+ * code which checks for the IRQD_WAKEUP_ARMED flag, suspends the
+ * interrupt and notifies the pm core about the wakeup.
  */
 void suspend_device_irqs(void)
 {
@@ -173,26 +199,3 @@ void resume_device_irqs(void)
 	resume_irqs(false);
 }
 EXPORT_SYMBOL_GPL(resume_device_irqs);
-
-/**
- * check_wakeup_irqs - check if any wake-up interrupts are pending
- */
-int check_wakeup_irqs(void)
-{
-	struct irq_desc *desc;
-	int irq;
-
-	for_each_irq_desc(irq, desc) {
-		/*
-		 * Only interrupts which are marked as wakeup source
-		 * and have not been disabled before the suspend check
-		 * can abort suspend.
-		 */
-		if (irqd_is_wakeup_set(&desc->irq_data)) {
-			if (desc->depth == 1 && desc->istate & IRQS_PENDING)
-				return -EBUSY;
-		}
-	}
-
-	return 0;
-}
-- 
cgit v1.2.3


From cfdbeeafdbbdbc006f700e92cbad2cb5d4529f3d Mon Sep 17 00:00:00 2001
From: Vincent Cuissard <cuissard@marvell.com>
Date: Tue, 22 Jul 2014 19:48:38 +0200
Subject: NFC: NCI: Add support of ISO15693

Update nci.h to respect latest NCI specification proposal
(stop using proprietary opcodes). Handle ISO15693 parameters
in NCI_RF_ACTIVATED_NTF handler.

Signed-off-by: Vincent Cuissard <cuissard@marvell.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h | 16 +++++++++++++---
 net/nfc/nci/core.c    |  8 ++++++++
 net/nfc/nci/ntf.c     | 31 +++++++++++++++++++++++++++++++
 3 files changed, 52 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index fbfa4e471abb..9eca9ae2280c 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -2,6 +2,7 @@
  *  The NFC Controller Interface is the communication protocol between an
  *  NFC Controller (NFCC) and a Device Host (DH).
  *
+ *  Copyright (C) 2014 Marvell International Ltd.
  *  Copyright (C) 2011 Texas Instruments, Inc.
  *
  *  Written by Ilan Elias <ilane@ti.com>
@@ -65,19 +66,18 @@
 #define NCI_NFC_F_PASSIVE_POLL_MODE				0x02
 #define NCI_NFC_A_ACTIVE_POLL_MODE				0x03
 #define NCI_NFC_F_ACTIVE_POLL_MODE				0x05
-#define NCI_NFC_15693_PASSIVE_POLL_MODE				0x06
+#define NCI_NFC_V_PASSIVE_POLL_MODE				0x06
 #define NCI_NFC_A_PASSIVE_LISTEN_MODE				0x80
 #define NCI_NFC_B_PASSIVE_LISTEN_MODE				0x81
 #define NCI_NFC_F_PASSIVE_LISTEN_MODE				0x82
 #define NCI_NFC_A_ACTIVE_LISTEN_MODE				0x83
 #define NCI_NFC_F_ACTIVE_LISTEN_MODE				0x85
-#define NCI_NFC_15693_PASSIVE_LISTEN_MODE			0x86
 
 /* NCI RF Technologies */
 #define NCI_NFC_RF_TECHNOLOGY_A					0x00
 #define NCI_NFC_RF_TECHNOLOGY_B					0x01
 #define NCI_NFC_RF_TECHNOLOGY_F					0x02
-#define NCI_NFC_RF_TECHNOLOGY_15693				0x03
+#define NCI_NFC_RF_TECHNOLOGY_V					0x03
 
 /* NCI Bit Rates */
 #define NCI_NFC_BIT_RATE_106					0x00
@@ -87,6 +87,7 @@
 #define NCI_NFC_BIT_RATE_1695					0x04
 #define NCI_NFC_BIT_RATE_3390					0x05
 #define NCI_NFC_BIT_RATE_6780					0x06
+#define NCI_NFC_BIT_RATE_26					0x20
 
 /* NCI RF Protocols */
 #define NCI_RF_PROTOCOL_UNKNOWN					0x00
@@ -95,6 +96,7 @@
 #define NCI_RF_PROTOCOL_T3T					0x03
 #define NCI_RF_PROTOCOL_ISO_DEP					0x04
 #define NCI_RF_PROTOCOL_NFC_DEP					0x05
+#define NCI_RF_PROTOCOL_T5T					0x06
 
 /* NCI RF Interfaces */
 #define NCI_RF_INTERFACE_NFCEE_DIRECT				0x00
@@ -328,6 +330,12 @@ struct rf_tech_specific_params_nfcf_poll {
 	__u8	sensf_res[18];	/* 16 or 18 Bytes */
 } __packed;
 
+struct rf_tech_specific_params_nfcv_poll {
+	__u8	res_flags;
+	__u8	dsfid;
+	__u8	uid[8];	/* 8 Bytes */
+} __packed;
+
 struct nci_rf_discover_ntf {
 	__u8	rf_discovery_id;
 	__u8	rf_protocol;
@@ -338,6 +346,7 @@ struct nci_rf_discover_ntf {
 		struct rf_tech_specific_params_nfca_poll nfca_poll;
 		struct rf_tech_specific_params_nfcb_poll nfcb_poll;
 		struct rf_tech_specific_params_nfcf_poll nfcf_poll;
+		struct rf_tech_specific_params_nfcv_poll nfcv_poll;
 	} rf_tech_specific_params;
 
 	__u8	ntf_type;
@@ -372,6 +381,7 @@ struct nci_rf_intf_activated_ntf {
 		struct rf_tech_specific_params_nfca_poll nfca_poll;
 		struct rf_tech_specific_params_nfcb_poll nfcb_poll;
 		struct rf_tech_specific_params_nfcf_poll nfcf_poll;
+		struct rf_tech_specific_params_nfcv_poll nfcv_poll;
 	} rf_tech_specific_params;
 
 	__u8	data_exch_rf_tech_and_mode;
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 2b400e1a8695..860080803a3e 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -231,6 +231,14 @@ static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt)
 		cmd.num_disc_configs++;
 	}
 
+	if ((cmd.num_disc_configs < NCI_MAX_NUM_RF_CONFIGS) &&
+	    (protocols & NFC_PROTO_ISO15693_MASK)) {
+		cmd.disc_configs[cmd.num_disc_configs].rf_tech_and_mode =
+			NCI_NFC_V_PASSIVE_POLL_MODE;
+		cmd.disc_configs[cmd.num_disc_configs].frequency = 1;
+		cmd.num_disc_configs++;
+	}
+
 	nci_send_cmd(ndev, NCI_OP_RF_DISCOVER_CMD,
 		     (1 + (cmd.num_disc_configs * sizeof(struct disc_config))),
 		     &cmd);
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index df91bb95b12a..25e44cebd60a 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -2,6 +2,7 @@
  *  The NFC Controller Interface is the communication protocol between an
  *  NFC Controller (NFCC) and a Device Host (DH).
  *
+ *  Copyright (C) 2014 Marvell International Ltd.
  *  Copyright (C) 2011 Texas Instruments, Inc.
  *
  *  Written by Ilan Elias <ilane@ti.com>
@@ -155,6 +156,17 @@ static __u8 *nci_extract_rf_params_nfcf_passive_poll(struct nci_dev *ndev,
 	return data;
 }
 
+static __u8 *nci_extract_rf_params_nfcv_passive_poll(struct nci_dev *ndev,
+			struct rf_tech_specific_params_nfcv_poll *nfcv_poll,
+						     __u8 *data)
+{
+	++data;
+	nfcv_poll->dsfid = *data++;
+	memcpy(nfcv_poll->uid, data, NFC_ISO15693_UID_MAXSIZE);
+	data += NFC_ISO15693_UID_MAXSIZE;
+	return data;
+}
+
 static int nci_add_new_protocol(struct nci_dev *ndev,
 				struct nfc_target *target,
 				__u8 rf_protocol,
@@ -164,6 +176,7 @@ static int nci_add_new_protocol(struct nci_dev *ndev,
 	struct rf_tech_specific_params_nfca_poll *nfca_poll;
 	struct rf_tech_specific_params_nfcb_poll *nfcb_poll;
 	struct rf_tech_specific_params_nfcf_poll *nfcf_poll;
+	struct rf_tech_specific_params_nfcv_poll *nfcv_poll;
 	__u32 protocol;
 
 	if (rf_protocol == NCI_RF_PROTOCOL_T1T)
@@ -179,6 +192,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev,
 		protocol = NFC_PROTO_FELICA_MASK;
 	else if (rf_protocol == NCI_RF_PROTOCOL_NFC_DEP)
 		protocol = NFC_PROTO_NFC_DEP_MASK;
+	else if (rf_protocol == NCI_RF_PROTOCOL_T5T)
+		protocol = NFC_PROTO_ISO15693_MASK;
 	else
 		protocol = 0;
 
@@ -213,6 +228,12 @@ static int nci_add_new_protocol(struct nci_dev *ndev,
 			memcpy(target->sensf_res, nfcf_poll->sensf_res,
 			       target->sensf_res_len);
 		}
+	} else if (rf_tech_and_mode == NCI_NFC_V_PASSIVE_POLL_MODE) {
+		nfcv_poll = (struct rf_tech_specific_params_nfcv_poll *)params;
+
+		target->is_iso15693 = 1;
+		target->iso15693_dsfid = nfcv_poll->dsfid;
+		memcpy(target->iso15693_uid, nfcv_poll->uid, NFC_ISO15693_UID_MAXSIZE);
 	} else {
 		pr_err("unsupported rf_tech_and_mode 0x%x\n", rf_tech_and_mode);
 		return -EPROTO;
@@ -305,6 +326,11 @@ static void nci_rf_discover_ntf_packet(struct nci_dev *ndev,
 				&(ntf.rf_tech_specific_params.nfcf_poll), data);
 			break;
 
+		case NCI_NFC_V_PASSIVE_POLL_MODE:
+			data = nci_extract_rf_params_nfcv_passive_poll(ndev,
+				&(ntf.rf_tech_specific_params.nfcv_poll), data);
+			break;
+
 		default:
 			pr_err("unsupported rf_tech_and_mode 0x%x\n",
 			       ntf.rf_tech_and_mode);
@@ -455,6 +481,11 @@ static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 				&(ntf.rf_tech_specific_params.nfcf_poll), data);
 			break;
 
+		case NCI_NFC_V_PASSIVE_POLL_MODE:
+			data = nci_extract_rf_params_nfcv_passive_poll(ndev,
+				&(ntf.rf_tech_specific_params.nfcv_poll), data);
+			break;
+
 		default:
 			pr_err("unsupported activation_rf_tech_and_mode 0x%x\n",
 			       ntf.activation_rf_tech_and_mode);
-- 
cgit v1.2.3


From 10b3ad8c21bb4b135768c30dd4c51a1c744da699 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 29 Aug 2014 21:07:24 -0700
Subject: net: Do txq_trans_update() in netdev_start_xmit()

That way we don't have to audit every call site to make sure it is
doing this properly.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/dlci.c    |  6 ++++--
 include/linux/netdevice.h | 10 ++++++++--
 net/core/dev.c            |  7 ++-----
 net/core/netpoll.c        |  4 +---
 net/core/pktgen.c         |  3 +--
 net/packet/af_packet.c    |  7 ++-----
 net/sched/sch_teql.c      |  3 +--
 7 files changed, 19 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 81b22a180aad..6427e8283419 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -192,8 +192,10 @@ static netdev_tx_t dlci_transmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dlci_local *dlp = netdev_priv(dev);
 
-	if (skb)
-		netdev_start_xmit(skb, dlp->slave);
+	if (skb) {
+		struct netdev_queue *txq = skb_get_tx_queue(dev, skb);
+		netdev_start_xmit(skb, dlp->slave, txq);
+	}
 	return NETDEV_TX_OK;
 }
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 456eb1fe51e8..16171802ea7d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3437,11 +3437,17 @@ static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
 	return ops->ndo_start_xmit(skb, dev);
 }
 
-static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev,
+					    struct netdev_queue *txq)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int rc;
 
-	return __netdev_start_xmit(ops, skb, dev);
+	rc = __netdev_start_xmit(ops, skb, dev);
+	if (rc == NETDEV_TX_OK)
+		txq_trans_update(txq);
+
+	return rc;
 }
 
 int netdev_class_create_file_ns(struct class_attribute *class_attr,
diff --git a/net/core/dev.c b/net/core/dev.c
index a6077ef56345..6392adaaa22f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2666,10 +2666,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 		skb_len = skb->len;
 		trace_net_dev_start_xmit(skb, dev);
-		rc = netdev_start_xmit(skb, dev);
+		rc = netdev_start_xmit(skb, dev, txq);
 		trace_net_dev_xmit(skb, rc, dev, skb_len);
-		if (rc == NETDEV_TX_OK)
-			txq_trans_update(txq);
 		return rc;
 	}
 
@@ -2685,7 +2683,7 @@ gso:
 
 		skb_len = nskb->len;
 		trace_net_dev_start_xmit(nskb, dev);
-		rc = netdev_start_xmit(nskb, dev);
+		rc = netdev_start_xmit(nskb, dev, txq);
 		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
@@ -2694,7 +2692,6 @@ gso:
 			skb->next = nskb;
 			return rc;
 		}
-		txq_trans_update(txq);
 		if (unlikely(netif_xmit_stopped(txq) && skb->next))
 			return NETDEV_TX_BUSY;
 	} while (skb->next);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 12b1df976562..05bc57edaa81 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -91,9 +91,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 		skb->vlan_tci = 0;
 	}
 
-	status = netdev_start_xmit(skb, dev);
-	if (status == NETDEV_TX_OK)
-		txq_trans_update(txq);
+	status = netdev_start_xmit(skb, dev, txq);
 
 out:
 	return status;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index d81b540096c3..34bd2ff9f121 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3335,11 +3335,10 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 		goto unlock;
 	}
 	atomic_inc(&(pkt_dev->skb->users));
-	ret = netdev_start_xmit(pkt_dev->skb, odev);
+	ret = netdev_start_xmit(pkt_dev->skb, odev, txq);
 
 	switch (ret) {
 	case NETDEV_TX_OK:
-		txq_trans_update(txq);
 		pkt_dev->last_ok = 1;
 		pkt_dev->sofar++;
 		pkt_dev->seq_num++;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b7a7f5a721bd..fe305a05a8fc 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -258,11 +258,8 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	local_bh_disable();
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
-	if (!netif_xmit_frozen_or_drv_stopped(txq)) {
-		ret = netdev_start_xmit(skb, dev);
-		if (ret == NETDEV_TX_OK)
-			txq_trans_update(txq);
-	}
+	if (!netif_xmit_frozen_or_drv_stopped(txq))
+		ret = netdev_start_xmit(skb, dev, txq);
 	HARD_TX_UNLOCK(dev, txq);
 
 	local_bh_enable();
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 64cd93ca8104..193dc2cba1ec 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -316,8 +316,7 @@ restart:
 				unsigned int length = qdisc_pkt_len(skb);
 
 				if (!netif_xmit_frozen_or_stopped(slave_txq) &&
-				    netdev_start_xmit(skb, slave) == NETDEV_TX_OK) {
-					txq_trans_update(slave_txq);
+				    netdev_start_xmit(skb, slave, slave_txq) == NETDEV_TX_OK) {
 					__netif_tx_unlock(slave_txq);
 					master->slaves = NEXT_SLAVE(q);
 					netif_wake_queue(dev);
-- 
cgit v1.2.3


From fa2dbdc253c2aee2a760c64de454cb62469ec11d Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 29 Aug 2014 21:55:22 -0700
Subject: net: Pass a "more" indication down into netdev_start_xmit() code
 paths.

For now it will always be false.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/dlci.c    | 2 +-
 include/linux/netdevice.h | 9 +++++----
 net/atm/mpc.c             | 2 +-
 net/core/dev.c            | 2 +-
 net/core/netpoll.c        | 2 +-
 net/core/pktgen.c         | 2 +-
 net/packet/af_packet.c    | 2 +-
 net/sched/sch_teql.c      | 3 ++-
 8 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 6427e8283419..ae6ecf401189 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -194,7 +194,7 @@ static netdev_tx_t dlci_transmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (skb) {
 		struct netdev_queue *txq = skb_get_tx_queue(dev, skb);
-		netdev_start_xmit(skb, dlp->slave, txq);
+		netdev_start_xmit(skb, dlp->slave, txq, false);
 	}
 	return NETDEV_TX_OK;
 }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 16171802ea7d..5050218c5b7f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3431,19 +3431,20 @@ int __init dev_proc_init(void);
 #endif
 
 static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
-					      struct sk_buff *skb, struct net_device *dev)
+					      struct sk_buff *skb, struct net_device *dev,
+					      bool more)
 {
-	skb->xmit_more = 0;
+	skb->xmit_more = more ? 1 : 0;
 	return ops->ndo_start_xmit(skb, dev);
 }
 
 static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev,
-					    struct netdev_queue *txq)
+					    struct netdev_queue *txq, bool more)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc;
 
-	rc = __netdev_start_xmit(ops, skb, dev);
+	rc = __netdev_start_xmit(ops, skb, dev, more);
 	if (rc == NETDEV_TX_OK)
 		txq_trans_update(txq);
 
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index d662da161e5a..0e982222d425 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -599,7 +599,7 @@ static netdev_tx_t mpc_send_packet(struct sk_buff *skb,
 	}
 
 non_ip:
-	return __netdev_start_xmit(mpc->old_ops, skb, dev);
+	return __netdev_start_xmit(mpc->old_ops, skb, dev, false);
 }
 
 static int atm_mpoa_vcc_attach(struct atm_vcc *vcc, void __user *arg)
diff --git a/net/core/dev.c b/net/core/dev.c
index ab7bb809711e..f0ed5a611a97 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2610,7 +2610,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 	len = skb->len;
 	trace_net_dev_start_xmit(skb, dev);
-	rc = netdev_start_xmit(skb, dev, txq);
+	rc = netdev_start_xmit(skb, dev, txq, false);
 	trace_net_dev_xmit(skb, rc, dev, len);
 
 	return rc;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 05bc57edaa81..e6645b4f330a 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -91,7 +91,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 		skb->vlan_tci = 0;
 	}
 
-	status = netdev_start_xmit(skb, dev, txq);
+	status = netdev_start_xmit(skb, dev, txq, false);
 
 out:
 	return status;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 34bd2ff9f121..5b36a9428c59 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3335,7 +3335,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 		goto unlock;
 	}
 	atomic_inc(&(pkt_dev->skb->users));
-	ret = netdev_start_xmit(pkt_dev->skb, odev, txq);
+	ret = netdev_start_xmit(pkt_dev->skb, odev, txq, false);
 
 	switch (ret) {
 	case NETDEV_TX_OK:
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index fe305a05a8fc..87d20f48ff06 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -259,7 +259,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_drv_stopped(txq))
-		ret = netdev_start_xmit(skb, dev, txq);
+		ret = netdev_start_xmit(skb, dev, txq, false);
 	HARD_TX_UNLOCK(dev, txq);
 
 	local_bh_enable();
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 193dc2cba1ec..aaa8d03ed054 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -316,7 +316,8 @@ restart:
 				unsigned int length = qdisc_pkt_len(skb);
 
 				if (!netif_xmit_frozen_or_stopped(slave_txq) &&
-				    netdev_start_xmit(skb, slave, slave_txq) == NETDEV_TX_OK) {
+				    netdev_start_xmit(skb, slave, slave_txq, false) ==
+				    NETDEV_TX_OK) {
 					__netif_tx_unlock(slave_txq);
 					master->slaves = NEXT_SLAVE(q);
 					netif_wake_queue(dev);
-- 
cgit v1.2.3


From 50cbe9ab5f8d92d2d4a327b56e96559d8f63a1fa Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 30 Aug 2014 19:13:51 -0700
Subject: net: Validate xmit SKBs right when we pull them out of the qdisc.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 1 +
 net/core/dev.c            | 6 +-----
 net/sched/sch_generic.c   | 5 ++++-
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5050218c5b7f..47c49ba2dcf4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2827,6 +2827,7 @@ int dev_set_mac_address(struct net_device *, struct sockaddr *);
 int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_port_id *ppid);
+struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev);
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			struct netdev_queue *txq);
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index 704a5434f77d..75bc5b068a13 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2656,7 +2656,7 @@ struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t featur
 	return skb;
 }
 
-static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
+struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
 {
 	netdev_features_t features;
 
@@ -2719,10 +2719,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 {
 	int rc = NETDEV_TX_OK;
 
-	skb = validate_xmit_skb(skb, dev);
-	if (!skb)
-		return rc;
-
 	if (likely(!skb->next))
 		return xmit_one(skb, dev, txq, false);
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 05b3f5d104af..f178798a5836 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -70,8 +70,11 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 		} else
 			skb = NULL;
 	} else {
-		if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq))
+		if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq)) {
 			skb = q->dequeue(q);
+			if (skb)
+				skb = validate_xmit_skb(skb, qdisc_dev(q));
+		}
 	}
 
 	return skb;
-- 
cgit v1.2.3


From ce93718fb7cdbc064c3000ff59e4d3200bdfa744 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 30 Aug 2014 19:22:20 -0700
Subject: net: Don't keep around original SKB when we software segment GSO
 frames.

Just maintain the list properly by returning the head of the remaining
SKB list from dev_hard_start_xmit().

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  4 +--
 net/core/dev.c            | 79 +++++++++--------------------------------------
 net/sched/sch_generic.c   |  2 +-
 3 files changed, 17 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 47c49ba2dcf4..202c25a9aadf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2828,8 +2828,8 @@ int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_port_id *ppid);
 struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev);
-int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq);
+struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
+				    struct netdev_queue *txq, int *ret);
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index 75bc5b068a13..c89da4f306b1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2485,52 +2485,6 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 	return 0;
 }
 
-struct dev_gso_cb {
-	void (*destructor)(struct sk_buff *skb);
-};
-
-#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb)
-
-static void dev_gso_skb_destructor(struct sk_buff *skb)
-{
-	struct dev_gso_cb *cb;
-
-	kfree_skb_list(skb->next);
-	skb->next = NULL;
-
-	cb = DEV_GSO_CB(skb);
-	if (cb->destructor)
-		cb->destructor(skb);
-}
-
-/**
- *	dev_gso_segment - Perform emulated hardware segmentation on skb.
- *	@skb: buffer to segment
- *	@features: device features as applicable to this skb
- *
- *	This function segments the given skb and stores the list of segments
- *	in skb->next.
- */
-static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
-{
-	struct sk_buff *segs;
-
-	segs = skb_gso_segment(skb, features);
-
-	/* Verifying header integrity only. */
-	if (!segs)
-		return 0;
-
-	if (IS_ERR(segs))
-		return PTR_ERR(segs);
-
-	skb->next = segs;
-	DEV_GSO_CB(skb)->destructor = skb->destructor;
-	skb->destructor = dev_gso_skb_destructor;
-
-	return 0;
-}
-
 /* If MPLS offload request, verify we are testing hardware MPLS features
  * instead of standard features for the netdev.
  */
@@ -2682,8 +2636,13 @@ struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
 		features &= dev->hw_enc_features;
 
 	if (netif_needs_gso(skb, features)) {
-		if (unlikely(dev_gso_segment(skb, features)))
-			goto out_kfree_skb;
+		struct sk_buff *segs;
+
+		segs = skb_gso_segment(skb, features);
+		kfree_skb(skb);
+		if (IS_ERR(segs))
+			segs = NULL;
+		skb = segs;
 	} else {
 		if (skb_needs_linearize(skb, features) &&
 		    __skb_linearize(skb))
@@ -2714,26 +2673,16 @@ out_null:
 	return NULL;
 }
 
-int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq)
+struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
+				    struct netdev_queue *txq, int *ret)
 {
-	int rc = NETDEV_TX_OK;
-
-	if (likely(!skb->next))
-		return xmit_one(skb, dev, txq, false);
-
-	skb->next = xmit_list(skb->next, dev, txq, &rc);
-	if (likely(skb->next == NULL)) {
-		skb->destructor = DEV_GSO_CB(skb)->destructor;
-		consume_skb(skb);
-		return rc;
+	if (likely(!skb->next)) {
+		*ret = xmit_one(skb, dev, txq, false);
+		return skb;
 	}
 
-	kfree_skb(skb);
-
-	return rc;
+	return xmit_list(skb, dev, txq, ret);
 }
-EXPORT_SYMBOL_GPL(dev_hard_start_xmit);
 
 static void qdisc_pkt_len_init(struct sk_buff *skb)
 {
@@ -2945,7 +2894,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 
 			if (!netif_xmit_stopped(txq)) {
 				__this_cpu_inc(xmit_recursion);
-				rc = dev_hard_start_xmit(skb, dev, txq);
+				skb = dev_hard_start_xmit(skb, dev, txq, &rc);
 				__this_cpu_dec(xmit_recursion);
 				if (dev_xmit_complete(rc)) {
 					HARD_TX_UNLOCK(dev, txq);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index f178798a5836..a8bf9f9928bd 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -129,7 +129,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_stopped(txq))
-		ret = dev_hard_start_xmit(skb, dev, txq);
+		skb = dev_hard_start_xmit(skb, dev, txq, &ret);
 
 	HARD_TX_UNLOCK(dev, txq);
 
-- 
cgit v1.2.3


From 5a21232983aa7acfe7fd26170832a9e0a4a7b4ae Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Sun, 31 Aug 2014 15:12:41 -0700
Subject: net: Support for csum_bad in skbuff

This flag indicates that an invalid checksum was detected in the
packet. __skb_mark_checksum_bad helper function was added to set this.

Checksums can be marked bad from a driver or the GRO path (the latter
is implemented in this patch). csum_bad is checked in
__skb_checksum_validate_complete (i.e. calling that when ip_summed ==
CHECKSUM_NONE).

csum_bad works in conjunction with ip_summed value. In the case that
ip_summed is CHECKSUM_NONE and csum_bad is set, this implies that the
first (or next) checksum encountered in the packet is bad. When
ip_summed is CHECKSUM_UNNECESSARY, the first checksum after the last
one validated is bad. For example, if ip_summed == CHECKSUM_UNNECESSARY,
csum_level == 1, and csum_bad is set-- then the third checksum in the
packet is bad. In the normal path, the packet will be dropped when
processing the protocol layer of the bad checksum:
__skb_decr_checksum_unnecessary called twice for the good checksums
changing ip_summed to CHECKSUM_NONE so that
__skb_checksum_validate_complete is called to validate the third
checksum and that will fail since csum_bad is set.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  4 +++-
 include/linux/skbuff.h    | 21 ++++++++++++++++++++-
 net/core/dev.c            |  2 +-
 3 files changed, 24 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 202c25a9aadf..a0ab6d9d400a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2216,7 +2216,9 @@ static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb)
 	if (__skb_gro_checksum_validate_needed(skb, zero_okay, check))	\
 		__ret = __skb_gro_checksum_validate_complete(skb,	\
 				compute_pseudo(skb, proto));		\
-	if (!__ret)							\
+	if (__ret)							\
+		__skb_mark_checksum_bad(skb);				\
+	else								\
 		skb_gro_incr_csum_unnecessary(skb);			\
 	__ret;								\
 })
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c93b5859a772..23710a243439 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -617,7 +617,8 @@ struct sk_buff {
 
 	kmemcheck_bitfield_begin(flags3);
 	__u8			csum_level:2;
-	/* 14 bit hole */
+	__u8			csum_bad:1;
+	/* 13 bit hole */
 	kmemcheck_bitfield_end(flags3);
 
 	__be16			inner_protocol;
@@ -2825,6 +2826,21 @@ static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb)
 	}
 }
 
+static inline void __skb_mark_checksum_bad(struct sk_buff *skb)
+{
+	/* Mark current checksum as bad (typically called from GRO
+	 * path). In the case that ip_summed is CHECKSUM_NONE
+	 * this must be the first checksum encountered in the packet.
+	 * When ip_summed is CHECKSUM_UNNECESSARY, this is the first
+	 * checksum after the last one validated. For UDP, a zero
+	 * checksum can not be marked as bad.
+	 */
+
+	if (skb->ip_summed == CHECKSUM_NONE ||
+	    skb->ip_summed == CHECKSUM_UNNECESSARY)
+		skb->csum_bad = 1;
+}
+
 /* Check if we need to perform checksum complete validation.
  *
  * Returns true if checksum complete is needed, false otherwise
@@ -2866,6 +2882,9 @@ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb,
 			skb->csum_valid = 1;
 			return 0;
 		}
+	} else if (skb->csum_bad) {
+		/* ip_summed == CHECKSUM_NONE in this case */
+		return 1;
 	}
 
 	skb->csum = psum;
diff --git a/net/core/dev.c b/net/core/dev.c
index 6857d57aa294..3774afc3bebf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3918,7 +3918,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (!(skb->dev->features & NETIF_F_GRO))
 		goto normal;
 
-	if (skb_is_gso(skb) || skb_has_frag_list(skb))
+	if (skb_is_gso(skb) || skb_has_frag_list(skb) || skb->csum_bad)
 		goto normal;
 
 	gro_list_prepare(napi, skb);
-- 
cgit v1.2.3


From d96535a17dbbafd567961d14c08c0984ddda9c3c Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Sun, 31 Aug 2014 15:12:42 -0700
Subject: net: Infrastructure for checksum unnecessary conversions

For normal path, added skb_checksum_try_convert which is called
to attempt to convert CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE. The
primary condition to allow this is that ip_summed is CHECKSUM_NONE
and csum_valid is true, which will be the state after consuming
a CHECKSUM_UNNECESSARY.

For GRO path, added skb_gro_checksum_try_convert which is the GRO
analogue of skb_checksum_try_convert. The primary condition to allow
this is that NAPI_GRO_CB(skb)->csum_cnt == 0 and
NAPI_GRO_CB(skb)->csum_valid is set. This implies that we have consumed
all available CHECKSUM_UNNECESSARY checksums in the GRO path.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 20 ++++++++++++++++++++
 include/linux/skbuff.h    | 20 ++++++++++++++++++++
 2 files changed, 40 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a0ab6d9d400a..5be20a7bbb0d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2233,6 +2233,26 @@ static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb)
 #define skb_gro_checksum_simple_validate(skb)				\
 	__skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo)
 
+static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb)
+{
+	return (NAPI_GRO_CB(skb)->csum_cnt == 0 &&
+		!NAPI_GRO_CB(skb)->csum_valid);
+}
+
+static inline void __skb_gro_checksum_convert(struct sk_buff *skb,
+					      __sum16 check, __wsum pseudo)
+{
+	NAPI_GRO_CB(skb)->csum = ~pseudo;
+	NAPI_GRO_CB(skb)->csum_valid = 1;
+}
+
+#define skb_gro_checksum_try_convert(skb, proto, check, compute_pseudo)	\
+do {									\
+	if (__skb_gro_checksum_convert_check(skb))			\
+		__skb_gro_checksum_convert(skb, check,			\
+					   compute_pseudo(skb, proto));	\
+} while (0)
+
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 				  unsigned short type,
 				  const void *daddr, const void *saddr,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 23710a243439..02529fcad1ac 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2942,6 +2942,26 @@ static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto)
 #define skb_checksum_simple_validate(skb)				\
 	__skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo)
 
+static inline bool __skb_checksum_convert_check(struct sk_buff *skb)
+{
+	return (skb->ip_summed == CHECKSUM_NONE &&
+		skb->csum_valid && !skb->csum_bad);
+}
+
+static inline void __skb_checksum_convert(struct sk_buff *skb,
+					  __sum16 check, __wsum pseudo)
+{
+	skb->csum = ~pseudo;
+	skb->ip_summed = CHECKSUM_COMPLETE;
+}
+
+#define skb_checksum_try_convert(skb, proto, check, compute_pseudo)	\
+do {									\
+	if (__skb_checksum_convert_check(skb))				\
+		__skb_checksum_convert(skb, check,			\
+				       compute_pseudo(skb, proto));	\
+} while (0)
+
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 void nf_conntrack_destroy(struct nf_conntrack *nfct);
 static inline void nf_conntrack_put(struct nf_conntrack *nfct)
-- 
cgit v1.2.3


From 2abb7cdc0dc84e99b76ef983a1ae1978922aa9b3 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Sun, 31 Aug 2014 15:12:43 -0700
Subject: udp: Add support for doing checksum unnecessary conversion

Add support for doing CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE
conversion in UDP tunneling path.

In the normal UDP path, we call skb_checksum_try_convert after locating
the UDP socket. The check is that checksum conversion is enabled for
the socket (new flag in UDP socket) and that checksum field is
non-zero.

In the UDP GRO path, we call skb_gro_checksum_try_convert after
checksum is validated and checksum field is non-zero. Since this is
already in GRO we assume that checksum conversion is always wanted.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h    | 16 +++++++++++++++-
 net/ipv4/udp.c         |  4 ++++
 net/ipv4/udp_offload.c | 25 +++++++++++++++++--------
 net/ipv6/udp.c         |  4 ++++
 net/ipv6/udp_offload.c | 24 +++++++++++++++++-------
 5 files changed, 57 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 247cfdcc4b08..ee3277593222 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -49,7 +49,11 @@ struct udp_sock {
 	unsigned int	 corkflag;	/* Cork is required */
 	__u8		 encap_type;	/* Is this an Encapsulation socket? */
 	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
-			 no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */
+			 no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
+			 convert_csum:1;/* On receive, convert checksum
+					 * unnecessary to checksum complete
+					 * if possible.
+					 */
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
@@ -98,6 +102,16 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
 	return udp_sk(sk)->no_check6_rx;
 }
 
+static inline void udp_set_convert_csum(struct sock *sk, bool val)
+{
+	udp_sk(sk)->convert_csum = val;
+}
+
+static inline bool udp_get_convert_csum(struct sock *sk)
+{
+	return udp_sk(sk)->convert_csum;
+}
+
 #define udp_portaddr_for_each_entry(__sk, node, list) \
 	hlist_nulls_for_each_entry(__sk, node, list, __sk_common.skc_portaddr_node)
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3549c21fe5f7..0da3849fd35b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1788,6 +1788,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (sk != NULL) {
 		int ret;
 
+		if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+						 inet_compute_pseudo);
+
 		ret = udp_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index a6adff98382a..84e0e05c9c0e 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -290,16 +290,25 @@ static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
-	/* Don't bother verifying checksum if we're going to flush anyway. */
-	if (unlikely(!uh) ||
-	    (!NAPI_GRO_CB(skb)->flush &&
-	     skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
-						  inet_gro_compute_pseudo))) {
-		NAPI_GRO_CB(skb)->flush = 1;
-		return NULL;
-	}
+	if (unlikely(!uh))
+		goto flush;
 
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if (!NAPI_GRO_CB(skb)->flush)
+		goto skip;
+
+	if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+						 inet_gro_compute_pseudo))
+		goto flush;
+	else if (uh->check)
+		skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+					     inet_gro_compute_pseudo);
+skip:
 	return udp_gro_receive(head, skb, uh);
+
+flush:
+	NAPI_GRO_CB(skb)->flush = 1;
+	return NULL;
 }
 
 int udp_gro_complete(struct sk_buff *skb, int nhoff)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 12fcce8fba46..f6ba535b6feb 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -891,6 +891,10 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			goto csum_error;
 		}
 
+		if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+						 ip6_compute_pseudo);
+
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b13e377e9c53..89cb9a9b8537 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -134,16 +134,26 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
+	if (unlikely(!uh))
+		goto flush;
+
 	/* Don't bother verifying checksum if we're going to flush anyway. */
-	if (unlikely(!uh) ||
-	    (!NAPI_GRO_CB(skb)->flush &&
-	     skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
-						  ip6_gro_compute_pseudo))) {
-		NAPI_GRO_CB(skb)->flush = 1;
-		return NULL;
-	}
+	if (!NAPI_GRO_CB(skb)->flush)
+		goto skip;
 
+	if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+						 ip6_gro_compute_pseudo))
+		goto flush;
+	else if (uh->check)
+		skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+					     ip6_gro_compute_pseudo);
+
+skip:
 	return udp_gro_receive(head, skb, uh);
+
+flush:
+	NAPI_GRO_CB(skb)->flush = 1;
+	return NULL;
 }
 
 int udp6_gro_complete(struct sk_buff *skb, int nhoff)
-- 
cgit v1.2.3


From 364a9e93243d1785f310c0964af0e24bf1adac03 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 31 Aug 2014 21:30:27 -0400
Subject: sock: deduplicate errqueue dequeue

sk->sk_error_queue is dequeued in four locations. All share the
exact same logic. Deduplicate.

Also collapse the two critical sections for dequeue (at the top of
the recv handler) and signal (at the bottom).

This moves signal generation for the next packet forward, which should
be harmless.

It also changes the behavior if the recv handler exits early with an
error. Previously, a signal for follow-up packets on the errqueue
would then not be scheduled. The new behavior, to always signal, is
arguably a bug fix.

For rxrpc, the change causes the same function to be called repeatedly
for each queued packet (because the recv handler == sk_error_report).
It is likely that all packets will fail for the same reason (e.g.,
memory exhaustion).

This code runs without sk_lock held, so it is not safe to trust that
sk->sk_err is immutable inbetween releasing q->lock and the subsequent
test. Introduce int err just to avoid this potential race.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h     |  1 +
 net/core/skbuff.c      | 20 ++++++++++++++++++++
 net/core/sock.c        | 14 ++------------
 net/ipv4/ip_sockglue.c | 15 ++-------------
 net/ipv6/datagram.c    | 15 ++-------------
 net/rxrpc/ar-error.c   | 14 +-------------
 6 files changed, 28 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 7f2ab72f321a..3fde6130789d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2041,6 +2041,7 @@ void sk_stop_timer(struct sock *sk, struct timer_list *timer);
 int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
+struct sk_buff *sock_dequeue_err_skb(struct sock *sk);
 
 /*
  *	Recover an error report and clear atomically
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 163b673f9e62..53ce536e3d6e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3491,6 +3491,26 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
 
+struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
+{
+	struct sk_buff_head *q = &sk->sk_error_queue;
+	struct sk_buff *skb, *skb_next;
+	int err = 0;
+
+	spin_lock_bh(&q->lock);
+	skb = __skb_dequeue(q);
+	if (skb && (skb_next = skb_peek(q)))
+		err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
+	spin_unlock_bh(&q->lock);
+
+	sk->sk_err = err;
+	if (err)
+		sk->sk_error_report(sk);
+
+	return skb;
+}
+EXPORT_SYMBOL(sock_dequeue_err_skb);
+
 void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     struct skb_shared_hwtstamps *hwtstamps,
 		     struct sock *sk, int tstype)
diff --git a/net/core/sock.c b/net/core/sock.c
index f7f2352200ad..f1a638ee93d9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2488,11 +2488,11 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
 		       int level, int type)
 {
 	struct sock_exterr_skb *serr;
-	struct sk_buff *skb, *skb2;
+	struct sk_buff *skb;
 	int copied, err;
 
 	err = -EAGAIN;
-	skb = skb_dequeue(&sk->sk_error_queue);
+	skb = sock_dequeue_err_skb(sk);
 	if (skb == NULL)
 		goto out;
 
@@ -2513,16 +2513,6 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
 	msg->msg_flags |= MSG_ERRQUEUE;
 	err = copied;
 
-	/* Reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
-		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-
 out_free_skb:
 	kfree_skb(skb);
 out:
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5cb830c78990..455e75bcb167 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -405,7 +405,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct sock_exterr_skb *serr;
-	struct sk_buff *skb, *skb2;
+	struct sk_buff *skb;
 	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct {
 		struct sock_extended_err ee;
@@ -415,7 +415,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	int copied;
 
 	err = -EAGAIN;
-	skb = skb_dequeue(&sk->sk_error_queue);
+	skb = sock_dequeue_err_skb(sk);
 	if (skb == NULL)
 		goto out;
 
@@ -462,17 +462,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	msg->msg_flags |= MSG_ERRQUEUE;
 	err = copied;
 
-	/* Reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	skb2 = skb_peek(&sk->sk_error_queue);
-	if (skb2 != NULL) {
-		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-
 out_free_skb:
 	kfree_skb(skb);
 out:
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 1844e874a350..2cdc38338be3 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -332,7 +332,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sock_exterr_skb *serr;
-	struct sk_buff *skb, *skb2;
+	struct sk_buff *skb;
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name);
 	struct {
 		struct sock_extended_err ee;
@@ -342,7 +342,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	int copied;
 
 	err = -EAGAIN;
-	skb = skb_dequeue(&sk->sk_error_queue);
+	skb = sock_dequeue_err_skb(sk);
 	if (skb == NULL)
 		goto out;
 
@@ -415,17 +415,6 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	msg->msg_flags |= MSG_ERRQUEUE;
 	err = copied;
 
-	/* Reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
-		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else {
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-	}
-
 out_free_skb:
 	kfree_skb(skb);
 out:
diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c
index db57458c824c..74c0fcd36838 100644
--- a/net/rxrpc/ar-error.c
+++ b/net/rxrpc/ar-error.c
@@ -37,7 +37,7 @@ void rxrpc_UDP_error_report(struct sock *sk)
 
 	_enter("%p{%d}", sk, local->debug_id);
 
-	skb = skb_dequeue(&sk->sk_error_queue);
+	skb = sock_dequeue_err_skb(sk);
 	if (!skb) {
 		_leave("UDP socket errqueue empty");
 		return;
@@ -111,18 +111,6 @@ void rxrpc_UDP_error_report(struct sock *sk)
 	skb_queue_tail(&trans->error_queue, skb);
 	rxrpc_queue_work(&trans->error_handler);
 
-	/* reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	skb = skb_peek(&sk->sk_error_queue);
-	if (skb) {
-		sk->sk_err = SKB_EXT_ERR(skb)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else {
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-	}
-
 	_leave("");
 }
 
-- 
cgit v1.2.3


From 0dbc8b7afef6e4fddcfebcbacbeb269a0a3b06d5 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 1 Sep 2014 15:15:40 +0200
Subject: gpio: move varargs hack outside #ifdef GPIOLIB

commit 39b2bbe3d715cf5013b5c48695ccdd25bd3bf120
"gpio: add flags argument to gpiod_get*() functions"
added a dynamic flags argument to all the GPIOD getter
functions, however this did not cover the stubs so
when people used gpiod stubs to compile out descriptor
code, compilation failed.

Solve this by:
- Also rename all the stub functions __gpiod_*
- Moving the vararg hack outside of #ifdef CONFIG_GPIOLIB
  so these will always be available.

Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio/consumer.h | 105 ++++++++++++++++++++++++------------------
 1 file changed, 60 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index c7e17de732f3..12f146fa6604 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -38,60 +38,32 @@ enum gpiod_flags {
 struct gpio_desc *__must_check __gpiod_get(struct device *dev,
 					 const char *con_id,
 					 enum gpiod_flags flags);
-#define __gpiod_get(dev, con_id, flags, ...) __gpiod_get(dev, con_id, flags)
-#define gpiod_get(varargs...) __gpiod_get(varargs, 0)
 struct gpio_desc *__must_check __gpiod_get_index(struct device *dev,
 					       const char *con_id,
 					       unsigned int idx,
 					       enum gpiod_flags flags);
-#define __gpiod_get_index(dev, con_id, index, flags, ...)		\
-	__gpiod_get_index(dev, con_id, index, flags)
-#define gpiod_get_index(varargs...) __gpiod_get_index(varargs, 0)
 struct gpio_desc *__must_check __gpiod_get_optional(struct device *dev,
 						  const char *con_id,
 						  enum gpiod_flags flags);
-#define __gpiod_get_optional(dev, con_id, flags, ...)			\
-	__gpiod_get_optional(dev, con_id, flags)
-#define gpiod_get_optional(varargs...) __gpiod_get_optional(varargs, 0)
 struct gpio_desc *__must_check __gpiod_get_index_optional(struct device *dev,
 							const char *con_id,
 							unsigned int index,
 							enum gpiod_flags flags);
-#define __gpiod_get_index_optional(dev, con_id, index, flags, ...)	\
-	__gpiod_get_index_optional(dev, con_id, index, flags)
-#define gpiod_get_index_optional(varargs...)				\
-	__gpiod_get_index_optional(varargs, 0)
-
 void gpiod_put(struct gpio_desc *desc);
 
 struct gpio_desc *__must_check __devm_gpiod_get(struct device *dev,
 					      const char *con_id,
 					      enum gpiod_flags flags);
-#define __devm_gpiod_get(dev, con_id, flags, ...)			\
-	__devm_gpiod_get(dev, con_id, flags)
-#define devm_gpiod_get(varargs...) __devm_gpiod_get(varargs, 0)
 struct gpio_desc *__must_check __devm_gpiod_get_index(struct device *dev,
 						    const char *con_id,
 						    unsigned int idx,
 						    enum gpiod_flags flags);
-#define __devm_gpiod_get_index(dev, con_id, index, flags, ...)		\
-	__devm_gpiod_get_index(dev, con_id, index, flags)
-#define devm_gpiod_get_index(varargs...) __devm_gpiod_get_index(varargs, 0)
 struct gpio_desc *__must_check __devm_gpiod_get_optional(struct device *dev,
 						       const char *con_id,
 						       enum gpiod_flags flags);
-#define __devm_gpiod_get_optional(dev, con_id, flags, ...)		\
-	__devm_gpiod_get_optional(dev, con_id, flags)
-#define devm_gpiod_get_optional(varargs...)				\
-	__devm_gpiod_get_optional(varargs, 0)
 struct gpio_desc *__must_check
 __devm_gpiod_get_index_optional(struct device *dev, const char *con_id,
 			      unsigned int index, enum gpiod_flags flags);
-#define __devm_gpiod_get_index_optional(dev, con_id, index, flags, ...)	\
-	__devm_gpiod_get_index_optional(dev, con_id, index, flags)
-#define devm_gpiod_get_index_optional(varargs...)			\
-	__devm_gpiod_get_index_optional(varargs, 0)
-
 void devm_gpiod_put(struct device *dev, struct gpio_desc *desc);
 
 int gpiod_get_direction(const struct gpio_desc *desc);
@@ -124,27 +96,31 @@ int desc_to_gpio(const struct gpio_desc *desc);
 
 #else /* CONFIG_GPIOLIB */
 
-static inline struct gpio_desc *__must_check gpiod_get(struct device *dev,
-						       const char *con_id)
+static inline struct gpio_desc *__must_check __gpiod_get(struct device *dev,
+						const char *con_id,
+						enum gpiod_flags flags)
 {
 	return ERR_PTR(-ENOSYS);
 }
-static inline struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
-							     const char *con_id,
-							     unsigned int idx)
+static inline struct gpio_desc *__must_check
+__gpiod_get_index(struct device *dev,
+		  const char *con_id,
+		  unsigned int idx,
+		  enum gpiod_flags flags)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
 static inline struct gpio_desc *__must_check
-gpiod_get_optional(struct device *dev, const char *con_id)
+__gpiod_get_optional(struct device *dev, const char *con_id,
+		     enum gpiod_flags flags)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
 static inline struct gpio_desc *__must_check
-gpiod_get_index_optional(struct device *dev, const char *con_id,
-			 unsigned int index)
+__gpiod_get_index_optional(struct device *dev, const char *con_id,
+			   unsigned int index, enum gpiod_flags flags)
 {
 	return ERR_PTR(-ENOSYS);
 }
@@ -157,28 +133,33 @@ static inline void gpiod_put(struct gpio_desc *desc)
 	WARN_ON(1);
 }
 
-static inline struct gpio_desc *__must_check devm_gpiod_get(struct device *dev,
-							    const char *con_id)
+static inline struct gpio_desc *__must_check
+__devm_gpiod_get(struct device *dev,
+		 const char *con_id,
+		 enum gpiod_flags flags)
 {
 	return ERR_PTR(-ENOSYS);
 }
 static inline
-struct gpio_desc *__must_check devm_gpiod_get_index(struct device *dev,
-						    const char *con_id,
-						    unsigned int idx)
+struct gpio_desc *__must_check
+__devm_gpiod_get_index(struct device *dev,
+		       const char *con_id,
+		       unsigned int idx,
+		       enum gpiod_flags flags)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
 static inline struct gpio_desc *__must_check
-devm_gpiod_get_optional(struct device *dev, const char *con_id)
+__devm_gpiod_get_optional(struct device *dev, const char *con_id,
+			  enum gpiod_flags flags)
 {
 	return ERR_PTR(-ENOSYS);
 }
 
 static inline struct gpio_desc *__must_check
-devm_gpiod_get_index_optional(struct device *dev, const char *con_id,
-			      unsigned int index)
+__devm_gpiod_get_index_optional(struct device *dev, const char *con_id,
+				unsigned int index, enum gpiod_flags flags)
 {
 	return ERR_PTR(-ENOSYS);
 }
@@ -303,9 +284,43 @@ static inline int desc_to_gpio(const struct gpio_desc *desc)
 	return -EINVAL;
 }
 
-
 #endif /* CONFIG_GPIOLIB */
 
+/*
+ * Vararg-hacks! This is done to transition the kernel to always pass
+ * the options flags argument to the below functions. During a transition
+ * phase these vararg macros make both old-and-newstyle code compile,
+ * but when all calls to the elder API are removed, these should go away
+ * and the __gpiod_get() etc functions above be renamed just gpiod_get()
+ * etc.
+ */
+#define __gpiod_get(dev, con_id, flags, ...) __gpiod_get(dev, con_id, flags)
+#define gpiod_get(varargs...) __gpiod_get(varargs, 0)
+#define __gpiod_get_index(dev, con_id, index, flags, ...)		\
+	__gpiod_get_index(dev, con_id, index, flags)
+#define gpiod_get_index(varargs...) __gpiod_get_index(varargs, 0)
+#define __gpiod_get_optional(dev, con_id, flags, ...)			\
+	__gpiod_get_optional(dev, con_id, flags)
+#define gpiod_get_optional(varargs...) __gpiod_get_optional(varargs, 0)
+#define __gpiod_get_index_optional(dev, con_id, index, flags, ...)	\
+	__gpiod_get_index_optional(dev, con_id, index, flags)
+#define gpiod_get_index_optional(varargs...)				\
+	__gpiod_get_index_optional(varargs, 0)
+#define __devm_gpiod_get(dev, con_id, flags, ...)			\
+	__devm_gpiod_get(dev, con_id, flags)
+#define devm_gpiod_get(varargs...) __devm_gpiod_get(varargs, 0)
+#define __devm_gpiod_get_index(dev, con_id, index, flags, ...)		\
+	__devm_gpiod_get_index(dev, con_id, index, flags)
+#define devm_gpiod_get_index(varargs...) __devm_gpiod_get_index(varargs, 0)
+#define __devm_gpiod_get_optional(dev, con_id, flags, ...)		\
+	__devm_gpiod_get_optional(dev, con_id, flags)
+#define devm_gpiod_get_optional(varargs...)				\
+	__devm_gpiod_get_optional(varargs, 0)
+#define __devm_gpiod_get_index_optional(dev, con_id, index, flags, ...)	\
+	__devm_gpiod_get_index_optional(dev, con_id, index, flags)
+#define devm_gpiod_get_index_optional(varargs...)			\
+	__devm_gpiod_get_index_optional(varargs, 0)
+
 #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_GPIO_SYSFS)
 
 int gpiod_export(struct gpio_desc *desc, bool direction_may_change);
-- 
cgit v1.2.3


From b58555f1767c9f4e330fcf168e4e753d2d9196e0 Mon Sep 17 00:00:00 2001
From: Christophe Gouault <christophe.gouault@6wind.com>
Date: Fri, 29 Aug 2014 16:16:04 +0200
Subject: xfrm: hash prefixed policies based on preflen thresholds

The idea is an extension of the current policy hashing.

Today only non-prefixed policies are stored in a hash table. This
patch relaxes the constraints, and hashes policies whose prefix
lengths are greater or equal to a configurable threshold.

Each hash table (one per direction) maintains its own set of IPv4 and
IPv6 thresholds (dbits4, sbits4, dbits6, sbits6), by default (32, 32,
128, 128).

Example, if the output hash table is configured with values (16, 24,
56, 64):

ip xfrm policy add dir out src 10.22.0.0/20 dst 10.24.1.0/24 ... => hashed
ip xfrm policy add dir out src 10.22.0.0/16 dst 10.24.1.1/32 ... => hashed
ip xfrm policy add dir out src 10.22.0.0/16 dst 10.24.0.0/16 ... => unhashed

ip xfrm policy add dir out \
    src 3ffe:304:124:2200::/60 dst 3ffe:304:124:2401::/64 ...    => hashed
ip xfrm policy add dir out \
    src 3ffe:304:124:2200::/56 dst 3ffe:304:124:2401::2/128 ...  => hashed
ip xfrm policy add dir out \
    src 3ffe:304:124:2200::/56 dst 3ffe:304:124:2400::/56 ...    => unhashed

The high order bits of the addresses (up to the threshold) are used to
compute the hash key.

Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/netns/xfrm.h |  4 +++
 net/xfrm/xfrm_hash.h     | 76 +++++++++++++++++++++++++++++++++++++++++-------
 net/xfrm/xfrm_policy.c   | 53 +++++++++++++++++++++++++++++----
 3 files changed, 117 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 3492434baf88..41902a8103bd 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -13,6 +13,10 @@ struct ctl_table_header;
 struct xfrm_policy_hash {
 	struct hlist_head	*table;
 	unsigned int		hmask;
+	u8			dbits4;
+	u8			sbits4;
+	u8			dbits6;
+	u8			sbits6;
 };
 
 struct netns_xfrm {
diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h
index 0622d319e1f2..666c5ffe929d 100644
--- a/net/xfrm/xfrm_hash.h
+++ b/net/xfrm/xfrm_hash.h
@@ -3,6 +3,7 @@
 
 #include <linux/xfrm.h>
 #include <linux/socket.h>
+#include <linux/jhash.h>
 
 static inline unsigned int __xfrm4_addr_hash(const xfrm_address_t *addr)
 {
@@ -28,6 +29,58 @@ static inline unsigned int __xfrm6_daddr_saddr_hash(const xfrm_address_t *daddr,
 		     saddr->a6[2] ^ saddr->a6[3]);
 }
 
+static inline u32 __bits2mask32(__u8 bits)
+{
+	u32 mask32 = 0xffffffff;
+
+	if (bits == 0)
+		mask32 = 0;
+	else if (bits < 32)
+		mask32 <<= (32 - bits);
+
+	return mask32;
+}
+
+static inline unsigned int __xfrm4_dpref_spref_hash(const xfrm_address_t *daddr,
+						    const xfrm_address_t *saddr,
+						    __u8 dbits,
+						    __u8 sbits)
+{
+	return jhash_2words(ntohl(daddr->a4) & __bits2mask32(dbits),
+			    ntohl(saddr->a4) & __bits2mask32(sbits),
+			    0);
+}
+
+static inline unsigned int __xfrm6_pref_hash(const xfrm_address_t *addr,
+					     __u8 prefixlen)
+{
+	int pdw;
+	int pbi;
+	u32 initval = 0;
+
+	pdw = prefixlen >> 5;     /* num of whole u32 in prefix */
+	pbi = prefixlen &  0x1f;  /* num of bits in incomplete u32 in prefix */
+
+	if (pbi) {
+		__be32 mask;
+
+		mask = htonl((0xffffffff) << (32 - pbi));
+
+		initval = (__force u32)(addr->a6[pdw] & mask);
+	}
+
+	return jhash2((__force u32 *)addr->a6, pdw, initval);
+}
+
+static inline unsigned int __xfrm6_dpref_spref_hash(const xfrm_address_t *daddr,
+						    const xfrm_address_t *saddr,
+						    __u8 dbits,
+						    __u8 sbits)
+{
+	return __xfrm6_pref_hash(daddr, dbits) ^
+	       __xfrm6_pref_hash(saddr, sbits);
+}
+
 static inline unsigned int __xfrm_dst_hash(const xfrm_address_t *daddr,
 					   const xfrm_address_t *saddr,
 					   u32 reqid, unsigned short family,
@@ -84,7 +137,8 @@ static inline unsigned int __idx_hash(u32 index, unsigned int hmask)
 }
 
 static inline unsigned int __sel_hash(const struct xfrm_selector *sel,
-				      unsigned short family, unsigned int hmask)
+				      unsigned short family, unsigned int hmask,
+				      u8 dbits, u8 sbits)
 {
 	const xfrm_address_t *daddr = &sel->daddr;
 	const xfrm_address_t *saddr = &sel->saddr;
@@ -92,19 +146,19 @@ static inline unsigned int __sel_hash(const struct xfrm_selector *sel,
 
 	switch (family) {
 	case AF_INET:
-		if (sel->prefixlen_d != 32 ||
-		    sel->prefixlen_s != 32)
+		if (sel->prefixlen_d < dbits ||
+		    sel->prefixlen_s < sbits)
 			return hmask + 1;
 
-		h = __xfrm4_daddr_saddr_hash(daddr, saddr);
+		h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits);
 		break;
 
 	case AF_INET6:
-		if (sel->prefixlen_d != 128 ||
-		    sel->prefixlen_s != 128)
+		if (sel->prefixlen_d < dbits ||
+		    sel->prefixlen_s < sbits)
 			return hmask + 1;
 
-		h = __xfrm6_daddr_saddr_hash(daddr, saddr);
+		h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits);
 		break;
 	}
 	h ^= (h >> 16);
@@ -113,17 +167,19 @@ static inline unsigned int __sel_hash(const struct xfrm_selector *sel,
 
 static inline unsigned int __addr_hash(const xfrm_address_t *daddr,
 				       const xfrm_address_t *saddr,
-				       unsigned short family, unsigned int hmask)
+				       unsigned short family,
+				       unsigned int hmask,
+				       u8 dbits, u8 sbits)
 {
 	unsigned int h = 0;
 
 	switch (family) {
 	case AF_INET:
-		h = __xfrm4_daddr_saddr_hash(daddr, saddr);
+		h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits);
 		break;
 
 	case AF_INET6:
-		h = __xfrm6_daddr_saddr_hash(daddr, saddr);
+		h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits);
 		break;
 	}
 	h ^= (h >> 16);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index beeed602aeb3..e6ff7b4046ea 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -344,12 +344,39 @@ static inline unsigned int idx_hash(struct net *net, u32 index)
 	return __idx_hash(index, net->xfrm.policy_idx_hmask);
 }
 
+/* calculate policy hash thresholds */
+static void __get_hash_thresh(struct net *net,
+			      unsigned short family, int dir,
+			      u8 *dbits, u8 *sbits)
+{
+	switch (family) {
+	case AF_INET:
+		*dbits = net->xfrm.policy_bydst[dir].dbits4;
+		*sbits = net->xfrm.policy_bydst[dir].sbits4;
+		break;
+
+	case AF_INET6:
+		*dbits = net->xfrm.policy_bydst[dir].dbits6;
+		*sbits = net->xfrm.policy_bydst[dir].sbits6;
+		break;
+
+	default:
+		*dbits = 0;
+		*sbits = 0;
+	}
+}
+
 static struct hlist_head *policy_hash_bysel(struct net *net,
 					    const struct xfrm_selector *sel,
 					    unsigned short family, int dir)
 {
 	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
-	unsigned int hash = __sel_hash(sel, family, hmask);
+	unsigned int hash;
+	u8 dbits;
+	u8 sbits;
+
+	__get_hash_thresh(net, family, dir, &dbits, &sbits);
+	hash = __sel_hash(sel, family, hmask, dbits, sbits);
 
 	return (hash == hmask + 1 ?
 		&net->xfrm.policy_inexact[dir] :
@@ -362,25 +389,35 @@ static struct hlist_head *policy_hash_direct(struct net *net,
 					     unsigned short family, int dir)
 {
 	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
-	unsigned int hash = __addr_hash(daddr, saddr, family, hmask);
+	unsigned int hash;
+	u8 dbits;
+	u8 sbits;
+
+	__get_hash_thresh(net, family, dir, &dbits, &sbits);
+	hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits);
 
 	return net->xfrm.policy_bydst[dir].table + hash;
 }
 
-static void xfrm_dst_hash_transfer(struct hlist_head *list,
+static void xfrm_dst_hash_transfer(struct net *net,
+				   struct hlist_head *list,
 				   struct hlist_head *ndsttable,
-				   unsigned int nhashmask)
+				   unsigned int nhashmask,
+				   int dir)
 {
 	struct hlist_node *tmp, *entry0 = NULL;
 	struct xfrm_policy *pol;
 	unsigned int h0 = 0;
+	u8 dbits;
+	u8 sbits;
 
 redo:
 	hlist_for_each_entry_safe(pol, tmp, list, bydst) {
 		unsigned int h;
 
+		__get_hash_thresh(net, pol->family, dir, &dbits, &sbits);
 		h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr,
-				pol->family, nhashmask);
+				pol->family, nhashmask, dbits, sbits);
 		if (!entry0) {
 			hlist_del(&pol->bydst);
 			hlist_add_head(&pol->bydst, ndsttable+h);
@@ -434,7 +471,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
 	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
 	for (i = hmask; i >= 0; i--)
-		xfrm_dst_hash_transfer(odst + i, ndst, nhashmask);
+		xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir);
 
 	net->xfrm.policy_bydst[dir].table = ndst;
 	net->xfrm.policy_bydst[dir].hmask = nhashmask;
@@ -2830,6 +2867,10 @@ static int __net_init xfrm_policy_init(struct net *net)
 		if (!htab->table)
 			goto out_bydst;
 		htab->hmask = hmask;
+		htab->dbits4 = 32;
+		htab->sbits4 = 32;
+		htab->dbits6 = 128;
+		htab->sbits6 = 128;
 	}
 
 	INIT_LIST_HEAD(&net->xfrm.policy_all);
-- 
cgit v1.2.3


From 880a6fab8f6ba5b5abe59ea68533202ddea1012c Mon Sep 17 00:00:00 2001
From: Christophe Gouault <christophe.gouault@6wind.com>
Date: Fri, 29 Aug 2014 16:16:05 +0200
Subject: xfrm: configure policy hash table thresholds by netlink

Enable to specify local and remote prefix length thresholds for the
policy hash table via a netlink XFRM_MSG_NEWSPDINFO message.

prefix length thresholds are specified by XFRMA_SPD_IPV4_HTHRESH and
XFRMA_SPD_IPV6_HTHRESH optional attributes (struct xfrmu_spdhthresh).

example:

    struct xfrmu_spdhthresh thresh4 = {
        .lbits = 0;
        .rbits = 24;
    };
    struct xfrmu_spdhthresh thresh6 = {
        .lbits = 0;
        .rbits = 56;
    };
    struct nlmsghdr *hdr;
    struct nl_msg *msg;

    msg = nlmsg_alloc();
    hdr = nlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, XFRMA_SPD_IPV4_HTHRESH, sizeof(__u32), NLM_F_REQUEST);
    nla_put(msg, XFRMA_SPD_IPV4_HTHRESH, sizeof(thresh4), &thresh4);
    nla_put(msg, XFRMA_SPD_IPV6_HTHRESH, sizeof(thresh6), &thresh6);
    nla_send_auto(sk, msg);

The numbers are the policy selector minimum prefix lengths to put a
policy in the hash table.

- lbits is the local threshold (source address for out policies,
  destination address for in and fwd policies).

- rbits is the remote threshold (destination address for out
  policies, source address for in and fwd policies).

The default values are:

XFRMA_SPD_IPV4_HTHRESH: 32 32
XFRMA_SPD_IPV6_HTHRESH: 128 128

Dynamic re-building of the SPD is performed when the thresholds values
are changed.

The current thresholds can be read via a XFRM_MSG_GETSPDINFO request:
the kernel replies to XFRM_MSG_GETSPDINFO requests by an
XFRM_MSG_NEWSPDINFO message, with both attributes
XFRMA_SPD_IPV4_HTHRESH and XFRMA_SPD_IPV6_HTHRESH.

Signed-off-by: Christophe Gouault <christophe.gouault@6wind.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/netns/xfrm.h  | 10 ++++++
 include/net/xfrm.h        |  1 +
 include/uapi/linux/xfrm.h |  7 ++++
 net/xfrm/xfrm_policy.c    | 87 +++++++++++++++++++++++++++++++++++++++++++++++
 net/xfrm/xfrm_user.c      | 80 +++++++++++++++++++++++++++++++++++++++++--
 5 files changed, 182 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 41902a8103bd..9da798256f0e 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -19,6 +19,15 @@ struct xfrm_policy_hash {
 	u8			sbits6;
 };
 
+struct xfrm_policy_hthresh {
+	struct work_struct	work;
+	seqlock_t		lock;
+	u8			lbits4;
+	u8			rbits4;
+	u8			lbits6;
+	u8			rbits6;
+};
+
 struct netns_xfrm {
 	struct list_head	state_all;
 	/*
@@ -45,6 +54,7 @@ struct netns_xfrm {
 	struct xfrm_policy_hash	policy_bydst[XFRM_POLICY_MAX * 2];
 	unsigned int		policy_count[XFRM_POLICY_MAX * 2];
 	struct work_struct	policy_hash_work;
+	struct xfrm_policy_hthresh policy_hthresh;
 
 
 	struct sock		*nlsk;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 721e9c3b11bd..dc4865e90fe4 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1591,6 +1591,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark,
 struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir,
 				     u32 id, int delete, int *err);
 int xfrm_policy_flush(struct net *net, u8 type, bool task_valid);
+void xfrm_policy_hash_rebuild(struct net *net);
 u32 xfrm_get_acqseq(void);
 int verify_spi_info(u8 proto, u32 min, u32 max);
 int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 25e5dd916ba4..02d5125a5ee8 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -328,6 +328,8 @@ enum xfrm_spdattr_type_t {
 	XFRMA_SPD_UNSPEC,
 	XFRMA_SPD_INFO,
 	XFRMA_SPD_HINFO,
+	XFRMA_SPD_IPV4_HTHRESH,
+	XFRMA_SPD_IPV6_HTHRESH,
 	__XFRMA_SPD_MAX
 
 #define XFRMA_SPD_MAX (__XFRMA_SPD_MAX - 1)
@@ -347,6 +349,11 @@ struct xfrmu_spdhinfo {
 	__u32 spdhmcnt;
 };
 
+struct xfrmu_spdhthresh {
+	__u8 lbits;
+	__u8 rbits;
+};
+
 struct xfrm_usersa_info {
 	struct xfrm_selector		sel;
 	struct xfrm_id			id;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index e6ff7b4046ea..55bcb8604bc6 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -566,6 +566,86 @@ static void xfrm_hash_resize(struct work_struct *work)
 	mutex_unlock(&hash_resize_mutex);
 }
 
+static void xfrm_hash_rebuild(struct work_struct *work)
+{
+	struct net *net = container_of(work, struct net,
+				       xfrm.policy_hthresh.work);
+	unsigned int hmask;
+	struct xfrm_policy *pol;
+	struct xfrm_policy *policy;
+	struct hlist_head *chain;
+	struct hlist_head *odst;
+	struct hlist_node *newpos;
+	int i;
+	int dir;
+	unsigned seq;
+	u8 lbits4, rbits4, lbits6, rbits6;
+
+	mutex_lock(&hash_resize_mutex);
+
+	/* read selector prefixlen thresholds */
+	do {
+		seq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
+
+		lbits4 = net->xfrm.policy_hthresh.lbits4;
+		rbits4 = net->xfrm.policy_hthresh.rbits4;
+		lbits6 = net->xfrm.policy_hthresh.lbits6;
+		rbits6 = net->xfrm.policy_hthresh.rbits6;
+	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
+
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
+
+	/* reset the bydst and inexact table in all directions */
+	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
+		hmask = net->xfrm.policy_bydst[dir].hmask;
+		odst = net->xfrm.policy_bydst[dir].table;
+		for (i = hmask; i >= 0; i--)
+			INIT_HLIST_HEAD(odst + i);
+		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
+			/* dir out => dst = remote, src = local */
+			net->xfrm.policy_bydst[dir].dbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = rbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = lbits6;
+		} else {
+			/* dir in/fwd => dst = local, src = remote */
+			net->xfrm.policy_bydst[dir].dbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = lbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = rbits6;
+		}
+	}
+
+	/* re-insert all policies by order of creation */
+	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		newpos = NULL;
+		chain = policy_hash_bysel(net, &policy->selector,
+					  policy->family,
+					  xfrm_policy_id2dir(policy->index));
+		hlist_for_each_entry(pol, chain, bydst) {
+			if (policy->priority >= pol->priority)
+				newpos = &pol->bydst;
+			else
+				break;
+		}
+		if (newpos)
+			hlist_add_behind(&policy->bydst, newpos);
+		else
+			hlist_add_head(&policy->bydst, chain);
+	}
+
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	mutex_unlock(&hash_resize_mutex);
+}
+
+void xfrm_policy_hash_rebuild(struct net *net)
+{
+	schedule_work(&net->xfrm.policy_hthresh.work);
+}
+EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
+
 /* Generate new index... KAME seems to generate them ordered by cost
  * of an absolute inpredictability of ordering of rules. This will not pass. */
 static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
@@ -2872,9 +2952,16 @@ static int __net_init xfrm_policy_init(struct net *net)
 		htab->dbits6 = 128;
 		htab->sbits6 = 128;
 	}
+	net->xfrm.policy_hthresh.lbits4 = 32;
+	net->xfrm.policy_hthresh.rbits4 = 32;
+	net->xfrm.policy_hthresh.lbits6 = 128;
+	net->xfrm.policy_hthresh.rbits6 = 128;
+
+	seqlock_init(&net->xfrm.policy_hthresh.lock);
 
 	INIT_LIST_HEAD(&net->xfrm.policy_all);
 	INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
+	INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
 	if (net_eq(net, &init_net))
 		register_netdevice_notifier(&xfrm_dev_notifier);
 	return 0;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index d4db6ebb089d..eaf8a8f1cbe8 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -964,7 +964,9 @@ static inline size_t xfrm_spdinfo_msgsize(void)
 {
 	return NLMSG_ALIGN(4)
 	       + nla_total_size(sizeof(struct xfrmu_spdinfo))
-	       + nla_total_size(sizeof(struct xfrmu_spdhinfo));
+	       + nla_total_size(sizeof(struct xfrmu_spdhinfo))
+	       + nla_total_size(sizeof(struct xfrmu_spdhthresh))
+	       + nla_total_size(sizeof(struct xfrmu_spdhthresh));
 }
 
 static int build_spdinfo(struct sk_buff *skb, struct net *net,
@@ -973,9 +975,11 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net,
 	struct xfrmk_spdinfo si;
 	struct xfrmu_spdinfo spc;
 	struct xfrmu_spdhinfo sph;
+	struct xfrmu_spdhthresh spt4, spt6;
 	struct nlmsghdr *nlh;
 	int err;
 	u32 *f;
+	unsigned lseq;
 
 	nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_NEWSPDINFO, sizeof(u32), 0);
 	if (nlh == NULL) /* shouldn't really happen ... */
@@ -993,9 +997,22 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net,
 	sph.spdhcnt = si.spdhcnt;
 	sph.spdhmcnt = si.spdhmcnt;
 
+	do {
+		lseq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
+
+		spt4.lbits = net->xfrm.policy_hthresh.lbits4;
+		spt4.rbits = net->xfrm.policy_hthresh.rbits4;
+		spt6.lbits = net->xfrm.policy_hthresh.lbits6;
+		spt6.rbits = net->xfrm.policy_hthresh.rbits6;
+	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, lseq));
+
 	err = nla_put(skb, XFRMA_SPD_INFO, sizeof(spc), &spc);
 	if (!err)
 		err = nla_put(skb, XFRMA_SPD_HINFO, sizeof(sph), &sph);
+	if (!err)
+		err = nla_put(skb, XFRMA_SPD_IPV4_HTHRESH, sizeof(spt4), &spt4);
+	if (!err)
+		err = nla_put(skb, XFRMA_SPD_IPV6_HTHRESH, sizeof(spt6), &spt6);
 	if (err) {
 		nlmsg_cancel(skb, nlh);
 		return err;
@@ -1004,6 +1021,51 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net,
 	return nlmsg_end(skb, nlh);
 }
 
+static int xfrm_set_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct nlattr **attrs)
+{
+	struct net *net = sock_net(skb->sk);
+	struct xfrmu_spdhthresh *thresh4 = NULL;
+	struct xfrmu_spdhthresh *thresh6 = NULL;
+
+	/* selector prefixlen thresholds to hash policies */
+	if (attrs[XFRMA_SPD_IPV4_HTHRESH]) {
+		struct nlattr *rta = attrs[XFRMA_SPD_IPV4_HTHRESH];
+
+		if (nla_len(rta) < sizeof(*thresh4))
+			return -EINVAL;
+		thresh4 = nla_data(rta);
+		if (thresh4->lbits > 32 || thresh4->rbits > 32)
+			return -EINVAL;
+	}
+	if (attrs[XFRMA_SPD_IPV6_HTHRESH]) {
+		struct nlattr *rta = attrs[XFRMA_SPD_IPV6_HTHRESH];
+
+		if (nla_len(rta) < sizeof(*thresh6))
+			return -EINVAL;
+		thresh6 = nla_data(rta);
+		if (thresh6->lbits > 128 || thresh6->rbits > 128)
+			return -EINVAL;
+	}
+
+	if (thresh4 || thresh6) {
+		write_seqlock(&net->xfrm.policy_hthresh.lock);
+		if (thresh4) {
+			net->xfrm.policy_hthresh.lbits4 = thresh4->lbits;
+			net->xfrm.policy_hthresh.rbits4 = thresh4->rbits;
+		}
+		if (thresh6) {
+			net->xfrm.policy_hthresh.lbits6 = thresh6->lbits;
+			net->xfrm.policy_hthresh.rbits6 = thresh6->rbits;
+		}
+		write_sequnlock(&net->xfrm.policy_hthresh.lock);
+
+		xfrm_policy_hash_rebuild(net);
+	}
+
+	return 0;
+}
+
 static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct nlattr **attrs)
 {
@@ -2274,6 +2336,7 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_REPORT      - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report),
 	[XFRM_MSG_MIGRATE     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
 	[XFRM_MSG_GETSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
 	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
 };
 
@@ -2308,10 +2371,17 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
 };
 
+static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
+	[XFRMA_SPD_IPV4_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
+	[XFRMA_SPD_IPV6_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
+};
+
 static const struct xfrm_link {
 	int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **);
 	int (*dump)(struct sk_buff *, struct netlink_callback *);
 	int (*done)(struct netlink_callback *);
+	const struct nla_policy *nla_pol;
+	int nla_max;
 } xfrm_dispatch[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = { .doit = xfrm_add_sa        },
 	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = { .doit = xfrm_del_sa        },
@@ -2335,6 +2405,9 @@ static const struct xfrm_link {
 	[XFRM_MSG_GETAE       - XFRM_MSG_BASE] = { .doit = xfrm_get_ae  },
 	[XFRM_MSG_MIGRATE     - XFRM_MSG_BASE] = { .doit = xfrm_do_migrate    },
 	[XFRM_MSG_GETSADINFO  - XFRM_MSG_BASE] = { .doit = xfrm_get_sadinfo   },
+	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = { .doit = xfrm_set_spdinfo,
+						   .nla_pol = xfrma_spd_policy,
+						   .nla_max = XFRMA_SPD_MAX },
 	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = { .doit = xfrm_get_spdinfo   },
 };
 
@@ -2371,8 +2444,9 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		}
 	}
 
-	err = nlmsg_parse(nlh, xfrm_msg_min[type], attrs, XFRMA_MAX,
-			  xfrma_policy);
+	err = nlmsg_parse(nlh, xfrm_msg_min[type], attrs,
+			  link->nla_max ? : XFRMA_MAX,
+			  link->nla_pol ? : xfrma_policy);
 	if (err < 0)
 		return err;
 
-- 
cgit v1.2.3


From 2ffd48f2e7ae06c3d7b2bcde9a0cb211d1a32468 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Tue, 19 Aug 2014 10:52:40 -0700
Subject: gpu: ipu-v3: Add Camera Sensor Interface unit

Adds the Camera Sensor Interface (CSI) unit required for video capture.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>

Removed the unused clk_get_rate in ipu_csi_init_interface and the
ipu_csi_ccir_err_detection_enable/disable functions.
Checkpatch cleanup.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/Makefile     |   2 +-
 drivers/gpu/ipu-v3/ipu-common.c |  44 ++-
 drivers/gpu/ipu-v3/ipu-csi.c    | 741 ++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/ipu-v3/ipu-prv.h    |   6 +
 include/video/imx-ipu-v3.h      |  32 +-
 5 files changed, 810 insertions(+), 15 deletions(-)
 create mode 100644 drivers/gpu/ipu-v3/ipu-csi.c

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/Makefile b/drivers/gpu/ipu-v3/Makefile
index 0b42836caae1..d22bd06caa6d 100644
--- a/drivers/gpu/ipu-v3/Makefile
+++ b/drivers/gpu/ipu-v3/Makefile
@@ -1,4 +1,4 @@
 obj-$(CONFIG_IMX_IPUV3_CORE) += imx-ipu-v3.o
 
-imx-ipu-v3-objs := ipu-common.o ipu-cpmem.o ipu-dc.o ipu-di.o \
+imx-ipu-v3-objs := ipu-common.o ipu-cpmem.o ipu-csi.o ipu-dc.o ipu-di.o \
 		ipu-dp.o ipu-dmfc.o ipu-smfc.o
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index cae543115856..511c364231a2 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -217,18 +217,6 @@ int ipu_module_disable(struct ipu_soc *ipu, u32 mask)
 }
 EXPORT_SYMBOL_GPL(ipu_module_disable);
 
-int ipu_csi_enable(struct ipu_soc *ipu, int csi)
-{
-	return ipu_module_enable(ipu, csi ? IPU_CONF_CSI1_EN : IPU_CONF_CSI0_EN);
-}
-EXPORT_SYMBOL_GPL(ipu_csi_enable);
-
-int ipu_csi_disable(struct ipu_soc *ipu, int csi)
-{
-	return ipu_module_disable(ipu, csi ? IPU_CONF_CSI1_EN : IPU_CONF_CSI0_EN);
-}
-EXPORT_SYMBOL_GPL(ipu_csi_disable);
-
 int ipu_smfc_enable(struct ipu_soc *ipu)
 {
 	return ipu_module_enable(ipu, IPU_CONF_SMFC_EN);
@@ -439,6 +427,8 @@ struct ipu_devtype {
 	unsigned long cpmem_ofs;
 	unsigned long srm_ofs;
 	unsigned long tpm_ofs;
+	unsigned long csi0_ofs;
+	unsigned long csi1_ofs;
 	unsigned long disp0_ofs;
 	unsigned long disp1_ofs;
 	unsigned long dc_tmpl_ofs;
@@ -452,6 +442,8 @@ static struct ipu_devtype ipu_type_imx51 = {
 	.cpmem_ofs = 0x1f000000,
 	.srm_ofs = 0x1f040000,
 	.tpm_ofs = 0x1f060000,
+	.csi0_ofs = 0x1f030000,
+	.csi1_ofs = 0x1f038000,
 	.disp0_ofs = 0x1e040000,
 	.disp1_ofs = 0x1e048000,
 	.dc_tmpl_ofs = 0x1f080000,
@@ -465,6 +457,8 @@ static struct ipu_devtype ipu_type_imx53 = {
 	.cpmem_ofs = 0x07000000,
 	.srm_ofs = 0x07040000,
 	.tpm_ofs = 0x07060000,
+	.csi0_ofs = 0x07030000,
+	.csi1_ofs = 0x07038000,
 	.disp0_ofs = 0x06040000,
 	.disp1_ofs = 0x06048000,
 	.dc_tmpl_ofs = 0x07080000,
@@ -478,6 +472,8 @@ static struct ipu_devtype ipu_type_imx6q = {
 	.cpmem_ofs = 0x00300000,
 	.srm_ofs = 0x00340000,
 	.tpm_ofs = 0x00360000,
+	.csi0_ofs = 0x00230000,
+	.csi1_ofs = 0x00238000,
 	.disp0_ofs = 0x00240000,
 	.disp1_ofs = 0x00248000,
 	.dc_tmpl_ofs = 0x00380000,
@@ -508,6 +504,20 @@ static int ipu_submodules_init(struct ipu_soc *ipu,
 		goto err_cpmem;
 	}
 
+	ret = ipu_csi_init(ipu, dev, 0, ipu_base + devtype->csi0_ofs,
+			   IPU_CONF_CSI0_EN, ipu_clk);
+	if (ret) {
+		unit = "csi0";
+		goto err_csi_0;
+	}
+
+	ret = ipu_csi_init(ipu, dev, 1, ipu_base + devtype->csi1_ofs,
+			   IPU_CONF_CSI1_EN, ipu_clk);
+	if (ret) {
+		unit = "csi1";
+		goto err_csi_1;
+	}
+
 	ret = ipu_di_init(ipu, dev, 0, ipu_base + devtype->disp0_ofs,
 			IPU_CONF_DI0_EN, ipu_clk);
 	if (ret) {
@@ -562,6 +572,10 @@ err_dc:
 err_di_1:
 	ipu_di_exit(ipu, 0);
 err_di_0:
+	ipu_csi_exit(ipu, 1);
+err_csi_1:
+	ipu_csi_exit(ipu, 0);
+err_csi_0:
 	ipu_cpmem_exit(ipu);
 err_cpmem:
 	dev_err(&pdev->dev, "init %s failed with %d\n", unit, ret);
@@ -640,6 +654,8 @@ static void ipu_submodules_exit(struct ipu_soc *ipu)
 	ipu_dc_exit(ipu);
 	ipu_di_exit(ipu, 1);
 	ipu_di_exit(ipu, 0);
+	ipu_csi_exit(ipu, 1);
+	ipu_csi_exit(ipu, 0);
 	ipu_cpmem_exit(ipu);
 }
 
@@ -859,6 +875,10 @@ static int ipu_probe(struct platform_device *pdev)
 			ipu_base + devtype->cm_ofs + IPU_CM_IDMAC_REG_OFS);
 	dev_dbg(&pdev->dev, "cpmem:    0x%08lx\n",
 			ipu_base + devtype->cpmem_ofs);
+	dev_dbg(&pdev->dev, "csi0:    0x%08lx\n",
+			ipu_base + devtype->csi0_ofs);
+	dev_dbg(&pdev->dev, "csi1:    0x%08lx\n",
+			ipu_base + devtype->csi1_ofs);
 	dev_dbg(&pdev->dev, "disp0:    0x%08lx\n",
 			ipu_base + devtype->disp0_ofs);
 	dev_dbg(&pdev->dev, "disp1:    0x%08lx\n",
diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c
new file mode 100644
index 000000000000..d6f56471bd2a
--- /dev/null
+++ b/drivers/gpu/ipu-v3/ipu-csi.c
@@ -0,0 +1,741 @@
+/*
+ * Copyright (C) 2012-2014 Mentor Graphics Inc.
+ * Copyright (C) 2005-2009 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ */
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/videodev2.h>
+#include <uapi/linux/v4l2-mediabus.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+
+#include "ipu-prv.h"
+
+struct ipu_csi {
+	void __iomem *base;
+	int id;
+	u32 module;
+	struct clk *clk_ipu;	/* IPU bus clock */
+	spinlock_t lock;
+	bool inuse;
+	struct ipu_soc *ipu;
+};
+
+/* CSI Register Offsets */
+#define CSI_SENS_CONF		0x0000
+#define CSI_SENS_FRM_SIZE	0x0004
+#define CSI_ACT_FRM_SIZE	0x0008
+#define CSI_OUT_FRM_CTRL	0x000c
+#define CSI_TST_CTRL		0x0010
+#define CSI_CCIR_CODE_1		0x0014
+#define CSI_CCIR_CODE_2		0x0018
+#define CSI_CCIR_CODE_3		0x001c
+#define CSI_MIPI_DI		0x0020
+#define CSI_SKIP		0x0024
+#define CSI_CPD_CTRL		0x0028
+#define CSI_CPD_RC(n)		(0x002c + ((n)*4))
+#define CSI_CPD_RS(n)		(0x004c + ((n)*4))
+#define CSI_CPD_GRC(n)		(0x005c + ((n)*4))
+#define CSI_CPD_GRS(n)		(0x007c + ((n)*4))
+#define CSI_CPD_GBC(n)		(0x008c + ((n)*4))
+#define CSI_CPD_GBS(n)		(0x00Ac + ((n)*4))
+#define CSI_CPD_BC(n)		(0x00Bc + ((n)*4))
+#define CSI_CPD_BS(n)		(0x00Dc + ((n)*4))
+#define CSI_CPD_OFFSET1		0x00ec
+#define CSI_CPD_OFFSET2		0x00f0
+
+/* CSI Register Fields */
+#define CSI_SENS_CONF_DATA_FMT_SHIFT		8
+#define CSI_SENS_CONF_DATA_FMT_MASK		0x00000700
+#define CSI_SENS_CONF_DATA_FMT_RGB_YUV444	0L
+#define CSI_SENS_CONF_DATA_FMT_YUV422_YUYV	1L
+#define CSI_SENS_CONF_DATA_FMT_YUV422_UYVY	2L
+#define CSI_SENS_CONF_DATA_FMT_BAYER		3L
+#define CSI_SENS_CONF_DATA_FMT_RGB565		4L
+#define CSI_SENS_CONF_DATA_FMT_RGB555		5L
+#define CSI_SENS_CONF_DATA_FMT_RGB444		6L
+#define CSI_SENS_CONF_DATA_FMT_JPEG		7L
+
+#define CSI_SENS_CONF_VSYNC_POL_SHIFT		0
+#define CSI_SENS_CONF_HSYNC_POL_SHIFT		1
+#define CSI_SENS_CONF_DATA_POL_SHIFT		2
+#define CSI_SENS_CONF_PIX_CLK_POL_SHIFT		3
+#define CSI_SENS_CONF_SENS_PRTCL_MASK		0x00000070
+#define CSI_SENS_CONF_SENS_PRTCL_SHIFT		4
+#define CSI_SENS_CONF_PACK_TIGHT_SHIFT		7
+#define CSI_SENS_CONF_DATA_WIDTH_SHIFT		11
+#define CSI_SENS_CONF_EXT_VSYNC_SHIFT		15
+#define CSI_SENS_CONF_DIVRATIO_SHIFT		16
+
+#define CSI_SENS_CONF_DIVRATIO_MASK		0x00ff0000
+#define CSI_SENS_CONF_DATA_DEST_SHIFT		24
+#define CSI_SENS_CONF_DATA_DEST_MASK		0x07000000
+#define CSI_SENS_CONF_JPEG8_EN_SHIFT		27
+#define CSI_SENS_CONF_JPEG_EN_SHIFT		28
+#define CSI_SENS_CONF_FORCE_EOF_SHIFT		29
+#define CSI_SENS_CONF_DATA_EN_POL_SHIFT		31
+
+#define CSI_DATA_DEST_IC			2
+#define CSI_DATA_DEST_IDMAC			4
+
+#define CSI_CCIR_ERR_DET_EN			0x01000000
+#define CSI_HORI_DOWNSIZE_EN			0x80000000
+#define CSI_VERT_DOWNSIZE_EN			0x40000000
+#define CSI_TEST_GEN_MODE_EN			0x01000000
+
+#define CSI_HSC_MASK				0x1fff0000
+#define CSI_HSC_SHIFT				16
+#define CSI_VSC_MASK				0x00000fff
+#define CSI_VSC_SHIFT				0
+
+#define CSI_TEST_GEN_R_MASK			0x000000ff
+#define CSI_TEST_GEN_R_SHIFT			0
+#define CSI_TEST_GEN_G_MASK			0x0000ff00
+#define CSI_TEST_GEN_G_SHIFT			8
+#define CSI_TEST_GEN_B_MASK			0x00ff0000
+#define CSI_TEST_GEN_B_SHIFT			16
+
+#define CSI_MAX_RATIO_SKIP_SMFC_MASK		0x00000007
+#define CSI_MAX_RATIO_SKIP_SMFC_SHIFT		0
+#define CSI_SKIP_SMFC_MASK			0x000000f8
+#define CSI_SKIP_SMFC_SHIFT			3
+#define CSI_ID_2_SKIP_MASK			0x00000300
+#define CSI_ID_2_SKIP_SHIFT			8
+
+#define CSI_COLOR_FIRST_ROW_MASK		0x00000002
+#define CSI_COLOR_FIRST_COMP_MASK		0x00000001
+
+/* MIPI CSI-2 data types */
+#define MIPI_DT_YUV420		0x18 /* YYY.../UYVY.... */
+#define MIPI_DT_YUV420_LEGACY	0x1a /* UYY.../VYY...   */
+#define MIPI_DT_YUV422		0x1e /* UYVY...         */
+#define MIPI_DT_RGB444		0x20
+#define MIPI_DT_RGB555		0x21
+#define MIPI_DT_RGB565		0x22
+#define MIPI_DT_RGB666		0x23
+#define MIPI_DT_RGB888		0x24
+#define MIPI_DT_RAW6		0x28
+#define MIPI_DT_RAW7		0x29
+#define MIPI_DT_RAW8		0x2a
+#define MIPI_DT_RAW10		0x2b
+#define MIPI_DT_RAW12		0x2c
+#define MIPI_DT_RAW14		0x2d
+
+/*
+ * Bitfield of CSI bus signal polarities and modes.
+ */
+struct ipu_csi_bus_config {
+	unsigned data_width:4;
+	unsigned clk_mode:3;
+	unsigned ext_vsync:1;
+	unsigned vsync_pol:1;
+	unsigned hsync_pol:1;
+	unsigned pixclk_pol:1;
+	unsigned data_pol:1;
+	unsigned sens_clksrc:1;
+	unsigned pack_tight:1;
+	unsigned force_eof:1;
+	unsigned data_en_pol:1;
+
+	unsigned data_fmt;
+	unsigned mipi_dt;
+};
+
+/*
+ * Enumeration of CSI data bus widths.
+ */
+enum ipu_csi_data_width {
+	IPU_CSI_DATA_WIDTH_4   = 0,
+	IPU_CSI_DATA_WIDTH_8   = 1,
+	IPU_CSI_DATA_WIDTH_10  = 3,
+	IPU_CSI_DATA_WIDTH_12  = 5,
+	IPU_CSI_DATA_WIDTH_16  = 9,
+};
+
+/*
+ * Enumeration of CSI clock modes.
+ */
+enum ipu_csi_clk_mode {
+	IPU_CSI_CLK_MODE_GATED_CLK,
+	IPU_CSI_CLK_MODE_NONGATED_CLK,
+	IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE,
+	IPU_CSI_CLK_MODE_CCIR656_INTERLACED,
+	IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_DDR,
+	IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_SDR,
+	IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_DDR,
+	IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_SDR,
+};
+
+static inline u32 ipu_csi_read(struct ipu_csi *csi, unsigned offset)
+{
+	return readl(csi->base + offset);
+}
+
+static inline void ipu_csi_write(struct ipu_csi *csi, u32 value,
+				 unsigned offset)
+{
+	writel(value, csi->base + offset);
+}
+
+/*
+ * Set mclk division ratio for generating test mode mclk. Only used
+ * for test generator.
+ */
+static int ipu_csi_set_testgen_mclk(struct ipu_csi *csi, u32 pixel_clk,
+					u32 ipu_clk)
+{
+	u32 temp;
+	u32 div_ratio;
+
+	div_ratio = (ipu_clk / pixel_clk) - 1;
+
+	if (div_ratio > 0xFF || div_ratio < 0) {
+		dev_err(csi->ipu->dev,
+			"value of pixel_clk extends normal range\n");
+		return -EINVAL;
+	}
+
+	temp = ipu_csi_read(csi, CSI_SENS_CONF);
+	temp &= ~CSI_SENS_CONF_DIVRATIO_MASK;
+	ipu_csi_write(csi, temp | (div_ratio << CSI_SENS_CONF_DIVRATIO_SHIFT),
+			  CSI_SENS_CONF);
+
+	return 0;
+}
+
+/*
+ * Find the CSI data format and data width for the given V4L2 media
+ * bus pixel format code.
+ */
+static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
+{
+	switch (mbus_code) {
+	case V4L2_MBUS_FMT_BGR565_2X8_BE:
+	case V4L2_MBUS_FMT_BGR565_2X8_LE:
+	case V4L2_MBUS_FMT_RGB565_2X8_BE:
+	case V4L2_MBUS_FMT_RGB565_2X8_LE:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB565;
+		cfg->mipi_dt = MIPI_DT_RGB565;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_RGB444_2X8_PADHI_BE:
+	case V4L2_MBUS_FMT_RGB444_2X8_PADHI_LE:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB444;
+		cfg->mipi_dt = MIPI_DT_RGB444;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_RGB555_2X8_PADHI_BE:
+	case V4L2_MBUS_FMT_RGB555_2X8_PADHI_LE:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB555;
+		cfg->mipi_dt = MIPI_DT_RGB555;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_UYVY8_2X8:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_UYVY;
+		cfg->mipi_dt = MIPI_DT_YUV422;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_YUYV8_2X8:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_YUYV;
+		cfg->mipi_dt = MIPI_DT_YUV422;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_UYVY8_1X16:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_UYVY;
+		cfg->mipi_dt = MIPI_DT_YUV422;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_16;
+		break;
+	case V4L2_MBUS_FMT_YUYV8_1X16:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_YUYV;
+		cfg->mipi_dt = MIPI_DT_YUV422;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_16;
+		break;
+	case V4L2_MBUS_FMT_SBGGR8_1X8:
+	case V4L2_MBUS_FMT_SGBRG8_1X8:
+	case V4L2_MBUS_FMT_SGRBG8_1X8:
+	case V4L2_MBUS_FMT_SRGGB8_1X8:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
+		cfg->mipi_dt = MIPI_DT_RAW8;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_SBGGR10_DPCM8_1X8:
+	case V4L2_MBUS_FMT_SGBRG10_DPCM8_1X8:
+	case V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8:
+	case V4L2_MBUS_FMT_SRGGB10_DPCM8_1X8:
+	case V4L2_MBUS_FMT_SBGGR10_2X8_PADHI_BE:
+	case V4L2_MBUS_FMT_SBGGR10_2X8_PADHI_LE:
+	case V4L2_MBUS_FMT_SBGGR10_2X8_PADLO_BE:
+	case V4L2_MBUS_FMT_SBGGR10_2X8_PADLO_LE:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
+		cfg->mipi_dt = MIPI_DT_RAW10;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_SBGGR10_1X10:
+	case V4L2_MBUS_FMT_SGBRG10_1X10:
+	case V4L2_MBUS_FMT_SGRBG10_1X10:
+	case V4L2_MBUS_FMT_SRGGB10_1X10:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
+		cfg->mipi_dt = MIPI_DT_RAW10;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_10;
+		break;
+	case V4L2_MBUS_FMT_SBGGR12_1X12:
+	case V4L2_MBUS_FMT_SGBRG12_1X12:
+	case V4L2_MBUS_FMT_SGRBG12_1X12:
+	case V4L2_MBUS_FMT_SRGGB12_1X12:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
+		cfg->mipi_dt = MIPI_DT_RAW12;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_12;
+		break;
+	case V4L2_MBUS_FMT_JPEG_1X8:
+		/* TODO */
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_JPEG;
+		cfg->mipi_dt = MIPI_DT_RAW8;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Fill a CSI bus config struct from mbus_config and mbus_framefmt.
+ */
+static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
+				 struct v4l2_mbus_config *mbus_cfg,
+				 struct v4l2_mbus_framefmt *mbus_fmt)
+{
+	memset(csicfg, 0, sizeof(*csicfg));
+
+	mbus_code_to_bus_cfg(csicfg, mbus_fmt->code);
+
+	switch (mbus_cfg->type) {
+	case V4L2_MBUS_PARALLEL:
+		csicfg->ext_vsync = 1;
+		csicfg->vsync_pol = (mbus_cfg->flags &
+				     V4L2_MBUS_VSYNC_ACTIVE_LOW) ? 1 : 0;
+		csicfg->hsync_pol = (mbus_cfg->flags &
+				     V4L2_MBUS_HSYNC_ACTIVE_LOW) ? 1 : 0;
+		csicfg->pixclk_pol = (mbus_cfg->flags &
+				      V4L2_MBUS_PCLK_SAMPLE_FALLING) ? 1 : 0;
+		csicfg->clk_mode = IPU_CSI_CLK_MODE_GATED_CLK;
+		break;
+	case V4L2_MBUS_BT656:
+		csicfg->ext_vsync = 0;
+		if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field))
+			csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_INTERLACED;
+		else
+			csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE;
+		break;
+	case V4L2_MBUS_CSI2:
+		/*
+		 * MIPI CSI-2 requires non gated clock mode, all other
+		 * parameters are not applicable for MIPI CSI-2 bus.
+		 */
+		csicfg->clk_mode = IPU_CSI_CLK_MODE_NONGATED_CLK;
+		break;
+	default:
+		/* will never get here, keep compiler quiet */
+		break;
+	}
+}
+
+int ipu_csi_init_interface(struct ipu_csi *csi,
+			   struct v4l2_mbus_config *mbus_cfg,
+			   struct v4l2_mbus_framefmt *mbus_fmt)
+{
+	struct ipu_csi_bus_config cfg;
+	unsigned long flags;
+	u32 data = 0;
+
+	fill_csi_bus_cfg(&cfg, mbus_cfg, mbus_fmt);
+
+	/* Set the CSI_SENS_CONF register remaining fields */
+	data |= cfg.data_width << CSI_SENS_CONF_DATA_WIDTH_SHIFT |
+		cfg.data_fmt << CSI_SENS_CONF_DATA_FMT_SHIFT |
+		cfg.data_pol << CSI_SENS_CONF_DATA_POL_SHIFT |
+		cfg.vsync_pol << CSI_SENS_CONF_VSYNC_POL_SHIFT |
+		cfg.hsync_pol << CSI_SENS_CONF_HSYNC_POL_SHIFT |
+		cfg.pixclk_pol << CSI_SENS_CONF_PIX_CLK_POL_SHIFT |
+		cfg.ext_vsync << CSI_SENS_CONF_EXT_VSYNC_SHIFT |
+		cfg.clk_mode << CSI_SENS_CONF_SENS_PRTCL_SHIFT |
+		cfg.pack_tight << CSI_SENS_CONF_PACK_TIGHT_SHIFT |
+		cfg.force_eof << CSI_SENS_CONF_FORCE_EOF_SHIFT |
+		cfg.data_en_pol << CSI_SENS_CONF_DATA_EN_POL_SHIFT;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	ipu_csi_write(csi, data, CSI_SENS_CONF);
+
+	/* Setup sensor frame size */
+	ipu_csi_write(csi,
+		      (mbus_fmt->width - 1) | ((mbus_fmt->height - 1) << 16),
+		      CSI_SENS_FRM_SIZE);
+
+	/* Set CCIR registers */
+
+	switch (cfg.clk_mode) {
+	case IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE:
+		ipu_csi_write(csi, 0x40030, CSI_CCIR_CODE_1);
+		ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3);
+		break;
+	case IPU_CSI_CLK_MODE_CCIR656_INTERLACED:
+		if (mbus_fmt->width == 720 && mbus_fmt->height == 576) {
+			/*
+			 * PAL case
+			 *
+			 * Field0BlankEnd = 0x6, Field0BlankStart = 0x2,
+			 * Field0ActiveEnd = 0x4, Field0ActiveStart = 0
+			 * Field1BlankEnd = 0x7, Field1BlankStart = 0x3,
+			 * Field1ActiveEnd = 0x5, Field1ActiveStart = 0x1
+			 */
+			ipu_csi_write(csi, 0x40596 | CSI_CCIR_ERR_DET_EN,
+					  CSI_CCIR_CODE_1);
+			ipu_csi_write(csi, 0xD07DF, CSI_CCIR_CODE_2);
+			ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3);
+
+		} else if (mbus_fmt->width == 720 && mbus_fmt->height == 480) {
+			/*
+			 * NTSC case
+			 *
+			 * Field0BlankEnd = 0x7, Field0BlankStart = 0x3,
+			 * Field0ActiveEnd = 0x5, Field0ActiveStart = 0x1
+			 * Field1BlankEnd = 0x6, Field1BlankStart = 0x2,
+			 * Field1ActiveEnd = 0x4, Field1ActiveStart = 0
+			 */
+			ipu_csi_write(csi, 0xD07DF | CSI_CCIR_ERR_DET_EN,
+					  CSI_CCIR_CODE_1);
+			ipu_csi_write(csi, 0x40596, CSI_CCIR_CODE_2);
+			ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3);
+		} else {
+			dev_err(csi->ipu->dev,
+				"Unsupported CCIR656 interlaced video mode\n");
+			spin_unlock_irqrestore(&csi->lock, flags);
+			return -EINVAL;
+		}
+		break;
+	case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_DDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_SDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_DDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_SDR:
+		ipu_csi_write(csi, 0x40030 | CSI_CCIR_ERR_DET_EN,
+				   CSI_CCIR_CODE_1);
+		ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3);
+		break;
+	case IPU_CSI_CLK_MODE_GATED_CLK:
+	case IPU_CSI_CLK_MODE_NONGATED_CLK:
+		ipu_csi_write(csi, 0, CSI_CCIR_CODE_1);
+		break;
+	}
+
+	dev_dbg(csi->ipu->dev, "CSI_SENS_CONF = 0x%08X\n",
+		ipu_csi_read(csi, CSI_SENS_CONF));
+	dev_dbg(csi->ipu->dev, "CSI_ACT_FRM_SIZE = 0x%08X\n",
+		ipu_csi_read(csi, CSI_ACT_FRM_SIZE));
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_init_interface);
+
+bool ipu_csi_is_interlaced(struct ipu_csi *csi)
+{
+	unsigned long flags;
+	u32 sensor_protocol;
+
+	spin_lock_irqsave(&csi->lock, flags);
+	sensor_protocol =
+		(ipu_csi_read(csi, CSI_SENS_CONF) &
+		 CSI_SENS_CONF_SENS_PRTCL_MASK) >>
+		CSI_SENS_CONF_SENS_PRTCL_SHIFT;
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	switch (sensor_protocol) {
+	case IPU_CSI_CLK_MODE_GATED_CLK:
+	case IPU_CSI_CLK_MODE_NONGATED_CLK:
+	case IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE:
+	case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_DDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_SDR:
+		return false;
+	case IPU_CSI_CLK_MODE_CCIR656_INTERLACED:
+	case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_DDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_SDR:
+		return true;
+	default:
+		dev_err(csi->ipu->dev,
+			"CSI %d sensor protocol unsupported\n", csi->id);
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(ipu_csi_is_interlaced);
+
+void ipu_csi_get_window(struct ipu_csi *csi, struct v4l2_rect *w)
+{
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	reg = ipu_csi_read(csi, CSI_ACT_FRM_SIZE);
+	w->width = (reg & 0xFFFF) + 1;
+	w->height = (reg >> 16 & 0xFFFF) + 1;
+
+	reg = ipu_csi_read(csi, CSI_OUT_FRM_CTRL);
+	w->left = (reg & CSI_HSC_MASK) >> CSI_HSC_SHIFT;
+	w->top = (reg & CSI_VSC_MASK) >> CSI_VSC_SHIFT;
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_get_window);
+
+void ipu_csi_set_window(struct ipu_csi *csi, struct v4l2_rect *w)
+{
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	ipu_csi_write(csi, (w->width - 1) | ((w->height - 1) << 16),
+			  CSI_ACT_FRM_SIZE);
+
+	reg = ipu_csi_read(csi, CSI_OUT_FRM_CTRL);
+	reg &= ~(CSI_HSC_MASK | CSI_VSC_MASK);
+	reg |= ((w->top << CSI_VSC_SHIFT) | (w->left << CSI_HSC_SHIFT));
+	ipu_csi_write(csi, reg, CSI_OUT_FRM_CTRL);
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_window);
+
+void ipu_csi_set_test_generator(struct ipu_csi *csi, bool active,
+				u32 r_value, u32 g_value, u32 b_value,
+				u32 pix_clk)
+{
+	unsigned long flags;
+	u32 ipu_clk = clk_get_rate(csi->clk_ipu);
+	u32 temp;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	temp = ipu_csi_read(csi, CSI_TST_CTRL);
+
+	if (active == false) {
+		temp &= ~CSI_TEST_GEN_MODE_EN;
+		ipu_csi_write(csi, temp, CSI_TST_CTRL);
+	} else {
+		/* Set sensb_mclk div_ratio */
+		ipu_csi_set_testgen_mclk(csi, pix_clk, ipu_clk);
+
+		temp &= ~(CSI_TEST_GEN_R_MASK | CSI_TEST_GEN_G_MASK |
+			  CSI_TEST_GEN_B_MASK);
+		temp |= CSI_TEST_GEN_MODE_EN;
+		temp |= (r_value << CSI_TEST_GEN_R_SHIFT) |
+			(g_value << CSI_TEST_GEN_G_SHIFT) |
+			(b_value << CSI_TEST_GEN_B_SHIFT);
+		ipu_csi_write(csi, temp, CSI_TST_CTRL);
+	}
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_test_generator);
+
+int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc,
+			      struct v4l2_mbus_framefmt *mbus_fmt)
+{
+	struct ipu_csi_bus_config cfg;
+	unsigned long flags;
+	u32 temp;
+
+	if (vc > 3)
+		return -EINVAL;
+
+	mbus_code_to_bus_cfg(&cfg, mbus_fmt->code);
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	temp = ipu_csi_read(csi, CSI_MIPI_DI);
+	temp &= ~(0xff << (vc * 8));
+	temp |= (cfg.mipi_dt << (vc * 8));
+	ipu_csi_write(csi, temp, CSI_MIPI_DI);
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_mipi_datatype);
+
+int ipu_csi_set_skip_smfc(struct ipu_csi *csi, u32 skip,
+			  u32 max_ratio, u32 id)
+{
+	unsigned long flags;
+	u32 temp;
+
+	if (max_ratio > 5 || id > 3)
+		return -EINVAL;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	temp = ipu_csi_read(csi, CSI_SKIP);
+	temp &= ~(CSI_MAX_RATIO_SKIP_SMFC_MASK | CSI_ID_2_SKIP_MASK |
+		  CSI_SKIP_SMFC_MASK);
+	temp |= (max_ratio << CSI_MAX_RATIO_SKIP_SMFC_SHIFT) |
+		(id << CSI_ID_2_SKIP_SHIFT) |
+		(skip << CSI_SKIP_SMFC_SHIFT);
+	ipu_csi_write(csi, temp, CSI_SKIP);
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_skip_smfc);
+
+int ipu_csi_set_dest(struct ipu_csi *csi, enum ipu_csi_dest csi_dest)
+{
+	unsigned long flags;
+	u32 csi_sens_conf, dest;
+
+	if (csi_dest == IPU_CSI_DEST_IDMAC)
+		dest = CSI_DATA_DEST_IDMAC;
+	else
+		dest = CSI_DATA_DEST_IC; /* IC or VDIC */
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	csi_sens_conf = ipu_csi_read(csi, CSI_SENS_CONF);
+	csi_sens_conf &= ~CSI_SENS_CONF_DATA_DEST_MASK;
+	csi_sens_conf |= (dest << CSI_SENS_CONF_DATA_DEST_SHIFT);
+	ipu_csi_write(csi, csi_sens_conf, CSI_SENS_CONF);
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_dest);
+
+int ipu_csi_enable(struct ipu_csi *csi)
+{
+	ipu_module_enable(csi->ipu, csi->module);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_enable);
+
+int ipu_csi_disable(struct ipu_csi *csi)
+{
+	ipu_module_disable(csi->ipu, csi->module);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_disable);
+
+struct ipu_csi *ipu_csi_get(struct ipu_soc *ipu, int id)
+{
+	unsigned long flags;
+	struct ipu_csi *csi, *ret;
+
+	if (id > 1)
+		return ERR_PTR(-EINVAL);
+
+	csi = ipu->csi_priv[id];
+	ret = csi;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	if (csi->inuse) {
+		ret = ERR_PTR(-EBUSY);
+		goto unlock;
+	}
+
+	csi->inuse = true;
+unlock:
+	spin_unlock_irqrestore(&csi->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_get);
+
+void ipu_csi_put(struct ipu_csi *csi)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&csi->lock, flags);
+	csi->inuse = false;
+	spin_unlock_irqrestore(&csi->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_put);
+
+int ipu_csi_init(struct ipu_soc *ipu, struct device *dev, int id,
+		 unsigned long base, u32 module, struct clk *clk_ipu)
+{
+	struct ipu_csi *csi;
+
+	if (id > 1)
+		return -ENODEV;
+
+	csi = devm_kzalloc(dev, sizeof(*csi), GFP_KERNEL);
+	if (!csi)
+		return -ENOMEM;
+
+	ipu->csi_priv[id] = csi;
+
+	spin_lock_init(&csi->lock);
+	csi->module = module;
+	csi->id = id;
+	csi->clk_ipu = clk_ipu;
+	csi->base = devm_ioremap(dev, base, PAGE_SIZE);
+	if (!csi->base)
+		return -ENOMEM;
+
+	dev_dbg(dev, "CSI%d base: 0x%08lx remapped to %p\n",
+		id, base, csi->base);
+	csi->ipu = ipu;
+
+	return 0;
+}
+
+void ipu_csi_exit(struct ipu_soc *ipu, int id)
+{
+}
+
+void ipu_csi_dump(struct ipu_csi *csi)
+{
+	dev_dbg(csi->ipu->dev, "CSI_SENS_CONF:     %08x\n",
+		ipu_csi_read(csi, CSI_SENS_CONF));
+	dev_dbg(csi->ipu->dev, "CSI_SENS_FRM_SIZE: %08x\n",
+		ipu_csi_read(csi, CSI_SENS_FRM_SIZE));
+	dev_dbg(csi->ipu->dev, "CSI_ACT_FRM_SIZE:  %08x\n",
+		ipu_csi_read(csi, CSI_ACT_FRM_SIZE));
+	dev_dbg(csi->ipu->dev, "CSI_OUT_FRM_CTRL:  %08x\n",
+		ipu_csi_read(csi, CSI_OUT_FRM_CTRL));
+	dev_dbg(csi->ipu->dev, "CSI_TST_CTRL:      %08x\n",
+		ipu_csi_read(csi, CSI_TST_CTRL));
+	dev_dbg(csi->ipu->dev, "CSI_CCIR_CODE_1:   %08x\n",
+		ipu_csi_read(csi, CSI_CCIR_CODE_1));
+	dev_dbg(csi->ipu->dev, "CSI_CCIR_CODE_2:   %08x\n",
+		ipu_csi_read(csi, CSI_CCIR_CODE_2));
+	dev_dbg(csi->ipu->dev, "CSI_CCIR_CODE_3:   %08x\n",
+		ipu_csi_read(csi, CSI_CCIR_CODE_3));
+	dev_dbg(csi->ipu->dev, "CSI_MIPI_DI:       %08x\n",
+		ipu_csi_read(csi, CSI_MIPI_DI));
+	dev_dbg(csi->ipu->dev, "CSI_SKIP:          %08x\n",
+		ipu_csi_read(csi, CSI_SKIP));
+}
+EXPORT_SYMBOL_GPL(ipu_csi_dump);
diff --git a/drivers/gpu/ipu-v3/ipu-prv.h b/drivers/gpu/ipu-v3/ipu-prv.h
index 1a5c55c05fe8..9b274f1259e1 100644
--- a/drivers/gpu/ipu-v3/ipu-prv.h
+++ b/drivers/gpu/ipu-v3/ipu-prv.h
@@ -157,6 +157,7 @@ struct ipuv3_channel {
 };
 
 struct ipu_cpmem;
+struct ipu_csi;
 struct ipu_dc_priv;
 struct ipu_dmfc_priv;
 struct ipu_di;
@@ -189,6 +190,7 @@ struct ipu_soc {
 	struct ipu_dp_priv	*dp_priv;
 	struct ipu_dmfc_priv	*dmfc_priv;
 	struct ipu_di		*di_priv[2];
+	struct ipu_csi		*csi_priv[2];
 	struct ipu_smfc_priv	*smfc_priv;
 };
 
@@ -211,6 +213,10 @@ int ipu_module_disable(struct ipu_soc *ipu, u32 mask);
 bool ipu_idmac_channel_busy(struct ipu_soc *ipu, unsigned int chno);
 int ipu_wait_interrupt(struct ipu_soc *ipu, int irq, int ms);
 
+int ipu_csi_init(struct ipu_soc *ipu, struct device *dev, int id,
+		 unsigned long base, u32 module, struct clk *clk_ipu);
+void ipu_csi_exit(struct ipu_soc *ipu, int id);
+
 int ipu_di_init(struct ipu_soc *ipu, struct device *dev, int id,
 		unsigned long base, u32 module, struct clk *ipu_clk);
 void ipu_di_exit(struct ipu_soc *ipu, int id);
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index f80fe13b0d4d..6d254275192b 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -16,6 +16,7 @@
 #include <linux/videodev2.h>
 #include <linux/bitmap.h>
 #include <linux/fb.h>
+#include <media/v4l2-mediabus.h>
 
 struct ipu_soc;
 
@@ -61,6 +62,15 @@ struct ipu_di_signal_cfg {
 	u8 vsync_pin;
 };
 
+/*
+ * Enumeration of CSI destinations
+ */
+enum ipu_csi_dest {
+	IPU_CSI_DEST_IDMAC, /* to memory via SMFC */
+	IPU_CSI_DEST_IC,	/* to Image Converter */
+	IPU_CSI_DEST_VDIC,  /* to VDIC */
+};
+
 enum ipu_color_space {
 	IPUV3_COLORSPACE_RGB,
 	IPUV3_COLORSPACE_YUV,
@@ -211,8 +221,26 @@ int ipu_dp_set_global_alpha(struct ipu_dp *dp, bool enable, u8 alpha,
 /*
  * IPU CMOS Sensor Interface (csi) functions
  */
-int ipu_csi_enable(struct ipu_soc *ipu, int csi);
-int ipu_csi_disable(struct ipu_soc *ipu, int csi);
+struct ipu_csi;
+int ipu_csi_init_interface(struct ipu_csi *csi,
+			   struct v4l2_mbus_config *mbus_cfg,
+			   struct v4l2_mbus_framefmt *mbus_fmt);
+bool ipu_csi_is_interlaced(struct ipu_csi *csi);
+void ipu_csi_get_window(struct ipu_csi *csi, struct v4l2_rect *w);
+void ipu_csi_set_window(struct ipu_csi *csi, struct v4l2_rect *w);
+void ipu_csi_set_test_generator(struct ipu_csi *csi, bool active,
+				u32 r_value, u32 g_value, u32 b_value,
+				u32 pix_clk);
+int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc,
+			      struct v4l2_mbus_framefmt *mbus_fmt);
+int ipu_csi_set_skip_smfc(struct ipu_csi *csi, u32 skip,
+			  u32 max_ratio, u32 id);
+int ipu_csi_set_dest(struct ipu_csi *csi, enum ipu_csi_dest csi_dest);
+int ipu_csi_enable(struct ipu_csi *csi);
+int ipu_csi_disable(struct ipu_csi *csi);
+struct ipu_csi *ipu_csi_get(struct ipu_soc *ipu, int id);
+void ipu_csi_put(struct ipu_csi *csi);
+void ipu_csi_dump(struct ipu_csi *csi);
 
 /*
  * IPU Sensor Multiple FIFO Controller (SMFC) functions
-- 
cgit v1.2.3


From 1aa8ea0d2bd5d4ba7b5d2b132a02157bc1fb9793 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Mon, 11 Aug 2014 13:04:50 +0200
Subject: gpu: ipu-v3: Add Image Converter unit

Adds the Image Converter (IC) unit.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>

Condensed the three CSC setup functions into a single one that
uses static tables to set up the CSC task parameters.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/Makefile     |   2 +-
 drivers/gpu/ipu-v3/ipu-common.c |  19 +-
 drivers/gpu/ipu-v3/ipu-ic.c     | 778 ++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/ipu-v3/ipu-prv.h    |   6 +
 include/video/imx-ipu-v3.h      |  45 +++
 5 files changed, 848 insertions(+), 2 deletions(-)
 create mode 100644 drivers/gpu/ipu-v3/ipu-ic.c

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/Makefile b/drivers/gpu/ipu-v3/Makefile
index d22bd06caa6d..107ec236a4a6 100644
--- a/drivers/gpu/ipu-v3/Makefile
+++ b/drivers/gpu/ipu-v3/Makefile
@@ -1,4 +1,4 @@
 obj-$(CONFIG_IMX_IPUV3_CORE) += imx-ipu-v3.o
 
 imx-ipu-v3-objs := ipu-common.o ipu-cpmem.o ipu-csi.o ipu-dc.o ipu-di.o \
-		ipu-dp.o ipu-dmfc.o ipu-smfc.o
+		ipu-dp.o ipu-dmfc.o ipu-ic.o ipu-smfc.o
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 511c364231a2..312eef6ffcad 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -429,6 +429,7 @@ struct ipu_devtype {
 	unsigned long tpm_ofs;
 	unsigned long csi0_ofs;
 	unsigned long csi1_ofs;
+	unsigned long ic_ofs;
 	unsigned long disp0_ofs;
 	unsigned long disp1_ofs;
 	unsigned long dc_tmpl_ofs;
@@ -444,6 +445,7 @@ static struct ipu_devtype ipu_type_imx51 = {
 	.tpm_ofs = 0x1f060000,
 	.csi0_ofs = 0x1f030000,
 	.csi1_ofs = 0x1f038000,
+	.ic_ofs = 0x1f020000,
 	.disp0_ofs = 0x1e040000,
 	.disp1_ofs = 0x1e048000,
 	.dc_tmpl_ofs = 0x1f080000,
@@ -459,6 +461,7 @@ static struct ipu_devtype ipu_type_imx53 = {
 	.tpm_ofs = 0x07060000,
 	.csi0_ofs = 0x07030000,
 	.csi1_ofs = 0x07038000,
+	.ic_ofs = 0x07020000,
 	.disp0_ofs = 0x06040000,
 	.disp1_ofs = 0x06048000,
 	.dc_tmpl_ofs = 0x07080000,
@@ -474,6 +477,7 @@ static struct ipu_devtype ipu_type_imx6q = {
 	.tpm_ofs = 0x00360000,
 	.csi0_ofs = 0x00230000,
 	.csi1_ofs = 0x00238000,
+	.ic_ofs = 0x00220000,
 	.disp0_ofs = 0x00240000,
 	.disp1_ofs = 0x00248000,
 	.dc_tmpl_ofs = 0x00380000,
@@ -518,8 +522,16 @@ static int ipu_submodules_init(struct ipu_soc *ipu,
 		goto err_csi_1;
 	}
 
+	ret = ipu_ic_init(ipu, dev,
+			  ipu_base + devtype->ic_ofs,
+			  ipu_base + devtype->tpm_ofs);
+	if (ret) {
+		unit = "ic";
+		goto err_ic;
+	}
+
 	ret = ipu_di_init(ipu, dev, 0, ipu_base + devtype->disp0_ofs,
-			IPU_CONF_DI0_EN, ipu_clk);
+			  IPU_CONF_DI0_EN, ipu_clk);
 	if (ret) {
 		unit = "di0";
 		goto err_di_0;
@@ -572,6 +584,8 @@ err_dc:
 err_di_1:
 	ipu_di_exit(ipu, 0);
 err_di_0:
+	ipu_ic_exit(ipu);
+err_ic:
 	ipu_csi_exit(ipu, 1);
 err_csi_1:
 	ipu_csi_exit(ipu, 0);
@@ -654,6 +668,7 @@ static void ipu_submodules_exit(struct ipu_soc *ipu)
 	ipu_dc_exit(ipu);
 	ipu_di_exit(ipu, 1);
 	ipu_di_exit(ipu, 0);
+	ipu_ic_exit(ipu);
 	ipu_csi_exit(ipu, 1);
 	ipu_csi_exit(ipu, 0);
 	ipu_cpmem_exit(ipu);
@@ -879,6 +894,8 @@ static int ipu_probe(struct platform_device *pdev)
 			ipu_base + devtype->csi0_ofs);
 	dev_dbg(&pdev->dev, "csi1:    0x%08lx\n",
 			ipu_base + devtype->csi1_ofs);
+	dev_dbg(&pdev->dev, "ic:      0x%08lx\n",
+			ipu_base + devtype->ic_ofs);
 	dev_dbg(&pdev->dev, "disp0:    0x%08lx\n",
 			ipu_base + devtype->disp0_ofs);
 	dev_dbg(&pdev->dev, "disp1:    0x%08lx\n",
diff --git a/drivers/gpu/ipu-v3/ipu-ic.c b/drivers/gpu/ipu-v3/ipu-ic.c
new file mode 100644
index 000000000000..ad75588e1629
--- /dev/null
+++ b/drivers/gpu/ipu-v3/ipu-ic.c
@@ -0,0 +1,778 @@
+/*
+ * Copyright (C) 2012-2014 Mentor Graphics Inc.
+ * Copyright 2005-2012 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/bitrev.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include "ipu-prv.h"
+
+/* IC Register Offsets */
+#define IC_CONF                 0x0000
+#define IC_PRP_ENC_RSC          0x0004
+#define IC_PRP_VF_RSC           0x0008
+#define IC_PP_RSC               0x000C
+#define IC_CMBP_1               0x0010
+#define IC_CMBP_2               0x0014
+#define IC_IDMAC_1              0x0018
+#define IC_IDMAC_2              0x001C
+#define IC_IDMAC_3              0x0020
+#define IC_IDMAC_4              0x0024
+
+/* IC Register Fields */
+#define IC_CONF_PRPENC_EN       (1 << 0)
+#define IC_CONF_PRPENC_CSC1     (1 << 1)
+#define IC_CONF_PRPENC_ROT_EN   (1 << 2)
+#define IC_CONF_PRPVF_EN        (1 << 8)
+#define IC_CONF_PRPVF_CSC1      (1 << 9)
+#define IC_CONF_PRPVF_CSC2      (1 << 10)
+#define IC_CONF_PRPVF_CMB       (1 << 11)
+#define IC_CONF_PRPVF_ROT_EN    (1 << 12)
+#define IC_CONF_PP_EN           (1 << 16)
+#define IC_CONF_PP_CSC1         (1 << 17)
+#define IC_CONF_PP_CSC2         (1 << 18)
+#define IC_CONF_PP_CMB          (1 << 19)
+#define IC_CONF_PP_ROT_EN       (1 << 20)
+#define IC_CONF_IC_GLB_LOC_A    (1 << 28)
+#define IC_CONF_KEY_COLOR_EN    (1 << 29)
+#define IC_CONF_RWS_EN          (1 << 30)
+#define IC_CONF_CSI_MEM_WR_EN   (1 << 31)
+
+#define IC_IDMAC_1_CB0_BURST_16         (1 << 0)
+#define IC_IDMAC_1_CB1_BURST_16         (1 << 1)
+#define IC_IDMAC_1_CB2_BURST_16         (1 << 2)
+#define IC_IDMAC_1_CB3_BURST_16         (1 << 3)
+#define IC_IDMAC_1_CB4_BURST_16         (1 << 4)
+#define IC_IDMAC_1_CB5_BURST_16         (1 << 5)
+#define IC_IDMAC_1_CB6_BURST_16         (1 << 6)
+#define IC_IDMAC_1_CB7_BURST_16         (1 << 7)
+#define IC_IDMAC_1_PRPENC_ROT_MASK      (0x7 << 11)
+#define IC_IDMAC_1_PRPENC_ROT_OFFSET    11
+#define IC_IDMAC_1_PRPVF_ROT_MASK       (0x7 << 14)
+#define IC_IDMAC_1_PRPVF_ROT_OFFSET     14
+#define IC_IDMAC_1_PP_ROT_MASK          (0x7 << 17)
+#define IC_IDMAC_1_PP_ROT_OFFSET        17
+#define IC_IDMAC_1_PP_FLIP_RS           (1 << 22)
+#define IC_IDMAC_1_PRPVF_FLIP_RS        (1 << 21)
+#define IC_IDMAC_1_PRPENC_FLIP_RS       (1 << 20)
+
+#define IC_IDMAC_2_PRPENC_HEIGHT_MASK   (0x3ff << 0)
+#define IC_IDMAC_2_PRPENC_HEIGHT_OFFSET 0
+#define IC_IDMAC_2_PRPVF_HEIGHT_MASK    (0x3ff << 10)
+#define IC_IDMAC_2_PRPVF_HEIGHT_OFFSET  10
+#define IC_IDMAC_2_PP_HEIGHT_MASK       (0x3ff << 20)
+#define IC_IDMAC_2_PP_HEIGHT_OFFSET     20
+
+#define IC_IDMAC_3_PRPENC_WIDTH_MASK    (0x3ff << 0)
+#define IC_IDMAC_3_PRPENC_WIDTH_OFFSET  0
+#define IC_IDMAC_3_PRPVF_WIDTH_MASK     (0x3ff << 10)
+#define IC_IDMAC_3_PRPVF_WIDTH_OFFSET   10
+#define IC_IDMAC_3_PP_WIDTH_MASK        (0x3ff << 20)
+#define IC_IDMAC_3_PP_WIDTH_OFFSET      20
+
+struct ic_task_regoffs {
+	u32 rsc;
+	u32 tpmem_csc[2];
+};
+
+struct ic_task_bitfields {
+	u32 ic_conf_en;
+	u32 ic_conf_rot_en;
+	u32 ic_conf_cmb_en;
+	u32 ic_conf_csc1_en;
+	u32 ic_conf_csc2_en;
+	u32 ic_cmb_galpha_bit;
+};
+
+static const struct ic_task_regoffs ic_task_reg[IC_NUM_TASKS] = {
+	[IC_TASK_ENCODER] = {
+		.rsc = IC_PRP_ENC_RSC,
+		.tpmem_csc = {0x2008, 0},
+	},
+	[IC_TASK_VIEWFINDER] = {
+		.rsc = IC_PRP_VF_RSC,
+		.tpmem_csc = {0x4028, 0x4040},
+	},
+	[IC_TASK_POST_PROCESSOR] = {
+		.rsc = IC_PP_RSC,
+		.tpmem_csc = {0x6060, 0x6078},
+	},
+};
+
+static const struct ic_task_bitfields ic_task_bit[IC_NUM_TASKS] = {
+	[IC_TASK_ENCODER] = {
+		.ic_conf_en = IC_CONF_PRPENC_EN,
+		.ic_conf_rot_en = IC_CONF_PRPENC_ROT_EN,
+		.ic_conf_cmb_en = 0,    /* NA */
+		.ic_conf_csc1_en = IC_CONF_PRPENC_CSC1,
+		.ic_conf_csc2_en = 0,   /* NA */
+		.ic_cmb_galpha_bit = 0, /* NA */
+	},
+	[IC_TASK_VIEWFINDER] = {
+		.ic_conf_en = IC_CONF_PRPVF_EN,
+		.ic_conf_rot_en = IC_CONF_PRPVF_ROT_EN,
+		.ic_conf_cmb_en = IC_CONF_PRPVF_CMB,
+		.ic_conf_csc1_en = IC_CONF_PRPVF_CSC1,
+		.ic_conf_csc2_en = IC_CONF_PRPVF_CSC2,
+		.ic_cmb_galpha_bit = 0,
+	},
+	[IC_TASK_POST_PROCESSOR] = {
+		.ic_conf_en = IC_CONF_PP_EN,
+		.ic_conf_rot_en = IC_CONF_PP_ROT_EN,
+		.ic_conf_cmb_en = IC_CONF_PP_CMB,
+		.ic_conf_csc1_en = IC_CONF_PP_CSC1,
+		.ic_conf_csc2_en = IC_CONF_PP_CSC2,
+		.ic_cmb_galpha_bit = 8,
+	},
+};
+
+struct ipu_ic_priv;
+
+struct ipu_ic {
+	enum ipu_ic_task task;
+	const struct ic_task_regoffs *reg;
+	const struct ic_task_bitfields *bit;
+
+	enum ipu_color_space in_cs, g_in_cs;
+	enum ipu_color_space out_cs;
+	bool graphics;
+	bool rotation;
+	bool in_use;
+
+	struct ipu_ic_priv *priv;
+};
+
+struct ipu_ic_priv {
+	void __iomem *base;
+	void __iomem *tpmem_base;
+	spinlock_t lock;
+	struct ipu_soc *ipu;
+	int use_count;
+	struct ipu_ic task[IC_NUM_TASKS];
+};
+
+static inline u32 ipu_ic_read(struct ipu_ic *ic, unsigned offset)
+{
+	return readl(ic->priv->base + offset);
+}
+
+static inline void ipu_ic_write(struct ipu_ic *ic, u32 value, unsigned offset)
+{
+	writel(value, ic->priv->base + offset);
+}
+
+struct ic_csc_params {
+	s16 coeff[3][3];	/* signed 9-bit integer coefficients */
+	s16 offset[3];		/* signed 11+2-bit fixed point offset */
+	u8 scale:2;		/* scale coefficients * 2^(scale-1) */
+	bool sat:1;		/* saturate to (16, 235(Y) / 240(U, V)) */
+};
+
+/*
+ * Y = R *  .299 + G *  .587 + B *  .114;
+ * U = R * -.169 + G * -.332 + B *  .500 + 128.;
+ * V = R *  .500 + G * -.419 + B * -.0813 + 128.;
+ */
+static const struct ic_csc_params ic_csc_rgb2ycbcr = {
+	.coeff = {
+		{ 77, 150, 29 },
+		{ 469, 427, 128 },
+		{ 128, 405, 491 },
+	},
+	.offset = { 0, 512, 512 },
+	.scale = 1,
+};
+
+/* transparent RGB->RGB matrix for graphics combining */
+static const struct ic_csc_params ic_csc_rgb2rgb = {
+	.coeff = {
+		{ 128, 0, 0 },
+		{ 0, 128, 0 },
+		{ 0, 0, 128 },
+	},
+	.scale = 2,
+};
+
+/*
+ * R = (1.164 * (Y - 16)) + (1.596 * (Cr - 128));
+ * G = (1.164 * (Y - 16)) - (0.392 * (Cb - 128)) - (0.813 * (Cr - 128));
+ * B = (1.164 * (Y - 16)) + (2.017 * (Cb - 128);
+ */
+static const struct ic_csc_params ic_csc_ycbcr2rgb = {
+	.coeff = {
+		{ 149, 0, 204 },
+		{ 149, 462, 408 },
+		{ 149, 255, 0 },
+	},
+	.offset = { -446, 266, -554 },
+	.scale = 2,
+};
+
+static int init_csc(struct ipu_ic *ic,
+		    enum ipu_color_space inf,
+		    enum ipu_color_space outf,
+		    int csc_index)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	const struct ic_csc_params *params;
+	u32 __iomem *base;
+	const u16 (*c)[3];
+	const u16 *a;
+	u32 param;
+
+	base = (u32 __iomem *)
+		(priv->tpmem_base + ic->reg->tpmem_csc[csc_index]);
+
+	if (inf == IPUV3_COLORSPACE_YUV && outf == IPUV3_COLORSPACE_RGB)
+		params = &ic_csc_ycbcr2rgb;
+	else if (inf == IPUV3_COLORSPACE_RGB && outf == IPUV3_COLORSPACE_YUV)
+		params = &ic_csc_rgb2ycbcr;
+	else if (inf == IPUV3_COLORSPACE_RGB && outf == IPUV3_COLORSPACE_RGB)
+		params = &ic_csc_rgb2rgb;
+	else {
+		dev_err(priv->ipu->dev, "Unsupported color space conversion\n");
+		return -EINVAL;
+	}
+
+	/* Cast to unsigned */
+	c = (const u16 (*)[3])params->coeff;
+	a = (const u16 *)params->offset;
+
+	param = ((a[0] & 0x1f) << 27) | ((c[0][0] & 0x1ff) << 18) |
+		((c[1][1] & 0x1ff) << 9) | (c[2][2] & 0x1ff);
+	writel(param, base++);
+
+	param = ((a[0] & 0x1fe0) >> 5) | (params->scale << 8) |
+		(params->sat << 9);
+	writel(param, base++);
+
+	param = ((a[1] & 0x1f) << 27) | ((c[0][1] & 0x1ff) << 18) |
+		((c[1][0] & 0x1ff) << 9) | (c[2][0] & 0x1ff);
+	writel(param, base++);
+
+	param = ((a[1] & 0x1fe0) >> 5);
+	writel(param, base++);
+
+	param = ((a[2] & 0x1f) << 27) | ((c[0][2] & 0x1ff) << 18) |
+		((c[1][2] & 0x1ff) << 9) | (c[2][1] & 0x1ff);
+	writel(param, base++);
+
+	param = ((a[2] & 0x1fe0) >> 5);
+	writel(param, base++);
+
+	return 0;
+}
+
+static int calc_resize_coeffs(struct ipu_ic *ic,
+			      u32 in_size, u32 out_size,
+			      u32 *resize_coeff,
+			      u32 *downsize_coeff)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	struct ipu_soc *ipu = priv->ipu;
+	u32 temp_size, temp_downsize;
+
+	/*
+	 * Input size cannot be more than 4096, and output size cannot
+	 * be more than 1024
+	 */
+	if (in_size > 4096) {
+		dev_err(ipu->dev, "Unsupported resize (in_size > 4096)\n");
+		return -EINVAL;
+	}
+	if (out_size > 1024) {
+		dev_err(ipu->dev, "Unsupported resize (out_size > 1024)\n");
+		return -EINVAL;
+	}
+
+	/* Cannot downsize more than 8:1 */
+	if ((out_size << 3) < in_size) {
+		dev_err(ipu->dev, "Unsupported downsize\n");
+		return -EINVAL;
+	}
+
+	/* Compute downsizing coefficient */
+	temp_downsize = 0;
+	temp_size = in_size;
+	while (((temp_size > 1024) || (temp_size >= out_size * 2)) &&
+	       (temp_downsize < 2)) {
+		temp_size >>= 1;
+		temp_downsize++;
+	}
+	*downsize_coeff = temp_downsize;
+
+	/*
+	 * compute resizing coefficient using the following equation:
+	 * resize_coeff = M * (SI - 1) / (SO - 1)
+	 * where M = 2^13, SI = input size, SO = output size
+	 */
+	*resize_coeff = (8192L * (temp_size - 1)) / (out_size - 1);
+	if (*resize_coeff >= 16384L) {
+		dev_err(ipu->dev, "Warning! Overflow on resize coeff.\n");
+		*resize_coeff = 0x3FFF;
+	}
+
+	return 0;
+}
+
+void ipu_ic_task_enable(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 ic_conf;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ic_conf = ipu_ic_read(ic, IC_CONF);
+
+	ic_conf |= ic->bit->ic_conf_en;
+
+	if (ic->rotation)
+		ic_conf |= ic->bit->ic_conf_rot_en;
+
+	if (ic->in_cs != ic->out_cs)
+		ic_conf |= ic->bit->ic_conf_csc1_en;
+
+	if (ic->graphics) {
+		ic_conf |= ic->bit->ic_conf_cmb_en;
+		ic_conf |= ic->bit->ic_conf_csc1_en;
+
+		if (ic->g_in_cs != ic->out_cs)
+			ic_conf |= ic->bit->ic_conf_csc2_en;
+	}
+
+	ipu_ic_write(ic, ic_conf, IC_CONF);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_enable);
+
+void ipu_ic_task_disable(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 ic_conf;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ic_conf = ipu_ic_read(ic, IC_CONF);
+
+	ic_conf &= ~(ic->bit->ic_conf_en |
+		     ic->bit->ic_conf_csc1_en |
+		     ic->bit->ic_conf_rot_en);
+	if (ic->bit->ic_conf_csc2_en)
+		ic_conf &= ~ic->bit->ic_conf_csc2_en;
+	if (ic->bit->ic_conf_cmb_en)
+		ic_conf &= ~ic->bit->ic_conf_cmb_en;
+
+	ipu_ic_write(ic, ic_conf, IC_CONF);
+
+	ic->rotation = ic->graphics = false;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_disable);
+
+int ipu_ic_task_graphics_init(struct ipu_ic *ic,
+			      enum ipu_color_space in_g_cs,
+			      bool galpha_en, u32 galpha,
+			      bool colorkey_en, u32 colorkey)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 reg, ic_conf;
+	int ret = 0;
+
+	if (ic->task == IC_TASK_ENCODER)
+		return -EINVAL;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ic_conf = ipu_ic_read(ic, IC_CONF);
+
+	if (!(ic_conf & ic->bit->ic_conf_csc1_en)) {
+		/* need transparent CSC1 conversion */
+		ret = init_csc(ic, IPUV3_COLORSPACE_RGB,
+			       IPUV3_COLORSPACE_RGB, 0);
+		if (ret)
+			goto unlock;
+	}
+
+	ic->g_in_cs = in_g_cs;
+
+	if (ic->g_in_cs != ic->out_cs) {
+		ret = init_csc(ic, ic->g_in_cs, ic->out_cs, 1);
+		if (ret)
+			goto unlock;
+	}
+
+	if (galpha_en) {
+		ic_conf |= IC_CONF_IC_GLB_LOC_A;
+		reg = ipu_ic_read(ic, IC_CMBP_1);
+		reg &= ~(0xff << ic->bit->ic_cmb_galpha_bit);
+		reg |= (galpha << ic->bit->ic_cmb_galpha_bit);
+		ipu_ic_write(ic, reg, IC_CMBP_1);
+	} else
+		ic_conf &= ~IC_CONF_IC_GLB_LOC_A;
+
+	if (colorkey_en) {
+		ic_conf |= IC_CONF_KEY_COLOR_EN;
+		ipu_ic_write(ic, colorkey, IC_CMBP_2);
+	} else
+		ic_conf &= ~IC_CONF_KEY_COLOR_EN;
+
+	ipu_ic_write(ic, ic_conf, IC_CONF);
+
+	ic->graphics = true;
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_graphics_init);
+
+int ipu_ic_task_init(struct ipu_ic *ic,
+		     int in_width, int in_height,
+		     int out_width, int out_height,
+		     enum ipu_color_space in_cs,
+		     enum ipu_color_space out_cs)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	u32 reg, downsize_coeff, resize_coeff;
+	unsigned long flags;
+	int ret = 0;
+
+	/* Setup vertical resizing */
+	ret = calc_resize_coeffs(ic, in_height, out_height,
+				 &resize_coeff, &downsize_coeff);
+	if (ret)
+		return ret;
+
+	reg = (downsize_coeff << 30) | (resize_coeff << 16);
+
+	/* Setup horizontal resizing */
+	ret = calc_resize_coeffs(ic, in_width, out_width,
+				 &resize_coeff, &downsize_coeff);
+	if (ret)
+		return ret;
+
+	reg |= (downsize_coeff << 14) | resize_coeff;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ipu_ic_write(ic, reg, ic->reg->rsc);
+
+	/* Setup color space conversion */
+	ic->in_cs = in_cs;
+	ic->out_cs = out_cs;
+
+	if (ic->in_cs != ic->out_cs) {
+		ret = init_csc(ic, ic->in_cs, ic->out_cs, 0);
+		if (ret)
+			goto unlock;
+	}
+
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_init);
+
+int ipu_ic_task_idma_init(struct ipu_ic *ic, struct ipuv3_channel *channel,
+			  u32 width, u32 height, int burst_size,
+			  enum ipu_rotate_mode rot)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	struct ipu_soc *ipu = priv->ipu;
+	u32 ic_idmac_1, ic_idmac_2, ic_idmac_3;
+	u32 temp_rot = bitrev8(rot) >> 5;
+	bool need_hor_flip = false;
+	unsigned long flags;
+	int ret = 0;
+
+	if ((burst_size != 8) && (burst_size != 16)) {
+		dev_err(ipu->dev, "Illegal burst length for IC\n");
+		return -EINVAL;
+	}
+
+	width--;
+	height--;
+
+	if (temp_rot & 0x2)	/* Need horizontal flip */
+		need_hor_flip = true;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ic_idmac_1 = ipu_ic_read(ic, IC_IDMAC_1);
+	ic_idmac_2 = ipu_ic_read(ic, IC_IDMAC_2);
+	ic_idmac_3 = ipu_ic_read(ic, IC_IDMAC_3);
+
+	switch (channel->num) {
+	case IPUV3_CHANNEL_IC_PP_MEM:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB2_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB2_BURST_16;
+
+		if (need_hor_flip)
+			ic_idmac_1 |= IC_IDMAC_1_PP_FLIP_RS;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_PP_FLIP_RS;
+
+		ic_idmac_2 &= ~IC_IDMAC_2_PP_HEIGHT_MASK;
+		ic_idmac_2 |= height << IC_IDMAC_2_PP_HEIGHT_OFFSET;
+
+		ic_idmac_3 &= ~IC_IDMAC_3_PP_WIDTH_MASK;
+		ic_idmac_3 |= width << IC_IDMAC_3_PP_WIDTH_OFFSET;
+		break;
+	case IPUV3_CHANNEL_MEM_IC_PP:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB5_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB5_BURST_16;
+		break;
+	case IPUV3_CHANNEL_MEM_ROT_PP:
+		ic_idmac_1 &= ~IC_IDMAC_1_PP_ROT_MASK;
+		ic_idmac_1 |= temp_rot << IC_IDMAC_1_PP_ROT_OFFSET;
+		break;
+	case IPUV3_CHANNEL_MEM_IC_PRP_VF:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB6_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB6_BURST_16;
+		break;
+	case IPUV3_CHANNEL_IC_PRP_ENC_MEM:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB0_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB0_BURST_16;
+
+		if (need_hor_flip)
+			ic_idmac_1 |= IC_IDMAC_1_PRPENC_FLIP_RS;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_PRPENC_FLIP_RS;
+
+		ic_idmac_2 &= ~IC_IDMAC_2_PRPENC_HEIGHT_MASK;
+		ic_idmac_2 |= height << IC_IDMAC_2_PRPENC_HEIGHT_OFFSET;
+
+		ic_idmac_3 &= ~IC_IDMAC_3_PRPENC_WIDTH_MASK;
+		ic_idmac_3 |= width << IC_IDMAC_3_PRPENC_WIDTH_OFFSET;
+		break;
+	case IPUV3_CHANNEL_MEM_ROT_ENC:
+		ic_idmac_1 &= ~IC_IDMAC_1_PRPENC_ROT_MASK;
+		ic_idmac_1 |= temp_rot << IC_IDMAC_1_PRPENC_ROT_OFFSET;
+		break;
+	case IPUV3_CHANNEL_IC_PRP_VF_MEM:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB1_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB1_BURST_16;
+
+		if (need_hor_flip)
+			ic_idmac_1 |= IC_IDMAC_1_PRPVF_FLIP_RS;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_PRPVF_FLIP_RS;
+
+		ic_idmac_2 &= ~IC_IDMAC_2_PRPVF_HEIGHT_MASK;
+		ic_idmac_2 |= height << IC_IDMAC_2_PRPVF_HEIGHT_OFFSET;
+
+		ic_idmac_3 &= ~IC_IDMAC_3_PRPVF_WIDTH_MASK;
+		ic_idmac_3 |= width << IC_IDMAC_3_PRPVF_WIDTH_OFFSET;
+		break;
+	case IPUV3_CHANNEL_MEM_ROT_VF:
+		ic_idmac_1 &= ~IC_IDMAC_1_PRPVF_ROT_MASK;
+		ic_idmac_1 |= temp_rot << IC_IDMAC_1_PRPVF_ROT_OFFSET;
+		break;
+	case IPUV3_CHANNEL_G_MEM_IC_PRP_VF:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB3_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB3_BURST_16;
+		break;
+	case IPUV3_CHANNEL_G_MEM_IC_PP:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB4_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB4_BURST_16;
+		break;
+	case IPUV3_CHANNEL_VDI_MEM_IC_VF:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB7_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB7_BURST_16;
+		break;
+	default:
+		goto unlock;
+	}
+
+	ipu_ic_write(ic, ic_idmac_1, IC_IDMAC_1);
+	ipu_ic_write(ic, ic_idmac_2, IC_IDMAC_2);
+	ipu_ic_write(ic, ic_idmac_3, IC_IDMAC_3);
+
+	if (rot >= IPU_ROTATE_90_RIGHT)
+		ic->rotation = true;
+
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_idma_init);
+
+int ipu_ic_enable(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 module = IPU_CONF_IC_EN;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	if (ic->rotation)
+		module |= IPU_CONF_ROT_EN;
+
+	if (!priv->use_count)
+		ipu_module_enable(priv->ipu, module);
+
+	priv->use_count++;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_enable);
+
+int ipu_ic_disable(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 module = IPU_CONF_IC_EN | IPU_CONF_ROT_EN;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	priv->use_count--;
+
+	if (!priv->use_count)
+		ipu_module_disable(priv->ipu, module);
+
+	if (priv->use_count < 0)
+		priv->use_count = 0;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_disable);
+
+struct ipu_ic *ipu_ic_get(struct ipu_soc *ipu, enum ipu_ic_task task)
+{
+	struct ipu_ic_priv *priv = ipu->ic_priv;
+	unsigned long flags;
+	struct ipu_ic *ic, *ret;
+
+	if (task >= IC_NUM_TASKS)
+		return ERR_PTR(-EINVAL);
+
+	ic = &priv->task[task];
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	if (ic->in_use) {
+		ret = ERR_PTR(-EBUSY);
+		goto unlock;
+	}
+
+	ic->in_use = true;
+	ret = ic;
+
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_get);
+
+void ipu_ic_put(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	ic->in_use = false;
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_ic_put);
+
+int ipu_ic_init(struct ipu_soc *ipu, struct device *dev,
+		unsigned long base, unsigned long tpmem_base)
+{
+	struct ipu_ic_priv *priv;
+	int i;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	ipu->ic_priv = priv;
+
+	spin_lock_init(&priv->lock);
+	priv->base = devm_ioremap(dev, base, PAGE_SIZE);
+	if (!priv->base)
+		return -ENOMEM;
+	priv->tpmem_base = devm_ioremap(dev, tpmem_base, SZ_64K);
+	if (!priv->tpmem_base)
+		return -ENOMEM;
+
+	dev_dbg(dev, "IC base: 0x%08lx remapped to %p\n", base, priv->base);
+
+	priv->ipu = ipu;
+
+	for (i = 0; i < IC_NUM_TASKS; i++) {
+		priv->task[i].task = i;
+		priv->task[i].priv = priv;
+		priv->task[i].reg = &ic_task_reg[i];
+		priv->task[i].bit = &ic_task_bit[i];
+	}
+
+	return 0;
+}
+
+void ipu_ic_exit(struct ipu_soc *ipu)
+{
+}
+
+void ipu_ic_dump(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	struct ipu_soc *ipu = priv->ipu;
+
+	dev_dbg(ipu->dev, "IC_CONF = \t0x%08X\n",
+		ipu_ic_read(ic, IC_CONF));
+	dev_dbg(ipu->dev, "IC_PRP_ENC_RSC = \t0x%08X\n",
+		ipu_ic_read(ic, IC_PRP_ENC_RSC));
+	dev_dbg(ipu->dev, "IC_PRP_VF_RSC = \t0x%08X\n",
+		ipu_ic_read(ic, IC_PRP_VF_RSC));
+	dev_dbg(ipu->dev, "IC_PP_RSC = \t0x%08X\n",
+		ipu_ic_read(ic, IC_PP_RSC));
+	dev_dbg(ipu->dev, "IC_CMBP_1 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_CMBP_1));
+	dev_dbg(ipu->dev, "IC_CMBP_2 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_CMBP_2));
+	dev_dbg(ipu->dev, "IC_IDMAC_1 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_IDMAC_1));
+	dev_dbg(ipu->dev, "IC_IDMAC_2 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_IDMAC_2));
+	dev_dbg(ipu->dev, "IC_IDMAC_3 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_IDMAC_3));
+	dev_dbg(ipu->dev, "IC_IDMAC_4 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_IDMAC_4));
+}
+EXPORT_SYMBOL_GPL(ipu_ic_dump);
diff --git a/drivers/gpu/ipu-v3/ipu-prv.h b/drivers/gpu/ipu-v3/ipu-prv.h
index 9b274f1259e1..1596a4f52faf 100644
--- a/drivers/gpu/ipu-v3/ipu-prv.h
+++ b/drivers/gpu/ipu-v3/ipu-prv.h
@@ -161,6 +161,7 @@ struct ipu_csi;
 struct ipu_dc_priv;
 struct ipu_dmfc_priv;
 struct ipu_di;
+struct ipu_ic_priv;
 struct ipu_smfc_priv;
 
 struct ipu_devtype;
@@ -191,6 +192,7 @@ struct ipu_soc {
 	struct ipu_dmfc_priv	*dmfc_priv;
 	struct ipu_di		*di_priv[2];
 	struct ipu_csi		*csi_priv[2];
+	struct ipu_ic_priv	*ic_priv;
 	struct ipu_smfc_priv	*smfc_priv;
 };
 
@@ -217,6 +219,10 @@ int ipu_csi_init(struct ipu_soc *ipu, struct device *dev, int id,
 		 unsigned long base, u32 module, struct clk *clk_ipu);
 void ipu_csi_exit(struct ipu_soc *ipu, int id);
 
+int ipu_ic_init(struct ipu_soc *ipu, struct device *dev,
+		unsigned long base, unsigned long tpmem_base);
+void ipu_ic_exit(struct ipu_soc *ipu);
+
 int ipu_di_init(struct ipu_soc *ipu, struct device *dev, int id,
 		unsigned long base, u32 module, struct clk *ipu_clk);
 void ipu_di_exit(struct ipu_soc *ipu, int id);
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 6d254275192b..a477814a03af 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -71,6 +71,20 @@ enum ipu_csi_dest {
 	IPU_CSI_DEST_VDIC,  /* to VDIC */
 };
 
+/*
+ * Enumeration of IPU rotation modes
+ */
+enum ipu_rotate_mode {
+	IPU_ROTATE_NONE = 0,
+	IPU_ROTATE_VERT_FLIP,
+	IPU_ROTATE_HORIZ_FLIP,
+	IPU_ROTATE_180,
+	IPU_ROTATE_90_RIGHT,
+	IPU_ROTATE_90_RIGHT_VFLIP,
+	IPU_ROTATE_90_RIGHT_HFLIP,
+	IPU_ROTATE_90_LEFT,
+};
+
 enum ipu_color_space {
 	IPUV3_COLORSPACE_RGB,
 	IPUV3_COLORSPACE_YUV,
@@ -242,6 +256,37 @@ struct ipu_csi *ipu_csi_get(struct ipu_soc *ipu, int id);
 void ipu_csi_put(struct ipu_csi *csi);
 void ipu_csi_dump(struct ipu_csi *csi);
 
+/*
+ * IPU Image Converter (ic) functions
+ */
+enum ipu_ic_task {
+	IC_TASK_ENCODER,
+	IC_TASK_VIEWFINDER,
+	IC_TASK_POST_PROCESSOR,
+	IC_NUM_TASKS,
+};
+
+struct ipu_ic;
+int ipu_ic_task_init(struct ipu_ic *ic,
+		     int in_width, int in_height,
+		     int out_width, int out_height,
+		     enum ipu_color_space in_cs,
+		     enum ipu_color_space out_cs);
+int ipu_ic_task_graphics_init(struct ipu_ic *ic,
+			      enum ipu_color_space in_g_cs,
+			      bool galpha_en, u32 galpha,
+			      bool colorkey_en, u32 colorkey);
+void ipu_ic_task_enable(struct ipu_ic *ic);
+void ipu_ic_task_disable(struct ipu_ic *ic);
+int ipu_ic_task_idma_init(struct ipu_ic *ic, struct ipuv3_channel *channel,
+			  u32 width, u32 height, int burst_size,
+			  enum ipu_rotate_mode rot);
+int ipu_ic_enable(struct ipu_ic *ic);
+int ipu_ic_disable(struct ipu_ic *ic);
+struct ipu_ic *ipu_ic_get(struct ipu_soc *ipu, enum ipu_ic_task task);
+void ipu_ic_put(struct ipu_ic *ic);
+void ipu_ic_dump(struct ipu_ic *ic);
+
 /*
  * IPU Sensor Multiple FIFO Controller (SMFC) functions
  */
-- 
cgit v1.2.3


From 7fafa8f06f9bdf32b806b4612bfe387de8e34125 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:34 -0700
Subject: gpu: ipu-v3: smfc: Convert to per-channel

Convert the smfc object to be specific to a single smfc channel.
Add ipu_smfc_{get|put} to retrieve and release a single smfc channel
for exclusive use, and add use counter to ipu_smfc_{enable|disable}.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-smfc.c | 132 +++++++++++++++++++++++++++++++++---------
 include/video/imx-ipu-v3.h    |  10 ++--
 2 files changed, 112 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-smfc.c b/drivers/gpu/ipu-v3/ipu-smfc.c
index 87ac624dd7ca..a6429ca913c1 100644
--- a/drivers/gpu/ipu-v3/ipu-smfc.c
+++ b/drivers/gpu/ipu-v3/ipu-smfc.c
@@ -21,9 +21,18 @@
 
 #include "ipu-prv.h"
 
+struct ipu_smfc {
+	struct ipu_smfc_priv *priv;
+	int chno;
+	bool inuse;
+};
+
 struct ipu_smfc_priv {
 	void __iomem *base;
 	spinlock_t lock;
+	struct ipu_soc *ipu;
+	struct ipu_smfc channel[4];
+	int use_count;
 };
 
 /*SMFC Registers */
@@ -31,75 +40,146 @@ struct ipu_smfc_priv {
 #define SMFC_WMC	0x0004
 #define SMFC_BS		0x0008
 
-int ipu_smfc_set_burstsize(struct ipu_soc *ipu, int channel, int burstsize)
+int ipu_smfc_set_burstsize(struct ipu_smfc *smfc, int burstsize)
 {
-	struct ipu_smfc_priv *smfc = ipu->smfc_priv;
+	struct ipu_smfc_priv *priv = smfc->priv;
 	unsigned long flags;
 	u32 val, shift;
 
-	spin_lock_irqsave(&smfc->lock, flags);
+	spin_lock_irqsave(&priv->lock, flags);
 
-	shift = channel * 4;
-	val = readl(smfc->base + SMFC_BS);
+	shift = smfc->chno * 4;
+	val = readl(priv->base + SMFC_BS);
 	val &= ~(0xf << shift);
 	val |= burstsize << shift;
-	writel(val, smfc->base + SMFC_BS);
+	writel(val, priv->base + SMFC_BS);
 
-	spin_unlock_irqrestore(&smfc->lock, flags);
+	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ipu_smfc_set_burstsize);
 
-int ipu_smfc_map_channel(struct ipu_soc *ipu, int channel, int csi_id, int mipi_id)
+int ipu_smfc_map_channel(struct ipu_smfc *smfc, int csi_id, int mipi_id)
 {
-	struct ipu_smfc_priv *smfc = ipu->smfc_priv;
+	struct ipu_smfc_priv *priv = smfc->priv;
 	unsigned long flags;
 	u32 val, shift;
 
-	spin_lock_irqsave(&smfc->lock, flags);
+	spin_lock_irqsave(&priv->lock, flags);
 
-	shift = channel * 3;
-	val = readl(smfc->base + SMFC_MAP);
+	shift = smfc->chno * 3;
+	val = readl(priv->base + SMFC_MAP);
 	val &= ~(0x7 << shift);
 	val |= ((csi_id << 2) | mipi_id) << shift;
-	writel(val, smfc->base + SMFC_MAP);
+	writel(val, priv->base + SMFC_MAP);
 
-	spin_unlock_irqrestore(&smfc->lock, flags);
+	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ipu_smfc_map_channel);
 
-int ipu_smfc_enable(struct ipu_soc *ipu)
+int ipu_smfc_enable(struct ipu_smfc *smfc)
 {
-	return ipu_module_enable(ipu, IPU_CONF_SMFC_EN);
+	struct ipu_smfc_priv *priv = smfc->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	if (!priv->use_count)
+		ipu_module_enable(priv->ipu, IPU_CONF_SMFC_EN);
+
+	priv->use_count++;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(ipu_smfc_enable);
 
-int ipu_smfc_disable(struct ipu_soc *ipu)
+int ipu_smfc_disable(struct ipu_smfc *smfc)
 {
-	return ipu_module_disable(ipu, IPU_CONF_SMFC_EN);
+	struct ipu_smfc_priv *priv = smfc->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	priv->use_count--;
+
+	if (!priv->use_count)
+		ipu_module_disable(priv->ipu, IPU_CONF_SMFC_EN);
+
+	if (priv->use_count < 0)
+		priv->use_count = 0;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(ipu_smfc_disable);
 
+struct ipu_smfc *ipu_smfc_get(struct ipu_soc *ipu, unsigned int chno)
+{
+	struct ipu_smfc_priv *priv = ipu->smfc_priv;
+	struct ipu_smfc *smfc, *ret;
+	unsigned long flags;
+
+	if (chno >= 4)
+		return ERR_PTR(-EINVAL);
+
+	smfc = &priv->channel[chno];
+	ret = smfc;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	if (smfc->inuse) {
+		ret = ERR_PTR(-EBUSY);
+		goto unlock;
+	}
+
+	smfc->inuse = true;
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_get);
+
+void ipu_smfc_put(struct ipu_smfc *smfc)
+{
+	struct ipu_smfc_priv *priv = smfc->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	smfc->inuse = false;
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_put);
+
 int ipu_smfc_init(struct ipu_soc *ipu, struct device *dev,
 		  unsigned long base)
 {
-	struct ipu_smfc_priv *smfc;
+	struct ipu_smfc_priv *priv;
+	int i;
 
-	smfc = devm_kzalloc(dev, sizeof(*smfc), GFP_KERNEL);
-	if (!smfc)
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
 		return -ENOMEM;
 
-	ipu->smfc_priv = smfc;
-	spin_lock_init(&smfc->lock);
+	ipu->smfc_priv = priv;
+	spin_lock_init(&priv->lock);
+	priv->ipu = ipu;
 
-	smfc->base = devm_ioremap(dev, base, PAGE_SIZE);
-	if (!smfc->base)
+	priv->base = devm_ioremap(dev, base, PAGE_SIZE);
+	if (!priv->base)
 		return -ENOMEM;
 
-	pr_debug("%s: ioremap 0x%08lx -> %p\n", __func__, base, smfc->base);
+	for (i = 0; i < 4; i++) {
+		priv->channel[i].priv = priv;
+		priv->channel[i].chno = i;
+	}
+
+	pr_debug("%s: ioremap 0x%08lx -> %p\n", __func__, base, priv->base);
 
 	return 0;
 }
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index a477814a03af..a695ee83e4e1 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -290,10 +290,12 @@ void ipu_ic_dump(struct ipu_ic *ic);
 /*
  * IPU Sensor Multiple FIFO Controller (SMFC) functions
  */
-int ipu_smfc_enable(struct ipu_soc *ipu);
-int ipu_smfc_disable(struct ipu_soc *ipu);
-int ipu_smfc_map_channel(struct ipu_soc *ipu, int channel, int csi_id, int mipi_id);
-int ipu_smfc_set_burstsize(struct ipu_soc *ipu, int channel, int burstsize);
+struct ipu_smfc *ipu_smfc_get(struct ipu_soc *ipu, unsigned int chno);
+void ipu_smfc_put(struct ipu_smfc *smfc);
+int ipu_smfc_enable(struct ipu_smfc *smfc);
+int ipu_smfc_disable(struct ipu_smfc *smfc);
+int ipu_smfc_map_channel(struct ipu_smfc *smfc, int csi_id, int mipi_id);
+int ipu_smfc_set_burstsize(struct ipu_smfc *smfc, int burstsize);
 
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
-- 
cgit v1.2.3


From a2be35e3320b27c84488729e9fb56a62e74d65fa Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:35 -0700
Subject: gpu: ipu-v3: smfc: Add ipu_smfc_set_watermark()

Adds ipu_smfc_set_watermark() which programs a channel's SMFC FIFO
levels at which the watermark signal is set and cleared.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-smfc.c | 20 ++++++++++++++++++++
 include/video/imx-ipu-v3.h    |  1 +
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-smfc.c b/drivers/gpu/ipu-v3/ipu-smfc.c
index a6429ca913c1..6ca9b43ce25a 100644
--- a/drivers/gpu/ipu-v3/ipu-smfc.c
+++ b/drivers/gpu/ipu-v3/ipu-smfc.c
@@ -80,6 +80,26 @@ int ipu_smfc_map_channel(struct ipu_smfc *smfc, int csi_id, int mipi_id)
 }
 EXPORT_SYMBOL_GPL(ipu_smfc_map_channel);
 
+int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level)
+{
+	struct ipu_smfc_priv *priv = smfc->priv;
+	unsigned long flags;
+	u32 val, shift;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	shift = smfc->chno * 6 + (smfc->chno > 1 ? 4 : 0);
+	val = readl(priv->base + SMFC_WMC);
+	val &= ~(0x3f << shift);
+	val |= ((clr_level << 3) | set_level) << shift;
+	writel(val, priv->base + SMFC_WMC);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_set_watermark);
+
 int ipu_smfc_enable(struct ipu_smfc *smfc)
 {
 	struct ipu_smfc_priv *priv = smfc->priv;
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index a695ee83e4e1..49e5954ac033 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -296,6 +296,7 @@ int ipu_smfc_enable(struct ipu_smfc *smfc);
 int ipu_smfc_disable(struct ipu_smfc *smfc);
 int ipu_smfc_map_channel(struct ipu_smfc *smfc, int csi_id, int mipi_id);
 int ipu_smfc_set_burstsize(struct ipu_smfc *smfc, int burstsize);
+int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level);
 
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
-- 
cgit v1.2.3


From ae0e9708b30b3eebe5a58e4d055eb49a73d641dd Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:36 -0700
Subject: gpu: ipu-v3: Add ipu_mbus_code_to_colorspace()

Add ipu_mbus_code_to_colorspace() to find ipu_color_space from a
media bus pixel format code.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 13 +++++++++++++
 include/video/imx-ipu-v3.h      |  1 +
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index f5a4e1ac2b50..49ee990b4d1f 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -101,6 +101,19 @@ enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat)
 }
 EXPORT_SYMBOL_GPL(ipu_pixelformat_to_colorspace);
 
+enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code)
+{
+	switch (mbus_code & 0xf000) {
+	case 0x1000:
+		return IPUV3_COLORSPACE_RGB;
+	case 0x2000:
+		return IPUV3_COLORSPACE_YUV;
+	default:
+		return IPUV3_COLORSPACE_UNKNOWN;
+	}
+}
+EXPORT_SYMBOL_GPL(ipu_mbus_code_to_colorspace);
+
 struct ipuv3_channel *ipu_idmac_get(struct ipu_soc *ipu, unsigned num)
 {
 	struct ipuv3_channel *channel;
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 49e5954ac033..7c97ccaf39f6 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -300,6 +300,7 @@ int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level);
 
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
+enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code);
 
 struct ipu_client_platformdata {
 	int csi;
-- 
cgit v1.2.3


From f835f386a119c3f78f5acb93e86a4f025211739a Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:37 -0700
Subject: gpu: ipu-v3: Add rotation mode conversion utilities

Add two functions:

- ipu_degrees_to_rot_mode(): converts a degrees, hflip, and vflip setting
  to an IPU rotation mode.
- ipu_rot_mode_to_degrees(): converts an IPU rotation mode with given hflip
  and vflip settings to degrees.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 64 +++++++++++++++++++++++++++++++++++++++++
 include/video/imx-ipu-v3.h      |  4 +++
 2 files changed, 68 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 49ee990b4d1f..a1d42eed5d06 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -114,6 +114,70 @@ enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code)
 }
 EXPORT_SYMBOL_GPL(ipu_mbus_code_to_colorspace);
 
+int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
+			    bool hflip, bool vflip)
+{
+	u32 r90, vf, hf;
+
+	switch (degrees) {
+	case 0:
+		vf = hf = r90 = 0;
+		break;
+	case 90:
+		vf = hf = 0;
+		r90 = 1;
+		break;
+	case 180:
+		vf = hf = 1;
+		r90 = 0;
+		break;
+	case 270:
+		vf = hf = r90 = 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	hf ^= (u32)hflip;
+	vf ^= (u32)vflip;
+
+	*mode = (enum ipu_rotate_mode)((r90 << 2) | (hf << 1) | vf);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_degrees_to_rot_mode);
+
+int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode,
+			    bool hflip, bool vflip)
+{
+	u32 r90, vf, hf;
+
+	r90 = ((u32)mode >> 2) & 0x1;
+	hf = ((u32)mode >> 1) & 0x1;
+	vf = ((u32)mode >> 0) & 0x1;
+	hf ^= (u32)hflip;
+	vf ^= (u32)vflip;
+
+	switch ((enum ipu_rotate_mode)((r90 << 2) | (hf << 1) | vf)) {
+	case IPU_ROTATE_NONE:
+		*degrees = 0;
+		break;
+	case IPU_ROTATE_90_RIGHT:
+		*degrees = 90;
+		break;
+	case IPU_ROTATE_180:
+		*degrees = 180;
+		break;
+	case IPU_ROTATE_90_LEFT:
+		*degrees = 270;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_rot_mode_to_degrees);
+
 struct ipuv3_channel *ipu_idmac_get(struct ipu_soc *ipu, unsigned num)
 {
 	struct ipuv3_channel *channel;
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 7c97ccaf39f6..3562698528bd 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -301,6 +301,10 @@ int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level);
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
 enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code);
+int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
+			    bool hflip, bool vflip);
+int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode,
+			    bool hflip, bool vflip);
 
 struct ipu_client_platformdata {
 	int csi;
-- 
cgit v1.2.3


From 4cea940d34319fb5d5e2f4d554e23f766c228e90 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:38 -0700
Subject: gpu: ipu-v3: Add helper function checking if pixfmt is planar

Add simple helper function returning true if passed pixel format is one
of supported planar ones.

Signed-off-by: Dmitry Eremin-Solenikov <dmitry_eremin@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 12 ++++++++++++
 include/video/imx-ipu-v3.h      |  1 +
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index a1d42eed5d06..18563c240f10 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -101,6 +101,18 @@ enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat)
 }
 EXPORT_SYMBOL_GPL(ipu_pixelformat_to_colorspace);
 
+bool ipu_pixelformat_is_planar(u32 pixelformat)
+{
+	switch (pixelformat) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YVU420:
+		return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(ipu_pixelformat_is_planar);
+
 enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code)
 {
 	switch (mbus_code & 0xf000) {
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 3562698528bd..ecb01f843aee 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -301,6 +301,7 @@ int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level);
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
 enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code);
+bool ipu_pixelformat_is_planar(u32 pixelformat);
 int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
 			    bool hflip, bool vflip);
 int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode,
-- 
cgit v1.2.3


From a4cd8f229ff71db0c95c0d96381d4fb9239fdb19 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:39 -0700
Subject: gpu: ipu-v3: Move IDMAC channel names to imx-ipu-v3.h

Move the IDMAC channel names to imx-ipu-v3.h, to make the names
available outside IPU. Add a couple new channels in the process
(async display BG/FG, channels 24 and 29).

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-prv.h | 25 -------------------------
 include/video/imx-ipu-v3.h   | 30 ++++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-prv.h b/drivers/gpu/ipu-v3/ipu-prv.h
index 1596a4f52faf..7f08a461c929 100644
--- a/drivers/gpu/ipu-v3/ipu-prv.h
+++ b/drivers/gpu/ipu-v3/ipu-prv.h
@@ -24,31 +24,6 @@ struct ipu_soc;
 
 #include <video/imx-ipu-v3.h>
 
-#define IPUV3_CHANNEL_CSI0			 0
-#define IPUV3_CHANNEL_CSI1			 1
-#define IPUV3_CHANNEL_CSI2			 2
-#define IPUV3_CHANNEL_CSI3			 3
-#define IPUV3_CHANNEL_VDI_MEM_IC_VF              5
-#define IPUV3_CHANNEL_MEM_IC_PP                 11
-#define IPUV3_CHANNEL_MEM_IC_PRP_VF             12
-#define IPUV3_CHANNEL_G_MEM_IC_PRP_VF           14
-#define IPUV3_CHANNEL_G_MEM_IC_PP               15
-#define IPUV3_CHANNEL_IC_PRP_ENC_MEM            20
-#define IPUV3_CHANNEL_IC_PRP_VF_MEM             21
-#define IPUV3_CHANNEL_IC_PP_MEM                 22
-#define IPUV3_CHANNEL_MEM_BG_SYNC		23
-#define IPUV3_CHANNEL_MEM_FG_SYNC		27
-#define IPUV3_CHANNEL_MEM_DC_SYNC		28
-#define IPUV3_CHANNEL_MEM_FG_SYNC_ALPHA		31
-#define IPUV3_CHANNEL_MEM_DC_ASYNC		41
-#define IPUV3_CHANNEL_MEM_ROT_ENC		45
-#define IPUV3_CHANNEL_MEM_ROT_VF		46
-#define IPUV3_CHANNEL_MEM_ROT_PP		47
-#define IPUV3_CHANNEL_ROT_ENC_MEM		48
-#define IPUV3_CHANNEL_ROT_VF_MEM		49
-#define IPUV3_CHANNEL_ROT_PP_MEM		50
-#define IPUV3_CHANNEL_MEM_BG_SYNC_ALPHA		51
-
 #define IPU_MCU_T_DEFAULT	8
 #define IPU_CM_IDMAC_REG_OFS	0x00008000
 #define IPU_CM_IC_REG_OFS	0x00020000
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index ecb01f843aee..2e9bfe24fb67 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -100,6 +100,36 @@ enum ipu_channel_irq {
 	IPU_IRQ_EOS = 192,
 };
 
+/*
+ * Enumeration of IDMAC channels
+ */
+#define IPUV3_CHANNEL_CSI0			 0
+#define IPUV3_CHANNEL_CSI1			 1
+#define IPUV3_CHANNEL_CSI2			 2
+#define IPUV3_CHANNEL_CSI3			 3
+#define IPUV3_CHANNEL_VDI_MEM_IC_VF		 5
+#define IPUV3_CHANNEL_MEM_IC_PP			11
+#define IPUV3_CHANNEL_MEM_IC_PRP_VF		12
+#define IPUV3_CHANNEL_G_MEM_IC_PRP_VF		14
+#define IPUV3_CHANNEL_G_MEM_IC_PP		15
+#define IPUV3_CHANNEL_IC_PRP_ENC_MEM		20
+#define IPUV3_CHANNEL_IC_PRP_VF_MEM		21
+#define IPUV3_CHANNEL_IC_PP_MEM			22
+#define IPUV3_CHANNEL_MEM_BG_SYNC		23
+#define IPUV3_CHANNEL_MEM_BG_ASYNC		24
+#define IPUV3_CHANNEL_MEM_FG_SYNC		27
+#define IPUV3_CHANNEL_MEM_DC_SYNC		28
+#define IPUV3_CHANNEL_MEM_FG_ASYNC		29
+#define IPUV3_CHANNEL_MEM_FG_SYNC_ALPHA		31
+#define IPUV3_CHANNEL_MEM_DC_ASYNC		41
+#define IPUV3_CHANNEL_MEM_ROT_ENC		45
+#define IPUV3_CHANNEL_MEM_ROT_VF		46
+#define IPUV3_CHANNEL_MEM_ROT_PP		47
+#define IPUV3_CHANNEL_ROT_ENC_MEM		48
+#define IPUV3_CHANNEL_ROT_VF_MEM		49
+#define IPUV3_CHANNEL_ROT_PP_MEM		50
+#define IPUV3_CHANNEL_MEM_BG_SYNC_ALPHA		51
+
 int ipu_map_irq(struct ipu_soc *ipu, int irq);
 int ipu_idmac_channel_irq(struct ipu_soc *ipu, struct ipuv3_channel *channel,
 		enum ipu_channel_irq irq);
-- 
cgit v1.2.3


From aa52f57894b93dcfdd615b35a7579e161f1e7a38 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:40 -0700
Subject: gpu: ipu-v3: Add ipu_idmac_buffer_is_ready()

Add ipu_idmac_buffer_is_ready(), returns true if the given buffer in
the given channel is set ready (owned by IPU), or false if not ready
(owned by CPU core).

Support has been added for third buffer, there is no support yet for
triple-buffering in idmac channels, but this function checks
buffer-ready for third buffer in case this support is added later.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 26 +++++++++++++++++++++++++-
 drivers/gpu/ipu-v3/ipu-prv.h    |  1 +
 include/video/imx-ipu-v3.h      |  1 +
 3 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 18563c240f10..fec72c0d18ba 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -232,7 +232,7 @@ void ipu_idmac_put(struct ipuv3_channel *channel)
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_put);
 
-#define idma_mask(ch)			(1 << (ch & 0x1f))
+#define idma_mask(ch)			(1 << ((ch) & 0x1f))
 
 void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
 		bool doublebuffer)
@@ -315,6 +315,30 @@ int ipu_idmac_get_current_buffer(struct ipuv3_channel *channel)
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_get_current_buffer);
 
+bool ipu_idmac_buffer_is_ready(struct ipuv3_channel *channel, u32 buf_num)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned long flags;
+	u32 reg = 0;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+	switch (buf_num) {
+	case 0:
+		reg = ipu_cm_read(ipu, IPU_CHA_BUF0_RDY(channel->num));
+		break;
+	case 1:
+		reg = ipu_cm_read(ipu, IPU_CHA_BUF1_RDY(channel->num));
+		break;
+	case 2:
+		reg = ipu_cm_read(ipu, IPU_CHA_BUF2_RDY(channel->num));
+		break;
+	}
+	spin_unlock_irqrestore(&ipu->lock, flags);
+
+	return ((reg & idma_mask(channel->num)) != 0);
+}
+EXPORT_SYMBOL_GPL(ipu_idmac_buffer_is_ready);
+
 void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num)
 {
 	struct ipu_soc *ipu = channel->ipu;
diff --git a/drivers/gpu/ipu-v3/ipu-prv.h b/drivers/gpu/ipu-v3/ipu-prv.h
index 7f08a461c929..bfb1e8a4483f 100644
--- a/drivers/gpu/ipu-v3/ipu-prv.h
+++ b/drivers/gpu/ipu-v3/ipu-prv.h
@@ -68,6 +68,7 @@ struct ipu_soc;
 #define IPU_DISP_TASK_STAT		IPU_CM_REG(0x0254)
 #define IPU_CHA_BUF0_RDY(ch)		IPU_CM_REG(0x0268 + 4 * ((ch) / 32))
 #define IPU_CHA_BUF1_RDY(ch)		IPU_CM_REG(0x0270 + 4 * ((ch) / 32))
+#define IPU_CHA_BUF2_RDY(ch)		IPU_CM_REG(0x0288 + 4 * ((ch) / 32))
 #define IPU_ALT_CHA_BUF0_RDY(ch)	IPU_CM_REG(0x0278 + 4 * ((ch) / 32))
 #define IPU_ALT_CHA_BUF1_RDY(ch)	IPU_CM_REG(0x0280 + 4 * ((ch) / 32))
 
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 2e9bfe24fb67..10013378394e 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -165,6 +165,7 @@ int ipu_idmac_wait_busy(struct ipuv3_channel *channel, int ms);
 void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
 		bool doublebuffer);
 int ipu_idmac_get_current_buffer(struct ipuv3_channel *channel);
+bool ipu_idmac_buffer_is_ready(struct ipuv3_channel *channel, u32 buf_num);
 void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num);
 
 /*
-- 
cgit v1.2.3


From bce6f087a958a21500c51a9e63a5f578f5b0510c Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:41 -0700
Subject: gpu: ipu-v3: Add ipu_idmac_clear_buffer()

Add the reverse of ipu_idmac_select_buffer(), that is, clear a buffer
ready status in a channel.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 28 ++++++++++++++++++++++++++++
 include/video/imx-ipu-v3.h      |  1 +
 2 files changed, 29 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index fec72c0d18ba..773a2fc8fed4 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -357,6 +357,34 @@ void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num)
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_select_buffer);
 
+void ipu_idmac_clear_buffer(struct ipuv3_channel *channel, u32 buf_num)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned int chno = channel->num;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	ipu_cm_write(ipu, 0xF0300000, IPU_GPR); /* write one to clear */
+	switch (buf_num) {
+	case 0:
+		ipu_cm_write(ipu, idma_mask(chno), IPU_CHA_BUF0_RDY(chno));
+		break;
+	case 1:
+		ipu_cm_write(ipu, idma_mask(chno), IPU_CHA_BUF1_RDY(chno));
+		break;
+	case 2:
+		ipu_cm_write(ipu, idma_mask(chno), IPU_CHA_BUF2_RDY(chno));
+		break;
+	default:
+		break;
+	}
+	ipu_cm_write(ipu, 0x0, IPU_GPR); /* write one to set */
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_idmac_clear_buffer);
+
 int ipu_idmac_enable_channel(struct ipuv3_channel *channel)
 {
 	struct ipu_soc *ipu = channel->ipu;
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 10013378394e..ae44eb067f5b 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -167,6 +167,7 @@ void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
 int ipu_idmac_get_current_buffer(struct ipuv3_channel *channel);
 bool ipu_idmac_buffer_is_ready(struct ipuv3_channel *channel, u32 buf_num);
 void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num);
+void ipu_idmac_clear_buffer(struct ipuv3_channel *channel, u32 buf_num);
 
 /*
  * IPU Channel Parameter Memory (cpmem) functions
-- 
cgit v1.2.3


From 6930afdccfd2b3e6669c305d97958d81cf0d072e Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:43 -0700
Subject: gpu: ipu-v3: Add ipu_stride_to_bytes()

Adds ipu_stride_to_bytes(), which converts a pixel stride to bytes,
suitable for passing to cpmem.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 30 ++++++++++++++++++++++++++++++
 include/video/imx-ipu-v3.h      |  1 +
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 985a7508af3a..e542d5e8a9e1 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -126,6 +126,36 @@ enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code)
 }
 EXPORT_SYMBOL_GPL(ipu_mbus_code_to_colorspace);
 
+int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat)
+{
+	switch (pixelformat) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YVU420:
+		/*
+		 * for the planar YUV formats, the stride passed to
+		 * cpmem must be the stride in bytes of the Y plane.
+		 * And all the planar YUV formats have an 8-bit
+		 * Y component.
+		 */
+		return (8 * pixel_stride) >> 3;
+	case V4L2_PIX_FMT_RGB565:
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_UYVY:
+		return (16 * pixel_stride) >> 3;
+	case V4L2_PIX_FMT_BGR24:
+	case V4L2_PIX_FMT_RGB24:
+		return (24 * pixel_stride) >> 3;
+	case V4L2_PIX_FMT_BGR32:
+	case V4L2_PIX_FMT_RGB32:
+		return (32 * pixel_stride) >> 3;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(ipu_stride_to_bytes);
+
 int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
 			    bool hflip, bool vflip)
 {
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index ae44eb067f5b..f24ef9a1dc48 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -333,6 +333,7 @@ int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level);
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
 enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code);
+int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat);
 bool ipu_pixelformat_is_planar(u32 pixelformat);
 int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
 			    bool hflip, bool vflip);
-- 
cgit v1.2.3


From 2bcf577eb6361827f8347529803528031033cb83 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:44 -0700
Subject: gpu: ipu-v3: Add ipu_idmac_enable_watermark()

Adds the function ipu_idmac_enable_watermark(), which enables or disables
watermarking in the IDMAC channel. Enabling watermarking can increase a
channel's AXI bus arbitration priority.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 25 +++++++++++++++++++++++++
 include/video/imx-ipu-v3.h      |  1 +
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index e542d5e8a9e1..0a02465ba102 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -536,6 +536,31 @@ int ipu_idmac_disable_channel(struct ipuv3_channel *channel)
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_disable_channel);
 
+/*
+ * The imx6 rev. D TRM says that enabling the WM feature will increase
+ * a channel's priority. Refer to Table 36-8 Calculated priority value.
+ * The sub-module that is the sink or source for the channel must enable
+ * watermark signal for this to take effect (SMFC_WM for instance).
+ */
+void ipu_idmac_enable_watermark(struct ipuv3_channel *channel, bool enable)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	val = ipu_idmac_read(ipu, IDMAC_WM_EN(channel->num));
+	if (enable)
+		val |= 1 << (channel->num % 32);
+	else
+		val &= ~(1 << (channel->num % 32));
+	ipu_idmac_write(ipu, val, IDMAC_WM_EN(channel->num));
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_idmac_enable_watermark);
+
 static int ipu_memory_reset(struct ipu_soc *ipu)
 {
 	unsigned long timeout;
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index f24ef9a1dc48..d0cce6e4bcf5 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -160,6 +160,7 @@ void ipu_idmac_put(struct ipuv3_channel *);
 
 int ipu_idmac_enable_channel(struct ipuv3_channel *channel);
 int ipu_idmac_disable_channel(struct ipuv3_channel *channel);
+void ipu_idmac_enable_watermark(struct ipuv3_channel *channel, bool enable);
 int ipu_idmac_wait_busy(struct ipuv3_channel *channel, int ms);
 
 void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
-- 
cgit v1.2.3


From 4fd1a07af59bf5e1cfb73f7035bf525522cebc76 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:45 -0700
Subject: gpu: ipu-v3: Add ipu_idmac_lock_enable()

Adds ipu_idmac_lock_enable(), which enables or disables channel
burst locking.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 69 +++++++++++++++++++++++++++++++++++++++++
 include/video/imx-ipu-v3.h      |  1 +
 2 files changed, 70 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 0a02465ba102..28be7415a198 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -305,6 +305,75 @@ void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_set_double_buffer);
 
+static const struct {
+	int chnum;
+	u32 reg;
+	int shift;
+} idmac_lock_en_info[] = {
+	{ .chnum =  5, .reg = IDMAC_CH_LOCK_EN_1, .shift =  0, },
+	{ .chnum = 11, .reg = IDMAC_CH_LOCK_EN_1, .shift =  2, },
+	{ .chnum = 12, .reg = IDMAC_CH_LOCK_EN_1, .shift =  4, },
+	{ .chnum = 14, .reg = IDMAC_CH_LOCK_EN_1, .shift =  6, },
+	{ .chnum = 15, .reg = IDMAC_CH_LOCK_EN_1, .shift =  8, },
+	{ .chnum = 20, .reg = IDMAC_CH_LOCK_EN_1, .shift = 10, },
+	{ .chnum = 21, .reg = IDMAC_CH_LOCK_EN_1, .shift = 12, },
+	{ .chnum = 22, .reg = IDMAC_CH_LOCK_EN_1, .shift = 14, },
+	{ .chnum = 23, .reg = IDMAC_CH_LOCK_EN_1, .shift = 16, },
+	{ .chnum = 27, .reg = IDMAC_CH_LOCK_EN_1, .shift = 18, },
+	{ .chnum = 28, .reg = IDMAC_CH_LOCK_EN_1, .shift = 20, },
+	{ .chnum = 45, .reg = IDMAC_CH_LOCK_EN_2, .shift =  0, },
+	{ .chnum = 46, .reg = IDMAC_CH_LOCK_EN_2, .shift =  2, },
+	{ .chnum = 47, .reg = IDMAC_CH_LOCK_EN_2, .shift =  4, },
+	{ .chnum = 48, .reg = IDMAC_CH_LOCK_EN_2, .shift =  6, },
+	{ .chnum = 49, .reg = IDMAC_CH_LOCK_EN_2, .shift =  8, },
+	{ .chnum = 50, .reg = IDMAC_CH_LOCK_EN_2, .shift = 10, },
+};
+
+int ipu_idmac_lock_enable(struct ipuv3_channel *channel, int num_bursts)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned long flags;
+	u32 bursts, regval;
+	int i;
+
+	switch (num_bursts) {
+	case 0:
+	case 1:
+		bursts = 0x00; /* locking disabled */
+		break;
+	case 2:
+		bursts = 0x01;
+		break;
+	case 4:
+		bursts = 0x02;
+		break;
+	case 8:
+		bursts = 0x03;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(idmac_lock_en_info); i++) {
+		if (channel->num == idmac_lock_en_info[i].chnum)
+			break;
+	}
+	if (i >= ARRAY_SIZE(idmac_lock_en_info))
+		return -EINVAL;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	regval = ipu_idmac_read(ipu, idmac_lock_en_info[i].reg);
+	regval &= ~(0x03 << idmac_lock_en_info[i].shift);
+	regval |= (bursts << idmac_lock_en_info[i].shift);
+	ipu_idmac_write(ipu, regval, idmac_lock_en_info[i].reg);
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_idmac_lock_enable);
+
 int ipu_module_enable(struct ipu_soc *ipu, u32 mask)
 {
 	unsigned long lock_flags;
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index d0cce6e4bcf5..b106c9b8b3e9 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -161,6 +161,7 @@ void ipu_idmac_put(struct ipuv3_channel *);
 int ipu_idmac_enable_channel(struct ipuv3_channel *channel);
 int ipu_idmac_disable_channel(struct ipuv3_channel *channel);
 void ipu_idmac_enable_watermark(struct ipuv3_channel *channel, bool enable);
+int ipu_idmac_lock_enable(struct ipuv3_channel *channel, int num_bursts);
 int ipu_idmac_wait_busy(struct ipuv3_channel *channel, int ms);
 
 void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
-- 
cgit v1.2.3


From 9b9da0be37490c77e92a2101a8c5d469ce1102f4 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:49 -0700
Subject: gpu: ipu-cpmem: Add ipu_cpmem_set_block_mode()

Adds ipu_cpmem_set_block_mode().

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-cpmem.c | 6 ++++++
 include/video/imx-ipu-v3.h     | 1 +
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 7adfa78a48bc..28adf39e4041 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -260,6 +260,12 @@ void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize)
 };
 EXPORT_SYMBOL_GPL(ipu_cpmem_set_burstsize);
 
+void ipu_cpmem_set_block_mode(struct ipuv3_channel *ch)
+{
+	ipu_ch_param_write_field(ch, IPU_FIELD_BM, 1);
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_block_mode);
+
 int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
 			     const struct ipu_rgb *rgb)
 {
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index b106c9b8b3e9..d2cc207985d8 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -195,6 +195,7 @@ void ipu_cpmem_set_high_priority(struct ipuv3_channel *ch);
 void ipu_cpmem_set_buffer(struct ipuv3_channel *ch, int bufnum, dma_addr_t buf);
 void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride);
 void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize);
+void ipu_cpmem_set_block_mode(struct ipuv3_channel *ch);
 int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
 			     const struct ipu_rgb *rgb);
 int ipu_cpmem_set_format_passthrough(struct ipuv3_channel *ch, int width);
-- 
cgit v1.2.3


From 555f0e6690a41245518003c02a1ecb84e4a69281 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:50 -0700
Subject: gpu: ipu-cpmem: Add ipu_cpmem_set_axi_id()

Adds ipu_cpmem_set_axi_id() to set which AXI bus master the channel
will use to transfer data onto AXI bus.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-cpmem.c | 7 +++++++
 include/video/imx-ipu-v3.h     | 1 +
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 28adf39e4041..2d1b3761f14c 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -254,6 +254,13 @@ void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride)
 };
 EXPORT_SYMBOL_GPL(ipu_cpmem_interlaced_scan);
 
+void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id)
+{
+	id &= 0x3;
+	ipu_ch_param_write_field(ch, IPU_FIELD_ID, id);
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_axi_id);
+
 void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize)
 {
 	ipu_ch_param_write_field(ch, IPU_FIELD_NPB, burstsize - 1);
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index d2cc207985d8..f30c06871db7 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -194,6 +194,7 @@ void ipu_cpmem_set_stride(struct ipuv3_channel *ch, int stride);
 void ipu_cpmem_set_high_priority(struct ipuv3_channel *ch);
 void ipu_cpmem_set_buffer(struct ipuv3_channel *ch, int bufnum, dma_addr_t buf);
 void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride);
+void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id);
 void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize);
 void ipu_cpmem_set_block_mode(struct ipuv3_channel *ch);
 int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
-- 
cgit v1.2.3


From c42d37ca421aa222e8f27744d4129bce726a3724 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:51 -0700
Subject: gpu: ipu-cpmem: Add ipu_cpmem_set_rotation()

Adds ipu_cpmem_set_rotation().

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-cpmem.c | 10 ++++++++++
 include/video/imx-ipu-v3.h     |  2 ++
 2 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 2d1b3761f14c..f52e4b4e172f 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -64,6 +64,7 @@ struct ipu_cpmem {
 #define IPU_FIELD_BNDM		IPU_CPMEM_WORD(0, 114, 3)
 #define IPU_FIELD_BM		IPU_CPMEM_WORD(0, 117, 2)
 #define IPU_FIELD_ROT		IPU_CPMEM_WORD(0, 119, 1)
+#define IPU_FIELD_ROT_HF_VF	IPU_CPMEM_WORD(0, 119, 3)
 #define IPU_FIELD_HF		IPU_CPMEM_WORD(0, 120, 1)
 #define IPU_FIELD_VF		IPU_CPMEM_WORD(0, 121, 1)
 #define IPU_FIELD_THE		IPU_CPMEM_WORD(0, 122, 1)
@@ -273,6 +274,15 @@ void ipu_cpmem_set_block_mode(struct ipuv3_channel *ch)
 }
 EXPORT_SYMBOL_GPL(ipu_cpmem_set_block_mode);
 
+void ipu_cpmem_set_rotation(struct ipuv3_channel *ch,
+			    enum ipu_rotate_mode rot)
+{
+	u32 temp_rot = bitrev8(rot) >> 5;
+
+	ipu_ch_param_write_field(ch, IPU_FIELD_ROT_HF_VF, temp_rot);
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_rotation);
+
 int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
 			     const struct ipu_rgb *rgb)
 {
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index f30c06871db7..699e0d8d135b 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -197,6 +197,8 @@ void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride);
 void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id);
 void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize);
 void ipu_cpmem_set_block_mode(struct ipuv3_channel *ch);
+void ipu_cpmem_set_rotation(struct ipuv3_channel *ch,
+			    enum ipu_rotate_mode rot);
 int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
 			     const struct ipu_rgb *rgb);
 int ipu_cpmem_set_format_passthrough(struct ipuv3_channel *ch, int width);
-- 
cgit v1.2.3


From 2094b603ae59be6785e52a00d09b47b6ae910154 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:52 -0700
Subject: gpu: ipu-cpmem: Add second buffer support to ipu_cpmem_set_image()

Add a second buffer physaddr to struct ipu_image, for double-buffering
support.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-cpmem.c | 32 ++++++++++++++++----------------
 include/video/imx-ipu-v3.h     |  3 ++-
 2 files changed, 18 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index f52e4b4e172f..cfe2f53f2c17 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -538,7 +538,7 @@ EXPORT_SYMBOL_GPL(ipu_cpmem_set_fmt);
 int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image)
 {
 	struct v4l2_pix_format *pix = &image->pix;
-	int y_offset, u_offset, v_offset;
+	int offset, y_offset, u_offset, v_offset;
 
 	pr_debug("%s: resolution: %dx%d stride: %d\n",
 		 __func__, pix->width, pix->height,
@@ -560,30 +560,30 @@ int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image)
 
 		ipu_cpmem_set_yuv_planar_full(ch, pix->pixelformat,
 				pix->bytesperline, u_offset, v_offset);
-		ipu_cpmem_set_buffer(ch, 0, image->phys + y_offset);
+		ipu_cpmem_set_buffer(ch, 0, image->phys0 + y_offset);
+		ipu_cpmem_set_buffer(ch, 1, image->phys1 + y_offset);
 		break;
 	case V4L2_PIX_FMT_UYVY:
 	case V4L2_PIX_FMT_YUYV:
-		ipu_cpmem_set_buffer(ch, 0, image->phys +
-				     image->rect.left * 2 +
-				     image->rect.top * image->pix.bytesperline);
+	case V4L2_PIX_FMT_RGB565:
+		offset = image->rect.left * 2 +
+			image->rect.top * pix->bytesperline;
+		ipu_cpmem_set_buffer(ch, 0, image->phys0 + offset);
+		ipu_cpmem_set_buffer(ch, 1, image->phys1 + offset);
 		break;
 	case V4L2_PIX_FMT_RGB32:
 	case V4L2_PIX_FMT_BGR32:
-		ipu_cpmem_set_buffer(ch, 0, image->phys +
-				     image->rect.left * 4 +
-				     image->rect.top * image->pix.bytesperline);
-		break;
-	case V4L2_PIX_FMT_RGB565:
-		ipu_cpmem_set_buffer(ch, 0, image->phys +
-				     image->rect.left * 2 +
-				     image->rect.top * image->pix.bytesperline);
+		offset = image->rect.left * 4 +
+			image->rect.top * pix->bytesperline;
+		ipu_cpmem_set_buffer(ch, 0, image->phys0 + offset);
+		ipu_cpmem_set_buffer(ch, 1, image->phys1 + offset);
 		break;
 	case V4L2_PIX_FMT_RGB24:
 	case V4L2_PIX_FMT_BGR24:
-		ipu_cpmem_set_buffer(ch, 0, image->phys +
-				     image->rect.left * 3 +
-				     image->rect.top * image->pix.bytesperline);
+		offset = image->rect.left * 3 +
+			image->rect.top * pix->bytesperline;
+		ipu_cpmem_set_buffer(ch, 0, image->phys0 + offset);
+		ipu_cpmem_set_buffer(ch, 1, image->phys1 + offset);
 		break;
 	default:
 		return -EINVAL;
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 699e0d8d135b..b519664c101e 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -185,7 +185,8 @@ struct ipu_rgb {
 struct ipu_image {
 	struct v4l2_pix_format pix;
 	struct v4l2_rect rect;
-	dma_addr_t phys;
+	dma_addr_t phys0;
+	dma_addr_t phys1;
 };
 
 void ipu_cpmem_zero(struct ipuv3_channel *ch);
-- 
cgit v1.2.3


From 60c04456f68f67f68180ebd84a47e4c58931f70f Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:54 -0700
Subject: gpu: ipu-cpmem: Add ipu_cpmem_dump()

Adds ipu_cpmem_dump() which dumps a channel's cpmem to debug.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-cpmem.c | 63 ++++++++++++++++++++++++++++++++++++++++++
 include/video/imx-ipu-v3.h     |  1 +
 2 files changed, 64 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index c55f3620e84a..3bf05bc4ab67 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -674,6 +674,69 @@ int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image)
 }
 EXPORT_SYMBOL_GPL(ipu_cpmem_set_image);
 
+void ipu_cpmem_dump(struct ipuv3_channel *ch)
+{
+	struct ipu_ch_param __iomem *p = ipu_get_cpmem(ch);
+	struct ipu_soc *ipu = ch->ipu;
+	int chno = ch->num;
+
+	dev_dbg(ipu->dev, "ch %d word 0 - %08X %08X %08X %08X %08X\n", chno,
+		readl(&p->word[0].data[0]),
+		readl(&p->word[0].data[1]),
+		readl(&p->word[0].data[2]),
+		readl(&p->word[0].data[3]),
+		readl(&p->word[0].data[4]));
+	dev_dbg(ipu->dev, "ch %d word 1 - %08X %08X %08X %08X %08X\n", chno,
+		readl(&p->word[1].data[0]),
+		readl(&p->word[1].data[1]),
+		readl(&p->word[1].data[2]),
+		readl(&p->word[1].data[3]),
+		readl(&p->word[1].data[4]));
+	dev_dbg(ipu->dev, "PFS 0x%x, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_PFS));
+	dev_dbg(ipu->dev, "BPP 0x%x, ",
+		ipu_ch_param_read_field(ch, IPU_FIELD_BPP));
+	dev_dbg(ipu->dev, "NPB 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_NPB));
+
+	dev_dbg(ipu->dev, "FW %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_FW));
+	dev_dbg(ipu->dev, "FH %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_FH));
+	dev_dbg(ipu->dev, "EBA0 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_EBA0) << 3);
+	dev_dbg(ipu->dev, "EBA1 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_EBA1) << 3);
+	dev_dbg(ipu->dev, "Stride %d\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_SL));
+	dev_dbg(ipu->dev, "scan_order %d\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_SO));
+	dev_dbg(ipu->dev, "uv_stride %d\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_SLUV));
+	dev_dbg(ipu->dev, "u_offset 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_UBO) << 3);
+	dev_dbg(ipu->dev, "v_offset 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_VBO) << 3);
+
+	dev_dbg(ipu->dev, "Width0 %d+1, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_WID0));
+	dev_dbg(ipu->dev, "Width1 %d+1, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_WID1));
+	dev_dbg(ipu->dev, "Width2 %d+1, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_WID2));
+	dev_dbg(ipu->dev, "Width3 %d+1, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_WID3));
+	dev_dbg(ipu->dev, "Offset0 %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_OFS0));
+	dev_dbg(ipu->dev, "Offset1 %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_OFS1));
+	dev_dbg(ipu->dev, "Offset2 %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_OFS2));
+	dev_dbg(ipu->dev, "Offset3 %d\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_OFS3));
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_dump);
+
 int ipu_cpmem_init(struct ipu_soc *ipu, struct device *dev, unsigned long base)
 {
 	struct ipu_cpmem *cpmem;
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index b519664c101e..b41c17d5afc3 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -211,6 +211,7 @@ void ipu_cpmem_set_yuv_planar(struct ipuv3_channel *ch,
 			      u32 pixel_format, int stride, int height);
 int ipu_cpmem_set_fmt(struct ipuv3_channel *ch, u32 drm_fourcc);
 int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image);
+void ipu_cpmem_dump(struct ipuv3_channel *ch);
 
 /*
  * IPU Display Controller (dc) functions
-- 
cgit v1.2.3


From 3feb049f378da6aa1209e05ef5c656a1f26a9183 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 25 Jun 2014 18:05:55 -0700
Subject: gpu: ipu-v3: Add ipu_dump()

Adds ipu_dump() which dumps IPU register state to debug.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 38 ++++++++++++++++++++++++++++++++++++++
 include/video/imx-ipu-v3.h      |  1 +
 2 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 5c3d5269056e..df65d2bca522 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -1145,6 +1145,44 @@ static void ipu_irq_exit(struct ipu_soc *ipu)
 	irq_domain_remove(ipu->domain);
 }
 
+void ipu_dump(struct ipu_soc *ipu)
+{
+	int i;
+
+	dev_dbg(ipu->dev, "IPU_CONF = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_CONF));
+	dev_dbg(ipu->dev, "IDMAC_CONF = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CONF));
+	dev_dbg(ipu->dev, "IDMAC_CHA_EN1 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CHA_EN(0)));
+	dev_dbg(ipu->dev, "IDMAC_CHA_EN2 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CHA_EN(32)));
+	dev_dbg(ipu->dev, "IDMAC_CHA_PRI1 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CHA_PRI(0)));
+	dev_dbg(ipu->dev, "IDMAC_CHA_PRI2 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CHA_PRI(32)));
+	dev_dbg(ipu->dev, "IDMAC_BAND_EN1 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_BAND_EN(0)));
+	dev_dbg(ipu->dev, "IDMAC_BAND_EN2 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_BAND_EN(32)));
+	dev_dbg(ipu->dev, "IPU_CHA_DB_MODE_SEL0 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_CHA_DB_MODE_SEL(0)));
+	dev_dbg(ipu->dev, "IPU_CHA_DB_MODE_SEL1 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_CHA_DB_MODE_SEL(32)));
+	dev_dbg(ipu->dev, "IPU_FS_PROC_FLOW1 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_FS_PROC_FLOW1));
+	dev_dbg(ipu->dev, "IPU_FS_PROC_FLOW2 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_FS_PROC_FLOW2));
+	dev_dbg(ipu->dev, "IPU_FS_PROC_FLOW3 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_FS_PROC_FLOW3));
+	dev_dbg(ipu->dev, "IPU_FS_DISP_FLOW1 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_FS_DISP_FLOW1));
+	for (i = 0; i < 15; i++)
+		dev_dbg(ipu->dev, "IPU_INT_CTRL(%d) = \t%08X\n", i,
+			ipu_cm_read(ipu, IPU_INT_CTRL(i)));
+}
+EXPORT_SYMBOL_GPL(ipu_dump);
+
 static int ipu_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id =
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index b41c17d5afc3..c74bf4a0520e 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -151,6 +151,7 @@ int ipu_idmac_channel_irq(struct ipu_soc *ipu, struct ipuv3_channel *channel,
  */
 void ipu_set_csi_src_mux(struct ipu_soc *ipu, int csi_id, bool mipi_csi2);
 void ipu_set_ic_src_mux(struct ipu_soc *ipu, int csi_id, bool vdi);
+void ipu_dump(struct ipu_soc *ipu);
 
 /*
  * IPU Image DMA Controller (idmac) functions
-- 
cgit v1.2.3


From fbff66108352d19b5cffa7dce26d7638c9dd4d70 Mon Sep 17 00:00:00 2001
From: Mark Rustad <mark.d.rustad@intel.com>
Date: Thu, 28 Aug 2014 04:43:09 -0700
Subject: security: Silence shadow warning

Renaming an unused formal parameter in the static inline function
security_inode_init_security eliminates many W=2 warnings.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>
---
 include/linux/security.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index 623f90e5f38d..3b3aeb1b74cb 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -2108,7 +2108,7 @@ static inline int security_dentry_init_security(struct dentry *dentry,
 static inline int security_inode_init_security(struct inode *inode,
 						struct inode *dir,
 						const struct qstr *qstr,
-						const initxattrs initxattrs,
+						const initxattrs xattrs,
 						void *fs_data)
 {
 	return 0;
-- 
cgit v1.2.3


From ea2fdf842365066c82ab941086c6a1741ced4f2a Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Date: Thu, 28 Aug 2014 13:58:53 +0200
Subject: usb: phy: samsung: remove old common USB PHY code

drivers/usb/phy/phy-samsung-usb[2,3] drivers got replaced by
drivers/phy/phy-samsung-usb[2,3] ones and the old common Samsung
USB PHY code is no longer used.

Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
Reviewed-by: Vivek Gautam <gautam.vivek@samsung.com>
Reviewed-by: Jingoo Han <jg1.han@samsung.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
Cc: Kamil Debski <k.debski@samsung.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/phy/phy-samsung-usb.c            | 241 --------------------
 drivers/usb/phy/phy-samsung-usb.h            | 317 ---------------------------
 include/linux/platform_data/samsung-usbphy.h |  27 ---
 3 files changed, 585 deletions(-)
 delete mode 100644 drivers/usb/phy/phy-samsung-usb.c
 delete mode 100644 drivers/usb/phy/phy-samsung-usb.h
 delete mode 100644 include/linux/platform_data/samsung-usbphy.h

(limited to 'include')

diff --git a/drivers/usb/phy/phy-samsung-usb.c b/drivers/usb/phy/phy-samsung-usb.c
deleted file mode 100644
index ac025ca08425..000000000000
--- a/drivers/usb/phy/phy-samsung-usb.c
+++ /dev/null
@@ -1,241 +0,0 @@
-/* linux/drivers/usb/phy/phy-samsung-usb.c
- *
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- *              http://www.samsung.com
- *
- * Author: Praveen Paneri <p.paneri@samsung.com>
- *
- * Samsung USB-PHY helper driver with common function calls;
- * interacts with Samsung USB 2.0 PHY controller driver and later
- * with Samsung USB 3.0 PHY driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/clk.h>
-#include <linux/device.h>
-#include <linux/err.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/usb/samsung_usb_phy.h>
-
-#include "phy-samsung-usb.h"
-
-int samsung_usbphy_parse_dt(struct samsung_usbphy *sphy)
-{
-	struct device_node *usbphy_sys;
-
-	/* Getting node for system controller interface for usb-phy */
-	usbphy_sys = of_get_child_by_name(sphy->dev->of_node, "usbphy-sys");
-	if (!usbphy_sys) {
-		dev_err(sphy->dev, "No sys-controller interface for usb-phy\n");
-		return -ENODEV;
-	}
-
-	sphy->pmuregs = of_iomap(usbphy_sys, 0);
-
-	if (sphy->pmuregs == NULL) {
-		dev_err(sphy->dev, "Can't get usb-phy pmu control register\n");
-		goto err0;
-	}
-
-	sphy->sysreg = of_iomap(usbphy_sys, 1);
-
-	/*
-	 * Not returning error code here, since this situation is not fatal.
-	 * Few SoCs may not have this switch available
-	 */
-	if (sphy->sysreg == NULL)
-		dev_warn(sphy->dev, "Can't get usb-phy sysreg cfg register\n");
-
-	of_node_put(usbphy_sys);
-
-	return 0;
-
-err0:
-	of_node_put(usbphy_sys);
-	return -ENXIO;
-}
-EXPORT_SYMBOL_GPL(samsung_usbphy_parse_dt);
-
-/*
- * Set isolation here for phy.
- * Here 'on = true' would mean USB PHY block is isolated, hence
- * de-activated and vice-versa.
- */
-void samsung_usbphy_set_isolation_4210(struct samsung_usbphy *sphy, bool on)
-{
-	void __iomem *reg = NULL;
-	u32 reg_val;
-	u32 en_mask = 0;
-
-	if (!sphy->pmuregs) {
-		dev_warn(sphy->dev, "Can't set pmu isolation\n");
-		return;
-	}
-
-	if (sphy->phy_type == USB_PHY_TYPE_DEVICE) {
-		reg = sphy->pmuregs + sphy->drv_data->devphy_reg_offset;
-		en_mask = sphy->drv_data->devphy_en_mask;
-	} else if (sphy->phy_type == USB_PHY_TYPE_HOST) {
-		reg = sphy->pmuregs + sphy->drv_data->hostphy_reg_offset;
-		en_mask = sphy->drv_data->hostphy_en_mask;
-	}
-
-	reg_val = readl(reg);
-
-	if (on)
-		reg_val &= ~en_mask;
-	else
-		reg_val |= en_mask;
-
-	writel(reg_val, reg);
-
-	if (sphy->drv_data->cpu_type == TYPE_EXYNOS4X12) {
-		writel(reg_val, sphy->pmuregs + EXYNOS4X12_PHY_HSIC_CTRL0);
-		writel(reg_val, sphy->pmuregs + EXYNOS4X12_PHY_HSIC_CTRL1);
-	}
-}
-EXPORT_SYMBOL_GPL(samsung_usbphy_set_isolation_4210);
-
-/*
- * Configure the mode of working of usb-phy here: HOST/DEVICE.
- */
-void samsung_usbphy_cfg_sel(struct samsung_usbphy *sphy)
-{
-	u32 reg;
-
-	if (!sphy->sysreg) {
-		dev_warn(sphy->dev, "Can't configure specified phy mode\n");
-		return;
-	}
-
-	reg = readl(sphy->sysreg);
-
-	if (sphy->phy_type == USB_PHY_TYPE_DEVICE)
-		reg &= ~EXYNOS_USB20PHY_CFG_HOST_LINK;
-	else if (sphy->phy_type == USB_PHY_TYPE_HOST)
-		reg |= EXYNOS_USB20PHY_CFG_HOST_LINK;
-
-	writel(reg, sphy->sysreg);
-}
-EXPORT_SYMBOL_GPL(samsung_usbphy_cfg_sel);
-
-/*
- * PHYs are different for USB Device and USB Host.
- * This make sure that correct PHY type is selected before
- * any operation on PHY.
- */
-int samsung_usbphy_set_type(struct usb_phy *phy,
-				enum samsung_usb_phy_type phy_type)
-{
-	struct samsung_usbphy *sphy = phy_to_sphy(phy);
-
-	sphy->phy_type = phy_type;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(samsung_usbphy_set_type);
-
-int samsung_usbphy_rate_to_clksel_64xx(struct samsung_usbphy *sphy,
-							unsigned long rate)
-{
-	unsigned int clksel;
-
-	switch (rate) {
-	case 12 * MHZ:
-		clksel = PHYCLK_CLKSEL_12M;
-		break;
-	case 24 * MHZ:
-		clksel = PHYCLK_CLKSEL_24M;
-		break;
-	case 48 * MHZ:
-		clksel = PHYCLK_CLKSEL_48M;
-		break;
-	default:
-		dev_err(sphy->dev,
-			"Invalid reference clock frequency: %lu\n", rate);
-		return -EINVAL;
-	}
-
-	return clksel;
-}
-EXPORT_SYMBOL_GPL(samsung_usbphy_rate_to_clksel_64xx);
-
-int samsung_usbphy_rate_to_clksel_4x12(struct samsung_usbphy *sphy,
-							unsigned long rate)
-{
-	unsigned int clksel;
-
-	switch (rate) {
-	case 9600 * KHZ:
-		clksel = FSEL_CLKSEL_9600K;
-		break;
-	case 10 * MHZ:
-		clksel = FSEL_CLKSEL_10M;
-		break;
-	case 12 * MHZ:
-		clksel = FSEL_CLKSEL_12M;
-		break;
-	case 19200 * KHZ:
-		clksel = FSEL_CLKSEL_19200K;
-		break;
-	case 20 * MHZ:
-		clksel = FSEL_CLKSEL_20M;
-		break;
-	case 24 * MHZ:
-		clksel = FSEL_CLKSEL_24M;
-		break;
-	case 50 * MHZ:
-		clksel = FSEL_CLKSEL_50M;
-		break;
-	default:
-		dev_err(sphy->dev,
-			"Invalid reference clock frequency: %lu\n", rate);
-		return -EINVAL;
-	}
-
-	return clksel;
-}
-EXPORT_SYMBOL_GPL(samsung_usbphy_rate_to_clksel_4x12);
-
-/*
- * Returns reference clock frequency selection value
- */
-int samsung_usbphy_get_refclk_freq(struct samsung_usbphy *sphy)
-{
-	struct clk *ref_clk;
-	unsigned long rate;
-	int refclk_freq;
-
-	/*
-	 * In exynos5250 USB host and device PHY use
-	 * external crystal clock XXTI
-	 */
-	if (sphy->drv_data->cpu_type == TYPE_EXYNOS5250)
-		ref_clk = clk_get(sphy->dev, "ext_xtal");
-	else
-		ref_clk = clk_get(sphy->dev, "xusbxti");
-	if (IS_ERR(ref_clk)) {
-		dev_err(sphy->dev, "Failed to get reference clock\n");
-		return PTR_ERR(ref_clk);
-	}
-
-	rate = clk_get_rate(ref_clk);
-	refclk_freq = sphy->drv_data->rate_to_clksel(sphy, rate);
-
-	clk_put(ref_clk);
-
-	return refclk_freq;
-}
-EXPORT_SYMBOL_GPL(samsung_usbphy_get_refclk_freq);
diff --git a/drivers/usb/phy/phy-samsung-usb.h b/drivers/usb/phy/phy-samsung-usb.h
deleted file mode 100644
index 4eef45555971..000000000000
--- a/drivers/usb/phy/phy-samsung-usb.h
+++ /dev/null
@@ -1,317 +0,0 @@
-/* linux/drivers/usb/phy/phy-samsung-usb.h
- *
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- *              http://www.samsung.com
- *
- * Samsung USB-PHY transceiver; talks to S3C HS OTG controller, EHCI-S5P and
- * OHCI-EXYNOS controllers.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/usb/phy.h>
-
-/* Register definitions */
-
-#define SAMSUNG_PHYPWR				(0x00)
-#define PHYPWR_NORMAL_MASK			(0x19 << 0)
-#define PHYPWR_OTG_DISABLE			(0x1 << 4)
-#define PHYPWR_ANALOG_POWERDOWN			(0x1 << 3)
-#define PHYPWR_FORCE_SUSPEND			(0x1 << 1)
-/* For Exynos4 */
-#define PHYPWR_NORMAL_MASK_PHY0			(0x39 << 0)
-#define PHYPWR_SLEEP_PHY0			(0x1 << 5)
-
-#define SAMSUNG_PHYCLK				(0x04)
-#define PHYCLK_MODE_USB11			(0x1 << 6)
-#define PHYCLK_EXT_OSC				(0x1 << 5)
-#define PHYCLK_COMMON_ON_N			(0x1 << 4)
-#define PHYCLK_ID_PULL				(0x1 << 2)
-#define PHYCLK_CLKSEL_MASK			(0x3 << 0)
-#define PHYCLK_CLKSEL_48M			(0x0 << 0)
-#define PHYCLK_CLKSEL_12M			(0x2 << 0)
-#define PHYCLK_CLKSEL_24M			(0x3 << 0)
-
-#define SAMSUNG_RSTCON				(0x08)
-#define RSTCON_PHYLINK_SWRST			(0x1 << 2)
-#define RSTCON_HLINK_SWRST			(0x1 << 1)
-#define RSTCON_SWRST				(0x1 << 0)
-
-/* EXYNOS4X12 */
-#define EXYNOS4X12_PHY_HSIC_CTRL0		(0x04)
-#define EXYNOS4X12_PHY_HSIC_CTRL1		(0x08)
-#define PHYPWR_NORMAL_MASK_HSIC1		(0x7 << 12)
-#define PHYPWR_NORMAL_MASK_HSIC0		(0x7 << 9)
-#define PHYPWR_NORMAL_MASK_PHY1			(0x7 << 6)
-#define RSTCON_HOSTPHY_SWRST			(0xf << 3)
-
-/* EXYNOS5 */
-#define EXYNOS5_PHY_HOST_CTRL0			(0x00)
-#define HOST_CTRL0_PHYSWRSTALL			(0x1 << 31)
-#define HOST_CTRL0_REFCLKSEL_MASK		(0x3 << 19)
-#define HOST_CTRL0_REFCLKSEL_XTAL		(0x0 << 19)
-#define HOST_CTRL0_REFCLKSEL_EXTL		(0x1 << 19)
-#define HOST_CTRL0_REFCLKSEL_CLKCORE		(0x2 << 19)
-#define HOST_CTRL0_FSEL_MASK			(0x7 << 16)
-#define HOST_CTRL0_FSEL(_x)			((_x) << 16)
-#define FSEL_CLKSEL_50M				(0x7)
-#define FSEL_CLKSEL_24M				(0x5)
-#define FSEL_CLKSEL_20M				(0x4)
-#define FSEL_CLKSEL_19200K			(0x3)
-#define FSEL_CLKSEL_12M				(0x2)
-#define FSEL_CLKSEL_10M				(0x1)
-#define FSEL_CLKSEL_9600K			(0x0)
-#define HOST_CTRL0_TESTBURNIN			(0x1 << 11)
-#define HOST_CTRL0_RETENABLE			(0x1 << 10)
-#define HOST_CTRL0_COMMONON_N			(0x1 << 9)
-#define HOST_CTRL0_SIDDQ			(0x1 << 6)
-#define HOST_CTRL0_FORCESLEEP			(0x1 << 5)
-#define HOST_CTRL0_FORCESUSPEND			(0x1 << 4)
-#define HOST_CTRL0_WORDINTERFACE		(0x1 << 3)
-#define HOST_CTRL0_UTMISWRST			(0x1 << 2)
-#define HOST_CTRL0_LINKSWRST			(0x1 << 1)
-#define HOST_CTRL0_PHYSWRST			(0x1 << 0)
-
-#define EXYNOS5_PHY_HOST_TUNE0			(0x04)
-
-#define EXYNOS5_PHY_HSIC_CTRL1			(0x10)
-
-#define EXYNOS5_PHY_HSIC_TUNE1			(0x14)
-
-#define EXYNOS5_PHY_HSIC_CTRL2			(0x20)
-
-#define EXYNOS5_PHY_HSIC_TUNE2			(0x24)
-#define HSIC_CTRL_REFCLKSEL_MASK		(0x3 << 23)
-#define HSIC_CTRL_REFCLKSEL			(0x2 << 23)
-#define HSIC_CTRL_REFCLKDIV_MASK		(0x7f << 16)
-#define HSIC_CTRL_REFCLKDIV(_x)			((_x) << 16)
-#define HSIC_CTRL_REFCLKDIV_12			(0x24 << 16)
-#define HSIC_CTRL_REFCLKDIV_15			(0x1c << 16)
-#define HSIC_CTRL_REFCLKDIV_16			(0x1a << 16)
-#define HSIC_CTRL_REFCLKDIV_19_2		(0x15 << 16)
-#define HSIC_CTRL_REFCLKDIV_20			(0x14 << 16)
-#define HSIC_CTRL_SIDDQ				(0x1 << 6)
-#define HSIC_CTRL_FORCESLEEP			(0x1 << 5)
-#define HSIC_CTRL_FORCESUSPEND			(0x1 << 4)
-#define HSIC_CTRL_WORDINTERFACE			(0x1 << 3)
-#define HSIC_CTRL_UTMISWRST			(0x1 << 2)
-#define HSIC_CTRL_PHYSWRST			(0x1 << 0)
-
-#define EXYNOS5_PHY_HOST_EHCICTRL		(0x30)
-#define HOST_EHCICTRL_ENAINCRXALIGN		(0x1 << 29)
-#define HOST_EHCICTRL_ENAINCR4			(0x1 << 28)
-#define HOST_EHCICTRL_ENAINCR8			(0x1 << 27)
-#define HOST_EHCICTRL_ENAINCR16			(0x1 << 26)
-
-#define EXYNOS5_PHY_HOST_OHCICTRL		(0x34)
-#define HOST_OHCICTRL_SUSPLGCY			(0x1 << 3)
-#define HOST_OHCICTRL_APPSTARTCLK		(0x1 << 2)
-#define HOST_OHCICTRL_CNTSEL			(0x1 << 1)
-#define HOST_OHCICTRL_CLKCKTRST			(0x1 << 0)
-
-#define EXYNOS5_PHY_OTG_SYS			(0x38)
-#define OTG_SYS_PHYLINK_SWRESET			(0x1 << 14)
-#define OTG_SYS_LINKSWRST_UOTG			(0x1 << 13)
-#define OTG_SYS_PHY0_SWRST			(0x1 << 12)
-#define OTG_SYS_REFCLKSEL_MASK			(0x3 << 9)
-#define OTG_SYS_REFCLKSEL_XTAL			(0x0 << 9)
-#define OTG_SYS_REFCLKSEL_EXTL			(0x1 << 9)
-#define OTG_SYS_REFCLKSEL_CLKCORE		(0x2 << 9)
-#define OTG_SYS_IDPULLUP_UOTG			(0x1 << 8)
-#define OTG_SYS_COMMON_ON			(0x1 << 7)
-#define OTG_SYS_FSEL_MASK			(0x7 << 4)
-#define OTG_SYS_FSEL(_x)			((_x) << 4)
-#define OTG_SYS_FORCESLEEP			(0x1 << 3)
-#define OTG_SYS_OTGDISABLE			(0x1 << 2)
-#define OTG_SYS_SIDDQ_UOTG			(0x1 << 1)
-#define OTG_SYS_FORCESUSPEND			(0x1 << 0)
-
-#define EXYNOS5_PHY_OTG_TUNE			(0x40)
-
-/* EXYNOS5: USB 3.0 DRD */
-#define EXYNOS5_DRD_LINKSYSTEM			(0x04)
-#define LINKSYSTEM_FLADJ_MASK			(0x3f << 1)
-#define LINKSYSTEM_FLADJ(_x)			((_x) << 1)
-#define LINKSYSTEM_XHCI_VERSION_CONTROL		(0x1 << 27)
-
-#define EXYNOS5_DRD_PHYUTMI			(0x08)
-#define PHYUTMI_OTGDISABLE			(0x1 << 6)
-#define PHYUTMI_FORCESUSPEND			(0x1 << 1)
-#define PHYUTMI_FORCESLEEP			(0x1 << 0)
-
-#define EXYNOS5_DRD_PHYPIPE			(0x0c)
-
-#define EXYNOS5_DRD_PHYCLKRST			(0x10)
-#define PHYCLKRST_SSC_REFCLKSEL_MASK		(0xff << 23)
-#define PHYCLKRST_SSC_REFCLKSEL(_x)		((_x) << 23)
-#define PHYCLKRST_SSC_RANGE_MASK		(0x03 << 21)
-#define PHYCLKRST_SSC_RANGE(_x)			((_x) << 21)
-#define PHYCLKRST_SSC_EN			(0x1 << 20)
-#define PHYCLKRST_REF_SSP_EN			(0x1 << 19)
-#define PHYCLKRST_REF_CLKDIV2			(0x1 << 18)
-#define PHYCLKRST_MPLL_MULTIPLIER_MASK		(0x7f << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_100MHZ_REF	(0x19 << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_50M_REF	(0x02 << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_24MHZ_REF	(0x68 << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_20MHZ_REF	(0x7d << 11)
-#define PHYCLKRST_MPLL_MULTIPLIER_19200KHZ_REF	(0x02 << 11)
-#define PHYCLKRST_FSEL_MASK			(0x3f << 5)
-#define PHYCLKRST_FSEL(_x)			((_x) << 5)
-#define PHYCLKRST_FSEL_PAD_100MHZ		(0x27 << 5)
-#define PHYCLKRST_FSEL_PAD_24MHZ		(0x2a << 5)
-#define PHYCLKRST_FSEL_PAD_20MHZ		(0x31 << 5)
-#define PHYCLKRST_FSEL_PAD_19_2MHZ		(0x38 << 5)
-#define PHYCLKRST_RETENABLEN			(0x1 << 4)
-#define PHYCLKRST_REFCLKSEL_MASK		(0x03 << 2)
-#define PHYCLKRST_REFCLKSEL_PAD_REFCLK		(0x2 << 2)
-#define PHYCLKRST_REFCLKSEL_EXT_REFCLK		(0x3 << 2)
-#define PHYCLKRST_PORTRESET			(0x1 << 1)
-#define PHYCLKRST_COMMONONN			(0x1 << 0)
-
-#define EXYNOS5_DRD_PHYREG0			(0x14)
-
-#define EXYNOS5_DRD_PHYREG1			(0x18)
-
-#define EXYNOS5_DRD_PHYPARAM0			(0x1c)
-#define PHYPARAM0_REF_USE_PAD			(0x1 << 31)
-#define PHYPARAM0_REF_LOSLEVEL_MASK		(0x1f << 26)
-#define PHYPARAM0_REF_LOSLEVEL			(0x9 << 26)
-
-#define EXYNOS5_DRD_PHYPARAM1			(0x20)
-#define PHYPARAM1_PCS_TXDEEMPH_MASK		(0x1f << 0)
-#define PHYPARAM1_PCS_TXDEEMPH			(0x1c)
-
-#define EXYNOS5_DRD_PHYTERM			(0x24)
-
-#define EXYNOS5_DRD_PHYTEST			(0x28)
-#define PHYTEST_POWERDOWN_SSP			(0x1 << 3)
-#define PHYTEST_POWERDOWN_HSP			(0x1 << 2)
-
-#define EXYNOS5_DRD_PHYADP			(0x2c)
-
-#define EXYNOS5_DRD_PHYBATCHG			(0x30)
-#define PHYBATCHG_UTMI_CLKSEL			(0x1 << 2)
-
-#define EXYNOS5_DRD_PHYRESUME			(0x34)
-
-#define EXYNOS5_DRD_LINKPORT			(0x44)
-
-#ifndef MHZ
-#define MHZ (1000*1000)
-#endif
-
-#ifndef KHZ
-#define KHZ (1000)
-#endif
-
-#define EXYNOS_USBHOST_PHY_CTRL_OFFSET		(0x4)
-#define S3C64XX_USBPHY_ENABLE			(0x1 << 16)
-#define EXYNOS_USBPHY_ENABLE			(0x1 << 0)
-#define EXYNOS_USB20PHY_CFG_HOST_LINK		(0x1 << 0)
-
-enum samsung_cpu_type {
-	TYPE_S3C64XX,
-	TYPE_EXYNOS4210,
-	TYPE_EXYNOS4X12,
-	TYPE_EXYNOS5250,
-};
-
-struct samsung_usbphy;
-
-/*
- * struct samsung_usbphy_drvdata - driver data for various SoC variants
- * @cpu_type: machine identifier
- * @devphy_en_mask: device phy enable mask for PHY CONTROL register
- * @hostphy_en_mask: host phy enable mask for PHY CONTROL register
- * @devphy_reg_offset: offset to DEVICE PHY CONTROL register from
- *		       mapped address of system controller.
- * @hostphy_reg_offset: offset to HOST PHY CONTROL register from
- *		       mapped address of system controller.
- *
- *	Here we have a separate mask for device type phy.
- *	Having different masks for host and device type phy helps
- *	in setting independent masks in case of SoCs like S5PV210,
- *	in which PHY0 and PHY1 enable bits belong to same register
- *	placed at position 0 and 1 respectively.
- *	Although for newer SoCs like exynos these bits belong to
- *	different registers altogether placed at position 0.
- */
-struct samsung_usbphy_drvdata {
-	int cpu_type;
-	int devphy_en_mask;
-	int hostphy_en_mask;
-	u32 devphy_reg_offset;
-	u32 hostphy_reg_offset;
-	int (*rate_to_clksel)(struct samsung_usbphy *, unsigned long);
-	void (*set_isolation)(struct samsung_usbphy *, bool);
-	void (*phy_enable)(struct samsung_usbphy *);
-	void (*phy_disable)(struct samsung_usbphy *);
-};
-
-/*
- * struct samsung_usbphy - transceiver driver state
- * @phy: transceiver structure
- * @plat: platform data
- * @dev: The parent device supplied to the probe function
- * @clk: usb phy clock
- * @regs: usb phy controller registers memory base
- * @pmuregs: USB device PHY_CONTROL register memory base
- * @sysreg: USB2.0 PHY_CFG register memory base
- * @ref_clk_freq: reference clock frequency selection
- * @drv_data: driver data available for different SoCs
- * @phy_type: Samsung SoCs specific phy types:	#HOST
- *						#DEVICE
- * @phy_usage: usage count for phy
- * @lock: lock for phy operations
- */
-struct samsung_usbphy {
-	struct usb_phy	phy;
-	struct samsung_usbphy_data *plat;
-	struct device	*dev;
-	struct clk	*clk;
-	void __iomem	*regs;
-	void __iomem	*pmuregs;
-	void __iomem	*sysreg;
-	int		ref_clk_freq;
-	const struct samsung_usbphy_drvdata *drv_data;
-	enum samsung_usb_phy_type phy_type;
-	atomic_t	phy_usage;
-	spinlock_t	lock;
-};
-
-#define phy_to_sphy(x)		container_of((x), struct samsung_usbphy, phy)
-
-static const struct of_device_id samsung_usbphy_dt_match[];
-
-static inline const struct samsung_usbphy_drvdata
-*samsung_usbphy_get_driver_data(struct platform_device *pdev)
-{
-	if (pdev->dev.of_node) {
-		const struct of_device_id *match;
-		match = of_match_node(samsung_usbphy_dt_match,
-							pdev->dev.of_node);
-		return match->data;
-	}
-
-	return (struct samsung_usbphy_drvdata *)
-				platform_get_device_id(pdev)->driver_data;
-}
-
-extern int samsung_usbphy_parse_dt(struct samsung_usbphy *sphy);
-extern void samsung_usbphy_set_isolation_4210(struct samsung_usbphy *sphy,
-								bool on);
-extern void samsung_usbphy_cfg_sel(struct samsung_usbphy *sphy);
-extern int samsung_usbphy_set_type(struct usb_phy *phy,
-					enum samsung_usb_phy_type phy_type);
-extern int samsung_usbphy_get_refclk_freq(struct samsung_usbphy *sphy);
-extern int samsung_usbphy_rate_to_clksel_64xx(struct samsung_usbphy *sphy,
-							unsigned long rate);
-extern int samsung_usbphy_rate_to_clksel_4x12(struct samsung_usbphy *sphy,
-							unsigned long rate);
diff --git a/include/linux/platform_data/samsung-usbphy.h b/include/linux/platform_data/samsung-usbphy.h
deleted file mode 100644
index 1bd24cba982b..000000000000
--- a/include/linux/platform_data/samsung-usbphy.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Copyright (C) 2012 Samsung Electronics Co.Ltd
- *		http://www.samsung.com/
- * Author: Praveen Paneri <p.paneri@samsung.com>
- *
- * Defines platform data for samsung usb phy driver.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef __SAMSUNG_USBPHY_PLATFORM_H
-#define __SAMSUNG_USBPHY_PLATFORM_H
-
-/**
- * samsung_usbphy_data - Platform data for USB PHY driver.
- * @pmu_isolation: Function to control usb phy isolation in PMU.
- */
-struct samsung_usbphy_data {
-	void (*pmu_isolation)(int on);
-};
-
-extern void samsung_usbphy_set_pdata(struct samsung_usbphy_data *pd);
-
-#endif /* __SAMSUNG_USBPHY_PLATFORM_H */
-- 
cgit v1.2.3


From 1df22b4ea9d91b01267fb61c155c31fb65d6b8a0 Mon Sep 17 00:00:00 2001
From: Michal Nazarewicz <mina86@mina86.com>
Date: Wed, 27 Aug 2014 22:58:45 +0200
Subject: usb: gadget: f_fs: add usb_functionfs_descs_head_v2 structure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The structure can be used with user space tools that use the new
functionfs description format, for example as follows:

static const struct {
	struct usb_functionfs_descs_head_v2 header;
	__le32 fs_count;
	__le32 hs_count;
	struct {
		…
	} fs_desc;
	struct {
		…
	} hs_desc;
} descriptors = {
	.header = {
		.magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC_V2),
		.length = cpu_to_le32(sizeof(descriptors)),
		.flags = cpu_to_le32(FUNCTIONFS_HAS_FS_DESC |
				     FUNCTIONFS_HAS_HS_DESC)
	},
	.fs_count = cpu_to_le32(X),
	.fs_desc = {
		…
	},
	.hs_count = cpu_to_le32(Y),
	.hs_desc = {
		…
	}
};

Signed-off-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/uapi/linux/usb/functionfs.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index 0154b2859fd7..3ca03de7c2a8 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -32,6 +32,16 @@ struct usb_endpoint_descriptor_no_audio {
 	__u8  bInterval;
 } __attribute__((packed));
 
+struct usb_functionfs_descs_head_v2 {
+	__le32 magic;
+	__le32 length;
+	__le32 flags;
+	/*
+	 * __le32 fs_count, hs_count, fs_count; must be included manually in
+	 * the structure taking flags into consideration.
+	 */
+} __attribute__((packed));
+
 /* Legacy format, deprecated as of 3.14. */
 struct usb_functionfs_descs_head {
 	__le32 magic;
-- 
cgit v1.2.3


From 51c208c746e800dba37d1a54d3c5e601630266c4 Mon Sep 17 00:00:00 2001
From: Michal Nazarewicz <mina86@mina86.com>
Date: Wed, 27 Aug 2014 22:58:46 +0200
Subject: tools: ffs-test: convert to new descriptor format
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit [ac8dde11: “Add flags to descriptors block”] functionfs
supports a new, more powerful and extensible, descriptor format.
Since ffs-test is probably the first thing users of the functionfs
interface see when they start writing functionfs user space daemons,
convert it to use the new format thus promoting it.

Signed-off-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/uapi/linux/usb/functionfs.h |  2 +-
 tools/usb/ffs-test.c                | 14 +++++++++-----
 2 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index 3ca03de7c2a8..6d2a16b834bf 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -102,7 +102,7 @@ struct usb_ext_prop_desc {
  * structure.  Any flags that are not recognised cause the whole block to be
  * rejected with -ENOSYS.
  *
- * Legacy descriptors format:
+ * Legacy descriptors format (deprecated as of 3.14):
  *
  * | off | name      | type         | description                          |
  * |-----+-----------+--------------+--------------------------------------|
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index a87e99f37c52..708d317b0f37 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -1,5 +1,5 @@
 /*
- * ffs-test.c.c -- user mode filesystem api for usb composite function
+ * ffs-test.c -- user mode filesystem api for usb composite function
  *
  * Copyright (C) 2010 Samsung Electronics
  *                    Author: Michal Nazarewicz <mina86@mina86.com>
@@ -106,7 +106,9 @@ static void _msg(unsigned level, const char *fmt, ...)
 /******************** Descriptors and Strings *******************************/
 
 static const struct {
-	struct usb_functionfs_descs_head header;
+	struct usb_functionfs_descs_head_v2 header;
+	__le32 fs_count;
+	__le32 hs_count;
 	struct {
 		struct usb_interface_descriptor intf;
 		struct usb_endpoint_descriptor_no_audio sink;
@@ -114,11 +116,12 @@ static const struct {
 	} __attribute__((packed)) fs_descs, hs_descs;
 } __attribute__((packed)) descriptors = {
 	.header = {
-		.magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC),
+		.magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC_V2),
+		.flags = cpu_to_le32(FUNCTIONFS_HAS_FS_DESC |
+				     FUNCTIONFS_HAS_HS_DESC),
 		.length = cpu_to_le32(sizeof descriptors),
-		.fs_count = cpu_to_le32(3),
-		.hs_count = cpu_to_le32(3),
 	},
+	.fs_count = cpu_to_le32(3),
 	.fs_descs = {
 		.intf = {
 			.bLength = sizeof descriptors.fs_descs.intf,
@@ -142,6 +145,7 @@ static const struct {
 			/* .wMaxPacketSize = autoconfiguration (kernel) */
 		},
 	},
+	.hs_count = cpu_to_le32(3),
 	.hs_descs = {
 		.intf = {
 			.bLength = sizeof descriptors.fs_descs.intf,
-- 
cgit v1.2.3


From f2c24b83ae90292d315aa7ac029c6ce7929e01aa Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Date: Wed, 2 Apr 2014 17:14:48 +0200
Subject: drm/ttm: flip the switch, and convert to dma_fence

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
---
 drivers/gpu/drm/nouveau/nouveau_bo.c     |  48 ++-------
 drivers/gpu/drm/nouveau/nouveau_fence.c  |  24 ++---
 drivers/gpu/drm/nouveau/nouveau_fence.h  |   2 +-
 drivers/gpu/drm/nouveau/nouveau_gem.c    |  16 +--
 drivers/gpu/drm/qxl/qxl_debugfs.c        |   6 +-
 drivers/gpu/drm/qxl/qxl_drv.h            |   2 -
 drivers/gpu/drm/qxl/qxl_kms.c            |   1 -
 drivers/gpu/drm/qxl/qxl_object.h         |   4 +-
 drivers/gpu/drm/qxl/qxl_release.c        |   3 -
 drivers/gpu/drm/qxl/qxl_ttm.c            | 104 -------------------
 drivers/gpu/drm/radeon/radeon_cs.c       |  10 +-
 drivers/gpu/drm/radeon/radeon_display.c  |   2 +-
 drivers/gpu/drm/radeon/radeon_mn.c       |   6 +-
 drivers/gpu/drm/radeon/radeon_object.c   |   4 +-
 drivers/gpu/drm/radeon/radeon_ttm.c      |  34 +-----
 drivers/gpu/drm/radeon/radeon_uvd.c      |   6 +-
 drivers/gpu/drm/radeon/radeon_vm.c       |  15 ++-
 drivers/gpu/drm/ttm/ttm_bo.c             | 171 +++++++++++++++++++++----------
 drivers/gpu/drm/ttm/ttm_bo_util.c        |  23 +----
 drivers/gpu/drm/ttm/ttm_execbuf_util.c   |  10 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c   |  40 --------
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c |  14 +--
 include/drm/ttm/ttm_bo_api.h             |   2 -
 include/drm/ttm/ttm_bo_driver.h          |  26 +----
 include/drm/ttm/ttm_execbuf_util.h       |  10 +-
 25 files changed, 197 insertions(+), 386 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 2d026c81ca1b..6cf7db070faf 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -88,13 +88,13 @@ nv10_bo_get_tile_region(struct drm_device *dev, int i)
 
 static void
 nv10_bo_put_tile_region(struct drm_device *dev, struct nouveau_drm_tile *tile,
-			struct nouveau_fence *fence)
+			struct fence *fence)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
 	if (tile) {
 		spin_lock(&drm->tile.lock);
-		tile->fence = nouveau_fence_ref(fence);
+		tile->fence = nouveau_fence_ref((struct nouveau_fence *)fence);
 		tile->used = false;
 		spin_unlock(&drm->tile.lock);
 	}
@@ -976,7 +976,8 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 		if (ret == 0) {
 			ret = nouveau_fence_new(chan, false, &fence);
 			if (ret == 0) {
-				ret = ttm_bo_move_accel_cleanup(bo, fence,
+				ret = ttm_bo_move_accel_cleanup(bo,
+								&fence->base,
 								evict,
 								no_wait_gpu,
 								new_mem);
@@ -1167,8 +1168,9 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo,
 {
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct drm_device *dev = drm->dev;
+	struct fence *fence = reservation_object_get_excl(bo->resv);
 
-	nv10_bo_put_tile_region(dev, *old_tile, bo->sync_obj);
+	nv10_bo_put_tile_region(dev, *old_tile, fence);
 	*old_tile = new_tile;
 }
 
@@ -1455,47 +1457,14 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	ttm_pool_unpopulate(ttm);
 }
 
-static void
-nouveau_bo_fence_unref(void **sync_obj)
-{
-	nouveau_fence_unref((struct nouveau_fence **)sync_obj);
-}
-
 void
 nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence)
 {
 	struct reservation_object *resv = nvbo->bo.resv;
 
-	nouveau_bo_fence_unref(&nvbo->bo.sync_obj);
-	nvbo->bo.sync_obj = nouveau_fence_ref(fence);
-
 	reservation_object_add_excl_fence(resv, &fence->base);
 }
 
-static void *
-nouveau_bo_fence_ref(void *sync_obj)
-{
-	return nouveau_fence_ref(sync_obj);
-}
-
-static bool
-nouveau_bo_fence_signalled(void *sync_obj)
-{
-	return nouveau_fence_done(sync_obj);
-}
-
-static int
-nouveau_bo_fence_wait(void *sync_obj, bool lazy, bool intr)
-{
-	return nouveau_fence_wait(sync_obj, lazy, intr);
-}
-
-static int
-nouveau_bo_fence_flush(void *sync_obj)
-{
-	return 0;
-}
-
 struct ttm_bo_driver nouveau_bo_driver = {
 	.ttm_tt_create = &nouveau_ttm_tt_create,
 	.ttm_tt_populate = &nouveau_ttm_tt_populate,
@@ -1506,11 +1475,6 @@ struct ttm_bo_driver nouveau_bo_driver = {
 	.move_notify = nouveau_bo_move_ntfy,
 	.move = nouveau_bo_move,
 	.verify_access = nouveau_bo_verify_access,
-	.sync_obj_signaled = nouveau_bo_fence_signalled,
-	.sync_obj_wait = nouveau_bo_fence_wait,
-	.sync_obj_flush = nouveau_bo_fence_flush,
-	.sync_obj_unref = nouveau_bo_fence_unref,
-	.sync_obj_ref = nouveau_bo_fence_ref,
 	.fault_reserve_notify = &nouveau_ttm_fault_reserve_notify,
 	.io_mem_reserve = &nouveau_ttm_io_mem_reserve,
 	.io_mem_free = &nouveau_ttm_io_mem_free,
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 3beb3bf130e2..5e7fa68bc438 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -185,17 +185,18 @@ static void nouveau_fence_work_cb(struct fence *fence, struct fence_cb *cb)
 }
 
 void
-nouveau_fence_work(struct nouveau_fence *fence,
+nouveau_fence_work(struct fence *fence,
 		   void (*func)(void *), void *data)
 {
 	struct nouveau_fence_work *work;
 
-	if (fence_is_signaled(&fence->base))
+	if (fence_is_signaled(fence))
 		goto err;
 
 	work = kmalloc(sizeof(*work), GFP_KERNEL);
 	if (!work) {
-		WARN_ON(nouveau_fence_wait(fence, false, false));
+		WARN_ON(nouveau_fence_wait((struct nouveau_fence *)fence,
+					   false, false));
 		goto err;
 	}
 
@@ -203,7 +204,7 @@ nouveau_fence_work(struct nouveau_fence *fence,
 	work->func = func;
 	work->data = data;
 
-	if (fence_add_callback(&fence->base, &work->cb, nouveau_fence_work_cb) < 0)
+	if (fence_add_callback(fence, &work->cb, nouveau_fence_work_cb) < 0)
 		goto err_free;
 	return;
 
@@ -349,14 +350,9 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan)
 	struct reservation_object_list *fobj;
 	int ret = 0, i;
 
-	fence = nvbo->bo.sync_obj;
-	if (fence && fence_is_signaled(fence)) {
-		nouveau_fence_unref((struct nouveau_fence **)
-				    &nvbo->bo.sync_obj);
-		fence = NULL;
-	}
+	fence = reservation_object_get_excl(resv);
 
-	if (fence) {
+	if (fence && !fence_is_signaled(fence)) {
 		struct nouveau_fence *f = from_fence(fence);
 		struct nouveau_channel *prev = f->channel;
 
@@ -370,12 +366,8 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan)
 	if (ret)
 		return ret;
 
-	fence = reservation_object_get_excl(resv);
-	if (fence && !nouveau_local_fence(fence, chan->drm))
-		ret = fence_wait(fence, true);
-
 	fobj = reservation_object_get_list(resv);
-	if (!fobj || ret)
+	if (!fobj)
 		return ret;
 
 	for (i = 0; i < fobj->shared_count && !ret; ++i) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 44efd8c7426c..0282e88274ff 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -26,7 +26,7 @@ void nouveau_fence_unref(struct nouveau_fence **);
 
 int  nouveau_fence_emit(struct nouveau_fence *, struct nouveau_channel *);
 bool nouveau_fence_done(struct nouveau_fence *);
-void nouveau_fence_work(struct nouveau_fence *, void (*)(void *), void *);
+void nouveau_fence_work(struct fence *, void (*)(void *), void *);
 int  nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr);
 int  nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index d68c9656e409..a28b5102c4a5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -98,13 +98,12 @@ static void
 nouveau_gem_object_unmap(struct nouveau_bo *nvbo, struct nouveau_vma *vma)
 {
 	const bool mapped = nvbo->bo.mem.mem_type != TTM_PL_SYSTEM;
-	struct nouveau_fence *fence = NULL;
+	struct fence *fence = NULL;
 
 	list_del(&vma->head);
 
-	if (mapped) {
-		fence = nouveau_fence_ref(nvbo->bo.sync_obj);
-	}
+	if (mapped)
+		fence = reservation_object_get_excl(nvbo->bo.resv);
 
 	if (fence) {
 		nouveau_fence_work(fence, nouveau_gem_object_delete, vma);
@@ -114,7 +113,6 @@ nouveau_gem_object_unmap(struct nouveau_bo *nvbo, struct nouveau_vma *vma)
 		nouveau_vm_put(vma);
 		kfree(vma);
 	}
-	nouveau_fence_unref(&fence);
 }
 
 void
@@ -874,8 +872,12 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
 	ret = ttm_bo_reserve(&nvbo->bo, true, false, false, NULL);
 	if (!ret) {
 		ret = ttm_bo_wait(&nvbo->bo, true, true, true);
-		if (!no_wait && ret)
-			fence = nouveau_fence_ref(nvbo->bo.sync_obj);
+		if (!no_wait && ret) {
+			struct fence *excl;
+
+			excl = reservation_object_get_excl(nvbo->bo.resv);
+			fence = nouveau_fence_ref((struct nouveau_fence *)excl);
+		}
 
 		ttm_bo_unreserve(&nvbo->bo);
 	}
diff --git a/drivers/gpu/drm/qxl/qxl_debugfs.c b/drivers/gpu/drm/qxl/qxl_debugfs.c
index 0d144e0646d6..a4a63fd84803 100644
--- a/drivers/gpu/drm/qxl/qxl_debugfs.c
+++ b/drivers/gpu/drm/qxl/qxl_debugfs.c
@@ -67,9 +67,9 @@ qxl_debugfs_buffers_info(struct seq_file *m, void *data)
 		rel = fobj ? fobj->shared_count : 0;
 		rcu_read_unlock();
 
-		seq_printf(m, "size %ld, pc %d, sync obj %p, num releases %d\n",
-			   (unsigned long)bo->gem_base.size, bo->pin_count,
-			   bo->tbo.sync_obj, rel);
+		seq_printf(m, "size %ld, pc %d, num releases %d\n",
+			   (unsigned long)bo->gem_base.size,
+			   bo->pin_count, rel);
 	}
 	spin_unlock(&qdev->release_lock);
 	return 0;
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 116eeae843b4..a8be87632cae 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -280,9 +280,7 @@ struct qxl_device {
 	uint8_t		slot_gen_bits;
 	uint64_t	va_slot_mask;
 
-	/* XXX: when rcu becomes available, release_lock can be killed */
 	spinlock_t	release_lock;
-	spinlock_t	fence_lock;
 	struct idr	release_idr;
 	uint32_t	release_seqno;
 	spinlock_t release_idr_lock;
diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c
index a9e7c30e92c5..7234561e09d9 100644
--- a/drivers/gpu/drm/qxl/qxl_kms.c
+++ b/drivers/gpu/drm/qxl/qxl_kms.c
@@ -224,7 +224,6 @@ static int qxl_device_init(struct qxl_device *qdev,
 	idr_init(&qdev->release_idr);
 	spin_lock_init(&qdev->release_idr_lock);
 	spin_lock_init(&qdev->release_lock);
-	spin_lock_init(&qdev->fence_lock);
 
 	idr_init(&qdev->surf_id_idr);
 	spin_lock_init(&qdev->surf_id_idr_lock);
diff --git a/drivers/gpu/drm/qxl/qxl_object.h b/drivers/gpu/drm/qxl/qxl_object.h
index 1edaf5768086..37af1bc0dd00 100644
--- a/drivers/gpu/drm/qxl/qxl_object.h
+++ b/drivers/gpu/drm/qxl/qxl_object.h
@@ -78,8 +78,8 @@ static inline int qxl_bo_wait(struct qxl_bo *bo, u32 *mem_type,
 	}
 	if (mem_type)
 		*mem_type = bo->tbo.mem.mem_type;
-	if (bo->tbo.sync_obj)
-		r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
+
+	r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
 	ttm_bo_unreserve(&bo->tbo);
 	return r;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 9731d2540a40..15158c5a5b3a 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -464,9 +464,6 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release)
 		bo = entry->bo;
 		qbo = to_qxl_bo(bo);
 
-		if (!entry->bo->sync_obj)
-			entry->bo->sync_obj = qbo;
-
 		reservation_object_add_shared_fence(bo->resv, &release->base);
 		ttm_bo_add_to_lru(bo);
 		__ttm_bo_unreserve(bo);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 29e0a758ee68..abe945a04fd4 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -357,105 +357,6 @@ static int qxl_bo_move(struct ttm_buffer_object *bo,
 	return ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 }
 
-static bool qxl_sync_obj_signaled(void *sync_obj);
-
-static int qxl_sync_obj_wait(void *sync_obj,
-			     bool lazy, bool interruptible)
-{
-	struct qxl_bo *bo = (struct qxl_bo *)sync_obj;
-	struct qxl_device *qdev = bo->gem_base.dev->dev_private;
-	struct reservation_object_list *fobj;
-	int count = 0, sc = 0, num_release = 0;
-	bool have_drawable_releases;
-
-retry:
-	if (sc == 0) {
-		if (bo->type == QXL_GEM_DOMAIN_SURFACE)
-			qxl_update_surface(qdev, bo);
-	} else if (sc >= 1) {
-		qxl_io_notify_oom(qdev);
-	}
-
-	sc++;
-
-	for (count = 0; count < 10; count++) {
-		if (qxl_sync_obj_signaled(sync_obj))
-			return 0;
-
-		if (!qxl_queue_garbage_collect(qdev, true))
-			break;
-	}
-
-	have_drawable_releases = false;
-	num_release = 0;
-
-	spin_lock(&qdev->release_lock);
-	fobj = bo->tbo.resv->fence;
-	for (count = 0; fobj && count < fobj->shared_count; count++) {
-		struct qxl_release *release;
-
-		release = container_of(fobj->shared[count],
-				       struct qxl_release, base);
-
-		if (fence_is_signaled(&release->base))
-			continue;
-
-		num_release++;
-
-		if (release->type == QXL_RELEASE_DRAWABLE)
-			have_drawable_releases = true;
-	}
-	spin_unlock(&qdev->release_lock);
-
-	qxl_queue_garbage_collect(qdev, true);
-
-	if (have_drawable_releases || sc < 4) {
-		if (sc > 2)
-			/* back off */
-			usleep_range(500, 1000);
-		if (have_drawable_releases && sc > 300) {
-			WARN(1, "sync obj %d still has outstanding releases %d %d %d %ld %d\n", sc, bo->surface_id, bo->is_primary, bo->pin_count, (unsigned long)bo->gem_base.size, num_release);
-			return -EBUSY;
-		}
-		goto retry;
-	}
-	return 0;
-}
-
-static int qxl_sync_obj_flush(void *sync_obj)
-{
-	return 0;
-}
-
-static void qxl_sync_obj_unref(void **sync_obj)
-{
-	*sync_obj = NULL;
-}
-
-static void *qxl_sync_obj_ref(void *sync_obj)
-{
-	return sync_obj;
-}
-
-static bool qxl_sync_obj_signaled(void *sync_obj)
-{
-	struct qxl_bo *qbo = (struct qxl_bo *)sync_obj;
-	struct qxl_device *qdev = qbo->gem_base.dev->dev_private;
-	struct reservation_object_list *fobj;
-	bool ret = true;
-	unsigned i;
-
-	spin_lock(&qdev->release_lock);
-	fobj = qbo->tbo.resv->fence;
-	for (i = 0; fobj && i < fobj->shared_count; ++i) {
-		ret = fence_is_signaled(fobj->shared[i]);
-		if (!ret)
-			break;
-	}
-	spin_unlock(&qdev->release_lock);
-	return ret;
-}
-
 static void qxl_bo_move_notify(struct ttm_buffer_object *bo,
 			       struct ttm_mem_reg *new_mem)
 {
@@ -482,11 +383,6 @@ static struct ttm_bo_driver qxl_bo_driver = {
 	.verify_access = &qxl_verify_access,
 	.io_mem_reserve = &qxl_ttm_io_mem_reserve,
 	.io_mem_free = &qxl_ttm_io_mem_free,
-	.sync_obj_signaled = &qxl_sync_obj_signaled,
-	.sync_obj_wait = &qxl_sync_obj_wait,
-	.sync_obj_flush = &qxl_sync_obj_flush,
-	.sync_obj_unref = &qxl_sync_obj_unref,
-	.sync_obj_ref = &qxl_sync_obj_ref,
 	.move_notify = &qxl_bo_move_notify,
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index bd328cb6fa61..6e3d1c8f3483 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -253,11 +253,17 @@ static void radeon_cs_sync_rings(struct radeon_cs_parser *p)
 	int i;
 
 	for (i = 0; i < p->nrelocs; i++) {
+		struct reservation_object *resv;
+		struct fence *fence;
+
 		if (!p->relocs[i].robj)
 			continue;
 
+		resv = p->relocs[i].robj->tbo.resv;
+		fence = reservation_object_get_excl(resv);
+
 		radeon_semaphore_sync_to(p->ib.semaphore,
-					 p->relocs[i].robj->tbo.sync_obj);
+					 (struct radeon_fence *)fence);
 	}
 }
 
@@ -427,7 +433,7 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo
 
 		ttm_eu_fence_buffer_objects(&parser->ticket,
 					    &parser->validated,
-					    parser->ib.fence);
+					    &parser->ib.fence->base);
 	} else if (backoff) {
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 7d0a7abdab2a..bc894c17b2f9 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -494,7 +494,7 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 		DRM_ERROR("failed to pin new rbo buffer before flip\n");
 		goto cleanup;
 	}
-	work->fence = radeon_fence_ref(new_rbo->tbo.sync_obj);
+	work->fence = (struct radeon_fence *)fence_get(reservation_object_get_excl(new_rbo->tbo.resv));
 	radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL);
 	radeon_bo_unreserve(new_rbo);
 
diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c
index 0157bc2f11f8..a69bd441dd2d 100644
--- a/drivers/gpu/drm/radeon/radeon_mn.c
+++ b/drivers/gpu/drm/radeon/radeon_mn.c
@@ -122,6 +122,7 @@ static void radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 	it = interval_tree_iter_first(&rmn->objects, start, end);
 	while (it) {
 		struct radeon_bo *bo;
+		struct fence *fence;
 		int r;
 
 		bo = container_of(it, struct radeon_bo, mn_it);
@@ -133,8 +134,9 @@ static void radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 			continue;
 		}
 
-		if (bo->tbo.sync_obj) {
-			r = radeon_fence_wait(bo->tbo.sync_obj, false);
+		fence = reservation_object_get_excl(bo->tbo.resv);
+		if (fence) {
+			r = radeon_fence_wait((struct radeon_fence *)fence, false);
 			if (r)
 				DRM_ERROR("(%d) failed to wait for user bo\n", r);
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 378fe9ea4d44..aadbd36e64b9 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -781,8 +781,8 @@ int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type, bool no_wait)
 		return r;
 	if (mem_type)
 		*mem_type = bo->tbo.mem.mem_type;
-	if (bo->tbo.sync_obj)
-		r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
+
+	r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
 	ttm_bo_unreserve(&bo->tbo);
 	return r;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 822eb3630045..62d1f4d730a2 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -270,12 +270,12 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 	BUILD_BUG_ON((PAGE_SIZE % RADEON_GPU_PAGE_SIZE) != 0);
 
 	/* sync other rings */
-	fence = bo->sync_obj;
+	fence = (struct radeon_fence *)reservation_object_get_excl(bo->resv);
 	r = radeon_copy(rdev, old_start, new_start,
 			new_mem->num_pages * (PAGE_SIZE / RADEON_GPU_PAGE_SIZE), /* GPU pages */
 			&fence);
 	/* FIXME: handle copy error */
-	r = ttm_bo_move_accel_cleanup(bo, (void *)fence,
+	r = ttm_bo_move_accel_cleanup(bo, &fence->base,
 				      evict, no_wait_gpu, new_mem);
 	radeon_fence_unref(&fence);
 	return r;
@@ -488,31 +488,6 @@ static void radeon_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_re
 {
 }
 
-static int radeon_sync_obj_wait(void *sync_obj, bool lazy, bool interruptible)
-{
-	return radeon_fence_wait((struct radeon_fence *)sync_obj, interruptible);
-}
-
-static int radeon_sync_obj_flush(void *sync_obj)
-{
-	return 0;
-}
-
-static void radeon_sync_obj_unref(void **sync_obj)
-{
-	radeon_fence_unref((struct radeon_fence **)sync_obj);
-}
-
-static void *radeon_sync_obj_ref(void *sync_obj)
-{
-	return radeon_fence_ref((struct radeon_fence *)sync_obj);
-}
-
-static bool radeon_sync_obj_signaled(void *sync_obj)
-{
-	return radeon_fence_signaled((struct radeon_fence *)sync_obj);
-}
-
 /*
  * TTM backend functions.
  */
@@ -847,11 +822,6 @@ static struct ttm_bo_driver radeon_bo_driver = {
 	.evict_flags = &radeon_evict_flags,
 	.move = &radeon_bo_move,
 	.verify_access = &radeon_verify_access,
-	.sync_obj_signaled = &radeon_sync_obj_signaled,
-	.sync_obj_wait = &radeon_sync_obj_wait,
-	.sync_obj_flush = &radeon_sync_obj_flush,
-	.sync_obj_unref = &radeon_sync_obj_unref,
-	.sync_obj_ref = &radeon_sync_obj_ref,
 	.move_notify = &radeon_bo_move_notify,
 	.fault_reserve_notify = &radeon_bo_fault_reserve_notify,
 	.io_mem_reserve = &radeon_ttm_io_mem_reserve,
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 5729e9bebd9d..ba4f38916026 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -400,6 +400,7 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 {
 	int32_t *msg, msg_type, handle;
 	unsigned img_size = 0;
+	struct fence *f;
 	void *ptr;
 
 	int i, r;
@@ -409,8 +410,9 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 		return -EINVAL;
 	}
 
-	if (bo->tbo.sync_obj) {
-		r = radeon_fence_wait(bo->tbo.sync_obj, false);
+	f = reservation_object_get_excl(bo->tbo.resv);
+	if (f) {
+		r = radeon_fence_wait((struct radeon_fence *)f, false);
 		if (r) {
 			DRM_ERROR("Failed waiting for UVD message (%d)!\n", r);
 			return r;
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 3d9a6a036f8a..671ee566aa51 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -424,7 +424,7 @@ static int radeon_vm_clear_bo(struct radeon_device *rdev,
 	if (r)
                 goto error;
 
-	ttm_eu_fence_buffer_objects(&ticket, &head, ib.fence);
+	ttm_eu_fence_buffer_objects(&ticket, &head, &ib.fence->base);
 	radeon_ib_free(rdev, &ib);
 
 	return 0;
@@ -693,8 +693,14 @@ int radeon_vm_update_page_directory(struct radeon_device *rdev,
 				    incr, R600_PTE_VALID);
 
 	if (ib.length_dw != 0) {
+		struct fence *fence;
+
 		radeon_asic_vm_pad_ib(rdev, &ib);
-		radeon_semaphore_sync_to(ib.semaphore, pd->tbo.sync_obj);
+
+		fence = reservation_object_get_excl(pd->tbo.resv);
+		radeon_semaphore_sync_to(ib.semaphore,
+					 (struct radeon_fence *)fence);
+
 		radeon_semaphore_sync_to(ib.semaphore, vm->last_id_use);
 		WARN_ON(ib.length_dw > ndw);
 		r = radeon_ib_schedule(rdev, &ib, NULL, false);
@@ -820,8 +826,11 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 		struct radeon_bo *pt = vm->page_tables[pt_idx].bo;
 		unsigned nptes;
 		uint64_t pte;
+		struct fence *fence;
 
-		radeon_semaphore_sync_to(ib->semaphore, pt->tbo.sync_obj);
+		fence = reservation_object_get_excl(pt->tbo.resv);
+		radeon_semaphore_sync_to(ib->semaphore,
+					 (struct radeon_fence *)fence);
 
 		if ((addr & ~mask) == (end & ~mask))
 			nptes = end - addr;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 195386f16ca4..66707be386f7 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -40,6 +40,7 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/atomic.h>
+#include <linux/reservation.h>
 
 #define TTM_ASSERT_LOCKED(param)
 #define TTM_DEBUG(fmt, arg...)
@@ -142,7 +143,6 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	BUG_ON(atomic_read(&bo->list_kref.refcount));
 	BUG_ON(atomic_read(&bo->kref.refcount));
 	BUG_ON(atomic_read(&bo->cpu_writers));
-	BUG_ON(bo->sync_obj != NULL);
 	BUG_ON(bo->mem.mm_node != NULL);
 	BUG_ON(!list_empty(&bo->lru));
 	BUG_ON(!list_empty(&bo->ddestroy));
@@ -403,12 +403,30 @@ static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo)
 	ww_mutex_unlock (&bo->resv->lock);
 }
 
+static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo)
+{
+	struct reservation_object_list *fobj;
+	struct fence *fence;
+	int i;
+
+	fobj = reservation_object_get_list(bo->resv);
+	fence = reservation_object_get_excl(bo->resv);
+	if (fence && !fence->ops->signaled)
+		fence_enable_sw_signaling(fence);
+
+	for (i = 0; fobj && i < fobj->shared_count; ++i) {
+		fence = rcu_dereference_protected(fobj->shared[i],
+					reservation_object_held(bo->resv));
+
+		if (!fence->ops->signaled)
+			fence_enable_sw_signaling(fence);
+	}
+}
+
 static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_bo_global *glob = bo->glob;
-	struct ttm_bo_driver *driver = bdev->driver;
-	void *sync_obj = NULL;
 	int put_count;
 	int ret;
 
@@ -416,9 +434,7 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	ret = __ttm_bo_reserve(bo, false, true, false, NULL);
 
 	if (!ret) {
-		(void) ttm_bo_wait(bo, false, false, true);
-
-		if (!bo->sync_obj) {
+		if (!ttm_bo_wait(bo, false, false, true)) {
 			put_count = ttm_bo_del_from_lru(bo);
 
 			spin_unlock(&glob->lru_lock);
@@ -427,8 +443,8 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 			ttm_bo_list_ref_sub(bo, put_count, true);
 
 			return;
-		}
-		sync_obj = driver->sync_obj_ref(bo->sync_obj);
+		} else
+			ttm_bo_flush_all_fences(bo);
 
 		/*
 		 * Make NO_EVICT bos immediately available to
@@ -447,14 +463,70 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	list_add_tail(&bo->ddestroy, &bdev->ddestroy);
 	spin_unlock(&glob->lru_lock);
 
-	if (sync_obj) {
-		driver->sync_obj_flush(sync_obj);
-		driver->sync_obj_unref(&sync_obj);
-	}
 	schedule_delayed_work(&bdev->wq,
 			      ((HZ / 100) < 1) ? 1 : HZ / 100);
 }
 
+static int ttm_bo_unreserve_and_wait(struct ttm_buffer_object *bo,
+				     bool interruptible)
+{
+	struct ttm_bo_global *glob = bo->glob;
+	struct reservation_object_list *fobj;
+	struct fence *excl = NULL;
+	struct fence **shared = NULL;
+	u32 shared_count = 0, i;
+	int ret = 0;
+
+	fobj = reservation_object_get_list(bo->resv);
+	if (fobj && fobj->shared_count) {
+		shared = kmalloc(sizeof(*shared) * fobj->shared_count,
+				 GFP_KERNEL);
+
+		if (!shared) {
+			ret = -ENOMEM;
+			__ttm_bo_unreserve(bo);
+			spin_unlock(&glob->lru_lock);
+			return ret;
+		}
+
+		for (i = 0; i < fobj->shared_count; ++i) {
+			if (!fence_is_signaled(fobj->shared[i])) {
+				fence_get(fobj->shared[i]);
+				shared[shared_count++] = fobj->shared[i];
+			}
+		}
+		if (!shared_count) {
+			kfree(shared);
+			shared = NULL;
+		}
+	}
+
+	excl = reservation_object_get_excl(bo->resv);
+	if (excl && !fence_is_signaled(excl))
+		fence_get(excl);
+	else
+		excl = NULL;
+
+	__ttm_bo_unreserve(bo);
+	spin_unlock(&glob->lru_lock);
+
+	if (excl) {
+		ret = fence_wait(excl, interruptible);
+		fence_put(excl);
+	}
+
+	if (shared_count > 0) {
+		for (i = 0; i < shared_count; ++i) {
+			if (!ret)
+				ret = fence_wait(shared[i], interruptible);
+			fence_put(shared[i]);
+		}
+		kfree(shared);
+	}
+
+	return ret;
+}
+
 /**
  * function ttm_bo_cleanup_refs_and_unlock
  * If bo idle, remove from delayed- and lru lists, and unref.
@@ -471,8 +543,6 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 					  bool interruptible,
 					  bool no_wait_gpu)
 {
-	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_driver *driver = bdev->driver;
 	struct ttm_bo_global *glob = bo->glob;
 	int put_count;
 	int ret;
@@ -480,20 +550,7 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 	ret = ttm_bo_wait(bo, false, false, true);
 
 	if (ret && !no_wait_gpu) {
-		void *sync_obj;
-
-		/*
-		 * Take a reference to the fence and unreserve,
-		 * at this point the buffer should be dead, so
-		 * no new sync objects can be attached.
-		 */
-		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-
-		__ttm_bo_unreserve(bo);
-		spin_unlock(&glob->lru_lock);
-
-		ret = driver->sync_obj_wait(sync_obj, false, interruptible);
-		driver->sync_obj_unref(&sync_obj);
+		ret = ttm_bo_unreserve_and_wait(bo, interruptible);
 		if (ret)
 			return ret;
 
@@ -1498,41 +1555,51 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo)
 
 EXPORT_SYMBOL(ttm_bo_unmap_virtual);
 
-
 int ttm_bo_wait(struct ttm_buffer_object *bo,
 		bool lazy, bool interruptible, bool no_wait)
 {
-	struct ttm_bo_driver *driver = bo->bdev->driver;
-	void *sync_obj;
-	int ret = 0;
-
-	lockdep_assert_held(&bo->resv->lock.base);
+	struct reservation_object_list *fobj;
+	struct reservation_object *resv;
+	struct fence *excl;
+	long timeout = 15 * HZ;
+	int i;
 
-	if (likely(bo->sync_obj == NULL))
-		return 0;
+	resv = bo->resv;
+	fobj = reservation_object_get_list(resv);
+	excl = reservation_object_get_excl(resv);
+	if (excl) {
+		if (!fence_is_signaled(excl)) {
+			if (no_wait)
+				return -EBUSY;
 
-	if (bo->sync_obj) {
-		if (driver->sync_obj_signaled(bo->sync_obj)) {
-			driver->sync_obj_unref(&bo->sync_obj);
-			clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
-			return 0;
+			timeout = fence_wait_timeout(excl,
+						     interruptible, timeout);
 		}
+	}
 
-		if (no_wait)
-			return -EBUSY;
+	for (i = 0; fobj && timeout > 0 && i < fobj->shared_count; ++i) {
+		struct fence *fence;
+		fence = rcu_dereference_protected(fobj->shared[i],
+						reservation_object_held(resv));
 
-		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-		ret = driver->sync_obj_wait(sync_obj,
-					    lazy, interruptible);
+		if (!fence_is_signaled(fence)) {
+			if (no_wait)
+				return -EBUSY;
 
-		if (likely(ret == 0)) {
-			clear_bit(TTM_BO_PRIV_FLAG_MOVING,
-				  &bo->priv_flags);
-			driver->sync_obj_unref(&bo->sync_obj);
+			timeout = fence_wait_timeout(fence,
+						     interruptible, timeout);
 		}
-		driver->sync_obj_unref(&sync_obj);
 	}
-	return ret;
+
+	if (timeout < 0)
+		return timeout;
+
+	if (timeout == 0)
+		return -EBUSY;
+
+	reservation_object_add_excl_fence(resv, NULL);
+	clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
+	return 0;
 }
 EXPORT_SYMBOL(ttm_bo_wait);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 495aebf0f9c3..824af90cbe31 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -37,6 +37,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/module.h>
+#include <linux/reservation.h>
 
 void ttm_bo_free_old_node(struct ttm_buffer_object *bo)
 {
@@ -444,8 +445,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 				      struct ttm_buffer_object **new_obj)
 {
 	struct ttm_buffer_object *fbo;
-	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_driver *driver = bdev->driver;
 	int ret;
 
 	fbo = kmalloc(sizeof(*fbo), GFP_KERNEL);
@@ -466,10 +465,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	drm_vma_node_reset(&fbo->vma_node);
 	atomic_set(&fbo->cpu_writers, 0);
 
-	if (bo->sync_obj)
-		fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj);
-	else
-		fbo->sync_obj = NULL;
 	kref_init(&fbo->list_kref);
 	kref_init(&fbo->kref);
 	fbo->destroy = &ttm_transfered_destroy;
@@ -642,28 +637,20 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map)
 EXPORT_SYMBOL(ttm_bo_kunmap);
 
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
-			      void *sync_obj,
+			      struct fence *fence,
 			      bool evict,
 			      bool no_wait_gpu,
 			      struct ttm_mem_reg *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_driver *driver = bdev->driver;
 	struct ttm_mem_type_manager *man = &bdev->man[new_mem->mem_type];
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	int ret;
 	struct ttm_buffer_object *ghost_obj;
-	void *tmp_obj = NULL;
 
-	if (bo->sync_obj) {
-		tmp_obj = bo->sync_obj;
-		bo->sync_obj = NULL;
-	}
-	bo->sync_obj = driver->sync_obj_ref(sync_obj);
+	reservation_object_add_excl_fence(bo->resv, fence);
 	if (evict) {
 		ret = ttm_bo_wait(bo, false, false, false);
-		if (tmp_obj)
-			driver->sync_obj_unref(&tmp_obj);
 		if (ret)
 			return ret;
 
@@ -684,13 +671,13 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		 */
 
 		set_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
-		if (tmp_obj)
-			driver->sync_obj_unref(&tmp_obj);
 
 		ret = ttm_buffer_object_transfer(bo, &ghost_obj);
 		if (ret)
 			return ret;
 
+		reservation_object_add_excl_fence(ghost_obj->resv, fence);
+
 		/**
 		 * If we're not moving to fixed memory, the TTM object
 		 * needs to stay alive. Otherwhise hang it on the ghost
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 108730e9147b..adafc0f8ec06 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -163,7 +163,7 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 EXPORT_SYMBOL(ttm_eu_reserve_buffers);
 
 void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
-				 struct list_head *list, void *sync_obj)
+				 struct list_head *list, struct fence *fence)
 {
 	struct ttm_validate_buffer *entry;
 	struct ttm_buffer_object *bo;
@@ -183,18 +183,12 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 
 	list_for_each_entry(entry, list, head) {
 		bo = entry->bo;
-		entry->old_sync_obj = bo->sync_obj;
-		bo->sync_obj = driver->sync_obj_ref(sync_obj);
+		reservation_object_add_excl_fence(bo->resv, fence);
 		ttm_bo_add_to_lru(bo);
 		__ttm_bo_unreserve(bo);
 	}
 	spin_unlock(&glob->lru_lock);
 	if (ticket)
 		ww_acquire_fini(ticket);
-
-	list_for_each_entry(entry, list, head) {
-		if (entry->old_sync_obj)
-			driver->sync_obj_unref(&entry->old_sync_obj);
-	}
 }
 EXPORT_SYMBOL(ttm_eu_fence_buffer_objects);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
index 4a449b2528a2..cff2bf9db9d2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
@@ -801,41 +801,6 @@ static int vmw_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
 	return 0;
 }
 
-/**
- * FIXME: We're using the old vmware polling method to sync.
- * Do this with fences instead.
- */
-
-static void *vmw_sync_obj_ref(void *sync_obj)
-{
-
-	return (void *)
-		vmw_fence_obj_reference((struct vmw_fence_obj *) sync_obj);
-}
-
-static void vmw_sync_obj_unref(void **sync_obj)
-{
-	vmw_fence_obj_unreference((struct vmw_fence_obj **) sync_obj);
-}
-
-static int vmw_sync_obj_flush(void *sync_obj)
-{
-	vmw_fence_obj_flush((struct vmw_fence_obj *) sync_obj);
-	return 0;
-}
-
-static bool vmw_sync_obj_signaled(void *sync_obj)
-{
-	return vmw_fence_obj_signaled((struct vmw_fence_obj *) sync_obj);
-}
-
-static int vmw_sync_obj_wait(void *sync_obj, bool lazy, bool interruptible)
-{
-	return vmw_fence_obj_wait((struct vmw_fence_obj *) sync_obj,
-				  lazy, interruptible,
-				  VMW_FENCE_WAIT_TIMEOUT);
-}
-
 /**
  * vmw_move_notify - TTM move_notify_callback
  *
@@ -873,11 +838,6 @@ struct ttm_bo_driver vmw_bo_driver = {
 	.evict_flags = vmw_evict_flags,
 	.move = NULL,
 	.verify_access = vmw_verify_access,
-	.sync_obj_signaled = vmw_sync_obj_signaled,
-	.sync_obj_wait = vmw_sync_obj_wait,
-	.sync_obj_flush = vmw_sync_obj_flush,
-	.sync_obj_unref = vmw_sync_obj_unref,
-	.sync_obj_ref = vmw_sync_obj_ref,
 	.move_notify = vmw_move_notify,
 	.swap_notify = vmw_swap_notify,
 	.fault_reserve_notify = &vmw_ttm_fault_reserve_notify,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 67aebdb13b8c..98d5afd9a9df 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -1420,22 +1420,16 @@ void vmw_fence_single_bo(struct ttm_buffer_object *bo,
 			 struct vmw_fence_obj *fence)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct vmw_fence_obj *old_fence_obj;
+
 	struct vmw_private *dev_priv =
 		container_of(bdev, struct vmw_private, bdev);
 
 	if (fence == NULL) {
 		vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
+		fence_put(&fence->base);
 	} else
-		vmw_fence_obj_reference(fence);
-
-	reservation_object_add_excl_fence(bo->resv, &fence->base);
-
-	old_fence_obj = bo->sync_obj;
-	bo->sync_obj = fence;
-
-	if (old_fence_obj)
-		vmw_fence_obj_unreference(&old_fence_obj);
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
 }
 
 /**
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 5805f4a49478..70b44917c368 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -173,7 +173,6 @@ struct ttm_tt;
  * @lru: List head for the lru list.
  * @ddestroy: List head for the delayed destroy list.
  * @swap: List head for swap LRU list.
- * @sync_obj: Pointer to a synchronization object.
  * @priv_flags: Flags describing buffer object internal state.
  * @vma_node: Address space manager node.
  * @offset: The current GPU offset, which can have different meanings
@@ -240,7 +239,6 @@ struct ttm_buffer_object {
 	 * Members protected by a bo reservation.
 	 */
 
-	void *sync_obj;
 	unsigned long priv_flags;
 
 	struct drm_vma_offset_node vma_node;
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index e1ee141e26cc..142d752fc450 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -312,11 +312,6 @@ struct ttm_mem_type_manager {
  * @move: Callback for a driver to hook in accelerated functions to
  * move a buffer.
  * If set to NULL, a potentially slow memcpy() move is used.
- * @sync_obj_signaled: See ttm_fence_api.h
- * @sync_obj_wait: See ttm_fence_api.h
- * @sync_obj_flush: See ttm_fence_api.h
- * @sync_obj_unref: See ttm_fence_api.h
- * @sync_obj_ref: See ttm_fence_api.h
  */
 
 struct ttm_bo_driver {
@@ -418,23 +413,6 @@ struct ttm_bo_driver {
 	int (*verify_access) (struct ttm_buffer_object *bo,
 			      struct file *filp);
 
-	/**
-	 * In case a driver writer dislikes the TTM fence objects,
-	 * the driver writer can replace those with sync objects of
-	 * his / her own. If it turns out that no driver writer is
-	 * using these. I suggest we remove these hooks and plug in
-	 * fences directly. The bo driver needs the following functionality:
-	 * See the corresponding functions in the fence object API
-	 * documentation.
-	 */
-
-	bool (*sync_obj_signaled) (void *sync_obj);
-	int (*sync_obj_wait) (void *sync_obj,
-			      bool lazy, bool interruptible);
-	int (*sync_obj_flush) (void *sync_obj);
-	void (*sync_obj_unref) (void **sync_obj);
-	void *(*sync_obj_ref) (void *sync_obj);
-
 	/* hook to notify driver about a driver move so it
 	 * can do tiling things */
 	void (*move_notify)(struct ttm_buffer_object *bo,
@@ -1022,7 +1000,7 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  * ttm_bo_move_accel_cleanup.
  *
  * @bo: A pointer to a struct ttm_buffer_object.
- * @sync_obj: A sync object that signals when moving is complete.
+ * @fence: A fence object that signals when moving is complete.
  * @evict: This is an evict move. Don't return until the buffer is idle.
  * @no_wait_gpu: Return immediately if the GPU is busy.
  * @new_mem: struct ttm_mem_reg indicating where to move.
@@ -1036,7 +1014,7 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  */
 
 extern int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
-				     void *sync_obj,
+				     struct fence *fence,
 				     bool evict, bool no_wait_gpu,
 				     struct ttm_mem_reg *new_mem);
 /**
diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index 8490cb8ee0d8..ff11a424f752 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -39,16 +39,11 @@
  *
  * @head:           list head for thread-private list.
  * @bo:             refcounted buffer object pointer.
- * @reserved:       Indicates whether @bo has been reserved for validation.
- * @removed:        Indicates whether @bo has been removed from lru lists.
- * @put_count:      Number of outstanding references on bo::list_kref.
- * @old_sync_obj:   Pointer to a sync object about to be unreferenced
  */
 
 struct ttm_validate_buffer {
 	struct list_head head;
 	struct ttm_buffer_object *bo;
-	void *old_sync_obj;
 };
 
 /**
@@ -100,7 +95,7 @@ extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
  *
  * @ticket:      ww_acquire_ctx from reserve call
  * @list:        thread private list of ttm_validate_buffer structs.
- * @sync_obj:    The new sync object for the buffers.
+ * @fence:       The new exclusive fence for the buffers.
  *
  * This function should be called when command submission is complete, and
  * it will add a new sync object to bos pointed to by entries on @list.
@@ -109,6 +104,7 @@ extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
  */
 
 extern void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
-					struct list_head *list, void *sync_obj);
+					struct list_head *list,
+					struct fence *fence);
 
 #endif
-- 
cgit v1.2.3


From 30766f4c2d60dd2a3fc67b7114174c417f43f4c6 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 5 Aug 2014 20:02:42 +0200
Subject: netfilter: nat: move specific NAT IPv4 to core

Move the specific NAT IPv4 core functions that are called from the
hooks from iptable_nat.c to nf_nat_l3proto_ipv4.c. This prepares the
ground to allow iptables and nft to use the same NAT engine code that
comes in a follow up patch.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l3proto.h   |  38 +++++
 net/ipv4/netfilter/iptable_nat.c         | 233 +++++--------------------------
 net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 199 ++++++++++++++++++++++++++
 3 files changed, 271 insertions(+), 199 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index 5a2919b2e09a..bc2d51574489 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -42,6 +42,44 @@ const struct nf_nat_l3proto *__nf_nat_l3proto_find(u8 l3proto);
 int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
 				  enum ip_conntrack_info ctinfo,
 				  unsigned int hooknum);
+
+unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
+unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			     const struct net_device *in,
+			     const struct net_device *out,
+			     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						      struct sk_buff *skb,
+						      const struct net_device *in,
+						      const struct net_device *out,
+						      struct nf_conn *ct));
+
+unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
+				  struct sk_buff *skb,
+				  const struct net_device *in,
+				  const struct net_device *out,
+				  unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+							   struct sk_buff *skb,
+							   const struct net_device *in,
+							   const struct net_device *out,
+							   struct nf_conn *ct));
+
+unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
 int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
 				    enum ip_conntrack_info ctinfo,
 				    unsigned int hooknum, unsigned int hdrlen);
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index f1787c04a4dd..6b67d7e9a75d 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -28,222 +28,57 @@ static const struct xt_table nf_nat_ipv4_table = {
 	.af		= NFPROTO_IPV4,
 };
 
-static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
-{
-	/* Force range to this IP; let proto decide mapping for
-	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
-	 */
-	struct nf_nat_range range;
-
-	range.flags = 0;
-	pr_debug("Allocating NULL binding for %p (%pI4)\n", ct,
-		 HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip :
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
-
-	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
-}
-
-static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
-				     const struct net_device *in,
-				     const struct net_device *out,
-				     struct nf_conn *ct)
+static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
-	unsigned int ret;
 
-	ret = ipt_do_table(skb, hooknum, in, out, net->ipv4.nat_table);
-	if (ret == NF_ACCEPT) {
-		if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
-			ret = alloc_null_binding(ct, hooknum);
-	}
-	return ret;
+	return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.nat_table);
 }
 
-static unsigned int
-nf_nat_ipv4_fn(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_fn(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
 {
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn_nat *nat;
-	/* maniptype == SRC for postrouting. */
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
-
-	/* We never see fragments: conntrack defrags on pre-routing
-	 * and local-out, and nf_nat_out protects post-routing.
-	 */
-	NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
-
-	ct = nf_ct_get(skb, &ctinfo);
-	/* Can't track?  It's not due to stress, or conntrack would
-	 * have dropped it.  Hence it's the user's responsibilty to
-	 * packet filter it out, or implement conntrack/NAT for that
-	 * protocol. 8) --RR
-	 */
-	if (!ct)
-		return NF_ACCEPT;
-
-	/* Don't try to NAT if this packet is not conntracked */
-	if (nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
-		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   ops->hooknum))
-				return NF_DROP;
-			else
-				return NF_ACCEPT;
-		}
-		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
-	case IP_CT_NEW:
-		/* Seen it before?  This can happen for loopback, retrans,
-		 * or local packets.
-		 */
-		if (!nf_nat_initialized(ct, maniptype)) {
-			unsigned int ret;
-
-			ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
-			if (ret != NF_ACCEPT)
-				return ret;
-		} else {
-			pr_debug("Already setup manip %s for ct %p\n",
-				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
-				 ct);
-			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-				goto oif_changed;
-		}
-		break;
-
-	default:
-		/* ESTABLISHED */
-		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
-			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-			goto oif_changed;
-	}
-
-	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
-
-oif_changed:
-	nf_ct_kill_acct(ct, ctinfo, skb);
-	return NF_DROP;
+	return nf_nat_ipv4_fn(ops, skb, in, out, iptable_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv4_in(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_in(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
 {
-	unsigned int ret;
-	__be32 daddr = ip_hdr(skb)->daddr;
-
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    daddr != ip_hdr(skb)->daddr)
-		skb_dst_drop(skb);
-
-	return ret;
+	return nf_nat_ipv4_in(ops, skb, in, out, iptable_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv4_out(const struct nf_hook_ops *ops,
-		struct sk_buff *skb,
-		const struct net_device *in,
-		const struct net_device *out,
-		int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_out(const struct nf_hook_ops *ops,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 int (*okfn)(struct sk_buff *))
 {
-#ifdef CONFIG_XFRM
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	int err;
-#endif
-	unsigned int ret;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct iphdr) ||
-	    ip_hdrlen(skb) < sizeof(struct iphdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
-#ifdef CONFIG_XFRM
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if ((ct->tuplehash[dir].tuple.src.u3.ip !=
-		     ct->tuplehash[!dir].tuple.dst.u3.ip) ||
-		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
-		     ct->tuplehash[dir].tuple.src.u.all !=
-		     ct->tuplehash[!dir].tuple.dst.u.all)) {
-			err = nf_xfrm_me_harder(skb, AF_INET);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-	}
-#endif
-	return ret;
+	return nf_nat_ipv4_out(ops, skb, in, out, iptable_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
-		     struct sk_buff *skb,
-		     const struct net_device *in,
-		     const struct net_device *out,
-		     int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
+					      struct sk_buff *skb,
+					      const struct net_device *in,
+					      const struct net_device *out,
+					      int (*okfn)(struct sk_buff *))
 {
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	unsigned int ret;
-	int err;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct iphdr) ||
-	    ip_hdrlen(skb) < sizeof(struct iphdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
-		    ct->tuplehash[!dir].tuple.src.u3.ip) {
-			err = ip_route_me_harder(skb, RTN_UNSPEC);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#ifdef CONFIG_XFRM
-		else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
-			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
-			 ct->tuplehash[dir].tuple.dst.u.all !=
-			 ct->tuplehash[!dir].tuple.src.u.all) {
-			err = nf_xfrm_me_harder(skb, AF_INET);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#endif
-	}
-	return ret;
+	return nf_nat_ipv4_local_fn(ops, skb, in, out, iptable_nat_do_chain);
 }
 
 static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv4_in,
+		.hook		= iptable_nat_ipv4_in,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_PRE_ROUTING,
@@ -251,7 +86,7 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv4_out,
+		.hook		= iptable_nat_ipv4_out,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_POST_ROUTING,
@@ -259,7 +94,7 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv4_local_fn,
+		.hook		= iptable_nat_ipv4_local_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_LOCAL_OUT,
@@ -267,7 +102,7 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv4_fn,
+		.hook		= iptable_nat_ipv4_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_LOCAL_IN,
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 14f5ccd06337..fc37711e11f3 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -254,6 +254,205 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);
 
+unsigned int
+nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	       const struct net_device *in, const struct net_device *out,
+	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					struct nf_conn *ct))
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn_nat *nat;
+	/* maniptype == SRC for postrouting. */
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+
+	/* We never see fragments: conntrack defrags on pre-routing
+	 * and local-out, and nf_nat_out protects post-routing.
+	 */
+	NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
+
+	ct = nf_ct_get(skb, &ctinfo);
+	/* Can't track?  It's not due to stress, or conntrack would
+	 * have dropped it.  Hence it's the user's responsibilty to
+	 * packet filter it out, or implement conntrack/NAT for that
+	 * protocol. 8) --RR
+	 */
+	if (!ct)
+		return NF_ACCEPT;
+
+	/* Don't try to NAT if this packet is not conntracked */
+	if (nf_ct_is_untracked(ct))
+		return NF_ACCEPT;
+
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED_REPLY:
+		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
+			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
+							   ops->hooknum))
+				return NF_DROP;
+			else
+				return NF_ACCEPT;
+		}
+		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+	case IP_CT_NEW:
+		/* Seen it before?  This can happen for loopback, retrans,
+		 * or local packets.
+		 */
+		if (!nf_nat_initialized(ct, maniptype)) {
+			unsigned int ret;
+
+			ret = do_chain(ops, skb, in, out, ct);
+			if (ret != NF_ACCEPT)
+				return ret;
+
+			if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum)))
+				break;
+
+			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+			if (ret != NF_ACCEPT)
+				return ret;
+		} else {
+			pr_debug("Already setup manip %s for ct %p\n",
+				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
+				 ct);
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+				goto oif_changed;
+		}
+		break;
+
+	default:
+		/* ESTABLISHED */
+		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
+			     ctinfo == IP_CT_ESTABLISHED_REPLY);
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+			goto oif_changed;
+	}
+
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+
+oif_changed:
+	nf_ct_kill_acct(ct, ctinfo, skb);
+	return NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn);
+
+unsigned int
+nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	       const struct net_device *in, const struct net_device *out,
+	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 struct nf_conn *ct))
+{
+	unsigned int ret;
+	__be32 daddr = ip_hdr(skb)->daddr;
+
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    daddr != ip_hdr(skb)->daddr)
+		skb_dst_drop(skb);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_in);
+
+unsigned int
+nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+		const struct net_device *in, const struct net_device *out,
+		unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					  struct sk_buff *skb,
+					  const struct net_device *in,
+					  const struct net_device *out,
+					  struct nf_conn *ct))
+{
+#ifdef CONFIG_XFRM
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	int err;
+#endif
+	unsigned int ret;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct iphdr) ||
+	    ip_hdrlen(skb) < sizeof(struct iphdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+#ifdef CONFIG_XFRM
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if ((ct->tuplehash[dir].tuple.src.u3.ip !=
+		     ct->tuplehash[!dir].tuple.dst.u3.ip) ||
+		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
+		     ct->tuplehash[dir].tuple.src.u.all !=
+		     ct->tuplehash[!dir].tuple.dst.u.all)) {
+			err = nf_xfrm_me_harder(skb, AF_INET);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+	}
+#endif
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_out);
+
+unsigned int
+nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+		     const struct net_device *in, const struct net_device *out,
+		     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					       struct sk_buff *skb,
+					       const struct net_device *in,
+					       const struct net_device *out,
+					       struct nf_conn *ct))
+{
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned int ret;
+	int err;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct iphdr) ||
+	    ip_hdrlen(skb) < sizeof(struct iphdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
+		    ct->tuplehash[!dir].tuple.src.u3.ip) {
+			err = ip_route_me_harder(skb, RTN_UNSPEC);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#ifdef CONFIG_XFRM
+		else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
+			 ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all) {
+			err = nf_xfrm_me_harder(skb, AF_INET);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#endif
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_local_fn);
+
 static int __init nf_nat_l3proto_ipv4_init(void)
 {
 	int err;
-- 
cgit v1.2.3


From 9067359faf890b3a18ab38c792d458fba77b32b4 Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Tue, 2 Sep 2014 02:03:12 -0700
Subject: Revert "leds: convert blink timer to workqueue"

This reverts commit 8b37e1bef5a6b60e949e28a4db3006e4b00bd758.

It's broken as it changes led_blink_set() in a way that it can now sleep
(while synchronously waiting for workqueue to be cancelled). That's a
problem, because it's possible that this function gets called from atomic
context (tpt_trig_timer() takes a readlock and thus disables preemption).

This has been brought up 3 weeks ago already [1] but no proper fix has
materialized, and I keep seeing the problem since 3.17-rc1.

[1] https://lkml.org/lkml/2014/8/16/128

 BUG: sleeping function called from invalid context at kernel/workqueue.c:2650
 in_atomic(): 1, irqs_disabled(): 0, pid: 2335, name: wpa_supplicant
 5 locks held by wpa_supplicant/2335:
  #0:  (rtnl_mutex){+.+.+.}, at: [<ffffffff814c7c92>] rtnl_lock+0x12/0x20
  #1:  (&wdev->mtx){+.+.+.}, at: [<ffffffffc06e649c>] cfg80211_mgd_wext_siwessid+0x5c/0x180 [cfg80211]
  #2:  (&local->mtx){+.+.+.}, at: [<ffffffffc0817dea>] ieee80211_prep_connection+0x17a/0x9a0 [mac80211]
  #3:  (&local->chanctx_mtx){+.+.+.}, at: [<ffffffffc08081ed>] ieee80211_vif_use_channel+0x5d/0x2a0 [mac80211]
  #4:  (&trig->leddev_list_lock){.+.+..}, at: [<ffffffffc081e68c>] tpt_trig_timer+0xec/0x170 [mac80211]
 CPU: 0 PID: 2335 Comm: wpa_supplicant Not tainted 3.17.0-rc3 #1
 Hardware name: LENOVO 7470BN2/7470BN2, BIOS 6DET38WW (2.02 ) 12/19/2008
  ffff8800360b5a50 ffff8800751f76d8 ffffffff8159e97f ffff8800360b5a30
  ffff8800751f76e8 ffffffff810739a5 ffff8800751f77b0 ffffffff8106862f
  ffffffff810685d0 0aa2209200000000 ffff880000000004 ffff8800361c59d0
 Call Trace:
  [<ffffffff8159e97f>] dump_stack+0x4d/0x66
  [<ffffffff810739a5>] __might_sleep+0xe5/0x120
  [<ffffffff8106862f>] flush_work+0x5f/0x270
  [<ffffffff810685d0>] ? mod_delayed_work_on+0x80/0x80
  [<ffffffff810945ca>] ? mark_held_locks+0x6a/0x90
  [<ffffffff81068a5f>] ? __cancel_work_timer+0x6f/0x100
  [<ffffffff810946ed>] ? trace_hardirqs_on_caller+0xfd/0x1c0
  [<ffffffff81068a6b>] __cancel_work_timer+0x7b/0x100
  [<ffffffff81068b0e>] cancel_delayed_work_sync+0xe/0x10
  [<ffffffff8147cf3b>] led_blink_set+0x1b/0x40
  [<ffffffffc081e6b0>] tpt_trig_timer+0x110/0x170 [mac80211]
  [<ffffffffc081ecdd>] ieee80211_mod_tpt_led_trig+0x9d/0x160 [mac80211]
  [<ffffffffc07e4278>] __ieee80211_recalc_idle+0x98/0x140 [mac80211]
  [<ffffffffc07e59ce>] ieee80211_idle_off+0xe/0x10 [mac80211]
  [<ffffffffc0804e5b>] ieee80211_add_chanctx+0x3b/0x220 [mac80211]
  [<ffffffffc08062e4>] ieee80211_new_chanctx+0x44/0xf0 [mac80211]
  [<ffffffffc080838a>] ieee80211_vif_use_channel+0x1fa/0x2a0 [mac80211]
  [<ffffffffc0817df8>] ieee80211_prep_connection+0x188/0x9a0 [mac80211]
  [<ffffffffc081c246>] ieee80211_mgd_auth+0x256/0x2e0 [mac80211]
  [<ffffffffc07eab33>] ieee80211_auth+0x13/0x20 [mac80211]
  [<ffffffffc06cb006>] cfg80211_mlme_auth+0x106/0x270 [cfg80211]
  [<ffffffffc06ce085>] cfg80211_conn_do_work+0x155/0x3b0 [cfg80211]
  [<ffffffffc06cf670>] cfg80211_connect+0x3f0/0x540 [cfg80211]
  [<ffffffffc06e6148>] cfg80211_mgd_wext_connect+0x158/0x1f0 [cfg80211]
  [<ffffffffc06e651e>] cfg80211_mgd_wext_siwessid+0xde/0x180 [cfg80211]
  [<ffffffffc06e36c0>] ? cfg80211_wext_giwessid+0x50/0x50 [cfg80211]
  [<ffffffffc06e36dd>] cfg80211_wext_siwessid+0x1d/0x40 [cfg80211]
  [<ffffffff81584d0c>] ioctl_standard_iw_point+0x14c/0x3e0
  [<ffffffff810946ed>] ? trace_hardirqs_on_caller+0xfd/0x1c0
  [<ffffffff8158502a>] ioctl_standard_call+0x8a/0xd0
  [<ffffffff81584fa0>] ? ioctl_standard_iw_point+0x3e0/0x3e0
  [<ffffffff81584b76>] wireless_process_ioctl.constprop.10+0xb6/0x100
  [<ffffffff8158521d>] wext_handle_ioctl+0x5d/0xb0
  [<ffffffff814cfb29>] dev_ioctl+0x329/0x620
  [<ffffffff810946ed>] ? trace_hardirqs_on_caller+0xfd/0x1c0
  [<ffffffff8149c7f2>] sock_ioctl+0x142/0x2e0
  [<ffffffff811b0140>] do_vfs_ioctl+0x300/0x520
  [<ffffffff815a67fb>] ? sysret_check+0x1b/0x56
  [<ffffffff810946ed>] ? trace_hardirqs_on_caller+0xfd/0x1c0
  [<ffffffff811b03e1>] SyS_ioctl+0x81/0xa0
  [<ffffffff815a67d6>] system_call_fastpath+0x1a/0x1f
 wlan0: send auth to 00:0b:6b:3c:8c:e4 (try 1/3)
 wlan0: authenticated
 wlan0: associate with 00:0b:6b:3c:8c:e4 (try 1/3)
 wlan0: RX AssocResp from 00:0b:6b:3c:8c:e4 (capab=0x431 status=0 aid=2)
 wlan0: associated
 IPv6: ADDRCONF(NETDEV_CHANGE): wlan0: link becomes ready
 cfg80211: Calling CRDA for country: NA
 wlan0: Limiting TX power to 27 (27 - 0) dBm as advertised by 00:0b:6b:3c:8c:e4

 =================================
 [ INFO: inconsistent lock state ]
 3.17.0-rc3 #1 Not tainted
 ---------------------------------
 inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
 swapper/0/0 [HC0[0]:SC1[1]:HE1:SE0] takes:
  ((&(&led_cdev->blink_work)->work)){+.?...}, at: [<ffffffff810685d0>] flush_work+0x0/0x270
 {SOFTIRQ-ON-W} state was registered at:
   [<ffffffff81094dbe>] __lock_acquire+0x30e/0x1a30
   [<ffffffff81096c81>] lock_acquire+0x91/0x110
   [<ffffffff81068608>] flush_work+0x38/0x270
   [<ffffffff81068a6b>] __cancel_work_timer+0x7b/0x100
   [<ffffffff81068b0e>] cancel_delayed_work_sync+0xe/0x10
   [<ffffffff8147cf3b>] led_blink_set+0x1b/0x40
   [<ffffffffc081e6b0>] tpt_trig_timer+0x110/0x170 [mac80211]
   [<ffffffffc081ecdd>] ieee80211_mod_tpt_led_trig+0x9d/0x160 [mac80211]
   [<ffffffffc07e4278>] __ieee80211_recalc_idle+0x98/0x140 [mac80211]
   [<ffffffffc07e59ce>] ieee80211_idle_off+0xe/0x10 [mac80211]
   [<ffffffffc0804e5b>] ieee80211_add_chanctx+0x3b/0x220 [mac80211]
   [<ffffffffc08062e4>] ieee80211_new_chanctx+0x44/0xf0 [mac80211]
   [<ffffffffc080838a>] ieee80211_vif_use_channel+0x1fa/0x2a0 [mac80211]
   [<ffffffffc0817df8>] ieee80211_prep_connection+0x188/0x9a0 [mac80211]
   [<ffffffffc081c246>] ieee80211_mgd_auth+0x256/0x2e0 [mac80211]
   [<ffffffffc07eab33>] ieee80211_auth+0x13/0x20 [mac80211]
   [<ffffffffc06cb006>] cfg80211_mlme_auth+0x106/0x270 [cfg80211]
   [<ffffffffc06ce085>] cfg80211_conn_do_work+0x155/0x3b0 [cfg80211]
   [<ffffffffc06cf670>] cfg80211_connect+0x3f0/0x540 [cfg80211]
   [<ffffffffc06e6148>] cfg80211_mgd_wext_connect+0x158/0x1f0 [cfg80211]
   [<ffffffffc06e651e>] cfg80211_mgd_wext_siwessid+0xde/0x180 [cfg80211]
   [<ffffffffc06e36dd>] cfg80211_wext_siwessid+0x1d/0x40 [cfg80211]
   [<ffffffff81584d0c>] ioctl_standard_iw_point+0x14c/0x3e0
   [<ffffffff8158502a>] ioctl_standard_call+0x8a/0xd0
   [<ffffffff81584b76>] wireless_process_ioctl.constprop.10+0xb6/0x100
   [<ffffffff8158521d>] wext_handle_ioctl+0x5d/0xb0
   [<ffffffff814cfb29>] dev_ioctl+0x329/0x620
   [<ffffffff8149c7f2>] sock_ioctl+0x142/0x2e0
   [<ffffffff811b0140>] do_vfs_ioctl+0x300/0x520
   [<ffffffff811b03e1>] SyS_ioctl+0x81/0xa0
   [<ffffffff815a67d6>] system_call_fastpath+0x1a/0x1f
 irq event stamp: 493416
 hardirqs last  enabled at (493416): [<ffffffff81068a5f>] __cancel_work_timer+0x6f/0x100
 hardirqs last disabled at (493415): [<ffffffff81067e9f>] try_to_grab_pending+0x1f/0x160
 softirqs last  enabled at (493408): [<ffffffff81053ced>] _local_bh_enable+0x1d/0x50
 softirqs last disabled at (493409): [<ffffffff81054c75>] irq_exit+0xa5/0xb0

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock((&(&led_cdev->blink_work)->work));
   <Interrupt>
     lock((&(&led_cdev->blink_work)->work));

  *** DEADLOCK ***

 2 locks held by swapper/0/0:
  #0:  (((&tpt_trig->timer))){+.-...}, at: [<ffffffff810b4c50>] call_timer_fn+0x0/0x180
  #1:  (&trig->leddev_list_lock){.+.?..}, at: [<ffffffffc081e68c>] tpt_trig_timer+0xec/0x170 [mac80211]

 stack backtrace:
 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.17.0-rc3 #1
 Hardware name: LENOVO 7470BN2/7470BN2, BIOS 6DET38WW (2.02 ) 12/19/2008
  ffffffff8246eb30 ffff88007c203b00 ffffffff8159e97f ffffffff81a194c0
  ffff88007c203b50 ffffffff81599c29 0000000000000001 ffffffff00000001
  ffff880000000000 0000000000000006 ffffffff81a194c0 ffffffff81093ad0
 Call Trace:
  <IRQ>  [<ffffffff8159e97f>] dump_stack+0x4d/0x66
  [<ffffffff81599c29>] print_usage_bug+0x1f4/0x205
  [<ffffffff81093ad0>] ? check_usage_backwards+0x140/0x140
  [<ffffffff810944d3>] mark_lock+0x223/0x2b0
  [<ffffffff81094d60>] __lock_acquire+0x2b0/0x1a30
  [<ffffffff81096c81>] lock_acquire+0x91/0x110
  [<ffffffff810685d0>] ? mod_delayed_work_on+0x80/0x80
  [<ffffffffc081e5a0>] ? __ieee80211_get_rx_led_name+0x10/0x10 [mac80211]
  [<ffffffff81068608>] flush_work+0x38/0x270
  [<ffffffff810685d0>] ? mod_delayed_work_on+0x80/0x80
  [<ffffffff810945ca>] ? mark_held_locks+0x6a/0x90
  [<ffffffff81068a5f>] ? __cancel_work_timer+0x6f/0x100
  [<ffffffffc081e5a0>] ? __ieee80211_get_rx_led_name+0x10/0x10 [mac80211]
  [<ffffffff8109469d>] ? trace_hardirqs_on_caller+0xad/0x1c0
  [<ffffffffc081e5a0>] ? __ieee80211_get_rx_led_name+0x10/0x10 [mac80211]
  [<ffffffff81068a6b>] __cancel_work_timer+0x7b/0x100
  [<ffffffff81068b0e>] cancel_delayed_work_sync+0xe/0x10
  [<ffffffff8147cf3b>] led_blink_set+0x1b/0x40
  [<ffffffffc081e6b0>] tpt_trig_timer+0x110/0x170 [mac80211]
  [<ffffffff810b4cc5>] call_timer_fn+0x75/0x180
  [<ffffffff810b4c50>] ? process_timeout+0x10/0x10
  [<ffffffffc081e5a0>] ? __ieee80211_get_rx_led_name+0x10/0x10 [mac80211]
  [<ffffffff810b50ac>] run_timer_softirq+0x1fc/0x2f0
  [<ffffffff81054805>] __do_softirq+0x115/0x2e0
  [<ffffffff81054c75>] irq_exit+0xa5/0xb0
  [<ffffffff810049b3>] do_IRQ+0x53/0xf0
  [<ffffffff815a74af>] common_interrupt+0x6f/0x6f
  <EOI>  [<ffffffff8147b56e>] ? cpuidle_enter_state+0x6e/0x180
  [<ffffffff8147b732>] cpuidle_enter+0x12/0x20
  [<ffffffff8108bba0>] cpu_startup_entry+0x330/0x360
  [<ffffffff8158fb51>] rest_init+0xc1/0xd0
  [<ffffffff8158fa90>] ? csum_partial_copy_generic+0x170/0x170
  [<ffffffff81af3ff2>] start_kernel+0x44f/0x45a
  [<ffffffff81af399c>] ? set_init_arg+0x53/0x53
  [<ffffffff81af35ad>] x86_64_start_reservations+0x2a/0x2c
  [<ffffffff81af36a0>] x86_64_start_kernel+0xf1/0xf4

Cc: Vincent Donnefort <vdonnefort@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 drivers/leds/led-class.c | 14 +++++++-------
 drivers/leds/led-core.c  | 11 +++++------
 include/linux/leds.h     |  3 ++-
 3 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 129729d35478..aa29198fca3e 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -15,10 +15,10 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/device.h>
+#include <linux/timer.h>
 #include <linux/err.h>
 #include <linux/ctype.h>
 #include <linux/leds.h>
-#include <linux/workqueue.h>
 #include "leds.h"
 
 static struct class *leds_class;
@@ -97,10 +97,9 @@ static const struct attribute_group *led_groups[] = {
 	NULL,
 };
 
-static void led_work_function(struct work_struct *ws)
+static void led_timer_function(unsigned long data)
 {
-	struct led_classdev *led_cdev =
-		container_of(ws, struct led_classdev, blink_work.work);
+	struct led_classdev *led_cdev = (void *)data;
 	unsigned long brightness;
 	unsigned long delay;
 
@@ -144,8 +143,7 @@ static void led_work_function(struct work_struct *ws)
 		}
 	}
 
-	queue_delayed_work(system_wq, &led_cdev->blink_work,
-			   msecs_to_jiffies(delay));
+	mod_timer(&led_cdev->blink_timer, jiffies + msecs_to_jiffies(delay));
 }
 
 static void set_brightness_delayed(struct work_struct *ws)
@@ -233,7 +231,9 @@ int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
 
 	INIT_WORK(&led_cdev->set_brightness_work, set_brightness_delayed);
 
-	INIT_DELAYED_WORK(&led_cdev->blink_work, led_work_function);
+	init_timer(&led_cdev->blink_timer);
+	led_cdev->blink_timer.function = led_timer_function;
+	led_cdev->blink_timer.data = (unsigned long)led_cdev;
 
 #ifdef CONFIG_LEDS_TRIGGERS
 	led_trigger_set_default(led_cdev);
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index 4bb116867b88..71b40d3bf776 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -16,7 +16,6 @@
 #include <linux/module.h>
 #include <linux/rwsem.h>
 #include <linux/leds.h>
-#include <linux/workqueue.h>
 #include "leds.h"
 
 DECLARE_RWSEM(leds_list_lock);
@@ -52,7 +51,7 @@ static void led_set_software_blink(struct led_classdev *led_cdev,
 		return;
 	}
 
-	queue_delayed_work(system_wq, &led_cdev->blink_work, 1);
+	mod_timer(&led_cdev->blink_timer, jiffies + 1);
 }
 
 
@@ -76,7 +75,7 @@ void led_blink_set(struct led_classdev *led_cdev,
 		   unsigned long *delay_on,
 		   unsigned long *delay_off)
 {
-	cancel_delayed_work_sync(&led_cdev->blink_work);
+	del_timer_sync(&led_cdev->blink_timer);
 
 	led_cdev->flags &= ~LED_BLINK_ONESHOT;
 	led_cdev->flags &= ~LED_BLINK_ONESHOT_STOP;
@@ -91,7 +90,7 @@ void led_blink_set_oneshot(struct led_classdev *led_cdev,
 			   int invert)
 {
 	if ((led_cdev->flags & LED_BLINK_ONESHOT) &&
-	     delayed_work_pending(&led_cdev->blink_work))
+	     timer_pending(&led_cdev->blink_timer))
 		return;
 
 	led_cdev->flags |= LED_BLINK_ONESHOT;
@@ -108,7 +107,7 @@ EXPORT_SYMBOL(led_blink_set_oneshot);
 
 void led_stop_software_blink(struct led_classdev *led_cdev)
 {
-	cancel_delayed_work_sync(&led_cdev->blink_work);
+	del_timer_sync(&led_cdev->blink_timer);
 	led_cdev->blink_delay_on = 0;
 	led_cdev->blink_delay_off = 0;
 }
@@ -117,7 +116,7 @@ EXPORT_SYMBOL_GPL(led_stop_software_blink);
 void led_set_brightness(struct led_classdev *led_cdev,
 			enum led_brightness brightness)
 {
-	/* delay brightness setting if need to stop soft-blink work */
+	/* delay brightness setting if need to stop soft-blink timer */
 	if (led_cdev->blink_delay_on || led_cdev->blink_delay_off) {
 		led_cdev->delayed_set_value = brightness;
 		schedule_work(&led_cdev->set_brightness_work);
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 6a599dce7f9d..e43686472197 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/rwsem.h>
+#include <linux/timer.h>
 #include <linux/workqueue.h>
 
 struct device;
@@ -68,7 +69,7 @@ struct led_classdev {
 	const char		*default_trigger;	/* Trigger to use */
 
 	unsigned long		 blink_delay_on, blink_delay_off;
-	struct delayed_work	 blink_work;
+	struct timer_list	 blink_timer;
 	int			 blink_brightness;
 
 	struct work_struct	set_brightness_work;
-- 
cgit v1.2.3


From 5835d96e9ce4efdba8c6cefffc2f1575925456de Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 2 Sep 2014 14:46:04 -0400
Subject: percpu: implement [__]alloc_percpu_gfp()

Now that pcpu_alloc_area() can allocate only from populated areas,
it's easy to add atomic allocation support to [__]alloc_percpu().
Update pcpu_alloc() so that it accepts @gfp and skips all the blocking
operations and allocates only from the populated areas if @gfp doesn't
contain GFP_KERNEL.  New interface functions [__]alloc_percpu_gfp()
are added.

While this means that atomic allocations are possible, this isn't
complete yet as there's no mechanism to ensure that certain amount of
populated areas is kept available and atomic allocations may keep
failing under certain conditions.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/percpu.h |  9 +++++--
 mm/percpu.c            | 64 ++++++++++++++++++++++++++++++--------------------
 2 files changed, 46 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 6f61b61b7996..d1b416da25ed 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -122,11 +122,16 @@ extern void __init setup_per_cpu_areas(void);
 #endif
 extern void __init percpu_init_late(void);
 
+extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp);
 extern void __percpu *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void __percpu *__pdata);
 extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
 
-#define alloc_percpu(type)	\
-	(typeof(type) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type))
+#define alloc_percpu_gfp(type, gfp)					\
+	(typeof(type) __percpu *)__alloc_percpu_gfp(sizeof(type),	\
+						__alignof__(type), gfp)
+#define alloc_percpu(type)						\
+	(typeof(type) __percpu *)__alloc_percpu(sizeof(type),		\
+						__alignof__(type))
 
 #endif /* __LINUX_PERCPU_H */
diff --git a/mm/percpu.c b/mm/percpu.c
index 577d84fb3002..c52b93117dc2 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -151,11 +151,6 @@ static struct pcpu_chunk *pcpu_first_chunk;
 static struct pcpu_chunk *pcpu_reserved_chunk;
 static int pcpu_reserved_chunk_limit;
 
-/*
- * Free path accesses and alters only the index data structures and can be
- * safely called from atomic context.  When memory needs to be returned to
- * the system, free path schedules reclaim_work.
- */
 static DEFINE_SPINLOCK(pcpu_lock);	/* all internal data structures */
 static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop */
 
@@ -727,20 +722,21 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  * @reserved: allocate from the reserved chunk if available
+ * @gfp: allocation flags
  *
- * Allocate percpu area of @size bytes aligned at @align.
- *
- * CONTEXT:
- * Does GFP_KERNEL allocation.
+ * Allocate percpu area of @size bytes aligned at @align.  If @gfp doesn't
+ * contain %GFP_KERNEL, the allocation is atomic.
  *
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
  */
-static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
+static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
+				 gfp_t gfp)
 {
 	static int warn_limit = 10;
 	struct pcpu_chunk *chunk;
 	const char *err;
+	bool is_atomic = !(gfp & GFP_KERNEL);
 	int slot, off, new_alloc, cpu, ret;
 	unsigned long flags;
 	void __percpu *ptr;
@@ -773,14 +769,15 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
 
 		while ((new_alloc = pcpu_need_to_extend(chunk))) {
 			spin_unlock_irqrestore(&pcpu_lock, flags);
-			if (pcpu_extend_area_map(chunk, new_alloc) < 0) {
+			if (is_atomic ||
+			    pcpu_extend_area_map(chunk, new_alloc) < 0) {
 				err = "failed to extend area map of reserved chunk";
 				goto fail;
 			}
 			spin_lock_irqsave(&pcpu_lock, flags);
 		}
 
-		off = pcpu_alloc_area(chunk, size, align, false);
+		off = pcpu_alloc_area(chunk, size, align, is_atomic);
 		if (off >= 0)
 			goto area_found;
 
@@ -797,6 +794,8 @@ restart:
 
 			new_alloc = pcpu_need_to_extend(chunk);
 			if (new_alloc) {
+				if (is_atomic)
+					continue;
 				spin_unlock_irqrestore(&pcpu_lock, flags);
 				if (pcpu_extend_area_map(chunk,
 							 new_alloc) < 0) {
@@ -811,7 +810,7 @@ restart:
 				goto restart;
 			}
 
-			off = pcpu_alloc_area(chunk, size, align, false);
+			off = pcpu_alloc_area(chunk, size, align, is_atomic);
 			if (off >= 0)
 				goto area_found;
 		}
@@ -824,6 +823,9 @@ restart:
 	 * tasks to create chunks simultaneously.  Serialize and create iff
 	 * there's still no empty chunk after grabbing the mutex.
 	 */
+	if (is_atomic)
+		goto fail;
+
 	mutex_lock(&pcpu_alloc_mutex);
 
 	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
@@ -846,7 +848,7 @@ area_found:
 	spin_unlock_irqrestore(&pcpu_lock, flags);
 
 	/* populate if not all pages are already there */
-	if (true) {
+	if (!is_atomic) {
 		int page_start, page_end, rs, re;
 
 		mutex_lock(&pcpu_alloc_mutex);
@@ -884,9 +886,9 @@ area_found:
 fail_unlock:
 	spin_unlock_irqrestore(&pcpu_lock, flags);
 fail:
-	if (warn_limit) {
-		pr_warning("PERCPU: allocation failed, size=%zu align=%zu, "
-			   "%s\n", size, align, err);
+	if (!is_atomic && warn_limit) {
+		pr_warning("PERCPU: allocation failed, size=%zu align=%zu atomic=%d, %s\n",
+			   size, align, is_atomic, err);
 		dump_stack();
 		if (!--warn_limit)
 			pr_info("PERCPU: limit reached, disable warning\n");
@@ -895,22 +897,34 @@ fail:
 }
 
 /**
- * __alloc_percpu - allocate dynamic percpu area
+ * __alloc_percpu_gfp - allocate dynamic percpu area
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
+ * @gfp: allocation flags
  *
- * Allocate zero-filled percpu area of @size bytes aligned at @align.
- * Might sleep.  Might trigger writeouts.
- *
- * CONTEXT:
- * Does GFP_KERNEL allocation.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align.  If
+ * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can
+ * be called from any context but is a lot more likely to fail.
  *
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
  */
+void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp)
+{
+	return pcpu_alloc(size, align, false, gfp);
+}
+EXPORT_SYMBOL_GPL(__alloc_percpu_gfp);
+
+/**
+ * __alloc_percpu - allocate dynamic percpu area
+ * @size: size of area to allocate in bytes
+ * @align: alignment of area (max PAGE_SIZE)
+ *
+ * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL).
+ */
 void __percpu *__alloc_percpu(size_t size, size_t align)
 {
-	return pcpu_alloc(size, align, false);
+	return pcpu_alloc(size, align, false, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(__alloc_percpu);
 
@@ -932,7 +946,7 @@ EXPORT_SYMBOL_GPL(__alloc_percpu);
  */
 void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
 {
-	return pcpu_alloc(size, align, true);
+	return pcpu_alloc(size, align, true, GFP_KERNEL);
 }
 
 /**
-- 
cgit v1.2.3


From 1a4d76076cda69b0abf15463a8cebc172406da25 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 2 Sep 2014 14:46:05 -0400
Subject: percpu: implement asynchronous chunk population

The percpu allocator now supports atomic allocations by only
allocating from already populated areas but the mechanism to ensure
that there's adequate amount of populated areas was missing.

This patch expands pcpu_balance_work so that in addition to freeing
excess free chunks it also populates chunks to maintain an adequate
level of populated areas.  pcpu_alloc() schedules pcpu_balance_work if
the amount of free populated areas is too low or after an atomic
allocation failure.

* PERPCU_DYNAMIC_RESERVE is increased by two pages to account for
  PCPU_EMPTY_POP_PAGES_LOW.

* pcpu_async_enabled is added to gate both async jobs -
  chunk->map_extend_work and pcpu_balance_work - so that we don't end
  up scheduling them while the needed subsystems aren't up yet.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/percpu.h |   4 +-
 mm/percpu.c            | 117 +++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 115 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index d1b416da25ed..a3aa63e47637 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -48,9 +48,9 @@
  * intelligent way to determine this would be nice.
  */
 #if BITS_PER_LONG > 32
-#define PERCPU_DYNAMIC_RESERVE		(20 << 10)
+#define PERCPU_DYNAMIC_RESERVE		(28 << 10)
 #else
-#define PERCPU_DYNAMIC_RESERVE		(12 << 10)
+#define PERCPU_DYNAMIC_RESERVE		(20 << 10)
 #endif
 
 extern void *pcpu_base_addr;
diff --git a/mm/percpu.c b/mm/percpu.c
index 28a830590b4c..867efd38d879 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -78,6 +78,8 @@
 #define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */
 #define PCPU_ATOMIC_MAP_MARGIN_LOW	32
 #define PCPU_ATOMIC_MAP_MARGIN_HIGH	64
+#define PCPU_EMPTY_POP_PAGES_LOW	2
+#define PCPU_EMPTY_POP_PAGES_HIGH	4
 
 #ifdef CONFIG_SMP
 /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
@@ -168,9 +170,22 @@ static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
  */
 static int pcpu_nr_empty_pop_pages;
 
-/* balance work is used to populate or destroy chunks asynchronously */
+/*
+ * Balance work is used to populate or destroy chunks asynchronously.  We
+ * try to keep the number of populated free pages between
+ * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one
+ * empty chunk.
+ */
 static void pcpu_balance_workfn(struct work_struct *work);
 static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn);
+static bool pcpu_async_enabled __read_mostly;
+static bool pcpu_atomic_alloc_failed;
+
+static void pcpu_schedule_balance_work(void)
+{
+	if (pcpu_async_enabled)
+		schedule_work(&pcpu_balance_work);
+}
 
 static bool pcpu_addr_in_first_chunk(void *addr)
 {
@@ -386,7 +401,8 @@ static int pcpu_need_to_extend(struct pcpu_chunk *chunk, bool is_atomic)
 		margin = 3;
 
 		if (chunk->map_alloc <
-		    chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW)
+		    chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW &&
+		    pcpu_async_enabled)
 			schedule_work(&chunk->map_extend_work);
 	} else {
 		margin = PCPU_ATOMIC_MAP_MARGIN_HIGH;
@@ -1005,6 +1021,9 @@ area_found:
 	if (chunk != pcpu_reserved_chunk)
 		pcpu_nr_empty_pop_pages -= occ_pages;
 
+	if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
+		pcpu_schedule_balance_work();
+
 	/* clear the areas and return address relative to base address */
 	for_each_possible_cpu(cpu)
 		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
@@ -1023,6 +1042,11 @@ fail:
 		if (!--warn_limit)
 			pr_info("PERCPU: limit reached, disable warning\n");
 	}
+	if (is_atomic) {
+		/* see the flag handling in pcpu_blance_workfn() */
+		pcpu_atomic_alloc_failed = true;
+		pcpu_schedule_balance_work();
+	}
 	return NULL;
 }
 
@@ -1080,7 +1104,7 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
 }
 
 /**
- * pcpu_balance_workfn - reclaim fully free chunks, workqueue function
+ * pcpu_balance_workfn - manage the amount of free chunks and populated pages
  * @work: unused
  *
  * Reclaim all fully free chunks except for the first one.
@@ -1090,7 +1114,12 @@ static void pcpu_balance_workfn(struct work_struct *work)
 	LIST_HEAD(to_free);
 	struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
 	struct pcpu_chunk *chunk, *next;
+	int slot, nr_to_pop, ret;
 
+	/*
+	 * There's no reason to keep around multiple unused chunks and VM
+	 * areas can be scarce.  Destroy all free chunks except for one.
+	 */
 	mutex_lock(&pcpu_alloc_mutex);
 	spin_lock_irq(&pcpu_lock);
 
@@ -1118,6 +1147,74 @@ static void pcpu_balance_workfn(struct work_struct *work)
 		pcpu_destroy_chunk(chunk);
 	}
 
+	/*
+	 * Ensure there are certain number of free populated pages for
+	 * atomic allocs.  Fill up from the most packed so that atomic
+	 * allocs don't increase fragmentation.  If atomic allocation
+	 * failed previously, always populate the maximum amount.  This
+	 * should prevent atomic allocs larger than PAGE_SIZE from keeping
+	 * failing indefinitely; however, large atomic allocs are not
+	 * something we support properly and can be highly unreliable and
+	 * inefficient.
+	 */
+retry_pop:
+	if (pcpu_atomic_alloc_failed) {
+		nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH;
+		/* best effort anyway, don't worry about synchronization */
+		pcpu_atomic_alloc_failed = false;
+	} else {
+		nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
+				  pcpu_nr_empty_pop_pages,
+				  0, PCPU_EMPTY_POP_PAGES_HIGH);
+	}
+
+	for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) {
+		int nr_unpop = 0, rs, re;
+
+		if (!nr_to_pop)
+			break;
+
+		spin_lock_irq(&pcpu_lock);
+		list_for_each_entry(chunk, &pcpu_slot[slot], list) {
+			nr_unpop = pcpu_unit_pages - chunk->nr_populated;
+			if (nr_unpop)
+				break;
+		}
+		spin_unlock_irq(&pcpu_lock);
+
+		if (!nr_unpop)
+			continue;
+
+		/* @chunk can't go away while pcpu_alloc_mutex is held */
+		pcpu_for_each_unpop_region(chunk, rs, re, 0, pcpu_unit_pages) {
+			int nr = min(re - rs, nr_to_pop);
+
+			ret = pcpu_populate_chunk(chunk, rs, rs + nr);
+			if (!ret) {
+				nr_to_pop -= nr;
+				spin_lock_irq(&pcpu_lock);
+				pcpu_chunk_populated(chunk, rs, rs + nr);
+				spin_unlock_irq(&pcpu_lock);
+			} else {
+				nr_to_pop = 0;
+			}
+
+			if (!nr_to_pop)
+				break;
+		}
+	}
+
+	if (nr_to_pop) {
+		/* ran out of chunks to populate, create a new one and retry */
+		chunk = pcpu_create_chunk();
+		if (chunk) {
+			spin_lock_irq(&pcpu_lock);
+			pcpu_chunk_relocate(chunk, -1);
+			spin_unlock_irq(&pcpu_lock);
+			goto retry_pop;
+		}
+	}
+
 	mutex_unlock(&pcpu_alloc_mutex);
 }
 
@@ -1160,7 +1257,7 @@ void free_percpu(void __percpu *ptr)
 
 		list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list)
 			if (pos != chunk) {
-				schedule_work(&pcpu_balance_work);
+				pcpu_schedule_balance_work();
 				break;
 			}
 	}
@@ -2187,3 +2284,15 @@ void __init percpu_init_late(void)
 		spin_unlock_irqrestore(&pcpu_lock, flags);
 	}
 }
+
+/*
+ * Percpu allocator is initialized early during boot when neither slab or
+ * workqueue is available.  Plug async management until everything is up
+ * and running.
+ */
+static int __init percpu_enable_async(void)
+{
+	pcpu_async_enabled = true;
+	return 0;
+}
+subsys_initcall(percpu_enable_async);
-- 
cgit v1.2.3


From 36d32314ae773283413a91259eab8f546e7f485b Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Tue, 2 Sep 2014 08:27:05 +0800
Subject: ACPICA: Add _PSx names to the METHOD_NAME list.

Will be used by iASL.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acnames.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index c728113374f5..f97804bdf1ff 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -59,6 +59,10 @@
 #define METHOD_NAME__PRS        "_PRS"
 #define METHOD_NAME__PRT        "_PRT"
 #define METHOD_NAME__PRW        "_PRW"
+#define METHOD_NAME__PS0        "_PS0"
+#define METHOD_NAME__PS1        "_PS1"
+#define METHOD_NAME__PS2        "_PS2"
+#define METHOD_NAME__PS3        "_PS3"
 #define METHOD_NAME__REG        "_REG"
 #define METHOD_NAME__SB_        "_SB_"
 #define METHOD_NAME__SEG        "_SEG"
-- 
cgit v1.2.3


From 63b8f8cd67fd8edfe1c30763e519e00b037891b5 Mon Sep 17 00:00:00 2001
From: Hanjun Guo <hanjun.guo@linaro.org>
Date: Tue, 2 Sep 2014 08:27:12 +0800
Subject: ACPICA: ACPI 5.1/Disassembler: Add GICC affinity subtable to SRAT
 table.

Update template for SRAT.
Add clock_domain to standard CPU affinity subtable.

Mostly by Hanjun Guo <hanjun.guo@linaro.org>

Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actbl1.h | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h
index 7626bfeac2cb..29e79370641d 100644
--- a/include/acpi/actbl1.h
+++ b/include/acpi/actbl1.h
@@ -952,7 +952,8 @@ enum acpi_srat_type {
 	ACPI_SRAT_TYPE_CPU_AFFINITY = 0,
 	ACPI_SRAT_TYPE_MEMORY_AFFINITY = 1,
 	ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY = 2,
-	ACPI_SRAT_TYPE_RESERVED = 3	/* 3 and greater are reserved */
+	ACPI_SRAT_TYPE_GICC_AFFINITY = 3,
+	ACPI_SRAT_TYPE_RESERVED = 4	/* 4 and greater are reserved */
 };
 
 /*
@@ -968,7 +969,7 @@ struct acpi_srat_cpu_affinity {
 	u32 flags;
 	u8 local_sapic_eid;
 	u8 proximity_domain_hi[3];
-	u32 reserved;		/* Reserved, must be zero */
+	u32 clock_domain;
 };
 
 /* Flags */
@@ -1010,6 +1011,20 @@ struct acpi_srat_x2apic_cpu_affinity {
 
 #define ACPI_SRAT_CPU_ENABLED       (1)	/* 00: Use affinity structure */
 
+/* 3: GICC Affinity (ACPI 5.1) */
+
+struct acpi_srat_gicc_affinity {
+	struct acpi_subtable_header header;
+	u32 proximity_domain;
+	u32 acpi_processor_uid;
+	u32 flags;
+	u32 clock_domain;
+};
+
+/* Flags for struct acpi_srat_gicc_affinity */
+
+#define ACPI_SRAT_GICC_ENABLED     (1)	/* 00: Use affinity structure */
+
 /* Reset to default packing */
 
 #pragma pack()
-- 
cgit v1.2.3


From 34ea065e5e607dcbb249046c42a491f8b24ad849 Mon Sep 17 00:00:00 2001
From: Hanjun Guo <hanjun.guo@linaro.org>
Date: Tue, 2 Sep 2014 08:27:19 +0800
Subject: ACPICA: Headers: Add GTDT flag definitions for the timer subtable.

Mostly by Hanjun Guo <hanjun.guo@linaro.org>

Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actbl3.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h
index 787bcc814463..5480cb2236bf 100644
--- a/include/acpi/actbl3.h
+++ b/include/acpi/actbl3.h
@@ -310,10 +310,15 @@ struct acpi_gtdt_timer_entry {
 	u32 common_flags;
 };
 
+/* Flag Definitions: timer_flags and virtual_timer_flags above */
+
+#define ACPI_GTDT_GT_IRQ_MODE               (1)
+#define ACPI_GTDT_GT_IRQ_POLARITY           (1<<1)
+
 /* Flag Definitions: common_flags above */
 
-#define ACPI_GTDT_GT_IS_SECURE_TIMER    (1)
-#define ACPI_GTDT_GT_ALWAYS_ON          (1<<1)
+#define ACPI_GTDT_GT_IS_SECURE_TIMER        (1)
+#define ACPI_GTDT_GT_ALWAYS_ON              (1<<1)
 
 /* 1: SBSA Generic Watchdog Structure */
 
-- 
cgit v1.2.3


From 48c1947c53163afaadb3f140f46f5d968d405f5c Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Tue, 2 Sep 2014 08:27:40 +0800
Subject: ACPICA: Update version to 20140828.

Version 20140828.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index b7c89d47efbe..dc9d037d3055 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -46,7 +46,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20140724
+#define ACPI_CA_VERSION                 0x20140828
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
-- 
cgit v1.2.3


From d07e9c178f188f76851aca8ab49a78da13dda006 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 29 Aug 2014 15:13:21 +0200
Subject: PM / domains: Make generic_pm_domain.name const

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm_domain.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 7c1d252b20c0..ebc4c76ffb73 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -60,7 +60,7 @@ struct generic_pm_domain {
 	struct mutex lock;
 	struct dev_power_governor *gov;
 	struct work_struct power_off_work;
-	char *name;
+	const char *name;
 	unsigned int in_progress;	/* Number of devices being suspended now */
 	atomic_t sd_count;	/* Number of subdomains with power "on" */
 	enum gpd_status status;	/* Current state of the domain */
-- 
cgit v1.2.3


From 0504cd170c86f0617f27a31f1ba2328caa976707 Mon Sep 17 00:00:00 2001
From: Sonika Jindal <sonika.jindal@intel.com>
Date: Fri, 8 Aug 2014 16:23:40 +0530
Subject: drm: Renaming DP training vswing pre emph defines

Adding new defines, older one will be removed in the last patch in the series.
This is to rename the defines to have levels instead of values for vswing and
pre-emph levels as the values may differ in other scenarios like low vswing of
eDP1.4 where the values are different.

Done using following cocci patch for each define:
@@
@@

 # define DP_TRAIN_VOLTAGE_SWING_400     (0 << 0)
+ # define DP_TRAIN_VOLTAGE_SWING_LEVEL_0     (0 << 0)

...
Cc: dri-devel@lists.freedesktop.org

Signed-off-by: Sonika Jindal <sonika.jindal@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_dp_helper.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index a21568bf1514..3840a055c6be 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -191,15 +191,23 @@
 # define DP_TRAIN_VOLTAGE_SWING_SHIFT	    0
 # define DP_TRAIN_MAX_SWING_REACHED	    (1 << 2)
 # define DP_TRAIN_VOLTAGE_SWING_400	    (0 << 0)
+# define DP_TRAIN_VOLTAGE_SWING_LEVEL_0 (0 << 0)
 # define DP_TRAIN_VOLTAGE_SWING_600	    (1 << 0)
+# define DP_TRAIN_VOLTAGE_SWING_LEVEL_1 (1 << 0)
 # define DP_TRAIN_VOLTAGE_SWING_800	    (2 << 0)
+# define DP_TRAIN_VOLTAGE_SWING_LEVEL_2 (2 << 0)
 # define DP_TRAIN_VOLTAGE_SWING_1200	    (3 << 0)
+# define DP_TRAIN_VOLTAGE_SWING_LEVEL_3 (3 << 0)
 
 # define DP_TRAIN_PRE_EMPHASIS_MASK	    (3 << 3)
 # define DP_TRAIN_PRE_EMPHASIS_0	    (0 << 3)
+# define DP_TRAIN_PRE_EMPH_LEVEL_0		(0 << 3)
 # define DP_TRAIN_PRE_EMPHASIS_3_5	    (1 << 3)
+# define DP_TRAIN_PRE_EMPH_LEVEL_1		(1 << 3)
 # define DP_TRAIN_PRE_EMPHASIS_6	    (2 << 3)
+# define DP_TRAIN_PRE_EMPH_LEVEL_2		(2 << 3)
 # define DP_TRAIN_PRE_EMPHASIS_9_5	    (3 << 3)
+# define DP_TRAIN_PRE_EMPH_LEVEL_3		(3 << 3)
 
 # define DP_TRAIN_PRE_EMPHASIS_SHIFT	    3
 # define DP_TRAIN_MAX_PRE_EMPHASIS_REACHED  (1 << 5)
-- 
cgit v1.2.3


From 26db63e3cb7af431707cd0467c7bcfefad25aa39 Mon Sep 17 00:00:00 2001
From: Sonika Jindal <sonika.jindal@intel.com>
Date: Fri, 8 Aug 2014 16:23:46 +0530
Subject: drm: Remove old defines for vswing and pre-emph values

This is the last patch in the series, so remove old defines

Signed-off-by: Sonika Jindal <sonika.jindal@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_dp_helper.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 3840a055c6be..9305c718d789 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -190,23 +190,15 @@
 # define DP_TRAIN_VOLTAGE_SWING_MASK	    0x3
 # define DP_TRAIN_VOLTAGE_SWING_SHIFT	    0
 # define DP_TRAIN_MAX_SWING_REACHED	    (1 << 2)
-# define DP_TRAIN_VOLTAGE_SWING_400	    (0 << 0)
 # define DP_TRAIN_VOLTAGE_SWING_LEVEL_0 (0 << 0)
-# define DP_TRAIN_VOLTAGE_SWING_600	    (1 << 0)
 # define DP_TRAIN_VOLTAGE_SWING_LEVEL_1 (1 << 0)
-# define DP_TRAIN_VOLTAGE_SWING_800	    (2 << 0)
 # define DP_TRAIN_VOLTAGE_SWING_LEVEL_2 (2 << 0)
-# define DP_TRAIN_VOLTAGE_SWING_1200	    (3 << 0)
 # define DP_TRAIN_VOLTAGE_SWING_LEVEL_3 (3 << 0)
 
 # define DP_TRAIN_PRE_EMPHASIS_MASK	    (3 << 3)
-# define DP_TRAIN_PRE_EMPHASIS_0	    (0 << 3)
 # define DP_TRAIN_PRE_EMPH_LEVEL_0		(0 << 3)
-# define DP_TRAIN_PRE_EMPHASIS_3_5	    (1 << 3)
 # define DP_TRAIN_PRE_EMPH_LEVEL_1		(1 << 3)
-# define DP_TRAIN_PRE_EMPHASIS_6	    (2 << 3)
 # define DP_TRAIN_PRE_EMPH_LEVEL_2		(2 << 3)
-# define DP_TRAIN_PRE_EMPHASIS_9_5	    (3 << 3)
 # define DP_TRAIN_PRE_EMPH_LEVEL_3		(3 << 3)
 
 # define DP_TRAIN_PRE_EMPHASIS_SHIFT	    3
-- 
cgit v1.2.3


From 257f8cce5d40b811d229ed71602882baa0012808 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 29 Aug 2014 15:32:29 +0200
Subject: ALSA: pcm: Allow nonatomic trigger operations

Currently, many PCM operations are performed in a critical section
protected by spinlock, typically the trigger and pointer callbacks are
assumed to be atomic.  This is basically because some trigger action
(e.g. PCM stop after drain or xrun) is done in the interrupt handler.
If a driver runs in a threaded irq, however, this doesn't have to be
atomic.  And many devices want to handle trigger in a non-atomic
context due to lengthy communications.

This patch tries all PCM calls operational in non-atomic context.
What it does is very simple: replaces the substream spinlock with the
corresponding substream mutex when pcm->nonatomic flag is set.  The
driver that wants to use the non-atomic PCM ops just needs to set the
flag and keep the rest as is.  (Of course, it must not handle any PCM
ops in irq context.)

Note that the code doesn't check whether it's atomic-safe or not, but
trust in 100% that the driver sets pcm->nonatomic correctly.

One possible problem is the case where linked PCM substreams have
inconsistent nonatomic states.  For avoiding this, snd_pcm_link()
returns an error if one tries to link an inconsistent PCM substream.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h     | 58 +++++++++++++++++++++++++++++--------
 sound/core/pcm.c        |  1 +
 sound/core/pcm_native.c | 76 ++++++++++++++++++++++++++++++++++++++++++++-----
 3 files changed, 116 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 6f3e10ca0e32..bc79962f4aa6 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -365,6 +365,7 @@ struct snd_pcm_runtime {
 
 struct snd_pcm_group {		/* keep linked substreams */
 	spinlock_t lock;
+	struct mutex mutex;
 	struct list_head substreams;
 	int count;
 };
@@ -460,6 +461,7 @@ struct snd_pcm {
 	void (*private_free) (struct snd_pcm *pcm);
 	struct device *dev; /* actual hw device this belongs to */
 	bool internal; /* pcm is for internal use only */
+	bool nonatomic; /* whole PCM operations are in non-atomic context */
 #if defined(CONFIG_SND_PCM_OSS) || defined(CONFIG_SND_PCM_OSS_MODULE)
 	struct snd_pcm_oss oss;
 #endif
@@ -493,6 +495,7 @@ int snd_pcm_notify(struct snd_pcm_notify *notify, int nfree);
  */
 
 extern rwlock_t snd_pcm_link_rwlock;
+extern struct rw_semaphore snd_pcm_link_rwsem;
 
 int snd_pcm_info(struct snd_pcm_substream *substream, struct snd_pcm_info *info);
 int snd_pcm_info_user(struct snd_pcm_substream *substream,
@@ -539,38 +542,69 @@ static inline int snd_pcm_stream_linked(struct snd_pcm_substream *substream)
 
 static inline void snd_pcm_stream_lock(struct snd_pcm_substream *substream)
 {
-	read_lock(&snd_pcm_link_rwlock);
-	spin_lock(&substream->self_group.lock);
+	if (substream->pcm->nonatomic) {
+		down_read(&snd_pcm_link_rwsem);
+		mutex_lock(&substream->self_group.mutex);
+	} else {
+		read_lock(&snd_pcm_link_rwlock);
+		spin_lock(&substream->self_group.lock);
+	}
 }
 
 static inline void snd_pcm_stream_unlock(struct snd_pcm_substream *substream)
 {
-	spin_unlock(&substream->self_group.lock);
-	read_unlock(&snd_pcm_link_rwlock);
+	if (substream->pcm->nonatomic) {
+		mutex_unlock(&substream->self_group.mutex);
+		up_read(&snd_pcm_link_rwsem);
+	} else {
+		spin_unlock(&substream->self_group.lock);
+		read_unlock(&snd_pcm_link_rwlock);
+	}
 }
 
 static inline void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
 {
-	read_lock_irq(&snd_pcm_link_rwlock);
-	spin_lock(&substream->self_group.lock);
+	if (substream->pcm->nonatomic) {
+		down_read(&snd_pcm_link_rwsem);
+		mutex_lock(&substream->self_group.mutex);
+	} else {
+		read_lock_irq(&snd_pcm_link_rwlock);
+		spin_lock(&substream->self_group.lock);
+	}
 }
 
 static inline void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream)
 {
-	spin_unlock(&substream->self_group.lock);
-	read_unlock_irq(&snd_pcm_link_rwlock);
+	if (substream->pcm->nonatomic) {
+		mutex_unlock(&substream->self_group.mutex);
+		up_read(&snd_pcm_link_rwsem);
+	} else {
+		spin_unlock(&substream->self_group.lock);
+		read_unlock_irq(&snd_pcm_link_rwlock);
+	}
 }
 
 #define snd_pcm_stream_lock_irqsave(substream, flags) \
 do { \
-	read_lock_irqsave(&snd_pcm_link_rwlock, (flags)); \
-	spin_lock(&substream->self_group.lock); \
+	if ((substream)->pcm->nonatomic) {			  \
+		(flags) = 0; /* XXX for avoid warning */	  \
+		down_read(&snd_pcm_link_rwsem);			  \
+		mutex_lock(&(substream)->self_group.mutex);	  \
+	} else {						  \
+		read_lock_irqsave(&snd_pcm_link_rwlock, (flags)); \
+		spin_lock(&(substream)->self_group.lock);	  \
+	}							  \
 } while (0)
 
 #define snd_pcm_stream_unlock_irqrestore(substream, flags) \
 do { \
-	spin_unlock(&substream->self_group.lock); \
-	read_unlock_irqrestore(&snd_pcm_link_rwlock, (flags)); \
+	if ((substream)->pcm->nonatomic) {			       \
+		mutex_unlock(&(substream)->self_group.mutex);	       \
+		up_read(&snd_pcm_link_rwsem);			       \
+	} else {						       \
+		spin_unlock(&(substream)->self_group.lock);	       \
+		read_unlock_irqrestore(&snd_pcm_link_rwlock, (flags)); \
+	}							       \
 } while (0)
 
 #define snd_pcm_group_for_each_entry(s, substream) \
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 43932e8dce66..afccdc553ef9 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -698,6 +698,7 @@ int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count)
 		}
 		substream->group = &substream->self_group;
 		spin_lock_init(&substream->self_group.lock);
+		mutex_init(&substream->self_group.mutex);
 		INIT_LIST_HEAD(&substream->self_group.substreams);
 		list_add_tail(&substream->link_list, &substream->self_group.substreams);
 		atomic_set(&substream->mmap_count, 0);
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 8cd2f930ad0b..16d9b7e15f8b 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -77,7 +77,8 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream);
 DEFINE_RWLOCK(snd_pcm_link_rwlock);
 EXPORT_SYMBOL(snd_pcm_link_rwlock);
 
-static DECLARE_RWSEM(snd_pcm_link_rwsem);
+DECLARE_RWSEM(snd_pcm_link_rwsem);
+EXPORT_SYMBOL(snd_pcm_link_rwsem);
 
 static inline mm_segment_t snd_enter_user(void)
 {
@@ -727,9 +728,14 @@ static int snd_pcm_action_group(struct action_ops *ops,
 	int res = 0;
 
 	snd_pcm_group_for_each_entry(s, substream) {
-		if (do_lock && s != substream)
-			spin_lock_nested(&s->self_group.lock,
-					 SINGLE_DEPTH_NESTING);
+		if (do_lock && s != substream) {
+			if (s->pcm->nonatomic)
+				mutex_lock_nested(&s->self_group.mutex,
+						  SINGLE_DEPTH_NESTING);
+			else
+				spin_lock_nested(&s->self_group.lock,
+						 SINGLE_DEPTH_NESTING);
+		}
 		res = ops->pre_action(s, state);
 		if (res < 0)
 			goto _unlock;
@@ -755,8 +761,12 @@ static int snd_pcm_action_group(struct action_ops *ops,
 	if (do_lock) {
 		/* unlock streams */
 		snd_pcm_group_for_each_entry(s1, substream) {
-			if (s1 != substream)
-				spin_unlock(&s1->self_group.lock);
+			if (s1 != substream) {
+				if (s->pcm->nonatomic)
+					mutex_unlock(&s1->self_group.mutex);
+				else
+					spin_unlock(&s1->self_group.lock);
+			}
 			if (s1 == s)	/* end */
 				break;
 		}
@@ -784,6 +794,27 @@ static int snd_pcm_action_single(struct action_ops *ops,
 	return res;
 }
 
+/* call in mutex-protected context */
+static int snd_pcm_action_mutex(struct action_ops *ops,
+				struct snd_pcm_substream *substream,
+				int state)
+{
+	int res;
+
+	if (snd_pcm_stream_linked(substream)) {
+		if (!mutex_trylock(&substream->group->mutex)) {
+			mutex_unlock(&substream->self_group.mutex);
+			mutex_lock(&substream->group->mutex);
+			mutex_lock(&substream->self_group.mutex);
+		}
+		res = snd_pcm_action_group(ops, substream, state, 1);
+		mutex_unlock(&substream->group->mutex);
+	} else {
+		res = snd_pcm_action_single(ops, substream, state);
+	}
+	return res;
+}
+
 /*
  *  Note: call with stream lock
  */
@@ -793,6 +824,9 @@ static int snd_pcm_action(struct action_ops *ops,
 {
 	int res;
 
+	if (substream->pcm->nonatomic)
+		return snd_pcm_action_mutex(ops, substream, state);
+
 	if (snd_pcm_stream_linked(substream)) {
 		if (!spin_trylock(&substream->group->lock)) {
 			spin_unlock(&substream->self_group.lock);
@@ -807,6 +841,29 @@ static int snd_pcm_action(struct action_ops *ops,
 	return res;
 }
 
+static int snd_pcm_action_lock_mutex(struct action_ops *ops,
+				     struct snd_pcm_substream *substream,
+				     int state)
+{
+	int res;
+
+	down_read(&snd_pcm_link_rwsem);
+	if (snd_pcm_stream_linked(substream)) {
+		mutex_lock(&substream->group->mutex);
+		mutex_lock_nested(&substream->self_group.mutex,
+				  SINGLE_DEPTH_NESTING);
+		res = snd_pcm_action_group(ops, substream, state, 1);
+		mutex_unlock(&substream->self_group.mutex);
+		mutex_unlock(&substream->group->mutex);
+	} else {
+		mutex_lock(&substream->self_group.mutex);
+		res = snd_pcm_action_single(ops, substream, state);
+		mutex_unlock(&substream->self_group.mutex);
+	}
+	up_read(&snd_pcm_link_rwsem);
+	return res;
+}
+
 /*
  *  Note: don't use any locks before
  */
@@ -816,6 +873,9 @@ static int snd_pcm_action_lock_irq(struct action_ops *ops,
 {
 	int res;
 
+	if (substream->pcm->nonatomic)
+		return snd_pcm_action_lock_mutex(ops, substream, state);
+
 	read_lock_irq(&snd_pcm_link_rwlock);
 	if (snd_pcm_stream_linked(substream)) {
 		spin_lock(&substream->group->lock);
@@ -1634,7 +1694,8 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 	down_write(&snd_pcm_link_rwsem);
 	write_lock_irq(&snd_pcm_link_rwlock);
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN ||
-	    substream->runtime->status->state != substream1->runtime->status->state) {
+	    substream->runtime->status->state != substream1->runtime->status->state ||
+	    substream->pcm->nonatomic != substream1->pcm->nonatomic) {
 		res = -EBADFD;
 		goto _end;
 	}
@@ -1646,6 +1707,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 		substream->group = group;
 		group = NULL;
 		spin_lock_init(&substream->group->lock);
+		mutex_init(&substream->group->mutex);
 		INIT_LIST_HEAD(&substream->group->substreams);
 		list_add_tail(&substream->link_list, &substream->group->substreams);
 		substream->group->count = 1;
-- 
cgit v1.2.3


From 7af142f752116e86adbe2073f2922d8265a77709 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 1 Sep 2014 11:19:37 +0200
Subject: ALSA: pcm: Uninline snd_pcm_stream_lock() and _unlock()

The previous commit for the non-atomic PCM ops added more codes to
snd_pcm_stream_lock() and its variants.  Since they are inlined
functions, it resulted in a significant code size bloat.  For reducing
the size bloat, this patch changes the inline functions to the normal
function calls.  The export of rwlock and rwsem are removed as well,
since they are referred only in pcm_native.c now.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h     | 81 ++++++++-----------------------------------------
 sound/core/pcm_native.c | 64 +++++++++++++++++++++++++++++++++++---
 2 files changed, 72 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index bc79962f4aa6..67e0bdb9f0fa 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -494,9 +494,6 @@ int snd_pcm_notify(struct snd_pcm_notify *notify, int nfree);
  *  Native I/O
  */
 
-extern rwlock_t snd_pcm_link_rwlock;
-extern struct rw_semaphore snd_pcm_link_rwsem;
-
 int snd_pcm_info(struct snd_pcm_substream *substream, struct snd_pcm_info *info);
 int snd_pcm_info_user(struct snd_pcm_substream *substream,
 		      struct snd_pcm_info __user *info);
@@ -540,72 +537,18 @@ static inline int snd_pcm_stream_linked(struct snd_pcm_substream *substream)
 	return substream->group != &substream->self_group;
 }
 
-static inline void snd_pcm_stream_lock(struct snd_pcm_substream *substream)
-{
-	if (substream->pcm->nonatomic) {
-		down_read(&snd_pcm_link_rwsem);
-		mutex_lock(&substream->self_group.mutex);
-	} else {
-		read_lock(&snd_pcm_link_rwlock);
-		spin_lock(&substream->self_group.lock);
-	}
-}
-
-static inline void snd_pcm_stream_unlock(struct snd_pcm_substream *substream)
-{
-	if (substream->pcm->nonatomic) {
-		mutex_unlock(&substream->self_group.mutex);
-		up_read(&snd_pcm_link_rwsem);
-	} else {
-		spin_unlock(&substream->self_group.lock);
-		read_unlock(&snd_pcm_link_rwlock);
-	}
-}
-
-static inline void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
-{
-	if (substream->pcm->nonatomic) {
-		down_read(&snd_pcm_link_rwsem);
-		mutex_lock(&substream->self_group.mutex);
-	} else {
-		read_lock_irq(&snd_pcm_link_rwlock);
-		spin_lock(&substream->self_group.lock);
-	}
-}
-
-static inline void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream)
-{
-	if (substream->pcm->nonatomic) {
-		mutex_unlock(&substream->self_group.mutex);
-		up_read(&snd_pcm_link_rwsem);
-	} else {
-		spin_unlock(&substream->self_group.lock);
-		read_unlock_irq(&snd_pcm_link_rwlock);
-	}
-}
-
-#define snd_pcm_stream_lock_irqsave(substream, flags) \
-do { \
-	if ((substream)->pcm->nonatomic) {			  \
-		(flags) = 0; /* XXX for avoid warning */	  \
-		down_read(&snd_pcm_link_rwsem);			  \
-		mutex_lock(&(substream)->self_group.mutex);	  \
-	} else {						  \
-		read_lock_irqsave(&snd_pcm_link_rwlock, (flags)); \
-		spin_lock(&(substream)->self_group.lock);	  \
-	}							  \
-} while (0)
-
-#define snd_pcm_stream_unlock_irqrestore(substream, flags) \
-do { \
-	if ((substream)->pcm->nonatomic) {			       \
-		mutex_unlock(&(substream)->self_group.mutex);	       \
-		up_read(&snd_pcm_link_rwsem);			       \
-	} else {						       \
-		spin_unlock(&(substream)->self_group.lock);	       \
-		read_unlock_irqrestore(&snd_pcm_link_rwlock, (flags)); \
-	}							       \
-} while (0)
+void snd_pcm_stream_lock(struct snd_pcm_substream *substream);
+void snd_pcm_stream_unlock(struct snd_pcm_substream *substream);
+void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream);
+void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream);
+unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream);
+#define snd_pcm_stream_lock_irqsave(substream, flags)		 \
+	do {							 \
+		typecheck(unsigned long, flags);		 \
+		flags = _snd_pcm_stream_lock_irqsave(substream); \
+	} while (0)
+void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
+				      unsigned long flags);
 
 #define snd_pcm_group_for_each_entry(s, substream) \
 	list_for_each_entry(s, &substream->group->substreams, link_list)
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 16d9b7e15f8b..85fe1a216225 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -74,11 +74,67 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream);
  *
  */
 
-DEFINE_RWLOCK(snd_pcm_link_rwlock);
-EXPORT_SYMBOL(snd_pcm_link_rwlock);
+static DEFINE_RWLOCK(snd_pcm_link_rwlock);
+static DECLARE_RWSEM(snd_pcm_link_rwsem);
 
-DECLARE_RWSEM(snd_pcm_link_rwsem);
-EXPORT_SYMBOL(snd_pcm_link_rwsem);
+void snd_pcm_stream_lock(struct snd_pcm_substream *substream)
+{
+	if (substream->pcm->nonatomic) {
+		down_read(&snd_pcm_link_rwsem);
+		mutex_lock(&substream->self_group.mutex);
+	} else {
+		read_lock(&snd_pcm_link_rwlock);
+		spin_lock(&substream->self_group.lock);
+	}
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_lock);
+
+void snd_pcm_stream_unlock(struct snd_pcm_substream *substream)
+{
+	if (substream->pcm->nonatomic) {
+		mutex_unlock(&substream->self_group.mutex);
+		up_read(&snd_pcm_link_rwsem);
+	} else {
+		spin_unlock(&substream->self_group.lock);
+		read_unlock(&snd_pcm_link_rwlock);
+	}
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock);
+
+void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
+{
+	if (!substream->pcm->nonatomic)
+		local_irq_disable();
+	snd_pcm_stream_lock(substream);
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq);
+
+void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream)
+{
+	snd_pcm_stream_unlock(substream);
+	if (!substream->pcm->nonatomic)
+		local_irq_enable();
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq);
+
+unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream)
+{
+	unsigned long flags = 0;
+	if (!substream->pcm->nonatomic)
+		local_irq_save(flags);
+	snd_pcm_stream_lock(substream);
+	return flags;
+}
+EXPORT_SYMBOL_GPL(_snd_pcm_stream_lock_irqsave);
+
+void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
+				      unsigned long flags)
+{
+	snd_pcm_stream_unlock(substream);
+	if (!substream->pcm->nonatomic)
+		local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore);
 
 static inline mm_segment_t snd_enter_user(void)
 {
-- 
cgit v1.2.3


From 76ba59f8366f2d9282cb5bda9de75b4b68cbe55f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 26 Aug 2014 11:03:16 +0100
Subject: genirq: Add irq_domain-aware core IRQ handler

Calling irq_find_mapping from outside a irq_{enter,exit} section is
unsafe and produces ugly messages if CONFIG_PROVE_RCU is enabled:
If coming from the idle state, the rcu_read_lock call in irq_find_mapping
will generate an unpleasant warning:

<quote>
===============================
[ INFO: suspicious RCU usage. ]
3.16.0-rc1+ #135 Not tainted
-------------------------------
include/linux/rcupdate.h:871 rcu_read_lock() used illegally while idle!

other info that might help us debug this:

RCU used illegally from idle CPU!
rcu_scheduler_active = 1, debug_locks = 0
RCU used illegally from extended quiescent state!
1 lock held by swapper/0/0:
 #0:  (rcu_read_lock){......}, at: [<ffffffc00010206c>]
irq_find_mapping+0x4c/0x198
</quote>

As this issue is fairly widespread and involves at least three
different architectures, a possible solution is to add a new
handle_domain_irq entry point into the generic IRQ code that
the interrupt controller code can call.

This new function takes an irq_domain, and calls into irq_find_domain
inside the irq_{enter,exit} block. An additional "lookup" parameter is
used to allow non-domain architecture code to be replaced by this as well.

Interrupt controllers can then be updated to use the new mechanism.

This code is sitting behind a new CONFIG_HANDLE_DOMAIN_IRQ, as not all
architectures implement set_irq_regs (yes, mn10300, I'm looking at you...).

Reported-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Link: https://lkml.kernel.org/r/1409047421-27649-2-git-send-email-marc.zyngier@arm.com
Signed-off-by: Jason Cooper <jason@lakedaemon.net>
---
 include/linux/irqdesc.h | 19 +++++++++++++++++++
 kernel/irq/Kconfig      |  3 +++
 kernel/irq/irqdesc.c    | 42 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 64 insertions(+)

(limited to 'include')

diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 472c021a2d4f..ff24667cd86c 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -12,6 +12,8 @@ struct irq_affinity_notify;
 struct proc_dir_entry;
 struct module;
 struct irq_desc;
+struct irq_domain;
+struct pt_regs;
 
 /**
  * struct irq_desc - interrupt descriptor
@@ -118,6 +120,23 @@ static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *de
 
 int generic_handle_irq(unsigned int irq);
 
+#ifdef CONFIG_HANDLE_DOMAIN_IRQ
+/*
+ * Convert a HW interrupt number to a logical one using a IRQ domain,
+ * and handle the result interrupt number. Return -EINVAL if
+ * conversion failed. Providing a NULL domain indicates that the
+ * conversion has already been done.
+ */
+int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq,
+			bool lookup, struct pt_regs *regs);
+
+static inline int handle_domain_irq(struct irq_domain *domain,
+				    unsigned int hwirq, struct pt_regs *regs)
+{
+	return __handle_domain_irq(domain, hwirq, true, regs);
+}
+#endif
+
 /* Test to see if a driver has successfully requested an irq */
 static inline int irq_has_action(unsigned int irq)
 {
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index d269cecdfbf0..225086b2652e 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -55,6 +55,9 @@ config GENERIC_IRQ_CHIP
 config IRQ_DOMAIN
 	bool
 
+config HANDLE_DOMAIN_IRQ
+	bool
+
 config IRQ_DOMAIN_DEBUG
 	bool "Expose hardware/virtual IRQ mapping via debugfs"
 	depends on IRQ_DOMAIN && DEBUG_FS
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 1487a123db5c..a1782f88f0af 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -14,6 +14,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/radix-tree.h>
 #include <linux/bitmap.h>
+#include <linux/irqdomain.h>
 
 #include "internals.h"
 
@@ -336,6 +337,47 @@ int generic_handle_irq(unsigned int irq)
 }
 EXPORT_SYMBOL_GPL(generic_handle_irq);
 
+#ifdef CONFIG_HANDLE_DOMAIN_IRQ
+/**
+ * __handle_domain_irq - Invoke the handler for a HW irq belonging to a domain
+ * @domain:	The domain where to perform the lookup
+ * @hwirq:	The HW irq number to convert to a logical one
+ * @lookup:	Whether to perform the domain lookup or not
+ * @regs:	Register file coming from the low-level handling code
+ *
+ * Returns:	0 on success, or -EINVAL if conversion has failed
+ */
+int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq,
+			bool lookup, struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	unsigned int irq = hwirq;
+	int ret = 0;
+
+	irq_enter();
+
+#ifdef CONFIG_IRQ_DOMAIN
+	if (lookup)
+		irq = irq_find_mapping(domain, hwirq);
+#endif
+
+	/*
+	 * Some hardware gives randomly wrong interrupts.  Rather
+	 * than crashing, do something sensible.
+	 */
+	if (unlikely(!irq || irq >= nr_irqs)) {
+		ack_bad_irq(irq);
+		ret = -EINVAL;
+	} else {
+		generic_handle_irq(irq);
+	}
+
+	irq_exit();
+	set_irq_regs(old_regs);
+	return ret;
+}
+#endif
+
 /* Dynamic interrupt handling */
 
 /**
-- 
cgit v1.2.3


From eadf9e26fab7f9841adcc36f3559dbce7604fcd5 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Thu, 21 Aug 2014 16:49:16 -0300
Subject: [media] videodev2.h: add __user to v4l2_ext_control pointers

These are not copied to kernel space by video_usercopy, so mark them
as __user.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 include/uapi/linux/videodev2.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 778a3298fb34..0b1ba5c6a8d2 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -1285,11 +1285,11 @@ struct v4l2_ext_control {
 	union {
 		__s32 value;
 		__s64 value64;
-		char *string;
-		__u8 *p_u8;
-		__u16 *p_u16;
-		__u32 *p_u32;
-		void *ptr;
+		char __user *string;
+		__u8 __user *p_u8;
+		__u16 __user *p_u16;
+		__u32 __user *p_u32;
+		void __user *ptr;
 	};
 } __attribute__ ((packed));
 
-- 
cgit v1.2.3


From a383b68d9fe9864c4d3b86f67ad6488f58136435 Mon Sep 17 00:00:00 2001
From: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Date: Wed, 3 Sep 2014 13:39:13 +0900
Subject: ACPI / scan: not cache _SUN value in struct acpi_device_pnp

The _SUN device indentification object is not guaranteed to return
the same value every time it is executed, so we should not cache its
return value, but rather execute it every time as needed.  If it is
cached, an incorrect stale value may be used in some situations.

This issue was exposed by commit 202317a573b2 (ACPI / scan: Add
acpi_device objects for all device nodes in the namespace).  Fix it
by avoiding to cache the return value of _SUN.

Fixes: 202317a573b2 (ACPI / scan: Add acpi_device objects for all device nodes in the namespace)
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: 3.14+ <stable@vger.kernel.org> # 3.14+
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/scan.c     | 15 ++++++++-------
 include/acpi/acpi_bus.h |  1 -
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 9a9298994e26..3bf7764659a4 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -667,8 +667,14 @@ static ssize_t
 acpi_device_sun_show(struct device *dev, struct device_attribute *attr,
 		     char *buf) {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	acpi_status status;
+	unsigned long long sun;
+
+	status = acpi_evaluate_integer(acpi_dev->handle, "_SUN", NULL, &sun);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
 
-	return sprintf(buf, "%lu\n", acpi_dev->pnp.sun);
+	return sprintf(buf, "%llu\n", sun);
 }
 static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL);
 
@@ -690,7 +696,6 @@ static int acpi_device_setup_files(struct acpi_device *dev)
 {
 	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
 	acpi_status status;
-	unsigned long long sun;
 	int result = 0;
 
 	/*
@@ -731,14 +736,10 @@ static int acpi_device_setup_files(struct acpi_device *dev)
 	if (dev->pnp.unique_id)
 		result = device_create_file(&dev->dev, &dev_attr_uid);
 
-	status = acpi_evaluate_integer(dev->handle, "_SUN", NULL, &sun);
-	if (ACPI_SUCCESS(status)) {
-		dev->pnp.sun = (unsigned long)sun;
+	if (acpi_has_method(dev->handle, "_SUN")) {
 		result = device_create_file(&dev->dev, &dev_attr_sun);
 		if (result)
 			goto end;
-	} else {
-		dev->pnp.sun = (unsigned long)-1;
 	}
 
 	if (acpi_has_method(dev->handle, "_STA")) {
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index bcfd808b1098..c1c9de19edbe 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -246,7 +246,6 @@ struct acpi_device_pnp {
 	acpi_device_name device_name;	/* Driver-determined */
 	acpi_device_class device_class;	/*        "          */
 	union acpi_object *str_obj;	/* unicode string for _STR method */
-	unsigned long sun;		/* _SUN */
 };
 
 #define acpi_device_bid(d)	((d)->pnp.bus_id)
-- 
cgit v1.2.3


From a4412fc9486ec85686c6c7929e7e829f62ae377e Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@amacapital.net>
Date: Mon, 21 Jul 2014 18:49:14 -0700
Subject: seccomp,x86,arm,mips,s390: Remove nr parameter from secure_computing

The secure_computing function took a syscall number parameter, but
it only paid any attention to that parameter if seccomp mode 1 was
enabled.  Rather than coming up with a kludge to get the parameter
to work in mode 2, just remove the parameter.

To avoid churn in arches that don't have seccomp filters (and may
not even support syscall_get_nr right now), this leaves the
parameter in secure_computing_strict, which is now a real function.

For ARM, this is a bit ugly due to the fact that ARM conditionally
supports seccomp filters.  Fixing that would probably only be a
couple of lines of code, but it should be coordinated with the audit
maintainers.

This will be a slight slowdown on some arches.  The right fix is to
pass in all of seccomp_data instead of trying to make just the
syscall nr part be fast.

This is a prerequisite for making two-phase seccomp work cleanly.

Cc: Russell King <linux@arm.linux.org.uk>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux-s390@vger.kernel.org
Cc: x86@kernel.org
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 arch/arm/kernel/ptrace.c      |  7 ++++-
 arch/mips/kernel/ptrace.c     |  2 +-
 arch/s390/kernel/ptrace.c     |  2 +-
 arch/x86/kernel/ptrace.c      |  2 +-
 arch/x86/kernel/vsyscall_64.c |  2 +-
 include/linux/seccomp.h       | 21 +++++++-------
 kernel/seccomp.c              | 64 ++++++++++++++++++++++++++++++-------------
 7 files changed, 66 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 0c27ed6f3f23..5e772a21ab97 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -933,8 +933,13 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
 	current_thread_info()->syscall = scno;
 
 	/* Do the secure computing check first; failures should be fast. */
-	if (secure_computing(scno) == -1)
+#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
+	if (secure_computing() == -1)
 		return -1;
+#else
+	/* XXX: remove this once OABI gets fixed */
+	secure_computing_strict(scno);
+#endif
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 645b3c4fcfba..f7aac5b57b4b 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -770,7 +770,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 	long ret = 0;
 	user_exit();
 
-	if (secure_computing(syscall) == -1)
+	if (secure_computing() == -1)
 		return -1;
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 5dc7ad9e2fbf..bebacad48305 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -803,7 +803,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	long ret = 0;
 
 	/* Do the secure computing check first. */
-	if (secure_computing(regs->gprs[2])) {
+	if (secure_computing()) {
 		/* seccomp failures shouldn't expose any additional code. */
 		ret = -1;
 		goto out;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 678c0ada3b3c..93c182a00506 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1471,7 +1471,7 @@ long syscall_trace_enter(struct pt_regs *regs)
 		regs->flags |= X86_EFLAGS_TF;
 
 	/* do the secure computing check first */
-	if (secure_computing(regs->orig_ax)) {
+	if (secure_computing()) {
 		/* seccomp failures shouldn't expose any additional code. */
 		ret = -1L;
 		goto out;
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index e1e1e80fc6a6..957779f4eb40 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -216,7 +216,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 	 */
 	regs->orig_ax = syscall_nr;
 	regs->ax = -ENOSYS;
-	tmp = secure_computing(syscall_nr);
+	tmp = secure_computing();
 	if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
 		warn_bad_vsyscall(KERN_DEBUG, regs,
 				  "seccomp tried to change syscall nr or ip");
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 5d586a45a319..aa3c040230be 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -27,19 +27,17 @@ struct seccomp {
 	struct seccomp_filter *filter;
 };
 
-extern int __secure_computing(int);
-static inline int secure_computing(int this_syscall)
+#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
+extern int __secure_computing(void);
+static inline int secure_computing(void)
 {
 	if (unlikely(test_thread_flag(TIF_SECCOMP)))
-		return  __secure_computing(this_syscall);
+		return  __secure_computing();
 	return 0;
 }
-
-/* A wrapper for architectures supporting only SECCOMP_MODE_STRICT. */
-static inline void secure_computing_strict(int this_syscall)
-{
-	BUG_ON(secure_computing(this_syscall) != 0);
-}
+#else
+extern void secure_computing_strict(int this_syscall);
+#endif
 
 extern long prctl_get_seccomp(void);
 extern long prctl_set_seccomp(unsigned long, char __user *);
@@ -56,8 +54,11 @@ static inline int seccomp_mode(struct seccomp *s)
 struct seccomp { };
 struct seccomp_filter { };
 
-static inline int secure_computing(int this_syscall) { return 0; }
+#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
+static inline int secure_computing(void) { return 0; }
+#else
 static inline void secure_computing_strict(int this_syscall) { return; }
+#endif
 
 static inline long prctl_get_seccomp(void)
 {
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 44eb005c6695..5e738e0dd2e9 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -23,8 +23,11 @@
 
 /* #define SECCOMP_DEBUG 1 */
 
-#ifdef CONFIG_SECCOMP_FILTER
+#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 #include <asm/syscall.h>
+#endif
+
+#ifdef CONFIG_SECCOMP_FILTER
 #include <linux/filter.h>
 #include <linux/pid.h>
 #include <linux/ptrace.h>
@@ -172,7 +175,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
  *
  * Returns valid seccomp BPF response codes.
  */
-static u32 seccomp_run_filters(int syscall)
+static u32 seccomp_run_filters(void)
 {
 	struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter);
 	struct seccomp_data sd;
@@ -564,10 +567,43 @@ static int mode1_syscalls_32[] = {
 };
 #endif
 
-int __secure_computing(int this_syscall)
+static void __secure_computing_strict(int this_syscall)
+{
+	int *syscall_whitelist = mode1_syscalls;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task())
+		syscall_whitelist = mode1_syscalls_32;
+#endif
+	do {
+		if (*syscall_whitelist == this_syscall)
+			return;
+	} while (*++syscall_whitelist);
+
+#ifdef SECCOMP_DEBUG
+	dump_stack();
+#endif
+	audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL);
+	do_exit(SIGKILL);
+}
+
+#ifndef CONFIG_HAVE_ARCH_SECCOMP_FILTER
+void secure_computing_strict(int this_syscall)
+{
+	int mode = current->seccomp.mode;
+
+	if (mode == 0)
+		return;
+	else if (mode == SECCOMP_MODE_STRICT)
+		__secure_computing_strict(this_syscall);
+	else
+		BUG();
+}
+#else
+int __secure_computing(void)
 {
+	struct pt_regs *regs = task_pt_regs(current);
+	int this_syscall = syscall_get_nr(current, regs);
 	int exit_sig = 0;
-	int *syscall;
 	u32 ret;
 
 	/*
@@ -578,23 +614,12 @@ int __secure_computing(int this_syscall)
 
 	switch (current->seccomp.mode) {
 	case SECCOMP_MODE_STRICT:
-		syscall = mode1_syscalls;
-#ifdef CONFIG_COMPAT
-		if (is_compat_task())
-			syscall = mode1_syscalls_32;
-#endif
-		do {
-			if (*syscall == this_syscall)
-				return 0;
-		} while (*++syscall);
-		exit_sig = SIGKILL;
-		ret = SECCOMP_RET_KILL;
-		break;
+		__secure_computing_strict(this_syscall);
+		return 0;
 #ifdef CONFIG_SECCOMP_FILTER
 	case SECCOMP_MODE_FILTER: {
 		int data;
-		struct pt_regs *regs = task_pt_regs(current);
-		ret = seccomp_run_filters(this_syscall);
+		ret = seccomp_run_filters();
 		data = ret & SECCOMP_RET_DATA;
 		ret &= SECCOMP_RET_ACTION;
 		switch (ret) {
@@ -652,9 +677,10 @@ int __secure_computing(int this_syscall)
 #ifdef CONFIG_SECCOMP_FILTER
 skip:
 	audit_seccomp(this_syscall, exit_sig, ret);
-#endif
 	return -1;
+#endif
 }
+#endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */
 
 long prctl_get_seccomp(void)
 {
-- 
cgit v1.2.3


From 13aa72f0fd0a9f98a41cefb662487269e2f1ad65 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@amacapital.net>
Date: Mon, 21 Jul 2014 18:49:15 -0700
Subject: seccomp: Refactor the filter callback and the API

The reason I did this is to add a seccomp API that will be usable
for an x86 fast path.  The x86 entry code needs to use a rather
expensive slow path for a syscall that might be visible to things
like ptrace.  By splitting seccomp into two phases, we can check
whether we need the slow path and then use the fast path in if the
filter allows the syscall or just returns some errno.

As a side effect, I think the new code is much easier to understand
than the old code.

This has one user-visible effect: the audit record written for
SECCOMP_RET_TRACE is now a simple indication that SECCOMP_RET_TRACE
happened.  It used to depend in a complicated way on what the tracer
did.  I couldn't make much sense of it.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/seccomp.h |   6 ++
 kernel/seccomp.c        | 190 +++++++++++++++++++++++++++++++-----------------
 2 files changed, 130 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index aa3c040230be..38851085e481 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -35,6 +35,12 @@ static inline int secure_computing(void)
 		return  __secure_computing();
 	return 0;
 }
+
+#define SECCOMP_PHASE1_OK	0
+#define SECCOMP_PHASE1_SKIP	1
+
+extern u32 seccomp_phase1(void);
+int seccomp_phase2(u32 phase1_result);
 #else
 extern void secure_computing_strict(int this_syscall);
 #endif
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 5e738e0dd2e9..6c8528ce9df9 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -21,8 +21,6 @@
 #include <linux/slab.h>
 #include <linux/syscalls.h>
 
-/* #define SECCOMP_DEBUG 1 */
-
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 #include <asm/syscall.h>
 #endif
@@ -601,10 +599,21 @@ void secure_computing_strict(int this_syscall)
 #else
 int __secure_computing(void)
 {
-	struct pt_regs *regs = task_pt_regs(current);
-	int this_syscall = syscall_get_nr(current, regs);
-	int exit_sig = 0;
-	u32 ret;
+	u32 phase1_result = seccomp_phase1();
+
+	if (likely(phase1_result == SECCOMP_PHASE1_OK))
+		return 0;
+	else if (likely(phase1_result == SECCOMP_PHASE1_SKIP))
+		return -1;
+	else
+		return seccomp_phase2(phase1_result);
+}
+
+#ifdef CONFIG_SECCOMP_FILTER
+static u32 __seccomp_phase1_filter(int this_syscall, struct pt_regs *regs)
+{
+	u32 filter_ret, action;
+	int data;
 
 	/*
 	 * Make sure that any changes to mode from another thread have
@@ -612,73 +621,122 @@ int __secure_computing(void)
 	 */
 	rmb();
 
-	switch (current->seccomp.mode) {
+	filter_ret = seccomp_run_filters();
+	data = filter_ret & SECCOMP_RET_DATA;
+	action = filter_ret & SECCOMP_RET_ACTION;
+
+	switch (action) {
+	case SECCOMP_RET_ERRNO:
+		/* Set the low-order 16-bits as a errno. */
+		syscall_set_return_value(current, regs,
+					 -data, 0);
+		goto skip;
+
+	case SECCOMP_RET_TRAP:
+		/* Show the handler the original registers. */
+		syscall_rollback(current, regs);
+		/* Let the filter pass back 16 bits of data. */
+		seccomp_send_sigsys(this_syscall, data);
+		goto skip;
+
+	case SECCOMP_RET_TRACE:
+		return filter_ret;  /* Save the rest for phase 2. */
+
+	case SECCOMP_RET_ALLOW:
+		return SECCOMP_PHASE1_OK;
+
+	case SECCOMP_RET_KILL:
+	default:
+		audit_seccomp(this_syscall, SIGSYS, action);
+		do_exit(SIGSYS);
+	}
+
+	unreachable();
+
+skip:
+	audit_seccomp(this_syscall, 0, action);
+	return SECCOMP_PHASE1_SKIP;
+}
+#endif
+
+/**
+ * seccomp_phase1() - run fast path seccomp checks on the current syscall
+ *
+ * This only reads pt_regs via the syscall_xyz helpers.  The only change
+ * it will make to pt_regs is via syscall_set_return_value, and it will
+ * only do that if it returns SECCOMP_PHASE1_SKIP.
+ *
+ * It may also call do_exit or force a signal; these actions must be
+ * safe.
+ *
+ * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should
+ * be processed normally.
+ *
+ * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be
+ * invoked.  In this case, seccomp_phase1 will have set the return value
+ * using syscall_set_return_value.
+ *
+ * If it returns anything else, then the return value should be passed
+ * to seccomp_phase2 from a context in which ptrace hooks are safe.
+ */
+u32 seccomp_phase1(void)
+{
+	int mode = current->seccomp.mode;
+	struct pt_regs *regs = task_pt_regs(current);
+	int this_syscall = syscall_get_nr(current, regs);
+
+	switch (mode) {
 	case SECCOMP_MODE_STRICT:
-		__secure_computing_strict(this_syscall);
-		return 0;
+		__secure_computing_strict(this_syscall);  /* may call do_exit */
+		return SECCOMP_PHASE1_OK;
 #ifdef CONFIG_SECCOMP_FILTER
-	case SECCOMP_MODE_FILTER: {
-		int data;
-		ret = seccomp_run_filters();
-		data = ret & SECCOMP_RET_DATA;
-		ret &= SECCOMP_RET_ACTION;
-		switch (ret) {
-		case SECCOMP_RET_ERRNO:
-			/* Set the low-order 16-bits as a errno. */
-			syscall_set_return_value(current, regs,
-						 -data, 0);
-			goto skip;
-		case SECCOMP_RET_TRAP:
-			/* Show the handler the original registers. */
-			syscall_rollback(current, regs);
-			/* Let the filter pass back 16 bits of data. */
-			seccomp_send_sigsys(this_syscall, data);
-			goto skip;
-		case SECCOMP_RET_TRACE:
-			/* Skip these calls if there is no tracer. */
-			if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
-				syscall_set_return_value(current, regs,
-							 -ENOSYS, 0);
-				goto skip;
-			}
-			/* Allow the BPF to provide the event message */
-			ptrace_event(PTRACE_EVENT_SECCOMP, data);
-			/*
-			 * The delivery of a fatal signal during event
-			 * notification may silently skip tracer notification.
-			 * Terminating the task now avoids executing a system
-			 * call that may not be intended.
-			 */
-			if (fatal_signal_pending(current))
-				break;
-			if (syscall_get_nr(current, regs) < 0)
-				goto skip;  /* Explicit request to skip. */
-
-			return 0;
-		case SECCOMP_RET_ALLOW:
-			return 0;
-		case SECCOMP_RET_KILL:
-		default:
-			break;
-		}
-		exit_sig = SIGSYS;
-		break;
-	}
+	case SECCOMP_MODE_FILTER:
+		return __seccomp_phase1_filter(this_syscall, regs);
 #endif
 	default:
 		BUG();
 	}
+}
 
-#ifdef SECCOMP_DEBUG
-	dump_stack();
-#endif
-	audit_seccomp(this_syscall, exit_sig, ret);
-	do_exit(exit_sig);
-#ifdef CONFIG_SECCOMP_FILTER
-skip:
-	audit_seccomp(this_syscall, exit_sig, ret);
-	return -1;
-#endif
+/**
+ * seccomp_phase2() - finish slow path seccomp work for the current syscall
+ * @phase1_result: The return value from seccomp_phase1()
+ *
+ * This must be called from a context in which ptrace hooks can be used.
+ *
+ * Returns 0 if the syscall should be processed or -1 to skip the syscall.
+ */
+int seccomp_phase2(u32 phase1_result)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	u32 action = phase1_result & SECCOMP_RET_ACTION;
+	int data = phase1_result & SECCOMP_RET_DATA;
+
+	BUG_ON(action != SECCOMP_RET_TRACE);
+
+	audit_seccomp(syscall_get_nr(current, regs), 0, action);
+
+	/* Skip these calls if there is no tracer. */
+	if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
+		syscall_set_return_value(current, regs,
+					 -ENOSYS, 0);
+		return -1;
+	}
+
+	/* Allow the BPF to provide the event message */
+	ptrace_event(PTRACE_EVENT_SECCOMP, data);
+	/*
+	 * The delivery of a fatal signal during event
+	 * notification may silently skip tracer notification.
+	 * Terminating the task now avoids executing a system
+	 * call that may not be intended.
+	 */
+	if (fatal_signal_pending(current))
+		do_exit(SIGSYS);
+	if (syscall_get_nr(current, regs) < 0)
+		return -1;  /* Explicit request to skip. */
+
+	return 0;
 }
 #endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */
 
-- 
cgit v1.2.3


From d39bd00deabe57420f2a3669eb71b0e0c4997184 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@amacapital.net>
Date: Mon, 21 Jul 2014 18:49:16 -0700
Subject: seccomp: Allow arch code to provide seccomp_data

populate_seccomp_data is expensive: it works by inspecting
task_pt_regs and various other bits to piece together all the
information, and it's does so in multiple partially redundant steps.

Arch-specific code in the syscall entry path can do much better.

Admittedly this adds a bit of additional room for error, but the
speedup should be worth it.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/seccomp.h |  2 +-
 kernel/seccomp.c        | 32 +++++++++++++++++++-------------
 2 files changed, 20 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 38851085e481..a19ddacdac30 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -39,7 +39,7 @@ static inline int secure_computing(void)
 #define SECCOMP_PHASE1_OK	0
 #define SECCOMP_PHASE1_SKIP	1
 
-extern u32 seccomp_phase1(void);
+extern u32 seccomp_phase1(struct seccomp_data *sd);
 int seccomp_phase2(u32 phase1_result);
 #else
 extern void secure_computing_strict(int this_syscall);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 6c8528ce9df9..1285cb205d49 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -173,10 +173,10 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
  *
  * Returns valid seccomp BPF response codes.
  */
-static u32 seccomp_run_filters(void)
+static u32 seccomp_run_filters(struct seccomp_data *sd)
 {
 	struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter);
-	struct seccomp_data sd;
+	struct seccomp_data sd_local;
 	u32 ret = SECCOMP_RET_ALLOW;
 
 	/* Ensure unexpected behavior doesn't result in failing open. */
@@ -186,14 +186,17 @@ static u32 seccomp_run_filters(void)
 	/* Make sure cross-thread synced filter points somewhere sane. */
 	smp_read_barrier_depends();
 
-	populate_seccomp_data(&sd);
+	if (!sd) {
+		populate_seccomp_data(&sd_local);
+		sd = &sd_local;
+	}
 
 	/*
 	 * All filters in the list are evaluated and the lowest BPF return
 	 * value always takes priority (ignoring the DATA).
 	 */
 	for (; f; f = f->prev) {
-		u32 cur_ret = BPF_PROG_RUN(f->prog, (void *)&sd);
+		u32 cur_ret = BPF_PROG_RUN(f->prog, (void *)sd);
 
 		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
 			ret = cur_ret;
@@ -599,7 +602,7 @@ void secure_computing_strict(int this_syscall)
 #else
 int __secure_computing(void)
 {
-	u32 phase1_result = seccomp_phase1();
+	u32 phase1_result = seccomp_phase1(NULL);
 
 	if (likely(phase1_result == SECCOMP_PHASE1_OK))
 		return 0;
@@ -610,7 +613,7 @@ int __secure_computing(void)
 }
 
 #ifdef CONFIG_SECCOMP_FILTER
-static u32 __seccomp_phase1_filter(int this_syscall, struct pt_regs *regs)
+static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
 {
 	u32 filter_ret, action;
 	int data;
@@ -621,20 +624,20 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct pt_regs *regs)
 	 */
 	rmb();
 
-	filter_ret = seccomp_run_filters();
+	filter_ret = seccomp_run_filters(sd);
 	data = filter_ret & SECCOMP_RET_DATA;
 	action = filter_ret & SECCOMP_RET_ACTION;
 
 	switch (action) {
 	case SECCOMP_RET_ERRNO:
 		/* Set the low-order 16-bits as a errno. */
-		syscall_set_return_value(current, regs,
+		syscall_set_return_value(current, task_pt_regs(current),
 					 -data, 0);
 		goto skip;
 
 	case SECCOMP_RET_TRAP:
 		/* Show the handler the original registers. */
-		syscall_rollback(current, regs);
+		syscall_rollback(current, task_pt_regs(current));
 		/* Let the filter pass back 16 bits of data. */
 		seccomp_send_sigsys(this_syscall, data);
 		goto skip;
@@ -661,11 +664,14 @@ skip:
 
 /**
  * seccomp_phase1() - run fast path seccomp checks on the current syscall
+ * @arg sd: The seccomp_data or NULL
  *
  * This only reads pt_regs via the syscall_xyz helpers.  The only change
  * it will make to pt_regs is via syscall_set_return_value, and it will
  * only do that if it returns SECCOMP_PHASE1_SKIP.
  *
+ * If sd is provided, it will not read pt_regs at all.
+ *
  * It may also call do_exit or force a signal; these actions must be
  * safe.
  *
@@ -679,11 +685,11 @@ skip:
  * If it returns anything else, then the return value should be passed
  * to seccomp_phase2 from a context in which ptrace hooks are safe.
  */
-u32 seccomp_phase1(void)
+u32 seccomp_phase1(struct seccomp_data *sd)
 {
 	int mode = current->seccomp.mode;
-	struct pt_regs *regs = task_pt_regs(current);
-	int this_syscall = syscall_get_nr(current, regs);
+	int this_syscall = sd ? sd->nr :
+		syscall_get_nr(current, task_pt_regs(current));
 
 	switch (mode) {
 	case SECCOMP_MODE_STRICT:
@@ -691,7 +697,7 @@ u32 seccomp_phase1(void)
 		return SECCOMP_PHASE1_OK;
 #ifdef CONFIG_SECCOMP_FILTER
 	case SECCOMP_MODE_FILTER:
-		return __seccomp_phase1_filter(this_syscall, regs);
+		return __seccomp_phase1_filter(this_syscall, sd);
 #endif
 	default:
 		BUG();
-- 
cgit v1.2.3


From 26ae4980b5e4739af93543a147facb421fb78ae8 Mon Sep 17 00:00:00 2001
From: Aaron Sierra <asierra@xes-inc.com>
Date: Fri, 15 Aug 2014 16:07:48 -0500
Subject: fsl_ifc: Fix csor_ext position in fsl_ifc_regs

According to Freescale manuals, the IFC_CSORn_EXT register is located
immediately _after_ the bank's IFC_CSORn register.

This patch adjusts the csor_ext member of and reserved register arrays
immediately surrounding the csor_cs structure to provide proper access
to this register.

Signed-off-by: Aaron Sierra <asierra@xes-inc.com>
Acked-by: Prabhakar Kushwaha <prabhakar@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
 include/linux/fsl_ifc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h
index f49ddb1b2273..84d60cb841b1 100644
--- a/include/linux/fsl_ifc.h
+++ b/include/linux/fsl_ifc.h
@@ -781,13 +781,13 @@ struct fsl_ifc_regs {
 		__be32 amask;
 		u32 res4[0x2];
 	} amask_cs[FSL_IFC_BANK_COUNT];
-	u32 res5[0x17];
+	u32 res5[0x18];
 	struct {
-		__be32 csor_ext;
 		__be32 csor;
+		__be32 csor_ext;
 		u32 res6;
 	} csor_cs[FSL_IFC_BANK_COUNT];
-	u32 res7[0x19];
+	u32 res7[0x18];
 	struct {
 		__be32 ftim[4];
 		u32 res8[0x8];
-- 
cgit v1.2.3


From 940001762ac514810e305aab356983829e5fa82a Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Wed, 3 Sep 2014 09:22:36 +0800
Subject: lib/rhashtable: allow user to set the minimum shifts of shrinking

Although rhashtable library allows user to specify a quiet big size
for user's created hash table, the table may be shrunk to a
very small size - HASH_MIN_SIZE(4) after object is removed from
the table at the first time. Subsequently, even if the total amount
of objects saved in the table is quite lower than user's initial
setting in a long time, the hash table size is still dynamically
adjusted by rhashtable_shrink() or rhashtable_expand() each time
object is inserted or removed from the table. However, as
synchronize_rcu() has to be called when table is shrunk or
expanded by the two functions, we should permit user to set the
minimum table size through configuring the minimum number of shifts
according to user specific requirement, avoiding these expensive
actions of shrinking or expanding because of calling synchronize_rcu().

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  2 ++
 lib/rhashtable.c           | 12 ++++++++----
 2 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 36826c0166c5..fb298e9d6d3a 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -44,6 +44,7 @@ struct rhashtable;
  * @head_offset: Offset of rhash_head in struct to be hashed
  * @hash_rnd: Seed to use while hashing
  * @max_shift: Maximum number of shifts while expanding
+ * @min_shift: Minimum number of shifts while shrinking
  * @hashfn: Function to hash key
  * @obj_hashfn: Function to hash object
  * @grow_decision: If defined, may return true if table should expand
@@ -57,6 +58,7 @@ struct rhashtable_params {
 	size_t			head_offset;
 	u32			hash_rnd;
 	size_t			max_shift;
+	size_t			min_shift;
 	rht_hashfn_t		hashfn;
 	rht_obj_hashfn_t	obj_hashfn;
 	bool			(*grow_decision)(const struct rhashtable *ht,
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index a2c78810ebc1..8dfec3f26d4c 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -298,7 +298,7 @@ int rhashtable_shrink(struct rhashtable *ht, gfp_t flags)
 
 	ASSERT_RHT_MUTEX(ht);
 
-	if (tbl->size <= HASH_MIN_SIZE)
+	if (ht->shift <= ht->p.min_shift)
 		return 0;
 
 	ntbl = bucket_table_alloc(tbl->size / 2, flags);
@@ -506,9 +506,10 @@ void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
 }
 EXPORT_SYMBOL_GPL(rhashtable_lookup_compare);
 
-static size_t rounded_hashtable_size(unsigned int nelem)
+static size_t rounded_hashtable_size(struct rhashtable_params *params)
 {
-	return max(roundup_pow_of_two(nelem * 4 / 3), HASH_MIN_SIZE);
+	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
+		   1UL << params->min_shift);
 }
 
 /**
@@ -566,8 +567,11 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
 	    (!params->key_len && !params->obj_hashfn))
 		return -EINVAL;
 
+	params->min_shift = max_t(size_t, params->min_shift,
+				  ilog2(HASH_MIN_SIZE));
+
 	if (params->nelem_hint)
-		size = rounded_hashtable_size(params->nelem_hint);
+		size = rounded_hashtable_size(params);
 
 	tbl = bucket_table_alloc(size, GFP_KERNEL);
 	if (tbl == NULL)
-- 
cgit v1.2.3


From 03e9f0cac5da6af85758276cb4624caf5911f2b9 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 3 Sep 2014 13:02:56 +0200
Subject: pinctrl: clean up after enable refactoring

commit 2243a87d90b42eb38bc281957df3e57c712b5e56
"pinctrl: avoid duplicated calling enable_pinmux_setting for a pin"
removed the .disable callback from the struct pinmux_ops,
making the .enable() callback the only remaining callback.

However .enable() is a bad name as it seems to imply that a
muxing can also be disabled. Rename the callback to .set_mux()
and also take this opportunity to clean out any remaining
mentions of .disable() from the documentation.

Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Bjorn Andersson <bjorn.andersson@sonymobile.com>
Acked-by: Fan Wu <fwu@marvell.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/pinctrl.txt                    | 14 ++------------
 drivers/pinctrl/berlin/berlin.c              |  8 ++++----
 drivers/pinctrl/mvebu/pinctrl-mvebu.c        |  6 +++---
 drivers/pinctrl/nomadik/pinctrl-abx500.c     |  6 +++---
 drivers/pinctrl/nomadik/pinctrl-nomadik.c    |  6 +++---
 drivers/pinctrl/pinctrl-adi2.c               |  6 +++---
 drivers/pinctrl/pinctrl-as3722.c             |  4 ++--
 drivers/pinctrl/pinctrl-at91.c               |  6 +++---
 drivers/pinctrl/pinctrl-bcm281xx.c           |  8 ++++----
 drivers/pinctrl/pinctrl-bcm2835.c            |  4 ++--
 drivers/pinctrl/pinctrl-imx.c                |  6 +++---
 drivers/pinctrl/pinctrl-imx1-core.c          |  6 +++---
 drivers/pinctrl/pinctrl-lantiq.c             |  8 ++++----
 drivers/pinctrl/pinctrl-mxs.c                |  6 +++---
 drivers/pinctrl/pinctrl-palmas.c             |  5 +++--
 drivers/pinctrl/pinctrl-rockchip.c           |  6 +++---
 drivers/pinctrl/pinctrl-single.c             |  4 ++--
 drivers/pinctrl/pinctrl-st.c                 |  6 +++---
 drivers/pinctrl/pinctrl-tb10x.c              |  4 ++--
 drivers/pinctrl/pinctrl-tegra-xusb.c         |  8 ++++----
 drivers/pinctrl/pinctrl-tegra.c              |  7 ++++---
 drivers/pinctrl/pinctrl-tz1090-pdc.c         |  7 ++++---
 drivers/pinctrl/pinctrl-tz1090.c             |  6 +++---
 drivers/pinctrl/pinctrl-u300.c               |  6 +++---
 drivers/pinctrl/pinmux.c                     | 10 +++++-----
 drivers/pinctrl/qcom/pinctrl-msm.c           |  8 ++++----
 drivers/pinctrl/samsung/pinctrl-exynos5440.c |  7 ++++---
 drivers/pinctrl/samsung/pinctrl-samsung.c    |  7 ++++---
 drivers/pinctrl/sh-pfc/pinctrl.c             |  6 +++---
 drivers/pinctrl/sirf/pinctrl-sirf.c          |  7 ++++---
 drivers/pinctrl/spear/pinctrl-spear.c        |  4 ++--
 drivers/pinctrl/sunxi/pinctrl-sunxi.c        |  8 ++++----
 drivers/pinctrl/vt8500/pinctrl-wmt.c         |  8 ++++----
 include/linux/pinctrl/pinmux.h               |  7 +++----
 34 files changed, 110 insertions(+), 115 deletions(-)

(limited to 'include')

diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index 23f1590f49fe..b8f2147b96dd 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -702,7 +702,7 @@ static int foo_get_groups(struct pinctrl_dev *pctldev, unsigned selector,
 	return 0;
 }
 
-int foo_enable(struct pinctrl_dev *pctldev, unsigned selector,
+int foo_set_mux(struct pinctrl_dev *pctldev, unsigned selector,
 		unsigned group)
 {
 	u8 regbit = (1 << selector + group);
@@ -711,21 +711,11 @@ int foo_enable(struct pinctrl_dev *pctldev, unsigned selector,
 	return 0;
 }
 
-void foo_disable(struct pinctrl_dev *pctldev, unsigned selector,
-		unsigned group)
-{
-	u8 regbit = (1 << selector + group);
-
-	writeb((readb(MUX) & ~(regbit)), MUX)
-	return 0;
-}
-
 struct pinmux_ops foo_pmxops = {
 	.get_functions_count = foo_get_functions_count,
 	.get_function_name = foo_get_fname,
 	.get_function_groups = foo_get_groups,
-	.enable = foo_enable,
-	.disable = foo_disable,
+	.set_mux = foo_set_mux,
 };
 
 /* Pinmux operations are handled by some pin controller */
diff --git a/drivers/pinctrl/berlin/berlin.c b/drivers/pinctrl/berlin/berlin.c
index 86db2235ab00..61f1bf0e60ba 100644
--- a/drivers/pinctrl/berlin/berlin.c
+++ b/drivers/pinctrl/berlin/berlin.c
@@ -170,9 +170,9 @@ berlin_pinctrl_find_function_by_name(struct berlin_pinctrl *pctrl,
 	return NULL;
 }
 
-static int berlin_pinmux_enable(struct pinctrl_dev *pctrl_dev,
-				unsigned function,
-				unsigned group)
+static int berlin_pinmux_set(struct pinctrl_dev *pctrl_dev,
+			     unsigned function,
+			     unsigned group)
 {
 	struct berlin_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctrl_dev);
 	const struct berlin_desc_group *group_desc = pctrl->desc->groups + group;
@@ -197,7 +197,7 @@ static const struct pinmux_ops berlin_pinmux_ops = {
 	.get_functions_count	= &berlin_pinmux_get_functions_count,
 	.get_function_name	= &berlin_pinmux_get_function_name,
 	.get_function_groups	= &berlin_pinmux_get_function_groups,
-	.enable			= &berlin_pinmux_enable,
+	.set_mux		= &berlin_pinmux_set,
 };
 
 static int berlin_pinctrl_add_function(struct berlin_pinctrl *pctrl,
diff --git a/drivers/pinctrl/mvebu/pinctrl-mvebu.c b/drivers/pinctrl/mvebu/pinctrl-mvebu.c
index 9908374f8f92..f3b426cdaf8f 100644
--- a/drivers/pinctrl/mvebu/pinctrl-mvebu.c
+++ b/drivers/pinctrl/mvebu/pinctrl-mvebu.c
@@ -259,8 +259,8 @@ static int mvebu_pinmux_get_groups(struct pinctrl_dev *pctldev, unsigned fid,
 	return 0;
 }
 
-static int mvebu_pinmux_enable(struct pinctrl_dev *pctldev, unsigned fid,
-			unsigned gid)
+static int mvebu_pinmux_set(struct pinctrl_dev *pctldev, unsigned fid,
+			    unsigned gid)
 {
 	struct mvebu_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
 	struct mvebu_pinctrl_function *func = &pctl->functions[fid];
@@ -344,7 +344,7 @@ static const struct pinmux_ops mvebu_pinmux_ops = {
 	.get_function_groups = mvebu_pinmux_get_groups,
 	.gpio_request_enable = mvebu_pinmux_gpio_request_enable,
 	.gpio_set_direction = mvebu_pinmux_gpio_set_direction,
-	.enable = mvebu_pinmux_enable,
+	.set_mux = mvebu_pinmux_set,
 };
 
 static int mvebu_pinctrl_get_groups_count(struct pinctrl_dev *pctldev)
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index a53a689a2bfa..b0289824cf73 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -709,8 +709,8 @@ static int abx500_pmx_get_func_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int abx500_pmx_enable(struct pinctrl_dev *pctldev, unsigned function,
-			     unsigned group)
+static int abx500_pmx_set(struct pinctrl_dev *pctldev, unsigned function,
+			  unsigned group)
 {
 	struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev);
 	struct gpio_chip *chip = &pct->chip;
@@ -784,7 +784,7 @@ static const struct pinmux_ops abx500_pinmux_ops = {
 	.get_functions_count = abx500_pmx_get_funcs_cnt,
 	.get_function_name = abx500_pmx_get_func_name,
 	.get_function_groups = abx500_pmx_get_func_groups,
-	.enable = abx500_pmx_enable,
+	.set_mux = abx500_pmx_set,
 	.gpio_request_enable = abx500_gpio_request_enable,
 	.gpio_disable_free = abx500_gpio_disable_free,
 };
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index e7cab07eef47..c093d75a022a 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -1647,8 +1647,8 @@ static int nmk_pmx_get_func_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int nmk_pmx_enable(struct pinctrl_dev *pctldev, unsigned function,
-			  unsigned group)
+static int nmk_pmx_set(struct pinctrl_dev *pctldev, unsigned function,
+		       unsigned group)
 {
 	struct nmk_pinctrl *npct = pinctrl_dev_get_drvdata(pctldev);
 	const struct nmk_pingroup *g;
@@ -1810,7 +1810,7 @@ static const struct pinmux_ops nmk_pinmux_ops = {
 	.get_functions_count = nmk_pmx_get_funcs_cnt,
 	.get_function_name = nmk_pmx_get_func_name,
 	.get_function_groups = nmk_pmx_get_func_groups,
-	.enable = nmk_pmx_enable,
+	.set_mux = nmk_pmx_set,
 	.gpio_request_enable = nmk_gpio_request_enable,
 	.gpio_disable_free = nmk_gpio_disable_free,
 };
diff --git a/drivers/pinctrl/pinctrl-adi2.c b/drivers/pinctrl/pinctrl-adi2.c
index b092b93c67a1..e02943b0285d 100644
--- a/drivers/pinctrl/pinctrl-adi2.c
+++ b/drivers/pinctrl/pinctrl-adi2.c
@@ -619,8 +619,8 @@ static struct pinctrl_ops adi_pctrl_ops = {
 	.get_group_pins = adi_get_group_pins,
 };
 
-static int adi_pinmux_enable(struct pinctrl_dev *pctldev, unsigned func_id,
-	unsigned group_id)
+static int adi_pinmux_set(struct pinctrl_dev *pctldev, unsigned func_id,
+			  unsigned group_id)
 {
 	struct adi_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
 	struct gpio_port *port;
@@ -698,7 +698,7 @@ static int adi_pinmux_request_gpio(struct pinctrl_dev *pctldev,
 }
 
 static struct pinmux_ops adi_pinmux_ops = {
-	.enable = adi_pinmux_enable,
+	.set_mux = adi_pinmux_set,
 	.get_functions_count = adi_pinmux_get_funcs_count,
 	.get_function_name = adi_pinmux_get_func_name,
 	.get_function_groups = adi_pinmux_get_groups,
diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c
index 0e4ec91f4d49..1f790a4b83fe 100644
--- a/drivers/pinctrl/pinctrl-as3722.c
+++ b/drivers/pinctrl/pinctrl-as3722.c
@@ -230,7 +230,7 @@ static int as3722_pinctrl_get_func_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int as3722_pinctrl_enable(struct pinctrl_dev *pctldev, unsigned function,
+static int as3722_pinctrl_set(struct pinctrl_dev *pctldev, unsigned function,
 		unsigned group)
 {
 	struct as3722_pctrl_info *as_pci = pinctrl_dev_get_drvdata(pctldev);
@@ -327,7 +327,7 @@ static const struct pinmux_ops as3722_pinmux_ops = {
 	.get_functions_count	= as3722_pinctrl_get_funcs_count,
 	.get_function_name	= as3722_pinctrl_get_func_name,
 	.get_function_groups	= as3722_pinctrl_get_func_groups,
-	.enable			= as3722_pinctrl_enable,
+	.set_mux		= as3722_pinctrl_set,
 	.gpio_request_enable	= as3722_pinctrl_gpio_request_enable,
 	.gpio_set_direction	= as3722_pinctrl_gpio_set_direction,
 };
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index af1ba4fc150d..4839c36a3a1c 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -554,8 +554,8 @@ static void at91_mux_gpio_enable(void __iomem *pio, unsigned mask, bool input)
 	writel_relaxed(mask, pio + (input ? PIO_ODR : PIO_OER));
 }
 
-static int at91_pmx_enable(struct pinctrl_dev *pctldev, unsigned selector,
-			   unsigned group)
+static int at91_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
+			unsigned group)
 {
 	struct at91_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
 	const struct at91_pmx_pin *pins_conf = info->groups[group].pins_conf;
@@ -684,7 +684,7 @@ static const struct pinmux_ops at91_pmx_ops = {
 	.get_functions_count	= at91_pmx_get_funcs_count,
 	.get_function_name	= at91_pmx_get_func_name,
 	.get_function_groups	= at91_pmx_get_groups,
-	.enable			= at91_pmx_enable,
+	.set_mux		= at91_pmx_set,
 	.gpio_request_enable	= at91_gpio_request_enable,
 	.gpio_disable_free	= at91_gpio_disable_free,
 };
diff --git a/drivers/pinctrl/pinctrl-bcm281xx.c b/drivers/pinctrl/pinctrl-bcm281xx.c
index c5ca9e633fff..a26e0c2ba33e 100644
--- a/drivers/pinctrl/pinctrl-bcm281xx.c
+++ b/drivers/pinctrl/pinctrl-bcm281xx.c
@@ -1055,9 +1055,9 @@ static int bcm281xx_pinctrl_get_fcn_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int bcm281xx_pinmux_enable(struct pinctrl_dev *pctldev,
-				  unsigned function,
-				  unsigned group)
+static int bcm281xx_pinmux_set(struct pinctrl_dev *pctldev,
+			       unsigned function,
+			       unsigned group)
 {
 	struct bcm281xx_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
 	const struct bcm281xx_pin_function *f = &pdata->functions[function];
@@ -1084,7 +1084,7 @@ static struct pinmux_ops bcm281xx_pinctrl_pinmux_ops = {
 	.get_functions_count = bcm281xx_pinctrl_get_fcns_count,
 	.get_function_name = bcm281xx_pinctrl_get_fcn_name,
 	.get_function_groups = bcm281xx_pinctrl_get_fcn_groups,
-	.enable = bcm281xx_pinmux_enable,
+	.set_mux = bcm281xx_pinmux_set,
 };
 
 static int bcm281xx_pinctrl_pin_config_get(struct pinctrl_dev *pctldev,
diff --git a/drivers/pinctrl/pinctrl-bcm2835.c b/drivers/pinctrl/pinctrl-bcm2835.c
index 5bcfd7ace0cd..eabba02f71f9 100644
--- a/drivers/pinctrl/pinctrl-bcm2835.c
+++ b/drivers/pinctrl/pinctrl-bcm2835.c
@@ -830,7 +830,7 @@ static int bcm2835_pmx_get_function_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int bcm2835_pmx_enable(struct pinctrl_dev *pctldev,
+static int bcm2835_pmx_set(struct pinctrl_dev *pctldev,
 		unsigned func_selector,
 		unsigned group_selector)
 {
@@ -869,7 +869,7 @@ static const struct pinmux_ops bcm2835_pmx_ops = {
 	.get_functions_count = bcm2835_pmx_get_functions_count,
 	.get_function_name = bcm2835_pmx_get_function_name,
 	.get_function_groups = bcm2835_pmx_get_function_groups,
-	.enable = bcm2835_pmx_enable,
+	.set_mux = bcm2835_pmx_set,
 	.gpio_disable_free = bcm2835_pmx_gpio_disable_free,
 	.gpio_set_direction = bcm2835_pmx_gpio_set_direction,
 };
diff --git a/drivers/pinctrl/pinctrl-imx.c b/drivers/pinctrl/pinctrl-imx.c
index 946d594a64dd..570e5acb4a6a 100644
--- a/drivers/pinctrl/pinctrl-imx.c
+++ b/drivers/pinctrl/pinctrl-imx.c
@@ -179,8 +179,8 @@ static const struct pinctrl_ops imx_pctrl_ops = {
 
 };
 
-static int imx_pmx_enable(struct pinctrl_dev *pctldev, unsigned selector,
-			   unsigned group)
+static int imx_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
+		       unsigned group)
 {
 	struct imx_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev);
 	const struct imx_pinctrl_soc_info *info = ipctl->info;
@@ -298,7 +298,7 @@ static const struct pinmux_ops imx_pmx_ops = {
 	.get_functions_count = imx_pmx_get_funcs_count,
 	.get_function_name = imx_pmx_get_func_name,
 	.get_function_groups = imx_pmx_get_groups,
-	.enable = imx_pmx_enable,
+	.set_mux = imx_pmx_set,
 };
 
 static int imx_pinconf_get(struct pinctrl_dev *pctldev,
diff --git a/drivers/pinctrl/pinctrl-imx1-core.c b/drivers/pinctrl/pinctrl-imx1-core.c
index 483420757c9f..176a3e62f1cf 100644
--- a/drivers/pinctrl/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/pinctrl-imx1-core.c
@@ -298,8 +298,8 @@ static const struct pinctrl_ops imx1_pctrl_ops = {
 
 };
 
-static int imx1_pmx_enable(struct pinctrl_dev *pctldev, unsigned selector,
-			   unsigned group)
+static int imx1_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
+			unsigned group)
 {
 	struct imx1_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev);
 	const struct imx1_pinctrl_soc_info *info = ipctl->info;
@@ -385,7 +385,7 @@ static const struct pinmux_ops imx1_pmx_ops = {
 	.get_functions_count = imx1_pmx_get_funcs_count,
 	.get_function_name = imx1_pmx_get_func_name,
 	.get_function_groups = imx1_pmx_get_groups,
-	.enable = imx1_pmx_enable,
+	.set_mux = imx1_pmx_set,
 };
 
 static int imx1_pinconf_get(struct pinctrl_dev *pctldev,
diff --git a/drivers/pinctrl/pinctrl-lantiq.c b/drivers/pinctrl/pinctrl-lantiq.c
index d22ca252b80d..296e5b37f768 100644
--- a/drivers/pinctrl/pinctrl-lantiq.c
+++ b/drivers/pinctrl/pinctrl-lantiq.c
@@ -257,9 +257,9 @@ static int match_group_mux(const struct ltq_pin_group *grp,
 	return ret;
 }
 
-static int ltq_pmx_enable(struct pinctrl_dev *pctrldev,
-				unsigned func,
-				unsigned group)
+static int ltq_pmx_set(struct pinctrl_dev *pctrldev,
+		       unsigned func,
+		       unsigned group)
 {
 	struct ltq_pinmux_info *info = pinctrl_dev_get_drvdata(pctrldev);
 	const struct ltq_pin_group *pin_grp = &info->grps[group];
@@ -316,7 +316,7 @@ static const struct pinmux_ops ltq_pmx_ops = {
 	.get_functions_count	= ltq_pmx_func_count,
 	.get_function_name	= ltq_pmx_func_name,
 	.get_function_groups	= ltq_pmx_get_groups,
-	.enable			= ltq_pmx_enable,
+	.set_mux		= ltq_pmx_set,
 	.gpio_request_enable	= ltq_pmx_gpio_request_enable,
 };
 
diff --git a/drivers/pinctrl/pinctrl-mxs.c b/drivers/pinctrl/pinctrl-mxs.c
index 40c76f26998c..67035091f8fd 100644
--- a/drivers/pinctrl/pinctrl-mxs.c
+++ b/drivers/pinctrl/pinctrl-mxs.c
@@ -195,8 +195,8 @@ static int mxs_pinctrl_get_func_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int mxs_pinctrl_enable(struct pinctrl_dev *pctldev, unsigned selector,
-			      unsigned group)
+static int mxs_pinctrl_set_mux(struct pinctrl_dev *pctldev, unsigned selector,
+			       unsigned group)
 {
 	struct mxs_pinctrl_data *d = pinctrl_dev_get_drvdata(pctldev);
 	struct mxs_group *g = &d->soc->groups[group];
@@ -223,7 +223,7 @@ static const struct pinmux_ops mxs_pinmux_ops = {
 	.get_functions_count = mxs_pinctrl_get_funcs_count,
 	.get_function_name = mxs_pinctrl_get_func_name,
 	.get_function_groups = mxs_pinctrl_get_func_groups,
-	.enable = mxs_pinctrl_enable,
+	.set_mux = mxs_pinctrl_set_mux,
 };
 
 static int mxs_pinconf_get(struct pinctrl_dev *pctldev,
diff --git a/drivers/pinctrl/pinctrl-palmas.c b/drivers/pinctrl/pinctrl-palmas.c
index f13d0e78a41c..e3079d3d19fe 100644
--- a/drivers/pinctrl/pinctrl-palmas.c
+++ b/drivers/pinctrl/pinctrl-palmas.c
@@ -685,7 +685,8 @@ static int palmas_pinctrl_get_func_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int palmas_pinctrl_enable(struct pinctrl_dev *pctldev, unsigned function,
+static int palmas_pinctrl_set_mux(struct pinctrl_dev *pctldev,
+		unsigned function,
 		unsigned group)
 {
 	struct palmas_pctrl_chip_info *pci = pinctrl_dev_get_drvdata(pctldev);
@@ -742,7 +743,7 @@ static const struct pinmux_ops palmas_pinmux_ops = {
 	.get_functions_count = palmas_pinctrl_get_funcs_count,
 	.get_function_name = palmas_pinctrl_get_func_name,
 	.get_function_groups = palmas_pinctrl_get_func_groups,
-	.enable = palmas_pinctrl_enable,
+	.set_mux = palmas_pinctrl_set_mux,
 };
 
 static int palmas_pinconf_get(struct pinctrl_dev *pctldev,
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 5e8b2e04cd7a..b91b966add8f 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -813,8 +813,8 @@ static int rockchip_pmx_get_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int rockchip_pmx_enable(struct pinctrl_dev *pctldev, unsigned selector,
-							    unsigned group)
+static int rockchip_pmx_set(struct pinctrl_dev *pctldev, unsigned selector,
+			    unsigned group)
 {
 	struct rockchip_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
 	const unsigned int *pins = info->groups[group].pins;
@@ -889,7 +889,7 @@ static const struct pinmux_ops rockchip_pmx_ops = {
 	.get_functions_count	= rockchip_pmx_get_funcs_count,
 	.get_function_name	= rockchip_pmx_get_func_name,
 	.get_function_groups	= rockchip_pmx_get_groups,
-	.enable			= rockchip_pmx_enable,
+	.set_mux		= rockchip_pmx_set,
 	.gpio_set_direction	= rockchip_pmx_gpio_set_direction,
 };
 
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 784de13facf3..9032422ad18f 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -447,7 +447,7 @@ static int pcs_get_function(struct pinctrl_dev *pctldev, unsigned pin,
 	return 0;
 }
 
-static int pcs_enable(struct pinctrl_dev *pctldev, unsigned fselector,
+static int pcs_set_mux(struct pinctrl_dev *pctldev, unsigned fselector,
 	unsigned group)
 {
 	struct pcs_device *pcs;
@@ -519,7 +519,7 @@ static const struct pinmux_ops pcs_pinmux_ops = {
 	.get_functions_count = pcs_get_functions_count,
 	.get_function_name = pcs_get_function_name,
 	.get_function_groups = pcs_get_function_groups,
-	.enable = pcs_enable,
+	.set_mux = pcs_sex_mux,
 	.gpio_request_enable = pcs_request_gpio,
 };
 
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index 5475374d803f..6c4c41bed1e3 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -914,8 +914,8 @@ static struct st_pio_control *st_get_pio_control(
 	return &bank->pc;
 }
 
-static int st_pmx_enable(struct pinctrl_dev *pctldev, unsigned fselector,
-		unsigned group)
+static int st_pmx_set_mux(struct pinctrl_dev *pctldev, unsigned fselector,
+			unsigned group)
 {
 	struct st_pinctrl *info = pinctrl_dev_get_drvdata(pctldev);
 	struct st_pinconf *conf = info->groups[group].pin_conf;
@@ -951,7 +951,7 @@ static struct pinmux_ops st_pmxops = {
 	.get_functions_count	= st_pmx_get_funcs_count,
 	.get_function_name	= st_pmx_get_fname,
 	.get_function_groups	= st_pmx_get_groups,
-	.enable			= st_pmx_enable,
+	.set_mux		= st_pmx_set_mux,
 	.gpio_set_direction	= st_pmx_set_gpio_direction,
 };
 
diff --git a/drivers/pinctrl/pinctrl-tb10x.c b/drivers/pinctrl/pinctrl-tb10x.c
index 71c5d4f0c538..3b9bfcf717ac 100644
--- a/drivers/pinctrl/pinctrl-tb10x.c
+++ b/drivers/pinctrl/pinctrl-tb10x.c
@@ -697,7 +697,7 @@ static void tb10x_gpio_disable_free(struct pinctrl_dev *pctl,
 	mutex_unlock(&state->mutex);
 }
 
-static int tb10x_pctl_enable(struct pinctrl_dev *pctl,
+static int tb10x_pctl_set_mux(struct pinctrl_dev *pctl,
 			unsigned func_selector, unsigned group_selector)
 {
 	struct tb10x_pinctrl *state = pinctrl_dev_get_drvdata(pctl);
@@ -744,7 +744,7 @@ static struct pinmux_ops tb10x_pinmux_ops = {
 	.get_function_groups = tb10x_get_function_groups,
 	.gpio_request_enable = tb10x_gpio_request_enable,
 	.gpio_disable_free = tb10x_gpio_disable_free,
-	.enable = tb10x_pctl_enable,
+	.set_mux = tb10x_pctl_set_mux,
 };
 
 static struct pinctrl_desc tb10x_pindesc = {
diff --git a/drivers/pinctrl/pinctrl-tegra-xusb.c b/drivers/pinctrl/pinctrl-tegra-xusb.c
index a06620474845..4648c9e5c582 100644
--- a/drivers/pinctrl/pinctrl-tegra-xusb.c
+++ b/drivers/pinctrl/pinctrl-tegra-xusb.c
@@ -281,9 +281,9 @@ static int tegra_xusb_padctl_get_function_groups(struct pinctrl_dev *pinctrl,
 	return 0;
 }
 
-static int tegra_xusb_padctl_pinmux_enable(struct pinctrl_dev *pinctrl,
-					   unsigned int function,
-					   unsigned int group)
+static int tegra_xusb_padctl_pinmux_set(struct pinctrl_dev *pinctrl,
+					unsigned int function,
+					unsigned int group)
 {
 	struct tegra_xusb_padctl *padctl = pinctrl_dev_get_drvdata(pinctrl);
 	const struct tegra_xusb_padctl_lane *lane;
@@ -311,7 +311,7 @@ static const struct pinmux_ops tegra_xusb_padctl_pinmux_ops = {
 	.get_functions_count = tegra_xusb_padctl_get_functions_count,
 	.get_function_name = tegra_xusb_padctl_get_function_name,
 	.get_function_groups = tegra_xusb_padctl_get_function_groups,
-	.enable = tegra_xusb_padctl_pinmux_enable,
+	.set_mux = tegra_xusb_padctl_pinmux_set,
 };
 
 static int tegra_xusb_padctl_pinconf_group_get(struct pinctrl_dev *pinctrl,
diff --git a/drivers/pinctrl/pinctrl-tegra.c b/drivers/pinctrl/pinctrl-tegra.c
index 150af5503c09..e5949d51bc52 100644
--- a/drivers/pinctrl/pinctrl-tegra.c
+++ b/drivers/pinctrl/pinctrl-tegra.c
@@ -262,8 +262,9 @@ static int tegra_pinctrl_get_func_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int tegra_pinctrl_enable(struct pinctrl_dev *pctldev, unsigned function,
-			       unsigned group)
+static int tegra_pinctrl_set_mux(struct pinctrl_dev *pctldev,
+				 unsigned function,
+				 unsigned group)
 {
 	struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
 	const struct tegra_pingroup *g;
@@ -294,7 +295,7 @@ static const struct pinmux_ops tegra_pinmux_ops = {
 	.get_functions_count = tegra_pinctrl_get_funcs_count,
 	.get_function_name = tegra_pinctrl_get_func_name,
 	.get_function_groups = tegra_pinctrl_get_func_groups,
-	.enable = tegra_pinctrl_enable,
+	.set_mux = tegra_pinctrl_set_mux,
 };
 
 static int tegra_pinconf_reg(struct tegra_pmx *pmx,
diff --git a/drivers/pinctrl/pinctrl-tz1090-pdc.c b/drivers/pinctrl/pinctrl-tz1090-pdc.c
index 41e81a35cabb..3bb6a3b78864 100644
--- a/drivers/pinctrl/pinctrl-tz1090-pdc.c
+++ b/drivers/pinctrl/pinctrl-tz1090-pdc.c
@@ -547,8 +547,9 @@ static void tz1090_pdc_pinctrl_mux(struct tz1090_pdc_pmx *pmx,
 	__global_unlock2(flags);
 }
 
-static int tz1090_pdc_pinctrl_enable(struct pinctrl_dev *pctldev,
-				     unsigned int function, unsigned int group)
+static int tz1090_pdc_pinctrl_set_mux(struct pinctrl_dev *pctldev,
+				      unsigned int function,
+				      unsigned int group)
 {
 	struct tz1090_pdc_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
 	const struct tz1090_pdc_pingroup *grp = &tz1090_pdc_groups[group];
@@ -634,7 +635,7 @@ static struct pinmux_ops tz1090_pdc_pinmux_ops = {
 	.get_functions_count	= tz1090_pdc_pinctrl_get_funcs_count,
 	.get_function_name	= tz1090_pdc_pinctrl_get_func_name,
 	.get_function_groups	= tz1090_pdc_pinctrl_get_func_groups,
-	.enable			= tz1090_pdc_pinctrl_enable,
+	.set_mux		= tz1090_pdc_pinctrl_set_mux,
 	.gpio_request_enable	= tz1090_pdc_pinctrl_gpio_request_enable,
 	.gpio_disable_free	= tz1090_pdc_pinctrl_gpio_disable_free,
 };
diff --git a/drivers/pinctrl/pinctrl-tz1090.c b/drivers/pinctrl/pinctrl-tz1090.c
index 24082216842e..48d36413b99f 100644
--- a/drivers/pinctrl/pinctrl-tz1090.c
+++ b/drivers/pinctrl/pinctrl-tz1090.c
@@ -1415,8 +1415,8 @@ found_mux:
  * the effect is the same as enabling the function on each individual pin in the
  * group.
  */
-static int tz1090_pinctrl_enable(struct pinctrl_dev *pctldev,
-				 unsigned int function, unsigned int group)
+static int tz1090_pinctrl_set_mux(struct pinctrl_dev *pctldev,
+				  unsigned int function, unsigned int group)
 {
 	struct tz1090_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
 	struct tz1090_pingroup *grp;
@@ -1517,7 +1517,7 @@ static struct pinmux_ops tz1090_pinmux_ops = {
 	.get_functions_count	= tz1090_pinctrl_get_funcs_count,
 	.get_function_name	= tz1090_pinctrl_get_func_name,
 	.get_function_groups	= tz1090_pinctrl_get_func_groups,
-	.enable			= tz1090_pinctrl_enable,
+	.set_mux		= tz1090_pinctrl_set_mux,
 	.gpio_request_enable	= tz1090_pinctrl_gpio_request_enable,
 	.gpio_disable_free	= tz1090_pinctrl_gpio_disable_free,
 };
diff --git a/drivers/pinctrl/pinctrl-u300.c b/drivers/pinctrl/pinctrl-u300.c
index 0959bb36450f..e9c7113d81f2 100644
--- a/drivers/pinctrl/pinctrl-u300.c
+++ b/drivers/pinctrl/pinctrl-u300.c
@@ -955,8 +955,8 @@ static void u300_pmx_endisable(struct u300_pmx *upmx, unsigned selector,
 	}
 }
 
-static int u300_pmx_enable(struct pinctrl_dev *pctldev, unsigned selector,
-			   unsigned group)
+static int u300_pmx_set_mux(struct pinctrl_dev *pctldev, unsigned selector,
+			    unsigned group)
 {
 	struct u300_pmx *upmx;
 
@@ -994,7 +994,7 @@ static const struct pinmux_ops u300_pmx_ops = {
 	.get_functions_count = u300_pmx_get_funcs_count,
 	.get_function_name = u300_pmx_get_func_name,
 	.get_function_groups = u300_pmx_get_groups,
-	.enable = u300_pmx_enable,
+	.set_mux = u300_pmx_set_mux,
 };
 
 static int u300_pin_config_get(struct pinctrl_dev *pctldev, unsigned pin,
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index c055daf9a80f..b874458dcb88 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -41,7 +41,7 @@ int pinmux_check_ops(struct pinctrl_dev *pctldev)
 	    !ops->get_functions_count ||
 	    !ops->get_function_name ||
 	    !ops->get_function_groups ||
-	    !ops->enable) {
+	    !ops->set_mux) {
 		dev_err(pctldev->dev, "pinmux ops lacks necessary functions\n");
 		return -EINVAL;
 	}
@@ -445,15 +445,15 @@ int pinmux_enable_setting(struct pinctrl_setting const *setting)
 		desc->mux_setting = &(setting->data.mux);
 	}
 
-	ret = ops->enable(pctldev, setting->data.mux.func,
-			  setting->data.mux.group);
+	ret = ops->set_mux(pctldev, setting->data.mux.func,
+			   setting->data.mux.group);
 
 	if (ret)
-		goto err_enable;
+		goto err_set_mux;
 
 	return 0;
 
-err_enable:
+err_set_mux:
 	for (i = 0; i < num_pins; i++) {
 		desc = pin_desc_get(pctldev, pins[i]);
 		if (desc)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 80a64cad907d..01eab47a746f 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -134,9 +134,9 @@ static int msm_get_function_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int msm_pinmux_enable(struct pinctrl_dev *pctldev,
-			     unsigned function,
-			     unsigned group)
+static int msm_pinmux_set_mux(struct pinctrl_dev *pctldev,
+			      unsigned function,
+			      unsigned group)
 {
 	struct msm_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
 	const struct msm_pingroup *g;
@@ -170,7 +170,7 @@ static const struct pinmux_ops msm_pinmux_ops = {
 	.get_functions_count	= msm_get_functions_count,
 	.get_function_name	= msm_get_function_name,
 	.get_function_groups	= msm_get_function_groups,
-	.enable			= msm_pinmux_enable,
+	.set_mux		= msm_pinmux_set_mux,
 };
 
 static int msm_config_reg(struct msm_pinctrl *pctrl,
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos5440.c b/drivers/pinctrl/samsung/pinctrl-exynos5440.c
index 603da2f9dd95..b995ec2c5d16 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos5440.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos5440.c
@@ -364,8 +364,9 @@ static void exynos5440_pinmux_setup(struct pinctrl_dev *pctldev, unsigned select
 }
 
 /* enable a specified pinmux by writing to registers */
-static int exynos5440_pinmux_enable(struct pinctrl_dev *pctldev, unsigned selector,
-					unsigned group)
+static int exynos5440_pinmux_set_mux(struct pinctrl_dev *pctldev,
+				     unsigned selector,
+				     unsigned group)
 {
 	exynos5440_pinmux_setup(pctldev, selector, group, true);
 	return 0;
@@ -387,7 +388,7 @@ static const struct pinmux_ops exynos5440_pinmux_ops = {
 	.get_functions_count	= exynos5440_get_functions_count,
 	.get_function_name	= exynos5440_pinmux_get_fname,
 	.get_function_groups	= exynos5440_pinmux_get_groups,
-	.enable			= exynos5440_pinmux_enable,
+	.set_mux		= exynos5440_pinmux_set_mux,
 	.gpio_set_direction	= exynos5440_pinmux_gpio_set_direction,
 };
 
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index b07406da333c..4a47691c32b1 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -401,8 +401,9 @@ static void samsung_pinmux_setup(struct pinctrl_dev *pctldev, unsigned selector,
 }
 
 /* enable a specified pinmux by writing to registers */
-static int samsung_pinmux_enable(struct pinctrl_dev *pctldev, unsigned selector,
-					unsigned group)
+static int samsung_pinmux_set_mux(struct pinctrl_dev *pctldev,
+				  unsigned selector,
+				  unsigned group)
 {
 	samsung_pinmux_setup(pctldev, selector, group, true);
 	return 0;
@@ -413,7 +414,7 @@ static const struct pinmux_ops samsung_pinmux_ops = {
 	.get_functions_count	= samsung_get_functions_count,
 	.get_function_name	= samsung_pinmux_get_fname,
 	.get_function_groups	= samsung_pinmux_get_groups,
-	.enable			= samsung_pinmux_enable,
+	.set_mux		= samsung_pinmux_set_mux,
 };
 
 /* set or get the pin config settings for a specified pin */
diff --git a/drivers/pinctrl/sh-pfc/pinctrl.c b/drivers/pinctrl/sh-pfc/pinctrl.c
index 11db3ee39d40..910deaefa0ac 100644
--- a/drivers/pinctrl/sh-pfc/pinctrl.c
+++ b/drivers/pinctrl/sh-pfc/pinctrl.c
@@ -312,8 +312,8 @@ static int sh_pfc_get_function_groups(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int sh_pfc_func_enable(struct pinctrl_dev *pctldev, unsigned selector,
-			      unsigned group)
+static int sh_pfc_func_set_mux(struct pinctrl_dev *pctldev, unsigned selector,
+			       unsigned group)
 {
 	struct sh_pfc_pinctrl *pmx = pinctrl_dev_get_drvdata(pctldev);
 	struct sh_pfc *pfc = pmx->pfc;
@@ -442,7 +442,7 @@ static const struct pinmux_ops sh_pfc_pinmux_ops = {
 	.get_functions_count	= sh_pfc_get_functions_count,
 	.get_function_name	= sh_pfc_get_function_name,
 	.get_function_groups	= sh_pfc_get_function_groups,
-	.enable			= sh_pfc_func_enable,
+	.set_mux		= sh_pfc_func_set_mux,
 	.gpio_request_enable	= sh_pfc_gpio_request_enable,
 	.gpio_disable_free	= sh_pfc_gpio_disable_free,
 	.gpio_set_direction	= sh_pfc_gpio_set_direction,
diff --git a/drivers/pinctrl/sirf/pinctrl-sirf.c b/drivers/pinctrl/sirf/pinctrl-sirf.c
index 45f93f952a39..6f252fd7cb0c 100644
--- a/drivers/pinctrl/sirf/pinctrl-sirf.c
+++ b/drivers/pinctrl/sirf/pinctrl-sirf.c
@@ -179,8 +179,9 @@ static void sirfsoc_pinmux_endisable(struct sirfsoc_pmx *spmx,
 	}
 }
 
-static int sirfsoc_pinmux_enable(struct pinctrl_dev *pmxdev, unsigned selector,
-	unsigned group)
+static int sirfsoc_pinmux_set_mux(struct pinctrl_dev *pmxdev,
+				unsigned selector,
+				unsigned group)
 {
 	struct sirfsoc_pmx *spmx;
 
@@ -237,7 +238,7 @@ static int sirfsoc_pinmux_request_gpio(struct pinctrl_dev *pmxdev,
 }
 
 static struct pinmux_ops sirfsoc_pinmux_ops = {
-	.enable = sirfsoc_pinmux_enable,
+	.set_mux = sirfsoc_pinmux_set_mux,
 	.get_functions_count = sirfsoc_pinmux_get_funcs_count,
 	.get_function_name = sirfsoc_pinmux_get_func_name,
 	.get_function_groups = sirfsoc_pinmux_get_groups,
diff --git a/drivers/pinctrl/spear/pinctrl-spear.c b/drivers/pinctrl/spear/pinctrl-spear.c
index f72cc4e192bd..abdb05ac43dc 100644
--- a/drivers/pinctrl/spear/pinctrl-spear.c
+++ b/drivers/pinctrl/spear/pinctrl-spear.c
@@ -268,7 +268,7 @@ static int spear_pinctrl_endisable(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int spear_pinctrl_enable(struct pinctrl_dev *pctldev, unsigned function,
+static int spear_pinctrl_set_mux(struct pinctrl_dev *pctldev, unsigned function,
 		unsigned group)
 {
 	return spear_pinctrl_endisable(pctldev, function, group, true);
@@ -338,7 +338,7 @@ static const struct pinmux_ops spear_pinmux_ops = {
 	.get_functions_count = spear_pinctrl_get_funcs_count,
 	.get_function_name = spear_pinctrl_get_func_name,
 	.get_function_groups = spear_pinctrl_get_func_groups,
-	.enable = spear_pinctrl_enable,
+	.set_mux = spear_pinctrl_set_mux,
 	.gpio_request_enable = gpio_request_enable,
 	.gpio_disable_free = gpio_disable_free,
 };
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 3df66e366c87..ef9d804e55de 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -393,9 +393,9 @@ static void sunxi_pmx_set(struct pinctrl_dev *pctldev,
 	spin_unlock_irqrestore(&pctl->lock, flags);
 }
 
-static int sunxi_pmx_enable(struct pinctrl_dev *pctldev,
-			    unsigned function,
-			    unsigned group)
+static int sunxi_pmx_set_mux(struct pinctrl_dev *pctldev,
+			     unsigned function,
+			     unsigned group)
 {
 	struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
 	struct sunxi_pinctrl_group *g = pctl->groups + group;
@@ -441,7 +441,7 @@ static const struct pinmux_ops sunxi_pmx_ops = {
 	.get_functions_count	= sunxi_pmx_get_funcs_cnt,
 	.get_function_name	= sunxi_pmx_get_func_name,
 	.get_function_groups	= sunxi_pmx_get_func_groups,
-	.enable			= sunxi_pmx_enable,
+	.set_mux		= sunxi_pmx_set_mux,
 	.gpio_set_direction	= sunxi_pmx_gpio_set_direction,
 };
 
diff --git a/drivers/pinctrl/vt8500/pinctrl-wmt.c b/drivers/pinctrl/vt8500/pinctrl-wmt.c
index 8cea355f9a81..d055d63309e4 100644
--- a/drivers/pinctrl/vt8500/pinctrl-wmt.c
+++ b/drivers/pinctrl/vt8500/pinctrl-wmt.c
@@ -131,9 +131,9 @@ static int wmt_set_pinmux(struct wmt_pinctrl_data *data, unsigned func,
 	return 0;
 }
 
-static int wmt_pmx_enable(struct pinctrl_dev *pctldev,
-			  unsigned func_selector,
-			  unsigned group_selector)
+static int wmt_pmx_set_mux(struct pinctrl_dev *pctldev,
+			   unsigned func_selector,
+			   unsigned group_selector)
 {
 	struct wmt_pinctrl_data *data = pinctrl_dev_get_drvdata(pctldev);
 	u32 pinnum = data->pins[group_selector].number;
@@ -168,7 +168,7 @@ static struct pinmux_ops wmt_pinmux_ops = {
 	.get_functions_count = wmt_pmx_get_functions_count,
 	.get_function_name = wmt_pmx_get_function_name,
 	.get_function_groups = wmt_pmx_get_function_groups,
-	.enable = wmt_pmx_enable,
+	.set_mux = wmt_pmx_set_mux,
 	.gpio_disable_free = wmt_pmx_gpio_disable_free,
 	.gpio_set_direction = wmt_pmx_gpio_set_direction,
 };
diff --git a/include/linux/pinctrl/pinmux.h b/include/linux/pinctrl/pinmux.h
index 3097aafbeb24..511bda9ed4bf 100644
--- a/include/linux/pinctrl/pinmux.h
+++ b/include/linux/pinctrl/pinmux.h
@@ -39,13 +39,12 @@ struct pinctrl_dev;
  *	name can be used with the generic @pinctrl_ops to retrieve the
  *	actual pins affected. The applicable groups will be returned in
  *	@groups and the number of groups in @num_groups
- * @enable: enable a certain muxing function with a certain pin group. The
+ * @set_mux: enable a certain muxing function with a certain pin group. The
  *	driver does not need to figure out whether enabling this function
  *	conflicts some other use of the pins in that group, such collisions
  *	are handled by the pinmux subsystem. The @func_selector selects a
  *	certain function whereas @group_selector selects a certain set of pins
  *	to be used. On simple controllers the latter argument may be ignored
- * @disable: disable a certain muxing selector with a certain pin group
  * @gpio_request_enable: requests and enables GPIO on a certain pin.
  *	Implement this only if you can mux every pin individually as GPIO. The
  *	affected GPIO range is passed along with an offset(pin number) into that
@@ -68,8 +67,8 @@ struct pinmux_ops {
 				  unsigned selector,
 				  const char * const **groups,
 				  unsigned * const num_groups);
-	int (*enable) (struct pinctrl_dev *pctldev, unsigned func_selector,
-		       unsigned group_selector);
+	int (*set_mux) (struct pinctrl_dev *pctldev, unsigned func_selector,
+			unsigned group_selector);
 	int (*gpio_request_enable) (struct pinctrl_dev *pctldev,
 				    struct pinctrl_gpio_range *range,
 				    unsigned offset);
-- 
cgit v1.2.3


From 3af0dbd592fe0a92002f16e341519ba03e92adf7 Mon Sep 17 00:00:00 2001
From: Sonic Zhang <sonic.zhang@analog.com>
Date: Mon, 1 Sep 2014 11:19:52 +0800
Subject: gpio: mcp23s08 to support both device tree and platform data

Device tree is not enabled in some architecture where gpio
driver mcp23s08 is still required.

v2-changes:
- Parse device tree properties into platform data other than
  individual variables.
v3-changes:
- Use of_node in gpio_chip device structure, because the
  struct device * always has an of_node which is NULL when
  OF is not used.

Signed-off-by: Sonic Zhang <sonic.zhang@analog.com>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/Kconfig         |  1 -
 drivers/gpio/gpio-mcp23s08.c | 64 +++++++++++++++++++++++---------------------
 include/linux/spi/mcp23s08.h | 18 +++++++++++++
 3 files changed, 52 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index ec27ec0be8c2..ec398bee7c60 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -806,7 +806,6 @@ config GPIO_MAX7301
 
 config GPIO_MCP23S08
 	tristate "Microchip MCP23xxx I/O expander"
-	depends on OF_GPIO
 	depends on (SPI_MASTER && !I2C) || I2C
 	help
 	  SPI/I2C driver for Microchip MCP23S08/MCP23S17/MCP23008/MCP23017
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index 6f183d9b487e..8488e2fd307c 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -479,7 +479,7 @@ static int mcp23s08_irq_setup(struct mcp23s08 *mcp)
 
 	mutex_init(&mcp->irq_lock);
 
-	mcp->irq_domain = irq_domain_add_linear(chip->of_node, chip->ngpio,
+	mcp->irq_domain = irq_domain_add_linear(chip->dev->of_node, chip->ngpio,
 						&irq_domain_simple_ops, mcp);
 	if (!mcp->irq_domain)
 		return -ENODEV;
@@ -581,7 +581,7 @@ done:
 
 static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 			      void *data, unsigned addr, unsigned type,
-			      unsigned base, unsigned pullups)
+			      struct mcp23s08_platform_data *pdata, int cs)
 {
 	int status;
 	bool mirror = false;
@@ -635,7 +635,7 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 		return -EINVAL;
 	}
 
-	mcp->chip.base = base;
+	mcp->chip.base = pdata->base;
 	mcp->chip.can_sleep = true;
 	mcp->chip.dev = dev;
 	mcp->chip.owner = THIS_MODULE;
@@ -648,11 +648,9 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 	if (status < 0)
 		goto fail;
 
-	mcp->irq_controller = of_property_read_bool(mcp->chip.of_node,
-						"interrupt-controller");
+	mcp->irq_controller = pdata->irq_controller;
 	if (mcp->irq && mcp->irq_controller && (type == MCP_TYPE_017))
-		mirror = of_property_read_bool(mcp->chip.of_node,
-						"microchip,irq-mirror");
+		mirror = pdata->mirror;
 
 	if ((status & IOCON_SEQOP) || !(status & IOCON_HAEN) || mirror) {
 		/* mcp23s17 has IOCON twice, make sure they are in sync */
@@ -668,7 +666,7 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 	}
 
 	/* configure ~100K pullups */
-	status = mcp->ops->write(mcp, MCP_GPPU, pullups);
+	status = mcp->ops->write(mcp, MCP_GPPU, pdata->chip[cs].pullups);
 	if (status < 0)
 		goto fail;
 
@@ -768,25 +766,29 @@ MODULE_DEVICE_TABLE(of, mcp23s08_i2c_of_match);
 static int mcp230xx_probe(struct i2c_client *client,
 				    const struct i2c_device_id *id)
 {
-	struct mcp23s08_platform_data *pdata;
+	struct mcp23s08_platform_data *pdata, local_pdata;
 	struct mcp23s08 *mcp;
-	int status, base, pullups;
+	int status;
 	const struct of_device_id *match;
 
 	match = of_match_device(of_match_ptr(mcp23s08_i2c_of_match),
 					&client->dev);
-	pdata = dev_get_platdata(&client->dev);
-	if (match || !pdata) {
-		base = -1;
-		pullups = 0;
+	if (match) {
+		pdata = &local_pdata;
+		pdata->base = -1;
+		pdata->chip[0].pullups = 0;
+		pdata->irq_controller =	of_property_read_bool(
+					client->dev.of_node,
+					"interrupt-controller");
+		pdata->mirror = of_property_read_bool(client->dev.of_node,
+						      "microchip,irq-mirror");
 		client->irq = irq_of_parse_and_map(client->dev.of_node, 0);
 	} else {
-		if (!gpio_is_valid(pdata->base)) {
+		pdata = dev_get_platdata(&client->dev);
+		if (!pdata || !gpio_is_valid(pdata->base)) {
 			dev_dbg(&client->dev, "invalid platform data\n");
 			return -EINVAL;
 		}
-		base = pdata->base;
-		pullups = pdata->chip[0].pullups;
 	}
 
 	mcp = kzalloc(sizeof(*mcp), GFP_KERNEL);
@@ -795,7 +797,7 @@ static int mcp230xx_probe(struct i2c_client *client,
 
 	mcp->irq = client->irq;
 	status = mcp23s08_probe_one(mcp, &client->dev, client, client->addr,
-				    id->driver_data, base, pullups);
+				    id->driver_data, pdata, 0);
 	if (status)
 		goto fail;
 
@@ -863,14 +865,12 @@ static void mcp23s08_i2c_exit(void) { }
 
 static int mcp23s08_probe(struct spi_device *spi)
 {
-	struct mcp23s08_platform_data	*pdata;
+	struct mcp23s08_platform_data	*pdata, local_pdata;
 	unsigned			addr;
 	int				chips = 0;
 	struct mcp23s08_driver_data	*data;
 	int				status, type;
-	unsigned			base = -1,
-					ngpio = 0,
-					pullups[ARRAY_SIZE(pdata->chip)];
+	unsigned			ngpio = 0;
 	const struct			of_device_id *match;
 	u32				spi_present_mask = 0;
 
@@ -893,11 +893,18 @@ static int mcp23s08_probe(struct spi_device *spi)
 			return -ENODEV;
 		}
 
+		pdata = &local_pdata;
+		pdata->base = -1;
 		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) {
-			pullups[addr] = 0;
+			pdata->chip[addr].pullups = 0;
 			if (spi_present_mask & (1 << addr))
 				chips++;
 		}
+		pdata->irq_controller =	of_property_read_bool(
+					spi->dev.of_node,
+					"interrupt-controller");
+		pdata->mirror = of_property_read_bool(spi->dev.of_node,
+						      "microchip,irq-mirror");
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
 		pdata = dev_get_platdata(&spi->dev);
@@ -917,10 +924,7 @@ static int mcp23s08_probe(struct spi_device *spi)
 				return -EINVAL;
 			}
 			spi_present_mask |= 1 << addr;
-			pullups[addr] = pdata->chip[addr].pullups;
 		}
-
-		base = pdata->base;
 	}
 
 	if (!chips)
@@ -938,13 +942,13 @@ static int mcp23s08_probe(struct spi_device *spi)
 		chips--;
 		data->mcp[addr] = &data->chip[chips];
 		status = mcp23s08_probe_one(data->mcp[addr], &spi->dev, spi,
-					    0x40 | (addr << 1), type, base,
-					    pullups[addr]);
+					    0x40 | (addr << 1), type, pdata,
+					    addr);
 		if (status < 0)
 			goto fail;
 
-		if (base != -1)
-			base += (type == MCP_TYPE_S17) ? 16 : 8;
+		if (pdata->base != -1)
+			pdata->base += (type == MCP_TYPE_S17) ? 16 : 8;
 		ngpio += (type == MCP_TYPE_S17) ? 16 : 8;
 	}
 	data->ngpio = ngpio;
diff --git a/include/linux/spi/mcp23s08.h b/include/linux/spi/mcp23s08.h
index 2d676d5aaa89..aa07d7b32568 100644
--- a/include/linux/spi/mcp23s08.h
+++ b/include/linux/spi/mcp23s08.h
@@ -22,4 +22,22 @@ struct mcp23s08_platform_data {
 	 * base to base+15 (or base+31 for s17 variant).
 	 */
 	unsigned	base;
+	/* Marks the device as a interrupt controller.
+	 * NOTE: The interrupt functionality is only supported for i2c
+	 * versions of the chips. The spi chips can also do the interrupts,
+	 * but this is not supported by the linux driver yet.
+	 */
+	bool		irq_controller;
+
+	/* Sets the mirror flag in the IOCON register. Devices
+	 * with two interrupt outputs (these are the devices ending with 17 and
+	 * those that have 16 IOs) have two IO banks: IO 0-7 form bank 1 and
+	 * IO 8-15 are bank 2. These chips have two different interrupt outputs:
+	 * One for bank 1 and another for bank 2. If irq-mirror is set, both
+	 * interrupts are generated regardless of the bank that an input change
+	 * occurred on. If it is not set, the interrupt are only generated for
+	 * the bank they belong to.
+	 * On devices with only one interrupt output this property is useless.
+	 */
+	bool		mirror;
 };
-- 
cgit v1.2.3


From 0d37899363b0e5486f8800231b7edd75e8b60942 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 3 Sep 2014 20:01:55 +0200
Subject: pinctrl: generic: Fix PIN_CONFIG_DRIVE_OPEN_SOURCE source/drain doc
 mismatch

PIN_CONFIG_DRIVE_OPEN_SOURCE enables open source, not open drain.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/pinctrl/pinconf-generic.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index a15f10727eb8..d578a60eff23 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -57,7 +57,7 @@
  *	which are then pulled up with an external resistor. Setting this
  *	config will enable open drain mode, the argument is ignored.
  * @PIN_CONFIG_DRIVE_OPEN_SOURCE: the pin will be driven with open source
- *	(open emitter). Setting this config will enable open drain mode, the
+ *	(open emitter). Setting this config will enable open source mode, the
  *	argument is ignored.
  * @PIN_CONFIG_DRIVE_STRENGTH: the pin will sink or source at most the current
  *	passed as argument. The argument is in mA.
-- 
cgit v1.2.3


From 87fed556d08d21dd7dd3e0222c94c187e4c2d5e2 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Wed, 3 Sep 2014 10:35:13 +0200
Subject: bcma: get info about flash type SoC booted from
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is an ongoing work on cleaning MIPS's nvram support so it could be
re-used on other platforms (bcm53xx to say precisely).
This will require a bit of extra logic in bcma this patch implements.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/driver_mips.c     | 62 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/bcma/bcma_regs.h |  5 ++++
 2 files changed, 67 insertions(+)

(limited to 'include')

diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index 11115bbe115c..004d6aa671ce 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -21,6 +21,14 @@
 #include <linux/serial_reg.h>
 #include <linux/time.h>
 
+enum bcma_boot_dev {
+	BCMA_BOOT_DEV_UNK = 0,
+	BCMA_BOOT_DEV_ROM,
+	BCMA_BOOT_DEV_PARALLEL,
+	BCMA_BOOT_DEV_SERIAL,
+	BCMA_BOOT_DEV_NAND,
+};
+
 static const char * const part_probes[] = { "bcm47xxpart", NULL };
 
 static struct physmap_flash_data bcma_pflash_data = {
@@ -229,11 +237,51 @@ u32 bcma_cpu_clock(struct bcma_drv_mips *mcore)
 }
 EXPORT_SYMBOL(bcma_cpu_clock);
 
+static enum bcma_boot_dev bcma_boot_dev(struct bcma_bus *bus)
+{
+	struct bcma_drv_cc *cc = &bus->drv_cc;
+	u8 cc_rev = cc->core->id.rev;
+
+	if (cc_rev == 42) {
+		struct bcma_device *core;
+
+		core = bcma_find_core(bus, BCMA_CORE_NS_ROM);
+		if (core) {
+			switch (bcma_aread32(core, BCMA_IOST) &
+				BCMA_NS_ROM_IOST_BOOT_DEV_MASK) {
+			case BCMA_NS_ROM_IOST_BOOT_DEV_NOR:
+				return BCMA_BOOT_DEV_SERIAL;
+			case BCMA_NS_ROM_IOST_BOOT_DEV_NAND:
+				return BCMA_BOOT_DEV_NAND;
+			case BCMA_NS_ROM_IOST_BOOT_DEV_ROM:
+			default:
+				return BCMA_BOOT_DEV_ROM;
+			}
+		}
+	} else {
+		if (cc_rev == 38) {
+			if (cc->status & BCMA_CC_CHIPST_5357_NAND_BOOT)
+				return BCMA_BOOT_DEV_NAND;
+			else if (cc->status & BIT(5))
+				return BCMA_BOOT_DEV_ROM;
+		}
+
+		if ((cc->capabilities & BCMA_CC_CAP_FLASHT) ==
+		    BCMA_CC_FLASHT_PARA)
+			return BCMA_BOOT_DEV_PARALLEL;
+		else
+			return BCMA_BOOT_DEV_SERIAL;
+	}
+
+	return BCMA_BOOT_DEV_SERIAL;
+}
+
 static void bcma_core_mips_flash_detect(struct bcma_drv_mips *mcore)
 {
 	struct bcma_bus *bus = mcore->core->bus;
 	struct bcma_drv_cc *cc = &bus->drv_cc;
 	struct bcma_pflash *pflash = &cc->pflash;
+	enum bcma_boot_dev boot_dev;
 
 	switch (cc->capabilities & BCMA_CC_CAP_FLASHT) {
 	case BCMA_CC_FLASHT_STSER:
@@ -269,6 +317,20 @@ static void bcma_core_mips_flash_detect(struct bcma_drv_mips *mcore)
 			bcma_nflash_init(cc);
 		}
 	}
+
+	/* Determine flash type this SoC boots from */
+	boot_dev = bcma_boot_dev(bus);
+	switch (boot_dev) {
+	case BCMA_BOOT_DEV_PARALLEL:
+	case BCMA_BOOT_DEV_SERIAL:
+		/* TODO: Init NVRAM using BCMA_SOC_FLASH2 window */
+		break;
+	case BCMA_BOOT_DEV_NAND:
+		/* TODO: Init NVRAM using BCMA_SOC_FLASH1 window */
+		break;
+	default:
+		break;
+	}
 }
 
 void bcma_core_mips_early_init(struct bcma_drv_mips *mcore)
diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h
index 917dcd7965e7..e64ae7bf80a1 100644
--- a/include/linux/bcma/bcma_regs.h
+++ b/include/linux/bcma/bcma_regs.h
@@ -39,6 +39,11 @@
 #define  BCMA_RESET_CTL_RESET		0x0001
 #define BCMA_RESET_ST			0x0804
 
+#define BCMA_NS_ROM_IOST_BOOT_DEV_MASK	0x0003
+#define BCMA_NS_ROM_IOST_BOOT_DEV_NOR	0x0000
+#define BCMA_NS_ROM_IOST_BOOT_DEV_NAND	0x0001
+#define BCMA_NS_ROM_IOST_BOOT_DEV_ROM	0x0002
+
 /* BCMA PCI config space registers. */
 #define BCMA_PCI_PMCSR			0x44
 #define  BCMA_PCI_PE			0x100
-- 
cgit v1.2.3


From 86dbf2ac6fcb2d2932d4610f2dfe0954aa0633f7 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Thu, 4 Sep 2014 19:44:06 +0200
Subject: ASoC: Add support for automatically going to BIAS_OFF on suspend

There is a substantial amount of drivers that in go to SND_SOC_BIAS_OFF on
suspend and go back to SND_SOC_BIAS_SUSPEND on resume (Often this is even
the only thing done in the suspend and resume handlers). This patch
introduces a new suspend_bias_off flag, which when set by a driver will let
the ASoC core automatically put the device's DAPM context at the
SND_SOC_BIAS_OFF level during suspend. Once the device is resumed the DAPM
context will go back to SND_SOC_BIAS_STANDBY (if the context is idle,
otherwise to SND_SOC_BIAS_ON).

This will allow us to remove a fair bit of duplicated code from the drivers.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h |  3 ++-
 include/sound/soc.h      |  1 +
 sound/soc/soc-core.c     |  1 +
 sound/soc/soc-dapm.c     | 20 ++++++++++++++++++--
 4 files changed, 22 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index aac04ff84eea..f955d65c5656 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -587,7 +587,8 @@ struct snd_soc_dapm_context {
 	enum snd_soc_bias_level suspend_bias_level;
 	struct delayed_work delayed_work;
 	unsigned int idle_bias_off:1; /* Use BIAS_OFF instead of STANDBY */
-
+	/* Go to BIAS_OFF in suspend if the DAPM context is idle */
+	unsigned int suspend_bias_off:1;
 	void (*seq_notifier)(struct snd_soc_dapm_context *,
 			     enum snd_soc_dapm_type, int);
 
diff --git a/include/sound/soc.h b/include/sound/soc.h
index ce09302bfd6d..ac99fc083eec 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -848,6 +848,7 @@ struct snd_soc_codec_driver {
 	int (*set_bias_level)(struct snd_soc_codec *,
 			      enum snd_soc_bias_level level);
 	bool idle_bias_off;
+	bool suspend_bias_off;
 
 	void (*seq_notifier)(struct snd_soc_dapm_context *,
 			     enum snd_soc_dapm_type, int);
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 068785fa1a06..2bdf9a4ac2b4 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -4402,6 +4402,7 @@ int snd_soc_register_codec(struct device *dev,
 	codec->component.ignore_pmdown_time = codec_drv->ignore_pmdown_time;
 	codec->dapm.codec = codec;
 	codec->dapm.idle_bias_off = codec_drv->idle_bias_off;
+	codec->dapm.suspend_bias_off = codec_drv->suspend_bias_off;
 	if (codec_drv->seq_notifier)
 		codec->dapm.seq_notifier = codec_drv->seq_notifier;
 	if (codec_drv->set_bias_level)
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 8348352dc2c6..a2025a6b6a29 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1683,6 +1683,22 @@ static void dapm_power_one_widget(struct snd_soc_dapm_widget *w,
 	}
 }
 
+static bool dapm_idle_bias_off(struct snd_soc_dapm_context *dapm)
+{
+	if (dapm->idle_bias_off)
+		return true;
+
+	switch (snd_power_get_state(dapm->card->snd_card)) {
+	case SNDRV_CTL_POWER_D3hot:
+	case SNDRV_CTL_POWER_D3cold:
+		return dapm->suspend_bias_off;
+	default:
+		break;
+	}
+
+	return false;
+}
+
 /*
  * Scan each dapm widget for complete audio path.
  * A complete path is a route that has valid endpoints i.e.:-
@@ -1706,7 +1722,7 @@ static int dapm_power_widgets(struct snd_soc_card *card, int event)
 	trace_snd_soc_dapm_start(card);
 
 	list_for_each_entry(d, &card->dapm_list, list) {
-		if (d->idle_bias_off)
+		if (dapm_idle_bias_off(d))
 			d->target_bias_level = SND_SOC_BIAS_OFF;
 		else
 			d->target_bias_level = SND_SOC_BIAS_STANDBY;
@@ -1772,7 +1788,7 @@ static int dapm_power_widgets(struct snd_soc_card *card, int event)
 		if (d->target_bias_level > bias)
 			bias = d->target_bias_level;
 	list_for_each_entry(d, &card->dapm_list, list)
-		if (!d->idle_bias_off)
+		if (!dapm_idle_bias_off(d))
 			d->target_bias_level = bias;
 
 	trace_snd_soc_dapm_walk_done(card);
-- 
cgit v1.2.3


From 40bea039593dfc7f3f9814dab844f6db43ae580b Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 13 Aug 2014 18:50:16 +0200
Subject: nohz: Restore NMI safe local irq work for local nohz kick

The local nohz kick is currently used by perf which needs it to be
NMI-safe. Recent commit though (7d1311b93e58ed55f3a31cc8f94c4b8fe988a2b9)
changed its implementation to fire the local kick using the remote kick
API. It was convenient to make the code more generic but the remote kick
isn't NMI-safe.

As a result:

	WARNING: CPU: 3 PID: 18062 at kernel/irq_work.c:72 irq_work_queue_on+0x11e/0x140()
	CPU: 3 PID: 18062 Comm: trinity-subchil Not tainted 3.16.0+ #34
	0000000000000009 00000000903774d1 ffff880244e06c00 ffffffff9a7f1e37
	0000000000000000 ffff880244e06c38 ffffffff9a0791dd ffff880244fce180
	0000000000000003 ffff880244e06d58 ffff880244e06ef8 0000000000000000
	Call Trace:
	<NMI>  [<ffffffff9a7f1e37>] dump_stack+0x4e/0x7a
	[<ffffffff9a0791dd>] warn_slowpath_common+0x7d/0xa0
	[<ffffffff9a07930a>] warn_slowpath_null+0x1a/0x20
	[<ffffffff9a17ca1e>] irq_work_queue_on+0x11e/0x140
	[<ffffffff9a10a2c7>] tick_nohz_full_kick_cpu+0x57/0x90
	[<ffffffff9a186cd5>] __perf_event_overflow+0x275/0x350
	[<ffffffff9a184f80>] ? perf_event_task_disable+0xa0/0xa0
	[<ffffffff9a01a4cf>] ? x86_perf_event_set_period+0xbf/0x150
	[<ffffffff9a187934>] perf_event_overflow+0x14/0x20
	[<ffffffff9a020386>] intel_pmu_handle_irq+0x206/0x410
	[<ffffffff9a0b54d3>] ? arch_vtime_task_switch+0x63/0x130
	[<ffffffff9a01937b>] perf_event_nmi_handler+0x2b/0x50
	[<ffffffff9a007b72>] nmi_handle+0xd2/0x390
	[<ffffffff9a007aa5>] ? nmi_handle+0x5/0x390
	[<ffffffff9a0d131b>] ? lock_release+0xab/0x330
	[<ffffffff9a008062>] default_do_nmi+0x72/0x1c0
	[<ffffffff9a0c925f>] ? cpuacct_account_field+0xcf/0x200
	[<ffffffff9a008268>] do_nmi+0xb8/0x100

Lets fix this by restoring the use of local irq work for the nohz local
kick.

Reported-by: Catalin Iacob <iacobcatalin@gmail.com>
Reported-and-tested-by: Dave Jones <davej@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 include/linux/tick.h     |  7 +------
 kernel/time/tick-sched.c | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/tick.h b/include/linux/tick.h
index 059052306831..9a82c7dc3fdd 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -183,13 +183,8 @@ static inline bool tick_nohz_full_cpu(int cpu)
 
 extern void tick_nohz_init(void);
 extern void __tick_nohz_full_check(void);
+extern void tick_nohz_full_kick(void);
 extern void tick_nohz_full_kick_cpu(int cpu);
-
-static inline void tick_nohz_full_kick(void)
-{
-	tick_nohz_full_kick_cpu(smp_processor_id());
-}
-
 extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(struct task_struct *tsk);
 #else
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 99aa6ee3908f..f654a8a298fa 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -224,6 +224,20 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
 	.func = nohz_full_kick_work_func,
 };
 
+/*
+ * Kick this CPU if it's full dynticks in order to force it to
+ * re-evaluate its dependency on the tick and restart it if necessary.
+ * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(),
+ * is NMI safe.
+ */
+void tick_nohz_full_kick(void)
+{
+	if (!tick_nohz_full_cpu(smp_processor_id()))
+		return;
+
+	irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
+}
+
 /*
  * Kick the CPU if it's full dynticks in order to force it to
  * re-evaluate its dependency on the tick and restart it if necessary.
-- 
cgit v1.2.3


From 8d38821cbcf51292cd5a23469d03bd38932a3ba9 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 1 Aug 2014 14:15:10 +0200
Subject: resources: Add device-managed request/release_resource()

Provide device-managed implementations of the request_resource() and
release_resource() functions.  Upon failure to request a resource, the new
devm_request_resource() function will output an error message for
consistent error reporting.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
---
 Documentation/driver-model/devres.txt |  2 +
 include/linux/ioport.h                |  5 +++
 kernel/resource.c                     | 70 +++++++++++++++++++++++++++++++++++
 3 files changed, 77 insertions(+)

(limited to 'include')

diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index d14710b04439..befc3fe12ba6 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -264,8 +264,10 @@ IIO
 IO region
   devm_release_mem_region()
   devm_release_region()
+  devm_release_resource()
   devm_request_mem_region()
   devm_request_region()
+  devm_request_resource()
 
 IOMAP
   devm_ioport_map()
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 142ec544167c..2c5250222278 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -215,6 +215,11 @@ static inline int __deprecated check_region(resource_size_t s,
 
 /* Wrappers for managed devices */
 struct device;
+
+extern int devm_request_resource(struct device *dev, struct resource *root,
+				 struct resource *new);
+extern void devm_release_resource(struct device *dev, struct resource *new);
+
 #define devm_request_region(dev,start,n,name) \
 	__devm_request_region(dev, &ioport_resource, (start), (n), (name))
 #define devm_request_mem_region(dev,start,n,name) \
diff --git a/kernel/resource.c b/kernel/resource.c
index da14b8d09296..ca24f19f9d18 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1248,6 +1248,76 @@ int release_mem_region_adjustable(struct resource *parent,
 /*
  * Managed region resource
  */
+static void devm_resource_release(struct device *dev, void *ptr)
+{
+	struct resource **r = ptr;
+
+	release_resource(*r);
+}
+
+/**
+ * devm_request_resource() - request and reserve an I/O or memory resource
+ * @dev: device for which to request the resource
+ * @root: root of the resource tree from which to request the resource
+ * @new: descriptor of the resource to request
+ *
+ * This is a device-managed version of request_resource(). There is usually
+ * no need to release resources requested by this function explicitly since
+ * that will be taken care of when the device is unbound from its driver.
+ * If for some reason the resource needs to be released explicitly, because
+ * of ordering issues for example, drivers must call devm_release_resource()
+ * rather than the regular release_resource().
+ *
+ * When a conflict is detected between any existing resources and the newly
+ * requested resource, an error message will be printed.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+int devm_request_resource(struct device *dev, struct resource *root,
+			  struct resource *new)
+{
+	struct resource *conflict, **ptr;
+
+	ptr = devres_alloc(devm_resource_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	*ptr = new;
+
+	conflict = request_resource_conflict(root, new);
+	if (conflict) {
+		dev_err(dev, "resource collision: %pR conflicts with %s %pR\n",
+			new, conflict->name, conflict);
+		devres_free(ptr);
+		return -EBUSY;
+	}
+
+	devres_add(dev, ptr);
+	return 0;
+}
+EXPORT_SYMBOL(devm_request_resource);
+
+static int devm_resource_match(struct device *dev, void *res, void *data)
+{
+	struct resource **ptr = res;
+
+	return *ptr == data;
+}
+
+/**
+ * devm_release_resource() - release a previously requested resource
+ * @dev: device for which to release the resource
+ * @new: descriptor of the resource to release
+ *
+ * Releases a resource previously requested using devm_request_resource().
+ */
+void devm_release_resource(struct device *dev, struct resource *new)
+{
+	WARN_ON(devres_release(dev, devm_resource_release, devm_resource_match,
+			       new));
+}
+EXPORT_SYMBOL(devm_release_resource);
+
 struct region_devres {
 	struct resource *parent;
 	resource_size_t start;
-- 
cgit v1.2.3


From efd01a72e7ec99ed583151fbf16b176cd2158967 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Tue, 5 Aug 2014 14:08:55 +0200
Subject: PCI/AER: Make <linux/aer.h> standalone includable

The header file references u16 and u32 types, but they are not defined in
the header nor does the header pull in the necessary includes for them.
This causes build breakage when the file is included without any of the
dependencies being satisfied from somewhere else.

Fix this by including linux/types.h (for u16 and u32).

[bhelgaas: removed pci_dev declaration (already added by 5ccb8225abf2)]
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/aer.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/aer.h b/include/linux/aer.h
index c826d1c28f9c..4fef65e57023 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -7,6 +7,8 @@
 #ifndef _AER_H_
 #define _AER_H_
 
+#include <linux/types.h>
+
 #define AER_NONFATAL			0
 #define AER_FATAL			1
 #define AER_CORRECTABLE			2
-- 
cgit v1.2.3


From 6fa9e1be7f28dd407d710c3ab367b1e5bc34c2bf Mon Sep 17 00:00:00 2001
From: Piotr Król <piotr.krol@3mdeb.com>
Date: Fri, 5 Sep 2014 00:58:02 +0200
Subject: usb: usbip: fix usbip.h path in userspace tool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes: 588b48caf65c ("usbip: move usbip userspace code out of staging")
which introduced build failure by not changing uapi/usbip.h include path
according to new location.

Signed-off-by: Piotr Król <piotr.krol@3mdeb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/Kbuild             | 1 +
 tools/usb/usbip/libsrc/usbip_common.h | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 24e9033f8b3f..9955c3b0ef93 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -395,6 +395,7 @@ header-y += un.h
 header-y += unistd.h
 header-y += unix_diag.h
 header-y += usbdevice_fs.h
+header-y += usbip.h
 header-y += utime.h
 header-y += utsname.h
 header-y += uuid.h
diff --git a/tools/usb/usbip/libsrc/usbip_common.h b/tools/usb/usbip/libsrc/usbip_common.h
index 5a0e95edf4df..15fe792e1e96 100644
--- a/tools/usb/usbip/libsrc/usbip_common.h
+++ b/tools/usb/usbip/libsrc/usbip_common.h
@@ -15,7 +15,7 @@
 #include <syslog.h>
 #include <unistd.h>
 #include <linux/usb/ch9.h>
-#include "../../uapi/usbip.h"
+#include <linux/usbip.h>
 
 #ifndef USBIDS_FILE
 #define USBIDS_FILE "/usr/share/hwdata/usb.ids"
-- 
cgit v1.2.3


From 2f711939d2ea9dfaecebecd1324d2ec7a7a21f65 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 2 Sep 2014 15:49:25 +0200
Subject: ipv6: add sysctl_mld_qrv to configure query robustness variable

This patch adds a new sysctl_mld_qrv knob to configure the mldv1/v2 query
robustness variable. It specifies how many retransmit of unsolicited mld
retransmit should happen. Admins might want to tune this on lossy links.

Also reset mld state on interface down/up, so we pick up new sysctl
settings during interface up event.

IPv6 certification requests this knob to be available.

I didn't make this knob netns specific, as it is mostly a setting in a
physical environment and should be per host.

Cc: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  5 +++++
 include/net/ipv6.h                     |  1 +
 net/ipv6/mcast.c                       | 25 +++++++++++++++----------
 net/ipv6/sysctl_net_ipv6.c             | 10 ++++++++++
 4 files changed, 31 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 3cce8ea6b139..cfc71ac0f764 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1152,6 +1152,11 @@ anycast_src_echo_reply - BOOLEAN
 	FALSE: disabled
 	Default: FALSE
 
+mld_qrv - INTEGER
+	Controls the MLD query robustness variable (see RFC3810 9.1).
+	Default: 2 (as specified by RFC3810 9.1)
+	Minimum: 1 (as specified by RFC6636 4.5)
+
 IPv6 Fragmentation:
 
 ip6frag_high_thresh - INTEGER
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index a2db816e8461..7e247e9b8765 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -121,6 +121,7 @@ struct frag_hdr {
 
 /* sysctls */
 extern int sysctl_mld_max_msf;
+extern int sysctl_mld_qrv;
 
 #define _DEVINC(net, statname, modifier, idev, field)			\
 ({									\
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 70881795da96..64919425f1ab 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -121,6 +121,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 #define IPV6_MLD_MAX_MSF	64
 
 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF;
+int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT;
 
 /*
  *	socket join on multicast group
@@ -1191,15 +1192,16 @@ static void mld_update_qrv(struct inet6_dev *idev,
 	 * and SHOULD NOT be one. Catch this here if we ever run
 	 * into such a case in future.
 	 */
+	const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv);
 	WARN_ON(idev->mc_qrv == 0);
 
 	if (mlh2->mld2q_qrv > 0)
 		idev->mc_qrv = mlh2->mld2q_qrv;
 
-	if (unlikely(idev->mc_qrv < 2)) {
+	if (unlikely(idev->mc_qrv < min_qrv)) {
 		net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n",
-				     idev->mc_qrv, MLD_QRV_DEFAULT);
-		idev->mc_qrv = MLD_QRV_DEFAULT;
+				     idev->mc_qrv, min_qrv);
+		idev->mc_qrv = min_qrv;
 	}
 }
 
@@ -2478,6 +2480,14 @@ void ipv6_mc_down(struct inet6_dev *idev)
 	mld_clear_delrec(idev);
 }
 
+static void ipv6_mc_reset(struct inet6_dev *idev)
+{
+	idev->mc_qrv = sysctl_mld_qrv;
+	idev->mc_qi = MLD_QI_DEFAULT;
+	idev->mc_qri = MLD_QRI_DEFAULT;
+	idev->mc_v1_seen = 0;
+	idev->mc_maxdelay = unsolicited_report_interval(idev);
+}
 
 /* Device going up */
 
@@ -2488,6 +2498,7 @@ void ipv6_mc_up(struct inet6_dev *idev)
 	/* Install multicast list, except for all-nodes (already installed) */
 
 	read_lock_bh(&idev->lock);
+	ipv6_mc_reset(idev);
 	for (i = idev->mc_list; i; i = i->next)
 		igmp6_group_added(i);
 	read_unlock_bh(&idev->lock);
@@ -2508,13 +2519,7 @@ void ipv6_mc_init_dev(struct inet6_dev *idev)
 			(unsigned long)idev);
 	setup_timer(&idev->mc_dad_timer, mld_dad_timer_expire,
 		    (unsigned long)idev);
-
-	idev->mc_qrv = MLD_QRV_DEFAULT;
-	idev->mc_qi = MLD_QI_DEFAULT;
-	idev->mc_qri = MLD_QRI_DEFAULT;
-
-	idev->mc_maxdelay = unsolicited_report_interval(idev);
-	idev->mc_v1_seen = 0;
+	ipv6_mc_reset(idev);
 	write_unlock_bh(&idev->lock);
 }
 
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 0c56c93619e0..c5c10fafcfe2 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -16,6 +16,8 @@
 #include <net/addrconf.h>
 #include <net/inet_frag.h>
 
+static int one = 1;
+
 static struct ctl_table ipv6_table_template[] = {
 	{
 		.procname	= "bindv6only",
@@ -63,6 +65,14 @@ static struct ctl_table ipv6_rotable[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "mld_qrv",
+		.data		= &sysctl_mld_qrv,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one
+	},
 	{ }
 };
 
-- 
cgit v1.2.3


From a9fe8e29945d56f35235a3a0fba99b4cf181d211 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 2 Sep 2014 15:49:26 +0200
Subject: ipv4: implement igmp_qrv sysctl to tune igmp robustness variable

As in IPv6 people might increase the igmp query robustness variable to
make sure unsolicited state change reports aren't lost on the network. Add
and document this new knob to igmp code.

RFCs allow tuning this parameter back to first IGMP RFC, so we also use
this setting for all counters, including source specific multicast.

Also take over sysctl value when upping the interface and don't reuse
the last one seen on the interface.

Cc: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  5 +++++
 include/linux/igmp.h                   |  1 +
 net/ipv4/igmp.c                        | 31 +++++++++++++++----------------
 net/ipv4/sysctl_net_ipv4.c             | 10 ++++++++++
 4 files changed, 31 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index cfc71ac0f764..db2383cb1df9 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -844,6 +844,11 @@ igmp_max_memberships - INTEGER
 
 	conf/all/*	  is special, changes the settings for all interfaces
 
+igmp_qrv - INTEGER
+	 Controls the IGMP query robustness variable (see RFC2236 8.1).
+	 Default: 2 (as specified by RFC2236 8.1)
+	 Minimum: 1 (as specified by RFC6636 4.5)
+
 log_martians - BOOLEAN
 	Log packets with impossible addresses to kernel log.
 	log_martians for the interface will be enabled if at least one of
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index f47550d75f85..2c677afeea47 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -39,6 +39,7 @@ static inline struct igmpv3_query *
 
 extern int sysctl_igmp_max_memberships;
 extern int sysctl_igmp_max_msf;
+extern int sysctl_igmp_qrv;
 
 struct ip_sf_socklist {
 	unsigned int		sl_max;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 890c4258804c..4146153d875d 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -117,7 +117,7 @@
 #define IGMP_V2_Unsolicited_Report_Interval	(10*HZ)
 #define IGMP_V3_Unsolicited_Report_Interval	(1*HZ)
 #define IGMP_Query_Response_Interval		(10*HZ)
-#define IGMP_Unsolicited_Report_Count		2
+#define IGMP_Query_Robustness_Variable		2
 
 
 #define IGMP_Initial_Report_Delay		(1)
@@ -756,8 +756,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
 {
 	if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
 		return;
-	in_dev->mr_ifc_count = in_dev->mr_qrv ? in_dev->mr_qrv :
-		IGMP_Unsolicited_Report_Count;
+	in_dev->mr_ifc_count = in_dev->mr_qrv ?: sysctl_igmp_qrv;
 	igmp_ifc_start_timer(in_dev, 1);
 }
 
@@ -1086,8 +1085,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	pmc->interface = im->interface;
 	in_dev_hold(in_dev);
 	pmc->multiaddr = im->multiaddr;
-	pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
-		IGMP_Unsolicited_Report_Count;
+	pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
 	pmc->sfmode = im->sfmode;
 	if (pmc->sfmode == MCAST_INCLUDE) {
 		struct ip_sf_list *psf;
@@ -1226,8 +1224,7 @@ static void igmp_group_added(struct ip_mc_list *im)
 	}
 	/* else, v3 */
 
-	im->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
-		IGMP_Unsolicited_Report_Count;
+	im->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
 	igmp_ifc_event(in_dev);
 #endif
 }
@@ -1322,7 +1319,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 	spin_lock_init(&im->lock);
 #ifdef CONFIG_IP_MULTICAST
 	setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im);
-	im->unsolicit_count = IGMP_Unsolicited_Report_Count;
+	im->unsolicit_count = sysctl_igmp_qrv;
 #endif
 
 	im->next_rcu = in_dev->mc_list;
@@ -1460,7 +1457,7 @@ void ip_mc_init_dev(struct in_device *in_dev)
 			(unsigned long)in_dev);
 	setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire,
 			(unsigned long)in_dev);
-	in_dev->mr_qrv = IGMP_Unsolicited_Report_Count;
+	in_dev->mr_qrv = sysctl_igmp_qrv;
 #endif
 
 	spin_lock_init(&in_dev->mc_tomb_lock);
@@ -1474,6 +1471,9 @@ void ip_mc_up(struct in_device *in_dev)
 
 	ASSERT_RTNL();
 
+#ifdef CONFIG_IP_MULTICAST
+	in_dev->mr_qrv = sysctl_igmp_qrv;
+#endif
 	ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS);
 
 	for_each_pmc_rtnl(in_dev, pmc)
@@ -1540,7 +1540,9 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr)
  */
 int sysctl_igmp_max_memberships __read_mostly = IP_MAX_MEMBERSHIPS;
 int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF;
-
+#ifdef CONFIG_IP_MULTICAST
+int sysctl_igmp_qrv __read_mostly = IGMP_Query_Robustness_Variable;
+#endif
 
 static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
 	__be32 *psfsrc)
@@ -1575,8 +1577,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
 #ifdef CONFIG_IP_MULTICAST
 		if (psf->sf_oldin &&
 		    !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) {
-			psf->sf_crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
-				IGMP_Unsolicited_Report_Count;
+			psf->sf_crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
 			psf->sf_next = pmc->tomb;
 			pmc->tomb = psf;
 			rv = 1;
@@ -1639,8 +1640,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 		/* filter mode change */
 		pmc->sfmode = MCAST_INCLUDE;
 #ifdef CONFIG_IP_MULTICAST
-		pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
-			IGMP_Unsolicited_Report_Count;
+		pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
 		in_dev->mr_ifc_count = pmc->crcount;
 		for (psf = pmc->sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;
@@ -1818,8 +1818,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 #ifdef CONFIG_IP_MULTICAST
 		/* else no filters; keep old mode for reports */
 
-		pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
-			IGMP_Unsolicited_Report_Count;
+		pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
 		in_dev->mr_ifc_count = pmc->crcount;
 		for (psf = pmc->sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 79a007c52558..45d156dacd61 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -450,6 +450,16 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+#ifdef CONFIG_IP_MULTICAST
+	{
+		.procname	= "igmp_qrv",
+		.data		= &sysctl_igmp_qrv,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one
+	},
+#endif
 	{
 		.procname	= "inet_peer_threshold",
 		.data		= &inet_peer_threshold,
-- 
cgit v1.2.3


From fb38ab4cd05e11184fd2c3ef916fa106ecc505fc Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 5 Sep 2014 15:52:28 +0800
Subject: crypto: drbg - backport "fix maximum value checks on 32 bit systems"

This is a backport of commit b9347aff91ce4789619168539f08202d8d6a1177.
This backport is needed as without it the code will crash on 32-bit
systems.

The maximum values for additional input string or generated blocks is
larger than 1<<32. To ensure a sensible value on 32 bit systems, return
SIZE_MAX on 32 bit systems. This value is lower than the maximum
allowed values defined in SP800-90A. The standard allow lower maximum
values, but not larger values.

SIZE_MAX - 1 is used for drbg_max_addtl to allow
drbg_healthcheck_sanity to check the enforcement of the variable
without wrapping.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/drbg.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index 831d786976c5..882675e7c055 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -162,12 +162,25 @@ static inline size_t drbg_max_request_bytes(struct drbg_state *drbg)
 
 static inline size_t drbg_max_addtl(struct drbg_state *drbg)
 {
+#if (__BITS_PER_LONG == 32)
+	/*
+	 * SP800-90A allows smaller maximum numbers to be returned -- we
+	 * return SIZE_MAX - 1 to allow the verification of the enforcement
+	 * of this value in drbg_healthcheck_sanity.
+	 */
+	return (SIZE_MAX - 1);
+#else
 	return (1UL<<(drbg->core->max_addtllen));
+#endif
 }
 
 static inline size_t drbg_max_requests(struct drbg_state *drbg)
 {
+#if (__BITS_PER_LONG == 32)
+	return SIZE_MAX;
+#else
 	return (1UL<<(drbg->core->max_req));
+#endif
 }
 
 /*
-- 
cgit v1.2.3


From 4334ac2db2be9e278c95fd15260c1f49f698ffc5 Mon Sep 17 00:00:00 2001
From: Marek Roszko <mark.roszko@gmail.com>
Date: Sat, 23 Aug 2014 23:12:04 -0400
Subject: pinctrl: at91: add drive strength configuration

The SAMA5 and SAM9x5 series both have drive strength
options for the PIOs. This patch adds the ability to set
one of three hardware options for drive strengths of low,
medium or high for the each pin. The actual current output
of the chip based on the setting is defined in the datasheets
and varies per pins separate from banks and with supply
voltage.

This patch adds three new dt-bindings that allow setting the
strength when configuring pins. By default, no change will
be made to the drive strength of a pin from its reset value.
Due to the difference between the register addresses of the
SAMA5 and SAM9x5 series, a new sama5d3-pinctrl id was added.

Signed-off-by: Marek Roszko <mark.roszko@gmail.com>
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/mach-at91/include/mach/at91_pio.h |   6 ++
 drivers/pinctrl/pinctrl-at91.c             | 162 ++++++++++++++++++++++++++++-
 include/dt-bindings/pinctrl/at91.h         |   5 +
 3 files changed, 172 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/arm/mach-at91/include/mach/at91_pio.h b/arch/arm/mach-at91/include/mach/at91_pio.h
index 732b11c37f1a..7b7366253ceb 100644
--- a/arch/arm/mach-at91/include/mach/at91_pio.h
+++ b/arch/arm/mach-at91/include/mach/at91_pio.h
@@ -71,4 +71,10 @@
 #define ABCDSR_PERIPH_C	0x2
 #define ABCDSR_PERIPH_D	0x3
 
+#define SAMA5D3_PIO_DRIVER1		0x118  /*PIO Driver 1 register offset*/
+#define SAMA5D3_PIO_DRIVER2		0x11C  /*PIO Driver 2 register offset*/
+
+#define AT91SAM9X5_PIO_DRIVER1	0x114  /*PIO Driver 1 register offset*/
+#define AT91SAM9X5_PIO_DRIVER2	0x118  /*PIO Driver 2 register offset*/
+
 #endif
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index 4839c36a3a1c..03b748ea3810 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -58,10 +58,27 @@ static int gpio_banks;
 #define DEGLITCH	(1 << 2)
 #define PULL_DOWN	(1 << 3)
 #define DIS_SCHMIT	(1 << 4)
+#define DRIVE_STRENGTH_SHIFT	5
+#define DRIVE_STRENGTH_MASK		0x3
+#define DRIVE_STRENGTH   (DRIVE_STRENGTH_MASK << DRIVE_STRENGTH_SHIFT)
 #define DEBOUNCE	(1 << 16)
 #define DEBOUNCE_VAL_SHIFT	17
 #define DEBOUNCE_VAL	(0x3fff << DEBOUNCE_VAL_SHIFT)
 
+/**
+ * These defines will translated the dt binding settings to our internal
+ * settings. They are not necessarily the same value as the register setting.
+ * The actual drive strength current of low, medium and high must be looked up
+ * from the corresponding device datasheet. This value is different for pins
+ * that are even in the same banks. It is also dependent on VCC.
+ * DRIVE_STRENGTH_DEFAULT is just a placeholder to avoid changing the drive
+ * strength when there is no dt config for it.
+ */
+#define DRIVE_STRENGTH_DEFAULT		(0 << DRIVE_STRENGTH_SHIFT)
+#define DRIVE_STRENGTH_LOW          (1 << DRIVE_STRENGTH_SHIFT)
+#define DRIVE_STRENGTH_MED          (2 << DRIVE_STRENGTH_SHIFT)
+#define DRIVE_STRENGTH_HI           (3 << DRIVE_STRENGTH_SHIFT)
+
 /**
  * struct at91_pmx_func - describes AT91 pinmux functions
  * @name: the name of this specific function
@@ -148,6 +165,9 @@ struct at91_pinctrl_mux_ops {
 	void (*set_pulldown)(void __iomem *pio, unsigned mask, bool is_on);
 	bool (*get_schmitt_trig)(void __iomem *pio, unsigned pin);
 	void (*disable_schmitt_trig)(void __iomem *pio, unsigned mask);
+	unsigned (*get_drivestrength)(void __iomem *pio, unsigned pin);
+	void (*set_drivestrength)(void __iomem *pio, unsigned pin,
+					u32 strength);
 	/* irq */
 	int (*irq_type)(struct irq_data *d, unsigned type);
 };
@@ -315,6 +335,30 @@ static unsigned pin_to_mask(unsigned int pin)
 	return 1 << pin;
 }
 
+static unsigned two_bit_pin_value_shift_amount(unsigned int pin)
+{
+	/* return the shift value for a pin for "two bit" per pin registers,
+	 * i.e. drive strength */
+	return 2*((pin >= MAX_NB_GPIO_PER_BANK/2)
+			? pin - MAX_NB_GPIO_PER_BANK/2 : pin);
+}
+
+static unsigned sama5d3_get_drive_register(unsigned int pin)
+{
+	/* drive strength is split between two registers
+	 * with two bits per pin */
+	return (pin >= MAX_NB_GPIO_PER_BANK/2)
+			? SAMA5D3_PIO_DRIVER2 : SAMA5D3_PIO_DRIVER1;
+}
+
+static unsigned at91sam9x5_get_drive_register(unsigned int pin)
+{
+	/* drive strength is split between two registers
+	 * with two bits per pin */
+	return (pin >= MAX_NB_GPIO_PER_BANK/2)
+			? AT91SAM9X5_PIO_DRIVER2 : AT91SAM9X5_PIO_DRIVER1;
+}
+
 static void at91_mux_disable_interrupt(void __iomem *pio, unsigned mask)
 {
 	writel_relaxed(mask, pio + PIO_IDR);
@@ -468,6 +512,79 @@ static bool at91_mux_pio3_get_schmitt_trig(void __iomem *pio, unsigned pin)
 	return (__raw_readl(pio + PIO_SCHMITT) >> pin) & 0x1;
 }
 
+static inline u32 read_drive_strength(void __iomem *reg, unsigned pin)
+{
+	unsigned tmp = __raw_readl(reg);
+
+	tmp = tmp >> two_bit_pin_value_shift_amount(pin);
+
+	return tmp & DRIVE_STRENGTH_MASK;
+}
+
+static unsigned at91_mux_sama5d3_get_drivestrength(void __iomem *pio,
+							unsigned pin)
+{
+	unsigned tmp = read_drive_strength(pio +
+					sama5d3_get_drive_register(pin), pin);
+
+	/* SAMA5 strength is 1:1 with our defines,
+	 * except 0 is equivalent to low per datasheet */
+	if (!tmp)
+		tmp = DRIVE_STRENGTH_LOW;
+
+	return tmp;
+}
+
+static unsigned at91_mux_sam9x5_get_drivestrength(void __iomem *pio,
+							unsigned pin)
+{
+	unsigned tmp = read_drive_strength(pio +
+				at91sam9x5_get_drive_register(pin), pin);
+
+	/* strength is inverse in SAM9x5s hardware with the pinctrl defines
+	 * hardware: 0 = hi, 1 = med, 2 = low, 3 = rsvd */
+	tmp = DRIVE_STRENGTH_HI - tmp;
+
+	return tmp;
+}
+
+static void set_drive_strength(void __iomem *reg, unsigned pin, u32 strength)
+{
+	unsigned tmp = __raw_readl(reg);
+	unsigned shift = two_bit_pin_value_shift_amount(pin);
+
+	tmp &= ~(DRIVE_STRENGTH_MASK  <<  shift);
+	tmp |= strength << shift;
+
+	__raw_writel(tmp, reg);
+}
+
+static void at91_mux_sama5d3_set_drivestrength(void __iomem *pio, unsigned pin,
+						u32 setting)
+{
+	/* do nothing if setting is zero */
+	if (!setting)
+		return;
+
+	/* strength is 1 to 1 with setting for SAMA5 */
+	set_drive_strength(pio + sama5d3_get_drive_register(pin), pin, setting);
+}
+
+static void at91_mux_sam9x5_set_drivestrength(void __iomem *pio, unsigned pin,
+						u32 setting)
+{
+	/* do nothing if setting is zero */
+	if (!setting)
+		return;
+
+	/* strength is inverse on SAM9x5s with our defines
+	 * 0 = hi, 1 = med, 2 = low, 3 = rsvd */
+	setting = DRIVE_STRENGTH_HI - setting;
+
+	set_drive_strength(pio + at91sam9x5_get_drive_register(pin), pin,
+				setting);
+}
+
 static struct at91_pinctrl_mux_ops at91rm9200_ops = {
 	.get_periph	= at91_mux_get_periph,
 	.mux_A_periph	= at91_mux_set_A_periph,
@@ -491,6 +608,27 @@ static struct at91_pinctrl_mux_ops at91sam9x5_ops = {
 	.set_pulldown	= at91_mux_pio3_set_pulldown,
 	.get_schmitt_trig = at91_mux_pio3_get_schmitt_trig,
 	.disable_schmitt_trig = at91_mux_pio3_disable_schmitt_trig,
+	.get_drivestrength = at91_mux_sam9x5_get_drivestrength,
+	.set_drivestrength = at91_mux_sam9x5_set_drivestrength,
+	.irq_type	= alt_gpio_irq_type,
+};
+
+static struct at91_pinctrl_mux_ops sama5d3_ops = {
+	.get_periph	= at91_mux_pio3_get_periph,
+	.mux_A_periph	= at91_mux_pio3_set_A_periph,
+	.mux_B_periph	= at91_mux_pio3_set_B_periph,
+	.mux_C_periph	= at91_mux_pio3_set_C_periph,
+	.mux_D_periph	= at91_mux_pio3_set_D_periph,
+	.get_deglitch	= at91_mux_pio3_get_deglitch,
+	.set_deglitch	= at91_mux_pio3_set_deglitch,
+	.get_debounce	= at91_mux_pio3_get_debounce,
+	.set_debounce	= at91_mux_pio3_set_debounce,
+	.get_pulldown	= at91_mux_pio3_get_pulldown,
+	.set_pulldown	= at91_mux_pio3_set_pulldown,
+	.get_schmitt_trig = at91_mux_pio3_get_schmitt_trig,
+	.disable_schmitt_trig = at91_mux_pio3_disable_schmitt_trig,
+	.get_drivestrength = at91_mux_sama5d3_get_drivestrength,
+	.set_drivestrength = at91_mux_sama5d3_set_drivestrength,
 	.irq_type	= alt_gpio_irq_type,
 };
 
@@ -716,6 +854,9 @@ static int at91_pinconf_get(struct pinctrl_dev *pctldev,
 		*config |= PULL_DOWN;
 	if (info->ops->get_schmitt_trig && info->ops->get_schmitt_trig(pio, pin))
 		*config |= DIS_SCHMIT;
+	if (info->ops->get_drivestrength)
+		*config |= (info->ops->get_drivestrength(pio, pin)
+				<< DRIVE_STRENGTH_SHIFT);
 
 	return 0;
 }
@@ -729,6 +870,7 @@ static int at91_pinconf_set(struct pinctrl_dev *pctldev,
 	void __iomem *pio;
 	int i;
 	unsigned long config;
+	unsigned pin;
 
 	for (i = 0; i < num_configs; i++) {
 		config = configs[i];
@@ -737,7 +879,8 @@ static int at91_pinconf_set(struct pinctrl_dev *pctldev,
 			"%s:%d, pin_id=%d, config=0x%lx",
 			__func__, __LINE__, pin_id, config);
 		pio = pin_to_controller(info, pin_to_bank(pin_id));
-		mask = pin_to_mask(pin_id % MAX_NB_GPIO_PER_BANK);
+		pin = pin_id % MAX_NB_GPIO_PER_BANK;
+		mask = pin_to_mask(pin);
 
 		if (config & PULL_UP && config & PULL_DOWN)
 			return -EINVAL;
@@ -753,6 +896,10 @@ static int at91_pinconf_set(struct pinctrl_dev *pctldev,
 			info->ops->set_pulldown(pio, mask, config & PULL_DOWN);
 		if (info->ops->disable_schmitt_trig && config & DIS_SCHMIT)
 			info->ops->disable_schmitt_trig(pio, mask);
+		if (info->ops->set_drivestrength)
+			info->ops->set_drivestrength(pio, pin,
+				(config & DRIVE_STRENGTH)
+					>> DRIVE_STRENGTH_SHIFT);
 
 	} /* for each config */
 
@@ -768,6 +915,15 @@ static int at91_pinconf_set(struct pinctrl_dev *pctldev,
 	}					\
 } while (0)
 
+#define DBG_SHOW_FLAG_MASKED(mask,flag) do {	\
+	if ((config & mask) == flag) {		\
+		if (num_conf)			\
+			seq_puts(s, "|");	\
+		seq_puts(s, #flag);		\
+		num_conf++;			\
+	}					\
+} while (0)
+
 static void at91_pinconf_dbg_show(struct pinctrl_dev *pctldev,
 				   struct seq_file *s, unsigned pin_id)
 {
@@ -781,6 +937,9 @@ static void at91_pinconf_dbg_show(struct pinctrl_dev *pctldev,
 	DBG_SHOW_FLAG(PULL_DOWN);
 	DBG_SHOW_FLAG(DIS_SCHMIT);
 	DBG_SHOW_FLAG(DEGLITCH);
+	DBG_SHOW_FLAG_MASKED(DRIVE_STRENGTH, DRIVE_STRENGTH_LOW);
+	DBG_SHOW_FLAG_MASKED(DRIVE_STRENGTH, DRIVE_STRENGTH_MED);
+	DBG_SHOW_FLAG_MASKED(DRIVE_STRENGTH, DRIVE_STRENGTH_HI);
 	DBG_SHOW_FLAG(DEBOUNCE);
 	if (config & DEBOUNCE) {
 		val = config >> DEBOUNCE_VAL_SHIFT;
@@ -945,6 +1104,7 @@ static int at91_pinctrl_parse_functions(struct device_node *np,
 }
 
 static struct of_device_id at91_pinctrl_of_match[] = {
+	{ .compatible = "atmel,sama5d3-pinctrl", .data = &sama5d3_ops },
 	{ .compatible = "atmel,at91sam9x5-pinctrl", .data = &at91sam9x5_ops },
 	{ .compatible = "atmel,at91rm9200-pinctrl", .data = &at91rm9200_ops },
 	{ /* sentinel */ }
diff --git a/include/dt-bindings/pinctrl/at91.h b/include/dt-bindings/pinctrl/at91.h
index 0fee6ff77ffc..bbca3d038900 100644
--- a/include/dt-bindings/pinctrl/at91.h
+++ b/include/dt-bindings/pinctrl/at91.h
@@ -20,6 +20,11 @@
 
 #define AT91_PINCTRL_PULL_UP_DEGLITCH	(AT91_PINCTRL_PULL_UP | AT91_PINCTRL_DEGLITCH)
 
+#define AT91_PINCTRL_DRIVE_STRENGTH_DEFAULT		(0x0 << 5)
+#define AT91_PINCTRL_DRIVE_STRENGTH_LOW			(0x1 << 5)
+#define AT91_PINCTRL_DRIVE_STRENGTH_MED			(0x2 << 5)
+#define AT91_PINCTRL_DRIVE_STRENGTH_HI			(0x3 << 5)
+
 #define AT91_PIOA	0
 #define AT91_PIOB	1
 #define AT91_PIOC	2
-- 
cgit v1.2.3


From 6b44f519017b219a12b37173c7eef8dfce2c0100 Mon Sep 17 00:00:00 2001
From: Scot Doyle <lkml14@scotdoyle.com>
Date: Sun, 24 Aug 2014 17:12:27 +0000
Subject: sched/wait: Document timeout corner case

The timeout may elapse without 0 being returned, such as when waiting
on an unused queue. Document this possibility.

Signed-off-by: Scot Doyle <lkml14@scotdoyle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/alpine.LNX.2.11.1408241710070.6462@localhost.localdomain
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 6fb1ba5f9b2f..034f6fc7c65f 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -280,9 +280,11 @@ do {									\
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  *
- * The function returns 0 if the @timeout elapsed, or the remaining
- * jiffies (at least 1) if the @condition evaluated to %true before
- * the @timeout elapsed.
+ * Returns:
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * or the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed.
  */
 #define wait_event_timeout(wq, condition, timeout)			\
 ({									\
@@ -363,9 +365,11 @@ do {									\
  * change the result of the wait condition.
  *
  * Returns:
- * 0 if the @timeout elapsed, -%ERESTARTSYS if it was interrupted by
- * a signal, or the remaining jiffies (at least 1) if the @condition
- * evaluated to %true before the @timeout elapsed.
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
+ * interrupted by a signal.
  */
 #define wait_event_interruptible_timeout(wq, condition, timeout)	\
 ({									\
-- 
cgit v1.2.3


From d98ad83ee86e523cc00cbf425f456fbd14b4fdc4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 3 Sep 2014 15:24:57 +0300
Subject: mac80211: add Intel Mobile Communications copyright

Our legal structure changed at some point (see wikipedia), but
we forgot to immediately switch over to the new copyright
notice.

For files that we have modified in the time since the change,
add the proper copyright notice now.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     | 1 +
 net/mac80211/cfg.c         | 1 +
 net/mac80211/debugfs.c     | 1 +
 net/mac80211/debugfs_sta.c | 1 +
 net/mac80211/ibss.c        | 1 +
 net/mac80211/ieee80211_i.h | 1 +
 net/mac80211/iface.c       | 1 +
 net/mac80211/key.c         | 1 +
 net/mac80211/main.c        | 1 +
 net/mac80211/mlme.c        | 1 +
 net/mac80211/rx.c          | 1 +
 net/mac80211/scan.c        | 1 +
 net/mac80211/sta_info.c    | 1 +
 net/mac80211/sta_info.h    | 1 +
 net/mac80211/status.c      | 1 +
 net/mac80211/tdls.c        | 1 +
 net/mac80211/tx.c          | 1 +
 net/mac80211/util.c        | 1 +
 net/mac80211/wme.c         | 1 +
 19 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index c9b2bec8db47..db4975c33861 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4,6 +4,7 @@
  * Copyright 2002-2005, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 4d8989b87960..d7f437ef6e7e 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2,6 +2,7 @@
  * mac80211 configuration hooks for cfg80211
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This file is GPLv2 as found in COPYING.
  */
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 0e963bc1ceac..574656174f91 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -3,6 +3,7 @@
  * mac80211 debugfs for wireless PHYs
  *
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * GPLv2
  *
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 4a20fb8f1e23..b5e0a5344e8c 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -2,6 +2,7 @@
  * Copyright 2003-2005	Devicescape Software, Inc.
  * Copyright (c) 2006	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 5f9654d31a8d..56b53571c807 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -6,6 +6,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2009, Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 78f95387e43f..b9d9508a6286 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -3,6 +3,7 @@
  * Copyright 2005, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index bb7288e3c41c..af237223a8cd 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -5,6 +5,7 @@
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz>
  * Copyright 2008, Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 6429d0e1d4a1..f320a04380b9 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -3,6 +3,7 @@
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007-2008	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index e0ab4320a078..0de7c93bf62b 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -2,6 +2,7 @@
  * Copyright 2002-2005, Instant802 Networks, Inc.
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 29fe91d6a094..305e5105aeb1 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -5,6 +5,7 @@
  * Copyright 2005, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 41eb12c87240..b04ca4049c95 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3,6 +3,7 @@
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index a9bb6eb8c3e0..af0d094b2f2f 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -6,6 +6,7 @@
  * Copyright 2005, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index e1f957d5935e..215752e8c5b6 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1,6 +1,7 @@
 /*
  * Copyright 2002-2005, Instant802 Networks, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 16dc1d414f69..9dc7a9d6b0d2 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -1,5 +1,6 @@
 /*
  * Copyright 2002-2005, Devicescape Software, Inc.
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index aa06dcad336e..2800e1c65519 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -3,6 +3,7 @@
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2008-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index f2cb3b6c1871..bcf51e43ccc1 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -3,6 +3,7 @@
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2014, Intel Corporation
+ * Copyright 2014  Intel Mobile Communications GmbH
  *
  * This file is GPLv2 as found in COPYING.
  */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 925c39f4099e..d1b3c223d6f9 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3,6 +3,7 @@
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 725af7a468d2..b444f27a788e 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3,6 +3,7 @@
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 6459946f0b74..3b873989992c 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -1,5 +1,6 @@
 /*
  * Copyright 2004, Instant802 Networks, Inc.
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
-- 
cgit v1.2.3


From 2740f0cf8ec8bc7ee6a58f68841759e367dda98f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 3 Sep 2014 15:24:58 +0300
Subject: cfg80211: add Intel Mobile Communications copyright

Our legal structure changed at some point (see wikipedia), but
we forgot to immediately switch over to the new copyright
notice.

For files that we have modified in the time since the change,
add the proper copyright notice now.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 1 +
 include/net/cfg80211.h    | 1 +
 net/wireless/chan.c       | 1 +
 net/wireless/core.c       | 1 +
 net/wireless/nl80211.c    | 1 +
 net/wireless/reg.c        | 1 +
 net/wireless/scan.c       | 1 +
 net/wireless/util.c       | 1 +
 8 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 8018c915ee63..77d4f26e0235 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -6,6 +6,7 @@
  * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi>
  * Copyright (c) 2005, Devicescape Software, Inc.
  * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
+ * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ab21299c8f4d..6be68bb31918 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4,6 +4,7 @@
  * 802.11 device and configuration interface
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014 Intel Mobile Communications GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 992b34070bcb..72d81e2154d5 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -4,6 +4,7 @@
  * any point in time.
  *
  * Copyright 2009	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  */
 
 #include <linux/export.h>
diff --git a/net/wireless/core.c b/net/wireless/core.c
index a207eb116829..9698fe709251 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -2,6 +2,7 @@
  * This is the linux wireless configuration interface.
  *
  * Copyright 2006-2010		Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 3011401f52c0..d876146498dd 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2,6 +2,7 @@
  * This is the new netlink-based wireless configuration interface.
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  */
 
 #include <linux/if.h>
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 1afdf45db38f..8bfc9b172a49 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -3,6 +3,7 @@
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2008-2011	Luis R. Rodriguez <mcgrof@qca.qualcomm.com>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 620a4b40d466..bda39f149810 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2,6 +2,7 @@
  * cfg80211 scan result handling
  *
  * Copyright 2008 Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  */
 #include <linux/kernel.h>
 #include <linux/slab.h>
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 728f1c0dc70d..a8b2816ffcb9 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -2,6 +2,7 @@
  * Wireless utility functions
  *
  * Copyright 2007-2009	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2013-2014  Intel Mobile Communications GmbH
  */
 #include <linux/export.h>
 #include <linux/bitops.h>
-- 
cgit v1.2.3


From 1c7e23bf50264a251de53ad9fb1604683b801258 Mon Sep 17 00:00:00 2001
From: Assaf Krauss <assaf.krauss@intel.com>
Date: Wed, 3 Sep 2014 15:25:00 +0300
Subject: nl80211: Allow declaring RRM-related features

Radio Resource Measurement (RRM) is a bundle of features which will
require the entire stack to participate.
In this patch, the driver is given the opportunity to advertise the
device's support for these RRM-related features, using feature flags:
1. Support for Quiet IEs.
2. Support for adding DS Parameter Set IE to probe requests.
3. Support for adding WFA TPC Report IE to probe requests.
4. Support for inserting tx power value to tx-ed packets at a fixed
   offset. This is used in action frames, such as RRM's Link
   Measurement Report, where the actual tx power should be reported
   in the frame.

Signed-off-by: Assaf Krauss <assaf.krauss@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index d097568da690..c166d3d23e55 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3968,6 +3968,16 @@ enum nl80211_ap_sme_features {
  * @NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE: This driver supports dynamic
  *	channel bandwidth change (e.g., HT 20 <-> 40 MHz channel) during the
  *	lifetime of a BSS.
+ * @NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES: This device adds a DS Parameter
+ *	Set IE to probe requests.
+ * @NL80211_FEATURE_WFA_TPC_IE_IN_PROBES: This device adds a WFA TPC Report IE
+ *	to probe requests.
+ * @NL80211_FEATURE_QUIET: This device, in client mode, supports Quiet Period
+ *	requests sent to it by an AP.
+ * @NL80211_FEATURE_TX_POWER_INSERTION: This device is capable of inserting the
+ *	current tx power value into the TPC Report IE in the spectrum
+ *	management TPC Report action frame, and in the Radio Measurement Link
+ *	Measurement Report action frame.
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -3989,6 +3999,10 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_USERSPACE_MPM			= 1 << 16,
 	NL80211_FEATURE_ACTIVE_MONITOR			= 1 << 17,
 	NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE	= 1 << 18,
+	NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES	= 1 << 19,
+	NL80211_FEATURE_WFA_TPC_IE_IN_PROBES		= 1 << 20,
+	NL80211_FEATURE_QUIET				= 1 << 21,
+	NL80211_FEATURE_TX_POWER_INSERTION		= 1 << 22,
 };
 
 /**
-- 
cgit v1.2.3


From bab5ab7d2a5466406e8003d038cc7ce6b2d5d804 Mon Sep 17 00:00:00 2001
From: Assaf Krauss <assaf.krauss@intel.com>
Date: Wed, 3 Sep 2014 15:25:01 +0300
Subject: nl80211: Add flag attribute for RRM connections

Add a flag attribute to use in associations, for tagging the target
connection as supporting RRM. It is the responsibility of upper
layers to set this flag only if both the underlying device, and the
target network indeed support RRM.
To be used in ASSOCIATE and CONNECT commands.

Signed-off-by: Assaf Krauss <assaf.krauss@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  2 ++
 include/uapi/linux/nl80211.h | 13 +++++++++++++
 net/wireless/nl80211.c       | 17 +++++++++++++++++
 3 files changed, 32 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 6be68bb31918..a887eeb5b31e 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1608,10 +1608,12 @@ struct cfg80211_auth_request {
  *
  * @ASSOC_REQ_DISABLE_HT:  Disable HT (802.11n)
  * @ASSOC_REQ_DISABLE_VHT:  Disable VHT
+ * @ASSOC_REQ_USE_RRM: Declare RRM capability in this association
  */
 enum cfg80211_assoc_req_flags {
 	ASSOC_REQ_DISABLE_HT		= BIT(0),
 	ASSOC_REQ_DISABLE_VHT		= BIT(1),
+	ASSOC_REQ_USE_RRM		= BIT(2),
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index c166d3d23e55..de69d3df5e55 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1594,6 +1594,17 @@ enum nl80211_commands {
  * @NL80211_ATTR_TDLS_INITIATOR: flag attribute indicating the current end is
  *	the TDLS link initiator.
  *
+ * @NL80211_ATTR_USE_RRM: flag for indicating whether the current connection
+ *	shall support Radio Resource Measurements (11k). This attribute can be
+ *	used with %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests.
+ *	User space applications are expected to use this flag only if the
+ *	underlying device supports these minimal RRM features:
+ *		%NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES,
+ *		%NL80211_FEATURE_QUIET,
+ *	If this flag is used, driver must add the Power Capabilities IE to the
+ *	association request. In addition, it must also set the RRM capability
+ *	flag in the association request's Capability Info field.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1936,6 +1947,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_TDLS_INITIATOR,
 
+	NL80211_ATTR_USE_RRM,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d876146498dd..459dc2769d0e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -389,6 +389,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 },
 	[NL80211_ATTR_IFACE_SOCKET_OWNER] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CSA_C_OFFSETS_TX] = { .type = NLA_BINARY },
+	[NL80211_ATTR_USE_RRM] = { .type = NLA_FLAG },
 };
 
 /* policy for the key attributes */
@@ -6584,6 +6585,14 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 		       sizeof(req.vht_capa));
 	}
 
+	if (nla_get_flag(info->attrs[NL80211_ATTR_USE_RRM])) {
+		if (!(rdev->wiphy.features &
+		      NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES) ||
+		    !(rdev->wiphy.features & NL80211_FEATURE_QUIET))
+			return -EINVAL;
+		req.flags |= ASSOC_REQ_USE_RRM;
+	}
+
 	err = nl80211_crypto_settings(rdev, info, &req.crypto, 1);
 	if (!err) {
 		wdev_lock(dev->ieee80211_ptr);
@@ -7241,6 +7250,14 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 		       sizeof(connect.vht_capa));
 	}
 
+	if (nla_get_flag(info->attrs[NL80211_ATTR_USE_RRM])) {
+		if (!(rdev->wiphy.features &
+		      NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES) ||
+		    !(rdev->wiphy.features & NL80211_FEATURE_QUIET))
+			return -EINVAL;
+		connect.flags |= ASSOC_REQ_USE_RRM;
+	}
+
 	wdev_lock(dev->ieee80211_ptr);
 	err = cfg80211_connect(rdev, dev, &connect, connkeys, NULL);
 	wdev_unlock(dev->ieee80211_ptr);
-- 
cgit v1.2.3


From 3057dbfdab1b86a77ed6d512fc857b032f78663b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
Date: Thu, 4 Sep 2014 23:57:40 +0200
Subject: cfg80211: enable dynack through nl80211

Enable ACK timeout estimation algorithm (dynack) using mac80211
set_coverage_class API. Dynack is activated passing coverage class equals to -1
to lower drivers and it is automatically disabled setting valid value for
coverage class.
Define NL80211_ATTR_WIPHY_DYN_ACK flag attribute to enable dynack from
userspace. In order to activate dynack NL80211_FEATURE_ACKTO_ESTIMATION feature
flag must be set by lower drivers to indicate dynack capability.

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  2 ++
 include/uapi/linux/nl80211.h | 12 ++++++++++++
 net/wireless/nl80211.c       | 11 +++++++++++
 3 files changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index a887eeb5b31e..0d17ec9df692 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1805,6 +1805,7 @@ struct cfg80211_connect_params {
  * @WIPHY_PARAM_FRAG_THRESHOLD: wiphy->frag_threshold has changed
  * @WIPHY_PARAM_RTS_THRESHOLD: wiphy->rts_threshold has changed
  * @WIPHY_PARAM_COVERAGE_CLASS: coverage class changed
+ * @WIPHY_PARAM_DYN_ACK: dynack has been enabled
  */
 enum wiphy_params_flags {
 	WIPHY_PARAM_RETRY_SHORT		= 1 << 0,
@@ -1812,6 +1813,7 @@ enum wiphy_params_flags {
 	WIPHY_PARAM_FRAG_THRESHOLD	= 1 << 2,
 	WIPHY_PARAM_RTS_THRESHOLD	= 1 << 3,
 	WIPHY_PARAM_COVERAGE_CLASS	= 1 << 4,
+	WIPHY_PARAM_DYN_ACK		= 1 << 5,
 };
 
 /*
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index de69d3df5e55..29c4399e08b9 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1605,6 +1605,12 @@ enum nl80211_commands {
  *	association request. In addition, it must also set the RRM capability
  *	flag in the association request's Capability Info field.
  *
+ * @NL80211_ATTR_WIPHY_DYN_ACK: flag attribute used to enable ACK timeout
+ *	estimation algorithm (dynack). In order to activate dynack
+ *	%NL80211_FEATURE_ACKTO_ESTIMATION feature flag must be set by lower
+ *	drivers to indicate dynack capability. Dynack is automatically disabled
+ *	setting valid value for coverage class.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1949,6 +1955,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_USE_RRM,
 
+	NL80211_ATTR_WIPHY_DYN_ACK,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -3991,6 +3999,9 @@ enum nl80211_ap_sme_features {
  *	current tx power value into the TPC Report IE in the spectrum
  *	management TPC Report action frame, and in the Radio Measurement Link
  *	Measurement Report action frame.
+ * @NL80211_FEATURE_ACKTO_ESTIMATION: This driver supports dynamic ACK timeout
+ *	estimation (dynack). %NL80211_ATTR_WIPHY_DYN_ACK flag attribute is used
+ *	to enable dynack.
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -4016,6 +4027,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_WFA_TPC_IE_IN_PROBES		= 1 << 20,
 	NL80211_FEATURE_QUIET				= 1 << 21,
 	NL80211_FEATURE_TX_POWER_INSERTION		= 1 << 22,
+	NL80211_FEATURE_ACKTO_ESTIMATION		= 1 << 23,
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 459dc2769d0e..cf178d2b621d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -226,6 +226,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_WIPHY_FRAG_THRESHOLD] = { .type = NLA_U32 },
 	[NL80211_ATTR_WIPHY_RTS_THRESHOLD] = { .type = NLA_U32 },
 	[NL80211_ATTR_WIPHY_COVERAGE_CLASS] = { .type = NLA_U8 },
+	[NL80211_ATTR_WIPHY_DYN_ACK] = { .type = NLA_FLAG },
 
 	[NL80211_ATTR_IFTYPE] = { .type = NLA_U32 },
 	[NL80211_ATTR_IFINDEX] = { .type = NLA_U32 },
@@ -2239,11 +2240,21 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_COVERAGE_CLASS]) {
+		if (info->attrs[NL80211_ATTR_WIPHY_DYN_ACK])
+			return -EINVAL;
+
 		coverage_class = nla_get_u8(
 			info->attrs[NL80211_ATTR_WIPHY_COVERAGE_CLASS]);
 		changed |= WIPHY_PARAM_COVERAGE_CLASS;
 	}
 
+	if (info->attrs[NL80211_ATTR_WIPHY_DYN_ACK]) {
+		if (!(rdev->wiphy.features & NL80211_FEATURE_ACKTO_ESTIMATION))
+			return -EOPNOTSUPP;
+
+		changed |= WIPHY_PARAM_DYN_ACK;
+	}
+
 	if (changed) {
 		u8 old_retry_short, old_retry_long;
 		u32 old_frag_threshold, old_rts_threshold;
-- 
cgit v1.2.3


From a4bcaf5556da649f0160e60fa7b4bb2c29801c12 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
Date: Thu, 4 Sep 2014 23:57:41 +0200
Subject: mac80211: extend set_coverage_class signature

Extend mac80211 set_coverage_class API in order to enable ACK timeout
estimation algorithm (dynack) passing coverage class equals to -1
to lower drivers. Synchronize set_coverage_class routine signature with
mac80211 function pointer for p54, ath9k, ath9k_htc and ath5k drivers.

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath5k/mac80211-ops.c | 2 +-
 drivers/net/wireless/ath/ath9k/htc_drv_main.c | 2 +-
 drivers/net/wireless/ath/ath9k/main.c         | 3 ++-
 drivers/net/wireless/p54/main.c               | 3 ++-
 include/net/mac80211.h                        | 6 ++++--
 net/mac80211/cfg.c                            | 9 +++++++--
 net/mac80211/driver-ops.h                     | 2 +-
 net/mac80211/trace.h                          | 4 ++--
 8 files changed, 20 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index b65c38fdaa4b..ab2709a43768 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -704,7 +704,7 @@ ath5k_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey)
  * reset.
  */
 static void
-ath5k_set_coverage_class(struct ieee80211_hw *hw, u8 coverage_class)
+ath5k_set_coverage_class(struct ieee80211_hw *hw, s16 coverage_class)
 {
 	struct ath5k_hw *ah = hw->priv;
 
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 5627917c5ff7..994fff1ff519 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -1722,7 +1722,7 @@ static int ath9k_htc_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 }
 
 static void ath9k_htc_set_coverage_class(struct ieee80211_hw *hw,
-					 u8 coverage_class)
+					 s16 coverage_class)
 {
 	struct ath9k_htc_priv *priv = hw->priv;
 
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index e6ac8d2e610c..97c028e36647 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -1959,7 +1959,8 @@ static int ath9k_get_survey(struct ieee80211_hw *hw, int idx,
 	return 0;
 }
 
-static void ath9k_set_coverage_class(struct ieee80211_hw *hw, u8 coverage_class)
+static void ath9k_set_coverage_class(struct ieee80211_hw *hw,
+				     s16 coverage_class)
 {
 	struct ath_softc *sc = hw->priv;
 	struct ath_hw *ah = sc->sc_ah;
diff --git a/drivers/net/wireless/p54/main.c b/drivers/net/wireless/p54/main.c
index 7be3a4839640..97aeff0edb84 100644
--- a/drivers/net/wireless/p54/main.c
+++ b/drivers/net/wireless/p54/main.c
@@ -696,7 +696,8 @@ static void p54_flush(struct ieee80211_hw *dev, struct ieee80211_vif *vif,
 	WARN(total, "tx flush timeout, unresponsive firmware");
 }
 
-static void p54_set_coverage_class(struct ieee80211_hw *dev, u8 coverage_class)
+static void p54_set_coverage_class(struct ieee80211_hw *dev,
+				   s16 coverage_class)
 {
 	struct p54_common *priv = dev->priv;
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index db4975c33861..c6e6a6804ee4 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2673,7 +2673,9 @@ enum ieee80211_roc_type {
  *
  * @set_coverage_class: Set slot time for given coverage class as specified
  *	in IEEE 802.11-2007 section 17.3.8.6 and modify ACK timeout
- *	accordingly. This callback is not required and may sleep.
+ *	accordingly; coverage class equals to -1 to enable ACK timeout
+ *	estimation algorithm (dynack). To disable dynack set valid value for
+ *	coverage class. This callback is not required and may sleep.
  *
  * @testmode_cmd: Implement a cfg80211 test mode command. The passed @vif may
  *	be %NULL. The callback can sleep.
@@ -2957,7 +2959,7 @@ struct ieee80211_ops {
 	int (*get_survey)(struct ieee80211_hw *hw, int idx,
 		struct survey_info *survey);
 	void (*rfkill_poll)(struct ieee80211_hw *hw);
-	void (*set_coverage_class)(struct ieee80211_hw *hw, u8 coverage_class);
+	void (*set_coverage_class)(struct ieee80211_hw *hw, s16 coverage_class);
 #ifdef CONFIG_NL80211_TESTMODE
 	int (*testmode_cmd)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			    void *data, int len);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 4c1681bae232..101ae6cfad81 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1978,8 +1978,13 @@ static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed)
 			return err;
 	}
 
-	if (changed & WIPHY_PARAM_COVERAGE_CLASS) {
-		err = drv_set_coverage_class(local, wiphy->coverage_class);
+	if ((changed & WIPHY_PARAM_COVERAGE_CLASS) ||
+	    (changed & WIPHY_PARAM_DYN_ACK)) {
+		s16 coverage_class;
+
+		coverage_class = changed & WIPHY_PARAM_COVERAGE_CLASS ?
+					wiphy->coverage_class : -1;
+		err = drv_set_coverage_class(local, coverage_class);
 
 		if (err)
 			return err;
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 11423958116a..196d48c68134 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -450,7 +450,7 @@ static inline int drv_set_rts_threshold(struct ieee80211_local *local,
 }
 
 static inline int drv_set_coverage_class(struct ieee80211_local *local,
-					 u8 value)
+					 s16 value)
 {
 	int ret = 0;
 	might_sleep();
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 02ac535d1274..38fae7ebe984 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -672,13 +672,13 @@ DEFINE_EVENT(local_u32_evt, drv_set_rts_threshold,
 );
 
 TRACE_EVENT(drv_set_coverage_class,
-	TP_PROTO(struct ieee80211_local *local, u8 value),
+	TP_PROTO(struct ieee80211_local *local, s16 value),
 
 	TP_ARGS(local, value),
 
 	TP_STRUCT__entry(
 		LOCAL_ENTRY
-		__field(u8, value)
+		__field(s16, value)
 	),
 
 	TP_fast_assign(
-- 
cgit v1.2.3


From 7d75a871888e3f5e1a7c99bf240d1cd67d8bdfa0 Mon Sep 17 00:00:00 2001
From: Paul Bolle <pebolle@tiscali.nl>
Date: Fri, 5 Sep 2014 13:09:25 +0200
Subject: gpio: fix 'CONFIG_GPIO_IRQCHIP' comments

These two typos were introduced in commit 1425052097b5 ("gpio: add IRQ
chip helpers in gpiolib").

The correct symbol name is CONFIG_GPIOLIB_IRQCHIP.

[jkosina@suse.cz: add changelog]
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/gpio/driver.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 573e4f3243d0..4fcd60913a42 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -105,7 +105,7 @@ struct gpio_chip {
 
 #ifdef CONFIG_GPIOLIB_IRQCHIP
 	/*
-	 * With CONFIG_GPIO_IRQCHIP we get an irqchip inside the gpiolib
+	 * With CONFIG_GPIOLIB_IRQCHIP we get an irqchip inside the gpiolib
 	 * to handle IRQs for most practical cases.
 	 */
 	struct irq_chip		*irqchip;
@@ -221,7 +221,7 @@ int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
 		irq_flow_handler_t handler,
 		unsigned int type);
 
-#endif /* CONFIG_GPIO_IRQCHIP */
+#endif /* CONFIG_GPIOLIB_IRQCHIP */
 
 #else /* CONFIG_GPIOLIB */
 
-- 
cgit v1.2.3


From 60a3b2253c413cf601783b070507d7dd6620c954 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Tue, 2 Sep 2014 22:53:44 +0200
Subject: net: bpf: make eBPF interpreter images read-only

With eBPF getting more extended and exposure to user space is on it's way,
hardening the memory range the interpreter uses to steer its command flow
seems appropriate.  This patch moves the to be interpreted bytecode to
read-only pages.

In case we execute a corrupted BPF interpreter image for some reason e.g.
caused by an attacker which got past a verifier stage, it would not only
provide arbitrary read/write memory access but arbitrary function calls
as well. After setting up the BPF interpreter image, its contents do not
change until destruction time, thus we can setup the image on immutable
made pages in order to mitigate modifications to that code. The idea
is derived from commit 314beb9bcabf ("x86: bpf_jit_comp: secure bpf jit
against spraying attacks").

This is possible because bpf_prog is not part of sk_filter anymore.
After setup bpf_prog cannot be altered during its life-time. This prevents
any modifications to the entire bpf_prog structure (incl. function/JIT
image pointer).

Every eBPF program (including classic BPF that are migrated) have to call
bpf_prog_select_runtime() to select either interpreter or a JIT image
as a last setup step, and they all are being freed via bpf_prog_free(),
including non-JIT. Therefore, we can easily integrate this into the
eBPF life-time, plus since we directly allocate a bpf_prog, we have no
performance penalty.

Tested with seccomp and test_bpf testsuite in JIT/non-JIT mode and manual
inspection of kernel_page_tables.  Brad Spengler proposed the same idea
via Twitter during development of this patch.

Joint work with Hannes Frederic Sowa.

Suggested-by: Brad Spengler <spender@grsecurity.net>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Kees Cook <keescook@chromium.org>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/net/bpf_jit_32.c       |  3 +-
 arch/mips/net/bpf_jit.c         |  3 +-
 arch/powerpc/net/bpf_jit_comp.c |  3 +-
 arch/s390/net/bpf_jit_comp.c    |  2 +-
 arch/sparc/net/bpf_jit_comp.c   |  3 +-
 arch/x86/net/bpf_jit_comp.c     | 18 ++++------
 include/linux/filter.h          | 49 ++++++++++++++++++++++---
 kernel/bpf/core.c               | 80 +++++++++++++++++++++++++++++++++++++++--
 kernel/seccomp.c                |  7 ++--
 lib/test_bpf.c                  |  2 +-
 net/core/filter.c               |  6 ++--
 11 files changed, 144 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index a37b989a2f91..a76623bcf722 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -930,5 +930,6 @@ void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
 		module_free(NULL, fp->bpf_func);
-	kfree(fp);
+
+	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 05a56619ece2..cfa83cf2447d 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -1427,5 +1427,6 @@ void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
 		module_free(NULL, fp->bpf_func);
-	kfree(fp);
+
+	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 3afa6f4c1957..40c53ff59124 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -697,5 +697,6 @@ void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
 		module_free(NULL, fp->bpf_func);
-	kfree(fp);
+
+	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 61e45b7c04d7..f2833c5b218a 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -887,5 +887,5 @@ void bpf_jit_free(struct bpf_prog *fp)
 	module_free(NULL, header);
 
 free_filter:
-	kfree(fp);
+	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 1f76c22a6a75..f7a736b645e8 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -812,5 +812,6 @@ void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
 		module_free(NULL, fp->bpf_func);
-	kfree(fp);
+
+	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b08a98c59530..39ccfbb4a723 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -972,23 +972,17 @@ out:
 	kfree(addrs);
 }
 
-static void bpf_jit_free_deferred(struct work_struct *work)
+void bpf_jit_free(struct bpf_prog *fp)
 {
-	struct bpf_prog *fp = container_of(work, struct bpf_prog, work);
 	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
 	struct bpf_binary_header *header = (void *)addr;
 
+	if (!fp->jited)
+		goto free_filter;
+
 	set_memory_rw(addr, header->pages);
 	module_free(NULL, header);
-	kfree(fp);
-}
 
-void bpf_jit_free(struct bpf_prog *fp)
-{
-	if (fp->jited) {
-		INIT_WORK(&fp->work, bpf_jit_free_deferred);
-		schedule_work(&fp->work);
-	} else {
-		kfree(fp);
-	}
+free_filter:
+	bpf_prog_unlock_free(fp);
 }
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a5227ab8ccb1..c78994593355 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -9,6 +9,11 @@
 #include <linux/skbuff.h>
 #include <linux/workqueue.h>
 #include <uapi/linux/filter.h>
+#include <asm/cacheflush.h>
+
+struct sk_buff;
+struct sock;
+struct seccomp_data;
 
 /* Internally used and optimized filter representation with extended
  * instruction set based on top of classic BPF.
@@ -320,20 +325,23 @@ struct sock_fprog_kern {
 	struct sock_filter	*filter;
 };
 
-struct sk_buff;
-struct sock;
-struct seccomp_data;
+struct bpf_work_struct {
+	struct bpf_prog *prog;
+	struct work_struct work;
+};
 
 struct bpf_prog {
+	u32			pages;		/* Number of allocated pages */
 	u32			jited:1,	/* Is our filter JIT'ed? */
 				len:31;		/* Number of filter blocks */
 	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
+	struct bpf_work_struct	*work;		/* Deferred free work struct */
 	unsigned int		(*bpf_func)(const struct sk_buff *skb,
 					    const struct bpf_insn *filter);
+	/* Instructions for interpreter */
 	union {
 		struct sock_filter	insns[0];
 		struct bpf_insn		insnsi[0];
-		struct work_struct	work;
 	};
 };
 
@@ -353,6 +361,26 @@ static inline unsigned int bpf_prog_size(unsigned int proglen)
 
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
 
+#ifdef CONFIG_DEBUG_SET_MODULE_RONX
+static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
+{
+	set_memory_ro((unsigned long)fp, fp->pages);
+}
+
+static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
+{
+	set_memory_rw((unsigned long)fp, fp->pages);
+}
+#else
+static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
+{
+}
+
+static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
+{
+}
+#endif /* CONFIG_DEBUG_SET_MODULE_RONX */
+
 int sk_filter(struct sock *sk, struct sk_buff *skb);
 
 void bpf_prog_select_runtime(struct bpf_prog *fp);
@@ -361,6 +389,17 @@ void bpf_prog_free(struct bpf_prog *fp);
 int bpf_convert_filter(struct sock_filter *prog, int len,
 		       struct bpf_insn *new_prog, int *new_len);
 
+struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
+struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
+				  gfp_t gfp_extra_flags);
+void __bpf_prog_free(struct bpf_prog *fp);
+
+static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
+{
+	bpf_prog_unlock_ro(fp);
+	__bpf_prog_free(fp);
+}
+
 int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
 void bpf_prog_destroy(struct bpf_prog *fp);
 
@@ -450,7 +489,7 @@ static inline void bpf_jit_compile(struct bpf_prog *fp)
 
 static inline void bpf_jit_free(struct bpf_prog *fp)
 {
-	kfree(fp);
+	bpf_prog_unlock_free(fp);
 }
 #endif /* CONFIG_BPF_JIT */
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7f0dbcbb34af..b54bb2c2e494 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -22,6 +22,7 @@
  */
 #include <linux/filter.h>
 #include <linux/skbuff.h>
+#include <linux/vmalloc.h>
 #include <asm/unaligned.h>
 
 /* Registers */
@@ -63,6 +64,67 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
 	return NULL;
 }
 
+struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
+{
+	gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
+			  gfp_extra_flags;
+	struct bpf_work_struct *ws;
+	struct bpf_prog *fp;
+
+	size = round_up(size, PAGE_SIZE);
+	fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+	if (fp == NULL)
+		return NULL;
+
+	ws = kmalloc(sizeof(*ws), GFP_KERNEL | gfp_extra_flags);
+	if (ws == NULL) {
+		vfree(fp);
+		return NULL;
+	}
+
+	fp->pages = size / PAGE_SIZE;
+	fp->work = ws;
+
+	return fp;
+}
+EXPORT_SYMBOL_GPL(bpf_prog_alloc);
+
+struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
+				  gfp_t gfp_extra_flags)
+{
+	gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
+			  gfp_extra_flags;
+	struct bpf_prog *fp;
+
+	BUG_ON(fp_old == NULL);
+
+	size = round_up(size, PAGE_SIZE);
+	if (size <= fp_old->pages * PAGE_SIZE)
+		return fp_old;
+
+	fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+	if (fp != NULL) {
+		memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
+		fp->pages = size / PAGE_SIZE;
+
+		/* We keep fp->work from fp_old around in the new
+		 * reallocated structure.
+		 */
+		fp_old->work = NULL;
+		__bpf_prog_free(fp_old);
+	}
+
+	return fp;
+}
+EXPORT_SYMBOL_GPL(bpf_prog_realloc);
+
+void __bpf_prog_free(struct bpf_prog *fp)
+{
+	kfree(fp->work);
+	vfree(fp);
+}
+EXPORT_SYMBOL_GPL(__bpf_prog_free);
+
 /* Base function for offset calculation. Needs to go into .text section,
  * therefore keeping it non-static as well; will also be used by JITs
  * anyway later on, so do not let the compiler omit it.
@@ -523,12 +585,26 @@ void bpf_prog_select_runtime(struct bpf_prog *fp)
 
 	/* Probe if internal BPF can be JITed */
 	bpf_int_jit_compile(fp);
+	/* Lock whole bpf_prog as read-only */
+	bpf_prog_lock_ro(fp);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
 
-/* free internal BPF program */
+static void bpf_prog_free_deferred(struct work_struct *work)
+{
+	struct bpf_work_struct *ws;
+
+	ws = container_of(work, struct bpf_work_struct, work);
+	bpf_jit_free(ws->prog);
+}
+
+/* Free internal BPF program */
 void bpf_prog_free(struct bpf_prog *fp)
 {
-	bpf_jit_free(fp);
+	struct bpf_work_struct *ws = fp->work;
+
+	INIT_WORK(&ws->work, bpf_prog_free_deferred);
+	ws->prog = fp;
+	schedule_work(&ws->work);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_free);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 44eb005c6695..84922befea84 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -395,16 +395,15 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 	if (!filter)
 		goto free_prog;
 
-	filter->prog = kzalloc(bpf_prog_size(new_len),
-			       GFP_KERNEL|__GFP_NOWARN);
+	filter->prog = bpf_prog_alloc(bpf_prog_size(new_len), __GFP_NOWARN);
 	if (!filter->prog)
 		goto free_filter;
 
 	ret = bpf_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len);
 	if (ret)
 		goto free_filter_prog;
-	kfree(fp);
 
+	kfree(fp);
 	atomic_set(&filter->usage, 1);
 	filter->prog->len = new_len;
 
@@ -413,7 +412,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 	return filter;
 
 free_filter_prog:
-	kfree(filter->prog);
+	__bpf_prog_free(filter->prog);
 free_filter:
 	kfree(filter);
 free_prog:
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 8c66c6aace04..9a67456ba29a 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -1836,7 +1836,7 @@ static struct bpf_prog *generate_filter(int which, int *err)
 		break;
 
 	case INTERNAL:
-		fp = kzalloc(bpf_prog_size(flen), GFP_KERNEL);
+		fp = bpf_prog_alloc(bpf_prog_size(flen), 0);
 		if (fp == NULL) {
 			pr_cont("UNEXPECTED_FAIL no memory left\n");
 			*err = -ENOMEM;
diff --git a/net/core/filter.c b/net/core/filter.c
index d814b8a89d0f..37f8eb06fdee 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -933,7 +933,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
 
 	/* Expand fp for appending the new filter representation. */
 	old_fp = fp;
-	fp = krealloc(old_fp, bpf_prog_size(new_len), GFP_KERNEL);
+	fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0);
 	if (!fp) {
 		/* The old_fp is still around in case we couldn't
 		 * allocate new memory, so uncharge on that one.
@@ -1013,7 +1013,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
 	if (fprog->filter == NULL)
 		return -EINVAL;
 
-	fp = kmalloc(bpf_prog_size(fprog->len), GFP_KERNEL);
+	fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
 	if (!fp)
 		return -ENOMEM;
 
@@ -1069,7 +1069,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (fprog->filter == NULL)
 		return -EINVAL;
 
-	prog = kmalloc(bpf_fsize, GFP_KERNEL);
+	prog = bpf_prog_alloc(bpf_fsize, 0);
 	if (!prog)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From f0db9b073415848709dd59a6394969882f517da9 Mon Sep 17 00:00:00 2001
From: Govindarajulu Varadarajan <_govind@gmx.com>
Date: Wed, 3 Sep 2014 03:17:20 +0530
Subject: ethtool: Add generic options for tunables

This patch adds new ethtool cmd, ETHTOOL_GTUNABLE & ETHTOOL_STUNABLE for getting
tunable values from driver.

Add get_tunable and set_tunable to ethtool_ops. Driver implements these
functions for getting/setting tunable value.

Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h      |  4 +++
 include/uapi/linux/ethtool.h | 28 +++++++++++++++
 net/core/ethtool.c           | 81 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 113 insertions(+)

(limited to 'include')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index e658229fee39..c1a2d60dfb82 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -257,6 +257,10 @@ struct ethtool_ops {
 				     struct ethtool_eeprom *, u8 *);
 	int	(*get_eee)(struct net_device *, struct ethtool_eee *);
 	int	(*set_eee)(struct net_device *, struct ethtool_eee *);
+	int	(*get_tunable)(struct net_device *,
+			       const struct ethtool_tunable *, void *);
+	int	(*set_tunable)(struct net_device *,
+			       const struct ethtool_tunable *, const void *);
 
 
 };
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index e3c7a719c76b..7a364f2f3d3f 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -209,6 +209,32 @@ struct ethtool_value {
 	__u32	data;
 };
 
+enum tunable_id {
+	ETHTOOL_ID_UNSPEC,
+	ETHTOOL_RX_COPYBREAK,
+};
+
+enum tunable_type_id {
+	ETHTOOL_TUNABLE_UNSPEC,
+	ETHTOOL_TUNABLE_U8,
+	ETHTOOL_TUNABLE_U16,
+	ETHTOOL_TUNABLE_U32,
+	ETHTOOL_TUNABLE_U64,
+	ETHTOOL_TUNABLE_STRING,
+	ETHTOOL_TUNABLE_S8,
+	ETHTOOL_TUNABLE_S16,
+	ETHTOOL_TUNABLE_S32,
+	ETHTOOL_TUNABLE_S64,
+};
+
+struct ethtool_tunable {
+	__u32	cmd;
+	__u32	id;
+	__u32	type_id;
+	__u32	len;
+	void	*data[0];
+};
+
 /**
  * struct ethtool_regs - hardware register dump
  * @cmd: Command number = %ETHTOOL_GREGS
@@ -1152,6 +1178,8 @@ enum ethtool_sfeatures_retval_bits {
 
 #define ETHTOOL_GRSSH		0x00000046 /* Get RX flow hash configuration */
 #define ETHTOOL_SRSSH		0x00000047 /* Set RX flow hash configuration */
+#define ETHTOOL_GTUNABLE	0x00000048 /* Get tunable configuration */
+#define ETHTOOL_STUNABLE	0x00000049 /* Set tunable configuration */
 
 /* compatibility with older code */
 #define SPARC_ETH_GSET		ETHTOOL_GSET
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 17cb912793fa..27e61b886520 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1621,6 +1621,80 @@ static int ethtool_get_module_eeprom(struct net_device *dev,
 				      modinfo.eeprom_len);
 }
 
+static int ethtool_tunable_valid(const struct ethtool_tunable *tuna)
+{
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		if (tuna->len != sizeof(u32) ||
+		    tuna->type_id != ETHTOOL_TUNABLE_U32)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr)
+{
+	int ret;
+	struct ethtool_tunable tuna;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	void *data;
+
+	if (!ops->get_tunable)
+		return -EOPNOTSUPP;
+	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
+		return -EFAULT;
+	ret = ethtool_tunable_valid(&tuna);
+	if (ret)
+		return ret;
+	data = kmalloc(tuna.len, GFP_USER);
+	if (!data)
+		return -ENOMEM;
+	ret = ops->get_tunable(dev, &tuna, data);
+	if (ret)
+		goto out;
+	useraddr += sizeof(tuna);
+	ret = -EFAULT;
+	if (copy_to_user(useraddr, data, tuna.len))
+		goto out;
+	ret = 0;
+
+out:
+	kfree(data);
+	return ret;
+}
+
+static int ethtool_set_tunable(struct net_device *dev, void __user *useraddr)
+{
+	int ret;
+	struct ethtool_tunable tuna;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	void *data;
+
+	if (!ops->set_tunable)
+		return -EOPNOTSUPP;
+	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
+		return -EFAULT;
+	ret = ethtool_tunable_valid(&tuna);
+	if (ret)
+		return ret;
+	data = kmalloc(tuna.len, GFP_USER);
+	if (!data)
+		return -ENOMEM;
+	useraddr += sizeof(tuna);
+	ret = -EFAULT;
+	if (copy_from_user(data, useraddr, tuna.len))
+		goto out;
+	ret = ops->set_tunable(dev, &tuna, data);
+
+out:
+	kfree(data);
+	return ret;
+}
+
 /* The main entry point in this file.  Called from net/core/dev_ioctl.c */
 
 int dev_ethtool(struct net *net, struct ifreq *ifr)
@@ -1670,6 +1744,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GCHANNELS:
 	case ETHTOOL_GET_TS_INFO:
 	case ETHTOOL_GEEE:
+	case ETHTOOL_GTUNABLE:
 		break;
 	default:
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -1857,6 +1932,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GMODULEEEPROM:
 		rc = ethtool_get_module_eeprom(dev, useraddr);
 		break;
+	case ETHTOOL_GTUNABLE:
+		rc = ethtool_get_tunable(dev, useraddr);
+		break;
+	case ETHTOOL_STUNABLE:
+		rc = ethtool_set_tunable(dev, useraddr);
+		break;
 	default:
 		rc = -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From c199105d154e029cd8c94cccd35bd073e64acc45 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 3 Sep 2014 12:01:18 -0400
Subject: net-timestamp: only report sw timestamp if reporting bit is set

The timestamping API has separate bits for generating and reporting
timestamps. A software timestamp should only be reported for a packet
when the packet has the relevant generation flag (SKBTX_..) set
and the socket has reporting bit SOF_TIMESTAMPING_SOFTWARE set.

The second check was accidentally removed. Reinstitute the original
behavior.

Tested:
  Without this patch, Documentation/networking/txtimestamp reports
  timestamps regardless of whether SOF_TIMESTAMPING_SOFTWARE is set.
  After the patch, it only reports them when the flag is set.

Fixes: f24b9be5957b ("net-timestamp: extend SCM_TIMESTAMPING ancillary data struct")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 4 +---
 net/socket.c       | 3 +--
 2 files changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 7f2ab72f321a..b9a5bd0ed9f3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2165,9 +2165,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 	 */
 	if (sock_flag(sk, SOCK_RCVTSTAMP) ||
 	    (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
-	    (kt.tv64 &&
-	     (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE ||
-	      skb_shinfo(skb)->tx_flags & SKBTX_ANY_SW_TSTAMP)) ||
+	    (kt.tv64 && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
 	    (hwtstamps->hwtstamp.tv64 &&
 	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
 		__sock_recv_timestamp(msg, sk, skb);
diff --git a/net/socket.c b/net/socket.c
index 95ee7d8682e7..4eb09b34b2d3 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -734,8 +734,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 	}
 
 	memset(&tss, 0, sizeof(tss));
-	if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE ||
-	     skb_shinfo(skb)->tx_flags & SKBTX_ANY_SW_TSTAMP) &&
+	if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) &&
 	    ktime_to_timespec_cond(skb->tstamp, tss.ts + 0))
 		empty = 0;
 	if (shhwtstamps &&
-- 
cgit v1.2.3


From caa415270c732505240bb60171c44a7838c555e8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 3 Sep 2014 22:21:56 -0700
Subject: ipv4: fix a race in update_or_create_fnhe()

nh_exceptions is effectively used under rcu, but lacks proper
barriers. Between kzalloc() and setting of nh->nh_exceptions(),
we need a proper memory barrier.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 4895c771c7f00 ("ipv4: Add FIB nexthop exceptions.")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     | 2 +-
 net/ipv4/fib_semantics.c | 8 +++++---
 net/ipv4/route.c         | 6 +++---
 3 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 9922093f575e..f30fd554127e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -87,7 +87,7 @@ struct fib_nh {
 	int			nh_saddr_genid;
 	struct rtable __rcu * __percpu *nh_pcpu_rth_output;
 	struct rtable __rcu	*nh_rth_input;
-	struct fnhe_hash_bucket	*nh_exceptions;
+	struct fnhe_hash_bucket	__rcu *nh_exceptions;
 };
 
 /*
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b10cd43a4722..5b6efb3d2308 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -157,9 +157,12 @@ static void rt_fibinfo_free(struct rtable __rcu **rtp)
 
 static void free_nh_exceptions(struct fib_nh *nh)
 {
-	struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+	struct fnhe_hash_bucket *hash;
 	int i;
 
+	hash = rcu_dereference_protected(nh->nh_exceptions, 1);
+	if (!hash)
+		return;
 	for (i = 0; i < FNHE_HASH_SIZE; i++) {
 		struct fib_nh_exception *fnhe;
 
@@ -205,8 +208,7 @@ static void free_fib_info_rcu(struct rcu_head *head)
 	change_nexthops(fi) {
 		if (nexthop_nh->nh_dev)
 			dev_put(nexthop_nh->nh_dev);
-		if (nexthop_nh->nh_exceptions)
-			free_nh_exceptions(nexthop_nh);
+		free_nh_exceptions(nexthop_nh);
 		rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
 		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
 	} endfor_nexthops(fi);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index eaa4b000c7b4..44b0cbdd76f1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -628,12 +628,12 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 
 	spin_lock_bh(&fnhe_lock);
 
-	hash = nh->nh_exceptions;
+	hash = rcu_dereference(nh->nh_exceptions);
 	if (!hash) {
 		hash = kzalloc(FNHE_HASH_SIZE * sizeof(*hash), GFP_ATOMIC);
 		if (!hash)
 			goto out_unlock;
-		nh->nh_exceptions = hash;
+		rcu_assign_pointer(nh->nh_exceptions, hash);
 	}
 
 	hash += hval;
@@ -1242,7 +1242,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 
 static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 {
-	struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+	struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
 	struct fib_nh_exception *fnhe;
 	u32 hval;
 
-- 
cgit v1.2.3


From e793c0f70e9bdf4a2e71c151a1a3cf85c4db92ad Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Thu, 4 Sep 2014 23:44:36 +0900
Subject: net: treewide: Fix typo found in DocBook/networking.xml

This patch fix spelling typo found in DocBook/networking.xml.
It is because the neworking.xml is generated from comments
in the source, I have to fix typo in comments within the source.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h  | 4 ++--
 include/net/wimax.h        | 2 +-
 include/trace/events/irq.h | 4 ++--
 net/core/datagram.c        | 2 +-
 net/core/gen_estimator.c   | 2 +-
 net/core/gen_stats.c       | 2 +-
 net/core/skbuff.c          | 4 ++--
 net/core/sock.c            | 4 ++--
 net/socket.c               | 2 +-
 9 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 38377392d082..c8e388e5fccc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3176,7 +3176,7 @@ static inline int __dev_uc_sync(struct net_device *dev,
 }
 
 /**
- *  __dev_uc_unsync - Remove synchonized addresses from device
+ *  __dev_uc_unsync - Remove synchronized addresses from device
  *  @dev:  device to sync
  *  @unsync: function to call if address should be removed
  *
@@ -3220,7 +3220,7 @@ static inline int __dev_mc_sync(struct net_device *dev,
 }
 
 /**
- *  __dev_mc_unsync - Remove synchonized addresses from device
+ *  __dev_mc_unsync - Remove synchronized addresses from device
  *  @dev:  device to sync
  *  @unsync: function to call if address should be removed
  *
diff --git a/include/net/wimax.h b/include/net/wimax.h
index e52ef5357e08..c52b68577cb0 100644
--- a/include/net/wimax.h
+++ b/include/net/wimax.h
@@ -290,7 +290,7 @@ struct wimax_dev;
  *     This operation has to be synchronous, and return only when the
  *     reset is complete. In case of having had to resort to bus/cold
  *     reset implying a device disconnection, the call is allowed to
- *     return inmediately.
+ *     return immediately.
  *     NOTE: wimax_dev->mutex is NOT locked when this op is being
  *     called; however, wimax_dev->mutex_reset IS locked to ensure
  *     serialization of calls to wimax_reset().
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
index 1c09820df585..3608bebd3d9c 100644
--- a/include/trace/events/irq.h
+++ b/include/trace/events/irq.h
@@ -107,7 +107,7 @@ DECLARE_EVENT_CLASS(softirq,
  * @vec_nr:  softirq vector number
  *
  * When used in combination with the softirq_exit tracepoint
- * we can determine the softirq handler runtine.
+ * we can determine the softirq handler routine.
  */
 DEFINE_EVENT(softirq, softirq_entry,
 
@@ -121,7 +121,7 @@ DEFINE_EVENT(softirq, softirq_entry,
  * @vec_nr:  softirq vector number
  *
  * When used in combination with the softirq_entry tracepoint
- * we can determine the softirq handler runtine.
+ * we can determine the softirq handler routine.
  */
 DEFINE_EVENT(softirq, softirq_exit,
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 488dd1a825c0..fdbc9a81d4c2 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -775,7 +775,7 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 EXPORT_SYMBOL(__skb_checksum_complete);
 
 /**
- *	skb_copy_and_csum_datagram_iovec - Copy and checkum skb to user iovec.
+ *	skb_copy_and_csum_datagram_iovec - Copy and checksum skb to user iovec.
  *	@skb: skbuff
  *	@hlen: hardware length
  *	@iov: io vector
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 6b5b6e7013ca..9d33dfffca19 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -197,7 +197,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats
  * as destination. A new timer with the interval specified in the
  * configuration TLV is created. Upon each interval, the latest statistics
  * will be read from &bstats and the estimated rate will be stored in
- * &rate_est with the statistics lock grabed during this period.
+ * &rate_est with the statistics lock grabbed during this period.
  *
  * Returns 0 on success or a negative error code.
  *
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 9d3d9e78397b..2ddbce4cce14 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -206,7 +206,7 @@ EXPORT_SYMBOL(gnet_stats_copy_queue);
  * @st: application specific statistics data
  * @len: length of data
  *
- * Appends the application sepecific statistics to the top level TLV created by
+ * Appends the application specific statistics to the top level TLV created by
  * gnet_stats_start_copy() and remembers the data for XSTATS if the dumping
  * handle is in backward compatibility mode.
  *
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 163b673f9e62..da1378a3e2c7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2647,7 +2647,7 @@ EXPORT_SYMBOL(skb_prepare_seq_read);
  * skb_seq_read() will return the remaining part of the block.
  *
  * Note 1: The size of each block of data returned can be arbitrary,
- *       this limitation is the cost for zerocopy seqeuental
+ *       this limitation is the cost for zerocopy sequential
  *       reads of potentially non linear data.
  *
  * Note 2: Fragment lists within fragments are not implemented
@@ -2781,7 +2781,7 @@ EXPORT_SYMBOL(skb_find_text);
 /**
  * skb_append_datato_frags - append the user data to a skb
  * @sk: sock  structure
- * @skb: skb structure to be appened with user data.
+ * @skb: skb structure to be appended with user data.
  * @getfrag: call back function to be used for getting the user data
  * @from: pointer to user message iov
  * @length: length of the iov message
diff --git a/net/core/sock.c b/net/core/sock.c
index 29870571c42f..d372b4bd3f99 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -166,7 +166,7 @@ EXPORT_SYMBOL(sk_ns_capable);
 /**
  * sk_capable - Socket global capability test
  * @sk: Socket to use a capability on or through
- * @cap: The global capbility to use
+ * @cap: The global capability to use
  *
  * Test to see if the opener of the socket had when the socket was
  * created and the current process has the capability @cap in all user
@@ -183,7 +183,7 @@ EXPORT_SYMBOL(sk_capable);
  * @sk: Socket to use a capability on or through
  * @cap: The capability to use
  *
- * Test to see if the opener of the socket had when the socke was created
+ * Test to see if the opener of the socket had when the socket was created
  * and the current process has the capability @cap over the network namespace
  * the socket is a member of.
  */
diff --git a/net/socket.c b/net/socket.c
index 4eb09b34b2d3..2e2586e2dee1 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2601,7 +2601,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
  *
  *	This function is called by a protocol handler that wants to
  *	advertise its address family, and have it linked into the
- *	socket interface. The value ops->family coresponds to the
+ *	socket interface. The value ops->family corresponds to the
  *	socket system call protocol family.
  */
 int sock_register(const struct net_proto_family *ops)
-- 
cgit v1.2.3


From d546c621542df9e45eedc91f35356e887ac63b7b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 4 Sep 2014 08:21:31 -0700
Subject: ipv4: harden fnhe_hashfun()

Lets make this hash function a bit secure, as ICMP attacks are still
in the wild.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h | 3 ++-
 net/ipv4/route.c     | 8 ++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index f30fd554127e..dc9d2a27c315 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -65,7 +65,8 @@ struct fnhe_hash_bucket {
 	struct fib_nh_exception __rcu	*chain;
 };
 
-#define FNHE_HASH_SIZE		2048
+#define FNHE_HASH_SHIFT		11
+#define FNHE_HASH_SIZE		(1 << FNHE_HASH_SHIFT)
 #define FNHE_RECLAIM_DEPTH	5
 
 struct fib_nh {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 44b0cbdd76f1..234a43e233dc 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -596,12 +596,12 @@ static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
 
 static inline u32 fnhe_hashfun(__be32 daddr)
 {
+	static u32 fnhe_hashrnd __read_mostly;
 	u32 hval;
 
-	hval = (__force u32) daddr;
-	hval ^= (hval >> 11) ^ (hval >> 22);
-
-	return hval & (FNHE_HASH_SIZE - 1);
+	net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd));
+	hval = jhash_1word((__force u32) daddr, fnhe_hashrnd);
+	return hash_32(hval, FNHE_HASH_SHIFT);
 }
 
 static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe)
-- 
cgit v1.2.3


From 62bccb8cdb69051b95a55ab0c489e3cab261c8ef Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 4 Sep 2014 13:31:35 -0400
Subject: net-timestamp: Make the clone operation stand-alone from phy
 timestamping

The phy timestamping takes a different path than the regular timestamping
does in that it will create a clone first so that the packets needing to be
timestamped can be placed in a queue, or the context block could be used.

In order to support these use cases I am pulling the core of the code out
so it can be used in other drivers beyond just phy devices.

In addition I have added a destructor named sock_efree which is meant to
provide a simple way for dropping the reference to skb exceptions that
aren't part of either the receive or send windows for the socket, and I
have removed some duplication in spots where this destructor could be used
in place of sock_edemux.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c |  6 +++---
 include/linux/skbuff.h    |  2 ++
 include/net/sock.h        |  1 +
 net/core/skbuff.c         | 32 +++++++++++++++++++++++++-------
 net/core/sock.c           |  6 ++++++
 net/core/timestamping.c   | 14 +++-----------
 6 files changed, 40 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index d5991ac46ab0..87648b306551 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1148,7 +1148,7 @@ static void dp83640_remove(struct phy_device *phydev)
 		kfree_skb(skb);
 
 	while ((skb = skb_dequeue(&dp83640->tx_queue)) != NULL)
-		skb_complete_tx_timestamp(skb, NULL);
+		kfree_skb(skb);
 
 	clock = dp83640_clock_get(dp83640->clock);
 
@@ -1405,7 +1405,7 @@ static void dp83640_txtstamp(struct phy_device *phydev,
 
 	case HWTSTAMP_TX_ONESTEP_SYNC:
 		if (is_sync(skb, type)) {
-			skb_complete_tx_timestamp(skb, NULL);
+			kfree_skb(skb);
 			return;
 		}
 		/* fall through */
@@ -1416,7 +1416,7 @@ static void dp83640_txtstamp(struct phy_device *phydev,
 
 	case HWTSTAMP_TX_OFF:
 	default:
-		skb_complete_tx_timestamp(skb, NULL);
+		kfree_skb(skb);
 		break;
 	}
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 02529fcad1ac..1cf0cfaef10a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2690,6 +2690,8 @@ static inline ktime_t net_invalid_timestamp(void)
 	return ktime_set(0, 0);
 }
 
+struct sk_buff *skb_clone_sk(struct sk_buff *skb);
+
 #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
 
 void skb_clone_tx_timestamp(struct sk_buff *skb);
diff --git a/include/net/sock.h b/include/net/sock.h
index 3fde6130789d..e02be37a3d91 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1574,6 +1574,7 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
 void sock_wfree(struct sk_buff *skb);
 void skb_orphan_partial(struct sk_buff *skb);
 void sock_rfree(struct sk_buff *skb);
+void sock_efree(struct sk_buff *skb);
 void sock_edemux(struct sk_buff *skb);
 
 int sock_setsockopt(struct socket *sock, int level, int op,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 697e696c914b..a936a401564e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3511,6 +3511,27 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
 }
 EXPORT_SYMBOL(sock_dequeue_err_skb);
 
+struct sk_buff *skb_clone_sk(struct sk_buff *skb)
+{
+	struct sock *sk = skb->sk;
+	struct sk_buff *clone;
+
+	if (!sk || !atomic_inc_not_zero(&sk->sk_refcnt))
+		return NULL;
+
+	clone = skb_clone(skb, GFP_ATOMIC);
+	if (!clone) {
+		sock_put(sk);
+		return NULL;
+	}
+
+	clone->sk = sk;
+	clone->destructor = sock_efree;
+
+	return clone;
+}
+EXPORT_SYMBOL(skb_clone_sk);
+
 static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 					struct sock *sk,
 					int tstype)
@@ -3540,14 +3561,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 {
 	struct sock *sk = skb->sk;
 
-	skb->sk = NULL;
+	/* take a reference to prevent skb_orphan() from freeing the socket */
+	sock_hold(sk);
 
-	if (hwtstamps) {
-		*skb_hwtstamps(skb) = *hwtstamps;
-		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
-	} else {
-		kfree_skb(skb);
-	}
+	*skb_hwtstamps(skb) = *hwtstamps;
+	__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
 
 	sock_put(sk);
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index f1a638ee93d9..d04005c51724 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1637,6 +1637,12 @@ void sock_rfree(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sock_rfree);
 
+void sock_efree(struct sk_buff *skb)
+{
+	sock_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_efree);
+
 void sock_edemux(struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index f48a59fd8f39..43d3dd62fcc8 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -36,10 +36,9 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
 {
 	struct phy_device *phydev;
 	struct sk_buff *clone;
-	struct sock *sk = skb->sk;
 	unsigned int type;
 
-	if (!sk)
+	if (!skb->sk)
 		return;
 
 	type = classify(skb);
@@ -48,16 +47,9 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
 
 	phydev = skb->dev->phydev;
 	if (likely(phydev->drv->txtstamp)) {
-		if (!atomic_inc_not_zero(&sk->sk_refcnt))
+		clone = skb_clone_sk(skb);
+		if (!clone)
 			return;
-
-		clone = skb_clone(skb, GFP_ATOMIC);
-		if (!clone) {
-			sock_put(sk);
-			return;
-		}
-
-		clone->sk = sk;
 		phydev->drv->txtstamp(phydev, clone, type);
 	}
 }
-- 
cgit v1.2.3


From 82eabd9eb2ec1603282a2c3f74dfcb6fe0aaea0e Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 4 Sep 2014 13:32:11 -0400
Subject: net: merge cases where sock_efree and sock_edemux are the same
 function

Since sock_efree and sock_demux are essentially the same code for non-TCP
sockets and the case where CONFIG_INET is not defined we can combine the
code or replace the call to sock_edemux in several spots.  As a result we
can avoid a bit of unnecessary code or code duplication.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 4 ++++
 net/core/sock.c    | 4 ++--
 net/ipv4/udp.c     | 2 +-
 3 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index e02be37a3d91..ad23e80cb8d3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1575,7 +1575,11 @@ void sock_wfree(struct sk_buff *skb);
 void skb_orphan_partial(struct sk_buff *skb);
 void sock_rfree(struct sk_buff *skb);
 void sock_efree(struct sk_buff *skb);
+#ifdef CONFIG_INET
 void sock_edemux(struct sk_buff *skb);
+#else
+#define sock_edemux(skb) sock_efree(skb)
+#endif
 
 int sock_setsockopt(struct socket *sock, int level, int op,
 		    char __user *optval, unsigned int optlen);
diff --git a/net/core/sock.c b/net/core/sock.c
index d04005c51724..69592cb66e3b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1643,18 +1643,18 @@ void sock_efree(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sock_efree);
 
+#ifdef CONFIG_INET
 void sock_edemux(struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 
-#ifdef CONFIG_INET
 	if (sk->sk_state == TCP_TIME_WAIT)
 		inet_twsk_put(inet_twsk(sk));
 	else
-#endif
 		sock_put(sk);
 }
 EXPORT_SYMBOL(sock_edemux);
+#endif
 
 kuid_t sock_i_uid(struct sock *sk)
 {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0da3849fd35b..cd0db5471bb5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1972,7 +1972,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		return;
 
 	skb->sk = sk;
-	skb->destructor = sock_edemux;
+	skb->destructor = sock_efree;
 	dst = sk->sk_rx_dst;
 
 	if (dst)
-- 
cgit v1.2.3


From 56193d1bce2b2759cb4bdcc00cd05544894a0c90 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Fri, 5 Sep 2014 19:20:26 -0400
Subject: net: Add function for parsing the header length out of linear
 ethernet frames

This patch updates some of the flow_dissector api so that it can be used to
parse the length of ethernet buffers stored in fragments.  Most of the
changes needed were to __skb_get_poff as it needed to be updated to support
sending a linear buffer instead of a skb.

I have split __skb_get_poff into two functions, the first is skb_get_poff
and it retains the functionality of the original __skb_get_poff.  The other
function is __skb_get_poff which now works much like __skb_flow_dissect in
relation to skb_flow_dissect in that it provides the same functionality but
works with just a data buffer and hlen instead of needing an skb.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/etherdevice.h |  1 +
 include/linux/skbuff.h      |  4 +++-
 include/net/flow_keys.h     |  2 ++
 net/core/filter.c           |  2 +-
 net/core/flow_dissector.c   | 46 +++++++++++++++++++++++++++++++--------------
 net/ethernet/eth.c          | 27 ++++++++++++++++++++++++++
 6 files changed, 66 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 9c5529dc6d07..733980fce8e3 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -29,6 +29,7 @@
 #include <asm/bitsperlong.h>
 
 #ifdef __KERNEL__
+u32 eth_get_headlen(void *data, unsigned int max_len);
 __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
 extern const struct header_ops eth_header_ops;
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1cf0cfaef10a..07c9fdd0c126 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3218,7 +3218,9 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
 
 int skb_checksum_setup(struct sk_buff *skb, bool recalculate);
 
-u32 __skb_get_poff(const struct sk_buff *skb);
+u32 skb_get_poff(const struct sk_buff *skb);
+u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+		   const struct flow_keys *keys, int hlen);
 
 /**
  * skb_head_is_locked - Determine if the skb->head is locked down
diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index 9a03f73c4974..7ee2df083542 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -40,4 +40,6 @@ static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8
 	return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
 }
 u32 flow_hash_from_keys(struct flow_keys *keys);
+unsigned int flow_get_hlen(const unsigned char *data, unsigned int max_len,
+			   __be16 protocol);
 #endif
diff --git a/net/core/filter.c b/net/core/filter.c
index 37f8eb06fdee..fa5b7d0f77ac 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -113,7 +113,7 @@ static unsigned int pkt_type_offset(void)
 
 static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {
-	return __skb_get_poff((struct sk_buff *)(unsigned long) ctx);
+	return skb_get_poff((struct sk_buff *)(unsigned long) ctx);
 }
 
 static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 12f48ca7a0b0..8560dea58803 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -13,6 +13,7 @@
 #include <linux/if_pppox.h>
 #include <linux/ppp_defs.h>
 #include <net/flow_keys.h>
+#include <scsi/fc/fc_fcoe.h>
 
 /* copy saddr & daddr, possibly using 64bit load/store
  * Equivalent to :	flow->src = iph->saddr;
@@ -117,6 +118,13 @@ ipv6:
 		flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
 		nhoff += sizeof(struct ipv6hdr);
 
+		/* skip the flow label processing if skb is NULL.  The
+		 * assumption here is that if there is no skb we are not
+		 * looking for flow info as much as we are length.
+		 */
+		if (!skb)
+			break;
+
 		flow_label = ip6_flowlabel(iph);
 		if (flow_label) {
 			/* Awesome, IPv6 packet has a flow label so we can
@@ -165,6 +173,9 @@ ipv6:
 			return false;
 		}
 	}
+	case htons(ETH_P_FCOE):
+		flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
+		/* fall through */
 	default:
 		return false;
 	}
@@ -316,26 +327,18 @@ u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(__skb_tx_hash);
 
-/* __skb_get_poff() returns the offset to the payload as far as it could
- * be dissected. The main user is currently BPF, so that we can dynamically
- * truncate packets without needing to push actual payload to the user
- * space and can analyze headers only, instead.
- */
-u32 __skb_get_poff(const struct sk_buff *skb)
+u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+		   const struct flow_keys *keys, int hlen)
 {
-	struct flow_keys keys;
-	u32 poff = 0;
+	u32 poff = keys->thoff;
 
-	if (!skb_flow_dissect(skb, &keys))
-		return 0;
-
-	poff += keys.thoff;
-	switch (keys.ip_proto) {
+	switch (keys->ip_proto) {
 	case IPPROTO_TCP: {
 		const struct tcphdr *tcph;
 		struct tcphdr _tcph;
 
-		tcph = skb_header_pointer(skb, poff, sizeof(_tcph), &_tcph);
+		tcph = __skb_header_pointer(skb, poff, sizeof(_tcph),
+					    data, hlen, &_tcph);
 		if (!tcph)
 			return poff;
 
@@ -369,6 +372,21 @@ u32 __skb_get_poff(const struct sk_buff *skb)
 	return poff;
 }
 
+/* skb_get_poff() returns the offset to the payload as far as it could
+ * be dissected. The main user is currently BPF, so that we can dynamically
+ * truncate packets without needing to push actual payload to the user
+ * space and can analyze headers only, instead.
+ */
+u32 skb_get_poff(const struct sk_buff *skb)
+{
+	struct flow_keys keys;
+
+	if (!skb_flow_dissect(skb, &keys))
+		return 0;
+
+	return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
+}
+
 static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_XPS
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 5cebca134585..33a140e15834 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -145,6 +145,33 @@ int eth_rebuild_header(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(eth_rebuild_header);
 
+/**
+ * eth_get_headlen - determine the the length of header for an ethernet frame
+ * @data: pointer to start of frame
+ * @len: total length of frame
+ *
+ * Make a best effort attempt to pull the length for all of the headers for
+ * a given frame in a linear buffer.
+ */
+u32 eth_get_headlen(void *data, unsigned int len)
+{
+	const struct ethhdr *eth = (const struct ethhdr *)data;
+	struct flow_keys keys;
+
+	/* this should never happen, but better safe than sorry */
+	if (len < sizeof(*eth))
+		return len;
+
+	/* parse any remaining L2/L3 headers, check for L4 */
+	if (!__skb_flow_dissect(NULL, &keys, data,
+				eth->h_proto, sizeof(*eth), len))
+		return max_t(u32, keys.thoff, sizeof(*eth));
+
+	/* parse for any L4 headers */
+	return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);
+}
+EXPORT_SYMBOL(eth_get_headlen);
+
 /**
  * eth_type_trans - determine the packet's protocol ID.
  * @skb: received socket data
-- 
cgit v1.2.3


From 04317dafd11dd7b0ec19b85f098414abae6ed5f7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 5 Sep 2014 15:33:32 -0700
Subject: tcp: introduce TCP_SKB_CB(skb)->tcp_tw_isn

TCP_SKB_CB(skb)->when has different meaning in output and input paths.

In output path, it contains a timestamp.
In input path, it contains an ISN, chosen by tcp_timewait_state_process()

Lets add a different name to ease code comprehension.

Note that 'when' field will disappear in following patch,
as skb_mstamp already contains timestamp, the anonymous
union will promptly disappear as well.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        | 7 ++++++-
 net/ipv4/tcp_input.c     | 2 +-
 net/ipv4/tcp_ipv4.c      | 2 +-
 net/ipv4/tcp_minisocks.c | 2 +-
 net/ipv6/tcp_ipv6.c      | 4 ++--
 5 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 590e01a476ac..0cd7d2c65dc0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -698,7 +698,12 @@ struct tcp_skb_cb {
 	} header;	/* For incoming frames		*/
 	__u32		seq;		/* Starting sequence number	*/
 	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
-	__u32		when;		/* used to compute rtt's	*/
+	union {
+		/* used in output path */
+		__u32		when;	/* used to compute rtt's	*/
+		/* used in input path */
+		__u32		tcp_tw_isn; /* isn chosen by tcp_timewait_state_process() */
+	};
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
 	__u8		sacked;		/* State flags for SACK/FACK.	*/
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index aba4926ca095..9c8b9f1dcf69 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5906,7 +5906,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	struct request_sock *req;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct dst_entry *dst = NULL;
-	__u32 isn = TCP_SKB_CB(skb)->when;
+	__u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn;
 	bool want_cookie = false, fastopen;
 	struct flowi fl;
 	struct tcp_fastopen_cookie foc = { .len = -1 };
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 487e2a41667f..02e6cd29ebf1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1627,7 +1627,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff * 4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->when	 = 0;
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
 	TCP_SKB_CB(skb)->sacked	 = 0;
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 1649988bd1b6..a058f411d3a6 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -232,7 +232,7 @@ kill:
 		u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
 		if (isn == 0)
 			isn++;
-		TCP_SKB_CB(skb)->when = isn;
+		TCP_SKB_CB(skb)->tcp_tw_isn = isn;
 		return TCP_TW_SYN;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 29964c3d363c..5b3c70ff7a72 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -738,7 +738,7 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
 		ireq->ir_iif = inet6_iif(skb);
 
-	if (!TCP_SKB_CB(skb)->when &&
+	if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
 	    (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo ||
 	     np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
 	     np->rxopt.bits.rxohlim || np->repflow)) {
@@ -1412,7 +1412,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff*4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->when = 0;
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
 	TCP_SKB_CB(skb)->sacked = 0;
 
-- 
cgit v1.2.3


From 7faee5c0d514162853a343d93e4a0b6bb8bfec21 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 5 Sep 2014 15:33:33 -0700
Subject: tcp: remove TCP_SKB_CB(skb)->when

After commit 740b0f1841f6 ("tcp: switch rtt estimations to usec resolution"),
we no longer need to maintain timestamps in two different fields.

TCP_SKB_CB(skb)->when can be removed, as same information sits in skb_mstamp.stamp_jiffies

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 13 +++++++------
 net/ipv4/tcp_input.c  |  3 ++-
 net/ipv4/tcp_ipv4.c   |  5 +++--
 net/ipv4/tcp_output.c | 39 ++++++++++++++++-----------------------
 net/ipv4/tcp_timer.c  |  7 +++----
 5 files changed, 31 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0cd7d2c65dc0..a4201ef216e8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -672,6 +672,12 @@ void tcp_send_window_probe(struct sock *sk);
  */
 #define tcp_time_stamp		((__u32)(jiffies))
 
+static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
+{
+	return skb->skb_mstamp.stamp_jiffies;
+}
+
+
 #define tcp_flag_byte(th) (((u_int8_t *)th)[13])
 
 #define TCPHDR_FIN 0x01
@@ -698,12 +704,7 @@ struct tcp_skb_cb {
 	} header;	/* For incoming frames		*/
 	__u32		seq;		/* Starting sequence number	*/
 	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
-	union {
-		/* used in output path */
-		__u32		when;	/* used to compute rtt's	*/
-		/* used in input path */
-		__u32		tcp_tw_isn; /* isn chosen by tcp_timewait_state_process() */
-	};
+	__u32		tcp_tw_isn;	/* isn chosen by tcp_timewait_state_process() */
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
 	__u8		sacked;		/* State flags for SACK/FACK.	*/
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9c8b9f1dcf69..f97003ad0af5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2967,7 +2967,8 @@ void tcp_rearm_rto(struct sock *sk)
 		if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
 		    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 			struct sk_buff *skb = tcp_write_queue_head(sk);
-			const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto;
+			const u32 rto_time_stamp =
+				tcp_skb_timestamp(skb) + rto;
 			s32 delta = (s32)(rto_time_stamp - tcp_time_stamp);
 			/* delta may not be positive if the socket is locked
 			 * when the retrans timer fires and is rescheduled.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 02e6cd29ebf1..3f9bc3f0bba0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -437,8 +437,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		skb = tcp_write_queue_head(sk);
 		BUG_ON(!skb);
 
-		remaining = icsk->icsk_rto - min(icsk->icsk_rto,
-				tcp_time_stamp - TCP_SKB_CB(skb)->when);
+		remaining = icsk->icsk_rto -
+			    min(icsk->icsk_rto,
+				tcp_time_stamp - tcp_skb_timestamp(skb));
 
 		if (remaining) {
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5a7c41fbc6d3..3b22dcb7bb5c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -550,7 +550,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 
 	if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = TCP_SKB_CB(skb)->when + tp->tsoffset;
+		opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -618,7 +618,7 @@ static unsigned int tcp_synack_options(struct sock *sk,
 	}
 	if (likely(ireq->tstamp_ok)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = TCP_SKB_CB(skb)->when;
+		opts->tsval = tcp_skb_timestamp(skb);
 		opts->tsecr = req->ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -647,7 +647,6 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 					struct tcp_out_options *opts,
 					struct tcp_md5sig_key **md5)
 {
-	struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL;
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int size = 0;
 	unsigned int eff_sacks;
@@ -666,7 +665,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 
 	if (likely(tp->rx_opt.tstamp_ok)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = tcb ? tcb->when + tp->tsoffset : 0;
+		opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		size += TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -886,8 +885,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 			skb = skb_clone(skb, gfp_mask);
 		if (unlikely(!skb))
 			return -ENOBUFS;
-		/* Our usage of tstamp should remain private */
-		skb->tstamp.tv64 = 0;
 	}
 
 	inet = inet_sk(sk);
@@ -975,7 +972,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
 			      tcp_skb_pcount(skb));
 
+	/* Our usage of tstamp should remain private */
+	skb->tstamp.tv64 = 0;
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
+
 	if (likely(err <= 0))
 		return err;
 
@@ -1149,7 +1149,6 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	/* Looks stupid, but our code really uses when of
 	 * skbs, which it never sent before. --ANK
 	 */
-	TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when;
 	buff->tstamp = skb->tstamp;
 	tcp_fragment_tstamp(skb, buff);
 
@@ -1874,8 +1873,8 @@ static int tcp_mtu_probe(struct sock *sk)
 	tcp_init_tso_segs(sk, nskb, nskb->len);
 
 	/* We're ready to send.  If this fails, the probe will
-	 * be resegmented into mss-sized pieces by tcp_write_xmit(). */
-	TCP_SKB_CB(nskb)->when = tcp_time_stamp;
+	 * be resegmented into mss-sized pieces by tcp_write_xmit().
+	 */
 	if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) {
 		/* Decrement cwnd here because we are sending
 		 * effectively two packets. */
@@ -1935,8 +1934,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		BUG_ON(!tso_segs);
 
 		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
-			/* "when" is used as a start point for the retransmit timer */
-			TCP_SKB_CB(skb)->when = tcp_time_stamp;
+			/* "skb_mstamp" is used as a start point for the retransmit timer */
+			skb_mstamp_get(&skb->skb_mstamp);
 			goto repair; /* Skip network transmission */
 		}
 
@@ -2000,8 +1999,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
 			break;
 
-		TCP_SKB_CB(skb)->when = tcp_time_stamp;
-
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 
@@ -2499,7 +2496,6 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	/* Make a copy, if the first transmission SKB clone we made
 	 * is still in somebody's hands, else make a clone.
 	 */
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 
 	/* make sure skb->data is aligned on arches that require it
 	 * and check if ack-trimming & collapsing extended the headroom
@@ -2544,7 +2540,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* Save stamp of the first retransmit. */
 		if (!tp->retrans_stamp)
-			tp->retrans_stamp = TCP_SKB_CB(skb)->when;
+			tp->retrans_stamp = tcp_skb_timestamp(skb);
 
 		/* snd_nxt is stored to detect loss of retransmitted segment,
 		 * see tcp_input.c tcp_sacktag_write_queue().
@@ -2752,7 +2748,6 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
 			     TCPHDR_ACK | TCPHDR_RST);
 	/* Send it off. */
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
 
@@ -2791,7 +2786,6 @@ int tcp_send_synack(struct sock *sk)
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK;
 		TCP_ECN_send_synack(tcp_sk(sk), skb);
 	}
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 	return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 }
 
@@ -2835,10 +2829,10 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	memset(&opts, 0, sizeof(opts));
 #ifdef CONFIG_SYN_COOKIES
 	if (unlikely(req->cookie_ts))
-		TCP_SKB_CB(skb)->when = cookie_init_timestamp(req);
+		skb->skb_mstamp.stamp_jiffies = cookie_init_timestamp(req);
 	else
 #endif
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
+	skb_mstamp_get(&skb->skb_mstamp);
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5,
 					     foc) + sizeof(*th);
 
@@ -3086,7 +3080,7 @@ int tcp_connect(struct sock *sk)
 	skb_reserve(buff, MAX_TCP_HEADER);
 
 	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
-	tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp;
+	tp->retrans_stamp = tcp_time_stamp;
 	tcp_connect_queue_skb(sk, buff);
 	TCP_ECN_send_syn(sk, buff);
 
@@ -3194,7 +3188,7 @@ void tcp_send_ack(struct sock *sk)
 	tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);
 
 	/* Send it off, this clears delayed acks for us. */
-	TCP_SKB_CB(buff)->when = tcp_time_stamp;
+	skb_mstamp_get(&buff->skb_mstamp);
 	tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
 }
 
@@ -3226,7 +3220,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 	 * send it.
 	 */
 	tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
-	TCP_SKB_CB(skb)->when = tcp_time_stamp;
+	skb_mstamp_get(&skb->skb_mstamp);
 	return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
 }
 
@@ -3270,7 +3264,6 @@ int tcp_write_wakeup(struct sock *sk)
 			tcp_set_skb_tso_segs(sk, skb, mss);
 
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
-		TCP_SKB_CB(skb)->when = tcp_time_stamp;
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 		if (!err)
 			tcp_event_new_data_sent(sk, skb);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index df90cd1ce37f..a339e7ba05a4 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -135,10 +135,9 @@ static bool retransmits_timed_out(struct sock *sk,
 	if (!inet_csk(sk)->icsk_retransmits)
 		return false;
 
-	if (unlikely(!tcp_sk(sk)->retrans_stamp))
-		start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when;
-	else
-		start_ts = tcp_sk(sk)->retrans_stamp;
+	start_ts = tcp_sk(sk)->retrans_stamp;
+	if (unlikely(!start_ts))
+		start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk));
 
 	if (likely(timeout == 0)) {
 		linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
-- 
cgit v1.2.3


From dec38b5ce6a9edb406c60c2670b26a1a4262fdb9 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Sat, 6 Sep 2014 01:11:12 +0100
Subject: regulator: isl9305: Add Intersil ISL9305/H driver

The ISL9305 and ISL9305H are mini-PMICs offering two DCDC regulators and
two LDO regulators. While there are some register differences between them
these do not affect the current Linux driver as the relevant features are
not yet supported.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/regulator/isl9305.txt      |  36 +++
 drivers/regulator/Kconfig                          |   6 +
 drivers/regulator/Makefile                         |   1 +
 drivers/regulator/isl9305.c                        | 247 +++++++++++++++++++++
 include/linux/platform_data/isl9305.h              |  30 +++
 5 files changed, 320 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/regulator/isl9305.txt
 create mode 100644 drivers/regulator/isl9305.c
 create mode 100644 include/linux/platform_data/isl9305.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/regulator/isl9305.txt b/Documentation/devicetree/bindings/regulator/isl9305.txt
new file mode 100644
index 000000000000..a626fc1bbf0d
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/isl9305.txt
@@ -0,0 +1,36 @@
+Intersil ISL9305/ISL9305H voltage regulator
+
+Required properties:
+
+- compatible: "isl,isl9305" or "isl,isl9305h"
+- reg: I2C slave address, usually 0x68.
+- regulators: A node that houses a sub-node for each regulator within the
+  device. Each sub-node is identified using the node's name, with valid
+  values being "dcd1", "dcd2", "ldo1" and "ldo2". The content of each sub-node
+  is defined by the standard binding for regulators; see regulator.txt.
+- VINDCD1-supply: A phandle to a regulator node supplying VINDCD1.
+  VINDCD2-supply: A phandle to a regulator node supplying VINDCD2.
+  VINLDO1-supply: A phandle to a regulator node supplying VINLDO1.
+  VINLDO2-supply: A phandle to a regulator node supplying VINLDO2.
+
+Optional properties:
+- Per-regulator optional properties are defined in regulator.txt
+
+Example
+
+	pmic: isl9305@68 {
+		compatible = "isl,isl9305";
+		reg = <0x68>;
+
+		VINDCD1-supply = <&system_power>;
+		VINDCD2-supply = <&system_power>;
+		VINLDO1-supply = <&system_power>;
+		VINLDO2-supply = <&system_power>;
+
+		regulators {
+			dcd1 {
+			        regulator-name = "VDD_DSP";
+				regulator-always-on;
+                        };
+		};
+	};
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index e6b98ed4c12f..3c8b6f401e4f 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -250,6 +250,12 @@ config REGULATOR_HI6421
 	  21 general purpose LDOs, 3 dedicated LDOs, and 5 BUCKs. All
 	  of them come with support to either ECO (idle) or sleep mode.
 
+config REGULATOR_ISL9305
+	tristate "Intersil ISL9305 regulator"
+	depends on I2C
+	help
+	  This driver supports ISL9305 voltage regulator chip.
+
 config REGULATOR_ISL6271A
 	tristate "Intersil ISL6271A Power regulator"
 	depends on I2C
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 5513e2c141b1..e12fee8c943b 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_REGULATOR_FAN53555) += fan53555.o
 obj-$(CONFIG_REGULATOR_GPIO) += gpio-regulator.o
 obj-$(CONFIG_REGULATOR_HI6421) += hi6421-regulator.o
 obj-$(CONFIG_REGULATOR_ISL6271A) += isl6271a-regulator.o
+obj-$(CONFIG_REGULATOR_ISL9305) += isl9305.o
 obj-$(CONFIG_REGULATOR_LP3971) += lp3971.o
 obj-$(CONFIG_REGULATOR_LP3972) += lp3972.o
 obj-$(CONFIG_REGULATOR_LP872X) += lp872x.o
diff --git a/drivers/regulator/isl9305.c b/drivers/regulator/isl9305.c
new file mode 100644
index 000000000000..b0d12d186b68
--- /dev/null
+++ b/drivers/regulator/isl9305.c
@@ -0,0 +1,247 @@
+/*
+ * isl9305 - Intersil ISL9305 DCDC regulator
+ *
+ * Copyright 2014 Linaro Ltd
+ *
+ * Author: Mark Brown <broonie@kernel.org>
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/of.h>
+#include <linux/platform_data/isl9305.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/of_regulator.h>
+#include <linux/slab.h>
+
+/*
+ * Registers
+ */
+#define ISL9305_DCD1OUT          0x0
+#define ISL9305_DCD2OUT          0x1
+#define ISL9305_LDO1OUT          0x2
+#define ISL9305_LDO2OUT          0x3
+#define ISL9305_DCD_PARAMETER    0x4
+#define ISL9305_SYSTEM_PARAMETER 0x5
+#define ISL9305_DCD_SRCTL        0x6
+
+#define ISL9305_MAX_REG ISL9305_DCD_SRCTL
+
+/*
+ * DCD_PARAMETER
+ */
+#define ISL9305_DCD_PHASE   0x40
+#define ISL9305_DCD2_ULTRA  0x20
+#define ISL9305_DCD1_ULTRA  0x10
+#define ISL9305_DCD2_BLD    0x08
+#define ISL9305_DCD1_BLD    0x04
+#define ISL9305_DCD2_MODE   0x02
+#define ISL9305_DCD1_MODE   0x01
+
+/*
+ * SYSTEM_PARAMETER
+ */
+#define ISL9305_I2C_EN      0x40
+#define ISL9305_DCDPOR_MASK 0x30
+#define ISL9305_LDO2_EN     0x08
+#define ISL9305_LDO1_EN     0x04
+#define ISL9305_DCD2_EN     0x02
+#define ISL9305_DCD1_EN     0x01
+
+/*
+ * DCD_SRCTL
+ */
+#define ISL9305_DCD2SR_MASK 0xc0
+#define ISL9305_DCD1SR_MASK 0x07
+
+static const struct regulator_ops isl9305_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_linear,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+};
+
+static const struct regulator_desc isl9305_regulators[] = {
+	[ISL9305_DCD1] = {
+		.name =		"DCD1",
+		.n_voltages =	0x70,
+		.min_uV =	825000,
+		.uV_step =	25000,
+		.vsel_reg =	ISL9305_DCD1OUT,
+		.vsel_mask =	0x7f,
+		.enable_reg =	ISL9305_SYSTEM_PARAMETER,
+		.enable_mask =	ISL9305_DCD1_EN,
+		.supply_name =	"VINDCD1",
+		.ops =		&isl9305_ops,
+	},
+	[ISL9305_DCD2] = {
+		.name =		"DCD2",
+		.n_voltages =	0x70,
+		.min_uV =	825000,
+		.uV_step =	25000,
+		.vsel_reg =	ISL9305_DCD2OUT,
+		.vsel_mask =	0x7f,
+		.enable_reg =	ISL9305_SYSTEM_PARAMETER,
+		.enable_mask =	ISL9305_DCD2_EN,
+		.supply_name =	"VINDCD2",
+		.ops =		&isl9305_ops,
+	},
+	[ISL9305_LDO1] = {
+		.name =		"LDO1",
+		.n_voltages =	0x37,
+		.min_uV =	900000,
+		.uV_step =	50000,
+		.vsel_reg =	ISL9305_LDO1OUT,
+		.vsel_mask =	0x3f,
+		.enable_reg =	ISL9305_SYSTEM_PARAMETER,
+		.enable_mask =	ISL9305_LDO1_EN,
+		.supply_name =	"VINLDO1",
+		.ops =		&isl9305_ops,
+	},
+	[ISL9305_LDO2] = {
+		.name =		"LDO2",
+		.n_voltages =	0x37,
+		.min_uV =	900000,
+		.uV_step =	50000,
+		.vsel_reg =	ISL9305_LDO2OUT,
+		.vsel_mask =	0x3f,
+		.enable_reg =	ISL9305_SYSTEM_PARAMETER,
+		.enable_mask =	ISL9305_LDO2_EN,
+		.supply_name =	"VINLDO2",
+		.ops =		&isl9305_ops,
+	},
+};
+
+#ifdef CONFIG_OF
+static struct of_regulator_match isl9305_reg_matches[] = {
+	[ISL9305_DCD1] = { .name = "dcd1" },
+	[ISL9305_DCD2] = { .name = "dcd2" },
+	[ISL9305_LDO1] = { .name = "ldo1" },
+	[ISL9305_LDO2] = { .name = "ldo2" },
+};
+
+static struct of_regulator_match *isl9305_parse_dt(struct i2c_client *i2c)
+{
+	struct device_node *node = i2c->dev.of_node;
+	struct of_regulator_match *matches;
+	struct device_node *regs;
+	int count;
+
+	regs = of_get_child_by_name(node, "regulators");
+	if (!regs)
+		return NULL;
+
+	matches = devm_kmemdup(&i2c->dev, isl9305_reg_matches,
+			       sizeof(isl9305_reg_matches), GFP_KERNEL);
+	if (!matches)
+		return NULL;
+
+	count = of_regulator_match(&i2c->dev, regs, matches,
+				   ARRAY_SIZE(isl9305_reg_matches));
+	of_node_put(regs);
+	if ((count < 0) || (count > ARRAY_SIZE(isl9305_reg_matches)))
+		return NULL;
+
+	return matches;
+}
+#else
+static struct of_regulator_match *isl9305_parse_dt(struct i2c_client *i2c)
+{
+	return NULL;
+}
+#endif
+
+static const struct regmap_config isl9305_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = ISL9305_MAX_REG,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static int isl9305_i2c_probe(struct i2c_client *i2c,
+			     const struct i2c_device_id *id)
+{
+	struct regulator_config config = { };
+	struct isl9305_pdata *pdata = i2c->dev.platform_data;
+	struct of_regulator_match *of_matches;
+	struct regulator_dev *rdev;
+	struct regmap *regmap;
+	int i, ret;
+
+	of_matches = isl9305_parse_dt(i2c);
+
+	regmap = devm_regmap_init_i2c(i2c, &isl9305_regmap);
+	if (IS_ERR(regmap)) {
+		ret = PTR_ERR(regmap);
+		dev_err(&i2c->dev, "Failed to create regmap: %d\n", ret);
+		return ret;
+	}
+
+	config.dev = &i2c->dev;
+
+	for (i = 0; i < ARRAY_SIZE(isl9305_regulators); i++) {
+		config.of_node = NULL;
+		config.init_data = NULL;
+
+		if (of_matches) {
+			config.init_data = of_matches[i].init_data;
+			config.of_node = of_matches[i].of_node;
+		}
+
+		if (!config.init_data && pdata)
+			config.init_data = pdata->init_data[i];
+
+		rdev = devm_regulator_register(&i2c->dev,
+					       &isl9305_regulators[i],
+					       &config);
+		if (IS_ERR(rdev)) {
+			ret = PTR_ERR(rdev);
+			dev_err(&i2c->dev, "Failed to register %s: %d\n",
+				isl9305_regulators[i].name, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id isl9305_dt_ids[] = {
+	{ .compatible = "isl,isl9305" },
+	{ .compatible = "isl,isl9305h" },
+	{},
+};
+#endif
+
+static const struct i2c_device_id isl9305_i2c_id[] = {
+	{ "isl9305", },
+	{ "isl9305h", },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, isl9305_i2c_id);
+
+static struct i2c_driver isl9305_regulator_driver = {
+	.driver = {
+		.name = "isl9305",
+		.owner = THIS_MODULE,
+		.of_match_table	= of_match_ptr(isl9305_dt_ids),
+	},
+	.probe = isl9305_i2c_probe,
+	.id_table = isl9305_i2c_id,
+};
+
+module_i2c_driver(isl9305_regulator_driver);
+
+MODULE_AUTHOR("Mark Brown");
+MODULE_DESCRIPTION("Intersil ISL9305 DCDC regulator");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/platform_data/isl9305.h b/include/linux/platform_data/isl9305.h
new file mode 100644
index 000000000000..1419133fa69e
--- /dev/null
+++ b/include/linux/platform_data/isl9305.h
@@ -0,0 +1,30 @@
+/*
+ * isl9305 - Intersil ISL9305 DCDC regulator
+ *
+ * Copyright 2014 Linaro Ltd
+ *
+ * Author: Mark Brown <broonie@kernel.org>
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#ifndef __ISL9305_H
+#define __ISL9305_H
+
+#define ISL9305_DCD1 0
+#define ISL9305_DCD2 1
+#define ISL9305_LDO1 2
+#define ISL9305_LDO2 3
+
+#define ISL9305_MAX_REGULATOR ISL9305_LDO2
+
+struct regulator_init_data;
+
+struct isl9305_pdata {
+	struct regulator_init_data *init_data[ISL9305_MAX_REGULATOR];
+};
+
+#endif
-- 
cgit v1.2.3


From c815dbb47758bd469927849fdd45fed3ce206e73 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Wed, 20 Aug 2014 13:08:46 +0200
Subject: ASoC: Add snd_soc_component_{get,set}_drvdata()

Add Add snd_soc_component_{get,set}_drvdata() similar to
snd_soc_codec_{get,set}_drvdata() and snd_soc_platform_{get,set}_drvdata().
Also update them to use the new functions internally.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Reviewed-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index ce09302bfd6d..f8b23dd7c3a7 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1298,26 +1298,37 @@ static inline void *snd_soc_card_get_drvdata(struct snd_soc_card *card)
 	return card->drvdata;
 }
 
+static inline void snd_soc_component_set_drvdata(struct snd_soc_component *c,
+		void *data)
+{
+	dev_set_drvdata(c->dev, data);
+}
+
+static inline void *snd_soc_component_get_drvdata(struct snd_soc_component *c)
+{
+	return dev_get_drvdata(c->dev);
+}
+
 static inline void snd_soc_codec_set_drvdata(struct snd_soc_codec *codec,
 		void *data)
 {
-	dev_set_drvdata(codec->dev, data);
+	snd_soc_component_set_drvdata(&codec->component, data);
 }
 
 static inline void *snd_soc_codec_get_drvdata(struct snd_soc_codec *codec)
 {
-	return dev_get_drvdata(codec->dev);
+	return snd_soc_component_get_drvdata(&codec->component);
 }
 
 static inline void snd_soc_platform_set_drvdata(struct snd_soc_platform *platform,
 		void *data)
 {
-	dev_set_drvdata(platform->dev, data);
+	snd_soc_component_set_drvdata(&platform->component, data);
 }
 
 static inline void *snd_soc_platform_get_drvdata(struct snd_soc_platform *platform)
 {
-	return dev_get_drvdata(platform->dev);
+	return snd_soc_component_get_drvdata(&platform->component);
 }
 
 static inline void snd_soc_pcm_set_drvdata(struct snd_soc_pcm_runtime *rtd,
-- 
cgit v1.2.3


From 0634814fe0f29a46c44386a03f259f99c983bf7e Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Wed, 20 Aug 2014 13:08:49 +0200
Subject: ASoC: Remove table based DAPM/control setup support from
 snd_soc_platform_driver

There are no users left and new users should rather use the component_driver
struct embedded in the snd_soc_platform_driver struct to do this. E.g.:

static const struct snd_soc_platform_driver foobar_driver = {
	.component_driver = {
		.dapm_widgets = ...,
		.num_dapm_widgets = ...,
		...,
	},
	...
};

instead of

static const struct snd_soc_platform_driver foobar_driver = {
	.dapm_widgets = ...,
	.num_dapm_widgets = ...,
	...
};

This also allows us to remove the steal_sibling_dai_widgets hack.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/soc.h  |  9 --------
 sound/soc/soc-core.c | 58 ++++++----------------------------------------------
 2 files changed, 6 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index f8b23dd7c3a7..cd141a156da2 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -764,7 +764,6 @@ struct snd_soc_component {
 	unsigned int num_dapm_widgets;
 	const struct snd_soc_dapm_route *dapm_routes;
 	unsigned int num_dapm_routes;
-	bool steal_sibling_dai_widgets;
 	struct snd_soc_codec *codec;
 
 	int (*probe)(struct snd_soc_component *);
@@ -868,14 +867,6 @@ struct snd_soc_platform_driver {
 	int (*pcm_new)(struct snd_soc_pcm_runtime *);
 	void (*pcm_free)(struct snd_pcm *);
 
-	/* Default control and setup, added after probe() is run */
-	const struct snd_kcontrol_new *controls;
-	int num_controls;
-	const struct snd_soc_dapm_widget *dapm_widgets;
-	int num_dapm_widgets;
-	const struct snd_soc_dapm_route *dapm_routes;
-	int num_dapm_routes;
-
 	/*
 	 * For platform caused delay reporting.
 	 * Optional.
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 1b422c5c36c8..052f59c1917f 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1087,7 +1087,6 @@ static int soc_probe_component(struct snd_soc_card *card,
 	struct snd_soc_component *component)
 {
 	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
-	struct snd_soc_component *dai_component, *component2;
 	struct snd_soc_dai *dai;
 	int ret;
 
@@ -1114,44 +1113,12 @@ static int soc_probe_component(struct snd_soc_card *card,
 		}
 	}
 
-	/*
-	 * This is rather ugly, but certain platforms expect that the DAPM
-	 * widgets for the DAIs for components with the same parent device are
-	 * created in the platforms DAPM context. Until that is fixed we need to
-	 * keep this.
-	 */
-	if (component->steal_sibling_dai_widgets) {
-		dai_component = NULL;
-		list_for_each_entry(component2, &component_list, list) {
-			if (component == component2)
-				continue;
-
-			if (component2->dev == component->dev &&
-			    !list_empty(&component2->dai_list)) {
-				dai_component = component2;
-				break;
-			}
-		}
-	} else {
-		dai_component = component;
-		list_for_each_entry(component2, &component_list, list) {
-			if (component2->dev == component->dev &&
-			    component2->steal_sibling_dai_widgets) {
-				dai_component = NULL;
-				break;
-			}
-		}
-	}
-
-	if (dai_component) {
-		list_for_each_entry(dai, &dai_component->dai_list, list) {
-			snd_soc_dapm_new_dai_widgets(dapm, dai);
-			if (ret != 0) {
-				dev_err(component->dev,
-					"Failed to create DAI widgets %d\n",
-					ret);
-				goto err_probe;
-			}
+	list_for_each_entry(dai, &component->dai_list, list) {
+		ret = snd_soc_dapm_new_dai_widgets(dapm, dai);
+		if (ret != 0) {
+			dev_err(component->dev,
+				"Failed to create DAI widgets %d\n", ret);
+			goto err_probe;
 		}
 	}
 
@@ -4164,19 +4131,6 @@ int snd_soc_add_platform(struct device *dev, struct snd_soc_platform *platform,
 
 	platform->dev = dev;
 	platform->driver = platform_drv;
-	if (platform_drv->controls) {
-		platform->component.controls = platform_drv->controls;
-		platform->component.num_controls = platform_drv->num_controls;
-	}
-	if (platform_drv->dapm_widgets) {
-		platform->component.dapm_widgets = platform_drv->dapm_widgets;
-		platform->component.num_dapm_widgets = platform_drv->num_dapm_widgets;
-		platform->component.steal_sibling_dai_widgets = true;
-	}
-	if (platform_drv->dapm_routes) {
-		platform->component.dapm_routes = platform_drv->dapm_routes;
-		platform->component.num_dapm_routes = platform_drv->num_dapm_routes;
-	}
 
 	if (platform_drv->probe)
 		platform->component.probe = snd_soc_platform_drv_probe;
-- 
cgit v1.2.3


From a8adcc9012d8502e06ba7b3f966bad8f2c58edc3 Mon Sep 17 00:00:00 2001
From: Ramakrishna Pallala <ramakrishna.pallala@intel.com>
Date: Wed, 27 Aug 2014 23:44:08 +0530
Subject: power_supply: Add boot and calibration attributes

Usually PMIC's come with coulomb counting mechanism which can be
used to implement a Fuel Gauginig solution in Software itself.
One of key input to these SW Fuel Gauge solutioons is the boot up
parameters like boot voltage and boot current.

This patch adds the VOLTAGE_BOOT and CURRENT_BOOT power supply attributes
to report bootup voltage and current.

This patch also adds CALIBRATE power supply attribute which useful is
for calibrating the battery/coulomb counter.

Signed-off-by: Ramakrishna Pallala <ramakrishna.pallala@intel.com>
Signed-off-by: Sebastian Reichel <sre@kernel.org>
---
 Documentation/power/power_supply_class.txt | 6 ++++++
 drivers/power/power_supply_sysfs.c         | 3 +++
 include/linux/power_supply.h               | 5 +++++
 3 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/Documentation/power/power_supply_class.txt b/Documentation/power/power_supply_class.txt
index 48cff881cb8a..82dacc06e355 100644
--- a/Documentation/power/power_supply_class.txt
+++ b/Documentation/power/power_supply_class.txt
@@ -101,6 +101,10 @@ VOLTAGE_MAX, VOLTAGE_MIN - same as _DESIGN voltage values except that
 these ones should be used if hardware could only guess (measure and
 retain) the thresholds of a given power supply.
 
+VOLTAGE_BOOT - Reports the voltage measured during boot
+
+CURRENT_BOOT - Reports the current measured during boot
+
 CHARGE_FULL_DESIGN, CHARGE_EMPTY_DESIGN - design charge values, when
 battery considered full/empty.
 
@@ -123,6 +127,8 @@ the current drawn from a charging source.
 CHARGE_TERM_CURRENT - Charge termination current used to detect the end of charge
 condition.
 
+CALIBRATE - battery or coulomb counter calibration status
+
 CONSTANT_CHARGE_VOLTAGE - constant charge voltage programmed by charger.
 CONSTANT_CHARGE_VOLTAGE_MAX - maximum charge voltage supported by the
 power supply object.
diff --git a/drivers/power/power_supply_sysfs.c b/drivers/power/power_supply_sysfs.c
index 750a20275664..7e4726d37211 100644
--- a/drivers/power/power_supply_sysfs.c
+++ b/drivers/power/power_supply_sysfs.c
@@ -149,9 +149,11 @@ static struct device_attribute power_supply_attrs[] = {
 	POWER_SUPPLY_ATTR(voltage_now),
 	POWER_SUPPLY_ATTR(voltage_avg),
 	POWER_SUPPLY_ATTR(voltage_ocv),
+	POWER_SUPPLY_ATTR(voltage_boot),
 	POWER_SUPPLY_ATTR(current_max),
 	POWER_SUPPLY_ATTR(current_now),
 	POWER_SUPPLY_ATTR(current_avg),
+	POWER_SUPPLY_ATTR(current_boot),
 	POWER_SUPPLY_ATTR(power_now),
 	POWER_SUPPLY_ATTR(power_avg),
 	POWER_SUPPLY_ATTR(charge_full_design),
@@ -193,6 +195,7 @@ static struct device_attribute power_supply_attrs[] = {
 	POWER_SUPPLY_ATTR(type),
 	POWER_SUPPLY_ATTR(scope),
 	POWER_SUPPLY_ATTR(charge_term_current),
+	POWER_SUPPLY_ATTR(calibrate),
 	/* Properties of type `const char *' */
 	POWER_SUPPLY_ATTR(model_name),
 	POWER_SUPPLY_ATTR(manufacturer),
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index f3dea41dbcd2..de59a28b1b5b 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -102,9 +102,11 @@ enum power_supply_property {
 	POWER_SUPPLY_PROP_VOLTAGE_NOW,
 	POWER_SUPPLY_PROP_VOLTAGE_AVG,
 	POWER_SUPPLY_PROP_VOLTAGE_OCV,
+	POWER_SUPPLY_PROP_VOLTAGE_BOOT,
 	POWER_SUPPLY_PROP_CURRENT_MAX,
 	POWER_SUPPLY_PROP_CURRENT_NOW,
 	POWER_SUPPLY_PROP_CURRENT_AVG,
+	POWER_SUPPLY_PROP_CURRENT_BOOT,
 	POWER_SUPPLY_PROP_POWER_NOW,
 	POWER_SUPPLY_PROP_POWER_AVG,
 	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
@@ -146,6 +148,7 @@ enum power_supply_property {
 	POWER_SUPPLY_PROP_TYPE, /* use power_supply.type instead */
 	POWER_SUPPLY_PROP_SCOPE,
 	POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT,
+	POWER_SUPPLY_PROP_CALIBRATE,
 	/* Properties of type `const char *' */
 	POWER_SUPPLY_PROP_MODEL_NAME,
 	POWER_SUPPLY_PROP_MANUFACTURER,
@@ -291,6 +294,7 @@ static inline bool power_supply_is_amp_property(enum power_supply_property psp)
 	case POWER_SUPPLY_PROP_CURRENT_MAX:
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
 	case POWER_SUPPLY_PROP_CURRENT_AVG:
+	case POWER_SUPPLY_PROP_CURRENT_BOOT:
 		return 1;
 	default:
 		break;
@@ -315,6 +319,7 @@ static inline bool power_supply_is_watt_property(enum power_supply_property psp)
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
 	case POWER_SUPPLY_PROP_VOLTAGE_AVG:
 	case POWER_SUPPLY_PROP_VOLTAGE_OCV:
+	case POWER_SUPPLY_PROP_VOLTAGE_BOOT:
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE:
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
 	case POWER_SUPPLY_PROP_POWER_NOW:
-- 
cgit v1.2.3


From 521d24ee598bd8a8b71d7ac76ce2c0da0e548406 Mon Sep 17 00:00:00 2001
From: Pranith Kumar <bobby.prani@gmail.com>
Date: Tue, 8 Jul 2014 18:26:18 -0400
Subject: rcu: Return bool type in rcu_lockdep_current_cpu_online()

Return true instead of 1 in rcu_lockdep_current_cpu_online() as this
has bool as return type.

Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d231aa17b1d7..7e47e44bce03 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -349,7 +349,7 @@ bool rcu_lockdep_current_cpu_online(void);
 #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
 static inline bool rcu_lockdep_current_cpu_online(void)
 {
-	return 1;
+	return true;
 }
 #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
 
-- 
cgit v1.2.3


From 85b39d305bfe809a11ff2770d380be3e2465beec Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 8 Jul 2014 15:17:59 -0700
Subject: rcu: Uninline rcu_read_lock_held()

This commit uninlines rcu_read_lock_held(). According to "size vmlinux"
this saves 28549 in .text:

	- 5541731 3014560 14757888 23314179
	+ 5513182 3026848 14757888 23297918

Note: it looks as if the data grows by 12288 bytes but this is not true,
it does not actually grow. But .data starts with ALIGN(THREAD_SIZE) and
since .text shrinks the padding grows, and thus .data grows too as it
seen by /bin/size. diff System.map:

	- ffffffff81510000 D _sdata
	- ffffffff81510000 D init_thread_union
	+ ffffffff81509000 D _sdata
	+ ffffffff8150c000 D init_thread_union

Perhaps we can change vmlinux.lds.S to .data itself, so that /bin/size
can't "wrongly" report that .data grows if .text shinks.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 36 +-----------------------------------
 kernel/rcu/update.c      | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 7e47e44bce03..321ed0d4e675 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -371,41 +371,7 @@ extern struct lockdep_map rcu_sched_lock_map;
 extern struct lockdep_map rcu_callback_map;
 int debug_lockdep_rcu_enabled(void);
 
-/**
- * rcu_read_lock_held() - might we be in RCU read-side critical section?
- *
- * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
- * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
- * this assumes we are in an RCU read-side critical section unless it can
- * prove otherwise.  This is useful for debug checks in functions that
- * require that they be called within an RCU read-side critical section.
- *
- * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
- * and while lockdep is disabled.
- *
- * Note that rcu_read_lock() and the matching rcu_read_unlock() must
- * occur in the same context, for example, it is illegal to invoke
- * rcu_read_unlock() in process context if the matching rcu_read_lock()
- * was invoked from within an irq handler.
- *
- * Note that rcu_read_lock() is disallowed if the CPU is either idle or
- * offline from an RCU perspective, so check for those as well.
- */
-static inline int rcu_read_lock_held(void)
-{
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
-	return lock_is_held(&rcu_lock_map);
-}
-
-/*
- * rcu_read_lock_bh_held() is defined out of line to avoid #include-file
- * hell.
- */
+int rcu_read_lock_held(void);
 int rcu_read_lock_bh_held(void);
 
 /**
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4056d7992a6c..ea8ea7b16e11 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -136,6 +136,38 @@ int notrace debug_lockdep_rcu_enabled(void)
 }
 EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
 
+/**
+ * rcu_read_lock_held() - might we be in RCU read-side critical section?
+ *
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
+ * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
+ * this assumes we are in an RCU read-side critical section unless it can
+ * prove otherwise.  This is useful for debug checks in functions that
+ * require that they be called within an RCU read-side critical section.
+ *
+ * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
+ *
+ * Note that rcu_read_lock() and the matching rcu_read_unlock() must
+ * occur in the same context, for example, it is illegal to invoke
+ * rcu_read_unlock() in process context if the matching rcu_read_lock()
+ * was invoked from within an irq handler.
+ *
+ * Note that rcu_read_lock() is disallowed if the CPU is either idle or
+ * offline from an RCU perspective, so check for those as well.
+ */
+int rcu_read_lock_held(void)
+{
+	if (!debug_lockdep_rcu_enabled())
+		return 1;
+	if (!rcu_is_watching())
+		return 0;
+	if (!rcu_lockdep_current_cpu_online())
+		return 0;
+	return lock_is_held(&rcu_lock_map);
+}
+EXPORT_SYMBOL_GPL(rcu_read_lock_held);
+
 /**
  * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
  *
-- 
cgit v1.2.3


From 9fdd3bc9005824704f9802bec7b3e06f5edae434 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 29 Jul 2014 14:50:47 -0700
Subject: rcu: Break more call_rcu() deadlock involving scheduler and perf

Commit 96d3fd0d315a9 (rcu: Break call_rcu() deadlock involving scheduler
and perf) covered the case where __call_rcu_nocb_enqueue() needs to wake
the rcuo kthread due to the queue being initially empty, but did not
do anything for the case where the queue was overflowing.  This commit
therefore also defers wakeup for the overflow case.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h |  3 +++
 kernel/rcu/tree.h          |  9 +++++++--
 kernel/rcu/tree_plugin.h   | 26 ++++++++++++++++++--------
 3 files changed, 28 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index aca382266411..9b56f37148cf 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -180,9 +180,12 @@ TRACE_EVENT(rcu_grace_period_init,
  * argument is a string as follows:
  *
  *	"WakeEmpty": Wake rcuo kthread, first CB to empty list.
+ *	"WakeEmptyIsDeferred": Wake rcuo kthread later, first CB to empty list.
  *	"WakeOvf": Wake rcuo kthread, CB list is huge.
+ *	"WakeOvfIsDeferred": Wake rcuo kthread later, CB list is huge.
  *	"WakeNot": Don't wake rcuo kthread.
  *	"WakeNotPoll": Don't wake rcuo kthread because it is polling.
+ *	"DeferredWake": Carried out the "IsDeferred" wakeup.
  *	"Poll": Start of new polling cycle for rcu_nocb_poll.
  *	"Sleep": Sleep waiting for CBs for !rcu_nocb_poll.
  *	"WokeEmpty": rcuo kthread woke to find empty list.
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 6a86eb7bac45..e33562f2a655 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -350,7 +350,7 @@ struct rcu_data {
 	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
-	bool nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
+	int nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
 
 	/* The following fields are used by the leader, hence own cacheline. */
 	struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
@@ -383,6 +383,11 @@ struct rcu_data {
 #define RCU_FORCE_QS		3	/* Need to force quiescent state. */
 #define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
 
+/* Values for nocb_defer_wakeup field in struct rcu_data. */
+#define RCU_NOGP_WAKE_NOT	0
+#define RCU_NOGP_WAKE		1
+#define RCU_NOGP_WAKE_FORCE	2
+
 #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
 					/* For jiffies_till_first_fqs and */
 					/*  and jiffies_till_next_fqs. */
@@ -589,7 +594,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 				      struct rcu_data *rdp,
 				      unsigned long flags);
-static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
+static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
 static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index bb564560aeb8..d67cc5c375c5 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2121,16 +2121,23 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
-			rdp->nocb_defer_wakeup = true;
+			rdp->nocb_defer_wakeup = RCU_NOGP_WAKE;
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("WakeEmptyIsDeferred"));
 		}
 		rdp->qlen_last_fqs_check = 0;
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
 		/* ... or if many callbacks queued. */
-		wake_nocb_leader(rdp, true);
+		if (!irqs_disabled_flags(flags)) {
+			wake_nocb_leader(rdp, true);
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeOvf"));
+		} else {
+			rdp->nocb_defer_wakeup = RCU_NOGP_WAKE_FORCE;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeOvfIsDeferred"));
+		}
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
-		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf"));
 	} else {
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot"));
 	}
@@ -2438,7 +2445,7 @@ static int rcu_nocb_kthread(void *arg)
 }
 
 /* Is a deferred wakeup of rcu_nocb_kthread() required? */
-static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 {
 	return ACCESS_ONCE(rdp->nocb_defer_wakeup);
 }
@@ -2446,11 +2453,14 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 /* Do a deferred wakeup of rcu_nocb_kthread(). */
 static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 {
+	int ndw;
+
 	if (!rcu_nocb_need_deferred_wakeup(rdp))
 		return;
-	ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
-	wake_nocb_leader(rdp, false);
-	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
+	ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup);
+	ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT;
+	wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE);
+	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake"));
 }
 
 /* Initialize per-rcu_data variables for no-CBs CPUs. */
@@ -2557,7 +2567,7 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 }
 
-static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 {
 	return false;
 }
-- 
cgit v1.2.3


From eea203fea3484598280a07fe503e025e886297fb Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 14 Jul 2014 09:16:15 -0400
Subject: rcu: Use pr_alert/pr_cont for printing logs

User pr_alert/pr_cont for printing the logs from rcutorture module directly
instead of writing it to a buffer and then printing it. This allows us from not
having to allocate such buffers. Also remove a resulting empty function.

I tested this using the parse-torture.sh script as follows:

$ dmesg | grep torture > log.txt
$ bash parse-torture.sh log.txt test
$

There were no warnings which means that parsing went fine.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/torture.h |   2 +-
 kernel/rcu/rcutorture.c | 127 +++++++++++++++++++++---------------------------
 kernel/torture.c        |  16 +++---
 3 files changed, 64 insertions(+), 81 deletions(-)

(limited to 'include')

diff --git a/include/linux/torture.h b/include/linux/torture.h
index 5ca58fcbaf1b..fec46f8c08eb 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -51,7 +51,7 @@
 
 /* Definitions for online/offline exerciser. */
 int torture_onoff_init(long ooholdoff, long oointerval);
-char *torture_onoff_stats(char *page);
+void torture_onoff_stats(void);
 bool torture_onoff_failures(void);
 
 /* Low-rider random number generator. */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 7e67711cbae8..ff4f0c756dee 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -242,7 +242,7 @@ struct rcu_torture_ops {
 	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
-	void (*stats)(char *page);
+	void (*stats)(void);
 	int irq_capable;
 	int can_boost;
 	const char *name;
@@ -525,21 +525,21 @@ static void srcu_torture_barrier(void)
 	srcu_barrier(&srcu_ctl);
 }
 
-static void srcu_torture_stats(char *page)
+static void srcu_torture_stats(void)
 {
 	int cpu;
 	int idx = srcu_ctl.completed & 0x1;
 
-	page += sprintf(page, "%s%s per-CPU(idx=%d):",
-		       torture_type, TORTURE_FLAG, idx);
+	pr_alert("%s%s per-CPU(idx=%d):",
+		 torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
 		long c0, c1;
 
 		c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx];
 		c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx];
-		page += sprintf(page, " %d(%ld,%ld)", cpu, c0, c1);
+		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
 	}
-	sprintf(page, "\n");
+	pr_cont("\n");
 }
 
 static void srcu_torture_synchronize_expedited(void)
@@ -1031,10 +1031,15 @@ rcu_torture_reader(void *arg)
 }
 
 /*
- * Create an RCU-torture statistics message in the specified buffer.
+ * Print torture statistics.  Caller must ensure that there is only
+ * one call to this function at a given time!!!  This is normally
+ * accomplished by relying on the module system to only have one copy
+ * of the module loaded, and then by giving the rcu_torture_stats
+ * kthread full control (or the init/cleanup functions when rcu_torture_stats
+ * thread is not running).
  */
 static void
-rcu_torture_printk(char *page)
+rcu_torture_stats_print(void)
 {
 	int cpu;
 	int i;
@@ -1052,55 +1057,60 @@ rcu_torture_printk(char *page)
 		if (pipesummary[i] != 0)
 			break;
 	}
-	page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
-	page += sprintf(page,
-		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
-		       rcu_torture_current,
-		       rcu_torture_current_version,
-		       list_empty(&rcu_torture_freelist),
-		       atomic_read(&n_rcu_torture_alloc),
-		       atomic_read(&n_rcu_torture_alloc_fail),
-		       atomic_read(&n_rcu_torture_free));
-	page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
-		       atomic_read(&n_rcu_torture_mberror),
-		       n_rcu_torture_boost_ktrerror,
-		       n_rcu_torture_boost_rterror);
-	page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
-		       n_rcu_torture_boost_failure,
-		       n_rcu_torture_boosts,
-		       n_rcu_torture_timers);
-	page = torture_onoff_stats(page);
-	page += sprintf(page, "barrier: %ld/%ld:%ld",
-		       n_barrier_successes,
-		       n_barrier_attempts,
-		       n_rcu_torture_barrier_error);
-	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+
+	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
+	pr_cont("rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
+		rcu_torture_current,
+		rcu_torture_current_version,
+		list_empty(&rcu_torture_freelist),
+		atomic_read(&n_rcu_torture_alloc),
+		atomic_read(&n_rcu_torture_alloc_fail),
+		atomic_read(&n_rcu_torture_free));
+	pr_cont("rtmbe: %d rtbke: %ld rtbre: %ld ",
+		atomic_read(&n_rcu_torture_mberror),
+		n_rcu_torture_boost_ktrerror,
+		n_rcu_torture_boost_rterror);
+	pr_cont("rtbf: %ld rtb: %ld nt: %ld ",
+		n_rcu_torture_boost_failure,
+		n_rcu_torture_boosts,
+		n_rcu_torture_timers);
+	torture_onoff_stats();
+	pr_cont("barrier: %ld/%ld:%ld\n",
+		n_barrier_successes,
+		n_barrier_attempts,
+		n_rcu_torture_barrier_error);
+
+	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
 	    n_rcu_torture_barrier_error != 0 ||
 	    n_rcu_torture_boost_ktrerror != 0 ||
 	    n_rcu_torture_boost_rterror != 0 ||
 	    n_rcu_torture_boost_failure != 0 ||
 	    i > 1) {
-		page += sprintf(page, "!!! ");
+		pr_cont("%s", "!!! ");
 		atomic_inc(&n_rcu_torture_error);
 		WARN_ON_ONCE(1);
 	}
-	page += sprintf(page, "Reader Pipe: ");
+	pr_cont("Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		page += sprintf(page, " %ld", pipesummary[i]);
-	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
-	page += sprintf(page, "Reader Batch: ");
+		pr_cont(" %ld", pipesummary[i]);
+	pr_cont("\n");
+
+	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
+	pr_cont("Reader Batch: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		page += sprintf(page, " %ld", batchsummary[i]);
-	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
-	page += sprintf(page, "Free-Block Circulation: ");
+		pr_cont(" %ld", batchsummary[i]);
+	pr_cont("\n");
+
+	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
+	pr_cont("Free-Block Circulation: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-		page += sprintf(page, " %d",
-			       atomic_read(&rcu_torture_wcount[i]));
+		pr_cont(" %d", atomic_read(&rcu_torture_wcount[i]));
 	}
-	page += sprintf(page, "\n");
+	pr_cont("\n");
+
 	if (cur_ops->stats)
-		cur_ops->stats(page);
+		cur_ops->stats();
 	if (rtcv_snap == rcu_torture_current_version &&
 	    rcu_torture_current != NULL) {
 		int __maybe_unused flags;
@@ -1109,40 +1119,15 @@ rcu_torture_printk(char *page)
 
 		rcutorture_get_gp_data(cur_ops->ttype,
 				       &flags, &gpnum, &completed);
-		page += sprintf(page,
-				"??? Writer stall state %d g%lu c%lu f%#x\n",
-				rcu_torture_writer_state,
-				gpnum, completed, flags);
+		pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n",
+			 rcu_torture_writer_state,
+			 gpnum, completed, flags);
 		show_rcu_gp_kthreads();
 		rcutorture_trace_dump();
 	}
 	rtcv_snap = rcu_torture_current_version;
 }
 
-/*
- * Print torture statistics.  Caller must ensure that there is only
- * one call to this function at a given time!!!  This is normally
- * accomplished by relying on the module system to only have one copy
- * of the module loaded, and then by giving the rcu_torture_stats
- * kthread full control (or the init/cleanup functions when rcu_torture_stats
- * thread is not running).
- */
-static void
-rcu_torture_stats_print(void)
-{
-	int size = nr_cpu_ids * 200 + 8192;
-	char *buf;
-
-	buf = kmalloc(size, GFP_KERNEL);
-	if (!buf) {
-		pr_err("rcu-torture: Out of memory, need: %d", size);
-		return;
-	}
-	rcu_torture_printk(buf);
-	pr_alert("%s", buf);
-	kfree(buf);
-}
-
 /*
  * Periodically prints torture statistics, if periodic statistics printing
  * was specified via the stat_interval module parameter.
diff --git a/kernel/torture.c b/kernel/torture.c
index d600af21f022..ede8b25ec1ae 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -211,18 +211,16 @@ EXPORT_SYMBOL_GPL(torture_onoff_cleanup);
 /*
  * Print online/offline testing statistics.
  */
-char *torture_onoff_stats(char *page)
+void torture_onoff_stats(void)
 {
 #ifdef CONFIG_HOTPLUG_CPU
-	page += sprintf(page,
-		       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
-		       n_online_successes, n_online_attempts,
-		       n_offline_successes, n_offline_attempts,
-		       min_online, max_online,
-		       min_offline, max_offline,
-		       sum_online, sum_offline, HZ);
+	pr_cont("onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
+		n_online_successes, n_online_attempts,
+		n_offline_successes, n_offline_attempts,
+		min_online, max_online,
+		min_offline, max_offline,
+		sum_online, sum_offline, HZ);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
-	return page;
 }
 EXPORT_SYMBOL_GPL(torture_onoff_stats);
 
-- 
cgit v1.2.3


From 8315f42295d2667a7f942f154b73a86fd7cb2227 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Jun 2014 13:42:20 -0700
Subject: rcu: Add call_rcu_tasks()

This commit adds a new RCU-tasks flavor of RCU, which provides
call_rcu_tasks().  This RCU flavor's quiescent states are voluntary
context switch (not preemption!) and userspace execution (not the idle
loop -- use some sort of schedule_on_each_cpu() if you need to handle the
idle tasks.  Note that unlike other RCU flavors, these quiescent states
occur in tasks, not necessarily CPUs.  Includes fixes from Steven Rostedt.

This RCU flavor is assumed to have very infrequent latency-tolerant
updaters.  This assumption permits significant simplifications, including
a single global callback list protected by a single global lock, along
with a single task-private linked list containing all tasks that have not
yet passed through a quiescent state.  If experience shows this assumption
to be incorrect, the required additional complexity will be added.

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/init_task.h |   9 +++
 include/linux/rcupdate.h  |  36 ++++++++++
 include/linux/sched.h     |  23 ++++---
 init/Kconfig              |  10 +++
 kernel/rcu/tiny.c         |   2 +
 kernel/rcu/tree.c         |   2 +
 kernel/rcu/update.c       | 171 ++++++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 242 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 2bb4c4f3531a..dffd9258ee60 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -117,6 +117,14 @@ extern struct group_info init_groups;
 #else
 #define INIT_TASK_RCU_PREEMPT(tsk)
 #endif
+#ifdef CONFIG_TASKS_RCU
+#define INIT_TASK_RCU_TASKS(tsk)					\
+	.rcu_tasks_holdout = false,					\
+	.rcu_tasks_holdout_list =					\
+		LIST_HEAD_INIT(tsk.rcu_tasks_holdout_list),
+#else
+#define INIT_TASK_RCU_TASKS(tsk)
+#endif
 
 extern struct cred init_cred;
 
@@ -224,6 +232,7 @@ extern struct task_group root_task_group;
 	INIT_FTRACE_GRAPH						\
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
+	INIT_TASK_RCU_TASKS(tsk)					\
 	INIT_CPUSET_SEQ(tsk)						\
 	INIT_RT_MUTEXES(tsk)						\
 	INIT_VTIME(tsk)							\
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d231aa17b1d7..3432063f4c87 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -197,6 +197,26 @@ void call_rcu_sched(struct rcu_head *head,
 
 void synchronize_sched(void);
 
+/**
+ * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks() assumes
+ * that the read-side critical sections end at a voluntary context
+ * switch (not a preemption!), entry into idle, or transition to usermode
+ * execution.  As such, there are no read-side primitives analogous to
+ * rcu_read_lock() and rcu_read_unlock() because this primitive is intended
+ * to determine that all tasks have passed through a safe state, not so
+ * much for data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks(struct rcu_head *head, void (*func)(struct rcu_head *head));
+
 #ifdef CONFIG_PREEMPT_RCU
 
 void __rcu_read_lock(void);
@@ -294,6 +314,22 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 		rcu_irq_exit(); \
 	} while (0)
 
+/*
+ * Note a voluntary context switch for RCU-tasks benefit.  This is a
+ * macro rather than an inline function to avoid #include hell.
+ */
+#ifdef CONFIG_TASKS_RCU
+#define rcu_note_voluntary_context_switch(t) \
+	do { \
+		preempt_disable(); /* Exclude synchronize_sched(); */ \
+		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
+			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
+		preempt_enable(); \
+	} while (0)
+#else /* #ifdef CONFIG_TASKS_RCU */
+#define rcu_note_voluntary_context_switch(t)	do { } while (0)
+#endif /* #else #ifdef CONFIG_TASKS_RCU */
+
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
 bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c2c885ee52b..eaacac4ae77d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1270,6 +1270,11 @@ struct task_struct {
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#ifdef CONFIG_TASKS_RCU
+	unsigned long rcu_tasks_nvcsw;
+	bool rcu_tasks_holdout;
+	struct list_head rcu_tasks_holdout_list;
+#endif /* #ifdef CONFIG_TASKS_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	struct sched_info sched_info;
@@ -2000,28 +2005,24 @@ extern void task_clear_jobctl_pending(struct task_struct *task,
 				      unsigned int mask);
 
 #ifdef CONFIG_PREEMPT_RCU
-
 #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
 #define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
+#ifdef CONFIG_PREEMPT_RCU
 	p->rcu_read_lock_nesting = 0;
 	p->rcu_read_unlock_special = 0;
-#ifdef CONFIG_TREE_PREEMPT_RCU
 	p->rcu_blocked_node = NULL;
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 	INIT_LIST_HEAD(&p->rcu_node_entry);
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TASKS_RCU
+	p->rcu_tasks_holdout = false;
+	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
+#endif /* #ifdef CONFIG_TASKS_RCU */
 }
 
-#else
-
-static inline void rcu_copy_process(struct task_struct *p)
-{
-}
-
-#endif
-
 static inline void tsk_restore_flags(struct task_struct *task,
 				unsigned long orig_flags, unsigned long flags)
 {
diff --git a/init/Kconfig b/init/Kconfig
index e84c6423a2e5..c4539c4e177f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -507,6 +507,16 @@ config PREEMPT_RCU
 	  This option enables preemptible-RCU code that is common between
 	  TREE_PREEMPT_RCU and, in the old days, TINY_PREEMPT_RCU.
 
+config TASKS_RCU
+	bool "Task_based RCU implementation using voluntary context switch"
+	default n
+	help
+	  This option enables a task-based RCU implementation that uses
+	  only voluntary context switch (not preemption!), idle, and
+	  user-mode execution as quiescent states.
+
+	  If unsure, say N.
+
 config RCU_STALL_COMMON
 	def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE )
 	help
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index d9efcc13008c..717f00854fc0 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -254,6 +254,8 @@ void rcu_check_callbacks(int cpu, int user)
 		rcu_sched_qs(cpu);
 	else if (!in_softirq())
 		rcu_bh_qs(cpu);
+	if (user)
+		rcu_note_voluntary_context_switch(current);
 }
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1b70cb6fbe3c..8ad91d1e317d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2410,6 +2410,8 @@ void rcu_check_callbacks(int cpu, int user)
 	rcu_preempt_check_callbacks(cpu);
 	if (rcu_pending(cpu))
 		invoke_rcu_core();
+	if (user)
+		rcu_note_voluntary_context_switch(current);
 	trace_rcu_utilization(TPS("End scheduler-tick"));
 }
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4056d7992a6c..19b3dacb0753 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -47,6 +47,7 @@
 #include <linux/hardirq.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/kthread.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -347,3 +348,173 @@ static int __init check_cpu_stall_init(void)
 early_initcall(check_cpu_stall_init);
 
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
+
+#ifdef CONFIG_TASKS_RCU
+
+/*
+ * Simple variant of RCU whose quiescent states are voluntary context switch,
+ * user-space execution, and idle.  As such, grace periods can take one good
+ * long time.  There are no read-side primitives similar to rcu_read_lock()
+ * and rcu_read_unlock() because this implementation is intended to get
+ * the system into a safe state for some of the manipulations involved in
+ * tracing and the like.  Finally, this implementation does not support
+ * high call_rcu_tasks() rates from multiple CPUs.  If this is required,
+ * per-CPU callback lists will be needed.
+ */
+
+/* Global list of callbacks and associated lock. */
+static struct rcu_head *rcu_tasks_cbs_head;
+static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
+static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
+
+/* Post an RCU-tasks callback. */
+void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp))
+{
+	unsigned long flags;
+
+	rhp->next = NULL;
+	rhp->func = func;
+	raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
+	*rcu_tasks_cbs_tail = rhp;
+	rcu_tasks_cbs_tail = &rhp->next;
+	raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks);
+
+/* See if the current task has stopped holding out, remove from list if so. */
+static void check_holdout_task(struct task_struct *t)
+{
+	if (!ACCESS_ONCE(t->rcu_tasks_holdout) ||
+	    t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) ||
+	    !ACCESS_ONCE(t->on_rq)) {
+		ACCESS_ONCE(t->rcu_tasks_holdout) = false;
+		list_del_rcu(&t->rcu_tasks_holdout_list);
+		put_task_struct(t);
+	}
+}
+
+/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
+static int __noreturn rcu_tasks_kthread(void *arg)
+{
+	unsigned long flags;
+	struct task_struct *g, *t;
+	struct rcu_head *list;
+	struct rcu_head *next;
+	LIST_HEAD(rcu_tasks_holdouts);
+
+	/* FIXME: Add housekeeping affinity. */
+
+	/*
+	 * Each pass through the following loop makes one check for
+	 * newly arrived callbacks, and, if there are some, waits for
+	 * one RCU-tasks grace period and then invokes the callbacks.
+	 * This loop is terminated by the system going down.  ;-)
+	 */
+	for (;;) {
+
+		/* Pick up any new callbacks. */
+		raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
+		list = rcu_tasks_cbs_head;
+		rcu_tasks_cbs_head = NULL;
+		rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
+		raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
+
+		/* If there were none, wait a bit and start over. */
+		if (!list) {
+			schedule_timeout_interruptible(HZ);
+			WARN_ON(signal_pending(current));
+			continue;
+		}
+
+		/*
+		 * Wait for all pre-existing t->on_rq and t->nvcsw
+		 * transitions to complete.  Invoking synchronize_sched()
+		 * suffices because all these transitions occur with
+		 * interrupts disabled.  Without this synchronize_sched(),
+		 * a read-side critical section that started before the
+		 * grace period might be incorrectly seen as having started
+		 * after the grace period.
+		 *
+		 * This synchronize_sched() also dispenses with the
+		 * need for a memory barrier on the first store to
+		 * ->rcu_tasks_holdout, as it forces the store to happen
+		 * after the beginning of the grace period.
+		 */
+		synchronize_sched();
+
+		/*
+		 * There were callbacks, so we need to wait for an
+		 * RCU-tasks grace period.  Start off by scanning
+		 * the task list for tasks that are not already
+		 * voluntarily blocked.  Mark these tasks and make
+		 * a list of them in rcu_tasks_holdouts.
+		 */
+		rcu_read_lock();
+		for_each_process_thread(g, t) {
+			if (t != current && ACCESS_ONCE(t->on_rq) &&
+			    !is_idle_task(t)) {
+				get_task_struct(t);
+				t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw);
+				ACCESS_ONCE(t->rcu_tasks_holdout) = true;
+				list_add(&t->rcu_tasks_holdout_list,
+					 &rcu_tasks_holdouts);
+			}
+		}
+		rcu_read_unlock();
+
+		/*
+		 * Each pass through the following loop scans the list
+		 * of holdout tasks, removing any that are no longer
+		 * holdouts.  When the list is empty, we are done.
+		 */
+		while (!list_empty(&rcu_tasks_holdouts)) {
+			schedule_timeout_interruptible(HZ);
+			WARN_ON(signal_pending(current));
+			rcu_read_lock();
+			list_for_each_entry_rcu(t, &rcu_tasks_holdouts,
+						rcu_tasks_holdout_list)
+				check_holdout_task(t);
+			rcu_read_unlock();
+		}
+
+		/*
+		 * Because ->on_rq and ->nvcsw are not guaranteed
+		 * to have a full memory barriers prior to them in the
+		 * schedule() path, memory reordering on other CPUs could
+		 * cause their RCU-tasks read-side critical sections to
+		 * extend past the end of the grace period.  However,
+		 * because these ->nvcsw updates are carried out with
+		 * interrupts disabled, we can use synchronize_sched()
+		 * to force the needed ordering on all such CPUs.
+		 *
+		 * This synchronize_sched() also confines all
+		 * ->rcu_tasks_holdout accesses to be within the grace
+		 * period, avoiding the need for memory barriers for
+		 * ->rcu_tasks_holdout accesses.
+		 */
+		synchronize_sched();
+
+		/* Invoke the callbacks. */
+		while (list) {
+			next = list->next;
+			local_bh_disable();
+			list->func(list);
+			local_bh_enable();
+			list = next;
+			cond_resched();
+		}
+	}
+}
+
+/* Spawn rcu_tasks_kthread() at boot time. */
+static int __init rcu_spawn_tasks_kthread(void)
+{
+	struct task_struct __maybe_unused *t;
+
+	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
+	BUG_ON(IS_ERR(t));
+	return 0;
+}
+early_initcall(rcu_spawn_tasks_kthread);
+
+#endif /* #ifdef CONFIG_TASKS_RCU */
-- 
cgit v1.2.3


From bde6c3aa993066acb0d6ce32ecabe03b9d5df92d Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 Jul 2014 11:26:57 -0700
Subject: rcu: Provide cond_resched_rcu_qs() to force quiescent states in long
 loops

RCU-tasks requires the occasional voluntary context switch
from CPU-bound in-kernel tasks.  In some cases, this requires
instrumenting cond_resched().  However, there is some reluctance
to countenance unconditionally instrumenting cond_resched() (see
http://lwn.net/Articles/603252/), so this commit creates a separate
cond_resched_rcu_qs() that may be used in place of cond_resched() in
locations prone to long-duration in-kernel looping.

This commit currently instruments only RCU-tasks.  Future possibilities
include also instrumenting RCU, RCU-bh, and RCU-sched in order to reduce
IPI usage.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 fs/file.c                |  2 +-
 include/linux/rcupdate.h | 13 +++++++++++++
 kernel/rcu/rcutorture.c  |  4 ++--
 kernel/rcu/tree.c        | 12 ++++++------
 kernel/rcu/tree_plugin.h |  2 +-
 mm/mlock.c               |  2 +-
 6 files changed, 24 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/fs/file.c b/fs/file.c
index 66923fe3176e..1cafc4c9275b 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -367,7 +367,7 @@ static struct fdtable *close_files(struct files_struct * files)
 				struct file * file = xchg(&fdt->fd[i], NULL);
 				if (file) {
 					filp_close(file, files);
-					cond_resched();
+					cond_resched_rcu_qs();
 				}
 			}
 			i++;
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 3432063f4c87..473350462d04 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -330,6 +330,19 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 #define rcu_note_voluntary_context_switch(t)	do { } while (0)
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
+/**
+ * cond_resched_rcu_qs - Report potential quiescent states to RCU
+ *
+ * This macro resembles cond_resched(), except that it is defined to
+ * report potential quiescent states to RCU-tasks even if the cond_resched()
+ * machinery were to be shut off, as some advocate for PREEMPT kernels.
+ */
+#define cond_resched_rcu_qs() \
+do { \
+	rcu_note_voluntary_context_switch(current); \
+	cond_resched(); \
+} while (0)
+
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
 bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 948a7693748e..178716713e11 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -667,7 +667,7 @@ static int rcu_torture_boost(void *arg)
 				}
 				call_rcu_time = jiffies;
 			}
-			cond_resched();
+			cond_resched_rcu_qs();
 			stutter_wait("rcu_torture_boost");
 			if (torture_must_stop())
 				goto checkwait;
@@ -1019,7 +1019,7 @@ rcu_torture_reader(void *arg)
 		__this_cpu_inc(rcu_torture_batch[completed]);
 		preempt_enable();
 		cur_ops->readunlock(idx);
-		cond_resched();
+		cond_resched_rcu_qs();
 		stutter_wait("rcu_torture_reader");
 	} while (!torture_must_stop());
 	if (irqreader && cur_ops->irq_capable) {
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8ad91d1e317d..e23dad0661e2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1647,7 +1647,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 
 	mutex_unlock(&rsp->onoff_mutex);
@@ -1736,7 +1736,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
@@ -1785,7 +1785,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
-			cond_resched();
+			cond_resched_rcu_qs();
 			flush_signals(current);
 			trace_rcu_grace_period(rsp->name,
 					       ACCESS_ONCE(rsp->gpnum),
@@ -1828,10 +1828,10 @@ static int __noreturn rcu_gp_kthread(void *arg)
 				trace_rcu_grace_period(rsp->name,
 						       ACCESS_ONCE(rsp->gpnum),
 						       TPS("fqsend"));
-				cond_resched();
+				cond_resched_rcu_qs();
 			} else {
 				/* Deal with stray signal. */
-				cond_resched();
+				cond_resched_rcu_qs();
 				flush_signals(current);
 				trace_rcu_grace_period(rsp->name,
 						       ACCESS_ONCE(rsp->gpnum),
@@ -2434,7 +2434,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rsp, rnp) {
-		cond_resched();
+		cond_resched_rcu_qs();
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index a7997e272564..7672586d3920 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1848,7 +1848,7 @@ static int rcu_oom_notify(struct notifier_block *self,
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 	put_online_cpus();
 
diff --git a/mm/mlock.c b/mm/mlock.c
index ce84cb0b83ef..ab3150c26711 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -789,7 +789,7 @@ static int do_mlockall(int flags)
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 out:
 	return 0;
-- 
cgit v1.2.3


From 53c6d4edf874d3cbc031a53738c6cba9277faea5 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 Jul 2014 12:22:23 -0700
Subject: rcu: Add synchronous grace-period waiting for RCU-tasks

It turns out to be easier to add the synchronous grace-period waiting
functions to RCU-tasks than to work around their absense in rcutorture,
so this commit adds them.  The key point is that the existence of
call_rcu_tasks() means that rcutorture needs an rcu_barrier_tasks().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h |  2 ++
 kernel/rcu/update.c      | 55 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 473350462d04..640152fedcde 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -216,6 +216,8 @@ void synchronize_sched(void);
  * memory ordering guarantees.
  */
 void call_rcu_tasks(struct rcu_head *head, void (*func)(struct rcu_head *head));
+void synchronize_rcu_tasks(void);
+void rcu_barrier_tasks(void);
 
 #ifdef CONFIG_PREEMPT_RCU
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 19b3dacb0753..5fd1ddbfcc55 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -381,6 +381,61 @@ void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp))
 }
 EXPORT_SYMBOL_GPL(call_rcu_tasks);
 
+/**
+ * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed.  These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_rcu_qs(), idle execution, userspace execution, calls
+ * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function
+ * preambles and profiling hooks.  The synchronize_rcu_tasks() function
+ * is not (yet) intended for heavy use from multiple CPUs.
+ *
+ * Note that this guarantee implies further memory-ordering guarantees.
+ * On systems with more than one CPU, when synchronize_rcu_tasks() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since the
+ * end of its last RCU-tasks read-side critical section whose beginning
+ * preceded the call to synchronize_rcu_tasks().  In addition, each CPU
+ * having an RCU-tasks read-side critical section that extends beyond
+ * the return from synchronize_rcu_tasks() is guaranteed to have executed
+ * a full memory barrier after the beginning of synchronize_rcu_tasks()
+ * and before the beginning of that RCU-tasks read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_rcu_tasks(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU
+ * (but again only if the system has more than one CPU).
+ */
+void synchronize_rcu_tasks(void)
+{
+	/* Complain if the scheduler has not started.  */
+	rcu_lockdep_assert(!rcu_scheduler_active,
+			   "synchronize_rcu_tasks called too soon");
+
+	/* Wait for the grace period. */
+	wait_rcu_gp(call_rcu_tasks);
+}
+
+/**
+ * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks(void)
+{
+	/* There is only one callback queue, so this is easy.  ;-) */
+	synchronize_rcu_tasks();
+}
+
 /* See if the current task has stopped holding out, remove from list if so. */
 static void check_holdout_task(struct task_struct *t)
 {
-- 
cgit v1.2.3


From 3f95aa81d265223fdb13ea2b59883766a05adbdf Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 4 Aug 2014 06:10:23 -0700
Subject: rcu: Make TASKS_RCU handle tasks that are almost done exiting

Once a task has passed exit_notify() in the do_exit() code path, it
is no longer on the task lists, and is therefore no longer visible
to rcu_tasks_kthread().  This means that an almost-exited task might
be preempted while within a trampoline, and this task won't be waited
on by rcu_tasks_kthread().  This commit fixes this bug by adding an
srcu_struct.  An exiting task does srcu_read_lock() just before calling
exit_notify(), and does the corresponding srcu_read_unlock() after
doing the final preempt_disable().  This means that rcu_tasks_kthread()
can do synchronize_srcu() to wait for all mostly-exited tasks to reach
their final preempt_disable() region, and then use synchronize_sched()
to wait for those tasks to finish exiting.

Reported-by: Oleg Nesterov <oleg@redhat.com>
Suggested-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h |  3 +++
 kernel/exit.c            |  3 +++
 kernel/rcu/update.c      | 21 +++++++++++++++++++++
 3 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 640152fedcde..54b2ebb20313 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -321,6 +321,8 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
  * macro rather than an inline function to avoid #include hell.
  */
 #ifdef CONFIG_TASKS_RCU
+#define TASKS_RCU(x) x
+extern struct srcu_struct tasks_rcu_exit_srcu;
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
 		preempt_disable(); /* Exclude synchronize_sched(); */ \
@@ -329,6 +331,7 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 		preempt_enable(); \
 	} while (0)
 #else /* #ifdef CONFIG_TASKS_RCU */
+#define TASKS_RCU(x) do { } while (0)
 #define rcu_note_voluntary_context_switch(t)	do { } while (0)
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 32c58f7433a3..d13f2eec4bb8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -667,6 +667,7 @@ void do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
+	TASKS_RCU(int tasks_rcu_i);
 
 	profile_task_exit(tsk);
 
@@ -775,6 +776,7 @@ void do_exit(long code)
 	 */
 	flush_ptrace_hw_breakpoint(tsk);
 
+	TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu));
 	exit_notify(tsk, group_dead);
 	proc_exit_connector(tsk);
 #ifdef CONFIG_NUMA
@@ -814,6 +816,7 @@ void do_exit(long code)
 	if (tsk->nr_dirtied)
 		__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
 	exit_rcu();
+	TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i));
 
 	/*
 	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 5fd1ddbfcc55..403fc4ae539e 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -367,6 +367,13 @@ static struct rcu_head *rcu_tasks_cbs_head;
 static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
 static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
 
+/* Track exiting tasks in order to allow them to be waited for. */
+DEFINE_SRCU(tasks_rcu_exit_srcu);
+
+/* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
+static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 3;
+module_param(rcu_task_stall_timeout, int, 0644);
+
 /* Post an RCU-tasks callback. */
 void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp))
 {
@@ -517,6 +524,15 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		}
 		rcu_read_unlock();
 
+		/*
+		 * Wait for tasks that are in the process of exiting.
+		 * This does only part of the job, ensuring that all
+		 * tasks that were previously exiting reach the point
+		 * where they have disabled preemption, allowing the
+		 * later synchronize_sched() to finish the job.
+		 */
+		synchronize_srcu(&tasks_rcu_exit_srcu);
+
 		/*
 		 * Each pass through the following loop scans the list
 		 * of holdout tasks, removing any that are no longer
@@ -546,6 +562,11 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		 * ->rcu_tasks_holdout accesses to be within the grace
 		 * period, avoiding the need for memory barriers for
 		 * ->rcu_tasks_holdout accesses.
+		 *
+		 * In addition, this synchronize_sched() waits for exiting
+		 * tasks to complete their final preempt_disable() region
+		 * of execution, cleaning up after the synchronize_srcu()
+		 * above.
 		 */
 		synchronize_sched();
 
-- 
cgit v1.2.3


From 69c604557ce34015629b325b85ff1a4996038a3b Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 Jul 2014 11:59:36 -0700
Subject: rcutorture: Add torture tests for RCU-tasks

This commit adds torture tests for RCU-tasks.  It also fixes a bug that
would segfault for an RCU flavor lacking a callback-barrier function.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
---
 include/linux/rcupdate.h |  1 +
 kernel/rcu/rcutorture.c  | 50 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 50 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 54b2ebb20313..a3123f53a4ce 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -55,6 +55,7 @@ enum rcutorture_type {
 	RCU_FLAVOR,
 	RCU_BH_FLAVOR,
 	RCU_SCHED_FLAVOR,
+	RCU_TASKS_FLAVOR,
 	SRCU_FLAVOR,
 	INVALID_RCU_FLAVOR
 };
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 178716713e11..75b1abf78c48 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -601,6 +601,52 @@ static struct rcu_torture_ops sched_ops = {
 	.name		= "sched"
 };
 
+#ifdef CONFIG_TASKS_RCU
+
+/*
+ * Definitions for RCU-tasks torture testing.
+ */
+
+static int tasks_torture_read_lock(void)
+{
+	return 0;
+}
+
+static void tasks_torture_read_unlock(int idx)
+{
+}
+
+static void rcu_tasks_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_ops = {
+	.ttype		= RCU_TASKS_FLAVOR,
+	.init		= rcu_sync_torture_init,
+	.readlock	= tasks_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= tasks_torture_read_unlock,
+	.completed	= rcu_no_completed,
+	.deferred_free	= rcu_tasks_torture_deferred_free,
+	.sync		= synchronize_rcu_tasks,
+	.exp_sync	= synchronize_rcu_tasks,
+	.call		= call_rcu_tasks,
+	.cb_barrier	= rcu_barrier_tasks,
+	.fqs		= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "tasks"
+};
+
+#define RCUTORTURE_TASKS_OPS &tasks_ops,
+
+#else /* #ifdef CONFIG_TASKS_RCU */
+
+#define RCUTORTURE_TASKS_OPS
+
+#endif /* #else #ifdef CONFIG_TASKS_RCU */
+
 /*
  * RCU torture priority-boost testing.  Runs one real-time thread per
  * CPU for moderate bursts, repeatedly registering RCU callbacks and
@@ -1295,7 +1341,8 @@ static int rcu_torture_barrier_cbs(void *arg)
 		if (atomic_dec_and_test(&barrier_cbs_count))
 			wake_up(&barrier_wq);
 	} while (!torture_must_stop());
-	cur_ops->cb_barrier();
+	if (cur_ops->cb_barrier != NULL)
+		cur_ops->cb_barrier();
 	destroy_rcu_head_on_stack(&rcu);
 	torture_kthread_stopping("rcu_torture_barrier_cbs");
 	return 0;
@@ -1534,6 +1581,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
+		RCUTORTURE_TASKS_OPS
 	};
 
 	if (!torture_init_begin(torture_type, verbose, &rcutorture_runnable))
-- 
cgit v1.2.3


From 176f8f7a52cc6d09d686f0d900abda6942a52fbb Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 4 Aug 2014 17:43:50 -0700
Subject: rcu: Make TASKS_RCU handle nohz_full= CPUs

Currently TASKS_RCU would ignore a CPU running a task in nohz_full=
usermode execution.  There would be neither a context switch nor a
scheduling-clock interrupt to tell TASKS_RCU that the task in question
had passed through a quiescent state.  The grace period would therefore
extend indefinitely.  This commit therefore makes RCU's dyntick-idle
subsystem record the task_struct structure of the task that is running
in dyntick-idle mode on each CPU.  The TASKS_RCU grace period can
then access this information and record a quiescent state on
behalf of any CPU running in dyntick-idle usermode.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/init_task.h |  3 ++-
 include/linux/sched.h     |  2 ++
 kernel/rcu/tree.c         |  2 ++
 kernel/rcu/tree.h         |  2 ++
 kernel/rcu/tree_plugin.h  | 16 ++++++++++++++++
 kernel/rcu/update.c       |  4 +++-
 6 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index dffd9258ee60..03b274873b06 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -121,7 +121,8 @@ extern struct group_info init_groups;
 #define INIT_TASK_RCU_TASKS(tsk)					\
 	.rcu_tasks_holdout = false,					\
 	.rcu_tasks_holdout_list =					\
-		LIST_HEAD_INIT(tsk.rcu_tasks_holdout_list),
+		LIST_HEAD_INIT(tsk.rcu_tasks_holdout_list),		\
+	.rcu_tasks_idle_cpu = -1,
 #else
 #define INIT_TASK_RCU_TASKS(tsk)
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index eaacac4ae77d..ec8b34722bcc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1274,6 +1274,7 @@ struct task_struct {
 	unsigned long rcu_tasks_nvcsw;
 	bool rcu_tasks_holdout;
 	struct list_head rcu_tasks_holdout_list;
+	int rcu_tasks_idle_cpu;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
@@ -2020,6 +2021,7 @@ static inline void rcu_copy_process(struct task_struct *p)
 #ifdef CONFIG_TASKS_RCU
 	p->rcu_tasks_holdout = false;
 	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
+	p->rcu_tasks_idle_cpu = -1;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 }
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e23dad0661e2..c880f5387b1f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -526,6 +526,7 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 	atomic_inc(&rdtp->dynticks);
 	smp_mb__after_atomic();  /* Force ordering with next sojourn. */
 	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	rcu_dynticks_task_enter();
 
 	/*
 	 * It is illegal to enter an extended quiescent state while
@@ -642,6 +643,7 @@ void rcu_irq_exit(void)
 static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
 			       int user)
 {
+	rcu_dynticks_task_exit();
 	smp_mb__before_atomic();  /* Force ordering w/previous sojourn. */
 	atomic_inc(&rdtp->dynticks);
 	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 6a86eb7bac45..3a92000c354f 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -605,6 +605,8 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
 static void rcu_bind_gp_kthread(void);
 static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
 static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
+static void rcu_dynticks_task_enter(void);
+static void rcu_dynticks_task_exit(void);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7672586d3920..e466b40052a7 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -3036,3 +3036,19 @@ static void rcu_bind_gp_kthread(void)
 		housekeeping_affine(current);
 #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 }
+
+/* Record the current task on dyntick-idle entry. */
+static void rcu_dynticks_task_enter(void)
+{
+#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
+	ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id();
+#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
+}
+
+/* Record no current task on dyntick-idle exit. */
+static void rcu_dynticks_task_exit(void)
+{
+#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
+	ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1;
+#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
+}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index e1d71741958f..2658de4a5975 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -463,7 +463,9 @@ static void check_holdout_task(struct task_struct *t,
 {
 	if (!ACCESS_ONCE(t->rcu_tasks_holdout) ||
 	    t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) ||
-	    !ACCESS_ONCE(t->on_rq)) {
+	    !ACCESS_ONCE(t->on_rq) ||
+	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
+	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
 		ACCESS_ONCE(t->rcu_tasks_holdout) = false;
 		list_del_rcu(&t->rcu_tasks_holdout_list);
 		put_task_struct(t);
-- 
cgit v1.2.3


From 01a81330344b09028881c953a51d1106a9e63518 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 5 Aug 2014 05:23:35 -0700
Subject: rcu: Remove redundant preempt_disable() from
 rcu_note_voluntary_context_switch()

In theory, synchronize_sched() requires a read-side critical section
to order against.  In practice, preemption can be thought of as
being disabled across every machine instruction, at least for those
machine instructions that are not in the idle loop and not on offline
CPUs.  So this commit removes the redundant preempt_disable() from
rcu_note_voluntary_context_switch().

Please note that the single instruction in question is the store of
zero to ->rcu_tasks_holdout.  The "if" is simply a performance optimization
that avoids unnecessary stores.  To see this, keep in mind that both
the "if" condition and the store are in a quiescent state.  Therefore,
even if the task is preempted for a full grace period (presumably due
to its having done a context switch beforehand), the store will be
recording a legitimate quiescent state.

Reported-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

Conflicts:
	include/linux/rcupdate.h
---
 include/linux/rcupdate.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a3123f53a4ce..132e1e34cdca 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -326,10 +326,8 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 extern struct srcu_struct tasks_rcu_exit_srcu;
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
-		preempt_disable(); /* Exclude synchronize_sched(); */ \
 		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
 			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
-		preempt_enable(); \
 	} while (0)
 #else /* #ifdef CONFIG_TASKS_RCU */
 #define TASKS_RCU(x) do { } while (0)
-- 
cgit v1.2.3


From 1d082fd061884a587c490c4fc8a2056ce1e47624 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 14 Aug 2014 16:01:53 -0700
Subject: rcu: Remove local_irq_disable() in rcu_preempt_note_context_switch()

The rcu_preempt_note_context_switch() function is on a scheduling fast
path, so it would be good to avoid disabling irqs.  The reason that irqs
are disabled is to synchronize process-level and irq-handler access to
the task_struct ->rcu_read_unlock_special bitmask.  This commit therefore
makes ->rcu_read_unlock_special instead be a union of bools with a short
allowing single-access checks in RCU's __rcu_read_unlock().  This results
in the process-level and irq-handler accesses being simple loads and
stores, so that irqs need no longer be disabled.  This commit therefore
removes the irq disabling from rcu_preempt_note_context_switch().

Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/init_task.h |  2 +-
 include/linux/sched.h     | 16 +++++++++-------
 kernel/rcu/tree_plugin.h  | 32 +++++++++++++++-----------------
 kernel/rcu/update.c       |  2 +-
 4 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 03b274873b06..77fc43f8fb72 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -111,7 +111,7 @@ extern struct group_info init_groups;
 #ifdef CONFIG_PREEMPT_RCU
 #define INIT_TASK_RCU_PREEMPT(tsk)					\
 	.rcu_read_lock_nesting = 0,					\
-	.rcu_read_unlock_special = 0,					\
+	.rcu_read_unlock_special.s = 0,					\
 	.rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),		\
 	INIT_TASK_RCU_TREE_PREEMPT()
 #else
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ec8b34722bcc..42888d715fb1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1212,6 +1212,13 @@ struct sched_dl_entity {
 	struct hrtimer dl_timer;
 };
 
+union rcu_special {
+	struct {
+		bool blocked;
+		bool need_qs;
+	} b;
+	short s;
+};
 struct rcu_node;
 
 enum perf_event_task_context {
@@ -1264,7 +1271,7 @@ struct task_struct {
 
 #ifdef CONFIG_PREEMPT_RCU
 	int rcu_read_lock_nesting;
-	char rcu_read_unlock_special;
+	union rcu_special rcu_read_unlock_special;
 	struct list_head rcu_node_entry;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TREE_PREEMPT_RCU
@@ -2005,16 +2012,11 @@ extern void task_clear_jobctl_trapping(struct task_struct *task);
 extern void task_clear_jobctl_pending(struct task_struct *task,
 				      unsigned int mask);
 
-#ifdef CONFIG_PREEMPT_RCU
-#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
-#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-
 static inline void rcu_copy_process(struct task_struct *p)
 {
 #ifdef CONFIG_PREEMPT_RCU
 	p->rcu_read_lock_nesting = 0;
-	p->rcu_read_unlock_special = 0;
+	p->rcu_read_unlock_special.s = 0;
 	p->rcu_blocked_node = NULL;
 	INIT_LIST_HEAD(&p->rcu_node_entry);
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index e466b40052a7..0981c0cd70fe 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -155,9 +155,8 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed);
  * not in a quiescent state.  There might be any number of tasks blocked
  * while in an RCU read-side critical section.
  *
- * Unlike the other rcu_*_qs() functions, callers to this function
- * must disable irqs in order to protect the assignment to
- * ->rcu_read_unlock_special.
+ * As with the other rcu_*_qs() functions, callers to this function
+ * must disable preemption.
  */
 static void rcu_preempt_qs(int cpu)
 {
@@ -166,7 +165,7 @@ static void rcu_preempt_qs(int cpu)
 	if (rdp->passed_quiesce == 0)
 		trace_rcu_grace_period(TPS("rcu_preempt"), rdp->gpnum, TPS("cpuqs"));
 	rdp->passed_quiesce = 1;
-	current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+	current->rcu_read_unlock_special.b.need_qs = false;
 }
 
 /*
@@ -190,14 +189,14 @@ static void rcu_preempt_note_context_switch(int cpu)
 	struct rcu_node *rnp;
 
 	if (t->rcu_read_lock_nesting > 0 &&
-	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
+	    !t->rcu_read_unlock_special.b.blocked) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
 		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
-		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
+		t->rcu_read_unlock_special.b.blocked = true;
 		t->rcu_blocked_node = rnp;
 
 		/*
@@ -239,7 +238,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 				       : rnp->gpnum + 1);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else if (t->rcu_read_lock_nesting < 0 &&
-		   t->rcu_read_unlock_special) {
+		   t->rcu_read_unlock_special.s) {
 
 		/*
 		 * Complete exit from RCU read-side critical section on
@@ -257,9 +256,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	 * grace period, then the fact that the task has been enqueued
 	 * means that we continue to block the current grace period.
 	 */
-	local_irq_save(flags);
 	rcu_preempt_qs(cpu);
-	local_irq_restore(flags);
 }
 
 /*
@@ -340,7 +337,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	bool drop_boost_mutex = false;
 #endif /* #ifdef CONFIG_RCU_BOOST */
 	struct rcu_node *rnp;
-	int special;
+	union rcu_special special;
 
 	/* NMI handlers cannot block and cannot safely manipulate state. */
 	if (in_nmi())
@@ -350,12 +347,13 @@ void rcu_read_unlock_special(struct task_struct *t)
 
 	/*
 	 * If RCU core is waiting for this CPU to exit critical section,
-	 * let it know that we have done so.
+	 * let it know that we have done so.  Because irqs are disabled,
+	 * t->rcu_read_unlock_special cannot change.
 	 */
 	special = t->rcu_read_unlock_special;
-	if (special & RCU_READ_UNLOCK_NEED_QS) {
+	if (special.b.need_qs) {
 		rcu_preempt_qs(smp_processor_id());
-		if (!t->rcu_read_unlock_special) {
+		if (!t->rcu_read_unlock_special.s) {
 			local_irq_restore(flags);
 			return;
 		}
@@ -368,8 +366,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 	}
 
 	/* Clean up if blocked during RCU read-side critical section. */
-	if (special & RCU_READ_UNLOCK_BLOCKED) {
-		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
+	if (special.b.blocked) {
+		t->rcu_read_unlock_special.b.blocked = false;
 
 		/*
 		 * Remove this task from the list it blocked on.  The
@@ -658,7 +656,7 @@ static void rcu_preempt_check_callbacks(int cpu)
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
 	    per_cpu(rcu_preempt_data, cpu).qs_pending)
-		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
+		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
 #ifdef CONFIG_RCU_BOOST
@@ -941,7 +939,7 @@ void exit_rcu(void)
 		return;
 	t->rcu_read_lock_nesting = 1;
 	barrier();
-	t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED;
+	t->rcu_read_unlock_special.b.blocked = true;
 	__rcu_read_unlock();
 }
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 9487b4898e51..6fb911558562 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -93,7 +93,7 @@ void __rcu_read_unlock(void)
 		barrier();  /* critical section before exit code. */
 		t->rcu_read_lock_nesting = INT_MIN;
 		barrier();  /* assign before ->rcu_read_unlock_special load */
-		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
 		barrier();  /* ->rcu_read_unlock_special load before assign */
 		t->rcu_read_lock_nesting = 0;
-- 
cgit v1.2.3


From 284a8c93af47306beed967a303d84730b32bab39 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 14 Aug 2014 16:38:46 -0700
Subject: rcu: Per-CPU operation cleanups to rcu_*_qs() functions

The rcu_bh_qs(), rcu_preempt_qs(), and rcu_sched_qs() functions use
old-style per-CPU variable access and write to ->passed_quiesce even
if it is already set.  This commit therefore updates to use the new-style
per-CPU variable access functions and avoids the spurious writes.
This commit also eliminates the "cpu" argument to these functions because
they are always invoked on the indicated CPU.

Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h |  4 ++--
 include/linux/rcutiny.h  |  2 +-
 kernel/rcu/tiny.c        | 10 +++++-----
 kernel/rcu/tree.c        | 34 ++++++++++++++++++----------------
 kernel/rcu/tree_plugin.h | 27 +++++++++++++++------------
 kernel/softirq.c         |  2 +-
 6 files changed, 42 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 132e1e34cdca..2fab0e37afe0 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -261,8 +261,8 @@ static inline int rcu_preempt_depth(void)
 
 /* Internal to kernel */
 void rcu_init(void);
-void rcu_sched_qs(int cpu);
-void rcu_bh_qs(int cpu);
+void rcu_sched_qs(void);
+void rcu_bh_qs(void);
 void rcu_check_callbacks(int cpu, int user);
 struct notifier_block;
 void rcu_idle_enter(void);
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index d40a6a451330..38cc5b1e252d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -80,7 +80,7 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 
 static inline void rcu_note_context_switch(int cpu)
 {
-	rcu_sched_qs(cpu);
+	rcu_sched_qs();
 }
 
 /*
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 717f00854fc0..61b8d2ccc2cb 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -72,7 +72,7 @@ static void rcu_idle_enter_common(long long newval)
 			  current->pid, current->comm,
 			  idle->pid, idle->comm); /* must be idle task! */
 	}
-	rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+	rcu_sched_qs(); /* implies rcu_bh_inc() */
 	barrier();
 	rcu_dynticks_nesting = newval;
 }
@@ -217,7 +217,7 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
  * are at it, given that any rcu quiescent state is also an rcu_bh
  * quiescent state.  Use "+" instead of "||" to defeat short circuiting.
  */
-void rcu_sched_qs(int cpu)
+void rcu_sched_qs(void)
 {
 	unsigned long flags;
 
@@ -231,7 +231,7 @@ void rcu_sched_qs(int cpu)
 /*
  * Record an rcu_bh quiescent state.
  */
-void rcu_bh_qs(int cpu)
+void rcu_bh_qs(void)
 {
 	unsigned long flags;
 
@@ -251,9 +251,9 @@ void rcu_check_callbacks(int cpu, int user)
 {
 	RCU_TRACE(check_cpu_stalls());
 	if (user || rcu_is_cpu_rrupt_from_idle())
-		rcu_sched_qs(cpu);
+		rcu_sched_qs();
 	else if (!in_softirq())
-		rcu_bh_qs(cpu);
+		rcu_bh_qs();
 	if (user)
 		rcu_note_voluntary_context_switch(current);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index c880f5387b1f..4c340625ffd4 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -188,22 +188,24 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
  * one since the start of the grace period, this just sets a flag.
  * The caller must have disabled preemption.
  */
-void rcu_sched_qs(int cpu)
+void rcu_sched_qs(void)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
-
-	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period(TPS("rcu_sched"), rdp->gpnum, TPS("cpuqs"));
-	rdp->passed_quiesce = 1;
+	if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) {
+		trace_rcu_grace_period(TPS("rcu_sched"),
+				       __this_cpu_read(rcu_sched_data.gpnum),
+				       TPS("cpuqs"));
+		__this_cpu_write(rcu_sched_data.passed_quiesce, 1);
+	}
 }
 
-void rcu_bh_qs(int cpu)
+void rcu_bh_qs(void)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
-
-	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period(TPS("rcu_bh"), rdp->gpnum, TPS("cpuqs"));
-	rdp->passed_quiesce = 1;
+	if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) {
+		trace_rcu_grace_period(TPS("rcu_bh"),
+				       __this_cpu_read(rcu_bh_data.gpnum),
+				       TPS("cpuqs"));
+		__this_cpu_write(rcu_bh_data.passed_quiesce, 1);
+	}
 }
 
 static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
@@ -278,7 +280,7 @@ static void rcu_momentary_dyntick_idle(void)
 void rcu_note_context_switch(int cpu)
 {
 	trace_rcu_utilization(TPS("Start context switch"));
-	rcu_sched_qs(cpu);
+	rcu_sched_qs();
 	rcu_preempt_note_context_switch(cpu);
 	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
 		rcu_momentary_dyntick_idle();
@@ -2395,8 +2397,8 @@ void rcu_check_callbacks(int cpu, int user)
 		 * at least not while the corresponding CPU is online.
 		 */
 
-		rcu_sched_qs(cpu);
-		rcu_bh_qs(cpu);
+		rcu_sched_qs();
+		rcu_bh_qs();
 
 	} else if (!in_softirq()) {
 
@@ -2407,7 +2409,7 @@ void rcu_check_callbacks(int cpu, int user)
 		 * critical section, so note it.
 		 */
 
-		rcu_bh_qs(cpu);
+		rcu_bh_qs();
 	}
 	rcu_preempt_check_callbacks(cpu);
 	if (rcu_pending(cpu))
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 0981c0cd70fe..25e692a36280 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -158,14 +158,16 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed);
  * As with the other rcu_*_qs() functions, callers to this function
  * must disable preemption.
  */
-static void rcu_preempt_qs(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
-
-	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period(TPS("rcu_preempt"), rdp->gpnum, TPS("cpuqs"));
-	rdp->passed_quiesce = 1;
-	current->rcu_read_unlock_special.b.need_qs = false;
+static void rcu_preempt_qs(void)
+{
+	if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) {
+		trace_rcu_grace_period(TPS("rcu_preempt"),
+				       __this_cpu_read(rcu_preempt_data.gpnum),
+				       TPS("cpuqs"));
+		__this_cpu_write(rcu_preempt_data.passed_quiesce, 1);
+		barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
+		current->rcu_read_unlock_special.b.need_qs = false;
+	}
 }
 
 /*
@@ -256,7 +258,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	 * grace period, then the fact that the task has been enqueued
 	 * means that we continue to block the current grace period.
 	 */
-	rcu_preempt_qs(cpu);
+	rcu_preempt_qs();
 }
 
 /*
@@ -352,7 +354,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	 */
 	special = t->rcu_read_unlock_special;
 	if (special.b.need_qs) {
-		rcu_preempt_qs(smp_processor_id());
+		rcu_preempt_qs();
 		if (!t->rcu_read_unlock_special.s) {
 			local_irq_restore(flags);
 			return;
@@ -651,11 +653,12 @@ static void rcu_preempt_check_callbacks(int cpu)
 	struct task_struct *t = current;
 
 	if (t->rcu_read_lock_nesting == 0) {
-		rcu_preempt_qs(cpu);
+		rcu_preempt_qs();
 		return;
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
-	    per_cpu(rcu_preempt_data, cpu).qs_pending)
+	    per_cpu(rcu_preempt_data, cpu).qs_pending &&
+	    !per_cpu(rcu_preempt_data, cpu).passed_quiesce)
 		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 5918d227730f..348ec763b104 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -278,7 +278,7 @@ restart:
 		pending >>= softirq_bit;
 	}
 
-	rcu_bh_qs(smp_processor_id());
+	rcu_bh_qs();
 	local_irq_disable();
 
 	pending = local_softirq_pending();
-- 
cgit v1.2.3


From 908c7f1949cb7cc6e92ba8f18f2998e87e265b8e Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 8 Sep 2014 09:51:29 +0900
Subject: percpu_counter: add @gfp to percpu_counter_init()

Percpu allocator now supports allocation mask.  Add @gfp to
percpu_counter_init() so that !GFP_KERNEL allocation masks can be used
with percpu_counters too.

We could have left percpu_counter_init() alone and added
percpu_counter_init_gfp(); however, the number of users isn't that
high and introducing _gfp variants to all percpu data structures would
be quite ugly, so let's just do the conversion.  This is the one with
the most users.  Other percpu data structures are a lot easier to
convert.

This patch doesn't make any functional difference.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: "David S. Miller" <davem@davemloft.net>
Cc: x86@kernel.org
Cc: Jens Axboe <axboe@kernel.dk>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/kvm/mmu.c             |  2 +-
 fs/btrfs/disk-io.c             |  8 ++++----
 fs/btrfs/extent-tree.c         |  2 +-
 fs/ext2/super.c                |  6 +++---
 fs/ext3/super.c                |  6 +++---
 fs/ext4/super.c                | 14 +++++++++-----
 fs/file_table.c                |  2 +-
 fs/quota/dquot.c               |  2 +-
 fs/super.c                     |  3 ++-
 include/linux/percpu_counter.h | 10 ++++++----
 include/net/dst_ops.h          |  2 +-
 include/net/inet_frag.h        |  2 +-
 lib/flex_proportions.c         |  4 ++--
 lib/percpu_counter.c           |  4 ++--
 lib/proportions.c              |  6 +++---
 mm/backing-dev.c               |  2 +-
 mm/mmap.c                      |  2 +-
 mm/nommu.c                     |  2 +-
 mm/shmem.c                     |  2 +-
 net/dccp/proto.c               |  2 +-
 net/ipv4/tcp.c                 |  4 ++--
 net/ipv4/tcp_memcontrol.c      |  2 +-
 net/sctp/protocol.c            |  2 +-
 23 files changed, 49 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 931467881da7..5bd53f206f4f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4534,7 +4534,7 @@ int kvm_mmu_module_init(void)
 	if (!mmu_page_header_cache)
 		goto nomem;
 
-	if (percpu_counter_init(&kvm_total_used_mmu_pages, 0))
+	if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
 		goto nomem;
 
 	register_shrinker(&mmu_shrinker);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 08e65e9cf2aa..61dae01788d7 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1180,7 +1180,7 @@ static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
 	if (!writers)
 		return ERR_PTR(-ENOMEM);
 
-	ret = percpu_counter_init(&writers->counter, 0);
+	ret = percpu_counter_init(&writers->counter, 0, GFP_KERNEL);
 	if (ret < 0) {
 		kfree(writers);
 		return ERR_PTR(ret);
@@ -2185,7 +2185,7 @@ int open_ctree(struct super_block *sb,
 		goto fail_srcu;
 	}
 
-	ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0);
+	ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
 	if (ret) {
 		err = ret;
 		goto fail_bdi;
@@ -2193,13 +2193,13 @@ int open_ctree(struct super_block *sb,
 	fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE *
 					(1 + ilog2(nr_cpu_ids));
 
-	ret = percpu_counter_init(&fs_info->delalloc_bytes, 0);
+	ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL);
 	if (ret) {
 		err = ret;
 		goto fail_dirty_metadata_bytes;
 	}
 
-	ret = percpu_counter_init(&fs_info->bio_counter, 0);
+	ret = percpu_counter_init(&fs_info->bio_counter, 0, GFP_KERNEL);
 	if (ret) {
 		err = ret;
 		goto fail_delalloc_bytes;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 813537f362f9..94ec71eda86b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3493,7 +3493,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 	if (!found)
 		return -ENOMEM;
 
-	ret = percpu_counter_init(&found->total_bytes_pinned, 0);
+	ret = percpu_counter_init(&found->total_bytes_pinned, 0, GFP_KERNEL);
 	if (ret) {
 		kfree(found);
 		return ret;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index b88edc05c230..170dc41e8bf4 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1067,14 +1067,14 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	ext2_rsv_window_add(sb, &sbi->s_rsv_window_head);
 
 	err = percpu_counter_init(&sbi->s_freeblocks_counter,
-				ext2_count_free_blocks(sb));
+				ext2_count_free_blocks(sb), GFP_KERNEL);
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_freeinodes_counter,
-				ext2_count_free_inodes(sb));
+				ext2_count_free_inodes(sb), GFP_KERNEL);
 	}
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_dirs_counter,
-				ext2_count_dirs(sb));
+				ext2_count_dirs(sb), GFP_KERNEL);
 	}
 	if (err) {
 		ext2_msg(sb, KERN_ERR, "error: insufficient memory");
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 08cdfe5461e3..eba021b88440 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -2039,14 +2039,14 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 		goto failed_mount2;
 	}
 	err = percpu_counter_init(&sbi->s_freeblocks_counter,
-			ext3_count_free_blocks(sb));
+			ext3_count_free_blocks(sb), GFP_KERNEL);
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_freeinodes_counter,
-				ext3_count_free_inodes(sb));
+				ext3_count_free_inodes(sb), GFP_KERNEL);
 	}
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_dirs_counter,
-				ext3_count_dirs(sb));
+				ext3_count_dirs(sb), GFP_KERNEL);
 	}
 	if (err) {
 		ext3_msg(sb, KERN_ERR, "error: insufficient memory");
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 32b43ad154b9..e25ca8fdde7d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3891,7 +3891,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/* Register extent status tree shrinker */
 	ext4_es_register_shrinker(sbi);
 
-	if ((err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0)) != 0) {
+	err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0, GFP_KERNEL);
+	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
 		goto failed_mount3;
 	}
@@ -4105,17 +4106,20 @@ no_journal:
 	block = ext4_count_free_clusters(sb);
 	ext4_free_blocks_count_set(sbi->s_es, 
 				   EXT4_C2B(sbi, block));
-	err = percpu_counter_init(&sbi->s_freeclusters_counter, block);
+	err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
+				  GFP_KERNEL);
 	if (!err) {
 		unsigned long freei = ext4_count_free_inodes(sb);
 		sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
-		err = percpu_counter_init(&sbi->s_freeinodes_counter, freei);
+		err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
+					  GFP_KERNEL);
 	}
 	if (!err)
 		err = percpu_counter_init(&sbi->s_dirs_counter,
-					  ext4_count_dirs(sb));
+					  ext4_count_dirs(sb), GFP_KERNEL);
 	if (!err)
-		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
+		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
+					  GFP_KERNEL);
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
 		goto failed_mount6;
diff --git a/fs/file_table.c b/fs/file_table.c
index 385bfd31512a..0bab12b20460 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -331,5 +331,5 @@ void __init files_init(unsigned long mempages)
 
 	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
-	percpu_counter_init(&nr_files, 0);
+	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
 } 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index f2d0eee9d1f1..8b663b2d9562 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2725,7 +2725,7 @@ static int __init dquot_init(void)
 		panic("Cannot create dquot hash table");
 
 	for (i = 0; i < _DQST_DQSTAT_LAST; i++) {
-		ret = percpu_counter_init(&dqstats.counter[i], 0);
+		ret = percpu_counter_init(&dqstats.counter[i], 0, GFP_KERNEL);
 		if (ret)
 			panic("Cannot create dquot stat counters");
 	}
diff --git a/fs/super.c b/fs/super.c
index b9a214d2fe98..1b836107acee 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -175,7 +175,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 		goto fail;
 
 	for (i = 0; i < SB_FREEZE_LEVELS; i++) {
-		if (percpu_counter_init(&s->s_writers.counter[i], 0) < 0)
+		if (percpu_counter_init(&s->s_writers.counter[i], 0,
+					GFP_KERNEL) < 0)
 			goto fail;
 		lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i],
 				 &type->s_writers_key[i], 0);
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index d5dd4657c8d6..50e50095c8d1 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -12,6 +12,7 @@
 #include <linux/threads.h>
 #include <linux/percpu.h>
 #include <linux/types.h>
+#include <linux/gfp.h>
 
 #ifdef CONFIG_SMP
 
@@ -26,14 +27,14 @@ struct percpu_counter {
 
 extern int percpu_counter_batch;
 
-int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
+int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
 			  struct lock_class_key *key);
 
-#define percpu_counter_init(fbc, value)					\
+#define percpu_counter_init(fbc, value, gfp)				\
 	({								\
 		static struct lock_class_key __key;			\
 									\
-		__percpu_counter_init(fbc, value, &__key);		\
+		__percpu_counter_init(fbc, value, gfp, &__key);		\
 	})
 
 void percpu_counter_destroy(struct percpu_counter *fbc);
@@ -89,7 +90,8 @@ struct percpu_counter {
 	s64 count;
 };
 
-static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount)
+static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount,
+				      gfp_t gfp)
 {
 	fbc->count = amount;
 	return 0;
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 2f26dfb8450e..1f99a1de0e4f 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -63,7 +63,7 @@ static inline void dst_entries_add(struct dst_ops *dst, int val)
 
 static inline int dst_entries_init(struct dst_ops *dst)
 {
-	return percpu_counter_init(&dst->pcpuc_entries, 0);
+	return percpu_counter_init(&dst->pcpuc_entries, 0, GFP_KERNEL);
 }
 
 static inline void dst_entries_destroy(struct dst_ops *dst)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 65a8855e99fe..8d1765577acc 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -151,7 +151,7 @@ static inline void add_frag_mem_limit(struct inet_frag_queue *q, int i)
 
 static inline void init_frag_mem_limit(struct netns_frags *nf)
 {
-	percpu_counter_init(&nf->mem, 0);
+	percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
 }
 
 static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c
index ebf3bac460b0..b9d026bfcf38 100644
--- a/lib/flex_proportions.c
+++ b/lib/flex_proportions.c
@@ -40,7 +40,7 @@ int fprop_global_init(struct fprop_global *p)
 
 	p->period = 0;
 	/* Use 1 to avoid dealing with periods with 0 events... */
-	err = percpu_counter_init(&p->events, 1);
+	err = percpu_counter_init(&p->events, 1, GFP_KERNEL);
 	if (err)
 		return err;
 	seqcount_init(&p->sequence);
@@ -172,7 +172,7 @@ int fprop_local_init_percpu(struct fprop_local_percpu *pl)
 {
 	int err;
 
-	err = percpu_counter_init(&pl->events, 0);
+	err = percpu_counter_init(&pl->events, 0, GFP_KERNEL);
 	if (err)
 		return err;
 	pl->period = 0;
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 3fde78275cd1..48144cdae819 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -112,7 +112,7 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
 }
 EXPORT_SYMBOL(__percpu_counter_sum);
 
-int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
+int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
 			  struct lock_class_key *key)
 {
 	unsigned long flags __maybe_unused;
@@ -120,7 +120,7 @@ int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
 	raw_spin_lock_init(&fbc->lock);
 	lockdep_set_class(&fbc->lock, key);
 	fbc->count = amount;
-	fbc->counters = alloc_percpu(s32);
+	fbc->counters = alloc_percpu_gfp(s32, gfp);
 	if (!fbc->counters)
 		return -ENOMEM;
 
diff --git a/lib/proportions.c b/lib/proportions.c
index 05df84801b56..ca95f8d54384 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -83,11 +83,11 @@ int prop_descriptor_init(struct prop_descriptor *pd, int shift)
 	pd->index = 0;
 	pd->pg[0].shift = shift;
 	mutex_init(&pd->mutex);
-	err = percpu_counter_init(&pd->pg[0].events, 0);
+	err = percpu_counter_init(&pd->pg[0].events, 0, GFP_KERNEL);
 	if (err)
 		goto out;
 
-	err = percpu_counter_init(&pd->pg[1].events, 0);
+	err = percpu_counter_init(&pd->pg[1].events, 0, GFP_KERNEL);
 	if (err)
 		percpu_counter_destroy(&pd->pg[0].events);
 
@@ -193,7 +193,7 @@ int prop_local_init_percpu(struct prop_local_percpu *pl)
 	raw_spin_lock_init(&pl->lock);
 	pl->shift = 0;
 	pl->period = 0;
-	return percpu_counter_init(&pl->events, 0);
+	return percpu_counter_init(&pl->events, 0, GFP_KERNEL);
 }
 
 void prop_local_destroy_percpu(struct prop_local_percpu *pl)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1706cbbdf5f0..f19a818be2d3 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -455,7 +455,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi_wb_init(&bdi->wb, bdi);
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
-		err = percpu_counter_init(&bdi->bdi_stat[i], 0);
+		err = percpu_counter_init(&bdi->bdi_stat[i], 0, GFP_KERNEL);
 		if (err)
 			goto err;
 	}
diff --git a/mm/mmap.c b/mm/mmap.c
index c1f2ea4a0b99..d7ec93e25fa1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3196,7 +3196,7 @@ void __init mmap_init(void)
 {
 	int ret;
 
-	ret = percpu_counter_init(&vm_committed_as, 0);
+	ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
 	VM_BUG_ON(ret);
 }
 
diff --git a/mm/nommu.c b/mm/nommu.c
index a881d9673c6b..bd1808e194a7 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -539,7 +539,7 @@ void __init mmap_init(void)
 {
 	int ret;
 
-	ret = percpu_counter_init(&vm_committed_as, 0);
+	ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
 	VM_BUG_ON(ret);
 	vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index 0e5fb225007c..d4bc55d3f107 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2993,7 +2993,7 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
 #endif
 
 	spin_lock_init(&sbinfo->stat_lock);
-	if (percpu_counter_init(&sbinfo->used_blocks, 0))
+	if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL))
 		goto failed;
 	sbinfo->free_inodes = sbinfo->max_inodes;
 
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index de2c1e719305..e421eddf67b4 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1115,7 +1115,7 @@ static int __init dccp_init(void)
 
 	BUILD_BUG_ON(sizeof(struct dccp_skb_cb) >
 		     FIELD_SIZEOF(struct sk_buff, cb));
-	rc = percpu_counter_init(&dccp_orphan_count, 0);
+	rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL);
 	if (rc)
 		goto out_fail;
 	rc = -ENOBUFS;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 541f26a67ba2..d59c2604c247 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3188,8 +3188,8 @@ void __init tcp_init(void)
 
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
-	percpu_counter_init(&tcp_sockets_allocated, 0);
-	percpu_counter_init(&tcp_orphan_count, 0);
+	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
+	percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
 	tcp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("tcp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 3af522622fad..1d191357bf88 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -32,7 +32,7 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 		res_parent = &parent_cg->memory_allocated;
 
 	res_counter_init(&cg_proto->memory_allocated, res_parent);
-	percpu_counter_init(&cg_proto->sockets_allocated, 0);
+	percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL);
 
 	return 0;
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6240834f4b95..f00a85a3fddd 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1341,7 +1341,7 @@ static __init int sctp_init(void)
 	if (!sctp_chunk_cachep)
 		goto err_chunk_cachep;
 
-	status = percpu_counter_init(&sctp_sockets_allocated, 0);
+	status = percpu_counter_init(&sctp_sockets_allocated, 0, GFP_KERNEL);
 	if (status)
 		goto err_percpu_counter_init;
 
-- 
cgit v1.2.3


From 20ae00792c6f1f18fc4fc5965445a145df92827e Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 8 Sep 2014 09:51:30 +0900
Subject: proportions: add @gfp to init functions

Percpu allocator now supports allocation mask.  Add @gfp to
[flex_]proportions init functions so that !GFP_KERNEL allocation masks
can be used with them too.

This patch doesn't make any functional difference.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Peter Zijlstra <peterz@infradead.org>
---
 include/linux/flex_proportions.h |  5 +++--
 include/linux/proportions.h      |  5 +++--
 lib/flex_proportions.c           |  8 ++++----
 lib/proportions.c                | 10 +++++-----
 mm/backing-dev.c                 |  2 +-
 mm/page-writeback.c              |  2 +-
 6 files changed, 17 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/flex_proportions.h b/include/linux/flex_proportions.h
index 4ebc49fae391..0d348e011a6e 100644
--- a/include/linux/flex_proportions.h
+++ b/include/linux/flex_proportions.h
@@ -10,6 +10,7 @@
 #include <linux/percpu_counter.h>
 #include <linux/spinlock.h>
 #include <linux/seqlock.h>
+#include <linux/gfp.h>
 
 /*
  * When maximum proportion of some event type is specified, this is the
@@ -32,7 +33,7 @@ struct fprop_global {
 	seqcount_t sequence;
 };
 
-int fprop_global_init(struct fprop_global *p);
+int fprop_global_init(struct fprop_global *p, gfp_t gfp);
 void fprop_global_destroy(struct fprop_global *p);
 bool fprop_new_period(struct fprop_global *p, int periods);
 
@@ -79,7 +80,7 @@ struct fprop_local_percpu {
 	raw_spinlock_t lock;	/* Protect period and numerator */
 };
 
-int fprop_local_init_percpu(struct fprop_local_percpu *pl);
+int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp);
 void fprop_local_destroy_percpu(struct fprop_local_percpu *pl);
 void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl);
 void __fprop_inc_percpu_max(struct fprop_global *p, struct fprop_local_percpu *pl,
diff --git a/include/linux/proportions.h b/include/linux/proportions.h
index 26a8a4ed9b07..00e8e8fa7358 100644
--- a/include/linux/proportions.h
+++ b/include/linux/proportions.h
@@ -12,6 +12,7 @@
 #include <linux/percpu_counter.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/gfp.h>
 
 struct prop_global {
 	/*
@@ -40,7 +41,7 @@ struct prop_descriptor {
 	struct mutex mutex;		/* serialize the prop_global switch */
 };
 
-int prop_descriptor_init(struct prop_descriptor *pd, int shift);
+int prop_descriptor_init(struct prop_descriptor *pd, int shift, gfp_t gfp);
 void prop_change_shift(struct prop_descriptor *pd, int new_shift);
 
 /*
@@ -61,7 +62,7 @@ struct prop_local_percpu {
 	raw_spinlock_t lock;		/* protect the snapshot state */
 };
 
-int prop_local_init_percpu(struct prop_local_percpu *pl);
+int prop_local_init_percpu(struct prop_local_percpu *pl, gfp_t gfp);
 void prop_local_destroy_percpu(struct prop_local_percpu *pl);
 void __prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl);
 void prop_fraction_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl,
diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c
index b9d026bfcf38..8f25652f40d4 100644
--- a/lib/flex_proportions.c
+++ b/lib/flex_proportions.c
@@ -34,13 +34,13 @@
  */
 #include <linux/flex_proportions.h>
 
-int fprop_global_init(struct fprop_global *p)
+int fprop_global_init(struct fprop_global *p, gfp_t gfp)
 {
 	int err;
 
 	p->period = 0;
 	/* Use 1 to avoid dealing with periods with 0 events... */
-	err = percpu_counter_init(&p->events, 1, GFP_KERNEL);
+	err = percpu_counter_init(&p->events, 1, gfp);
 	if (err)
 		return err;
 	seqcount_init(&p->sequence);
@@ -168,11 +168,11 @@ void fprop_fraction_single(struct fprop_global *p,
  */
 #define PROP_BATCH (8*(1+ilog2(nr_cpu_ids)))
 
-int fprop_local_init_percpu(struct fprop_local_percpu *pl)
+int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp)
 {
 	int err;
 
-	err = percpu_counter_init(&pl->events, 0, GFP_KERNEL);
+	err = percpu_counter_init(&pl->events, 0, gfp);
 	if (err)
 		return err;
 	pl->period = 0;
diff --git a/lib/proportions.c b/lib/proportions.c
index ca95f8d54384..6f724298f67a 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -73,7 +73,7 @@
 #include <linux/proportions.h>
 #include <linux/rcupdate.h>
 
-int prop_descriptor_init(struct prop_descriptor *pd, int shift)
+int prop_descriptor_init(struct prop_descriptor *pd, int shift, gfp_t gfp)
 {
 	int err;
 
@@ -83,11 +83,11 @@ int prop_descriptor_init(struct prop_descriptor *pd, int shift)
 	pd->index = 0;
 	pd->pg[0].shift = shift;
 	mutex_init(&pd->mutex);
-	err = percpu_counter_init(&pd->pg[0].events, 0, GFP_KERNEL);
+	err = percpu_counter_init(&pd->pg[0].events, 0, gfp);
 	if (err)
 		goto out;
 
-	err = percpu_counter_init(&pd->pg[1].events, 0, GFP_KERNEL);
+	err = percpu_counter_init(&pd->pg[1].events, 0, gfp);
 	if (err)
 		percpu_counter_destroy(&pd->pg[0].events);
 
@@ -188,12 +188,12 @@ prop_adjust_shift(int *pl_shift, unsigned long *pl_period, int new_shift)
 
 #define PROP_BATCH (8*(1+ilog2(nr_cpu_ids)))
 
-int prop_local_init_percpu(struct prop_local_percpu *pl)
+int prop_local_init_percpu(struct prop_local_percpu *pl, gfp_t gfp)
 {
 	raw_spin_lock_init(&pl->lock);
 	pl->shift = 0;
 	pl->period = 0;
-	return percpu_counter_init(&pl->events, 0, GFP_KERNEL);
+	return percpu_counter_init(&pl->events, 0, gfp);
 }
 
 void prop_local_destroy_percpu(struct prop_local_percpu *pl)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f19a818be2d3..64ec49d1772b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -470,7 +470,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->write_bandwidth = INIT_BW;
 	bdi->avg_write_bandwidth = INIT_BW;
 
-	err = fprop_local_init_percpu(&bdi->completions);
+	err = fprop_local_init_percpu(&bdi->completions, GFP_KERNEL);
 
 	if (err) {
 err:
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 91d73ef1744d..508599403721 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1777,7 +1777,7 @@ void __init page_writeback_init(void)
 	writeback_set_ratelimit();
 	register_cpu_notifier(&ratelimit_nb);
 
-	fprop_global_init(&writeout_completions);
+	fprop_global_init(&writeout_completions, GFP_KERNEL);
 }
 
 /**
-- 
cgit v1.2.3


From a34375ef9e65340a138fc0be287de5c940d260fc Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 8 Sep 2014 09:51:30 +0900
Subject: percpu-refcount: add @gfp to percpu_ref_init()

Percpu allocator now supports allocation mask.  Add @gfp to
percpu_ref_init() so that !GFP_KERNEL allocation masks can be used
with percpu_refs too.

This patch doesn't make any functional difference.

v2: blk-mq conversion was missing.  Updated.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <koverstreet@google.com>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Nicholas A. Bellinger <nab@linux-iscsi.org>
Cc: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c                   | 3 ++-
 drivers/target/target_core_tpg.c | 3 ++-
 fs/aio.c                         | 4 ++--
 include/linux/percpu-refcount.h  | 3 ++-
 kernel/cgroup.c                  | 6 +++---
 lib/percpu-refcount.c            | 6 ++++--
 6 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5189cb1e478a..702df07b980d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1776,7 +1776,8 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	if (!q)
 		goto err_hctxs;
 
-	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release))
+	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
+			    GFP_KERNEL))
 		goto err_map;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index fddfae61222f..4ab6da338585 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -819,7 +819,8 @@ int core_tpg_add_lun(
 {
 	int ret;
 
-	ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release);
+	ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release,
+			      GFP_KERNEL);
 	if (ret < 0)
 		return ret;
 
diff --git a/fs/aio.c b/fs/aio.c
index bd7ec2cc2674..93fbcc0f5696 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -666,10 +666,10 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 
 	INIT_LIST_HEAD(&ctx->active_reqs);
 
-	if (percpu_ref_init(&ctx->users, free_ioctx_users))
+	if (percpu_ref_init(&ctx->users, free_ioctx_users, GFP_KERNEL))
 		goto err;
 
-	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs))
+	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs, GFP_KERNEL))
 		goto err;
 
 	ctx->cpu = alloc_percpu(struct kioctx_cpu);
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 3dfbf237cd8f..ee8325122dbd 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -49,6 +49,7 @@
 #include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/rcupdate.h>
+#include <linux/gfp.h>
 
 struct percpu_ref;
 typedef void (percpu_ref_func_t)(struct percpu_ref *);
@@ -66,7 +67,7 @@ struct percpu_ref {
 };
 
 int __must_check percpu_ref_init(struct percpu_ref *ref,
-				 percpu_ref_func_t *release);
+				 percpu_ref_func_t *release, gfp_t gfp);
 void percpu_ref_reinit(struct percpu_ref *ref);
 void percpu_ref_exit(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 7dc8788cfd52..589b4d89a0a5 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1628,7 +1628,7 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned int ss_mask)
 		goto out;
 	root_cgrp->id = ret;
 
-	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release);
+	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, GFP_KERNEL);
 	if (ret)
 		goto out;
 
@@ -4487,7 +4487,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
 
 	init_and_link_css(css, ss, cgrp);
 
-	err = percpu_ref_init(&css->refcnt, css_release);
+	err = percpu_ref_init(&css->refcnt, css_release, GFP_KERNEL);
 	if (err)
 		goto err_free_css;
 
@@ -4555,7 +4555,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 		goto out_unlock;
 	}
 
-	ret = percpu_ref_init(&cgrp->self.refcnt, css_release);
+	ret = percpu_ref_init(&cgrp->self.refcnt, css_release, GFP_KERNEL);
 	if (ret)
 		goto out_free_cgrp;
 
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index fe5a3342e960..ff9903264a91 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -40,6 +40,7 @@ static unsigned __percpu *pcpu_count_ptr(struct percpu_ref *ref)
  * percpu_ref_init - initialize a percpu refcount
  * @ref: percpu_ref to initialize
  * @release: function which will be called when refcount hits 0
+ * @gfp: allocation mask to use
  *
  * Initializes the refcount in single atomic counter mode with a refcount of 1;
  * analagous to atomic_set(ref, 1).
@@ -47,11 +48,12 @@ static unsigned __percpu *pcpu_count_ptr(struct percpu_ref *ref)
  * Note that @release must not sleep - it may potentially be called from RCU
  * callback context by percpu_ref_kill().
  */
-int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release)
+int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
+		    gfp_t gfp)
 {
 	atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);
 
-	ref->pcpu_count_ptr = (unsigned long)alloc_percpu(unsigned);
+	ref->pcpu_count_ptr = (unsigned long)alloc_percpu_gfp(unsigned, gfp);
 	if (!ref->pcpu_count_ptr)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From e78c3496790ee8a36522a838b59b388e8a709e65 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Sat, 16 Aug 2014 13:40:10 -0400
Subject: time, signal: Protect resource use statistics with seqlock

Both times() and clock_gettime(CLOCK_PROCESS_CPUTIME_ID) have scalability
issues on large systems, due to both functions being serialized with a
lock.

The lock protects against reporting a wrong value, due to a thread in the
task group exiting, its statistics reporting up to the signal struct, and
that exited task's statistics being counted twice (or not at all).

Protecting that with a lock results in times() and clock_gettime() being
completely serialized on large systems.

This can be fixed by using a seqlock around the events that gather and
propagate statistics. As an additional benefit, the protection code can
be moved into thread_group_cputime(), slightly simplifying the calling
functions.

In the case of posix_cpu_clock_get_task() things can be simplified a
lot, because the calling function already ensures that the task sticks
around, and the rest is now taken care of in thread_group_cputime().

This way the statistics reporting code can run lockless.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alex Thorlton <athorlton@sgi.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Daeseok Youn <daeseok.youn@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Guillaume Morin <guillaume@morinfr.org>
Cc: Ionut Alexa <ionut.m.alexa@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Michal Schmidt <mschmidt@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: umgwanakikbuti@gmail.com
Cc: fweisbec@gmail.com
Cc: srao@redhat.com
Cc: lwoodman@redhat.com
Cc: atheurer@redhat.com
Link: http://lkml.kernel.org/r/20140816134010.26a9b572@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h          |  1 +
 kernel/exit.c                  |  4 ++++
 kernel/fork.c                  |  1 +
 kernel/sched/cputime.c         | 33 ++++++++++++++++++++-------------
 kernel/sys.c                   |  2 --
 kernel/time/posix-cpu-timers.c | 14 --------------
 6 files changed, 26 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c2c885ee52b..dd9eb4807389 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -645,6 +645,7 @@ struct signal_struct {
 	 * Live threads maintain their own counters and add to these
 	 * in __exit_signal, except for the group leader.
 	 */
+	seqlock_t stats_lock;
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
diff --git a/kernel/exit.c b/kernel/exit.c
index b93d46dab6fc..fa09b86609db 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -127,6 +127,7 @@ static void __exit_signal(struct task_struct *tsk)
 	 * the signal_struct.
 	 */
 	task_cputime(tsk, &utime, &stime);
+	write_seqlock(&sig->stats_lock);
 	sig->utime += utime;
 	sig->stime += stime;
 	sig->gtime += task_gtime(tsk);
@@ -140,6 +141,7 @@ static void __exit_signal(struct task_struct *tsk)
 	sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 	sig->nr_threads--;
 	__unhash_process(tsk, group_dead);
+	write_sequnlock(&sig->stats_lock);
 
 	/*
 	 * Do this under ->siglock, we can race with another thread
@@ -1042,6 +1044,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		spin_lock_irq(&p->real_parent->sighand->siglock);
 		psig = p->real_parent->signal;
 		sig = p->signal;
+		write_seqlock(&psig->stats_lock);
 		psig->cutime += tgutime + sig->cutime;
 		psig->cstime += tgstime + sig->cstime;
 		psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
@@ -1064,6 +1067,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 			psig->cmaxrss = maxrss;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
+		write_sequnlock(&psig->stats_lock);
 		spin_unlock_irq(&p->real_parent->sighand->siglock);
 	}
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 0cf9cdb6e491..9387ae8ab048 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1068,6 +1068,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
 	INIT_LIST_HEAD(&sig->posix_timers);
+	seqlock_init(&sig->stats_lock);
 
 	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	sig->real_timer.function = it_real_fn;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 3e52836359ba..49b7cfe98f7a 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -288,18 +288,28 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 	struct signal_struct *sig = tsk->signal;
 	cputime_t utime, stime;
 	struct task_struct *t;
-
-	times->utime = sig->utime;
-	times->stime = sig->stime;
-	times->sum_exec_runtime = sig->sum_sched_runtime;
+	unsigned int seq, nextseq;
 
 	rcu_read_lock();
-	for_each_thread(tsk, t) {
-		task_cputime(t, &utime, &stime);
-		times->utime += utime;
-		times->stime += stime;
-		times->sum_exec_runtime += task_sched_runtime(t);
-	}
+	/* Attempt a lockless read on the first round. */
+	nextseq = 0;
+	do {
+		seq = nextseq;
+		read_seqbegin_or_lock(&sig->stats_lock, &seq);
+		times->utime = sig->utime;
+		times->stime = sig->stime;
+		times->sum_exec_runtime = sig->sum_sched_runtime;
+
+		for_each_thread(tsk, t) {
+			task_cputime(t, &utime, &stime);
+			times->utime += utime;
+			times->stime += stime;
+			times->sum_exec_runtime += task_sched_runtime(t);
+		}
+		/* If lockless access failed, take the lock. */
+		nextseq = 1;
+	} while (need_seqretry(&sig->stats_lock, seq));
+	done_seqretry(&sig->stats_lock, seq);
 	rcu_read_unlock();
 }
 
@@ -611,9 +621,6 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 
-/*
- * Must be called with siglock held.
- */
 void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	struct task_cputime cputime;
diff --git a/kernel/sys.c b/kernel/sys.c
index ce8129192a26..b6636643cbd1 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -862,11 +862,9 @@ void do_sys_times(struct tms *tms)
 {
 	cputime_t tgutime, tgstime, cutime, cstime;
 
-	spin_lock_irq(&current->sighand->siglock);
 	thread_group_cputime_adjusted(current, &tgutime, &tgstime);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
-	spin_unlock_irq(&current->sighand->siglock);
 	tms->tms_utime = cputime_to_clock_t(tgutime);
 	tms->tms_stime = cputime_to_clock_t(tgstime);
 	tms->tms_cutime = cputime_to_clock_t(cutime);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 3b8946416a5f..492b986195d5 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -272,22 +272,8 @@ static int posix_cpu_clock_get_task(struct task_struct *tsk,
 		if (same_thread_group(tsk, current))
 			err = cpu_clock_sample(which_clock, tsk, &rtn);
 	} else {
-		unsigned long flags;
-		struct sighand_struct *sighand;
-
-		/*
-		 * while_each_thread() is not yet entirely RCU safe,
-		 * keep locking the group while sampling process
-		 * clock for now.
-		 */
-		sighand = lock_task_sighand(tsk, &flags);
-		if (!sighand)
-			return err;
-
 		if (tsk == current || thread_group_leader(tsk))
 			err = cpu_clock_sample_group(which_clock, tsk, &rtn);
-
-		unlock_task_sighand(tsk, &flags);
 	}
 
 	if (!err)
-- 
cgit v1.2.3


From 0b750b3baa2d64f1b77aecc10f20deeb28efe60d Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 5 Sep 2014 18:08:47 +0200
Subject: HID: usbhid: add always-poll quirk

Add quirk to make sure that a device is always polled for input events
even if it hasn't been opened.

This is needed for devices that disconnects from the bus unless the
interrupt endpoint has been polled at least once or when not responding
to an input event (e.g. after having shut down X).

Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/usbhid/hid-core.c | 26 +++++++++++++++++++++++---
 include/linux/hid.h           |  1 +
 2 files changed, 24 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 79cf503e37bf..ddd547ad6d7e 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -82,7 +82,7 @@ static int hid_start_in(struct hid_device *hid)
 	struct usbhid_device *usbhid = hid->driver_data;
 
 	spin_lock_irqsave(&usbhid->lock, flags);
-	if (hid->open > 0 &&
+	if ((hid->open > 0 || hid->quirks & HID_QUIRK_ALWAYS_POLL) &&
 			!test_bit(HID_DISCONNECTED, &usbhid->iofl) &&
 			!test_bit(HID_SUSPENDED, &usbhid->iofl) &&
 			!test_and_set_bit(HID_IN_RUNNING, &usbhid->iofl)) {
@@ -292,6 +292,8 @@ static void hid_irq_in(struct urb *urb)
 	case 0:			/* success */
 		usbhid_mark_busy(usbhid);
 		usbhid->retry_delay = 0;
+		if ((hid->quirks & HID_QUIRK_ALWAYS_POLL) && !hid->open)
+			break;
 		hid_input_report(urb->context, HID_INPUT_REPORT,
 				 urb->transfer_buffer,
 				 urb->actual_length, 1);
@@ -735,8 +737,10 @@ void usbhid_close(struct hid_device *hid)
 	if (!--hid->open) {
 		spin_unlock_irq(&usbhid->lock);
 		hid_cancel_delayed_stuff(usbhid);
-		usb_kill_urb(usbhid->urbin);
-		usbhid->intf->needs_remote_wakeup = 0;
+		if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) {
+			usb_kill_urb(usbhid->urbin);
+			usbhid->intf->needs_remote_wakeup = 0;
+		}
 	} else {
 		spin_unlock_irq(&usbhid->lock);
 	}
@@ -1134,6 +1138,19 @@ static int usbhid_start(struct hid_device *hid)
 
 	set_bit(HID_STARTED, &usbhid->iofl);
 
+	if (hid->quirks & HID_QUIRK_ALWAYS_POLL) {
+		ret = usb_autopm_get_interface(usbhid->intf);
+		if (ret)
+			goto fail;
+		usbhid->intf->needs_remote_wakeup = 1;
+		ret = hid_start_in(hid);
+		if (ret) {
+			dev_err(&hid->dev,
+				"failed to start in urb: %d\n", ret);
+		}
+		usb_autopm_put_interface(usbhid->intf);
+	}
+
 	/* Some keyboards don't work until their LEDs have been set.
 	 * Since BIOSes do set the LEDs, it must be safe for any device
 	 * that supports the keyboard boot protocol.
@@ -1166,6 +1183,9 @@ static void usbhid_stop(struct hid_device *hid)
 	if (WARN_ON(!usbhid))
 		return;
 
+	if (hid->quirks & HID_QUIRK_ALWAYS_POLL)
+		usbhid->intf->needs_remote_wakeup = 0;
+
 	clear_bit(HID_STARTED, &usbhid->iofl);
 	spin_lock_irq(&usbhid->lock);	/* Sync with error and led handlers */
 	set_bit(HID_DISCONNECTED, &usbhid->iofl);
diff --git a/include/linux/hid.h b/include/linux/hid.h
index f53c4a9cca1d..26ee25fced27 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -287,6 +287,7 @@ struct hid_item {
 #define HID_QUIRK_HIDINPUT_FORCE		0x00000080
 #define HID_QUIRK_NO_EMPTY_INPUT		0x00000100
 #define HID_QUIRK_NO_INIT_INPUT_REPORTS		0x00000200
+#define HID_QUIRK_ALWAYS_POLL			0x00000400
 #define HID_QUIRK_SKIP_OUTPUT_REPORTS		0x00010000
 #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID		0x00020000
 #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP	0x00040000
-- 
cgit v1.2.3


From c8d6591752e96c550cb98b781326d72d8eedcc79 Mon Sep 17 00:00:00 2001
From: "Steinar H. Gunderson" <sgunderson@bigfoot.com>
Date: Wed, 3 Sep 2014 06:48:37 -0700
Subject: mac80211: support DTPC IE (from Cisco Client eXtensions)

Linux already supports 802.11h, where the access point can tell the
client to reduce its transmission power. However, 802.11h is only
defined for 5 GHz, where the need for this is much smaller than on
2.4 GHz.

Cisco has their own solution, called DTPC (Dynamic Transmit Power
Control). Cisco APs on a controller sometimes but not always send
802.11h; they always send DTPC, even on 2.4 GHz. This patch adds support
for parsing and honoring the DTPC IE in addition to the 802.11h
element (they do not always contain the same limits, so both must
be honored); the format is not documented, but very simple.

Tested (on top of wireless.git and on 3.16.1) against a Cisco Aironet
1142 joined to a Cisco 2504 WLC, by setting various transmit power
levels for the given access points and observing the results.
The Wireshark 802.11 dissector agrees with the interpretation of the
element, except for negative numbers, which seem to never happen
anyway.

Signed-off-by: Steinar H. Gunderson <sgunderson@bigfoot.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 include/linux/ieee80211.h  |  3 ++-
 net/mac80211/ieee80211_i.h |  1 +
 net/mac80211/mlme.c        | 60 +++++++++++++++++++++++++++++++++++++---------
 net/mac80211/util.c        | 25 +++++++++++++++++++
 4 files changed, 77 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 77d4f26e0235..61a09f0644aa 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1824,7 +1824,8 @@ enum ieee80211_eid {
 	WLAN_EID_DMG_TSPEC = 146,
 	WLAN_EID_DMG_AT = 147,
 	WLAN_EID_DMG_CAP = 148,
-	/* 149-150 reserved for Cisco */
+	/* 149 reserved for Cisco */
+	WLAN_EID_CISCO_VENDOR_SPECIFIC = 150,
 	WLAN_EID_DMG_OPERATION = 151,
 	WLAN_EID_DMG_BSS_PARAM_CHANGE = 152,
 	WLAN_EID_DMG_BEAM_REFINEMENT = 153,
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 6b7bdd8fae29..c2aaec4dfcf0 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1369,6 +1369,7 @@ struct ieee802_11_elems {
 	const struct ieee80211_wide_bw_chansw_ie *wide_bw_chansw_ie;
 	const u8 *country_elem;
 	const u8 *pwr_constr_elem;
+	const u8 *cisco_dtpc_elem;
 	const struct ieee80211_timeout_interval_ie *timeout_int;
 	const u8 *opmode_notif;
 	const struct ieee80211_sec_chan_offs_ie *sec_chan_offs;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 0b812a88f95f..a7b92f5f7161 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1230,14 +1230,30 @@ ieee80211_find_80211h_pwr_constr(struct ieee80211_sub_if_data *sdata,
 	return have_chan_pwr;
 }
 
+static void ieee80211_find_cisco_dtpc(struct ieee80211_sub_if_data *sdata,
+				      struct ieee80211_channel *channel,
+				      const u8 *cisco_dtpc_ie,
+				      int *pwr_level)
+{
+	/* From practical testing, the first data byte of the DTPC element
+	 * seems to contain the requested dBm level, and the CLI on Cisco
+	 * APs clearly state the range is -127 to 127 dBm, which indicates
+	 * a signed byte, although it seemingly never actually goes negative.
+	 * The other byte seems to always be zero.
+	 */
+	*pwr_level = (__s8)cisco_dtpc_ie[4];
+}
+
 static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
 				       struct ieee80211_channel *channel,
 				       struct ieee80211_mgmt *mgmt,
 				       const u8 *country_ie, u8 country_ie_len,
-				       const u8 *pwr_constr_ie)
+				       const u8 *pwr_constr_ie,
+				       const u8 *cisco_dtpc_ie)
 {
-	bool has_80211h_pwr = false;
-	int chan_pwr, pwr_reduction_80211h;
+	bool has_80211h_pwr = false, has_cisco_pwr = false;
+	int chan_pwr = 0, pwr_reduction_80211h = 0;
+	int pwr_level_cisco, pwr_level_80211h;
 	int new_ap_level;
 
 	if (country_ie && pwr_constr_ie &&
@@ -1246,16 +1262,35 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
 		has_80211h_pwr = ieee80211_find_80211h_pwr_constr(
 			sdata, channel, country_ie, country_ie_len,
 			pwr_constr_ie, &chan_pwr, &pwr_reduction_80211h);
-		new_ap_level = max_t(int, 0, chan_pwr - pwr_reduction_80211h);
+		pwr_level_80211h =
+			max_t(int, 0, chan_pwr - pwr_reduction_80211h);
+	}
+
+	if (cisco_dtpc_ie) {
+		ieee80211_find_cisco_dtpc(
+			sdata, channel, cisco_dtpc_ie, &pwr_level_cisco);
+		has_cisco_pwr = true;
 	}
 
-	if (!has_80211h_pwr)
+	if (!has_80211h_pwr && !has_cisco_pwr)
 		return 0;
 
-	sdata_info(sdata,
-		   "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n",
-		   new_ap_level, chan_pwr, pwr_reduction_80211h,
-		   sdata->u.mgd.bssid);
+	/* If we have both 802.11h and Cisco DTPC, apply both limits
+	 * by picking the smallest of the two power levels advertised.
+	 */
+	if (has_80211h_pwr &&
+	    (!has_cisco_pwr || pwr_level_80211h <= pwr_level_cisco)) {
+		sdata_info(sdata,
+			   "Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n",
+			   pwr_level_80211h, chan_pwr, pwr_reduction_80211h,
+			   sdata->u.mgd.bssid);
+		new_ap_level = pwr_level_80211h;
+	} else {  /* has_cisco_pwr is always true here. */
+		sdata_info(sdata,
+			   "Limiting TX power to %d dBm as advertised by %pM\n",
+			   pwr_level_cisco, sdata->u.mgd.bssid);
+		new_ap_level = pwr_level_cisco;
+	}
 
 	if (sdata->ap_power_level == new_ap_level)
 		return 0;
@@ -2923,7 +2958,9 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata,
 /*
  * This is the canonical list of information elements we care about,
  * the filter code also gives us all changes to the Microsoft OUI
- * (00:50:F2) vendor IE which is used for WMM which we need to track.
+ * (00:50:F2) vendor IE which is used for WMM which we need to track,
+ * as well as the DTPC IE (part of the Cisco OUI) used for signaling
+ * changes to requested client power.
  *
  * We implement beacon filtering in software since that means we can
  * avoid processing the frame here and in cfg80211, and userspace
@@ -3232,7 +3269,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	changed |= ieee80211_handle_pwr_constr(sdata, chan, mgmt,
 					       elems.country_elem,
 					       elems.country_elem_len,
-					       elems.pwr_constr_elem);
+					       elems.pwr_constr_elem,
+					       elems.cisco_dtpc_elem);
 
 	ieee80211_bss_info_change_notify(sdata, changed);
 }
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index b444f27a788e..3c61060a4d2b 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1015,6 +1015,31 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 			}
 			elems->pwr_constr_elem = pos;
 			break;
+		case WLAN_EID_CISCO_VENDOR_SPECIFIC:
+			/* Lots of different options exist, but we only care
+			 * about the Dynamic Transmit Power Control element.
+			 * First check for the Cisco OUI, then for the DTPC
+			 * tag (0x00).
+			 */
+			if (elen < 4) {
+				elem_parse_failed = true;
+				break;
+			}
+
+			if (pos[0] != 0x00 || pos[1] != 0x40 ||
+			    pos[2] != 0x96 || pos[3] != 0x00)
+				break;
+
+			if (elen != 6) {
+				elem_parse_failed = true;
+				break;
+			}
+
+			if (calc_crc)
+				crc = crc32_be(crc, pos - 2, elen + 2);
+
+			elems->cisco_dtpc_elem = pos;
+			break;
 		case WLAN_EID_TIMEOUT_INTERVAL:
 			if (elen >= sizeof(struct ieee80211_timeout_interval_ie))
 				elems->timeout_int = (void *)pos;
-- 
cgit v1.2.3


From 4930d247af29f849cd1bddd65be2400684dc886e Mon Sep 17 00:00:00 2001
From: Gaël PORTAY <gael.portay@gmail.com>
Date: Sat, 6 Sep 2014 19:52:35 +0200
Subject: ARM: at91/tclib: move initialization from alloc to probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move resource retrieval from atmel_tc_alloc to tc_probe to avoid lately
reporting resource related issues when a TC block user request a TC block.

Moreover, resources retrieval are usually done in the probe function,
thus moving them add some consistency with other drivers.

Initialization is done once, ie not every time a tc block is requested.
If it fails, the device is not appended to the list of tc blocks.

Furhermore, the device id is retrieved at probe as well, avoiding parsing
DT every time the user requests of tc block.

Signed-off-by: Gaël PORTAY <gael.portay@gmail.com>
Acked-by: Thierry Reding <thierry.reding@gmail.com>
Acked-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
 drivers/clocksource/tcb_clksrc.c |  2 +-
 drivers/misc/atmel_tclib.c       | 71 +++++++++++++---------------------------
 drivers/pwm/pwm-atmel-tcb.c      |  2 +-
 include/linux/atmel_tc.h         |  8 +++--
 4 files changed, 29 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index a8d7ea14f183..f922e81d531b 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -279,7 +279,7 @@ static int __init tcb_clksrc_init(void)
 	int i;
 	int ret;
 
-	tc = atmel_tc_alloc(CONFIG_ATMEL_TCB_CLKSRC_BLOCK, clksrc.name);
+	tc = atmel_tc_alloc(CONFIG_ATMEL_TCB_CLKSRC_BLOCK);
 	if (!tc) {
 		pr_debug("can't alloc TC for clocksource\n");
 		return -ENODEV;
diff --git a/drivers/misc/atmel_tclib.c b/drivers/misc/atmel_tclib.c
index b514a2d4485b..d505d1e0857b 100644
--- a/drivers/misc/atmel_tclib.c
+++ b/drivers/misc/atmel_tclib.c
@@ -35,60 +35,31 @@ static LIST_HEAD(tc_list);
 /**
  * atmel_tc_alloc - allocate a specified TC block
  * @block: which block to allocate
- * @name: name to be associated with the iomem resource
  *
  * Caller allocates a block.  If it is available, a pointer to a
  * pre-initialized struct atmel_tc is returned. The caller can access
  * the registers directly through the "regs" field.
  */
-struct atmel_tc *atmel_tc_alloc(unsigned block, const char *name)
+struct atmel_tc *atmel_tc_alloc(unsigned block)
 {
 	struct atmel_tc		*tc;
 	struct platform_device	*pdev = NULL;
-	struct resource		*r;
-	size_t			size;
 
 	spin_lock(&tc_list_lock);
 	list_for_each_entry(tc, &tc_list, node) {
-		if (tc->pdev->dev.of_node) {
-			if (of_alias_get_id(tc->pdev->dev.of_node, "tcb")
-					== block) {
-				pdev = tc->pdev;
-				break;
-			}
-		} else if (tc->pdev->id == block) {
+		if (tc->allocated)
+			continue;
+
+		if ((tc->pdev->dev.of_node && tc->id == block) ||
+		    (tc->pdev->id == block)) {
 			pdev = tc->pdev;
+			tc->allocated = true;
 			break;
 		}
 	}
-
-	if (!pdev || tc->iomem)
-		goto fail;
-
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!r)
-		goto fail;
-
-	size = resource_size(r);
-	r = request_mem_region(r->start, size, name);
-	if (!r)
-		goto fail;
-
-	tc->regs = ioremap(r->start, size);
-	if (!tc->regs)
-		goto fail_ioremap;
-
-	tc->iomem = r;
-
-out:
 	spin_unlock(&tc_list_lock);
-	return tc;
 
-fail_ioremap:
-	release_mem_region(r->start, size);
-fail:
-	tc = NULL;
-	goto out;
+	return pdev ? tc : NULL;
 }
 EXPORT_SYMBOL_GPL(atmel_tc_alloc);
 
@@ -96,19 +67,14 @@ EXPORT_SYMBOL_GPL(atmel_tc_alloc);
  * atmel_tc_free - release a specified TC block
  * @tc: Timer/counter block that was returned by atmel_tc_alloc()
  *
- * This reverses the effect of atmel_tc_alloc(), unmapping the I/O
- * registers, invalidating the resource returned by that routine and
- * making the TC available to other drivers.
+ * This reverses the effect of atmel_tc_alloc(), invalidating the resource
+ * returned by that routine and making the TC available to other drivers.
  */
 void atmel_tc_free(struct atmel_tc *tc)
 {
 	spin_lock(&tc_list_lock);
-	if (tc->regs) {
-		iounmap(tc->regs);
-		release_mem_region(tc->iomem->start, resource_size(tc->iomem));
-		tc->regs = NULL;
-		tc->iomem = NULL;
-	}
+	if (tc->allocated)
+		tc->allocated = false;
 	spin_unlock(&tc_list_lock);
 }
 EXPORT_SYMBOL_GPL(atmel_tc_free);
@@ -142,9 +108,7 @@ static int __init tc_probe(struct platform_device *pdev)
 	struct atmel_tc *tc;
 	struct clk	*clk;
 	int		irq;
-
-	if (!platform_get_resource(pdev, IORESOURCE_MEM, 0))
-		return -EINVAL;
+	struct resource	*r;
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
@@ -160,12 +124,21 @@ static int __init tc_probe(struct platform_device *pdev)
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	tc->regs = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(tc->regs))
+		return PTR_ERR(tc->regs);
+
 	/* Now take SoC information if available */
 	if (pdev->dev.of_node) {
 		const struct of_device_id *match;
 		match = of_match_node(atmel_tcb_dt_ids, pdev->dev.of_node);
 		if (match)
 			tc->tcb_config = match->data;
+
+		tc->id = of_alias_get_id(tc->pdev->dev.of_node, "tcb");
+	} else {
+		tc->id = pdev->id;
 	}
 
 	tc->clk[0] = clk;
diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index f3dcd02390f1..d56e5b717431 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -379,7 +379,7 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	tc = atmel_tc_alloc(tcblock, "tcb-pwm");
+	tc = atmel_tc_alloc(tcblock);
 	if (tc == NULL) {
 		dev_err(&pdev->dev, "failed to allocate Timer Counter Block\n");
 		return -ENOMEM;
diff --git a/include/linux/atmel_tc.h b/include/linux/atmel_tc.h
index 89a931babecf..d8aa88461c64 100644
--- a/include/linux/atmel_tc.h
+++ b/include/linux/atmel_tc.h
@@ -44,12 +44,13 @@ struct atmel_tcb_config {
 /**
  * struct atmel_tc - information about a Timer/Counter Block
  * @pdev: physical device
- * @iomem: resource associated with the I/O register
  * @regs: mapping through which the I/O registers can be accessed
+ * @id: block id
  * @tcb_config: configuration data from SoC
  * @irq: irq for each of the three channels
  * @clk: internal clock source for each of the three channels
  * @node: list node, for tclib internal use
+ * @allocated: if already used, for tclib internal use
  *
  * On some platforms, each TC channel has its own clocks and IRQs,
  * while on others, all TC channels share the same clock and IRQ.
@@ -61,15 +62,16 @@ struct atmel_tcb_config {
  */
 struct atmel_tc {
 	struct platform_device	*pdev;
-	struct resource		*iomem;
 	void __iomem		*regs;
+	int                     id;
 	const struct atmel_tcb_config *tcb_config;
 	int			irq[3];
 	struct clk		*clk[3];
 	struct list_head	node;
+	bool			allocated;
 };
 
-extern struct atmel_tc *atmel_tc_alloc(unsigned block, const char *name);
+extern struct atmel_tc *atmel_tc_alloc(unsigned block);
 extern void atmel_tc_free(struct atmel_tc *tc);
 
 /* platform-specific ATMEL_TC_TIMER_CLOCKx divisors (0 means 32KiHz) */
-- 
cgit v1.2.3


From 84f462371cc07272a17e2ae96c3540f795db273a Mon Sep 17 00:00:00 2001
From: Gaël PORTAY <gael.portay@gmail.com>
Date: Sat, 6 Sep 2014 19:52:36 +0200
Subject: ARM: at91/tclib: mask interruptions at shutdown and probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Shutdown properly the timer counter block by masking interruptions. Otherwise,
a segmentation may happen when kexec-ing a new kernel (see backtrace below).
An interruption may happen before the handler is set, leading to a kernel
segmentation fault.

Furthermore, we make sure the interruptions are masked when the driver is
initialized. This will prevent freshly kexec-ed kernel from crashing when
launched from a kernel which does not properly mask interruptions at shutdown.

The backtrace below happened after kexec-ing a new kernel, from a kernel
that did not shut down properly leaving interruptions unmasked.

Unable to handle kernel NULL pointer dereference at virtual address 00000000
pgd = c0004000
[00000000] *pgd=00000000
Internal error: Oops: 80000005 [#1] ARM
Modules linked in:
CPU: 0 PID: 1 Comm: swapper Not tainted 3.16.0+ #144
task: c1828aa0 ti: c182a000 task.ti: c182a000
PC is at 0x0
LR is at ch2_irq+0x28/0x30
pc : [<00000000>]    lr : [<c01db904>]    psr: 000000d3
sp : c182bd38  ip : c182bd48  fp : c182bd44
r10: c0373390  r9 : c1825b00  r8 : 60000053
r7 : 00000000  r6 : 00000000  r5 : 00000013  r4 : c036e800
r3 : 00000000  r2 : 00002004  r1 : c036e760  r0 : c036e760
Flags: nzcv  IRQs off  FIQs off  Mode SVC_32  ISA ARM  Segment kernel
Control: 0005317f  Table: 20004000  DAC: 00000017
Process swapper (pid: 1, stack limit = 0xc182a1c0)
Stack: (0xc182bd38 to 0xc182c000)
bd20:                                                       c182bd7c c182bd48
bd40: c0045430 c01db8ec 00000000 c18c6f40 c182bd74 c1825b00 c035cec4 00000000
bd60: c182be2c 60000053 c1825b34 00000000 c182bd94 c182bd80 c0045570 c0045408
bd80: 00000000 c1825b00 c182bdac c182bd98 c0047f34 c0045550 00000013 c036619c
bda0: c182bdc4 c182bdb0 c0044da4 c0047e98 0000007f 00000013 c182bde4 c182bdc8
bdc0: c0009e34 c0044d8c fefff000 c0046728 60000053 ffffffff c182bdf4 c182bde8
bde0: c00086a8 c0009ddc c182be74 c182bdf8 c000cb80 c0008674 00000000 00000013
be00: 00000000 00014200 c1825b00 c036e800 00000013 c035ed98 60000053 c1825b34
be20: 00000000 c182be74 c182be20 c182be40 c0047994 c0046728 60000053 ffffffff
be40: 00000013 c036e800 c182be64 c1825b00 00000013 c036e800 c035ed98 c03874bc
be60: 00000004 c036e700 c182be94 c182be78 c004689c c0046398 c036e760 c18c6080
be80: 00000000 c035ed10 c182bedc c182be98 c0348b08 c004684c 0000000c c034dac8
bea0: 004c4b3f c028c338 c036e760 00000013 c014ecc8 c18e67e0 c035b9c0 c0348884
bec0: c035b9c0 c182a020 00000000 00000000 c182bf54 c182bee0 c00089fc c0348894
bee0: c00da51c c1ffcc78 c182bf0c c182bef8 c002d100 c002d09c c1ffcc78 00000000
bf00: c182bf54 c182bf10 c002d308 c0336570 c182bf3c c0334e44 00000003 00000003
bf20: 00000030 c0334b44 c0044d74 00000003 00000003 c034dac8 c0350a94 c0373440
bf40: c0373440 00000030 c182bf94 c182bf58 c0336d24 c000890c 00000003 00000003
bf60: c0336560 c182bf64 c182bf64 6e616e0d 00000000 c0272fc8 00000000 00000000
bf80: 00000000 00000000 c182bfac c182bf98 c0272fd8 c0336bd8 c182a000 00000000
bfa0: 00000000 c182bfb0 c00095d0 c0272fd8 00000000 00000000 00000000 00000000
bfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
bfe0: 00000000 00000000 00000000 00000000 00000013 00000000 374d27cd 33cc33e4
Backtrace:
[<c01db8dc>] (ch2_irq) from [<c0045430>] (handle_irq_event_percpu+0x38/0x148)
[<c00453f8>] (handle_irq_event_percpu) from [<c0045570>] (handle_irq_event+0x30/0x40)
 r10:00000000 r9:c1825b34 r8:60000053 r7:c182be2c r6:00000000 r5:c035cec4
 r4:c1825b00
[<c0045540>] (handle_irq_event) from [<c0047f34>] (handle_fasteoi_irq+0xac/0x11c)
 r4:c1825b00 r3:00000000
[<c0047e88>] (handle_fasteoi_irq) from [<c0044da4>] (generic_handle_irq+0x28/0x38)
 r5:c036619c r4:00000013
[<c0044d7c>] (generic_handle_irq) from [<c0009e34>] (handle_IRQ+0x68/0x88)
 r4:00000013 r3:0000007f
[<c0009dcc>] (handle_IRQ) from [<c00086a8>] (at91_aic_handle_irq+0x44/0x4c)
 r6:ffffffff r5:60000053 r4:c0046728 r3:fefff000
[<c0008664>] (at91_aic_handle_irq) from [<c000cb80>] (__irq_svc+0x40/0x4c)
Exception stack(0xc182bdf8 to 0xc182be40)
bde0:                                                       00000000 00000013
be00: 00000000 00014200 c1825b00 c036e800 00000013 c035ed98 60000053 c1825b34
be20: 00000000 c182be74 c182be20 c182be40 c0047994 c0046728 60000053 ffffffff
[<c0046388>] (__setup_irq) from [<c004689c>] (setup_irq+0x60/0x8c)
 r10:c036e700 r9:00000004 r8:c03874bc r7:c035ed98 r6:c036e800 r5:00000013
 r4:c1825b00
[<c004683c>] (setup_irq) from [<c0348b08>] (tcb_clksrc_init+0x284/0x31c)
 r6:c035ed10 r5:00000000 r4:c18c6080 r3:c036e760
[<c0348884>] (tcb_clksrc_init) from [<c00089fc>] (do_one_initcall+0x100/0x1b4)
 r10:00000000 r9:00000000 r8:c182a020 r7:c035b9c0 r6:c0348884 r5:c035b9c0
 r4:c18e67e0
[<c00088fc>] (do_one_initcall) from [<c0336d24>] (kernel_init_freeable+0x15c/0x224)
 r9:00000030 r8:c0373440 r7:c0373440 r6:c0350a94 r5:c034dac8 r4:00000003
[<c0336bc8>] (kernel_init_freeable) from [<c0272fd8>] (kernel_init+0x10/0xec)
 r9:00000000 r8:00000000 r7:00000000 r6:00000000 r5:c0272fc8 r4:00000000
[<c0272fc8>] (kernel_init) from [<c00095d0>] (ret_from_fork+0x14/0x24)
 r4:00000000 r3:c182a000
Code: bad PC value
---[ end trace 5b30f0017e282e47 ]---
Kernel panic - not syncing: Fatal exception in interrupt

Signed-off-by: Gaël PORTAY <gael.portay@gmail.com>
Acked-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
 drivers/misc/atmel_tclib.c | 16 ++++++++++++++++
 include/linux/atmel_tc.h   |  5 +++++
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/misc/atmel_tclib.c b/drivers/misc/atmel_tclib.c
index d505d1e0857b..0ca05c3ec8d6 100644
--- a/drivers/misc/atmel_tclib.c
+++ b/drivers/misc/atmel_tclib.c
@@ -109,6 +109,7 @@ static int __init tc_probe(struct platform_device *pdev)
 	struct clk	*clk;
 	int		irq;
 	struct resource	*r;
+	unsigned int	i;
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
@@ -157,18 +158,33 @@ static int __init tc_probe(struct platform_device *pdev)
 	if (tc->irq[2] < 0)
 		tc->irq[2] = irq;
 
+	for (i = 0; i < 3; i++)
+		writel(ATMEL_TC_ALL_IRQ, tc->regs + ATMEL_TC_REG(i, IDR));
+
 	spin_lock(&tc_list_lock);
 	list_add_tail(&tc->node, &tc_list);
 	spin_unlock(&tc_list_lock);
 
+	platform_set_drvdata(pdev, tc);
+
 	return 0;
 }
 
+static void tc_shutdown(struct platform_device *pdev)
+{
+	int i;
+	struct atmel_tc *tc = platform_get_drvdata(pdev);
+
+	for (i = 0; i < 3; i++)
+		writel(ATMEL_TC_ALL_IRQ, tc->regs + ATMEL_TC_REG(i, IDR));
+}
+
 static struct platform_driver tc_driver = {
 	.driver = {
 		.name	= "atmel_tcb",
 		.of_match_table	= of_match_ptr(atmel_tcb_dt_ids),
 	},
+	.shutdown = tc_shutdown,
 };
 
 static int __init tc_init(void)
diff --git a/include/linux/atmel_tc.h b/include/linux/atmel_tc.h
index d8aa88461c64..b87c1c7c242a 100644
--- a/include/linux/atmel_tc.h
+++ b/include/linux/atmel_tc.h
@@ -260,5 +260,10 @@ extern const u8 atmel_tc_divisors[5];
 #define     ATMEL_TC_LDRAS	(1 <<  5)	/* RA loading */
 #define     ATMEL_TC_LDRBS	(1 <<  6)	/* RB loading */
 #define     ATMEL_TC_ETRGS	(1 <<  7)	/* external trigger */
+#define     ATMEL_TC_ALL_IRQ	(ATMEL_TC_COVFS	| ATMEL_TC_LOVRS | \
+				 ATMEL_TC_CPAS | ATMEL_TC_CPBS | \
+				 ATMEL_TC_CPCS | ATMEL_TC_LDRAS | \
+				 ATMEL_TC_LDRBS | ATMEL_TC_ETRGS) \
+				 /* all IRQs */
 
 #endif
-- 
cgit v1.2.3


From d4288d3fac18bbc31cb6d369679b1fa1d9321ae9 Mon Sep 17 00:00:00 2001
From: Jurgen Kramer <gtmkramer@xs4all.nl>
Date: Fri, 5 Sep 2014 10:47:56 +0200
Subject: ALSA: pcm: add new DSD sampleformat for native DSD playback on XMOS
 based devices

XMOS based USB DACs with native DSD support expose this feature via a USB
alternate setting. The audio format is either 32-bit raw or a 32-bit PCM format.
To utilize this feature on linux this patch introduces a new 32-bit DSD
sampleformat DSD_U32_LE.
A follow up patch will add a quirk for XMOS based devices to utilize the new format.
Further patches will add support to alsa-lib.

Signed-off-by: Jurgen Kramer <gtmkramer@xs4all.nl>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h         | 1 +
 include/uapi/sound/asound.h | 3 ++-
 sound/core/pcm.c            | 1 +
 sound/core/pcm_misc.c       | 4 ++++
 4 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 67e0bdb9f0fa..e862497f7556 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -183,6 +183,7 @@ struct snd_pcm_ops {
 #define SNDRV_PCM_FMTBIT_G723_40_1B	_SNDRV_PCM_FMTBIT(G723_40_1B)
 #define SNDRV_PCM_FMTBIT_DSD_U8		_SNDRV_PCM_FMTBIT(DSD_U8)
 #define SNDRV_PCM_FMTBIT_DSD_U16_LE	_SNDRV_PCM_FMTBIT(DSD_U16_LE)
+#define SNDRV_PCM_FMTBIT_DSD_U32_LE	_SNDRV_PCM_FMTBIT(DSD_U32_LE)
 
 #ifdef SNDRV_LITTLE_ENDIAN
 #define SNDRV_PCM_FMTBIT_S16		SNDRV_PCM_FMTBIT_S16_LE
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 32168f7ffce3..6ee586728df9 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -219,7 +219,8 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_G723_40_1B	((__force snd_pcm_format_t) 47) /* 1 sample in 1 byte */
 #define	SNDRV_PCM_FORMAT_DSD_U8		((__force snd_pcm_format_t) 48) /* DSD, 1-byte samples DSD (x8) */
 #define	SNDRV_PCM_FORMAT_DSD_U16_LE	((__force snd_pcm_format_t) 49) /* DSD, 2-byte samples DSD (x16), little endian */
-#define	SNDRV_PCM_FORMAT_LAST		SNDRV_PCM_FORMAT_DSD_U16_LE
+#define	SNDRV_PCM_FORMAT_DSD_U32_LE	((__force snd_pcm_format_t) 50) /* DSD, 4-byte samples DSD (x32), little endian */
+#define	SNDRV_PCM_FORMAT_LAST		SNDRV_PCM_FORMAT_DSD_U32_LE
 
 #ifdef SNDRV_LITTLE_ENDIAN
 #define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_LE
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index afccdc553ef9..42ded997b223 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -215,6 +215,7 @@ static char *snd_pcm_format_names[] = {
 	FORMAT(G723_40_1B),
 	FORMAT(DSD_U8),
 	FORMAT(DSD_U16_LE),
+	FORMAT(DSD_U32_LE),
 };
 
 const char *snd_pcm_format_name(snd_pcm_format_t format)
diff --git a/sound/core/pcm_misc.c b/sound/core/pcm_misc.c
index 4560ca0e5651..83f54e1dbac9 100644
--- a/sound/core/pcm_misc.c
+++ b/sound/core/pcm_misc.c
@@ -148,6 +148,10 @@ static struct pcm_format_data pcm_formats[(INT)SNDRV_PCM_FORMAT_LAST+1] = {
 		.width = 16, .phys = 16, .le = 1, .signd = 0,
 		.silence = {},
 	},
+	[SNDRV_PCM_FORMAT_DSD_U32_LE] = {
+		.width = 32, .phys = 32, .le = 1, .signd = 0,
+		.silence = { 0x69, 0x69, 0x69, 0x69 },
+	},
 	/* FIXME: the following three formats are not defined properly yet */
 	[SNDRV_PCM_FORMAT_MPEG] = {
 		.le = -1, .signd = -1,
-- 
cgit v1.2.3


From ff9ea323816dc1c8ac7144afd4eab3ac97704430 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 8 Sep 2014 08:03:56 +0900
Subject: block, bdi: an active gendisk always has a request_queue associated
 with it

bdev_get_queue() returns the request_queue associated with the
specified block_device.  blk_get_backing_dev_info() makes use of
bdev_get_queue() to determine the associated bdi given a block_device.

All the callers of bdev_get_queue() including
blk_get_backing_dev_info() assume that bdev_get_queue() may return
NULL and implement NULL handling; however, bdev_get_queue() requires
the passed in block_device is opened and attached to its gendisk.
Because an active gendisk always has a valid request_queue associated
with it, bdev_get_queue() can never return NULL and neither can
blk_get_backing_dev_info().

Make it clear that neither of the two functions can return NULL and
remove NULL handling from all the callers.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Chris Mason <clm@fb.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c       | 10 +++-------
 block/compat_ioctl.c   |  4 ----
 block/ioctl.c          |  4 ----
 fs/block_dev.c         |  2 --
 fs/btrfs/disk-io.c     |  2 +-
 fs/xfs/xfs_buf.c       |  2 --
 include/linux/blkdev.h |  2 +-
 7 files changed, 5 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 93603e6ff479..817446175489 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -83,18 +83,14 @@ void blk_queue_congestion_threshold(struct request_queue *q)
  * @bdev:	device
  *
  * Locates the passed device's request queue and returns the address of its
- * backing_dev_info
- *
- * Will return NULL if the request queue cannot be located.
+ * backing_dev_info.  This function can only be called if @bdev is opened
+ * and the return value is never NULL.
  */
 struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
 {
-	struct backing_dev_info *ret = NULL;
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (q)
-		ret = &q->backing_dev_info;
-	return ret;
+	return &q->backing_dev_info;
 }
 EXPORT_SYMBOL(blk_get_backing_dev_info);
 
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 18b282ce361e..f678c733df40 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -709,8 +709,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		if (!arg)
 			return -EINVAL;
 		bdi = blk_get_backing_dev_info(bdev);
-		if (bdi == NULL)
-			return -ENOTTY;
 		return compat_put_long(arg,
 				       (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
 	case BLKROGET: /* compatible */
@@ -731,8 +729,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 		bdi = blk_get_backing_dev_info(bdev);
-		if (bdi == NULL)
-			return -ENOTTY;
 		bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
 		return 0;
 	case BLKGETSIZE:
diff --git a/block/ioctl.c b/block/ioctl.c
index d6cda8147c91..6c7bf903742f 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -356,8 +356,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		if (!arg)
 			return -EINVAL;
 		bdi = blk_get_backing_dev_info(bdev);
-		if (bdi == NULL)
-			return -ENOTTY;
 		return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
 	case BLKROGET:
 		return put_int(arg, bdev_read_only(bdev) != 0);
@@ -386,8 +384,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		if(!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 		bdi = blk_get_backing_dev_info(bdev);
-		if (bdi == NULL)
-			return -ENOTTY;
 		bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
 		return 0;
 	case BLKBSZSET:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6d7274619bf9..d3251eca6429 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1173,8 +1173,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (!ret) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
 				bdi = blk_get_backing_dev_info(bdev);
-				if (bdi == NULL)
-					bdi = &default_backing_dev_info;
 				bdev_inode_switch_bdi(bdev->bd_inode, bdi);
 			}
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d0ed9e664f7d..39ff591ae1b4 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1694,7 +1694,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 		if (!device->bdev)
 			continue;
 		bdi = blk_get_backing_dev_info(device->bdev);
-		if (bdi && bdi_congested(bdi, bdi_bits)) {
+		if (bdi_congested(bdi, bdi_bits)) {
 			ret = 1;
 			break;
 		}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index cd7b8ca9b064..497fcde381d7 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1678,8 +1678,6 @@ xfs_alloc_buftarg(
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
 	btp->bt_bdi = blk_get_backing_dev_info(bdev);
-	if (!btp->bt_bdi)
-		goto error;
 
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 518b46555b80..e267bf0db559 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -865,7 +865,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
-	return bdev->bd_disk->queue;
+	return bdev->bd_disk->queue;	/* this is never NULL */
 }
 
 /*
-- 
cgit v1.2.3


From e36f1dfce0b45d347927568efe1088821758cc3c Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 8 Sep 2014 08:03:57 +0900
Subject: bdi: remove unused stuff

Two flags and one bdi_writeback field are no longer used.  Remove
them.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/backing-dev.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index e488e9459a93..2103a7fa3fd8 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -28,12 +28,10 @@ struct dentry;
  * Bits in backing_dev_info.state
  */
 enum bdi_state {
-	BDI_wb_alloc,		/* Default embedded wb allocated */
 	BDI_async_congested,	/* The async (write) queue is getting full */
 	BDI_sync_congested,	/* The sync queue is getting full */
 	BDI_registered,		/* bdi_register() was done */
 	BDI_writeback_running,	/* Writeback is in progress */
-	BDI_unused,		/* Available bits start here */
 };
 
 typedef int (congested_fn)(void *, int);
@@ -50,7 +48,6 @@ enum bdi_stat_item {
 
 struct bdi_writeback {
 	struct backing_dev_info *bdi;	/* our parent bdi */
-	unsigned int nr;
 
 	unsigned long last_old_flush;	/* last old data flush */
 
-- 
cgit v1.2.3


From 018a17bdc8658ad448497c84d4ba21b6985820ec Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 8 Sep 2014 08:04:01 +0900
Subject: bdi: reimplement bdev_inode_switch_bdi()

A block_device may be attached to different gendisks and thus
different bdis over time.  bdev_inode_switch_bdi() is used to switch
the associated bdi.  The function assumes that the inode could be
dirty and transfers it between bdis if so.  This is a bit nasty in
that it reaches into bdi internals.

This patch reimplements the function so that it writes out the inode
if dirty.  This is a lot simpler and can be implemented without
exposing bdi internals.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 fs/block_dev.c              | 32 +++++++++++---------------------
 include/linux/backing-dev.h |  1 -
 mm/backing-dev.c            |  2 +-
 3 files changed, 12 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index d3251eca6429..cc8d68ac29aa 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -50,32 +50,22 @@ inline struct block_device *I_BDEV(struct inode *inode)
 EXPORT_SYMBOL(I_BDEV);
 
 /*
- * Move the inode from its current bdi to a new bdi. If the inode is dirty we
- * need to move it onto the dirty list of @dst so that the inode is always on
- * the right list.
+ * Move the inode from its current bdi to a new bdi.  Make sure the inode
+ * is clean before moving so that it doesn't linger on the old bdi.
  */
 static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
-	struct backing_dev_info *old = inode->i_data.backing_dev_info;
-	bool wakeup_bdi = false;
-
-	if (unlikely(dst == old))		/* deadlock avoidance */
-		return;
-	bdi_lock_two(&old->wb, &dst->wb);
-	spin_lock(&inode->i_lock);
-	inode->i_data.backing_dev_info = dst;
-	if (inode->i_state & I_DIRTY) {
-		if (bdi_cap_writeback_dirty(dst) && !wb_has_dirty_io(&dst->wb))
-			wakeup_bdi = true;
-		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
+	while (true) {
+		spin_lock(&inode->i_lock);
+		if (!(inode->i_state & I_DIRTY)) {
+			inode->i_data.backing_dev_info = dst;
+			spin_unlock(&inode->i_lock);
+			return;
+		}
+		spin_unlock(&inode->i_lock);
+		WARN_ON_ONCE(write_inode_now(inode, true));
 	}
-	spin_unlock(&inode->i_lock);
-	spin_unlock(&old->wb.list_lock);
-	spin_unlock(&dst->wb.list_lock);
-
-	if (wakeup_bdi)
-		bdi_wakeup_thread_delayed(dst);
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 2103a7fa3fd8..5da6012b7a14 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -121,7 +121,6 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi);
 void bdi_writeback_workfn(struct work_struct *work);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
-void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2);
 
 extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index b65fe93ad612..7d63d5e9d3de 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -40,7 +40,7 @@ LIST_HEAD(bdi_list);
 /* bdi_wq serves all asynchronous writeback tasks */
 struct workqueue_struct *bdi_wq;
 
-void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
 {
 	if (wb1 < wb2) {
 		spin_lock(&wb1->list_lock);
-- 
cgit v1.2.3


From c16900cf285ca240f0f84117bf8b88a03c55469b Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 15 Aug 2014 21:17:06 +0300
Subject: Bluetooth: Fix hci_conn reference counting for fixed channels

Now that SMP has been converted to use fixed channels we've got a bit of
a problem with the hci_conn reference counting. So far the L2CAP code
has kept a reference for each L2CAP channel that was notified of the
connection. With SMP however this would mean that the connection is
never dropped even though there are no other users of it. Furthermore,
SMP already does its own hci_conn reference counting internally,
starting from a security or pairing request and ending with the key
distribution.

This patch makes L2CAP fixed channels default to the L2CAP core not
keeping a hci_conn reference for them. A new FLAG_HOLD_HCI_CONN flag is
added so that L2CAP users can declare an exception to this rule and hold
a reference even for their fixed channels. One such exception is the
L2CAP socket layer which does want a reference for each socket (e.g. an
ATT socket which uses a fixed channel).

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/l2cap_core.c    | 12 ++++++++++--
 net/bluetooth/l2cap_sock.c    |  8 ++++++++
 3 files changed, 19 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index cedda399f9c0..1558eccb19db 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -711,6 +711,7 @@ enum {
 	FLAG_DEFER_SETUP,
 	FLAG_LE_CONN_REQ_SENT,
 	FLAG_PENDING_SECURITY,
+	FLAG_HOLD_HCI_CONN,
 };
 
 enum {
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 777c41dbfdbe..a6559225bb50 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -546,7 +546,10 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
 
 	l2cap_chan_hold(chan);
 
-	hci_conn_hold(conn->hcon);
+	/* Only keep a reference for fixed channels if they requested it */
+	if (chan->chan_type != L2CAP_CHAN_FIXED ||
+	    test_bit(FLAG_HOLD_HCI_CONN, &chan->flags))
+		hci_conn_hold(conn->hcon);
 
 	list_add(&chan->list, &conn->chan_l);
 }
@@ -577,7 +580,12 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err)
 
 		chan->conn = NULL;
 
-		if (chan->scid != L2CAP_CID_A2MP)
+		/* Reference was only held for non-fixed channels or
+		 * fixed channels that explicitly requested it using the
+		 * FLAG_HOLD_HCI_CONN flag.
+		 */
+		if (chan->chan_type != L2CAP_CHAN_FIXED ||
+		    test_bit(FLAG_HOLD_HCI_CONN, &chan->flags))
 			hci_conn_drop(conn->hcon);
 
 		if (mgr && mgr->bredr_chan == chan)
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index ed06f88e6f10..31f106e61ca2 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -146,6 +146,14 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 	case L2CAP_CHAN_RAW:
 		chan->sec_level = BT_SECURITY_SDP;
 		break;
+	case L2CAP_CHAN_FIXED:
+		/* Fixed channels default to the L2CAP core not holding a
+		 * hci_conn reference for them. For fixed channels mapping to
+		 * L2CAP sockets we do want to hold a reference so set the
+		 * appropriate flag to request it.
+		 */
+		set_bit(FLAG_HOLD_HCI_CONN, &chan->flags);
+		break;
 	}
 
 	bacpy(&chan->src, &la.l2_bdaddr);
-- 
cgit v1.2.3


From 51bb8457ddfa74ede52bf8c02054dea831d59fff Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 15 Aug 2014 21:06:57 +0300
Subject: Bluetooth: Improve *_get() functions to return the object type

It's natural to have *_get() functions that increment the reference
count of an object to return the object type itself. This way it's
simple to make a copy of the object pointer and increase the reference
count in a single step. This patch updates two such get() functions,
namely hci_conn_get() and l2cap_conn_get(), and updates the users to
take advantage of the new API.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  3 ++-
 include/net/bluetooth/l2cap.h    |  2 +-
 net/bluetooth/hidp/core.c        | 10 ++++------
 net/bluetooth/l2cap_core.c       |  6 +++---
 4 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b0ded1333865..aa75eee8ad7f 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -756,9 +756,10 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status);
  * _get()/_drop() in it, but require the caller to have a valid ref (FIXME).
  */
 
-static inline void hci_conn_get(struct hci_conn *conn)
+static inline struct hci_conn *hci_conn_get(struct hci_conn *conn)
 {
 	get_device(&conn->dev);
+	return conn;
 }
 
 static inline void hci_conn_put(struct hci_conn *conn)
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 1558eccb19db..8f1652ed3326 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -948,7 +948,7 @@ void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
 void __l2cap_physical_cfm(struct l2cap_chan *chan, int result);
 
 void l2cap_conn_shutdown(struct l2cap_conn *conn, int err);
-void l2cap_conn_get(struct l2cap_conn *conn);
+struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn);
 void l2cap_conn_put(struct l2cap_conn *conn);
 
 int l2cap_register_user(struct l2cap_conn *conn, struct l2cap_user *user);
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 6c7ecf116e74..1b7d605706aa 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -915,7 +915,7 @@ static int hidp_session_new(struct hidp_session **out, const bdaddr_t *bdaddr,
 
 	/* connection management */
 	bacpy(&session->bdaddr, bdaddr);
-	session->conn = conn;
+	session->conn = l2cap_conn_get(conn);
 	session->user.probe = hidp_session_probe;
 	session->user.remove = hidp_session_remove;
 	session->ctrl_sock = ctrl_sock;
@@ -941,13 +941,13 @@ static int hidp_session_new(struct hidp_session **out, const bdaddr_t *bdaddr,
 	if (ret)
 		goto err_free;
 
-	l2cap_conn_get(session->conn);
 	get_file(session->intr_sock->file);
 	get_file(session->ctrl_sock->file);
 	*out = session;
 	return 0;
 
 err_free:
+	l2cap_conn_put(session->conn);
 	kfree(session);
 	return ret;
 }
@@ -1327,10 +1327,8 @@ int hidp_connection_add(struct hidp_connadd_req *req,
 
 	conn = NULL;
 	l2cap_chan_lock(chan);
-	if (chan->conn) {
-		l2cap_conn_get(chan->conn);
-		conn = chan->conn;
-	}
+	if (chan->conn)
+		conn = l2cap_conn_get(chan->conn);
 	l2cap_chan_unlock(chan);
 
 	if (!conn)
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index a6559225bb50..cb36169ef300 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1695,9 +1695,10 @@ static void l2cap_conn_free(struct kref *ref)
 	kfree(conn);
 }
 
-void l2cap_conn_get(struct l2cap_conn *conn)
+struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn)
 {
 	kref_get(&conn->ref);
+	return conn;
 }
 EXPORT_SYMBOL(l2cap_conn_get);
 
@@ -6908,8 +6909,7 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
 
 	kref_init(&conn->ref);
 	hcon->l2cap_data = conn;
-	conn->hcon = hcon;
-	hci_conn_get(conn->hcon);
+	conn->hcon = hci_conn_get(hcon);
 	conn->hchan = hchan;
 
 	BT_DBG("hcon %p conn %p hchan %p", hcon, conn, hchan);
-- 
cgit v1.2.3


From eb78d7e53d144995b9e023b151de19fa40af72f3 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 18 Aug 2014 00:41:41 +0300
Subject: Bluetooth: Use zero timeout for immediate scheduling

There's no point in passing a "small" timeout to queue_delayed_work() to
try to get the callback faster scheduled. Passing 0 is perfectly valid
and will cause a shortcut to a direct queue_work().

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index aa75eee8ad7f..18c24f6fce6c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -791,7 +791,7 @@ static inline void hci_conn_drop(struct hci_conn *conn)
 				if (!conn->out)
 					timeo *= 2;
 			} else {
-				timeo = msecs_to_jiffies(10);
+				timeo = 0;
 			}
 			break;
 
@@ -800,7 +800,7 @@ static inline void hci_conn_drop(struct hci_conn *conn)
 			break;
 
 		default:
-			timeo = msecs_to_jiffies(10);
+			timeo = 0;
 			break;
 		}
 
-- 
cgit v1.2.3


From f94b665dcf15324f5ac8aa639e47be0829b6409d Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 18 Aug 2014 00:41:44 +0300
Subject: Bluetooth: Ignore incoming data after initiating disconnection

When hci_chan_del is called the disconnection routines get scheduled
through a workqueue. If there's any incoming ACL data before the
routines get executed there's a chance that a new hci_chan is created
and the disconnection never happens. This patch adds a new hci_conn flag
to indicate that we're in the process of driving the connection down. We
set the flag in hci_chan_del and check for it in hci_chan_create so that
no new channels are created for the same connection.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h | 1 +
 net/bluetooth/hci_conn.c         | 6 ++++++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 18c24f6fce6c..dbe73642c54c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -553,6 +553,7 @@ enum {
 	HCI_CONN_FIPS,
 	HCI_CONN_STK_ENCRYPT,
 	HCI_CONN_AUTH_INITIATOR,
+	HCI_CONN_DROP,
 };
 
 static inline bool hci_conn_ssp_enabled(struct hci_conn *conn)
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index cb04a4e3c829..aaa7e388d026 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1291,6 +1291,11 @@ struct hci_chan *hci_chan_create(struct hci_conn *conn)
 
 	BT_DBG("%s hcon %p", hdev->name, conn);
 
+	if (test_bit(HCI_CONN_DROP, &conn->flags)) {
+		BT_DBG("Refusing to create new hci_chan");
+		return NULL;
+	}
+
 	chan = kzalloc(sizeof(*chan), GFP_KERNEL);
 	if (!chan)
 		return NULL;
@@ -1318,6 +1323,7 @@ void hci_chan_del(struct hci_chan *chan)
 
 	/* Force the connection to be immediately dropped */
 	conn->disc_timeout = 0;
+	set_bit(HCI_CONN_DROP, &conn->flags);
 
 	hci_conn_drop(conn);
 	hci_conn_put(conn);
-- 
cgit v1.2.3


From b04afa0c280b7e7ced88692251d75a78c8fcb2a7 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 18 Aug 2014 20:33:30 +0300
Subject: Bluetooth: Remove unused l2cap_conn_shutdown API

Now that there are no more users of the l2cap_conn_shutdown API (since
smp.c switched to using hci_disconnect) we can simply remove it along
with all of it's l2cap_conn variables.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |  4 ----
 net/bluetooth/l2cap_core.c    | 25 -------------------------
 2 files changed, 29 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 8f1652ed3326..be25eddea615 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -625,9 +625,6 @@ struct l2cap_conn {
 
 	struct delayed_work	info_timer;
 
-	int			disconn_err;
-	struct work_struct	disconn_work;
-
 	struct sk_buff		*rx_skb;
 	__u32			rx_len;
 	__u8			tx_ident;
@@ -947,7 +944,6 @@ void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
 		       u8 status);
 void __l2cap_physical_cfm(struct l2cap_chan *chan, int result);
 
-void l2cap_conn_shutdown(struct l2cap_conn *conn, int err);
 struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn);
 void l2cap_conn_put(struct l2cap_conn *conn);
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 2d550afe4322..2d9a2b58d2c8 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1635,9 +1635,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 	if (work_pending(&conn->pending_rx_work))
 		cancel_work_sync(&conn->pending_rx_work);
 
-	if (work_pending(&conn->disconn_work))
-		cancel_work_sync(&conn->disconn_work);
-
 	l2cap_unregister_all_users(conn);
 
 	/* Force the connection to be immediately dropped */
@@ -1670,26 +1667,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 	l2cap_conn_put(conn);
 }
 
-static void disconn_work(struct work_struct *work)
-{
-	struct l2cap_conn *conn = container_of(work, struct l2cap_conn,
-					       disconn_work);
-
-	BT_DBG("conn %p", conn);
-
-	l2cap_conn_del(conn->hcon, conn->disconn_err);
-}
-
-void l2cap_conn_shutdown(struct l2cap_conn *conn, int err)
-{
-	struct hci_dev *hdev = conn->hcon->hdev;
-
-	BT_DBG("conn %p err %d", conn, err);
-
-	conn->disconn_err = err;
-	queue_work(hdev->workqueue, &conn->disconn_work);
-}
-
 static void l2cap_conn_free(struct kref *ref)
 {
 	struct l2cap_conn *conn = container_of(ref, struct l2cap_conn, ref);
@@ -6943,8 +6920,6 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
 
 	INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout);
 
-	INIT_WORK(&conn->disconn_work, disconn_work);
-
 	skb_queue_head_init(&conn->pending_rx);
 	INIT_WORK(&conn->pending_rx_work, process_pending_rx);
 
-- 
cgit v1.2.3


From e3b679d56caa2bc555dee646a6ac5861631e7a28 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 18 Aug 2014 20:33:32 +0300
Subject: Bluetooth: Update hci_disconnect() to return an error value

We'll soon use hci_disconnect() from places that are interested to know
whether the hci_send_cmd() really succeeded or not. This patch updates
hci_disconnect() to pass on any error returned from hci_send_cmd().

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h | 2 +-
 net/bluetooth/hci_conn.c         | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index dbe73642c54c..2b6e04d37593 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -703,7 +703,7 @@ static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev,
 	return NULL;
 }
 
-void hci_disconnect(struct hci_conn *conn, __u8 reason);
+int hci_disconnect(struct hci_conn *conn, __u8 reason);
 bool hci_setup_sync(struct hci_conn *conn, __u16 handle);
 void hci_sco_setup(struct hci_conn *conn, __u8 status);
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 5157a0990732..dd2df20b0f7d 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -122,7 +122,7 @@ static void hci_reject_sco(struct hci_conn *conn)
 	hci_send_cmd(conn->hdev, HCI_OP_REJECT_SYNC_CONN_REQ, sizeof(cp), &cp);
 }
 
-void hci_disconnect(struct hci_conn *conn, __u8 reason)
+int hci_disconnect(struct hci_conn *conn, __u8 reason)
 {
 	struct hci_cp_disconnect cp;
 
@@ -132,7 +132,7 @@ void hci_disconnect(struct hci_conn *conn, __u8 reason)
 
 	cp.handle = cpu_to_le16(conn->handle);
 	cp.reason = reason;
-	hci_send_cmd(conn->hdev, HCI_OP_DISCONNECT, sizeof(cp), &cp);
+	return hci_send_cmd(conn->hdev, HCI_OP_DISCONNECT, sizeof(cp), &cp);
 }
 
 static void hci_amp_disconn(struct hci_conn *conn)
-- 
cgit v1.2.3


From f3d82d0c8ec025fc113408e3ad5775fed5a060ff Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 5 Sep 2014 22:19:50 +0300
Subject: Bluetooth: Move identity address update behind a workqueue

The identity address update of all channels for an l2cap_conn needs to
take the lock for each channel, i.e. it's safest to do this by a
separate workqueue callback.

Previously this was partially solved by moving the entire SMP key
distribution behind a workqueue. However, if we want SMP context locking
to be correct and safe we should always use the l2cap_chan lock when
accessing it, meaning even smp_distribute_keys needs to take that lock
which would once again create a dead lock when updating the identity
address.

The simplest way to solve this is to have l2cap_conn manage the deferred
work which is what this patch does. A subsequent patch will remove the
now unnecessary SMP key distribution work struct.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |  3 ++-
 net/bluetooth/l2cap_core.c    | 10 ++++++++--
 net/bluetooth/smp.c           |  2 +-
 3 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index be25eddea615..ead99f032f7a 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -633,6 +633,8 @@ struct l2cap_conn {
 	struct sk_buff_head	pending_rx;
 	struct work_struct	pending_rx_work;
 
+	struct work_struct	id_addr_update_work;
+
 	__u8			disc_reason;
 
 	struct l2cap_chan	*smp;
@@ -937,7 +939,6 @@ int l2cap_ertm_init(struct l2cap_chan *chan);
 void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
 void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan);
 void l2cap_chan_del(struct l2cap_chan *chan, int err);
-void l2cap_conn_update_id_addr(struct hci_conn *hcon);
 void l2cap_send_conn_req(struct l2cap_chan *chan);
 void l2cap_move_start(struct l2cap_chan *chan);
 void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ab405f0e53cb..b71430caab4a 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -631,9 +631,11 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err)
 }
 EXPORT_SYMBOL_GPL(l2cap_chan_del);
 
-void l2cap_conn_update_id_addr(struct hci_conn *hcon)
+static void l2cap_conn_update_id_addr(struct work_struct *work)
 {
-	struct l2cap_conn *conn = hcon->l2cap_data;
+	struct l2cap_conn *conn = container_of(work, struct l2cap_conn,
+					       id_addr_update_work);
+	struct hci_conn *hcon = conn->hcon;
 	struct l2cap_chan *chan;
 
 	mutex_lock(&conn->chan_lock);
@@ -1635,6 +1637,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 	if (work_pending(&conn->pending_rx_work))
 		cancel_work_sync(&conn->pending_rx_work);
 
+	if (work_pending(&conn->id_addr_update_work))
+		cancel_work_sync(&conn->id_addr_update_work);
+
 	l2cap_unregister_all_users(conn);
 
 	/* Force the connection to be immediately dropped */
@@ -6927,6 +6932,7 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
 
 	skb_queue_head_init(&conn->pending_rx);
 	INIT_WORK(&conn->pending_rx_work, process_pending_rx);
+	INIT_WORK(&conn->id_addr_update_work, l2cap_conn_update_id_addr);
 
 	conn->disc_reason = HCI_ERROR_REMOTE_USER_TERM;
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 9accb4739488..795c603bed30 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -654,7 +654,7 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 		 */
 		bacpy(&hcon->dst, &smp->remote_irk->bdaddr);
 		hcon->dst_type = smp->remote_irk->addr_type;
-		l2cap_conn_update_id_addr(hcon);
+		queue_work(hdev->workqueue, &conn->id_addr_update_work);
 
 		/* When receiving an indentity resolving key for
 		 * a remote device that does not use a resolvable
-- 
cgit v1.2.3


From fc75cc8684d21d3649b28c4c37d4ce3f000759e4 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 5 Sep 2014 22:19:52 +0300
Subject: Bluetooth: Fix locking of the SMP context

Before the move the l2cap_chan the SMP context (smp_chan) didn't have
any kind of proper locking. The best there existed was the
HCI_CONN_LE_SMP_PEND flag which was used to enable mutual exclusion for
potential multiple creators of the SMP context.

Now that SMP has been converted to use the l2cap_chan infrastructure and
since the SMP context is directly mapped to a corresponding l2cap_chan
we get the SMP context locking essentially for free through the
l2cap_chan lock. For all callbacks that l2cap_core.c makes for each
channel implementation (smp.c in the case of SMP) the l2cap_chan lock is
held through l2cap_chan_lock(chan).

Since the calls from l2cap_core.c to smp.c are covered the only missing
piece to have the locking implemented properly is to ensure that the
lock is held for any other call path that may access the SMP context.
This means user responses through mgmt.c, requests to elevate the
security of a connection through hci_conn.c, as well as any deferred
work through workqueues.

This patch adds the necessary locking to all these other code paths that
try to access the SMP context. Since mutual exclusion for the l2cap_chan
access is now covered from all directions the patch also removes
unnecessary HCI_CONN_LE_SMP_PEND flag (once we've acquired the chan lock
we can simply check whether chan->smp is set to know if there's an SMP
context).

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/smp.c              | 76 +++++++++++++++++++++++-----------------
 2 files changed, 44 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2b6e04d37593..045d9133d180 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -539,7 +539,6 @@ enum {
 	HCI_CONN_RSWITCH_PEND,
 	HCI_CONN_MODE_CHANGE_PEND,
 	HCI_CONN_SCO_SETUP_PEND,
-	HCI_CONN_LE_SMP_PEND,
 	HCI_CONN_MGMT_CONNECTED,
 	HCI_CONN_SSP_ENABLED,
 	HCI_CONN_SC_ENABLED,
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 0b4403f3dce1..c71589f4b435 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -409,7 +409,6 @@ static void smp_failure(struct l2cap_conn *conn, u8 reason)
 {
 	struct hci_conn *hcon = conn->hcon;
 	struct l2cap_chan *chan = conn->smp;
-	struct smp_chan *smp;
 
 	if (reason)
 		smp_send_cmd(conn, SMP_CMD_PAIRING_FAIL, sizeof(reason),
@@ -419,12 +418,7 @@ static void smp_failure(struct l2cap_conn *conn, u8 reason)
 	mgmt_auth_failed(hcon->hdev, &hcon->dst, hcon->type, hcon->dst_type,
 			 HCI_ERROR_AUTH_FAILURE);
 
-	if (!chan->data)
-		return;
-
-	smp = chan->data;
-
-	if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags))
+	if (chan->data)
 		smp_chan_destroy(conn);
 }
 
@@ -706,9 +700,6 @@ static void smp_distribute_keys(struct smp_chan *smp)
 
 	BT_DBG("conn %p", conn);
 
-	if (!test_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags))
-		return;
-
 	rsp = (void *) &smp->prsp[1];
 
 	/* The responder sends its keys first */
@@ -801,7 +792,6 @@ static void smp_distribute_keys(struct smp_chan *smp)
 	if ((smp->remote_key_dist & 0x07))
 		return;
 
-	clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags);
 	set_bit(SMP_FLAG_COMPLETE, &smp->flags);
 	smp_notify_keys(conn);
 
@@ -825,16 +815,13 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 	struct smp_chan *smp;
 
 	smp = kzalloc(sizeof(*smp), GFP_ATOMIC);
-	if (!smp) {
-		clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags);
+	if (!smp)
 		return NULL;
-	}
 
 	smp->tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(smp->tfm_aes)) {
 		BT_ERR("Unable to create ECB crypto context");
 		kfree(smp);
-		clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags);
 		return NULL;
 	}
 
@@ -854,16 +841,23 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 	struct l2cap_chan *chan;
 	struct smp_chan *smp;
 	u32 value;
+	int err;
 
 	BT_DBG("");
 
-	if (!conn || !test_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags))
+	if (!conn)
 		return -ENOTCONN;
 
 	chan = conn->smp;
 	if (!chan)
 		return -ENOTCONN;
 
+	l2cap_chan_lock(chan);
+	if (!chan->data) {
+		err = -ENOTCONN;
+		goto unlock;
+	}
+
 	smp = chan->data;
 
 	switch (mgmt_op) {
@@ -879,12 +873,16 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 	case MGMT_OP_USER_PASSKEY_NEG_REPLY:
 	case MGMT_OP_USER_CONFIRM_NEG_REPLY:
 		smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED);
-		return 0;
+		err = 0;
+		goto unlock;
 	default:
 		smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED);
-		return -EOPNOTSUPP;
+		err = -EOPNOTSUPP;
+		goto unlock;
 	}
 
+	err = 0;
+
 	/* If it is our turn to send Pairing Confirm, do so now */
 	if (test_bit(SMP_FLAG_CFM_PENDING, &smp->flags)) {
 		u8 rsp = smp_confirm(smp);
@@ -892,12 +890,15 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 			smp_failure(conn, rsp);
 	}
 
-	return 0;
+unlock:
+	l2cap_chan_unlock(chan);
+	return err;
 }
 
 static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_pairing rsp, *req = (void *) skb->data;
+	struct l2cap_chan *chan = conn->smp;
 	struct hci_dev *hdev = conn->hcon->hdev;
 	struct smp_chan *smp;
 	u8 key_size, auth, sec_level;
@@ -911,12 +912,10 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (conn->hcon->role != HCI_ROLE_SLAVE)
 		return SMP_CMD_NOTSUPP;
 
-	if (!test_and_set_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) {
+	if (!chan->data)
 		smp = smp_chan_create(conn);
-	} else {
-		struct l2cap_chan *chan = conn->smp;
+	else
 		smp = chan->data;
-	}
 
 	if (!smp)
 		return SMP_UNSPECIFIED;
@@ -1122,6 +1121,7 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct smp_cmd_security_req *rp = (void *) skb->data;
 	struct smp_cmd_pairing cp;
 	struct hci_conn *hcon = conn->hcon;
+	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp;
 	u8 sec_level;
 
@@ -1143,7 +1143,8 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (smp_ltk_encrypt(conn, hcon->pending_sec_level))
 		return 0;
 
-	if (test_and_set_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags))
+	/* If SMP is already in progress ignore this request */
+	if (chan->data)
 		return 0;
 
 	smp = smp_chan_create(conn);
@@ -1170,8 +1171,10 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 {
 	struct l2cap_conn *conn = hcon->l2cap_data;
+	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp;
 	__u8 authreq;
+	int ret;
 
 	BT_DBG("conn %p hcon %p level 0x%2.2x", conn, hcon, sec_level);
 
@@ -1192,12 +1195,19 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 		if (smp_ltk_encrypt(conn, hcon->pending_sec_level))
 			return 0;
 
-	if (test_and_set_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags))
-		return 0;
+	l2cap_chan_lock(chan);
+
+	/* If SMP is already in progress ignore this request */
+	if (chan->data) {
+		ret = 0;
+		goto unlock;
+	}
 
 	smp = smp_chan_create(conn);
-	if (!smp)
-		return 1;
+	if (!smp) {
+		ret = 1;
+		goto unlock;
+	}
 
 	authreq = seclevel_to_authreq(sec_level);
 
@@ -1223,8 +1233,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 	}
 
 	set_bit(SMP_FLAG_INITIATOR, &smp->flags);
+	ret = 0;
 
-	return 0;
+unlock:
+	l2cap_chan_unlock(chan);
+	return ret;
 }
 
 static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb)
@@ -1315,7 +1328,6 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn,
 	struct l2cap_chan *chan = conn->smp;
 	struct smp_chan *smp = chan->data;
 	struct hci_conn *hcon = conn->hcon;
-	struct hci_dev *hdev = hcon->hdev;
 	bdaddr_t rpa;
 
 	BT_DBG("");
@@ -1430,7 +1442,7 @@ static int smp_sig_channel(struct l2cap_chan *chan, struct sk_buff *skb)
 	 * returns an error).
 	 */
 	if (code != SMP_CMD_PAIRING_REQ && code != SMP_CMD_SECURITY_REQ &&
-	    !test_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags)) {
+	    !chan->data) {
 		BT_ERR("Unexpected SMP command 0x%02x. Disconnecting.", code);
 		err = -EOPNOTSUPP;
 		goto done;
@@ -1504,7 +1516,7 @@ static void smp_teardown_cb(struct l2cap_chan *chan, int err)
 
 	BT_DBG("chan %p", chan);
 
-	if (test_and_clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags))
+	if (chan->data)
 		smp_chan_destroy(conn);
 
 	conn->smp = NULL;
-- 
cgit v1.2.3


From 7611392fe8ff95ecae528b01a815ae3d72ca6b95 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 8 Sep 2014 14:42:12 -0700
Subject: Input: add INPUT_PROP_POINTING_STICK property

It is useful for userspace to know that there not dealing with a regular
mouse but rather with a pointing stick (e.g. a trackpoint) so that
userspace can e.g. automatically enable middle button scrollwheel
emulation.

It is impossible to tell the difference from the evdev info without
resorting to putting a list of device / driver names in userspace, this is
undesirable.

Add a property which allows userspace to see if a device is a pointing
stick, and set it on all the pointing stick drivers.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Acked-by: Peter Hutterer <peter.hutterer@who-t.net>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/alps.c          | 3 +++
 drivers/input/mouse/elantech.c      | 3 +++
 drivers/input/mouse/synaptics_usb.c | 1 +
 drivers/input/mouse/trackpoint.c    | 2 ++
 include/uapi/linux/input.h          | 1 +
 5 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index a956b980ee73..9d9e5076d402 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -2373,6 +2373,9 @@ int alps_init(struct psmouse *psmouse)
 	dev2->keybit[BIT_WORD(BTN_LEFT)] =
 		BIT_MASK(BTN_LEFT) | BIT_MASK(BTN_MIDDLE) | BIT_MASK(BTN_RIGHT);
 
+	if (priv->flags & ALPS_DUALPOINT)
+		__set_bit(INPUT_PROP_POINTING_STICK, dev2->propbit);
+
 	if (input_register_device(priv->dev2))
 		goto init_fail;
 
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index d71bd3635de1..0cbf6281899c 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1614,6 +1614,9 @@ int elantech_init(struct psmouse *psmouse)
 		tp_dev->keybit[BIT_WORD(BTN_LEFT)] =
 			BIT_MASK(BTN_LEFT) | BIT_MASK(BTN_MIDDLE) |
 			BIT_MASK(BTN_RIGHT);
+
+		__set_bit(INPUT_PROP_POINTING_STICK, tp_dev->propbit);
+
 		error = input_register_device(etd->tp_dev);
 		if (error < 0)
 			goto init_fail_tp_reg;
diff --git a/drivers/input/mouse/synaptics_usb.c b/drivers/input/mouse/synaptics_usb.c
index e122bda16aab..db3973d78207 100644
--- a/drivers/input/mouse/synaptics_usb.c
+++ b/drivers/input/mouse/synaptics_usb.c
@@ -387,6 +387,7 @@ static int synusb_probe(struct usb_interface *intf,
 		__set_bit(EV_REL, input_dev->evbit);
 		__set_bit(REL_X, input_dev->relbit);
 		__set_bit(REL_Y, input_dev->relbit);
+		__set_bit(INPUT_PROP_POINTING_STICK, input_dev->propbit);
 		input_set_abs_params(input_dev, ABS_PRESSURE, 0, 127, 0, 0);
 	} else {
 		input_set_abs_params(input_dev, ABS_X,
diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c
index ca843b6cf6bd..b377462748a2 100644
--- a/drivers/input/mouse/trackpoint.c
+++ b/drivers/input/mouse/trackpoint.c
@@ -393,6 +393,8 @@ int trackpoint_detect(struct psmouse *psmouse, bool set_properties)
 	if ((button_info & 0x0f) >= 3)
 		__set_bit(BTN_MIDDLE, psmouse->dev->keybit);
 
+	__set_bit(INPUT_PROP_POINTING_STICK, psmouse->dev->propbit);
+
 	trackpoint_defaults(psmouse->private);
 
 	error = trackpoint_power_on_reset(&psmouse->ps2dev);
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index 19df18c9b8be..1874ebe9ac1e 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -165,6 +165,7 @@ struct input_keymap_entry {
 #define INPUT_PROP_BUTTONPAD		0x02	/* has button(s) under pad */
 #define INPUT_PROP_SEMI_MT		0x03	/* touch rectangle only */
 #define INPUT_PROP_TOPBUTTONPAD		0x04	/* softbuttons at top of pad */
+#define INPUT_PROP_POINTING_STICK	0x05	/* is a pointing stick */
 
 #define INPUT_PROP_MAX			0x1f
 #define INPUT_PROP_CNT			(INPUT_PROP_MAX + 1)
-- 
cgit v1.2.3


From e676253b19b2d269cccf67fdb1592120a0cd0676 Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Date: Tue, 5 Aug 2014 11:45:59 +0200
Subject: serial/8250: Add support for RS485 IOCTLs

This patch allow the users of the 8250 infrastructure to define a
handler for RS485 configration.

If no handler is defined the 8250 driver will work as usual.

Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Acked-by: Alan Cox <alan@linux.intel.com>
--
v2:Change suggested by Alan "One Thousand Gnomes":
- Move rs485 structure further down on the uart_8250_port structure

 drivers/tty/serial/8250/8250_core.c | 39 +++++++++++++++++++++++++++++++++++++
 include/linux/serial_8250.h         |  3 +++
 2 files changed, 42 insertions(+)
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_core.c | 39 +++++++++++++++++++++++++++++++++++++
 include/linux/serial_8250.h         |  3 +++
 2 files changed, 42 insertions(+)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 1d42dba6121d..b28ed1beb50f 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -2843,6 +2843,42 @@ serial8250_verify_port(struct uart_port *port, struct serial_struct *ser)
 	return 0;
 }
 
+static int serial8250_ioctl(struct uart_port *port, unsigned int cmd,
+			   unsigned long arg)
+{
+	struct uart_8250_port *up =
+		container_of(port, struct uart_8250_port, port);
+	int ret;
+	struct serial_rs485 rs485_config;
+
+	if (!up->rs485_config)
+		return -ENOIOCTLCMD;
+
+	switch (cmd) {
+	case TIOCSRS485:
+		if (copy_from_user(&rs485_config, (void __user *)arg,
+				   sizeof(rs485_config)))
+			return -EFAULT;
+
+		ret = up->rs485_config(up, &rs485_config);
+		if (ret)
+			return ret;
+
+		memcpy(&up->rs485, &rs485_config, sizeof(rs485_config));
+
+		return 0;
+	case TIOCGRS485:
+		if (copy_to_user((void __user *)arg, &up->rs485,
+				 sizeof(up->rs485)))
+			return -EFAULT;
+		return 0;
+	default:
+		break;
+	}
+
+	return -ENOIOCTLCMD;
+}
+
 static const char *
 serial8250_type(struct uart_port *port)
 {
@@ -2872,6 +2908,7 @@ static struct uart_ops serial8250_pops = {
 	.request_port	= serial8250_request_port,
 	.config_port	= serial8250_config_port,
 	.verify_port	= serial8250_verify_port,
+	.ioctl		= serial8250_ioctl,
 #ifdef CONFIG_CONSOLE_POLL
 	.poll_get_char = serial8250_get_poll_char,
 	.poll_put_char = serial8250_put_poll_char,
@@ -3388,6 +3425,8 @@ int serial8250_register_8250_port(struct uart_8250_port *up)
 		uart->port.fifosize	= up->port.fifosize;
 		uart->tx_loadsz		= up->tx_loadsz;
 		uart->capabilities	= up->capabilities;
+		uart->rs485_config	= up->rs485_config;
+		uart->rs485		= up->rs485;
 
 		/* Take tx_loadsz from fifosize if it wasn't set separately */
 		if (uart->port.fifosize && !uart->tx_loadsz)
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index f93649e22c43..6dd671765312 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -96,10 +96,13 @@ struct uart_8250_port {
 	unsigned char		msr_saved_flags;
 
 	struct uart_8250_dma	*dma;
+	struct serial_rs485     rs485;
 
 	/* 8250 specific callbacks */
 	int			(*dl_read)(struct uart_8250_port *);
 	void			(*dl_write)(struct uart_8250_port *, int);
+	int			(*rs485_config)(struct uart_8250_port *,
+						struct serial_rs485 *rs485);
 };
 
 static inline struct uart_8250_port *up_to_u8250p(struct uart_port *up)
-- 
cgit v1.2.3


From 55e15c949fd05d247a889df0ed0177a676fec665 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 3 Sep 2014 12:52:17 +0200
Subject: PM / domains: Remove the pm_genpd_add|remove_callbacks APIs

There are no users of these APIs. To simplify the generic power domain
let's remove them.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 106 --------------------------------------------
 include/linux/pm_domain.h   |  19 --------
 2 files changed, 125 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index eee55c1e5fde..e613e3cb96d8 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1743,112 +1743,6 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	return ret;
 }
 
-/**
- * pm_genpd_add_callbacks - Add PM domain callbacks to a given device.
- * @dev: Device to add the callbacks to.
- * @ops: Set of callbacks to add.
- * @td: Timing data to add to the device along with the callbacks (optional).
- *
- * Every call to this routine should be balanced with a call to
- * __pm_genpd_remove_callbacks() and they must not be nested.
- */
-int pm_genpd_add_callbacks(struct device *dev, struct gpd_dev_ops *ops,
-			   struct gpd_timing_data *td)
-{
-	struct generic_pm_domain_data *gpd_data_new, *gpd_data = NULL;
-	int ret = 0;
-
-	if (!(dev && ops))
-		return -EINVAL;
-
-	gpd_data_new = __pm_genpd_alloc_dev_data(dev);
-	if (!gpd_data_new)
-		return -ENOMEM;
-
-	pm_runtime_disable(dev);
-	device_pm_lock();
-
-	ret = dev_pm_get_subsys_data(dev);
-	if (ret)
-		goto out;
-
-	spin_lock_irq(&dev->power.lock);
-
-	if (dev->power.subsys_data->domain_data) {
-		gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
-	} else {
-		gpd_data = gpd_data_new;
-		dev->power.subsys_data->domain_data = &gpd_data->base;
-	}
-	gpd_data->refcount++;
-	gpd_data->ops = *ops;
-	if (td)
-		gpd_data->td = *td;
-
-	spin_unlock_irq(&dev->power.lock);
-
- out:
-	device_pm_unlock();
-	pm_runtime_enable(dev);
-
-	if (gpd_data != gpd_data_new)
-		__pm_genpd_free_dev_data(dev, gpd_data_new);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(pm_genpd_add_callbacks);
-
-/**
- * __pm_genpd_remove_callbacks - Remove PM domain callbacks from a given device.
- * @dev: Device to remove the callbacks from.
- * @clear_td: If set, clear the device's timing data too.
- *
- * This routine can only be called after pm_genpd_add_callbacks().
- */
-int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td)
-{
-	struct generic_pm_domain_data *gpd_data = NULL;
-	bool remove = false;
-	int ret = 0;
-
-	if (!(dev && dev->power.subsys_data))
-		return -EINVAL;
-
-	pm_runtime_disable(dev);
-	device_pm_lock();
-
-	spin_lock_irq(&dev->power.lock);
-
-	if (dev->power.subsys_data->domain_data) {
-		gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
-		gpd_data->ops = (struct gpd_dev_ops){ NULL };
-		if (clear_td)
-			gpd_data->td = (struct gpd_timing_data){ 0 };
-
-		if (--gpd_data->refcount == 0) {
-			dev->power.subsys_data->domain_data = NULL;
-			remove = true;
-		}
-	} else {
-		ret = -EINVAL;
-	}
-
-	spin_unlock_irq(&dev->power.lock);
-
-	device_pm_unlock();
-	pm_runtime_enable(dev);
-
-	if (ret)
-		return ret;
-
-	dev_pm_put_subsys_data(dev);
-	if (remove)
-		__pm_genpd_free_dev_data(dev, gpd_data);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(__pm_genpd_remove_callbacks);
-
 /**
  * pm_genpd_attach_cpuidle - Connect the given PM domain with cpuidle.
  * @genpd: PM domain to be connected with cpuidle.
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index ebc4c76ffb73..9ae2b9e88d61 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -151,10 +151,6 @@ extern int pm_genpd_add_subdomain_names(const char *master_name,
 					const char *subdomain_name);
 extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 				     struct generic_pm_domain *target);
-extern int pm_genpd_add_callbacks(struct device *dev,
-				  struct gpd_dev_ops *ops,
-				  struct gpd_timing_data *td);
-extern int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td);
 extern int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state);
 extern int pm_genpd_name_attach_cpuidle(const char *name, int state);
 extern int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd);
@@ -217,16 +213,6 @@ static inline int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 {
 	return -ENOSYS;
 }
-static inline int pm_genpd_add_callbacks(struct device *dev,
-					 struct gpd_dev_ops *ops,
-					 struct gpd_timing_data *td)
-{
-	return -ENOSYS;
-}
-static inline int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td)
-{
-	return -ENOSYS;
-}
 static inline int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int st)
 {
 	return -ENOSYS;
@@ -281,11 +267,6 @@ static inline int pm_genpd_name_add_device(const char *domain_name,
 	return __pm_genpd_name_add_device(domain_name, dev, NULL);
 }
 
-static inline int pm_genpd_remove_callbacks(struct device *dev)
-{
-	return __pm_genpd_remove_callbacks(dev, true);
-}
-
 #ifdef CONFIG_PM_GENERIC_DOMAINS_RUNTIME
 extern void genpd_queue_power_off_work(struct generic_pm_domain *genpd);
 extern void pm_genpd_poweroff_unused(void);
-- 
cgit v1.2.3


From 67da6d4bf43c4208433ef8f3ee487401b4dc9c74 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 3 Sep 2014 12:52:18 +0200
Subject: PM / domains: Ignore callbacks for subsys generic_pm_domain_data

In a step of simplifying the generic power domain let's move away from
using these callbacks.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 131 +++-----------------------------------------
 include/linux/pm_domain.h   |   1 -
 2 files changed, 8 insertions(+), 124 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e613e3cb96d8..aa5b14c1e643 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -25,10 +25,6 @@
 	__routine = genpd->dev_ops.callback; 			\
 	if (__routine) {					\
 		__ret = __routine(dev); 			\
-	} else {						\
-		__routine = dev_gpd_data(dev)->ops.callback;	\
-		if (__routine) 					\
-			__ret = __routine(dev);			\
 	}							\
 	__ret;							\
 })
@@ -1871,10 +1867,6 @@ static int pm_genpd_default_save_state(struct device *dev)
 {
 	int (*cb)(struct device *__dev);
 
-	cb = dev_gpd_data(dev)->ops.save_state;
-	if (cb)
-		return cb(dev);
-
 	if (dev->type && dev->type->pm)
 		cb = dev->type->pm->runtime_suspend;
 	else if (dev->class && dev->class->pm)
@@ -1898,10 +1890,6 @@ static int pm_genpd_default_restore_state(struct device *dev)
 {
 	int (*cb)(struct device *__dev);
 
-	cb = dev_gpd_data(dev)->ops.restore_state;
-	if (cb)
-		return cb(dev);
-
 	if (dev->type && dev->type->pm)
 		cb = dev->type->pm->runtime_resume;
 	else if (dev->class && dev->class->pm)
@@ -1917,109 +1905,6 @@ static int pm_genpd_default_restore_state(struct device *dev)
 	return cb ? cb(dev) : 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-
-/**
- * pm_genpd_default_suspend - Default "device suspend" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_suspend(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.suspend;
-
-	return cb ? cb(dev) : pm_generic_suspend(dev);
-}
-
-/**
- * pm_genpd_default_suspend_late - Default "late device suspend" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_suspend_late(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.suspend_late;
-
-	return cb ? cb(dev) : pm_generic_suspend_late(dev);
-}
-
-/**
- * pm_genpd_default_resume_early - Default "early device resume" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_resume_early(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.resume_early;
-
-	return cb ? cb(dev) : pm_generic_resume_early(dev);
-}
-
-/**
- * pm_genpd_default_resume - Default "device resume" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_resume(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.resume;
-
-	return cb ? cb(dev) : pm_generic_resume(dev);
-}
-
-/**
- * pm_genpd_default_freeze - Default "device freeze" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_freeze(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.freeze;
-
-	return cb ? cb(dev) : pm_generic_freeze(dev);
-}
-
-/**
- * pm_genpd_default_freeze_late - Default "late device freeze" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_freeze_late(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.freeze_late;
-
-	return cb ? cb(dev) : pm_generic_freeze_late(dev);
-}
-
-/**
- * pm_genpd_default_thaw_early - Default "early device thaw" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_thaw_early(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.thaw_early;
-
-	return cb ? cb(dev) : pm_generic_thaw_early(dev);
-}
-
-/**
- * pm_genpd_default_thaw - Default "device thaw" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_thaw(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.thaw;
-
-	return cb ? cb(dev) : pm_generic_thaw(dev);
-}
-
-#else /* !CONFIG_PM_SLEEP */
-
-#define pm_genpd_default_suspend	NULL
-#define pm_genpd_default_suspend_late	NULL
-#define pm_genpd_default_resume_early	NULL
-#define pm_genpd_default_resume		NULL
-#define pm_genpd_default_freeze		NULL
-#define pm_genpd_default_freeze_late	NULL
-#define pm_genpd_default_thaw_early	NULL
-#define pm_genpd_default_thaw		NULL
-
-#endif /* !CONFIG_PM_SLEEP */
-
 /**
  * pm_genpd_init - Initialize a generic I/O PM domain object.
  * @genpd: PM domain object to initialize.
@@ -2071,14 +1956,14 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->domain.ops.complete = pm_genpd_complete;
 	genpd->dev_ops.save_state = pm_genpd_default_save_state;
 	genpd->dev_ops.restore_state = pm_genpd_default_restore_state;
-	genpd->dev_ops.suspend = pm_genpd_default_suspend;
-	genpd->dev_ops.suspend_late = pm_genpd_default_suspend_late;
-	genpd->dev_ops.resume_early = pm_genpd_default_resume_early;
-	genpd->dev_ops.resume = pm_genpd_default_resume;
-	genpd->dev_ops.freeze = pm_genpd_default_freeze;
-	genpd->dev_ops.freeze_late = pm_genpd_default_freeze_late;
-	genpd->dev_ops.thaw_early = pm_genpd_default_thaw_early;
-	genpd->dev_ops.thaw = pm_genpd_default_thaw;
+	genpd->dev_ops.suspend = pm_generic_suspend;
+	genpd->dev_ops.suspend_late = pm_generic_suspend_late;
+	genpd->dev_ops.resume_early = pm_generic_resume_early;
+	genpd->dev_ops.resume = pm_generic_resume;
+	genpd->dev_ops.freeze = pm_generic_freeze;
+	genpd->dev_ops.freeze_late = pm_generic_freeze_late;
+	genpd->dev_ops.thaw_early = pm_generic_thaw_early;
+	genpd->dev_ops.thaw = pm_generic_thaw;
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 9ae2b9e88d61..436ea149d40c 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -108,7 +108,6 @@ struct gpd_timing_data {
 
 struct generic_pm_domain_data {
 	struct pm_domain_data base;
-	struct gpd_dev_ops ops;
 	struct gpd_timing_data td;
 	struct notifier_block nb;
 	struct mutex lock;
-- 
cgit v1.2.3


From 1e0407ca54d28db8e5f02e437ff21cc6416c0be8 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 3 Sep 2014 12:52:19 +0200
Subject: PM / domains: Remove system PM callbacks from gpd_dev_ops

There no users of these callbacks, let's simplify the generic power
domain by removing them.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 64 ++++++---------------------------------------
 include/linux/pm_domain.h   |  8 ------
 2 files changed, 8 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index aa5b14c1e643..e777609ccc77 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -770,46 +770,6 @@ static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
 	return GENPD_DEV_CALLBACK(genpd, bool, active_wakeup, dev);
 }
 
-static int genpd_suspend_dev(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, suspend, dev);
-}
-
-static int genpd_suspend_late(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, suspend_late, dev);
-}
-
-static int genpd_resume_early(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, resume_early, dev);
-}
-
-static int genpd_resume_dev(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, resume, dev);
-}
-
-static int genpd_freeze_dev(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, freeze, dev);
-}
-
-static int genpd_freeze_late(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, freeze_late, dev);
-}
-
-static int genpd_thaw_early(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, thaw_early, dev);
-}
-
-static int genpd_thaw_dev(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, thaw, dev);
-}
-
 /**
  * pm_genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
  * @genpd: PM domain to power off, if possible.
@@ -991,7 +951,7 @@ static int pm_genpd_suspend(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_suspend_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_suspend(dev);
 }
 
 /**
@@ -1012,7 +972,7 @@ static int pm_genpd_suspend_late(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_suspend_late(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_suspend_late(dev);
 }
 
 /**
@@ -1099,7 +1059,7 @@ static int pm_genpd_resume_early(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_resume_early(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_resume_early(dev);
 }
 
 /**
@@ -1120,7 +1080,7 @@ static int pm_genpd_resume(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_resume_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_resume(dev);
 }
 
 /**
@@ -1141,7 +1101,7 @@ static int pm_genpd_freeze(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_freeze_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_freeze(dev);
 }
 
 /**
@@ -1163,7 +1123,7 @@ static int pm_genpd_freeze_late(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_freeze_late(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_freeze_late(dev);
 }
 
 /**
@@ -1227,7 +1187,7 @@ static int pm_genpd_thaw_early(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_thaw_early(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_thaw_early(dev);
 }
 
 /**
@@ -1248,7 +1208,7 @@ static int pm_genpd_thaw(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_thaw_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_thaw(dev);
 }
 
 /**
@@ -1956,14 +1916,6 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->domain.ops.complete = pm_genpd_complete;
 	genpd->dev_ops.save_state = pm_genpd_default_save_state;
 	genpd->dev_ops.restore_state = pm_genpd_default_restore_state;
-	genpd->dev_ops.suspend = pm_generic_suspend;
-	genpd->dev_ops.suspend_late = pm_generic_suspend_late;
-	genpd->dev_ops.resume_early = pm_generic_resume_early;
-	genpd->dev_ops.resume = pm_generic_resume;
-	genpd->dev_ops.freeze = pm_generic_freeze;
-	genpd->dev_ops.freeze_late = pm_generic_freeze_late;
-	genpd->dev_ops.thaw_early = pm_generic_thaw_early;
-	genpd->dev_ops.thaw = pm_generic_thaw;
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 436ea149d40c..b6343d4b9b04 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -35,14 +35,6 @@ struct gpd_dev_ops {
 	int (*stop)(struct device *dev);
 	int (*save_state)(struct device *dev);
 	int (*restore_state)(struct device *dev);
-	int (*suspend)(struct device *dev);
-	int (*suspend_late)(struct device *dev);
-	int (*resume_early)(struct device *dev);
-	int (*resume)(struct device *dev);
-	int (*freeze)(struct device *dev);
-	int (*freeze_late)(struct device *dev);
-	int (*thaw_early)(struct device *dev);
-	int (*thaw)(struct device *dev);
 	bool (*active_wakeup)(struct device *dev);
 };
 
-- 
cgit v1.2.3


From c5d79ec2a5715489cff16a0d1cf4fa9108a5509e Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 3 Sep 2014 12:52:22 +0200
Subject: PM / domains: Remove dev_irq_safe from genpd config

The genpd dev_irq_safe configuration somewhat overlaps with the runtime
PM pm_runtime_irq_safe() option. Also, currently genpd don't have a
good way to deal with these device. So, until we figured out if and how
to support this in genpd, let's remove the option to configure it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 4 ----
 include/linux/pm_domain.h   | 1 -
 2 files changed, 5 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e777609ccc77..4298a2bcd228 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -615,8 +615,6 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	might_sleep_if(!genpd->dev_irq_safe);
-
 	stop_ok = genpd->gov ? genpd->gov->stop_ok : NULL;
 	if (stop_ok && !stop_ok(dev))
 		return -EBUSY;
@@ -661,8 +659,6 @@ static int pm_genpd_runtime_resume(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	might_sleep_if(!genpd->dev_irq_safe);
-
 	/* If power.irq_safe, the PM domain is never powered off. */
 	if (dev->power.irq_safe)
 		return genpd_start_dev_no_timing(genpd, dev);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index b6343d4b9b04..360c94ceeebb 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -63,7 +63,6 @@ struct generic_pm_domain {
 	unsigned int suspended_count;	/* System suspend device counter */
 	unsigned int prepared_count;	/* Suspend counter of prepared devices */
 	bool suspend_power_off;	/* Power status before system suspend */
-	bool dev_irq_safe;	/* Device callbacks are IRQ-safe */
 	int (*power_off)(struct generic_pm_domain *domain);
 	s64 power_off_latency_ns;
 	int (*power_on)(struct generic_pm_domain *domain);
-- 
cgit v1.2.3


From d47e6464ae6c96735d4706f5cb0537fe717b6b00 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 3 Sep 2014 12:52:24 +0200
Subject: PM / domains: Remove pm_genpd_syscore_switch() API

The pm_genpd_syscore_poweroff() API and pm_genpd_syscore_poweron() API
makes the pm_genpd_syscore_switch() API redundant.

Moreover, since there are no active users, let's just remove it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 17 ++++++++++++++---
 include/linux/pm_domain.h   | 16 ++++------------
 2 files changed, 18 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index b910d0f6ff60..601e35b2fa71 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1292,13 +1292,13 @@ static void pm_genpd_complete(struct device *dev)
 }
 
 /**
- * pm_genpd_syscore_switch - Switch power during system core suspend or resume.
+ * genpd_syscore_switch - Switch power during system core suspend or resume.
  * @dev: Device that normally is marked as "always on" to switch power for.
  *
  * This routine may only be called during the system core (syscore) suspend or
  * resume phase for devices whose "always on" flags are set.
  */
-void pm_genpd_syscore_switch(struct device *dev, bool suspend)
+static void genpd_syscore_switch(struct device *dev, bool suspend)
 {
 	struct generic_pm_domain *genpd;
 
@@ -1314,7 +1314,18 @@ void pm_genpd_syscore_switch(struct device *dev, bool suspend)
 		genpd->suspended_count--;
 	}
 }
-EXPORT_SYMBOL_GPL(pm_genpd_syscore_switch);
+
+void pm_genpd_syscore_poweroff(struct device *dev)
+{
+	genpd_syscore_switch(dev, true);
+}
+EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweroff);
+
+void pm_genpd_syscore_poweron(struct device *dev)
+{
+	genpd_syscore_switch(dev, false);
+}
+EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
 
 #else
 
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 360c94ceeebb..3997af691600 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -266,19 +266,11 @@ static inline void pm_genpd_poweroff_unused(void) {}
 #endif
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP
-extern void pm_genpd_syscore_switch(struct device *dev, bool suspend);
+extern void pm_genpd_syscore_poweroff(struct device *dev);
+extern void pm_genpd_syscore_poweron(struct device *dev);
 #else
-static inline void pm_genpd_syscore_switch(struct device *dev, bool suspend) {}
+static inline void pm_genpd_syscore_poweroff(struct device *dev) {}
+static inline void pm_genpd_syscore_poweron(struct device *dev) {}
 #endif
 
-static inline void pm_genpd_syscore_poweroff(struct device *dev)
-{
-	pm_genpd_syscore_switch(dev, true);
-}
-
-static inline void pm_genpd_syscore_poweron(struct device *dev)
-{
-	pm_genpd_syscore_switch(dev, false);
-}
-
 #endif /* _LINUX_PM_DOMAIN_H */
-- 
cgit v1.2.3


From d971f0b0eaaf3f2086bf21bbd64f7ea7e2f28459 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 3 Sep 2014 12:52:25 +0200
Subject: PM / domains: Remove genpd_queue_power_off_work() API

There are no active users of this API. Let's remove it and if future
needs shows up we could consider to have a get/put API instead.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 5 ++++-
 include/linux/pm_domain.h   | 2 --
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 601e35b2fa71..d71d0458d41f 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -422,7 +422,7 @@ static bool genpd_abort_poweroff(struct generic_pm_domain *genpd)
  * Queue up the execution of pm_genpd_poweroff() unless it's already been done
  * before.
  */
-void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
+static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
 {
 	queue_work(pm_wq, &genpd->power_off_work);
 }
@@ -729,6 +729,9 @@ static inline int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+static inline void
+genpd_queue_power_off_work(struct generic_pm_domain *genpd) {}
+
 static inline void genpd_power_off_work_fn(struct work_struct *work) {}
 
 #define pm_genpd_runtime_suspend	NULL
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 3997af691600..c19c90b839b8 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -258,10 +258,8 @@ static inline int pm_genpd_name_add_device(const char *domain_name,
 }
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS_RUNTIME
-extern void genpd_queue_power_off_work(struct generic_pm_domain *genpd);
 extern void pm_genpd_poweroff_unused(void);
 #else
-static inline void genpd_queue_power_off_work(struct generic_pm_domain *gpd) {}
 static inline void pm_genpd_poweroff_unused(void) {}
 #endif
 
-- 
cgit v1.2.3


From 0f574d4c3a7a325cbbef28ee738dedca9851e957 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 3 Sep 2014 12:52:30 +0200
Subject: PM / domains: Remove default_stop_ok() API

There are currently no need to export default_stop_ok() as an API,
instead let's keep it local to the PM domain governor.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain_governor.c | 7 ++-----
 include/linux/pm_domain.h            | 6 ------
 2 files changed, 2 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index a089e3bcdfbc..d88a62e104d4 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -42,7 +42,7 @@ static int dev_update_qos_constraint(struct device *dev, void *data)
  * default_stop_ok - Default PM domain governor routine for stopping devices.
  * @dev: Device to check.
  */
-bool default_stop_ok(struct device *dev)
+static bool default_stop_ok(struct device *dev)
 {
 	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
 	unsigned long flags;
@@ -229,10 +229,7 @@ static bool always_on_power_down_ok(struct dev_pm_domain *domain)
 
 #else /* !CONFIG_PM_RUNTIME */
 
-bool default_stop_ok(struct device *dev)
-{
-	return false;
-}
+static inline bool default_stop_ok(struct device *dev) { return false; }
 
 #define default_power_down_ok	NULL
 #define always_on_power_down_ok	NULL
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index c19c90b839b8..3b59f296e6ec 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -151,8 +151,6 @@ extern void pm_genpd_init(struct generic_pm_domain *genpd,
 extern int pm_genpd_poweron(struct generic_pm_domain *genpd);
 extern int pm_genpd_name_poweron(const char *domain_name);
 
-extern bool default_stop_ok(struct device *dev);
-
 extern struct dev_power_governor pm_domain_always_on_gov;
 #else
 
@@ -231,10 +229,6 @@ static inline int pm_genpd_name_poweron(const char *domain_name)
 {
 	return -ENOSYS;
 }
-static inline bool default_stop_ok(struct device *dev)
-{
-	return false;
-}
 #define simple_qos_governor NULL
 #define pm_domain_always_on_gov NULL
 #endif
-- 
cgit v1.2.3


From ae3c511c2d72161b11e93866203b59a3a37dfac7 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 3 Sep 2014 12:52:31 +0200
Subject: PM / domains: Keep declaration of dev_power_governors together

This is a pure code cleanup in the header file for the PM domain. No
functional change.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm_domain.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 3b59f296e6ec..aa03586c94a2 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -117,8 +117,6 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
 	return to_gpd_data(dev->power.subsys_data->domain_data);
 }
 
-extern struct dev_power_governor simple_qos_governor;
-
 extern struct generic_pm_domain *dev_to_genpd(struct device *dev);
 extern int __pm_genpd_add_device(struct generic_pm_domain *genpd,
 				 struct device *dev,
@@ -151,6 +149,7 @@ extern void pm_genpd_init(struct generic_pm_domain *genpd,
 extern int pm_genpd_poweron(struct generic_pm_domain *genpd);
 extern int pm_genpd_name_poweron(const char *domain_name);
 
+extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
 #else
 
-- 
cgit v1.2.3


From ff7693d079e58fb62d735b7b8085b53fcfb74528 Mon Sep 17 00:00:00 2001
From: Carlo Caione <carlo@caione.org>
Date: Sun, 17 Aug 2014 12:49:49 +0200
Subject: ARM: meson: serial: add MesonX SoC on-chip uart driver

The SoC has four fully functional UARTs which use the same programming
model. They are named UART_A, UART_B, UART_C and UART_AO (Always-On)
which cannot be powered off.

Signed-off-by: Carlo Caione <carlo@caione.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/Kconfig       |  18 ++
 drivers/tty/serial/Makefile      |   1 +
 drivers/tty/serial/meson_uart.c  | 634 +++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/serial_core.h |   3 +
 4 files changed, 656 insertions(+)
 create mode 100644 drivers/tty/serial/meson_uart.c

(limited to 'include')

diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 75cc59f5d253..636949d8144d 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -200,6 +200,24 @@ config SERIAL_KS8695_CONSOLE
 	  receives all kernel messages and warnings and which allows
 	  logins in single user mode).
 
+config SERIAL_MESON
+	tristate "Meson serial port support"
+	depends on ARCH_MESON
+	select SERIAL_CORE
+	help
+	  This enables the driver for the on-chip UARTs of the Amlogic
+	  MesonX processors.
+
+config SERIAL_MESON_CONSOLE
+	bool "Support for console on meson"
+	depends on SERIAL_MESON=y
+	select SERIAL_CORE_CONSOLE
+	help
+	  Say Y here if you wish to use a Amlogic MesonX UART as the
+	  system console (the system console is the device which
+	  receives all kernel messages and warnings and which allows
+	  logins in single user mode) as /dev/ttyAMLx.
+
 config SERIAL_CLPS711X
 	tristate "CLPS711X serial port support"
 	depends on ARCH_CLPS711X || COMPILE_TEST
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index 0080cc362e09..9a548acf5fdc 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_SERIAL_MPC52xx) += mpc52xx_uart.o
 obj-$(CONFIG_SERIAL_ICOM) += icom.o
 obj-$(CONFIG_SERIAL_M32R_SIO) += m32r_sio.o
 obj-$(CONFIG_SERIAL_MPSC) += mpsc.o
+obj-$(CONFIG_SERIAL_MESON) += meson_uart.o
 obj-$(CONFIG_SERIAL_SB1250_DUART) += sb1250-duart.o
 obj-$(CONFIG_ETRAX_SERIAL) += crisv10.o
 obj-$(CONFIG_SERIAL_SCCNXP) += sccnxp.o
diff --git a/drivers/tty/serial/meson_uart.c b/drivers/tty/serial/meson_uart.c
new file mode 100644
index 000000000000..15c749753317
--- /dev/null
+++ b/drivers/tty/serial/meson_uart.c
@@ -0,0 +1,634 @@
+/*
+ *  Based on meson_uart.c, by AMLOGIC, INC.
+ *
+ * Copyright (C) 2014 Carlo Caione <carlo@caione.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/serial.h>
+#include <linux/serial_core.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+
+/* Register offsets */
+#define AML_UART_WFIFO			0x00
+#define AML_UART_RFIFO			0x04
+#define AML_UART_CONTROL		0x08
+#define AML_UART_STATUS			0x0c
+#define AML_UART_MISC			0x10
+#define AML_UART_REG5			0x14
+
+/* AML_UART_CONTROL bits */
+#define AML_UART_TX_EN			BIT(12)
+#define AML_UART_RX_EN			BIT(13)
+#define AML_UART_TX_RST			BIT(22)
+#define AML_UART_RX_RST			BIT(23)
+#define AML_UART_CLR_ERR		BIT(24)
+#define AML_UART_RX_INT_EN		BIT(27)
+#define AML_UART_TX_INT_EN		BIT(28)
+#define AML_UART_DATA_LEN_MASK		(0x03 << 20)
+#define AML_UART_DATA_LEN_8BIT		(0x00 << 20)
+#define AML_UART_DATA_LEN_7BIT		(0x01 << 20)
+#define AML_UART_DATA_LEN_6BIT		(0x02 << 20)
+#define AML_UART_DATA_LEN_5BIT		(0x03 << 20)
+
+/* AML_UART_STATUS bits */
+#define AML_UART_PARITY_ERR		BIT(16)
+#define AML_UART_FRAME_ERR		BIT(17)
+#define AML_UART_TX_FIFO_WERR		BIT(18)
+#define AML_UART_RX_EMPTY		BIT(20)
+#define AML_UART_TX_FULL		BIT(21)
+#define AML_UART_TX_EMPTY		BIT(22)
+#define AML_UART_ERR			(AML_UART_PARITY_ERR | \
+					 AML_UART_FRAME_ERR  | \
+					 AML_UART_TX_FIFO_WERR)
+
+/* AML_UART_CONTROL bits */
+#define AML_UART_TWO_WIRE_EN		BIT(15)
+#define AML_UART_PARITY_TYPE		BIT(18)
+#define AML_UART_PARITY_EN		BIT(19)
+#define AML_UART_CLEAR_ERR		BIT(24)
+#define AML_UART_STOP_BIN_LEN_MASK	(0x03 << 16)
+#define AML_UART_STOP_BIN_1SB		(0x00 << 16)
+#define AML_UART_STOP_BIN_2SB		(0x01 << 16)
+
+/* AML_UART_MISC bits */
+#define AML_UART_XMIT_IRQ(c)		(((c) & 0xff) << 8)
+#define AML_UART_RECV_IRQ(c)		((c) & 0xff)
+
+/* AML_UART_REG5 bits */
+#define AML_UART_BAUD_MASK		0x7fffff
+#define AML_UART_BAUD_USE		BIT(23)
+
+#define AML_UART_PORT_NUM		6
+#define AML_UART_DEV_NAME		"ttyAML"
+
+
+static struct uart_driver meson_uart_driver;
+
+static struct uart_port *meson_ports[AML_UART_PORT_NUM];
+
+static void meson_uart_set_mctrl(struct uart_port *port, unsigned int mctrl)
+{
+}
+
+static unsigned int meson_uart_get_mctrl(struct uart_port *port)
+{
+	return TIOCM_CTS;
+}
+
+static unsigned int meson_uart_tx_empty(struct uart_port *port)
+{
+	u32 val;
+
+	val = readl(port->membase + AML_UART_STATUS);
+	return (val & AML_UART_TX_EMPTY) ? TIOCSER_TEMT : 0;
+}
+
+static void meson_uart_stop_tx(struct uart_port *port)
+{
+	u32 val;
+
+	val = readl(port->membase + AML_UART_CONTROL);
+	val &= ~AML_UART_TX_EN;
+	writel(val, port->membase + AML_UART_CONTROL);
+}
+
+static void meson_uart_stop_rx(struct uart_port *port)
+{
+	u32 val;
+
+	val = readl(port->membase + AML_UART_CONTROL);
+	val &= ~AML_UART_RX_EN;
+	writel(val, port->membase + AML_UART_CONTROL);
+}
+
+static void meson_uart_shutdown(struct uart_port *port)
+{
+	unsigned long flags;
+	u32 val;
+
+	free_irq(port->irq, port);
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	val = readl(port->membase + AML_UART_CONTROL);
+	val &= ~(AML_UART_RX_EN | AML_UART_TX_EN);
+	val &= ~(AML_UART_RX_INT_EN | AML_UART_TX_INT_EN);
+	writel(val, port->membase + AML_UART_CONTROL);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static void meson_uart_start_tx(struct uart_port *port)
+{
+	struct circ_buf *xmit = &port->state->xmit;
+	unsigned int ch;
+
+	if (uart_tx_stopped(port)) {
+		meson_uart_stop_tx(port);
+		return;
+	}
+
+	while (!(readl(port->membase + AML_UART_STATUS) & AML_UART_TX_FULL)) {
+		if (port->x_char) {
+			writel(port->x_char, port->membase + AML_UART_WFIFO);
+			port->icount.tx++;
+			port->x_char = 0;
+			continue;
+		}
+
+		if (uart_circ_empty(xmit))
+			break;
+
+		ch = xmit->buf[xmit->tail];
+		writel(ch, port->membase + AML_UART_WFIFO);
+		xmit->tail = (xmit->tail+1) & (SERIAL_XMIT_SIZE - 1);
+		port->icount.tx++;
+	}
+
+	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
+		uart_write_wakeup(port);
+}
+
+static void meson_receive_chars(struct uart_port *port)
+{
+	struct tty_port *tport = &port->state->port;
+	char flag;
+	u32 status, ch, mode;
+
+	do {
+		flag = TTY_NORMAL;
+		port->icount.rx++;
+		status = readl(port->membase + AML_UART_STATUS);
+
+		if (status & AML_UART_ERR) {
+			if (status & AML_UART_TX_FIFO_WERR)
+				port->icount.overrun++;
+			else if (status & AML_UART_FRAME_ERR)
+				port->icount.frame++;
+			else if (status & AML_UART_PARITY_ERR)
+				port->icount.frame++;
+
+			mode = readl(port->membase + AML_UART_CONTROL);
+			mode |= AML_UART_CLEAR_ERR;
+			writel(mode, port->membase + AML_UART_CONTROL);
+
+			/* It doesn't clear to 0 automatically */
+			mode &= ~AML_UART_CLEAR_ERR;
+			writel(mode, port->membase + AML_UART_CONTROL);
+
+			status &= port->read_status_mask;
+			if (status & AML_UART_FRAME_ERR)
+				flag = TTY_FRAME;
+			else if (status & AML_UART_PARITY_ERR)
+				flag = TTY_PARITY;
+		}
+
+		ch = readl(port->membase + AML_UART_RFIFO);
+		ch &= 0xff;
+
+		if ((status & port->ignore_status_mask) == 0)
+			tty_insert_flip_char(tport, ch, flag);
+
+		if (status & AML_UART_TX_FIFO_WERR)
+			tty_insert_flip_char(tport, 0, TTY_OVERRUN);
+
+	} while (!(readl(port->membase + AML_UART_STATUS) & AML_UART_RX_EMPTY));
+
+	spin_unlock(&port->lock);
+	tty_flip_buffer_push(tport);
+	spin_lock(&port->lock);
+}
+
+static irqreturn_t meson_uart_interrupt(int irq, void *dev_id)
+{
+	struct uart_port *port = (struct uart_port *)dev_id;
+
+	spin_lock(&port->lock);
+
+	if (!(readl(port->membase + AML_UART_STATUS) & AML_UART_RX_EMPTY))
+		meson_receive_chars(port);
+
+	if (!(readl(port->membase + AML_UART_STATUS) & AML_UART_TX_FULL))
+		meson_uart_start_tx(port);
+
+	spin_unlock(&port->lock);
+
+	return IRQ_HANDLED;
+}
+
+static const char *meson_uart_type(struct uart_port *port)
+{
+	return (port->type == PORT_MESON) ? "meson_uart" : NULL;
+}
+
+static int meson_uart_startup(struct uart_port *port)
+{
+	u32 val;
+	int ret = 0;
+
+	val = readl(port->membase + AML_UART_CONTROL);
+	val |= (AML_UART_RX_RST | AML_UART_TX_RST | AML_UART_CLR_ERR);
+	writel(val, port->membase + AML_UART_CONTROL);
+
+	val &= ~(AML_UART_RX_RST | AML_UART_TX_RST | AML_UART_CLR_ERR);
+	writel(val, port->membase + AML_UART_CONTROL);
+
+	val |= (AML_UART_RX_EN | AML_UART_TX_EN);
+	writel(val, port->membase + AML_UART_CONTROL);
+
+	val |= (AML_UART_RX_INT_EN | AML_UART_TX_INT_EN);
+	writel(val, port->membase + AML_UART_CONTROL);
+
+	val = (AML_UART_RECV_IRQ(1) | AML_UART_XMIT_IRQ(port->fifosize / 2));
+	writel(val, port->membase + AML_UART_MISC);
+
+	ret = request_irq(port->irq, meson_uart_interrupt, 0,
+			  meson_uart_type(port), port);
+
+	return ret;
+}
+
+static void meson_uart_change_speed(struct uart_port *port, unsigned long baud)
+{
+	u32 val;
+
+	while (!(readl(port->membase + AML_UART_STATUS) & AML_UART_TX_EMPTY))
+		cpu_relax();
+
+	val = readl(port->membase + AML_UART_REG5);
+	val &= ~AML_UART_BAUD_MASK;
+	val = ((port->uartclk * 10 / (baud * 4) + 5) / 10) - 1;
+	val |= AML_UART_BAUD_USE;
+	writel(val, port->membase + AML_UART_REG5);
+}
+
+static void meson_uart_set_termios(struct uart_port *port,
+				   struct ktermios *termios,
+				   struct ktermios *old)
+{
+	unsigned int cflags, iflags, baud;
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	cflags = termios->c_cflag;
+	iflags = termios->c_iflag;
+
+	val = readl(port->membase + AML_UART_CONTROL);
+
+	val &= ~AML_UART_DATA_LEN_MASK;
+	switch (cflags & CSIZE) {
+	case CS8:
+		val |= AML_UART_DATA_LEN_8BIT;
+		break;
+	case CS7:
+		val |= AML_UART_DATA_LEN_7BIT;
+		break;
+	case CS6:
+		val |= AML_UART_DATA_LEN_6BIT;
+		break;
+	case CS5:
+		val |= AML_UART_DATA_LEN_5BIT;
+		break;
+	}
+
+	if (cflags & PARENB)
+		val |= AML_UART_PARITY_EN;
+	else
+		val &= ~AML_UART_PARITY_EN;
+
+	if (cflags & PARODD)
+		val |= AML_UART_PARITY_TYPE;
+	else
+		val &= ~AML_UART_PARITY_TYPE;
+
+	val &= ~AML_UART_STOP_BIN_LEN_MASK;
+	if (cflags & CSTOPB)
+		val |= AML_UART_STOP_BIN_2SB;
+	else
+		val &= ~AML_UART_STOP_BIN_1SB;
+
+	if (cflags & CRTSCTS)
+		val &= ~AML_UART_TWO_WIRE_EN;
+	else
+		val |= AML_UART_TWO_WIRE_EN;
+
+	writel(val, port->membase + AML_UART_CONTROL);
+
+	baud = uart_get_baud_rate(port, termios, old, 9600, 115200);
+	meson_uart_change_speed(port, baud);
+
+	port->read_status_mask = AML_UART_TX_FIFO_WERR;
+	if (iflags & INPCK)
+		port->read_status_mask |= AML_UART_PARITY_ERR |
+					  AML_UART_FRAME_ERR;
+
+	port->ignore_status_mask = 0;
+	if (iflags & IGNPAR)
+		port->ignore_status_mask |= AML_UART_PARITY_ERR |
+					    AML_UART_FRAME_ERR;
+
+	uart_update_timeout(port, termios->c_cflag, baud);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static int meson_uart_verify_port(struct uart_port *port,
+				  struct serial_struct *ser)
+{
+	int ret = 0;
+
+	if (port->type != PORT_MESON)
+		ret = -EINVAL;
+	if (port->irq != ser->irq)
+		ret = -EINVAL;
+	if (ser->baud_base < 9600)
+		ret = -EINVAL;
+	return ret;
+}
+
+static void meson_uart_release_port(struct uart_port *port)
+{
+	if (port->flags & UPF_IOREMAP) {
+		iounmap(port->membase);
+		port->membase = NULL;
+	}
+}
+
+static int meson_uart_request_port(struct uart_port *port)
+{
+	struct platform_device *pdev = to_platform_device(port->dev);
+	struct resource *res;
+	int size;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "cannot obtain I/O memory region");
+		return -ENODEV;
+	}
+	size = resource_size(res);
+
+	if (!devm_request_mem_region(port->dev, port->mapbase, size,
+				     dev_name(port->dev))) {
+		dev_err(port->dev, "Memory region busy\n");
+		return -EBUSY;
+	}
+
+	if (port->flags & UPF_IOREMAP) {
+		port->membase = devm_ioremap_nocache(port->dev,
+						     port->mapbase,
+						     size);
+		if (port->membase == NULL)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void meson_uart_config_port(struct uart_port *port, int flags)
+{
+	if (flags & UART_CONFIG_TYPE) {
+		port->type = PORT_MESON;
+		meson_uart_request_port(port);
+	}
+}
+
+static struct uart_ops meson_uart_ops = {
+	.set_mctrl      = meson_uart_set_mctrl,
+	.get_mctrl      = meson_uart_get_mctrl,
+	.tx_empty	= meson_uart_tx_empty,
+	.start_tx	= meson_uart_start_tx,
+	.stop_tx	= meson_uart_stop_tx,
+	.stop_rx	= meson_uart_stop_rx,
+	.startup	= meson_uart_startup,
+	.shutdown	= meson_uart_shutdown,
+	.set_termios	= meson_uart_set_termios,
+	.type		= meson_uart_type,
+	.config_port	= meson_uart_config_port,
+	.request_port	= meson_uart_request_port,
+	.release_port	= meson_uart_release_port,
+	.verify_port	= meson_uart_verify_port,
+};
+
+#ifdef CONFIG_SERIAL_MESON_CONSOLE
+
+static void meson_console_putchar(struct uart_port *port, int ch)
+{
+	if (!port->membase)
+		return;
+
+	while (readl(port->membase + AML_UART_STATUS) & AML_UART_TX_FULL)
+		cpu_relax();
+	writel(ch, port->membase + AML_UART_WFIFO);
+}
+
+static void meson_serial_console_write(struct console *co, const char *s,
+				       u_int count)
+{
+	struct uart_port *port;
+	unsigned long flags;
+	int locked;
+
+	port = meson_ports[co->index];
+	if (!port)
+		return;
+
+	local_irq_save(flags);
+	if (port->sysrq) {
+		locked = 0;
+	} else if (oops_in_progress) {
+		locked = spin_trylock(&port->lock);
+	} else {
+		spin_lock(&port->lock);
+		locked = 1;
+	}
+
+	uart_console_write(port, s, count, meson_console_putchar);
+
+	if (locked)
+		spin_unlock(&port->lock);
+	local_irq_restore(flags);
+}
+
+static int meson_serial_console_setup(struct console *co, char *options)
+{
+	struct uart_port *port;
+	int baud = 115200;
+	int bits = 8;
+	int parity = 'n';
+	int flow = 'n';
+
+	if (co->index < 0 || co->index >= AML_UART_PORT_NUM)
+		return -EINVAL;
+
+	port = meson_ports[co->index];
+	if (!port || !port->membase)
+		return -ENODEV;
+
+	if (options)
+		uart_parse_options(options, &baud, &parity, &bits, &flow);
+
+	return uart_set_options(port, co, baud, parity, bits, flow);
+}
+
+static struct console meson_serial_console = {
+	.name		= AML_UART_DEV_NAME,
+	.write		= meson_serial_console_write,
+	.device		= uart_console_device,
+	.setup		= meson_serial_console_setup,
+	.flags		= CON_PRINTBUFFER,
+	.index		= -1,
+	.data		= &meson_uart_driver,
+};
+
+static int __init meson_serial_console_init(void)
+{
+	register_console(&meson_serial_console);
+	return 0;
+}
+console_initcall(meson_serial_console_init);
+
+#define MESON_SERIAL_CONSOLE	(&meson_serial_console)
+#else
+#define MESON_SERIAL_CONSOLE	NULL
+#endif
+
+static struct uart_driver meson_uart_driver = {
+	.owner		= THIS_MODULE,
+	.driver_name	= "meson_uart",
+	.dev_name	= AML_UART_DEV_NAME,
+	.nr		= AML_UART_PORT_NUM,
+	.cons		= MESON_SERIAL_CONSOLE,
+};
+
+static int meson_uart_probe(struct platform_device *pdev)
+{
+	struct resource *res_mem, *res_irq;
+	struct uart_port *port;
+	struct clk *clk;
+	int ret = 0;
+
+	if (pdev->dev.of_node)
+		pdev->id = of_alias_get_id(pdev->dev.of_node, "serial");
+
+	if (pdev->id < 0 || pdev->id >= AML_UART_PORT_NUM)
+		return -EINVAL;
+
+	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res_mem)
+		return -ENODEV;
+
+	res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res_irq)
+		return -ENODEV;
+
+	if (meson_ports[pdev->id]) {
+		dev_err(&pdev->dev, "port %d already allocated\n", pdev->id);
+		return -EBUSY;
+	}
+
+	port = devm_kzalloc(&pdev->dev, sizeof(struct uart_port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+
+	clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	port->uartclk = clk_get_rate(clk);
+	port->iotype = UPIO_MEM;
+	port->mapbase = res_mem->start;
+	port->irq = res_irq->start;
+	port->flags = UPF_BOOT_AUTOCONF | UPF_IOREMAP | UPF_LOW_LATENCY;
+	port->dev = &pdev->dev;
+	port->line = pdev->id;
+	port->type = PORT_MESON;
+	port->x_char = 0;
+	port->ops = &meson_uart_ops;
+	port->fifosize = 64;
+
+	meson_ports[pdev->id] = port;
+	platform_set_drvdata(pdev, port);
+
+	ret = uart_add_one_port(&meson_uart_driver, port);
+	if (ret)
+		meson_ports[pdev->id] = NULL;
+
+	return ret;
+}
+
+static int meson_uart_remove(struct platform_device *pdev)
+{
+	struct uart_port *port;
+
+	port = platform_get_drvdata(pdev);
+	uart_remove_one_port(&meson_uart_driver, port);
+	meson_ports[pdev->id] = NULL;
+
+	return 0;
+}
+
+
+static const struct of_device_id meson_uart_dt_match[] = {
+	{ .compatible = "amlogic,meson-uart" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, meson_uart_dt_match);
+
+static  struct platform_driver meson_uart_platform_driver = {
+	.probe		= meson_uart_probe,
+	.remove		= meson_uart_remove,
+	.driver		= {
+		.owner		= THIS_MODULE,
+		.name		= "meson_uart",
+		.of_match_table	= meson_uart_dt_match,
+	},
+};
+
+static int __init meson_uart_init(void)
+{
+	int ret;
+
+	ret = uart_register_driver(&meson_uart_driver);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&meson_uart_platform_driver);
+	if (ret)
+		uart_unregister_driver(&meson_uart_driver);
+
+	return ret;
+}
+
+static void __exit meson_uart_exit(void)
+{
+	platform_driver_unregister(&meson_uart_platform_driver);
+	uart_unregister_driver(&meson_uart_driver);
+}
+
+module_init(meson_uart_init);
+module_exit(meson_uart_exit);
+
+MODULE_AUTHOR("Carlo Caione <carlo@caione.org>");
+MODULE_DESCRIPTION("Amlogic Meson serial port driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h
index 5820269aa132..16ad8521af6a 100644
--- a/include/uapi/linux/serial_core.h
+++ b/include/uapi/linux/serial_core.h
@@ -244,4 +244,7 @@
 /* SC16IS74xx */
 #define PORT_SC16IS7XX   108
 
+/* MESON */
+#define PORT_MESON	109
+
 #endif /* _UAPILINUX_SERIAL_CORE_H */
-- 
cgit v1.2.3


From 8a949b07e4062cbd07e04e6a47249e69ca65b944 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Tue, 2 Sep 2014 17:39:19 -0400
Subject: serial: core: Document lock requirement for UPF_* flags updates

The flags field of struct uart_port can only be safely modified
if the port mutex is held; no other lock prevents concurrent
changes from corrupting the field.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/serial_core.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index cf3a1e789bf5..8cb267b1fcd5 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -152,6 +152,7 @@ struct uart_port {
 	unsigned long		sysrq;			/* sysrq timeout */
 #endif
 
+	/* flags must be updated while holding port mutex */
 	upf_t			flags;
 
 #define UPF_FOURPORT		((__force upf_t) (1 << 1))
-- 
cgit v1.2.3


From b99b121b2aa42e60e5b73fdd3a49863337839c7b Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 5 Sep 2014 21:02:37 +0200
Subject: tty: serial: 8250_core: allow to overwrite & export
 serial8250_startup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The OMAP version of the 8250 can actually use 1:1 serial8250_startup().
However it needs to be extended by a wake up irq which should to be
requested & enabled at ->startup() time and disabled at ->shutdown() time.

v2…v3: properly copy callbacks
v1…v2: add shutdown callback

Acked-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_core.c | 25 +++++++++++++++++++++++--
 include/linux/serial_8250.h         |  2 ++
 include/linux/serial_core.h         |  2 ++
 3 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 90e0d5e2b7ee..872c020607a8 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -1930,7 +1930,7 @@ static void serial8250_put_poll_char(struct uart_port *port,
 
 #endif /* CONFIG_CONSOLE_POLL */
 
-static int serial8250_startup(struct uart_port *port)
+int serial8250_do_startup(struct uart_port *port)
 {
 	struct uart_8250_port *up = up_to_u8250p(port);
 	unsigned long flags;
@@ -2181,8 +2181,16 @@ dont_test_tx_en:
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(serial8250_do_startup);
 
-static void serial8250_shutdown(struct uart_port *port)
+static int serial8250_startup(struct uart_port *port)
+{
+	if (port->startup)
+		return port->startup(port);
+	return serial8250_do_startup(port);
+}
+
+void serial8250_do_shutdown(struct uart_port *port)
 {
 	struct uart_8250_port *up = up_to_u8250p(port);
 	unsigned long flags;
@@ -2232,6 +2240,15 @@ static void serial8250_shutdown(struct uart_port *port)
 	if (port->irq)
 		serial_unlink_irq_chain(up);
 }
+EXPORT_SYMBOL_GPL(serial8250_do_shutdown);
+
+static void serial8250_shutdown(struct uart_port *port)
+{
+	if (port->shutdown)
+		port->shutdown(port);
+	else
+		serial8250_do_shutdown(port);
+}
 
 static unsigned int serial8250_get_divisor(struct uart_port *port, unsigned int baud)
 {
@@ -3466,6 +3483,10 @@ int serial8250_register_8250_port(struct uart_8250_port *up)
 		/*  Possibly override set_termios call */
 		if (up->port.set_termios)
 			uart->port.set_termios = up->port.set_termios;
+		if (up->port.startup)
+			uart->port.startup = up->port.startup;
+		if (up->port.shutdown)
+			uart->port.shutdown = up->port.shutdown;
 		if (up->port.pm)
 			uart->port.pm = up->port.pm;
 		if (up->port.handle_break)
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index 6dd671765312..6fc9d7bee05e 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -124,6 +124,8 @@ extern void serial8250_early_out(struct uart_port *port, int offset, int value);
 extern int setup_early_serial8250_console(char *cmdline);
 extern void serial8250_do_set_termios(struct uart_port *port,
 		struct ktermios *termios, struct ktermios *old);
+extern int serial8250_do_startup(struct uart_port *port);
+extern void serial8250_do_shutdown(struct uart_port *port);
 extern void serial8250_do_pm(struct uart_port *port, unsigned int state,
 			     unsigned int oldstate);
 extern int fsl8250_handle_irq(struct uart_port *port);
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 8cb267b1fcd5..3bd7d55eebce 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -122,6 +122,8 @@ struct uart_port {
 	void			(*set_termios)(struct uart_port *,
 				               struct ktermios *new,
 				               struct ktermios *old);
+	int			(*startup)(struct uart_port *port);
+	void			(*shutdown)(struct uart_port *port);
 	int			(*handle_irq)(struct uart_port *);
 	void			(*pm)(struct uart_port *, unsigned int state,
 				      unsigned int old);
-- 
cgit v1.2.3


From a7f26b7e1ee73ac9e766c430fea5af658d839954 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 8 Sep 2014 19:08:34 -0400
Subject: inet: remove dead inetpeer sequence code

inetpeer sequence numbers are no longer incremented, so no need to
check and flush the tree. The function that increments the sequence
number was already dead code and removed in in "ipv4: remove unused
function" (068a6e18). Remove the code that checks for a change, too.

Verifying that v4_seq and v6_seq are never incremented and thus that
flush_check compares bp->flush_seq to 0 is trivial.

The second part of the change removes flush_check completely even
though bp->flush_seq is exactly !0 once, at initialization. This
change is correct because the time this branch is true is when
bp->root == peer_avl_empty_rcu, in which the branch and
inetpeer_invalidate_tree are a NOOP.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inetpeer.h |  1 -
 net/ipv4/inetpeer.c    | 21 ---------------------
 2 files changed, 22 deletions(-)

(limited to 'include')

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 01d590ee5e7e..80479abddf73 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -61,7 +61,6 @@ struct inet_peer {
 struct inet_peer_base {
 	struct inet_peer __rcu	*root;
 	seqlock_t		lock;
-	u32			flush_seq;
 	int			total;
 };
 
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index bd5f5928167d..241afd743d2c 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -72,29 +72,10 @@ void inet_peer_base_init(struct inet_peer_base *bp)
 {
 	bp->root = peer_avl_empty_rcu;
 	seqlock_init(&bp->lock);
-	bp->flush_seq = ~0U;
 	bp->total = 0;
 }
 EXPORT_SYMBOL_GPL(inet_peer_base_init);
 
-static atomic_t v4_seq = ATOMIC_INIT(0);
-static atomic_t v6_seq = ATOMIC_INIT(0);
-
-static atomic_t *inetpeer_seq_ptr(int family)
-{
-	return (family == AF_INET ? &v4_seq : &v6_seq);
-}
-
-static inline void flush_check(struct inet_peer_base *base, int family)
-{
-	atomic_t *fp = inetpeer_seq_ptr(family);
-
-	if (unlikely(base->flush_seq != atomic_read(fp))) {
-		inetpeer_invalidate_tree(base);
-		base->flush_seq = atomic_read(fp);
-	}
-}
-
 #define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */
 
 /* Exported for sysctl_net_ipv4.  */
@@ -444,8 +425,6 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 	unsigned int sequence;
 	int invalidated, gccnt = 0;
 
-	flush_check(base, daddr->family);
-
 	/* Attempt a lockless lookup first.
 	 * Because of a concurrent writer, we might not find an existing entry.
 	 */
-- 
cgit v1.2.3


From 413fffc3a1db7f270afdf1ecb35c1edc013acc68 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 28 Aug 2014 11:22:23 +0530
Subject: cpufreq: Add support for per-policy driver data

Drivers supporting multiple clusters or multiple 'struct cpufreq_policy'
instances may need to keep per-policy data. If the core doesn't provide support
for that, they might do it in the most unoptimized way: 'per-cpu' data.

This patch adds another field in struct cpufreq_policy: 'driver_data'. It isn't
accessed by core and is for driver's internal use only.

Tested-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpufreq.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 7d1955afa62c..138336b6bb04 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -112,6 +112,9 @@ struct cpufreq_policy {
 	spinlock_t		transition_lock;
 	wait_queue_head_t	transition_wait;
 	struct task_struct	*transition_task; /* Task which is doing the transition */
+
+	/* For cpufreq driver's internal use */
+	void			*driver_data;
 };
 
 /* Only for ACPI */
-- 
cgit v1.2.3


From e1e930f591bfd9604c3077f0af5c390f4f890259 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 8 Sep 2014 17:09:49 -0700
Subject: Bluetooth: Fix mgmt pairing failure when authentication fails

Whether through HCI with BR/EDR or SMP with LE when authentication fails
we should also notify any pending Pair Device mgmt command. This patch
updates the mgmt_auth_failed function to take the actual hci_conn object
and makes sure that any pending pairing command is notified and cleaned
up appropriately.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  3 +--
 net/bluetooth/hci_event.c        |  6 ++----
 net/bluetooth/mgmt.c             | 19 +++++++++++++------
 net/bluetooth/smp.c              |  3 +--
 4 files changed, 17 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 045d9133d180..206b92bfeebb 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1342,8 +1342,7 @@ int mgmt_user_passkey_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			     u8 link_type, u8 addr_type, u32 passkey,
 			     u8 entered);
-void mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		      u8 addr_type, u8 status);
+void mgmt_auth_failed(struct hci_conn *conn, u8 status);
 void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status);
 void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
 void mgmt_sc_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index e6a496ae0318..3a8381ab992f 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2320,8 +2320,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			conn->sec_level = conn->pending_sec_level;
 		}
 	} else {
-		mgmt_auth_failed(hdev, &conn->dst, conn->type, conn->dst_type,
-				 ev->status);
+		mgmt_auth_failed(conn, ev->status);
 	}
 
 	clear_bit(HCI_CONN_AUTH_PEND, &conn->flags);
@@ -3900,8 +3899,7 @@ static void hci_simple_pair_complete_evt(struct hci_dev *hdev,
 	 * event gets always produced as initiator and is also mapped to
 	 * the mgmt_auth_failed event */
 	if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) && ev->status)
-		mgmt_auth_failed(hdev, &conn->dst, conn->type, conn->dst_type,
-				 ev->status);
+		mgmt_auth_failed(conn, ev->status);
 
 	hci_conn_drop(conn);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ab9521ae3c63..efb71b022ab6 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -6485,16 +6485,23 @@ int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	return mgmt_event(MGMT_EV_PASSKEY_NOTIFY, hdev, &ev, sizeof(ev), NULL);
 }
 
-void mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		      u8 addr_type, u8 status)
+void mgmt_auth_failed(struct hci_conn *conn, u8 hci_status)
 {
 	struct mgmt_ev_auth_failed ev;
+	struct pending_cmd *cmd;
+	u8 status = mgmt_status(hci_status);
 
-	bacpy(&ev.addr.bdaddr, bdaddr);
-	ev.addr.type = link_to_bdaddr(link_type, addr_type);
-	ev.status = mgmt_status(status);
+	bacpy(&ev.addr.bdaddr, &conn->dst);
+	ev.addr.type = link_to_bdaddr(conn->type, conn->dst_type);
+	ev.status = status;
 
-	mgmt_event(MGMT_EV_AUTH_FAILED, hdev, &ev, sizeof(ev), NULL);
+	cmd = find_pairing(conn);
+
+	mgmt_event(MGMT_EV_AUTH_FAILED, conn->hdev, &ev, sizeof(ev),
+		    cmd ? cmd->sk : NULL);
+
+	if (cmd)
+		pairing_complete(cmd, status);
 }
 
 void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 560f78a9f960..25c9040e0b12 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -420,8 +420,7 @@ static void smp_failure(struct l2cap_conn *conn, u8 reason)
 			     &reason);
 
 	clear_bit(HCI_CONN_ENCRYPT_PEND, &hcon->flags);
-	mgmt_auth_failed(hcon->hdev, &hcon->dst, hcon->type, hcon->dst_type,
-			 HCI_ERROR_AUTH_FAILURE);
+	mgmt_auth_failed(hcon, HCI_ERROR_AUTH_FAILURE);
 
 	if (chan->data)
 		smp_chan_destroy(conn);
-- 
cgit v1.2.3


From 0dce5454d5c258582a7da5590332d9e085886bf7 Mon Sep 17 00:00:00 2001
From: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Date: Fri, 5 Sep 2014 12:23:48 +0200
Subject: ARM: shmobile: Initial r8a7794 SoC device tree

Signed-off-by: Hisashi Nakamura <hisashi.nakamura.ak@renesas.com>
[uli: reduced to minimum, added cmt, enabled scif2, split off board part]
Signed-off-by: Ulrich Hecht <ulrich.hecht+renesas@gmail.com>
Acked-by: Magnus Damm <damm@opensource.se>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 arch/arm/boot/dts/r8a7794.dtsi            | 531 ++++++++++++++++++++++++++++++
 include/dt-bindings/clock/r8a7794-clock.h |  80 +++++
 2 files changed, 611 insertions(+)
 create mode 100644 arch/arm/boot/dts/r8a7794.dtsi
 create mode 100644 include/dt-bindings/clock/r8a7794-clock.h

(limited to 'include')

diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
new file mode 100644
index 000000000000..d4e8bce1e0b7
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -0,0 +1,531 @@
+/*
+ * Device Tree Source for the r8a7794 SoC
+ *
+ * Copyright (C) 2014 Renesas Electronics Corporation
+ * Copyright (C) 2014 Ulrich Hecht
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <dt-bindings/clock/r8a7794-clock.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	compatible = "renesas,r8a7794";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0>;
+			clock-frequency = <1000000000>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <1>;
+			clock-frequency = <1000000000>;
+		};
+	};
+
+	gic: interrupt-controller@f1001000 {
+		compatible = "arm,cortex-a7-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0xf1001000 0 0x1000>,
+			<0 0xf1002000 0 0x1000>,
+			<0 0xf1004000 0 0x2000>,
+			<0 0xf1006000 0 0x2000>;
+		interrupts = <1 9 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
+	cmt0: timer@ffca0000 {
+		compatible = "renesas,cmt-48-gen2";
+		reg = <0 0xffca0000 0 0x1004>;
+		interrupts = <0 142 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 143 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp1_clks R8A7794_CLK_CMT0>;
+		clock-names = "fck";
+
+		renesas,channels-mask = <0x60>;
+
+		status = "disabled";
+	};
+
+	cmt1: timer@e6130000 {
+		compatible = "renesas,cmt-48-gen2";
+		reg = <0 0xe6130000 0 0x1004>;
+		interrupts = <0 120 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 121 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 122 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 123 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 124 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 125 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 126 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 127 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp3_clks R8A7794_CLK_CMT1>;
+		clock-names = "fck";
+
+		renesas,channels-mask = <0xff>;
+
+		status = "disabled";
+	};
+
+	irqc0: interrupt-controller@e61c0000 {
+		compatible = "renesas,irqc-r8a7794", "renesas,irqc";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0 0xe61c0000 0 0x200>;
+		interrupts = <0 0 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 1 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 2 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 3 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 12 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 13 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 14 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 15 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 16 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 17 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	scifa0: serial@e6c40000 {
+		compatible = "renesas,scifa-r8a7794", "renesas,scifa";
+		reg = <0 0xe6c40000 0 64>;
+		interrupts = <0 144 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7794_CLK_SCIFA0>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scifa1: serial@e6c50000 {
+		compatible = "renesas,scifa-r8a7794", "renesas,scifa";
+		reg = <0 0xe6c50000 0 64>;
+		interrupts = <0 145 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7794_CLK_SCIFA1>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scifa2: serial@e6c60000 {
+		compatible = "renesas,scifa-r8a7794", "renesas,scifa";
+		reg = <0 0xe6c60000 0 64>;
+		interrupts = <0 151 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7794_CLK_SCIFA2>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scifa3: serial@e6c70000 {
+		compatible = "renesas,scifa-r8a7794", "renesas,scifa";
+		reg = <0 0xe6c70000 0 64>;
+		interrupts = <0 29 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp11_clks R8A7794_CLK_SCIFA3>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scifa4: serial@e6c78000 {
+		compatible = "renesas,scifa-r8a7794", "renesas,scifa";
+		reg = <0 0xe6c78000 0 64>;
+		interrupts = <0 30 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp11_clks R8A7794_CLK_SCIFA4>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scifa5: serial@e6c80000 {
+		compatible = "renesas,scifa-r8a7794", "renesas,scifa";
+		reg = <0 0xe6c80000 0 64>;
+		interrupts = <0 31 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp11_clks R8A7794_CLK_SCIFA5>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scifb0: serial@e6c20000 {
+		compatible = "renesas,scifb-r8a7794", "renesas,scifb";
+		reg = <0 0xe6c20000 0 64>;
+		interrupts = <0 148 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7794_CLK_SCIFB0>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scifb1: serial@e6c30000 {
+		compatible = "renesas,scifb-r8a7794", "renesas,scifb";
+		reg = <0 0xe6c30000 0 64>;
+		interrupts = <0 149 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7794_CLK_SCIFB1>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scifb2: serial@e6ce0000 {
+		compatible = "renesas,scifb-r8a7794", "renesas,scifb";
+		reg = <0 0xe6ce0000 0 64>;
+		interrupts = <0 150 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7794_CLK_SCIFB2>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scif0: serial@e6e60000 {
+		compatible = "renesas,scif-r8a7794", "renesas,scif";
+		reg = <0 0xe6e60000 0 64>;
+		interrupts = <0 152 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7794_CLK_SCIF0>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scif1: serial@e6e68000 {
+		compatible = "renesas,scif-r8a7794", "renesas,scif";
+		reg = <0 0xe6e68000 0 64>;
+		interrupts = <0 153 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7794_CLK_SCIF1>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scif2: serial@e6e58000 {
+		compatible = "renesas,scif-r8a7794", "renesas,scif";
+		reg = <0 0xe6e58000 0 64>;
+		interrupts = <0 22 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7794_CLK_SCIF2>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scif3: serial@e6ea8000 {
+		compatible = "renesas,scif-r8a7794", "renesas,scif";
+		reg = <0 0xe6ea8000 0 64>;
+		interrupts = <0 23 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7794_CLK_SCIF3>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scif4: serial@e6ee0000 {
+		compatible = "renesas,scif-r8a7794", "renesas,scif";
+		reg = <0 0xe6ee0000 0 64>;
+		interrupts = <0 24 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7794_CLK_SCIF4>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	scif5: serial@e6ee8000 {
+		compatible = "renesas,scif-r8a7794", "renesas,scif";
+		reg = <0 0xe6ee8000 0 64>;
+		interrupts = <0 25 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7794_CLK_SCIF5>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	hscif0: serial@e62c0000 {
+		compatible = "renesas,hscif-r8a7794", "renesas,hscif";
+		reg = <0 0xe62c0000 0 96>;
+		interrupts = <0 154 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7794_CLK_HSCIF0>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	hscif1: serial@e62c8000 {
+		compatible = "renesas,hscif-r8a7794", "renesas,hscif";
+		reg = <0 0xe62c8000 0 96>;
+		interrupts = <0 155 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7794_CLK_HSCIF1>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	hscif2: serial@e62d0000 {
+		compatible = "renesas,hscif-r8a7794", "renesas,hscif";
+		reg = <0 0xe62d0000 0 96>;
+		interrupts = <0 21 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7794_CLK_HSCIF2>;
+		clock-names = "sci_ick";
+		status = "disabled";
+	};
+
+	clocks {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/* External root clock */
+		extal_clk: extal_clk {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			/* This value must be overriden by the board. */
+			clock-frequency = <0>;
+			clock-output-names = "extal";
+		};
+
+		/* Special CPG clocks */
+		cpg_clocks: cpg_clocks@e6150000 {
+			compatible = "renesas,r8a7794-cpg-clocks",
+				     "renesas,rcar-gen2-cpg-clocks";
+			reg = <0 0xe6150000 0 0x1000>;
+			clocks = <&extal_clk>;
+			#clock-cells = <1>;
+			clock-output-names = "main", "pll0", "pll1", "pll3",
+					     "lb", "qspi", "sdh", "sd0", "z";
+		};
+
+		/* Fixed factor clocks */
+		pll1_div2_clk: pll1_div2_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <2>;
+			clock-mult = <1>;
+			clock-output-names = "pll1_div2";
+		};
+		zg_clk: zg_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <6>;
+			clock-mult = <1>;
+			clock-output-names = "zg";
+		};
+		zx_clk: zx_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <3>;
+			clock-mult = <1>;
+			clock-output-names = "zx";
+		};
+		zs_clk: zs_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <6>;
+			clock-mult = <1>;
+			clock-output-names = "zs";
+		};
+		hp_clk: hp_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <12>;
+			clock-mult = <1>;
+			clock-output-names = "hp";
+		};
+		i_clk: i_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <2>;
+			clock-mult = <1>;
+			clock-output-names = "i";
+		};
+		b_clk: b_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <12>;
+			clock-mult = <1>;
+			clock-output-names = "b";
+		};
+		p_clk: p_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <24>;
+			clock-mult = <1>;
+			clock-output-names = "p";
+		};
+		cl_clk: cl_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <48>;
+			clock-mult = <1>;
+			clock-output-names = "cl";
+		};
+		m2_clk: m2_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <8>;
+			clock-mult = <1>;
+			clock-output-names = "m2";
+		};
+		imp_clk: imp_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <4>;
+			clock-mult = <1>;
+			clock-output-names = "imp";
+		};
+		rclk_clk: rclk_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <(48 * 1024)>;
+			clock-mult = <1>;
+			clock-output-names = "rclk";
+		};
+		oscclk_clk: oscclk_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <(12 * 1024)>;
+			clock-mult = <1>;
+			clock-output-names = "oscclk";
+		};
+		zb3_clk: zb3_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL3>;
+			#clock-cells = <0>;
+			clock-div = <4>;
+			clock-mult = <1>;
+			clock-output-names = "zb3";
+		};
+		zb3d2_clk: zb3d2_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL3>;
+			#clock-cells = <0>;
+			clock-div = <8>;
+			clock-mult = <1>;
+			clock-output-names = "zb3d2";
+		};
+		ddr_clk: ddr_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL3>;
+			#clock-cells = <0>;
+			clock-div = <8>;
+			clock-mult = <1>;
+			clock-output-names = "ddr";
+		};
+		mp_clk: mp_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&pll1_div2_clk>;
+			#clock-cells = <0>;
+			clock-div = <15>;
+			clock-mult = <1>;
+			clock-output-names = "mp";
+		};
+		cp_clk: cp_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&cpg_clocks R8A7794_CLK_PLL1>;
+			#clock-cells = <0>;
+			clock-div = <48>;
+			clock-mult = <1>;
+			clock-output-names = "cp";
+		};
+
+		acp_clk: acp_clk {
+			compatible = "fixed-factor-clock";
+			clocks = <&extal_clk>;
+			#clock-cells = <0>;
+			clock-div = <2>;
+			clock-mult = <1>;
+			clock-output-names = "acp";
+		};
+
+		/* Gate clocks */
+		mstp0_clks: mstp0_clks@e6150130 {
+			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150130 0 4>, <0 0xe6150030 0 4>;
+			clocks = <&mp_clk>;
+			#clock-cells = <1>;
+			renesas,clock-indices = <R8A7794_CLK_MSIOF0>;
+			clock-output-names = "msiof0";
+		};
+		mstp1_clks: mstp1_clks@e6150134 {
+			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150134 0 4>, <0 0xe6150038 0 4>;
+			clocks = <&p_clk>, <&p_clk>, <&p_clk>, <&rclk_clk>,
+				 <&cp_clk>,
+				 <&zs_clk>, <&zs_clk>, <&zs_clk>;
+			#clock-cells = <1>;
+			renesas,clock-indices = <
+				R8A7794_CLK_TMU1 R8A7794_CLK_TMU3 R8A7794_CLK_TMU2
+				R8A7794_CLK_CMT0 R8A7794_CLK_TMU0
+			>;
+			clock-output-names =
+				"tmu1", "tmu3", "tmu2", "cmt0", "tmu0";
+		};
+		mstp2_clks: mstp2_clks@e6150138 {
+			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150138 0 4>, <0 0xe6150040 0 4>;
+			clocks = <&mp_clk>, <&mp_clk>, <&mp_clk>, <&mp_clk>, <&mp_clk>,
+				 <&mp_clk>, <&mp_clk>, <&mp_clk>;
+			#clock-cells = <1>;
+			renesas,clock-indices = <
+				R8A7794_CLK_SCIFA2 R8A7794_CLK_SCIFA1 R8A7794_CLK_SCIFA0
+				R8A7794_CLK_MSIOF2 R8A7794_CLK_SCIFB0 R8A7794_CLK_SCIFB1
+				R8A7794_CLK_MSIOF1 R8A7794_CLK_SCIFB2
+			>;
+			clock-output-names =
+				"scifa2", "scifa1", "scifa0", "msiof2", "scifb0",
+				"scifb1", "msiof1", "scifb2";
+		};
+		mstp3_clks: mstp3_clks@e615013c {
+			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
+			reg = <0 0xe615013c 0 4>, <0 0xe6150048 0 4>;
+			clocks = <&rclk_clk>;
+			#clock-cells = <1>;
+			renesas,clock-indices = <
+				R8A7794_CLK_CMT1
+			>;
+			clock-output-names =
+				"cmt1";
+		};
+		mstp7_clks: mstp7_clks@e615014c {
+			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
+			reg = <0 0xe615014c 0 4>, <0 0xe61501c4 0 4>;
+			clocks = <&zs_clk>, <&p_clk>, <&p_clk>, <&zs_clk>,
+				 <&zs_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>;
+			#clock-cells = <1>;
+			renesas,clock-indices = <
+				R8A7794_CLK_HSCIF2 R8A7794_CLK_SCIF5
+				R8A7794_CLK_SCIF4 R8A7794_CLK_HSCIF1 R8A7794_CLK_HSCIF0
+				R8A7794_CLK_SCIF3 R8A7794_CLK_SCIF2 R8A7794_CLK_SCIF1
+				R8A7794_CLK_SCIF0
+			>;
+			clock-output-names =
+				"hscif2", "scif5", "scif4", "hscif1", "hscif0",
+				"scif3", "scif2", "scif1", "scif0";
+		};
+		mstp8_clks: mstp8_clks@e6150990 {
+			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
+			reg = <0 0xe6150990 0 4>, <0 0xe61509a0 0 4>;
+			clocks = <&p_clk>;
+			#clock-cells = <1>;
+			renesas,clock-indices = <
+				R8A7794_CLK_ETHER
+			>;
+			clock-output-names =
+				"ether";
+		};
+		mstp11_clks: mstp11_clks@e615099c {
+			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
+			reg = <0 0xe615099c 0 4>, <0 0xe61509ac 0 4>;
+			clocks = <&mp_clk>, <&mp_clk>, <&mp_clk>;
+			#clock-cells = <1>;
+			renesas,clock-indices = <
+				R8A7794_CLK_SCIFA3 R8A7794_CLK_SCIFA4 R8A7794_CLK_SCIFA5
+			>;
+			clock-output-names = "scifa3", "scifa4", "scifa5";
+		};
+	};
+};
diff --git a/include/dt-bindings/clock/r8a7794-clock.h b/include/dt-bindings/clock/r8a7794-clock.h
new file mode 100644
index 000000000000..9ac1043e25bc
--- /dev/null
+++ b/include/dt-bindings/clock/r8a7794-clock.h
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 2014 Renesas Electronics Corporation
+ * Copyright 2013 Ideas On Board SPRL
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_R8A7794_H__
+#define __DT_BINDINGS_CLOCK_R8A7794_H__
+
+/* CPG */
+#define R8A7794_CLK_MAIN		0
+#define R8A7794_CLK_PLL0		1
+#define R8A7794_CLK_PLL1		2
+#define R8A7794_CLK_PLL3		3
+#define R8A7794_CLK_LB			4
+#define R8A7794_CLK_QSPI		5
+#define R8A7794_CLK_SDH			6
+#define R8A7794_CLK_SD0			7
+#define R8A7794_CLK_Z			8
+
+/* MSTP0 */
+#define R8A7794_CLK_MSIOF0		0
+
+/* MSTP1 */
+#define R8A7794_CLK_TMU1		11
+#define R8A7794_CLK_TMU3		21
+#define R8A7794_CLK_TMU2		22
+#define R8A7794_CLK_CMT0		24
+#define R8A7794_CLK_TMU0		25
+
+/* MSTP2 */
+#define R8A7794_CLK_SCIFA2		2
+#define R8A7794_CLK_SCIFA1		3
+#define R8A7794_CLK_SCIFA0		4
+#define R8A7794_CLK_MSIOF2		5
+#define R8A7794_CLK_SCIFB0		6
+#define R8A7794_CLK_SCIFB1		7
+#define R8A7794_CLK_MSIOF1		8
+#define R8A7794_CLK_SCIFB2		16
+
+/* MSTP3 */
+#define R8A7794_CLK_CMT1		29
+
+/* MSTP5 */
+#define R8A7794_CLK_THERMAL		22
+#define R8A7794_CLK_PWM			23
+
+/* MSTP7 */
+#define R8A7794_CLK_HSCIF2		13
+#define R8A7794_CLK_SCIF5		14
+#define R8A7794_CLK_SCIF4		15
+#define R8A7794_CLK_HSCIF1		16
+#define R8A7794_CLK_HSCIF0		17
+#define R8A7794_CLK_SCIF3		18
+#define R8A7794_CLK_SCIF2		19
+#define R8A7794_CLK_SCIF1		20
+#define R8A7794_CLK_SCIF0		21
+
+/* MSTP8 */
+#define R8A7794_CLK_ETHER		13
+
+/* MSTP9 */
+#define R8A7794_CLK_GPIO6		5
+#define R8A7794_CLK_GPIO5		7
+#define R8A7794_CLK_GPIO4		8
+#define R8A7794_CLK_GPIO3		9
+#define R8A7794_CLK_GPIO2		10
+#define R8A7794_CLK_GPIO1		11
+#define R8A7794_CLK_GPIO0		12
+
+/* MSTP11 */
+#define R8A7794_CLK_SCIFA3		6
+#define R8A7794_CLK_SCIFA4		7
+#define R8A7794_CLK_SCIFA5		8
+
+#endif /* __DT_BINDINGS_CLOCK_R8A7794_H__ */
-- 
cgit v1.2.3


From f3dbd802b3caf8da92173870bc270dda6b3f84ba Mon Sep 17 00:00:00 2001
From: Rajat Jain <rajatxjain@gmail.com>
Date: Tue, 2 Sep 2014 16:26:00 -0700
Subject: PCI: Enable CRS Software Visibility for root port if it is supported

Per PCIe r3.0, sec 2.3.2, an endpoint may respond to a Configuration
Request with a Completion with Configuration Request Retry Status (CRS).
This terminates the Configuration Request.

When the CRS Software Visibility feature is disabled (as it is by default),
a Root Complex must handle a CRS Completion by re-issuing the Configuration
Request.  This is invisible to software.  From the CPU's point of view, an
endpoint that always responds with CRS causes a hang because the Root
Complex never supplies data to complete the CPU read.

When CRS Software Visibility is enabled, a Root Complex that receives a CRS
Completion for a read of the Vendor ID must return data of 0x0001.  The
Vendor ID of 0x0001 indicates to software that the endpoint is not ready.

We now have more devices that require CRS Software Visibility.  For
example, a PLX 8713 NT bridge may respond with CRS until it has been
configured via I2C, and the I2C configuration is completely independent of
PCI enumeration.

Enable CRS Software Visibility if it is supported.  This allows a system
with such a device to work (though the PCI core times out waiting for it to
become ready, and we have to rescan the bus after it is ready).

This essentially reverts ad7edfe04908 ("[PCI] Do not enable CRS Software
Visibility by default").  The failures that led to ad7edfe04908 should be
addressed by 89665a6a7140 ("PCI: Check only the Vendor ID to identify
Configuration Request Retry").

[bhelgaas: changelog]
Link: http://lkml.kernel.org/r/20071029061532.5d10dfc6@snowcone
Link: http://lkml.kernel.org/r/alpine.LFD.0.9999.0712271023090.21557@woody.linux-foundation.org
Signed-off-by: Rajat Jain <rajatxjain@gmail.com>
Signed-off-by: Rajat Jain <rajatjain@juniper.net>
Signed-off-by: Guenter Roeck <groeck@juniper.net>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c           | 13 +++++++++++++
 include/uapi/linux/pci_regs.h |  1 +
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 9c26663c91d2..e02cdaa5bf0c 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -740,6 +740,17 @@ struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev,
 }
 EXPORT_SYMBOL(pci_add_new_bus);
 
+static void pci_enable_crs(struct pci_dev *pdev)
+{
+	u16 root_cap = 0;
+
+	/* Enable CRS Software Visibility if supported */
+	pcie_capability_read_word(pdev, PCI_EXP_RTCAP, &root_cap);
+	if (root_cap & PCI_EXP_RTCAP_CRSVIS)
+		pcie_capability_set_word(pdev, PCI_EXP_RTCTL,
+					 PCI_EXP_RTCTL_CRSSVE);
+}
+
 /*
  * If it's a bridge, configure it and scan the bus behind it.
  * For CardBus bridges, we don't scan behind as the devices will
@@ -787,6 +798,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 	pci_write_config_word(dev, PCI_BRIDGE_CONTROL,
 			      bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT);
 
+	pci_enable_crs(dev);
+
 	if ((secondary || subordinate) && !pcibios_assign_all_busses() &&
 	    !is_cardbus && !broken) {
 		unsigned int cmax;
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 30db069bce62..57d6e56a086a 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -552,6 +552,7 @@
 #define  PCI_EXP_RTCTL_PMEIE	0x0008	/* PME Interrupt Enable */
 #define  PCI_EXP_RTCTL_CRSSVE	0x0010	/* CRS Software Visibility Enable */
 #define PCI_EXP_RTCAP		30	/* Root Capabilities */
+#define  PCI_EXP_RTCAP_CRSVIS	0x0001	/* CRS Software Visibility capability */
 #define PCI_EXP_RTSTA		32	/* Root Status */
 #define PCI_EXP_RTSTA_PME	0x00010000 /* PME status */
 #define PCI_EXP_RTSTA_PENDING	0x00020000 /* PME pending */
-- 
cgit v1.2.3


From da3dae54e4ff09886b9a19224c8d9556bb2ba096 Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Tue, 9 Sep 2014 01:27:23 +0900
Subject: Documentation: Docbook: Fix generated DocBook/kernel-api.xml

This patch fix spelling typo found in DocBook/kernel-api.xml.
It is because the file is generated from the source comments,
I have to fix the comments in source codes.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 block/blk-core.c      | 8 ++++----
 block/genhd.c         | 2 +-
 include/linux/clk.h   | 2 +-
 include/linux/kfifo.h | 2 +-
 ipc/util.c            | 6 +++---
 kernel/auditsc.c      | 2 +-
 lib/bitmap.c          | 4 ++--
 lib/idr.c             | 2 +-
 lib/vsprintf.c        | 2 +-
 mm/filemap.c          | 2 +-
 security/inode.c      | 2 +-
 11 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 6f8dba161bfe..ce5a389cea94 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -240,7 +240,7 @@ EXPORT_SYMBOL(blk_stop_queue);
  *     this function.
  *
  *     This function does not cancel any asynchronous activity arising
- *     out of elevator or throttling code. That would require elevaotor_exit()
+ *     out of elevator or throttling code. That would require elevator_exit()
  *     and blkcg_exit_queue() to be called with queue lock initialized.
  *
  */
@@ -930,7 +930,7 @@ static struct io_context *rq_ioc(struct bio *bio)
  * Get a free request from @q.  This function may fail under memory
  * pressure or if @q is dead.
  *
- * Must be callled with @q->queue_lock held and,
+ * Must be called with @q->queue_lock held and,
  * Returns %NULL on failure, with @q->queue_lock held.
  * Returns !%NULL on success, with @q->queue_lock *not held*.
  */
@@ -1107,7 +1107,7 @@ rq_starved:
  * Get a free request from @q.  If %__GFP_WAIT is set in @gfp_mask, this
  * function keeps retrying under memory pressure and fails iff @q is dead.
  *
- * Must be callled with @q->queue_lock held and,
+ * Must be called with @q->queue_lock held and,
  * Returns %NULL on failure, with @q->queue_lock held.
  * Returns !%NULL on success, with @q->queue_lock *not held*.
  */
@@ -1238,7 +1238,7 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 EXPORT_SYMBOL(blk_make_request);
 
 /**
- * blk_rq_set_block_pc - initialize a requeest to type BLOCK_PC
+ * blk_rq_set_block_pc - initialize a request to type BLOCK_PC
  * @rq:		request to be initialized
  *
  */
diff --git a/block/genhd.c b/block/genhd.c
index 791f41943132..048e2cee43d2 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1543,7 +1543,7 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask)
 /**
  * disk_clear_events - synchronously check, clear and return pending events
  * @disk: disk to fetch and clear events from
- * @mask: mask of events to be fetched and clearted
+ * @mask: mask of events to be fetched and cleared
  *
  * Disk events are synchronously checked and pending events in @mask
  * are cleared and returned.  This ignores the block count.
diff --git a/include/linux/clk.h b/include/linux/clk.h
index fb5e097d8f72..afb44bfaf8d1 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -238,7 +238,7 @@ void clk_put(struct clk *clk);
 
 /**
  * devm_clk_put	- "free" a managed clock source
- * @dev: device used to acuqire the clock
+ * @dev: device used to acquire the clock
  * @clk: clock source acquired with devm_clk_get()
  *
  * Note: drivers must ensure that all clk_enable calls made on this
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 554fde3a3927..473b43678ad1 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -722,7 +722,7 @@ __kfifo_uint_must_check_helper( \
 /**
  * kfifo_dma_out_finish - finish a DMA OUT operation
  * @fifo: address of the fifo to be used
- * @len: number of bytes transferrd
+ * @len: number of bytes transferred
  *
  * This macro finish a DMA OUT operation. The out counter will be updated by
  * the len parameter. No error checking will be done.
diff --git a/ipc/util.c b/ipc/util.c
index 27d74e69fd57..d73b7af581e2 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -309,7 +309,7 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size)
 /**
  * ipcget_new -	create a new ipc object
  * @ns: ipc namespace
- * @ids: ipc identifer set
+ * @ids: ipc identifier set
  * @ops: the actual creation routine to call
  * @params: its parameters
  *
@@ -363,7 +363,7 @@ static int ipc_check_perms(struct ipc_namespace *ns,
 /**
  * ipcget_public - get an ipc object or create a new one
  * @ns: ipc namespace
- * @ids: ipc identifer set
+ * @ids: ipc identifier set
  * @ops: the actual creation routine to call
  * @params: its parameters
  *
@@ -669,7 +669,7 @@ out:
 
 /**
  * ipcget - Common sys_*get() code
- * @ns: namsepace
+ * @ns: namespace
  * @ids: ipc identifier set
  * @ops: operations to be called on ipc object creation, permission checks
  *       and further checks
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 21eae3c05ec0..7208c1df248d 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2406,7 +2406,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
  * @new: the new credentials
  * @old: the old (current) credentials
  *
- * Record the aguments userspace sent to sys_capset for later printing by the
+ * Record the arguments userspace sent to sys_capset for later printing by the
  * audit system if applicable
  */
 void __audit_log_capset(const struct cred *new, const struct cred *old)
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 06f7e4fe8d2d..ed0f00c3da0a 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -882,7 +882,7 @@ EXPORT_SYMBOL(bitmap_bitremap);
  * read it, you're overqualified for your current job.)
  *
  * In other words, @orig is mapped onto (surjectively) @dst,
- * using the the map { <n, m> | the n-th bit of @relmap is the
+ * using the map { <n, m> | the n-th bit of @relmap is the
  * m-th set bit of @relmap }.
  *
  * Any set bits in @orig above bit number W, where W is the
@@ -930,7 +930,7 @@ EXPORT_SYMBOL(bitmap_bitremap);
  *
  *  Further lets say we use the following code, invoking
  *  bitmap_fold() then bitmap_onto, as suggested above to
- *  avoid the possitility of an empty @dst result:
+ *  avoid the possibility of an empty @dst result:
  *
  *	unsigned long *tmp;	// a temporary bitmap's bits
  *
diff --git a/lib/idr.c b/lib/idr.c
index 39158abebad1..460abfd1450b 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -625,7 +625,7 @@ static void __idr_remove_all(struct idr *idp)
  * idr_destroy().
  *
  * A typical clean-up sequence for objects stored in an idr tree will use
- * idr_for_each() to free all objects, if necessay, then idr_destroy() to
+ * idr_for_each() to free all objects, if necessary, then idr_destroy() to
  * free up the id mappings and cached idr_layers.
  */
 void idr_destroy(struct idr *idp)
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 6fe2c84eb055..ba3cd0a35640 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1937,7 +1937,7 @@ EXPORT_SYMBOL(sprintf);
  * @args: Arguments for the format string
  *
  * The format follows C99 vsnprintf, except %n is ignored, and its argument
- * is skiped.
+ * is skipped.
  *
  * The return value is the number of words(32bits) which would be generated for
  * the given input.
diff --git a/mm/filemap.c b/mm/filemap.c
index 65d44fd88c78..f092654cc1a3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -720,7 +720,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
  *
  * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
  * Also wakes sleepers in wait_on_page_writeback() because the wakeup
- * mechananism between PageLocked pages and PageWriteback pages is shared.
+ * mechanism between PageLocked pages and PageWriteback pages is shared.
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
  *
  * The mb is necessary to enforce ordering between the clear_bit and the read
diff --git a/security/inode.c b/security/inode.c
index 43ce6e19015f..8e7ca62078ab 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -74,7 +74,7 @@ static struct file_system_type fs_type = {
  * pointer must be passed to the securityfs_remove() function when the file is
  * to be removed (no automatic cleanup happens if your module is unloaded,
  * you are responsible here).  If an error occurs, the function will return
- * the erorr value (via ERR_PTR).
+ * the error value (via ERR_PTR).
  *
  * If securityfs is not enabled in the kernel, the value %-ENODEV is
  * returned.
-- 
cgit v1.2.3


From 8ca28610e5e37193cd61fefa4310941e28de10ca Mon Sep 17 00:00:00 2001
From: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Date: Thu, 7 Aug 2014 15:14:06 +0200
Subject: mmc: include linux/types.h for bool definition in atmel-mci.h

This patch adds an include of linux/types.h to make sure bool is defined
before utilized in this header file.

Signed-off-by: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Acked-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 include/linux/atmel-mci.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/atmel-mci.h b/include/linux/atmel-mci.h
index 4c7a4b2104bf..91b77f8d495d 100644
--- a/include/linux/atmel-mci.h
+++ b/include/linux/atmel-mci.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_ATMEL_MCI_H
 #define __LINUX_ATMEL_MCI_H
 
+#include <linux/types.h>
+
 #define ATMCI_MAX_NR_SLOTS	2
 
 /**
-- 
cgit v1.2.3


From b3683994843a0ede0e19daccd1ac32a46b21eb39 Mon Sep 17 00:00:00 2001
From: Yi Sun <yi.y.sun@intel.com>
Date: Wed, 13 Aug 2014 13:34:01 +0800
Subject: mmc: Correct the value of MMC_NUM_PHY_PARTITION

eMMC card can support up to 7 physical partitions, including 2 boot,
1 RPMB and 4 GPs. Change MMC_NUM_PHY_PARTITION from 6 to 7, which is
the correct value.

Signed-off-by: Yi Sun <yi.y.sun@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 include/linux/mmc/card.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index d424b9de3aff..bde5147a4221 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -214,11 +214,12 @@ enum mmc_blk_status {
 };
 
 /* The number of MMC physical partitions.  These consist of:
- * boot partitions (2), general purpose partitions (4) in MMC v4.4.
+ * boot partitions (2), general purpose partitions (4) and
+ * RPMB partition (1) in MMC v4.4.
  */
 #define MMC_NUM_BOOT_PARTITION	2
 #define MMC_NUM_GP_PARTITION	4
-#define MMC_NUM_PHY_PARTITION	6
+#define MMC_NUM_PHY_PARTITION	7
 #define MAX_MMC_PART_NAME_LEN	20
 
 /*
-- 
cgit v1.2.3


From 3d705d14fe4c72be83bae1610680e209ee226b9d Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Tue, 19 Aug 2014 10:45:51 +0200
Subject: mmc: implement Driver Stage Register handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some eMMC and SD cards implement a DSR register that allows to tune
raise/fall times and drive strength of the CMD and DATA outputs.
The values to use depend on the card in use and the host.
It might be needed to reduce the drive strength to prevent voltage peaks
above the host's specification.

Implement a 'dsr' devicetree property that allows to specify the value
to set the DSR to. For non-dt setups the new members of mmc_host can be
set by board code.

This patch was initially authored by Sascha Hauer. It contains
improvements authored by Markus Niebel and Uwe Kleine-König.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Markus Niebel <Markus.Niebel@tq-group.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 Documentation/devicetree/bindings/mmc/mmc.txt |  2 ++
 drivers/mmc/core/host.c                       |  8 ++++++++
 drivers/mmc/core/mmc.c                        |  8 ++++++++
 drivers/mmc/core/mmc_ops.c                    | 20 ++++++++++++++++++++
 drivers/mmc/core/mmc_ops.h                    |  1 +
 drivers/mmc/core/sd.c                         |  8 ++++++++
 include/linux/mmc/card.h                      |  3 ++-
 include/linux/mmc/host.h                      |  3 +++
 8 files changed, 52 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index 431716e37a39..b52628b18a53 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -40,6 +40,8 @@ Optional properties:
 - mmc-hs200-1_2v: eMMC HS200 mode(1.2V I/O) is supported
 - mmc-hs400-1_8v: eMMC HS400 mode(1.8V I/O) is supported
 - mmc-hs400-1_2v: eMMC HS400 mode(1.2V I/O) is supported
+- dsr: Value the card's (optional) Driver Stage Register (DSR) should be
+  programmed with. Valid range: [0 .. 0xffff].
 
 *NOTE* on CD and WP polarity. To use common for all SD/MMC host controllers line
 polarity properties, we have to fix the meaning of the "normal" and "inverted"
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 95cceae96944..d572b2beb65a 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -452,6 +452,14 @@ int mmc_of_parse(struct mmc_host *host)
 	if (of_find_property(np, "mmc-hs400-1_2v", &len))
 		host->caps2 |= MMC_CAP2_HS400_1_2V | MMC_CAP2_HS200_1_2V_SDR;
 
+	host->dsr_req = !of_property_read_u32(np, "dsr", &host->dsr);
+	if (host->dsr_req && (host->dsr & ~0xffff)) {
+		dev_err(host->parent,
+			"device tree specified broken value for DSR: 0x%x, ignoring\n",
+			host->dsr);
+		host->dsr_req = 0;
+	}
+
 	return 0;
 
 out:
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 1eda8dd8c867..31c43165f8bc 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -162,6 +162,7 @@ static int mmc_decode_csd(struct mmc_card *card)
 	csd->read_partial = UNSTUFF_BITS(resp, 79, 1);
 	csd->write_misalign = UNSTUFF_BITS(resp, 78, 1);
 	csd->read_misalign = UNSTUFF_BITS(resp, 77, 1);
+	csd->dsr_imp = UNSTUFF_BITS(resp, 76, 1);
 	csd->r2w_factor = UNSTUFF_BITS(resp, 26, 3);
 	csd->write_blkbits = UNSTUFF_BITS(resp, 22, 4);
 	csd->write_partial = UNSTUFF_BITS(resp, 21, 1);
@@ -1271,6 +1272,13 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 			goto free_card;
 	}
 
+	/*
+	 * handling only for cards supporting DSR and hosts requesting
+	 * DSR configuration
+	 */
+	if (card->csd.dsr_imp && host->dsr_req)
+		mmc_set_dsr(host);
+
 	/*
 	 * Select card, as all following commands rely on that.
 	 */
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index f51b5ba3bbea..ba0275e90617 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -93,6 +93,26 @@ int mmc_deselect_cards(struct mmc_host *host)
 	return _mmc_select_card(host, NULL);
 }
 
+/*
+ * Write the value specified in the device tree or board code into the optional
+ * 16 bit Driver Stage Register. This can be used to tune raise/fall times and
+ * drive strength of the DAT and CMD outputs. The actual meaning of a given
+ * value is hardware dependant.
+ * The presence of the DSR register can be determined from the CSD register,
+ * bit 76.
+ */
+int mmc_set_dsr(struct mmc_host *host)
+{
+	struct mmc_command cmd = {0};
+
+	cmd.opcode = MMC_SET_DSR;
+
+	cmd.arg = (host->dsr << 16) | 0xffff;
+	cmd.flags = MMC_RSP_NONE | MMC_CMD_AC;
+
+	return mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
+}
+
 int mmc_go_idle(struct mmc_host *host)
 {
 	int err;
diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h
index 80ae9f4e0293..390dac665b2a 100644
--- a/drivers/mmc/core/mmc_ops.h
+++ b/drivers/mmc/core/mmc_ops.h
@@ -14,6 +14,7 @@
 
 int mmc_select_card(struct mmc_card *card);
 int mmc_deselect_cards(struct mmc_host *host);
+int mmc_set_dsr(struct mmc_host *host);
 int mmc_go_idle(struct mmc_host *host);
 int mmc_send_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr);
 int mmc_all_send_cid(struct mmc_host *host, u32 *cid);
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 0c44510bf717..25913889cbaa 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -127,6 +127,7 @@ static int mmc_decode_csd(struct mmc_card *card)
 		csd->read_partial = UNSTUFF_BITS(resp, 79, 1);
 		csd->write_misalign = UNSTUFF_BITS(resp, 78, 1);
 		csd->read_misalign = UNSTUFF_BITS(resp, 77, 1);
+		csd->dsr_imp = UNSTUFF_BITS(resp, 76, 1);
 		csd->r2w_factor = UNSTUFF_BITS(resp, 26, 3);
 		csd->write_blkbits = UNSTUFF_BITS(resp, 22, 4);
 		csd->write_partial = UNSTUFF_BITS(resp, 21, 1);
@@ -953,6 +954,13 @@ static int mmc_sd_init_card(struct mmc_host *host, u32 ocr,
 		mmc_decode_cid(card);
 	}
 
+	/*
+	 * handling only for cards supporting DSR and hosts requesting
+	 * DSR configuration
+	 */
+	if (card->csd.dsr_imp && host->dsr_req)
+		mmc_set_dsr(host);
+
 	/*
 	 * Select card, as all following commands rely on that.
 	 */
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index bde5147a4221..0ea795f5feb9 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -42,7 +42,8 @@ struct mmc_csd {
 	unsigned int		read_partial:1,
 				read_misalign:1,
 				write_partial:1,
-				write_misalign:1;
+				write_misalign:1,
+				dsr_imp:1;
 };
 
 struct mmc_ext_csd {
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 7960424d0bc0..4cbf61476999 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -365,6 +365,9 @@ struct mmc_host {
 
 	unsigned int		slotno;	/* used for sdio acpi binding */
 
+	int			dsr_req;	/* DSR value is valid */
+	u32			dsr;	/* optional driver stage (DSR) value */
+
 	unsigned long		private[0] ____cacheline_aligned;
 };
 
-- 
cgit v1.2.3


From 384b2cbd56a02efb16358ed7c0c039e4afca5ed0 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Sun, 24 Aug 2014 19:58:48 -0700
Subject: mmc: tmio: care about DMA tx/rx addr offset

Basically, SD_BUF0 Tx/Rx addresses are same
in normal TMIO controller,
but, it is different on Renesas R-Car SDHI controller
if it uses DMAC
(Rx address needs to add 0x2000 to Tx address)

This patch adds new .dma_rx_offset and cares it

Tested-by: Nguyen Xuan Nui <nx-nui@jinso.co.jp>
Tested-by: Hiep Cao Minh <cm-hiep@jinso.co.jp>
Acked-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Acked-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 3 +++
 drivers/mmc/host/tmio_mmc_dma.c   | 2 +-
 include/linux/mfd/tmio.h          | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 2dafe28c8df9..f0818cd0242c 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -39,6 +39,7 @@ struct sh_mobile_sdhi_of_data {
 	unsigned long tmio_flags;
 	unsigned long capabilities;
 	unsigned long capabilities2;
+	dma_addr_t dma_rx_offset;
 };
 
 static const struct sh_mobile_sdhi_of_data sh_mobile_sdhi_of_cfg[] = {
@@ -56,6 +57,7 @@ static const struct sh_mobile_sdhi_of_data of_rcar_gen2_compatible = {
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ,
 	.capabilities2	= MMC_CAP2_NO_MULTI_READ,
+	.dma_rx_offset	= 0x2000,
 };
 
 static const struct of_device_id sh_mobile_sdhi_of_match[] = {
@@ -228,6 +230,7 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 		mmc_data->flags |= of_data->tmio_flags;
 		mmc_data->capabilities |= of_data->capabilities;
 		mmc_data->capabilities2 |= of_data->capabilities2;
+		dma_priv->dma_rx_offset = of_data->dma_rx_offset;
 	}
 
 	/* SD control register space size is 0x100, 0x200 for bus_shift=1 */
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index eb8f1d5c34b1..bd646b041085 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -312,7 +312,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat
 		if (pdata->dma->chan_priv_rx)
 			cfg.slave_id = pdata->dma->slave_id_rx;
 		cfg.direction = DMA_DEV_TO_MEM;
-		cfg.src_addr = cfg.dst_addr;
+		cfg.src_addr = cfg.dst_addr + pdata->dma->dma_rx_offset;
 		cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 		cfg.dst_addr = 0;
 		ret = dmaengine_slave_config(host->chan_rx, &cfg);
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 8f6f2e91e7ae..777e29b1ad0f 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -96,6 +96,7 @@ struct tmio_mmc_dma {
 	int slave_id_tx;
 	int slave_id_rx;
 	int alignment_shift;
+	dma_addr_t dma_rx_offset;
 	bool (*filter)(struct dma_chan *chan, void *arg);
 };
 
-- 
cgit v1.2.3


From b8d11962c2d83c984d5afd091e5b725ad2fd5607 Mon Sep 17 00:00:00 2001
From: Shinobu Uehara <shinobu.uehara.xc@renesas.com>
Date: Sun, 24 Aug 2014 20:00:25 -0700
Subject: mmc: tmio: control multiple block transfer mode

Renesas SDHI has "Multiple Block Transfer Mode" settings
on SD_CMD register which controls CMD12 automatically.

This patch cares it, because
CMD12 is not needed when CMD53 (= SD_IO_RW_EXTENDED)

[Kuninori Morimoto: tidyuped for upstreaming
                    enabled this flags for all SH-Mobile/R-Car]

Tested-by: Nguyen Xuan Nui <nx-nui@jinso.co.jp>
Tested-by: Hiep Cao Minh <cm-hiep@jinso.co.jp>
Signed-off-by: Shinobu Uehara <shinobu.uehara.xc@renesas.com>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c |  5 +++++
 drivers/mmc/host/tmio_mmc_pio.c   | 10 ++++++++++
 include/linux/mfd/tmio.h          |  6 ++++++
 3 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index f0818cd0242c..4727586b063e 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -225,6 +225,11 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	 */
 	mmc_data->flags |= TMIO_MMC_SDIO_IRQ;
 
+	/*
+	 * All SDHI have CMD12 controll bit
+	 */
+	mmc_data->flags |= TMIO_MMC_HAVE_CMD12_CTRL;
+
 	if (of_id && of_id->data) {
 		const struct sh_mobile_sdhi_of_data *of_data = of_id->data;
 		mmc_data->flags |= of_data->tmio_flags;
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 3d0ad737abea..c2804827be9f 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -44,6 +44,7 @@
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
+#include <linux/mmc/sdio.h>
 #include <linux/scatterlist.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
@@ -310,6 +311,7 @@ static void tmio_mmc_done_work(struct work_struct *work)
 #define TRANSFER_READ  0x1000
 #define TRANSFER_MULTI 0x2000
 #define SECURITY_CMD   0x4000
+#define NO_CMD12_ISSUE 0x4000 /* TMIO_MMC_HAVE_CMD12_CTRL */
 
 static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command *cmd)
 {
@@ -346,6 +348,14 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 		if (data->blocks > 1) {
 			sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, 0x100);
 			c |= TRANSFER_MULTI;
+
+			/*
+			 * Disable auto CMD12 at IO_RW_EXTENDED when
+			 * multiple block transfer
+			 */
+			if ((host->pdata->flags & TMIO_MMC_HAVE_CMD12_CTRL) &&
+			    (cmd->opcode == SD_IO_RW_EXTENDED))
+				c |= NO_CMD12_ISSUE;
 		}
 		if (data->flags & MMC_DATA_READ)
 			c |= TRANSFER_READ;
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 777e29b1ad0f..7432d95b08e2 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -83,6 +83,12 @@
  */
 #define TMIO_MMC_HAVE_HIGH_REG		(1 << 6)
 
+/*
+ * Some controllers have CMD12 automatically
+ * issue/non-issue register
+ */
+#define TMIO_MMC_HAVE_CMD12_CTRL	(1 << 7)
+
 int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base);
 int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base);
 void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state);
-- 
cgit v1.2.3


From 6b98757e53cb0e93b02db4067c14afcb32c90615 Mon Sep 17 00:00:00 2001
From: Shinobu Uehara <shinobu.uehara.xc@renesas.com>
Date: Sun, 24 Aug 2014 20:00:52 -0700
Subject: mmc: tmio: add TMIO_MMC_SDIO_STATUS_QUIRK

Renesas R-Car SDHI should set reserved bits
on CTL_SDIO_STATUS register when writing.
This patch adds new TMIO_MMC_SDIO_STATUS_QUIRK flags
for this purpose

[Kuninori Morimoto: tidyuped for upstreaming
                    enabled this flags for all SH-Mobile/R-Car]

Tested-by: Nguyen Xuan Nui <nx-nui@jinso.co.jp>
Tested-by: Hiep Cao Minh <cm-hiep@jinso.co.jp>
Signed-off-by: Shinobu Uehara <shinobu.uehara.xc@renesas.com>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 5 +++++
 drivers/mmc/host/tmio_mmc_pio.c   | 7 ++++++-
 include/linux/mfd/tmio.h          | 5 +++++
 3 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 4727586b063e..ebcfc659b799 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -230,6 +230,11 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	 */
 	mmc_data->flags |= TMIO_MMC_HAVE_CMD12_CTRL;
 
+	/*
+	 * All SDHI need SDIO_INFO1 reserved bit
+	 */
+	mmc_data->flags |= TMIO_MMC_SDIO_STATUS_QUIRK;
+
 	if (of_id && of_id->data) {
 		const struct sh_mobile_sdhi_of_data *of_data = of_id->data;
 		mmc_data->flags |= of_data->tmio_flags;
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index c2804827be9f..c5ffa92ccb18 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -665,6 +665,7 @@ irqreturn_t tmio_mmc_sdio_irq(int irq, void *devid)
 	struct mmc_host *mmc = host->mmc;
 	struct tmio_mmc_data *pdata = host->pdata;
 	unsigned int ireg, status;
+	unsigned int sdio_status;
 
 	if (!(pdata->flags & TMIO_MMC_SDIO_IRQ))
 		return IRQ_HANDLED;
@@ -672,7 +673,11 @@ irqreturn_t tmio_mmc_sdio_irq(int irq, void *devid)
 	status = sd_ctrl_read16(host, CTL_SDIO_STATUS);
 	ireg = status & TMIO_SDIO_MASK_ALL & ~host->sdcard_irq_mask;
 
-	sd_ctrl_write16(host, CTL_SDIO_STATUS, status & ~TMIO_SDIO_MASK_ALL);
+	sdio_status = status & ~TMIO_SDIO_MASK_ALL;
+	if (pdata->flags & TMIO_MMC_SDIO_STATUS_QUIRK)
+		sdio_status |= 6;
+
+	sd_ctrl_write16(host, CTL_SDIO_STATUS, sdio_status);
 
 	if (mmc->caps & MMC_CAP_SDIO_IRQ && ireg & TMIO_SDIO_STAT_IOIRQ)
 		mmc_signal_sdio_irq(mmc);
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 7432d95b08e2..a7493ae01b58 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -89,6 +89,11 @@
  */
 #define TMIO_MMC_HAVE_CMD12_CTRL	(1 << 7)
 
+/*
+ * Some controllers needs to set 1 on SDIO status reserved bits
+ */
+#define TMIO_MMC_SDIO_STATUS_QUIRK	(1 << 8)
+
 int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base);
 int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base);
 void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state);
-- 
cgit v1.2.3


From e85dd04ea8c8d32ba8eae278959d28df34338e9d Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Sun, 24 Aug 2014 20:01:54 -0700
Subject: mmc: tmio: remove Renesas specific #ifdef

This patch adds new TMIO_MMC_HAVE_CTL_DMA_REG flag,
and remove Renesas specific #ifdef from tmio driver

Tested-by: Nguyen Xuan Nui <nx-nui@jinso.co.jp>
Tested-by: Hiep Cao Minh <cm-hiep@jinso.co.jp>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 5 +++++
 drivers/mmc/host/tmio_mmc_dma.c   | 6 ++----
 include/linux/mfd/tmio.h          | 5 +++++
 3 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index ebcfc659b799..a077da02bb8e 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -235,6 +235,11 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	 */
 	mmc_data->flags |= TMIO_MMC_SDIO_STATUS_QUIRK;
 
+	/*
+	 * All SDHI have DMA control register
+	 */
+	mmc_data->flags |= TMIO_MMC_HAVE_CTL_DMA_REG;
+
 	if (of_id && of_id->data) {
 		const struct sh_mobile_sdhi_of_data *of_data = of_id->data;
 		mmc_data->flags |= of_data->tmio_flags;
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index bd646b041085..7d077388b9eb 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -28,10 +28,8 @@ void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable)
 	if (!host->chan_tx || !host->chan_rx)
 		return;
 
-#if defined(CONFIG_SUPERH) || defined(CONFIG_ARCH_SHMOBILE)
-	/* Switch DMA mode on or off - SuperH specific? */
-	sd_ctrl_write16(host, CTL_DMA_ENABLE, enable ? 2 : 0);
-#endif
+	if (host->pdata->flags & TMIO_MMC_HAVE_CTL_DMA_REG)
+		sd_ctrl_write16(host, CTL_DMA_ENABLE, enable ? 2 : 0);
 }
 
 void tmio_mmc_abort_dma(struct tmio_mmc_host *host)
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index a7493ae01b58..adcb0cdb2fdb 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -94,6 +94,11 @@
  */
 #define TMIO_MMC_SDIO_STATUS_QUIRK	(1 << 8)
 
+/*
+ * Some controllers have DMA enable/disable register
+ */
+#define TMIO_MMC_HAVE_CTL_DMA_REG	(1 << 9)
+
 int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base);
 int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base);
 void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state);
-- 
cgit v1.2.3


From da29fe2bf573f0ae56fdc2e790387cb73fc8c6f8 Mon Sep 17 00:00:00 2001
From: Shinobu Uehara <shinobu.uehara.xc@renesas.com>
Date: Sun, 24 Aug 2014 20:03:00 -0700
Subject: mmc: tmio: add actual clock support as option

Some controller is supporting actual clock on SD_CLK_CTRL :: DIV[7:0].
Renesas SH-Mobile SDHI doesn't support,
but, Renesas R-Car SDHI supports it.
This patch adds new TMIO_MMC_CLK_ACTUAL flag for it.

[Kuninori Morimoto: tidyuped for upstreaming]

Tested-by: Nguyen Xuan Nui <nx-nui@jinso.co.jp>
Tested-by: Hiep Cao Minh <cm-hiep@jinso.co.jp>
Signed-off-by: Shinobu Uehara <shinobu.uehara.xc@renesas.com>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 6 ++++--
 drivers/mmc/host/tmio_mmc_pio.c   | 5 +++++
 include/linux/mfd/tmio.h          | 5 +++++
 3 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index a077da02bb8e..d5d493719491 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -49,12 +49,14 @@ static const struct sh_mobile_sdhi_of_data sh_mobile_sdhi_of_cfg[] = {
 };
 
 static const struct sh_mobile_sdhi_of_data of_rcar_gen1_compatible = {
-	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE,
+	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE |
+			  TMIO_MMC_CLK_ACTUAL,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ,
 };
 
 static const struct sh_mobile_sdhi_of_data of_rcar_gen2_compatible = {
-	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE,
+	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE |
+			  TMIO_MMC_CLK_ACTUAL,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ,
 	.capabilities2	= MMC_CAP2_NO_MULTI_READ,
 	.dma_rx_offset	= 0x2000,
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 7cfe939992de..ba454131f9a8 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -159,6 +159,11 @@ static void tmio_mmc_set_clock(struct tmio_mmc_host *host,
 		for (clock = host->mmc->f_min, clk = 0x80000080;
 			new_clock >= (clock<<1); clk >>= 1)
 			clock <<= 1;
+
+		/* 1/1 clock is option */
+		if ((host->pdata->flags & TMIO_MMC_CLK_ACTUAL) &&
+		    ((clk >> 22) & 0x1))
+			clk |= 0xff;
 	}
 
 	if (host->set_clk_div)
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index adcb0cdb2fdb..90436d523e5e 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -99,6 +99,11 @@
  */
 #define TMIO_MMC_HAVE_CTL_DMA_REG	(1 << 9)
 
+/*
+ * Some controllers allows to set SDx actual clock
+ */
+#define TMIO_MMC_CLK_ACTUAL		(1 << 10)
+
 int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base);
 int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base);
 void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state);
-- 
cgit v1.2.3


From 51da2240906cb94e8f6ba55e403b6206df6fb2dd Mon Sep 17 00:00:00 2001
From: Yuvaraj CD <yuvaraj.cd@gmail.com>
Date: Fri, 22 Aug 2014 19:17:50 +0530
Subject: mmc: dw_mmc: use mmc_regulator_get_supply to handle regulators

This patch makes use of mmc_regulator_get_supply() to handle
the vmmc and vqmmc regulators.Also it moves the code handling
the these regulators to dw_mci_set_ios().It turned on the vmmc
and vqmmc during MMC_POWER_UP and MMC_POWER_ON,and turned off
during MMC_POWER_OFF.

Signed-off-by: Yuvaraj Kumar C D <yuvaraj.cd@samsung.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/dw_mmc.c  | 72 ++++++++++++++++++++++------------------------
 include/linux/mmc/dw_mmc.h |  2 +-
 2 files changed, 36 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 7f227e964265..aadb0d6aa63f 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -936,6 +936,7 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	struct dw_mci_slot *slot = mmc_priv(mmc);
 	const struct dw_mci_drv_data *drv_data = slot->host->drv_data;
 	u32 regs;
+	int ret;
 
 	switch (ios->bus_width) {
 	case MMC_BUS_WIDTH_4:
@@ -974,12 +975,38 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	switch (ios->power_mode) {
 	case MMC_POWER_UP:
+		if (!IS_ERR(mmc->supply.vmmc)) {
+			ret = mmc_regulator_set_ocr(mmc, mmc->supply.vmmc,
+					ios->vdd);
+			if (ret) {
+				dev_err(slot->host->dev,
+					"failed to enable vmmc regulator\n");
+				/*return, if failed turn on vmmc*/
+				return;
+			}
+		}
+		if (!IS_ERR(mmc->supply.vqmmc) && !slot->host->vqmmc_enabled) {
+			ret = regulator_enable(mmc->supply.vqmmc);
+			if (ret < 0)
+				dev_err(slot->host->dev,
+					"failed to enable vqmmc regulator\n");
+			else
+				slot->host->vqmmc_enabled = true;
+		}
 		set_bit(DW_MMC_CARD_NEED_INIT, &slot->flags);
 		regs = mci_readl(slot->host, PWREN);
 		regs |= (1 << slot->id);
 		mci_writel(slot->host, PWREN, regs);
 		break;
 	case MMC_POWER_OFF:
+		if (!IS_ERR(mmc->supply.vmmc))
+			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
+
+		if (!IS_ERR(mmc->supply.vqmmc) && slot->host->vqmmc_enabled) {
+			regulator_disable(mmc->supply.vqmmc);
+			slot->host->vqmmc_enabled = false;
+		}
+
 		regs = mci_readl(slot->host, PWREN);
 		regs &= ~(1 << slot->id);
 		mci_writel(slot->host, PWREN, regs);
@@ -2110,7 +2137,13 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 		mmc->f_max = freq[1];
 	}
 
-	mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
+	/*if there are external regulators, get them*/
+	ret = mmc_regulator_get_supply(mmc);
+	if (ret == -EPROBE_DEFER)
+		goto err_setup_bus;
+
+	if (!mmc->ocr_avail)
+		mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
 
 	if (host->pdata->caps)
 		mmc->caps = host->pdata->caps;
@@ -2176,7 +2209,7 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 
 err_setup_bus:
 	mmc_free_host(mmc);
-	return -EINVAL;
+	return ret;
 }
 
 static void dw_mci_cleanup_slot(struct dw_mci_slot *slot, unsigned int id)
@@ -2469,24 +2502,6 @@ int dw_mci_probe(struct dw_mci *host)
 		}
 	}
 
-	host->vmmc = devm_regulator_get_optional(host->dev, "vmmc");
-	if (IS_ERR(host->vmmc)) {
-		ret = PTR_ERR(host->vmmc);
-		if (ret == -EPROBE_DEFER)
-			goto err_clk_ciu;
-
-		dev_info(host->dev, "no vmmc regulator found: %d\n", ret);
-		host->vmmc = NULL;
-	} else {
-		ret = regulator_enable(host->vmmc);
-		if (ret) {
-			if (ret != -EPROBE_DEFER)
-				dev_err(host->dev,
-					"regulator_enable fail: %d\n", ret);
-			goto err_clk_ciu;
-		}
-	}
-
 	host->quirks = host->pdata->quirks;
 
 	spin_lock_init(&host->lock);
@@ -2630,8 +2645,6 @@ err_workqueue:
 err_dmaunmap:
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
-	if (host->vmmc)
-		regulator_disable(host->vmmc);
 
 err_clk_ciu:
 	if (!IS_ERR(host->ciu_clk))
@@ -2667,9 +2680,6 @@ void dw_mci_remove(struct dw_mci *host)
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
 
-	if (host->vmmc)
-		regulator_disable(host->vmmc);
-
 	if (!IS_ERR(host->ciu_clk))
 		clk_disable_unprepare(host->ciu_clk);
 
@@ -2686,9 +2696,6 @@ EXPORT_SYMBOL(dw_mci_remove);
  */
 int dw_mci_suspend(struct dw_mci *host)
 {
-	if (host->vmmc)
-		regulator_disable(host->vmmc);
-
 	return 0;
 }
 EXPORT_SYMBOL(dw_mci_suspend);
@@ -2697,15 +2704,6 @@ int dw_mci_resume(struct dw_mci *host)
 {
 	int i, ret;
 
-	if (host->vmmc) {
-		ret = regulator_enable(host->vmmc);
-		if (ret) {
-			dev_err(host->dev,
-				"failed to enable regulator: %d\n", ret);
-			return ret;
-		}
-	}
-
 	if (!dw_mci_ctrl_reset(host, SDMMC_CTRL_ALL_RESET_FLAGS)) {
 		ret = -ENODEV;
 		return ret;
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 29ce014ab421..84e2827d0f0b 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -188,7 +188,7 @@ struct dw_mci {
 	/* Workaround flags */
 	u32			quirks;
 
-	struct regulator	*vmmc;	/* Power regulator */
+	bool			vqmmc_enabled;
 	unsigned long		irq_flags; /* IRQ flags */
 	int			irq;
 };
-- 
cgit v1.2.3


From 0173055842cd1d9ed3984e70891c22dbf2f29372 Mon Sep 17 00:00:00 2001
From: Doug Anderson <dianders@chromium.org>
Date: Fri, 22 Aug 2014 19:17:51 +0530
Subject: mmc: dw_mmc: Support voltage changes

For UHS cards we need the ability to switch voltages from 3.3V to
1.8V.  Add support to the dw_mmc driver to handle this.  Note that
dw_mmc needs a little bit of extra code since the interface needs a
special bit programmed to the CMD register while CMD11 is progressing.
This means adding a few extra states to the state machine to track.

Signed-off-by: Doug Anderson <dianders@chromium.org>
Signed-off-by: Yuvaraj Kumar C D <yuvaraj.cd@samsung.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/dw_mmc.c  | 137 ++++++++++++++++++++++++++++++++++++++++++---
 drivers/mmc/host/dw_mmc.h  |   5 +-
 include/linux/mmc/dw_mmc.h |   2 +
 3 files changed, 134 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index aadb0d6aa63f..23719249182b 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -29,6 +29,7 @@
 #include <linux/irq.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
 #include <linux/mmc/sdio.h>
 #include <linux/mmc/dw_mmc.h>
 #include <linux/bitops.h>
@@ -234,10 +235,13 @@ err:
 }
 #endif /* defined(CONFIG_DEBUG_FS) */
 
+static void mci_send_cmd(struct dw_mci_slot *slot, u32 cmd, u32 arg);
+
 static u32 dw_mci_prepare_command(struct mmc_host *mmc, struct mmc_command *cmd)
 {
 	struct mmc_data	*data;
 	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct dw_mci *host = slot->host;
 	const struct dw_mci_drv_data *drv_data = slot->host->drv_data;
 	u32 cmdr;
 	cmd->error = -EINPROGRESS;
@@ -253,6 +257,34 @@ static u32 dw_mci_prepare_command(struct mmc_host *mmc, struct mmc_command *cmd)
 	else if (cmd->opcode != MMC_SEND_STATUS && cmd->data)
 		cmdr |= SDMMC_CMD_PRV_DAT_WAIT;
 
+	if (cmd->opcode == SD_SWITCH_VOLTAGE) {
+		u32 clk_en_a;
+
+		/* Special bit makes CMD11 not die */
+		cmdr |= SDMMC_CMD_VOLT_SWITCH;
+
+		/* Change state to continue to handle CMD11 weirdness */
+		WARN_ON(slot->host->state != STATE_SENDING_CMD);
+		slot->host->state = STATE_SENDING_CMD11;
+
+		/*
+		 * We need to disable low power mode (automatic clock stop)
+		 * while doing voltage switch so we don't confuse the card,
+		 * since stopping the clock is a specific part of the UHS
+		 * voltage change dance.
+		 *
+		 * Note that low power mode (SDMMC_CLKEN_LOW_PWR) will be
+		 * unconditionally turned back on in dw_mci_setup_bus() if it's
+		 * ever called with a non-zero clock.  That shouldn't happen
+		 * until the voltage change is all done.
+		 */
+		clk_en_a = mci_readl(host, CLKENA);
+		clk_en_a &= ~(SDMMC_CLKEN_LOW_PWR << slot->id);
+		mci_writel(host, CLKENA, clk_en_a);
+		mci_send_cmd(slot, SDMMC_CMD_UPD_CLK |
+			     SDMMC_CMD_PRV_DAT_WAIT, 0);
+	}
+
 	if (cmd->flags & MMC_RSP_PRESENT) {
 		/* We expect a response, so set this bit */
 		cmdr |= SDMMC_CMD_RESP_EXP;
@@ -775,11 +807,15 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 	unsigned int clock = slot->clock;
 	u32 div;
 	u32 clk_en_a;
+	u32 sdmmc_cmd_bits = SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT;
+
+	/* We must continue to set bit 28 in CMD until the change is complete */
+	if (host->state == STATE_WAITING_CMD11_DONE)
+		sdmmc_cmd_bits |= SDMMC_CMD_VOLT_SWITCH;
 
 	if (!clock) {
 		mci_writel(host, CLKENA, 0);
-		mci_send_cmd(slot,
-			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
+		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
 	} else if (clock != host->current_speed || force_clkinit) {
 		div = host->bus_hz / clock;
 		if (host->bus_hz % clock && host->bus_hz > clock)
@@ -803,15 +839,13 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 		mci_writel(host, CLKSRC, 0);
 
 		/* inform CIU */
-		mci_send_cmd(slot,
-			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
+		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
 
 		/* set clock to desired speed */
 		mci_writel(host, CLKDIV, div);
 
 		/* inform CIU */
-		mci_send_cmd(slot,
-			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
+		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
 
 		/* enable clock; only low power if no SDIO */
 		clk_en_a = SDMMC_CLKEN_ENABLE << slot->id;
@@ -820,8 +854,7 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 		mci_writel(host, CLKENA, clk_en_a);
 
 		/* inform CIU */
-		mci_send_cmd(slot,
-			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
+		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
 
 		/* keep the clock with reflecting clock dividor */
 		slot->__clk_old = clock << div;
@@ -897,6 +930,17 @@ static void dw_mci_queue_request(struct dw_mci *host, struct dw_mci_slot *slot,
 
 	slot->mrq = mrq;
 
+	if (host->state == STATE_WAITING_CMD11_DONE) {
+		dev_warn(&slot->mmc->class_dev,
+			 "Voltage change didn't complete\n");
+		/*
+		 * this case isn't expected to happen, so we can
+		 * either crash here or just try to continue on
+		 * in the closest possible state
+		 */
+		host->state = STATE_IDLE;
+	}
+
 	if (host->state == STATE_IDLE) {
 		host->state = STATE_SENDING_CMD;
 		dw_mci_start_request(host, slot);
@@ -973,6 +1017,9 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	/* Slot specific timing and width adjustment */
 	dw_mci_setup_bus(slot, false);
 
+	if (slot->host->state == STATE_WAITING_CMD11_DONE && ios->clock != 0)
+		slot->host->state = STATE_IDLE;
+
 	switch (ios->power_mode) {
 	case MMC_POWER_UP:
 		if (!IS_ERR(mmc->supply.vmmc)) {
@@ -1016,6 +1063,59 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	}
 }
 
+static int dw_mci_card_busy(struct mmc_host *mmc)
+{
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	u32 status;
+
+	/*
+	 * Check the busy bit which is low when DAT[3:0]
+	 * (the data lines) are 0000
+	 */
+	status = mci_readl(slot->host, STATUS);
+
+	return !!(status & SDMMC_STATUS_BUSY);
+}
+
+static int dw_mci_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct dw_mci *host = slot->host;
+	u32 uhs;
+	u32 v18 = SDMMC_UHS_18V << slot->id;
+	int min_uv, max_uv;
+	int ret;
+
+	/*
+	 * Program the voltage.  Note that some instances of dw_mmc may use
+	 * the UHS_REG for this.  For other instances (like exynos) the UHS_REG
+	 * does no harm but you need to set the regulator directly.  Try both.
+	 */
+	uhs = mci_readl(host, UHS_REG);
+	if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+		min_uv = 2700000;
+		max_uv = 3600000;
+		uhs &= ~v18;
+	} else {
+		min_uv = 1700000;
+		max_uv = 1950000;
+		uhs |= v18;
+	}
+	if (!IS_ERR(mmc->supply.vqmmc)) {
+		ret = regulator_set_voltage(mmc->supply.vqmmc, min_uv, max_uv);
+
+		if (ret) {
+			dev_err(&mmc->class_dev,
+					 "Regulator set error %d: %d - %d\n",
+					 ret, min_uv, max_uv);
+			return ret;
+		}
+	}
+	mci_writel(host, UHS_REG, uhs);
+
+	return 0;
+}
+
 static int dw_mci_get_ro(struct mmc_host *mmc)
 {
 	int read_only;
@@ -1158,6 +1258,9 @@ static const struct mmc_host_ops dw_mci_ops = {
 	.get_cd			= dw_mci_get_cd,
 	.enable_sdio_irq	= dw_mci_enable_sdio_irq,
 	.execute_tuning		= dw_mci_execute_tuning,
+	.card_busy		= dw_mci_card_busy,
+	.start_signal_voltage_switch = dw_mci_switch_voltage,
+
 };
 
 static void dw_mci_request_end(struct dw_mci *host, struct mmc_request *mrq)
@@ -1181,7 +1284,11 @@ static void dw_mci_request_end(struct dw_mci *host, struct mmc_request *mrq)
 		dw_mci_start_request(host, slot);
 	} else {
 		dev_vdbg(host->dev, "list empty\n");
-		host->state = STATE_IDLE;
+
+		if (host->state == STATE_SENDING_CMD11)
+			host->state = STATE_WAITING_CMD11_DONE;
+		else
+			host->state = STATE_IDLE;
 	}
 
 	spin_unlock(&host->lock);
@@ -1292,8 +1399,10 @@ static void dw_mci_tasklet_func(unsigned long priv)
 
 		switch (state) {
 		case STATE_IDLE:
+		case STATE_WAITING_CMD11_DONE:
 			break;
 
+		case STATE_SENDING_CMD11:
 		case STATE_SENDING_CMD:
 			if (!test_and_clear_bit(EVENT_CMD_COMPLETE,
 						&host->pending_events))
@@ -1894,6 +2003,14 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 	}
 
 	if (pending) {
+		/* Check volt switch first, since it can look like an error */
+		if ((host->state == STATE_SENDING_CMD11) &&
+		    (pending & SDMMC_INT_VOLT_SWITCH)) {
+			mci_writel(host, RINTSTS, SDMMC_INT_VOLT_SWITCH);
+			pending &= ~SDMMC_INT_VOLT_SWITCH;
+			dw_mci_cmd_interrupt(host, pending);
+		}
+
 		if (pending & DW_MCI_CMD_ERROR_FLAGS) {
 			mci_writel(host, RINTSTS, DW_MCI_CMD_ERROR_FLAGS);
 			host->cmd_status = pending;
@@ -1999,7 +2116,9 @@ static void dw_mci_work_routine_card(struct work_struct *work)
 
 					switch (host->state) {
 					case STATE_IDLE:
+					case STATE_WAITING_CMD11_DONE:
 						break;
+					case STATE_SENDING_CMD11:
 					case STATE_SENDING_CMD:
 						mrq->cmd->error = -ENOMEDIUM;
 						if (!mrq->data)
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 08fd956d81f3..01b99e8a9190 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -99,6 +99,7 @@
 #define SDMMC_INT_HLE			BIT(12)
 #define SDMMC_INT_FRUN			BIT(11)
 #define SDMMC_INT_HTO			BIT(10)
+#define SDMMC_INT_VOLT_SWITCH		BIT(10) /* overloads bit 10! */
 #define SDMMC_INT_DRTO			BIT(9)
 #define SDMMC_INT_RTO			BIT(8)
 #define SDMMC_INT_DCRC			BIT(7)
@@ -113,6 +114,7 @@
 /* Command register defines */
 #define SDMMC_CMD_START			BIT(31)
 #define SDMMC_CMD_USE_HOLD_REG	BIT(29)
+#define SDMMC_CMD_VOLT_SWITCH		BIT(28)
 #define SDMMC_CMD_CCS_EXP		BIT(23)
 #define SDMMC_CMD_CEATA_RD		BIT(22)
 #define SDMMC_CMD_UPD_CLK		BIT(21)
@@ -130,6 +132,7 @@
 /* Status register defines */
 #define SDMMC_GET_FCNT(x)		(((x)>>17) & 0x1FFF)
 #define SDMMC_STATUS_DMA_REQ		BIT(31)
+#define SDMMC_STATUS_BUSY		BIT(9)
 /* FIFOTH register defines */
 #define SDMMC_SET_FIFOTH(m, r, t)	(((m) & 0x7) << 28 | \
 					 ((r) & 0xFFF) << 16 | \
@@ -150,7 +153,7 @@
 #define SDMMC_GET_VERID(x)		((x) & 0xFFFF)
 /* Card read threshold */
 #define SDMMC_SET_RD_THLD(v, x)		(((v) & 0x1FFF) << 16 | (x))
-
+#define SDMMC_UHS_18V			BIT(0)
 /* All ctrl reset bits */
 #define SDMMC_CTRL_ALL_RESET_FLAGS \
 	(SDMMC_CTRL_RESET | SDMMC_CTRL_FIFO_RESET | SDMMC_CTRL_DMA_RESET)
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 84e2827d0f0b..001366927cf4 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -26,6 +26,8 @@ enum dw_mci_state {
 	STATE_DATA_BUSY,
 	STATE_SENDING_STOP,
 	STATE_DATA_ERROR,
+	STATE_SENDING_CMD11,
+	STATE_WAITING_CMD11_DONE,
 };
 
 enum {
-- 
cgit v1.2.3


From e99783a45220a2c5f5a598e0e81213ecf2dbcf2f Mon Sep 17 00:00:00 2001
From: Chanho Min <chanho.min@lge.com>
Date: Sat, 30 Aug 2014 12:40:40 +0900
Subject: mmc: sdhci: handle busy-end interrupt during command

It is fully legal for a controller to start handling busy-end interrupt
before it has signaled that the command has completed. So make sure
we do things in the proper order, Or it results that command interrupt
is ignored so it can cause unexpected operations. This is founded at some
toshiba emmc with the bellow warning.

"mmc0: Got command interrupt 0x00000001 even though
no command operation was in progress."

This issue has been also reported by Youssef TRIKI:
It is not specific to Toshiba devices, and happens with eMMC devices
as well as SD card which support Auto-CMD12 rather than CMD23.

Also, similar patch is submitted by:
Gwendal Grignou <gwendal@chromium.org>

Changes since v1:
 Fixed conflict with the next of git.linaro.org/people/ulf.hansson/mmc.git
 and Tested if issue is fixed again.

Signed-off-by: Hankyung Yu <hankyung.yu@lge.com>
Signed-off-by: Chanho Min <chanho.min@lge.com>
Tested-by: Youssef TRIKI <youssef.triki@st.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 17 +++++++++++++++--
 include/linux/mmc/sdhci.h |  1 +
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index b5e22b8c4885..335cdf3b5224 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1016,6 +1016,7 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 	mod_timer(&host->timer, timeout);
 
 	host->cmd = cmd;
+	host->busy_handle = 0;
 
 	sdhci_prepare_data(host, cmd);
 
@@ -2261,8 +2262,12 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask)
 		if (host->cmd->data)
 			DBG("Cannot wait for busy signal when also "
 				"doing a data transfer");
-		else if (!(host->quirks & SDHCI_QUIRK_NO_BUSY_IRQ))
+		else if (!(host->quirks & SDHCI_QUIRK_NO_BUSY_IRQ)
+				&& !host->busy_handle) {
+			/* Mark that command complete before busy is ended */
+			host->busy_handle = 1;
 			return;
+		}
 
 		/* The controller does not support the end-of-busy IRQ,
 		 * fall through and take the SDHCI_INT_RESPONSE */
@@ -2330,7 +2335,15 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 				return;
 			}
 			if (intmask & SDHCI_INT_DATA_END) {
-				sdhci_finish_command(host);
+				/*
+				 * Some cards handle busy-end interrupt
+				 * before the command completed, so make
+				 * sure we do things in the proper order.
+				 */
+				if (host->busy_handle)
+					sdhci_finish_command(host);
+				else
+					host->busy_handle = 1;
 				return;
 			}
 		}
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 09ebe57d5ce9..0aa85ca0c788 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -146,6 +146,7 @@ struct sdhci_host {
 	struct mmc_command *cmd;	/* Current command */
 	struct mmc_data *data;	/* Current data request */
 	unsigned int data_early:1;	/* Data finished before cmd */
+	unsigned int busy_handle:1;	/* Handling the order of Busy-end */
 
 	struct sg_mapping_iter sg_miter;	/* SG state for PIO */
 	unsigned int blocks;	/* remaining PIO blocks */
-- 
cgit v1.2.3


From 2e47e84245adcb1b3872210678b6146f674fb3ff Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 2 Sep 2014 19:08:53 -0700
Subject: mmc: Add .multi_io_quirk callback for multi I/O HW bug

Historically, we have been using MMC_CAP* to handle host HW issues and
currently the block layer uses MMC_CAP2_NO_MULTI_READ flag for a multi
I/O HW bug workaround.

There are a few tweaks needed to make MMC_CAP2_NO_MULTI_READ suite all
situations. Therefore let's add an optional host ops callback to enable
host drivers to return the number of blocks it allows per request.

In a future patch and when host drivers have converted to the new
callback, MMC_CAP2_NO_MULTI_READ shall be removed.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/card/block.c | 10 ++++++++++
 include/linux/mmc/host.h |  7 +++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index ede41f05c392..adab9038f6f7 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1402,6 +1402,16 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 		if (card->host->caps2 & MMC_CAP2_NO_MULTI_READ &&
 		    rq_data_dir(req) == READ)
 			brq->data.blocks = 1;
+
+		/*
+		 * Some controllers have HW issues while operating
+		 * in multiple I/O mode
+		 */
+		if (card->host->ops->multi_io_quirk)
+			brq->data.blocks = card->host->ops->multi_io_quirk(card,
+						(rq_data_dir(req) == READ) ?
+						MMC_DATA_READ : MMC_DATA_WRITE,
+						brq->data.blocks);
 	}
 
 	if (brq->data.blocks > 1 || do_rel_wr) {
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 4cbf61476999..10e2bd6985ae 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -139,6 +139,13 @@ struct mmc_host_ops {
 	int	(*select_drive_strength)(unsigned int max_dtr, int host_drv, int card_drv);
 	void	(*hw_reset)(struct mmc_host *host);
 	void	(*card_event)(struct mmc_host *host);
+
+	/*
+	 * Optional callback to support controllers with HW issues for multiple
+	 * I/O. Returns the number of supported blocks for the request.
+	 */
+	int	(*multi_io_quirk)(struct mmc_card *card,
+				  unsigned int direction, int blk_size);
 };
 
 struct mmc_card;
-- 
cgit v1.2.3


From bbf0208d39121bd8873b032459cb2b5f35e14593 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 8 Sep 2014 23:45:25 -0700
Subject: mmc: use .multi_io_quirk on tmio_mmc

Now, tmio_mmc can use .multi_io_quirk callback
instead of MMC_CAP2_NO_MULTI_READ flags.
let's use it.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/tmio_mmc_pio.c | 13 +++++++++++++
 include/linux/mfd/tmio.h        |  3 +++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index ba454131f9a8..ff5ff0f725c9 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -970,12 +970,25 @@ static int tmio_mmc_get_ro(struct mmc_host *mmc)
 	return ret;
 }
 
+static int tmio_multi_io_quirk(struct mmc_card *card,
+			       unsigned int direction, int blk_size)
+{
+	struct tmio_mmc_host *host = mmc_priv(card->host);
+	struct tmio_mmc_data *pdata = host->pdata;
+
+	if (pdata->multi_io_quirk)
+		return pdata->multi_io_quirk(card, direction, blk_size);
+
+	return blk_size;
+}
+
 static const struct mmc_host_ops tmio_mmc_ops = {
 	.request	= tmio_mmc_request,
 	.set_ios	= tmio_mmc_set_ios,
 	.get_ro         = tmio_mmc_get_ro,
 	.get_cd		= mmc_gpio_get_cd,
 	.enable_sdio_irq = tmio_mmc_enable_sdio_irq,
+	.multi_io_quirk	= tmio_multi_io_quirk,
 };
 
 static int tmio_mmc_init_ocr(struct tmio_mmc_host *host)
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 90436d523e5e..57388171610d 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -5,6 +5,7 @@
 #include <linux/fb.h>
 #include <linux/io.h>
 #include <linux/jiffies.h>
+#include <linux/mmc/card.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 
@@ -142,6 +143,8 @@ struct tmio_mmc_data {
 	/* clock management callbacks */
 	int (*clk_enable)(struct platform_device *pdev, unsigned int *f);
 	void (*clk_disable)(struct platform_device *pdev);
+	int (*multi_io_quirk)(struct mmc_card *card,
+			      unsigned int direction, int blk_size);
 };
 
 /*
-- 
cgit v1.2.3


From 0abb71feb228ddbd17e0dfa13216541e036bb549 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 8 Sep 2014 23:46:49 -0700
Subject: mmc: remove MMC_CAP2_NO_MULTI_READ flags

Now, mmc framework uses multi_io_quirk
for I/O HW bug workaround.
MMC_CAP2_NO_MULTI_READ flag is no longer needed

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/card/block.c | 5 -----
 include/linux/mmc/host.h | 1 -
 2 files changed, 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index adab9038f6f7..413f984cb76d 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1398,11 +1398,6 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 		if (disable_multi)
 			brq->data.blocks = 1;
 
-		/* Some controllers can't do multiblock reads due to hw bugs */
-		if (card->host->caps2 & MMC_CAP2_NO_MULTI_READ &&
-		    rq_data_dir(req) == READ)
-			brq->data.blocks = 1;
-
 		/*
 		 * Some controllers have HW issues while operating
 		 * in multiple I/O mode
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 10e2bd6985ae..797ae657dc3d 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -272,7 +272,6 @@ struct mmc_host {
 
 #define MMC_CAP2_BOOTPART_NOACC	(1 << 0)	/* Boot partition no access */
 #define MMC_CAP2_FULL_PWR_CYCLE	(1 << 2)	/* Can do full power cycle */
-#define MMC_CAP2_NO_MULTI_READ	(1 << 3)	/* Multiblock reads don't work */
 #define MMC_CAP2_HS200_1_8V_SDR	(1 << 5)        /* can support */
 #define MMC_CAP2_HS200_1_2V_SDR	(1 << 6)        /* can support */
 #define MMC_CAP2_HS200		(MMC_CAP2_HS200_1_8V_SDR | \
-- 
cgit v1.2.3


From 9d2fa2428ae149ba3a5b7a4ceb0a9e11f1882b3b Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Aug 2014 13:00:51 +0200
Subject: mmc: slot-gpio: add gpiod variant to get wp GPIO

This makes it possible to get the write protect (read only)
GPIO line from a GPIO descriptor. Written to exactly mirror
the card detect function.

Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/slot-gpio.c  | 48 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/mmc/slot-gpio.h |  3 +++
 2 files changed, 51 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 908c2b29e79f..e3fce4493fab 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -325,6 +325,54 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 }
 EXPORT_SYMBOL(mmc_gpiod_request_cd);
 
+/**
+ * mmc_gpiod_request_ro - request a gpio descriptor for write protection
+ * @host: mmc host
+ * @con_id: function within the GPIO consumer
+ * @idx: index of the GPIO to obtain in the consumer
+ * @override_active_level: ignore %GPIO_ACTIVE_LOW flag
+ * @debounce: debounce time in microseconds
+ *
+ * Use this function in place of mmc_gpio_request_ro() to use the GPIO
+ * descriptor API.  Note that it is paired with mmc_gpiod_free_ro() not
+ * mmc_gpio_free_ro().
+ *
+ * Returns zero on success, else an error.
+ */
+int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
+			 unsigned int idx, bool override_active_level,
+			 unsigned int debounce)
+{
+	struct mmc_gpio *ctx;
+	struct gpio_desc *desc;
+	int ret;
+
+	ret = mmc_gpio_alloc(host);
+	if (ret < 0)
+		return ret;
+
+	ctx = host->slot.handler_priv;
+
+	if (!con_id)
+		con_id = ctx->ro_label;
+
+	desc = devm_gpiod_get_index(host->parent, con_id, idx, GPIOD_IN);
+	if (IS_ERR(desc))
+		return PTR_ERR(desc);
+
+	if (debounce) {
+		ret = gpiod_set_debounce(desc, debounce);
+		if (ret < 0)
+			return ret;
+	}
+
+	ctx->override_ro_active_level = override_active_level;
+	ctx->ro_gpio = desc;
+
+	return 0;
+}
+EXPORT_SYMBOL(mmc_gpiod_request_ro);
+
 /**
  * mmc_gpiod_free_cd - free the card-detection gpio descriptor
  * @host: mmc host
diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h
index d2433381e828..a0d0442c15bf 100644
--- a/include/linux/mmc/slot-gpio.h
+++ b/include/linux/mmc/slot-gpio.h
@@ -25,6 +25,9 @@ void mmc_gpio_free_cd(struct mmc_host *host);
 int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
 			 unsigned int debounce);
+int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
+			 unsigned int idx, bool override_active_level,
+			 unsigned int debounce);
 void mmc_gpiod_free_cd(struct mmc_host *host);
 void mmc_gpiod_request_cd_irq(struct mmc_host *host);
 
-- 
cgit v1.2.3


From 3034a146820c26fe6da66a45f6340fe87fe0983a Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Fri, 27 Jun 2014 18:15:44 +0300
Subject: ima: pass 'opened' flag to identify newly created files

Empty files and missing xattrs do not guarantee that a file was
just created.  This patch passes FILE_CREATED flag to IMA to
reliably identify new files.

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org>  3.14+
---
 fs/namei.c                            |  2 +-
 fs/nfsd/vfs.c                         |  2 +-
 include/linux/ima.h                   |  4 ++--
 security/integrity/ima/ima.h          |  4 ++--
 security/integrity/ima/ima_appraise.c |  4 ++--
 security/integrity/ima/ima_main.c     | 16 ++++++++--------
 6 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 985c6f368485..005771f97189 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3058,7 +3058,7 @@ opened:
 	error = open_check_o_direct(file);
 	if (error)
 		goto exit_fput;
-	error = ima_file_check(file, op->acc_mode);
+	error = ima_file_check(file, op->acc_mode, *opened);
 	if (error)
 		goto exit_fput;
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 140c496f612c..d49c778faecb 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -709,7 +709,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 		host_err = PTR_ERR(*filp);
 		*filp = NULL;
 	} else {
-		host_err = ima_file_check(*filp, may_flags);
+		host_err = ima_file_check(*filp, may_flags, 0);
 
 		if (may_flags & NFSD_MAY_64BIT_COOKIE)
 			(*filp)->f_mode |= FMODE_64BITHASH;
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 7cf5e9b32550..120ccc53fcb7 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -15,7 +15,7 @@ struct linux_binprm;
 
 #ifdef CONFIG_IMA
 extern int ima_bprm_check(struct linux_binprm *bprm);
-extern int ima_file_check(struct file *file, int mask);
+extern int ima_file_check(struct file *file, int mask, int opened);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
 extern int ima_module_check(struct file *file);
@@ -27,7 +27,7 @@ static inline int ima_bprm_check(struct linux_binprm *bprm)
 	return 0;
 }
 
-static inline int ima_file_check(struct file *file, int mask)
+static inline int ima_file_check(struct file *file, int mask, int opened)
 {
 	return 0;
 }
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 57da4bd7ba0c..0fb456c20eda 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -177,7 +177,7 @@ void ima_delete_rules(void);
 int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len);
+			     int xattr_len, int opened);
 int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
 void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
 enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
@@ -193,7 +193,7 @@ static inline int ima_appraise_measurement(int func,
 					   struct file *file,
 					   const unsigned char *filename,
 					   struct evm_ima_xattr_data *xattr_value,
-					   int xattr_len)
+					   int xattr_len, int opened)
 {
 	return INTEGRITY_UNKNOWN;
 }
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index a4605d677248..225fd944a4ef 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -183,7 +183,7 @@ int ima_read_xattr(struct dentry *dentry,
 int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len)
+			     int xattr_len, int opened)
 {
 	static const char op[] = "appraise_data";
 	char *cause = "unknown";
@@ -203,7 +203,7 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 
 		cause = "missing-hash";
 		status = INTEGRITY_NOLABEL;
-		if (inode->i_size == 0) {
+		if (opened & FILE_CREATED) {
 			iint->flags |= IMA_NEW_FILE;
 			status = INTEGRITY_PASS;
 		}
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 0a2298f90c9c..f82cf9b8e92b 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -157,7 +157,7 @@ void ima_file_free(struct file *file)
 }
 
 static int process_measurement(struct file *file, const char *filename,
-			       int mask, int function)
+			       int mask, int function, int opened)
 {
 	struct inode *inode = file_inode(file);
 	struct integrity_iint_cache *iint;
@@ -226,7 +226,7 @@ static int process_measurement(struct file *file, const char *filename,
 				      xattr_value, xattr_len);
 	if (action & IMA_APPRAISE_SUBMASK)
 		rc = ima_appraise_measurement(_func, iint, file, pathname,
-					      xattr_value, xattr_len);
+					      xattr_value, xattr_len, opened);
 	if (action & IMA_AUDIT)
 		ima_audit_measurement(iint, pathname);
 	kfree(pathbuf);
@@ -255,7 +255,7 @@ out:
 int ima_file_mmap(struct file *file, unsigned long prot)
 {
 	if (file && (prot & PROT_EXEC))
-		return process_measurement(file, NULL, MAY_EXEC, MMAP_CHECK);
+		return process_measurement(file, NULL, MAY_EXEC, MMAP_CHECK, 0);
 	return 0;
 }
 
@@ -277,7 +277,7 @@ int ima_bprm_check(struct linux_binprm *bprm)
 	return process_measurement(bprm->file,
 				   (strcmp(bprm->filename, bprm->interp) == 0) ?
 				   bprm->filename : bprm->interp,
-				   MAY_EXEC, BPRM_CHECK);
+				   MAY_EXEC, BPRM_CHECK, 0);
 }
 
 /**
@@ -290,12 +290,12 @@ int ima_bprm_check(struct linux_binprm *bprm)
  * On success return 0.  On integrity appraisal error, assuming the file
  * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
  */
-int ima_file_check(struct file *file, int mask)
+int ima_file_check(struct file *file, int mask, int opened)
 {
 	ima_rdwr_violation_check(file);
 	return process_measurement(file, NULL,
 				   mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
-				   FILE_CHECK);
+				   FILE_CHECK, opened);
 }
 EXPORT_SYMBOL_GPL(ima_file_check);
 
@@ -318,7 +318,7 @@ int ima_module_check(struct file *file)
 #endif
 		return 0;	/* We rely on module signature checking */
 	}
-	return process_measurement(file, NULL, MAY_EXEC, MODULE_CHECK);
+	return process_measurement(file, NULL, MAY_EXEC, MODULE_CHECK, 0);
 }
 
 int ima_fw_from_file(struct file *file, char *buf, size_t size)
@@ -329,7 +329,7 @@ int ima_fw_from_file(struct file *file, char *buf, size_t size)
 			return -EACCES;	/* INTEGRITY_UNKNOWN */
 		return 0;
 	}
-	return process_measurement(file, NULL, MAY_EXEC, FIRMWARE_CHECK);
+	return process_measurement(file, NULL, MAY_EXEC, FIRMWARE_CHECK, 0);
 }
 
 static int __init init_ima(void)
-- 
cgit v1.2.3


From 2a5538e9aa4929329813bee69922c9ae4990fcad Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 25 Aug 2014 12:05:27 +0200
Subject: netfilter: nat: move specific NAT IPv6 to core

Move the specific NAT IPv6 core functions that are called from the
hooks from ip6table_nat.c to nf_nat_l3proto_ipv6.c. This prepares the
ground to allow iptables and nft to use the same NAT engine code that
comes in a follow up patch.

This also renames nf_nat_ipv6_fn to nft_nat_ipv6_fn in
net/ipv6/netfilter/nft_chain_nat_ipv6.c to avoid a compilation breakage.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_l3proto.h   |  37 +++++
 net/ipv6/netfilter/ip6table_nat.c        | 233 +++++--------------------------
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 199 ++++++++++++++++++++++++++
 net/ipv6/netfilter/nft_chain_nat_ipv6.c  |  10 +-
 4 files changed, 275 insertions(+), 204 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index bc2d51574489..340c013795a4 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -84,4 +84,41 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
 				    enum ip_conntrack_info ctinfo,
 				    unsigned int hooknum, unsigned int hdrlen);
 
+unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
+unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			     const struct net_device *in,
+			     const struct net_device *out,
+			     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						      struct sk_buff *skb,
+						      const struct net_device *in,
+						      const struct net_device *out,
+						      struct nf_conn *ct));
+
+unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops,
+				  struct sk_buff *skb,
+				  const struct net_device *in,
+				  const struct net_device *out,
+				  unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+							   struct sk_buff *skb,
+							   const struct net_device *in,
+							   const struct net_device *out,
+							   struct nf_conn *ct));
+
+unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct net_device *in,
+			    const struct net_device *out,
+			    unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+						     struct sk_buff *skb,
+						     const struct net_device *in,
+						     const struct net_device *out,
+						     struct nf_conn *ct));
+
 #endif /* _NF_NAT_L3PROTO_H */
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 387d8b8fc18d..b0634ac996b7 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -30,222 +30,57 @@ static const struct xt_table nf_nat_ipv6_table = {
 	.af		= NFPROTO_IPV6,
 };
 
-static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
-{
-	/* Force range to this IP; let proto decide mapping for
-	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
-	 */
-	struct nf_nat_range range;
-
-	range.flags = 0;
-	pr_debug("Allocating NULL binding for %p (%pI6)\n", ct,
-		 HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip6 :
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip6);
-
-	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
-}
-
-static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
-				     const struct net_device *in,
-				     const struct net_device *out,
-				     struct nf_conn *ct)
+static unsigned int ip6table_nat_do_chain(const struct nf_hook_ops *ops,
+					  struct sk_buff *skb,
+					  const struct net_device *in,
+					  const struct net_device *out,
+					  struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
-	unsigned int ret;
 
-	ret = ip6t_do_table(skb, hooknum, in, out, net->ipv6.ip6table_nat);
-	if (ret == NF_ACCEPT) {
-		if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
-			ret = alloc_null_binding(ct, hooknum);
-	}
-	return ret;
+	return ip6t_do_table(skb, ops->hooknum, in, out, net->ipv6.ip6table_nat);
 }
 
-static unsigned int
-nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_fn(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
 {
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn_nat *nat;
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
-	__be16 frag_off;
-	int hdrlen;
-	u8 nexthdr;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	/* Can't track?  It's not due to stress, or conntrack would
-	 * have dropped it.  Hence it's the user's responsibilty to
-	 * packet filter it out, or implement conntrack/NAT for that
-	 * protocol. 8) --RR
-	 */
-	if (!ct)
-		return NF_ACCEPT;
-
-	/* Don't try to NAT if this packet is not conntracked */
-	if (nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
-		nexthdr = ipv6_hdr(skb)->nexthdr;
-		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
-					  &nexthdr, &frag_off);
-
-		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
-			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
-							     ops->hooknum,
-							     hdrlen))
-				return NF_DROP;
-			else
-				return NF_ACCEPT;
-		}
-		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
-	case IP_CT_NEW:
-		/* Seen it before?  This can happen for loopback, retrans,
-		 * or local packets.
-		 */
-		if (!nf_nat_initialized(ct, maniptype)) {
-			unsigned int ret;
-
-			ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
-			if (ret != NF_ACCEPT)
-				return ret;
-		} else {
-			pr_debug("Already setup manip %s for ct %p\n",
-				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
-				 ct);
-			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-				goto oif_changed;
-		}
-		break;
-
-	default:
-		/* ESTABLISHED */
-		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
-			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-			goto oif_changed;
-	}
-
-	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
-
-oif_changed:
-	nf_ct_kill_acct(ct, ctinfo, skb);
-	return NF_DROP;
+	return nf_nat_ipv6_fn(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv6_in(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_in(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
 {
-	unsigned int ret;
-	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
-
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
-		skb_dst_drop(skb);
-
-	return ret;
+	return nf_nat_ipv6_in(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv6_out(const struct nf_hook_ops *ops,
-		struct sk_buff *skb,
-		const struct net_device *in,
-		const struct net_device *out,
-		int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_out(const struct nf_hook_ops *ops,
+				     struct sk_buff *skb,
+				     const struct net_device *in,
+				     const struct net_device *out,
+				     int (*okfn)(struct sk_buff *))
 {
-#ifdef CONFIG_XFRM
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	int err;
-#endif
-	unsigned int ret;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct ipv6hdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
-#ifdef CONFIG_XFRM
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
-				      &ct->tuplehash[!dir].tuple.dst.u3) ||
-		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
-		     ct->tuplehash[dir].tuple.src.u.all !=
-		     ct->tuplehash[!dir].tuple.dst.u.all)) {
-			err = nf_xfrm_me_harder(skb, AF_INET6);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-	}
-#endif
-	return ret;
+	return nf_nat_ipv6_out(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops,
-		     struct sk_buff *skb,
-		     const struct net_device *in,
-		     const struct net_device *out,
-		     int (*okfn)(struct sk_buff *))
+static unsigned int ip6table_nat_local_fn(const struct nf_hook_ops *ops,
+					  struct sk_buff *skb,
+					  const struct net_device *in,
+					  const struct net_device *out,
+					  int (*okfn)(struct sk_buff *))
 {
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	unsigned int ret;
-	int err;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct ipv6hdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
-				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			err = ip6_route_me_harder(skb);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#ifdef CONFIG_XFRM
-		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
-			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
-			 ct->tuplehash[dir].tuple.dst.u.all !=
-			 ct->tuplehash[!dir].tuple.src.u.all) {
-			err = nf_xfrm_me_harder(skb, AF_INET6);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#endif
-	}
-	return ret;
+	return nf_nat_ipv6_local_fn(ops, skb, in, out, ip6table_nat_do_chain);
 }
 
 static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv6_in,
+		.hook		= ip6table_nat_in,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_PRE_ROUTING,
@@ -253,7 +88,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv6_out,
+		.hook		= ip6table_nat_out,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_POST_ROUTING,
@@ -261,7 +96,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv6_local_fn,
+		.hook		= ip6table_nat_local_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_LOCAL_OUT,
@@ -269,7 +104,7 @@ static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv6_fn,
+		.hook		= ip6table_nat_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_LOCAL_IN,
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index fc8e49b2ff3e..c5812e1c1ffb 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -261,6 +261,205 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation);
 
+unsigned int
+nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	       const struct net_device *in, const struct net_device *out,
+	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					struct nf_conn *ct))
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn_nat *nat;
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+	__be16 frag_off;
+	int hdrlen;
+	u8 nexthdr;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	/* Can't track?  It's not due to stress, or conntrack would
+	 * have dropped it.  Hence it's the user's responsibilty to
+	 * packet filter it out, or implement conntrack/NAT for that
+	 * protocol. 8) --RR
+	 */
+	if (!ct)
+		return NF_ACCEPT;
+
+	/* Don't try to NAT if this packet is not conntracked */
+	if (nf_ct_is_untracked(ct))
+		return NF_ACCEPT;
+
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED_REPLY:
+		nexthdr = ipv6_hdr(skb)->nexthdr;
+		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
+					  &nexthdr, &frag_off);
+
+		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
+			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
+							     ops->hooknum,
+							     hdrlen))
+				return NF_DROP;
+			else
+				return NF_ACCEPT;
+		}
+		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+	case IP_CT_NEW:
+		/* Seen it before?  This can happen for loopback, retrans,
+		 * or local packets.
+		 */
+		if (!nf_nat_initialized(ct, maniptype)) {
+			unsigned int ret;
+
+			ret = do_chain(ops, skb, in, out, ct);
+			if (ret != NF_ACCEPT)
+				return ret;
+
+			if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum)))
+				break;
+
+			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+			if (ret != NF_ACCEPT)
+				return ret;
+		} else {
+			pr_debug("Already setup manip %s for ct %p\n",
+				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
+				 ct);
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+				goto oif_changed;
+		}
+		break;
+
+	default:
+		/* ESTABLISHED */
+		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
+			     ctinfo == IP_CT_ESTABLISHED_REPLY);
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+			goto oif_changed;
+	}
+
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+
+oif_changed:
+	nf_ct_kill_acct(ct, ctinfo, skb);
+	return NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_fn);
+
+unsigned int
+nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	       const struct net_device *in, const struct net_device *out,
+	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					struct nf_conn *ct))
+{
+	unsigned int ret;
+	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
+		skb_dst_drop(skb);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_in);
+
+unsigned int
+nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+		const struct net_device *in, const struct net_device *out,
+		unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 struct nf_conn *ct))
+{
+#ifdef CONFIG_XFRM
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	int err;
+#endif
+	unsigned int ret;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+#ifdef CONFIG_XFRM
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
+				      &ct->tuplehash[!dir].tuple.dst.u3) ||
+		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
+		     ct->tuplehash[dir].tuple.src.u.all !=
+		     ct->tuplehash[!dir].tuple.dst.u.all)) {
+			err = nf_xfrm_me_harder(skb, AF_INET6);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+	}
+#endif
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_out);
+
+unsigned int
+nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+		     const struct net_device *in, const struct net_device *out,
+		     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					      struct sk_buff *skb,
+					      const struct net_device *in,
+					      const struct net_device *out,
+					      struct nf_conn *ct))
+{
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned int ret;
+	int err;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
+				      &ct->tuplehash[!dir].tuple.src.u3)) {
+			err = ip6_route_me_harder(skb);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#ifdef CONFIG_XFRM
+		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
+			 ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all) {
+			err = nf_xfrm_me_harder(skb, AF_INET6);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#endif
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv6_local_fn);
+
 static int __init nf_nat_l3proto_ipv6_init(void)
 {
 	int err;
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index d189fcb437fe..c1c74491a10b 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -28,7 +28,7 @@
  * IPv6 NAT chains
  */
 
-static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
+static unsigned int nft_nat_ipv6_fn(const struct nf_hook_ops *ops,
 			      struct sk_buff *skb,
 			      const struct net_device *in,
 			      const struct net_device *out,
@@ -97,7 +97,7 @@ static unsigned int nf_nat_ipv6_prerouting(const struct nf_hook_ops *ops,
 	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
 	unsigned int ret;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
 		skb_dst_drop(skb);
@@ -115,7 +115,7 @@ static unsigned int nf_nat_ipv6_postrouting(const struct nf_hook_ops *ops,
 	const struct nf_conn *ct __maybe_unused;
 	unsigned int ret;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
@@ -143,7 +143,7 @@ static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops,
 	const struct nf_conn *ct;
 	unsigned int ret;
 
-	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	ret = nft_nat_ipv6_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
@@ -177,7 +177,7 @@ static const struct nf_chain_type nft_chain_nat_ipv6 = {
 		[NF_INET_PRE_ROUTING]	= nf_nat_ipv6_prerouting,
 		[NF_INET_POST_ROUTING]	= nf_nat_ipv6_postrouting,
 		[NF_INET_LOCAL_OUT]	= nf_nat_ipv6_output,
-		[NF_INET_LOCAL_IN]	= nf_nat_ipv6_fn,
+		[NF_INET_LOCAL_IN]	= nft_nat_ipv6_fn,
 	},
 };
 
-- 
cgit v1.2.3


From 3045d76070abe725dbb7fd8ff39c27b820d5a7eb Mon Sep 17 00:00:00 2001
From: Ana Rey <anarey@gmail.com>
Date: Tue, 2 Sep 2014 20:36:14 +0200
Subject: netfilter: nf_tables: add devgroup support in meta expresion

Add devgroup support to let us match device group of a packets incoming
or outgoing interface.

Signed-off-by: Ana Rey <anarey@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  4 ++++
 net/netfilter/nft_meta.c                 | 12 ++++++++++++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index c9b6f00a3fb7..c000947d3f38 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -573,6 +573,8 @@ enum nft_exthdr_attributes {
  * @NFT_META_BRI_OIFNAME: packet output bridge interface name
  * @NFT_META_PKTTYPE: packet type (skb->pkt_type), special handling for loopback
  * @NFT_META_CPU: cpu id through smp_processor_id()
+ * @NFT_META_IIFGROUP: packet input interface group
+ * @NFT_META_OIFGROUP: packet output interface group
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -596,6 +598,8 @@ enum nft_meta_keys {
 	NFT_META_BRI_OIFNAME,
 	NFT_META_PKTTYPE,
 	NFT_META_CPU,
+	NFT_META_IIFGROUP,
+	NFT_META_OIFGROUP,
 };
 
 /**
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 843e099a962d..1e7c076ca63a 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -155,6 +155,16 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 	case NFT_META_CPU:
 		dest->data[0] = smp_processor_id();
 		break;
+	case NFT_META_IIFGROUP:
+		if (in == NULL)
+			goto err;
+		dest->data[0] = in->group;
+		break;
+	case NFT_META_OIFGROUP:
+		if (out == NULL)
+			goto err;
+		dest->data[0] = out->group;
+		break;
 	default:
 		WARN_ON(1);
 		goto err;
@@ -228,6 +238,8 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 #endif
 	case NFT_META_PKTTYPE:
 	case NFT_META_CPU:
+	case NFT_META_IIFGROUP:
+	case NFT_META_OIFGROUP:
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From e42eff8a32f8b7bde88ea3c5a56391407cbe84f3 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Thu, 4 Sep 2014 14:06:14 +0200
Subject: netfilter: nft_nat: include a flag attribute

Both SNAT and DNAT (and the upcoming masquerade) can have additional
configuration parameters, such as port randomization and NAT addressing
persistence. We can cover these scenarios by simply adding a flag
attribute for userspace to fill when needed.

The flags to use are defined in include/uapi/linux/netfilter/nf_nat.h:

 NF_NAT_RANGE_MAP_IPS
 NF_NAT_RANGE_PROTO_SPECIFIED
 NF_NAT_RANGE_PROTO_RANDOM
 NF_NAT_RANGE_PERSISTENT
 NF_NAT_RANGE_PROTO_RANDOM_FULLY
 NF_NAT_RANGE_PROTO_RANDOM_ALL

The caller must take care of not messing up with the flags, as they are
added unconditionally to the final resulting nf_nat_range.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_nat.h    |  5 +++++
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nft_nat.c                  | 16 ++++++++++++++++
 3 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_nat.h b/include/uapi/linux/netfilter/nf_nat.h
index 1ad3659102b6..0880781ad7b6 100644
--- a/include/uapi/linux/netfilter/nf_nat.h
+++ b/include/uapi/linux/netfilter/nf_nat.h
@@ -13,6 +13,11 @@
 #define NF_NAT_RANGE_PROTO_RANDOM_ALL		\
 	(NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PROTO_RANDOM_FULLY)
 
+#define NF_NAT_RANGE_MASK					\
+	(NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED |	\
+	 NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PERSISTENT |	\
+	 NF_NAT_RANGE_PROTO_RANDOM_FULLY)
+
 struct nf_nat_ipv4_range {
 	unsigned int			flags;
 	__be32				min_ip;
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index c000947d3f38..6022c6e6be18 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -785,6 +785,7 @@ enum nft_nat_types {
  * @NFTA_NAT_REG_ADDR_MAX: source register of address range end (NLA_U32: nft_registers)
  * @NFTA_NAT_REG_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
  * @NFTA_NAT_REG_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
+ * @NFTA_NAT_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32)
  */
 enum nft_nat_attributes {
 	NFTA_NAT_UNSPEC,
@@ -794,6 +795,7 @@ enum nft_nat_attributes {
 	NFTA_NAT_REG_ADDR_MAX,
 	NFTA_NAT_REG_PROTO_MIN,
 	NFTA_NAT_REG_PROTO_MAX,
+	NFTA_NAT_FLAGS,
 	__NFTA_NAT_MAX
 };
 #define NFTA_NAT_MAX		(__NFTA_NAT_MAX - 1)
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 79ff58cd36dc..799550b476fb 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -33,6 +33,7 @@ struct nft_nat {
 	enum nft_registers      sreg_proto_max:8;
 	enum nf_nat_manip_type  type:8;
 	u8			family;
+	u16			flags;
 };
 
 static void nft_nat_eval(const struct nft_expr *expr,
@@ -71,6 +72,8 @@ static void nft_nat_eval(const struct nft_expr *expr,
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
+	range.flags |= priv->flags;
+
 	data[NFT_REG_VERDICT].verdict =
 		nf_nat_setup_info(ct, &range, priv->type);
 }
@@ -82,6 +85,7 @@ static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
 	[NFTA_NAT_REG_ADDR_MAX]	 = { .type = NLA_U32 },
 	[NFTA_NAT_REG_PROTO_MIN] = { .type = NLA_U32 },
 	[NFTA_NAT_REG_PROTO_MAX] = { .type = NLA_U32 },
+	[NFTA_NAT_FLAGS]	 = { .type = NLA_U32 },
 };
 
 static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
@@ -149,6 +153,12 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	} else
 		priv->sreg_proto_max = priv->sreg_proto_min;
 
+	if (tb[NFTA_NAT_FLAGS]) {
+		priv->flags = ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS]));
+		if (priv->flags & ~NF_NAT_RANGE_MASK)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -183,6 +193,12 @@ static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
 				 htonl(priv->sreg_proto_max)))
 			goto nla_put_failure;
 	}
+
+	if (priv->flags != 0) {
+		if (nla_put_be32(skb, NFTA_NAT_FLAGS, htonl(priv->flags)))
+			goto nla_put_failure;
+	}
+
 	return 0;
 
 nla_put_failure:
-- 
cgit v1.2.3


From 8dd33cc93ec92b8460ed2ad98c6db39276f6a72b Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Thu, 4 Sep 2014 14:06:33 +0200
Subject: netfilter: nf_nat: generalize IPv4 masquerading support for nf_tables

Let's refactor the code so we can reach the masquerade functionality
from outside the xt context (ie. nftables).

The patch includes the addition of an atomic counter to the masquerade
notifier: the stuff to be done by the notifier is the same for xt and
nftables. Therefore, only one notification handler is needed.

This factorization only involves IPv4; a similar patch follows to
handle IPv6.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv4/nf_nat_masquerade.h |  14 +++
 net/ipv4/netfilter/Kconfig                     |   7 ++
 net/ipv4/netfilter/Makefile                    |   1 +
 net/ipv4/netfilter/ipt_MASQUERADE.c            | 108 ++---------------
 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c    | 153 +++++++++++++++++++++++++
 5 files changed, 184 insertions(+), 99 deletions(-)
 create mode 100644 include/net/netfilter/ipv4/nf_nat_masquerade.h
 create mode 100644 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c

(limited to 'include')

diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h
new file mode 100644
index 000000000000..a9c001c646da
--- /dev/null
+++ b/include/net/netfilter/ipv4/nf_nat_masquerade.h
@@ -0,0 +1,14 @@
+#ifndef _NF_NAT_MASQUERADE_IPV4_H_
+#define _NF_NAT_MASQUERADE_IPV4_H_
+
+#include <net/netfilter/nf_nat.h>
+
+unsigned int
+nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
+		       const struct nf_nat_range *range,
+		       const struct net_device *out);
+
+void nf_nat_masquerade_ipv4_register_notifier(void);
+void nf_nat_masquerade_ipv4_unregister_notifier(void);
+
+#endif /*_NF_NAT_MASQUERADE_IPV4_H_ */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index fb173126f03d..4be3e541350e 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -184,8 +184,15 @@ config NF_NAT_IPV4
 
 if NF_NAT_IPV4
 
+config NF_NAT_MASQUERADE_IPV4
+	tristate "IPv4 masquerade support"
+	help
+	This is the kernel functionality to provide NAT in the masquerade
+	flavour (automatic source address selection).
+
 config IP_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
+	select NF_NAT_MASQUERADE_IPV4
 	default m if NETFILTER_ADVANCED=n
 	help
 	  Masquerading is a special case of NAT: all outgoing connections are
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 33001621465b..42056b2fd0e3 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o
 obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
 obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
+obj-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
 
 # NAT protocols (nf_nat)
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index 00352ce0f0de..da7f02a0b868 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -22,6 +22,7 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
 #include <net/netfilter/nf_nat.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -46,103 +47,17 @@ static int masquerade_tg_check(const struct xt_tgchk_param *par)
 static unsigned int
 masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	struct nf_conn *ct;
-	struct nf_conn_nat *nat;
-	enum ip_conntrack_info ctinfo;
-	struct nf_nat_range newrange;
+	struct nf_nat_range range;
 	const struct nf_nat_ipv4_multi_range_compat *mr;
-	const struct rtable *rt;
-	__be32 newsrc, nh;
-
-	NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING);
-
-	ct = nf_ct_get(skb, &ctinfo);
-	nat = nfct_nat(ct);
-
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED_REPLY));
-
-	/* Source address is 0.0.0.0 - locally generated packet that is
-	 * probably not supposed to be masqueraded.
-	 */
-	if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0)
-		return NF_ACCEPT;
 
 	mr = par->targinfo;
-	rt = skb_rtable(skb);
-	nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
-	newsrc = inet_select_addr(par->out, nh, RT_SCOPE_UNIVERSE);
-	if (!newsrc) {
-		pr_info("%s ate my IP address\n", par->out->name);
-		return NF_DROP;
-	}
-
-	nat->masq_index = par->out->ifindex;
-
-	/* Transfer from original range. */
-	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
-	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
-	newrange.flags       = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.ip = newsrc;
-	newrange.max_addr.ip = newsrc;
-	newrange.min_proto   = mr->range[0].min;
-	newrange.max_proto   = mr->range[0].max;
+	range.flags = mr->range[0].flags;
+	range.min_proto = mr->range[0].min;
+	range.max_proto = mr->range[0].max;
 
-	/* Hand modified range to generic setup. */
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+	return nf_nat_masquerade_ipv4(skb, par->hooknum, &range, par->out);
 }
 
-static int
-device_cmp(struct nf_conn *i, void *ifindex)
-{
-	const struct nf_conn_nat *nat = nfct_nat(i);
-
-	if (!nat)
-		return 0;
-	if (nf_ct_l3num(i) != NFPROTO_IPV4)
-		return 0;
-	return nat->masq_index == (int)(long)ifindex;
-}
-
-static int masq_device_event(struct notifier_block *this,
-			     unsigned long event,
-			     void *ptr)
-{
-	const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct net *net = dev_net(dev);
-
-	if (event == NETDEV_DOWN) {
-		/* Device was downed.  Search entire table for
-		   conntracks which were associated with that device,
-		   and forget them. */
-		NF_CT_ASSERT(dev->ifindex != 0);
-
-		nf_ct_iterate_cleanup(net, device_cmp,
-				      (void *)(long)dev->ifindex, 0, 0);
-	}
-
-	return NOTIFY_DONE;
-}
-
-static int masq_inet_event(struct notifier_block *this,
-			   unsigned long event,
-			   void *ptr)
-{
-	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
-	struct netdev_notifier_info info;
-
-	netdev_notifier_info_init(&info, dev);
-	return masq_device_event(this, event, &info);
-}
-
-static struct notifier_block masq_dev_notifier = {
-	.notifier_call	= masq_device_event,
-};
-
-static struct notifier_block masq_inet_notifier = {
-	.notifier_call	= masq_inet_event,
-};
-
 static struct xt_target masquerade_tg_reg __read_mostly = {
 	.name		= "MASQUERADE",
 	.family		= NFPROTO_IPV4,
@@ -160,12 +75,8 @@ static int __init masquerade_tg_init(void)
 
 	ret = xt_register_target(&masquerade_tg_reg);
 
-	if (ret == 0) {
-		/* Register for device down reports */
-		register_netdevice_notifier(&masq_dev_notifier);
-		/* Register IP address change reports */
-		register_inetaddr_notifier(&masq_inet_notifier);
-	}
+	if (ret == 0)
+		nf_nat_masquerade_ipv4_register_notifier();
 
 	return ret;
 }
@@ -173,8 +84,7 @@ static int __init masquerade_tg_init(void)
 static void __exit masquerade_tg_exit(void)
 {
 	xt_unregister_target(&masquerade_tg_reg);
-	unregister_netdevice_notifier(&masq_dev_notifier);
-	unregister_inetaddr_notifier(&masq_inet_notifier);
+	nf_nat_masquerade_ipv4_unregister_notifier();
 }
 
 module_init(masquerade_tg_init);
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
new file mode 100644
index 000000000000..c6eb42100e9a
--- /dev/null
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -0,0 +1,153 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/atomic.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/timer.h>
+#include <linux/netfilter.h>
+#include <net/protocol.h>
+#include <net/ip.h>
+#include <net/checksum.h>
+#include <net/route.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+
+unsigned int
+nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
+		       const struct nf_nat_range *range,
+		       const struct net_device *out)
+{
+	struct nf_conn *ct;
+	struct nf_conn_nat *nat;
+	enum ip_conntrack_info ctinfo;
+	struct nf_nat_range newrange;
+	const struct rtable *rt;
+	__be32 newsrc, nh;
+
+	NF_CT_ASSERT(hooknum == NF_INET_POST_ROUTING);
+
+	ct = nf_ct_get(skb, &ctinfo);
+	nat = nfct_nat(ct);
+
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
+			    ctinfo == IP_CT_RELATED_REPLY));
+
+	/* Source address is 0.0.0.0 - locally generated packet that is
+	 * probably not supposed to be masqueraded.
+	 */
+	if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0)
+		return NF_ACCEPT;
+
+	rt = skb_rtable(skb);
+	nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
+	newsrc = inet_select_addr(out, nh, RT_SCOPE_UNIVERSE);
+	if (!newsrc) {
+		pr_info("%s ate my IP address\n", out->name);
+		return NF_DROP;
+	}
+
+	nat->masq_index = out->ifindex;
+
+	/* Transfer from original range. */
+	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
+	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
+	newrange.flags       = range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.ip = newsrc;
+	newrange.max_addr.ip = newsrc;
+	newrange.min_proto   = range->min_proto;
+	newrange.max_proto   = range->max_proto;
+
+	/* Hand modified range to generic setup. */
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4);
+
+static int device_cmp(struct nf_conn *i, void *ifindex)
+{
+	const struct nf_conn_nat *nat = nfct_nat(i);
+
+	if (!nat)
+		return 0;
+	if (nf_ct_l3num(i) != NFPROTO_IPV4)
+		return 0;
+	return nat->masq_index == (int)(long)ifindex;
+}
+
+static int masq_device_event(struct notifier_block *this,
+			     unsigned long event,
+			     void *ptr)
+{
+	const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(dev);
+
+	if (event == NETDEV_DOWN) {
+		/* Device was downed.  Search entire table for
+		 * conntracks which were associated with that device,
+		 * and forget them.
+		 */
+		NF_CT_ASSERT(dev->ifindex != 0);
+
+		nf_ct_iterate_cleanup(net, device_cmp,
+				      (void *)(long)dev->ifindex, 0, 0);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int masq_inet_event(struct notifier_block *this,
+			   unsigned long event,
+			   void *ptr)
+{
+	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+	struct netdev_notifier_info info;
+
+	netdev_notifier_info_init(&info, dev);
+	return masq_device_event(this, event, &info);
+}
+
+static struct notifier_block masq_dev_notifier = {
+	.notifier_call	= masq_device_event,
+};
+
+static struct notifier_block masq_inet_notifier = {
+	.notifier_call	= masq_inet_event,
+};
+
+static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+
+void nf_nat_masquerade_ipv4_register_notifier(void)
+{
+	/* check if the notifier was already set */
+	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
+		return;
+
+	/* Register for device down reports */
+	register_netdevice_notifier(&masq_dev_notifier);
+	/* Register IP address change reports */
+	register_inetaddr_notifier(&masq_inet_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
+
+void nf_nat_masquerade_ipv4_unregister_notifier(void)
+{
+	/* check if the notifier still has clients */
+	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
+		return;
+
+	unregister_netdevice_notifier(&masq_dev_notifier);
+	unregister_inetaddr_notifier(&masq_inet_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>");
-- 
cgit v1.2.3


From be6b635cd674add9410efa9ac6f03e0040848b12 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Thu, 4 Sep 2014 14:06:49 +0200
Subject: netfilter: nf_nat: generalize IPv6 masquerading support for nf_tables

Let's refactor the code so we can reach the masquerade functionality
from outside the xt context (ie. nftables).

The patch includes the addition of an atomic counter to the masquerade
notifier: the stuff to be done by the notifier is the same for xt and
nftables. Therefore, only one notification handler is needed.

This factorization only involves IPv6; a similar patch exists to
handle IPv4.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv6/nf_nat_masquerade.h |  10 +++
 net/ipv6/netfilter/Kconfig                     |   7 ++
 net/ipv6/netfilter/Makefile                    |   1 +
 net/ipv6/netfilter/ip6t_MASQUERADE.c           |  76 ++--------------
 net/ipv6/netfilter/nf_nat_masquerade_ipv6.c    | 120 +++++++++++++++++++++++++
 5 files changed, 143 insertions(+), 71 deletions(-)
 create mode 100644 include/net/netfilter/ipv6/nf_nat_masquerade.h
 create mode 100644 net/ipv6/netfilter/nf_nat_masquerade_ipv6.c

(limited to 'include')

diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h
new file mode 100644
index 000000000000..0a13396cd390
--- /dev/null
+++ b/include/net/netfilter/ipv6/nf_nat_masquerade.h
@@ -0,0 +1,10 @@
+#ifndef _NF_NAT_MASQUERADE_IPV6_H_
+#define _NF_NAT_MASQUERADE_IPV6_H_
+
+unsigned int
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		       const struct net_device *out);
+void nf_nat_masquerade_ipv6_register_notifier(void);
+void nf_nat_masquerade_ipv6_unregister_notifier(void);
+
+#endif /* _NF_NAT_MASQUERADE_IPV6_H_ */
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ac93df16f5af..6c8cfec6836a 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -246,8 +246,15 @@ config NF_NAT_IPV6
 
 if NF_NAT_IPV6
 
+config NF_NAT_MASQUERADE_IPV6
+	tristate "IPv6 masquerade support"
+	help
+	 This is the kernel functionality to provide NAT in the masquerade
+	 flavour (automatic source address selection) for IPv6.
+
 config IP6_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
+	select NF_NAT_MASQUERADE_IPV6
 	help
 	  Masquerading is a special case of NAT: all outgoing connections are
 	  changed to seem to come from a particular interface's address, and
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index c0b263104ed2..89a0bd751f82 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o
 
 nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
 obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
+obj-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o
 
 # defrag
 nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 3e4e92d5e157..7f9f45d829d2 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -19,33 +19,12 @@
 #include <net/netfilter/nf_nat.h>
 #include <net/addrconf.h>
 #include <net/ipv6.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
 
 static unsigned int
 masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	const struct nf_nat_range *range = par->targinfo;
-	enum ip_conntrack_info ctinfo;
-	struct in6_addr src;
-	struct nf_conn *ct;
-	struct nf_nat_range newrange;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED_REPLY));
-
-	if (ipv6_dev_get_saddr(dev_net(par->out), par->out,
-			       &ipv6_hdr(skb)->daddr, 0, &src) < 0)
-		return NF_DROP;
-
-	nfct_nat(ct)->masq_index = par->out->ifindex;
-
-	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.in6	= src;
-	newrange.max_addr.in6	= src;
-	newrange.min_proto	= range->min_proto;
-	newrange.max_proto	= range->max_proto;
-
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+	return nf_nat_masquerade_ipv6(skb, par->targinfo, par->out);
 }
 
 static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
@@ -57,48 +36,6 @@ static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
 	return 0;
 }
 
-static int device_cmp(struct nf_conn *ct, void *ifindex)
-{
-	const struct nf_conn_nat *nat = nfct_nat(ct);
-
-	if (!nat)
-		return 0;
-	if (nf_ct_l3num(ct) != NFPROTO_IPV6)
-		return 0;
-	return nat->masq_index == (int)(long)ifindex;
-}
-
-static int masq_device_event(struct notifier_block *this,
-			     unsigned long event, void *ptr)
-{
-	const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct net *net = dev_net(dev);
-
-	if (event == NETDEV_DOWN)
-		nf_ct_iterate_cleanup(net, device_cmp,
-				      (void *)(long)dev->ifindex, 0, 0);
-
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block masq_dev_notifier = {
-	.notifier_call	= masq_device_event,
-};
-
-static int masq_inet_event(struct notifier_block *this,
-			   unsigned long event, void *ptr)
-{
-	struct inet6_ifaddr *ifa = ptr;
-	struct netdev_notifier_info info;
-
-	netdev_notifier_info_init(&info, ifa->idev->dev);
-	return masq_device_event(this, event, &info);
-}
-
-static struct notifier_block masq_inet_notifier = {
-	.notifier_call	= masq_inet_event,
-};
-
 static struct xt_target masquerade_tg6_reg __read_mostly = {
 	.name		= "MASQUERADE",
 	.family		= NFPROTO_IPV6,
@@ -115,17 +52,14 @@ static int __init masquerade_tg6_init(void)
 	int err;
 
 	err = xt_register_target(&masquerade_tg6_reg);
-	if (err == 0) {
-		register_netdevice_notifier(&masq_dev_notifier);
-		register_inet6addr_notifier(&masq_inet_notifier);
-	}
+	if (err == 0)
+		nf_nat_masquerade_ipv6_register_notifier();
 
 	return err;
 }
 static void __exit masquerade_tg6_exit(void)
 {
-	unregister_inet6addr_notifier(&masq_inet_notifier);
-	unregister_netdevice_notifier(&masq_dev_notifier);
+	nf_nat_masquerade_ipv6_unregister_notifier();
 	xt_unregister_target(&masquerade_tg6_reg);
 }
 
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
new file mode 100644
index 000000000000..7745609665cd
--- /dev/null
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -0,0 +1,120 @@
+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/atomic.h>
+#include <linux/netdevice.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+
+unsigned int
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
+		       const struct net_device *out)
+{
+	enum ip_conntrack_info ctinfo;
+	struct in6_addr src;
+	struct nf_conn *ct;
+	struct nf_nat_range newrange;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
+			    ctinfo == IP_CT_RELATED_REPLY));
+
+	if (ipv6_dev_get_saddr(dev_net(out), out,
+			       &ipv6_hdr(skb)->daddr, 0, &src) < 0)
+		return NF_DROP;
+
+	nfct_nat(ct)->masq_index = out->ifindex;
+
+	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.in6	= src;
+	newrange.max_addr.in6	= src;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6);
+
+static int device_cmp(struct nf_conn *ct, void *ifindex)
+{
+	const struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (!nat)
+		return 0;
+	if (nf_ct_l3num(ct) != NFPROTO_IPV6)
+		return 0;
+	return nat->masq_index == (int)(long)ifindex;
+}
+
+static int masq_device_event(struct notifier_block *this,
+			     unsigned long event, void *ptr)
+{
+	const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(dev);
+
+	if (event == NETDEV_DOWN)
+		nf_ct_iterate_cleanup(net, device_cmp,
+				      (void *)(long)dev->ifindex, 0, 0);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block masq_dev_notifier = {
+	.notifier_call	= masq_device_event,
+};
+
+static int masq_inet_event(struct notifier_block *this,
+			   unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = ptr;
+	struct netdev_notifier_info info;
+
+	netdev_notifier_info_init(&info, ifa->idev->dev);
+	return masq_device_event(this, event, &info);
+}
+
+static struct notifier_block masq_inet_notifier = {
+	.notifier_call	= masq_inet_event,
+};
+
+static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+
+void nf_nat_masquerade_ipv6_register_notifier(void)
+{
+	/* check if the notifier is already set */
+	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
+		return;
+
+	register_netdevice_notifier(&masq_dev_notifier);
+	register_inet6addr_notifier(&masq_inet_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
+
+void nf_nat_masquerade_ipv6_unregister_notifier(void)
+{
+	/* check if the notifier still has clients */
+	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
+		return;
+
+	unregister_inet6addr_notifier(&masq_inet_notifier);
+	unregister_netdevice_notifier(&masq_dev_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-- 
cgit v1.2.3


From 9ba1f726bec090399eb9bb9157eb32dedc8e8c45 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Mon, 8 Sep 2014 13:45:00 +0200
Subject: netfilter: nf_tables: add new nft_masq expression

The nft_masq expression is intended to perform NAT in the masquerade flavour.

We decided to have the masquerade functionality in a separated expression other
than nft_nat.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nft_masq.h         | 16 ++++++
 include/uapi/linux/netfilter/nf_tables.h | 11 ++++
 net/ipv4/netfilter/Kconfig               |  6 +++
 net/ipv4/netfilter/Makefile              |  1 +
 net/ipv4/netfilter/nft_masq_ipv4.c       | 89 ++++++++++++++++++++++++++++++++
 net/ipv6/netfilter/Kconfig               |  6 +++
 net/ipv6/netfilter/Makefile              |  1 +
 net/ipv6/netfilter/nft_masq_ipv6.c       | 89 ++++++++++++++++++++++++++++++++
 net/netfilter/Kconfig                    |  9 ++++
 net/netfilter/Makefile                   |  1 +
 net/netfilter/nft_masq.c                 | 59 +++++++++++++++++++++
 11 files changed, 288 insertions(+)
 create mode 100644 include/net/netfilter/nft_masq.h
 create mode 100644 net/ipv4/netfilter/nft_masq_ipv4.c
 create mode 100644 net/ipv6/netfilter/nft_masq_ipv6.c
 create mode 100644 net/netfilter/nft_masq.c

(limited to 'include')

diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h
new file mode 100644
index 000000000000..c72729f954f4
--- /dev/null
+++ b/include/net/netfilter/nft_masq.h
@@ -0,0 +1,16 @@
+#ifndef _NFT_MASQ_H_
+#define _NFT_MASQ_H_
+
+struct nft_masq {
+	u32	flags;
+};
+
+extern const struct nla_policy nft_masq_policy[];
+
+int nft_masq_init(const struct nft_ctx *ctx,
+		  const struct nft_expr *expr,
+		  const struct nlattr * const tb[]);
+
+int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr);
+
+#endif /* _NFT_MASQ_H_ */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 6022c6e6be18..eeec0ae845ef 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -800,4 +800,15 @@ enum nft_nat_attributes {
 };
 #define NFTA_NAT_MAX		(__NFTA_NAT_MAX - 1)
 
+/**
+ * enum nft_masq_attributes - nf_tables masquerade expression attributes
+ *
+ * @NFTA_MASQ_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32)
+ */
+enum nft_masq_attributes {
+	NFTA_MASQ_FLAGS,
+	__NFTA_MASQ_MAX
+};
+#define NFTA_MASQ_MAX		(__NFTA_MASQ_MAX - 1)
+
 #endif /* _LINUX_NF_TABLES_H */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 4be3e541350e..8dd3d9f19d82 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -190,6 +190,12 @@ config NF_NAT_MASQUERADE_IPV4
 	This is the kernel functionality to provide NAT in the masquerade
 	flavour (automatic source address selection).
 
+config NFT_MASQ_IPV4
+	tristate "IPv4 masquerading support for nf_tables"
+	depends on NF_TABLES_IPV4
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV4
+
 config IP_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
 	select NF_NAT_MASQUERADE_IPV4
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 42056b2fd0e3..7d019aefb0ed 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
+obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
new file mode 100644
index 000000000000..6ea1d207b6a5
--- /dev/null
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_masq.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+
+static void nft_masq_ipv4_eval(const struct nft_expr *expr,
+			       struct nft_data data[NFT_REG_MAX + 1],
+			       const struct nft_pktinfo *pkt)
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+	struct nf_nat_range range;
+	unsigned int verdict;
+
+	range.flags = priv->flags;
+
+	verdict = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum,
+					 &range, pkt->out);
+
+	data[NFT_REG_VERDICT].verdict = verdict;
+}
+
+static int nft_masq_ipv4_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr * const tb[])
+{
+	int err;
+
+	err = nft_masq_init(ctx, expr, tb);
+	if (err < 0)
+		return err;
+
+	nf_nat_masquerade_ipv4_register_notifier();
+	return 0;
+}
+
+static void nft_masq_ipv4_destroy(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr)
+{
+	nf_nat_masquerade_ipv4_unregister_notifier();
+}
+
+static struct nft_expr_type nft_masq_ipv4_type;
+static const struct nft_expr_ops nft_masq_ipv4_ops = {
+	.type		= &nft_masq_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+	.eval		= nft_masq_ipv4_eval,
+	.init		= nft_masq_ipv4_init,
+	.destroy	= nft_masq_ipv4_destroy,
+	.dump		= nft_masq_dump,
+};
+
+static struct nft_expr_type nft_masq_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "masq",
+	.ops		= &nft_masq_ipv4_ops,
+	.policy		= nft_masq_policy,
+	.maxattr	= NFTA_MASQ_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_masq_ipv4_module_init(void)
+{
+	return nft_register_expr(&nft_masq_ipv4_type);
+}
+
+static void __exit nft_masq_ipv4_module_exit(void)
+{
+	nft_unregister_expr(&nft_masq_ipv4_type);
+}
+
+module_init(nft_masq_ipv4_module_init);
+module_exit(nft_masq_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "masq");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 6c8cfec6836a..24c535f66df0 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -252,6 +252,12 @@ config NF_NAT_MASQUERADE_IPV6
 	 This is the kernel functionality to provide NAT in the masquerade
 	 flavour (automatic source address selection) for IPv6.
 
+config NFT_MASQ_IPV6
+	tristate "IPv6 masquerade support for nf_tables"
+	depends on NF_TABLES_IPV6
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV6
+
 config IP6_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
 	select NF_NAT_MASQUERADE_IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 89a0bd751f82..482c4dff273f 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
 obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
+obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
new file mode 100644
index 000000000000..4e51334ef6b7
--- /dev/null
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nft_masq.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+
+static void nft_masq_ipv6_eval(const struct nft_expr *expr,
+			       struct nft_data data[NFT_REG_MAX + 1],
+			       const struct nft_pktinfo *pkt)
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+	struct nf_nat_range range;
+	unsigned int verdict;
+
+	range.flags = priv->flags;
+
+	verdict = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out);
+
+	data[NFT_REG_VERDICT].verdict = verdict;
+}
+
+static int nft_masq_ipv6_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr * const tb[])
+{
+	int err;
+
+	err = nft_masq_init(ctx, expr, tb);
+	if (err < 0)
+		return err;
+
+	nf_nat_masquerade_ipv6_register_notifier();
+	return 0;
+}
+
+static void nft_masq_ipv6_destroy(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr)
+{
+	nf_nat_masquerade_ipv6_unregister_notifier();
+}
+
+static struct nft_expr_type nft_masq_ipv6_type;
+static const struct nft_expr_ops nft_masq_ipv6_ops = {
+	.type		= &nft_masq_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+	.eval		= nft_masq_ipv6_eval,
+	.init		= nft_masq_ipv6_init,
+	.destroy	= nft_masq_ipv6_destroy,
+	.dump		= nft_masq_dump,
+};
+
+static struct nft_expr_type nft_masq_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "masq",
+	.ops		= &nft_masq_ipv6_ops,
+	.policy		= nft_masq_policy,
+	.maxattr	= NFTA_MASQ_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_masq_ipv6_module_init(void)
+{
+	return nft_register_expr(&nft_masq_ipv6_type);
+}
+
+static void __exit nft_masq_ipv6_module_exit(void)
+{
+	nft_unregister_expr(&nft_masq_ipv6_type);
+}
+
+module_init(nft_masq_ipv6_module_init);
+module_exit(nft_masq_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "masq");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index ad751fe2e82b..37428723394f 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -496,6 +496,15 @@ config NFT_LIMIT
 	  This option adds the "limit" expression that you can use to
 	  ratelimit rule matchings.
 
+config NFT_MASQ
+	depends on NF_TABLES
+	depends on NF_CONNTRACK
+	depends on NF_NAT
+	tristate "Netfilter nf_tables masquerade support"
+	help
+	  This option adds the "masquerade" expression that you can use
+	  to perform NAT in the masquerade flavour.
+
 config NFT_NAT
 	depends on NF_TABLES
 	depends on NF_CONNTRACK
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 8308624a406a..0637792f6faf 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -87,6 +87,7 @@ obj-$(CONFIG_NFT_RBTREE)	+= nft_rbtree.o
 obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
+obj-$(CONFIG_NFT_MASQ)		+= nft_masq.o
 
 # generic X tables 
 obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
new file mode 100644
index 000000000000..6637bab00567
--- /dev/null
+++ b/net/netfilter/nft_masq.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nft_masq.h>
+
+const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = {
+	[NFTA_MASQ_FLAGS]	= { .type = NLA_U32 },
+};
+EXPORT_SYMBOL_GPL(nft_masq_policy);
+
+int nft_masq_init(const struct nft_ctx *ctx,
+		  const struct nft_expr *expr,
+		  const struct nlattr * const tb[])
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_MASQ_FLAGS] == NULL)
+		return 0;
+
+	priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS]));
+	if (priv->flags & ~NF_NAT_RANGE_MASK)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_masq_init);
+
+int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_masq *priv = nft_expr_priv(expr);
+
+	if (priv->flags == 0)
+		return 0;
+
+	if (nla_put_be32(skb, NFTA_MASQ_FLAGS, htonl(priv->flags)))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nft_masq_dump);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
-- 
cgit v1.2.3


From ef979a26e3d521d51dbd9950e46a69e303073171 Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@freescale.com>
Date: Tue, 9 Sep 2014 08:56:48 +0800
Subject: usb: gadget: add reset API at usb_gadget_driver

Adding reset API for UDC bus reset handler is useful for below
two issues.

Current disconnect API at usb_gadget_driver is also invoked at
udc's bus reset handler, but the document says it is invoked when
the host is disconnected.

Besides, we may expect the gadget_driver to do different things
for host sends bus reset and host disconnects gadget, eg, we may not
want to flush dirty page for mass storage at bus reset, and want to
do it at disconnection.

Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/linux/usb/gadget.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index c540557b564b..598a6e9b2850 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -817,6 +817,8 @@ static inline int usb_gadget_disconnect(struct usb_gadget *gadget)
  *	Called in a context that permits sleeping.
  * @suspend: Invoked on USB suspend.  May be called in_interrupt.
  * @resume: Invoked on USB resume.  May be called in_interrupt.
+ * @reset: Invoked on USB bus reset. It is mandatory for all gadget drivers
+ *	and should be called in_interrupt.
  * @driver: Driver model state for this driver.
  *
  * Devices are disabled till a gadget driver successfully bind()s, which
@@ -874,6 +876,7 @@ struct usb_gadget_driver {
 	void			(*disconnect)(struct usb_gadget *);
 	void			(*suspend)(struct usb_gadget *);
 	void			(*resume)(struct usb_gadget *);
+	void			(*reset)(struct usb_gadget *);
 
 	/* FIXME support safe rmmod */
 	struct device_driver	driver;
-- 
cgit v1.2.3


From c559a353410939c0884e83bdb0e2420a986ac53b Mon Sep 17 00:00:00 2001
From: Robert Baldyga <r.baldyga@samsung.com>
Date: Tue, 9 Sep 2014 08:23:16 +0200
Subject: usb: gadget: f_fs: add ioctl returning ep descriptor

This patch introduces ioctl named FUNCTIONFS_ENDPOINT_DESC, which
returns endpoint descriptor to userspace. It works only if function
is active.

Signed-off-by: Robert Baldyga <r.baldyga@samsung.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/gadget/function/f_fs.c  | 23 +++++++++++++++++++++++
 include/uapi/linux/usb/functionfs.h |  6 ++++++
 2 files changed, 29 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 1aad353c1f11..a345385a5abe 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1026,6 +1026,29 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code,
 		case FUNCTIONFS_ENDPOINT_REVMAP:
 			ret = epfile->ep->num;
 			break;
+		case FUNCTIONFS_ENDPOINT_DESC:
+		{
+			int desc_idx;
+			struct usb_endpoint_descriptor *desc;
+
+			switch (epfile->ffs->gadget->speed) {
+			case USB_SPEED_SUPER:
+				desc_idx = 2;
+				break;
+			case USB_SPEED_HIGH:
+				desc_idx = 1;
+				break;
+			default:
+				desc_idx = 0;
+			}
+			desc = epfile->ep->descs[desc_idx];
+
+			spin_unlock_irq(&epfile->ffs->eps_lock);
+			ret = copy_to_user((void *)value, desc, sizeof(*desc));
+			if (ret)
+				ret = -EFAULT;
+			return ret;
+		}
 		default:
 			ret = -ENOTTY;
 		}
diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index 6d2a16b834bf..7c7a2feb0e6e 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -275,6 +275,12 @@ struct usb_functionfs_event {
  */
 #define	FUNCTIONFS_ENDPOINT_REVMAP	_IO('g', 129)
 
+/*
+ * Returns endpoint descriptor. If function is not active returns -ENODEV.
+ */
+#define	FUNCTIONFS_ENDPOINT_DESC	_IOR('g', 130, \
+					     struct usb_endpoint_descriptor)
+
 
 
 #endif /* _UAPI__LINUX_FUNCTIONFS_H__ */
-- 
cgit v1.2.3


From 02ab695bb37ee9ad515df0d0790d5977505dd04a Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Thu, 4 Sep 2014 22:17:17 -0700
Subject: net: filter: add "load 64-bit immediate" eBPF instruction

add BPF_LD_IMM64 instruction to load 64-bit immediate value into a register.
All previous instructions were 8-byte. This is first 16-byte instruction.
Two consecutive 'struct bpf_insn' blocks are interpreted as single instruction:
insn[0].code = BPF_LD | BPF_DW | BPF_IMM
insn[0].dst_reg = destination register
insn[0].imm = lower 32-bit
insn[1].code = 0
insn[1].imm = upper 32-bit
All unused fields must be zero.

Classic BPF has similar instruction: BPF_LD | BPF_W | BPF_IMM
which loads 32-bit immediate value into a register.

x64 JITs it as single 'movabsq %rax, imm64'
arm64 may JIT as sequence of four 'movk x0, #imm16, lsl #shift' insn

Note that old eBPF programs are binary compatible with new interpreter.

It helps eBPF programs load 64-bit constant into a register with one
instruction instead of using two registers and 4 instructions:
BPF_MOV32_IMM(R1, imm32)
BPF_ALU64_IMM(BPF_LSH, R1, 32)
BPF_MOV32_IMM(R2, imm32)
BPF_ALU64_REG(BPF_OR, R1, R2)

User space generated programs will use this instruction to load constants only.

To tell kernel that user space needs a pointer the _pseudo_ variant of
this instruction may be added later, which will use extra bits of encoding
to indicate what type of pointer user space is asking kernel to provide.
For example 'off' or 'src_reg' fields can be used for such purpose.
src_reg = 1 could mean that user space is asking kernel to validate and
load in-kernel map pointer.
src_reg = 2 could mean that user space needs readonly data section pointer
src_reg = 3 could mean that user space needs a pointer to per-cpu local data
All such future pseudo instructions will not be carrying the actual pointer
as part of the instruction, but rather will be treated as a request to kernel
to provide one. The kernel will verify the request_for_a_pointer, then
will drop _pseudo_ marking and will store actual internal pointer inside
the instruction, so the end result is the interpreter and JITs never
see pseudo BPF_LD_IMM64 insns and only operate on generic BPF_LD_IMM64 that
loads 64-bit immediate into a register. User space never operates on direct
pointers and verifier can easily recognize request_for_pointer vs other
instructions.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/filter.txt |  8 +++++++-
 arch/x86/net/bpf_jit_comp.c         | 17 +++++++++++++++++
 include/linux/filter.h              | 18 ++++++++++++++++++
 kernel/bpf/core.c                   |  5 +++++
 lib/test_bpf.c                      | 21 +++++++++++++++++++++
 5 files changed, 68 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index c48a9704bda8..81916ab5d96f 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -951,7 +951,7 @@ Size modifier is one of ...
 
 Mode modifier is one of:
 
-  BPF_IMM  0x00  /* classic BPF only, reserved in eBPF */
+  BPF_IMM  0x00  /* used for 32-bit mov in classic BPF and 64-bit in eBPF */
   BPF_ABS  0x20
   BPF_IND  0x40
   BPF_MEM  0x60
@@ -995,6 +995,12 @@ BPF_XADD | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg
 Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. Note that 1 and
 2 byte atomic increments are not supported.
 
+eBPF has one 16-byte instruction: BPF_LD | BPF_DW | BPF_IMM which consists
+of two consecutive 'struct bpf_insn' 8-byte blocks and interpreted as single
+instruction that loads 64-bit immediate value into a dst_reg.
+Classic BPF has similar instruction: BPF_LD | BPF_W | BPF_IMM which loads
+32-bit immediate value into a register.
+
 Testing
 -------
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 39ccfbb4a723..06f8c17f5484 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -393,6 +393,23 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
 			break;
 
+		case BPF_LD | BPF_IMM | BPF_DW:
+			if (insn[1].code != 0 || insn[1].src_reg != 0 ||
+			    insn[1].dst_reg != 0 || insn[1].off != 0) {
+				/* verifier must catch invalid insns */
+				pr_err("invalid BPF_LD_IMM64 insn\n");
+				return -EINVAL;
+			}
+
+			/* movabsq %rax, imm64 */
+			EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
+			EMIT(insn[0].imm, 4);
+			EMIT(insn[1].imm, 4);
+
+			insn++;
+			i++;
+			break;
+
 			/* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */
 		case BPF_ALU | BPF_MOD | BPF_X:
 		case BPF_ALU | BPF_DIV | BPF_X:
diff --git a/include/linux/filter.h b/include/linux/filter.h
index c78994593355..bf323da77950 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -166,6 +166,24 @@ enum {
 		.off   = 0,					\
 		.imm   = IMM })
 
+/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
+#define BPF_LD_IMM64(DST, IMM)					\
+	BPF_LD_IMM64_RAW(DST, 0, IMM)
+
+#define BPF_LD_IMM64_RAW(DST, SRC, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_LD | BPF_DW | BPF_IMM,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = (__u32) (IMM) }),			\
+	((struct bpf_insn) {					\
+		.code  = 0, /* zero is reserved opcode */	\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = ((__u64) (IMM)) >> 32 })
+
 /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */
 
 #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM)			\
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index b54bb2c2e494..2c2bfaacce66 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -242,6 +242,7 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn)
 		[BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
 		[BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
 		[BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
+		[BPF_LD | BPF_IMM | BPF_DW] = &&LD_IMM_DW,
 	};
 	void *ptr;
 	int off;
@@ -301,6 +302,10 @@ select_insn:
 	ALU64_MOV_K:
 		DST = IMM;
 		CONT;
+	LD_IMM_DW:
+		DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32;
+		insn++;
+		CONT;
 	ALU64_ARSH_X:
 		(*(s64 *) &DST) >>= SRC;
 		CONT;
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 9a67456ba29a..413890815d3e 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -1735,6 +1735,27 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 1, 0 } },
 	},
+	{
+		"load 64-bit immediate",
+		.u.insns_int = {
+			BPF_LD_IMM64(R1, 0x567800001234L),
+			BPF_MOV64_REG(R2, R1),
+			BPF_MOV64_REG(R3, R2),
+			BPF_ALU64_IMM(BPF_RSH, R2, 32),
+			BPF_ALU64_IMM(BPF_LSH, R3, 32),
+			BPF_ALU64_IMM(BPF_RSH, R3, 32),
+			BPF_ALU64_IMM(BPF_MOV, R0, 0),
+			BPF_JMP_IMM(BPF_JEQ, R2, 0x5678, 1),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JEQ, R3, 0x1234, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
 };
 
 static struct net_device dev;
-- 
cgit v1.2.3


From daedfb22451dd02b35c0549566cbb7cc06bdd53b Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Thu, 4 Sep 2014 22:17:18 -0700
Subject: net: filter: split filter.h and expose eBPF to user space

allow user space to generate eBPF programs

uapi/linux/bpf.h: eBPF instruction set definition

linux/filter.h: the rest

This patch only moves macro definitions, but practically it freezes existing
eBPF instruction set, though new instructions can still be added in the future.

These eBPF definitions cannot go into uapi/linux/filter.h, since the names
may conflict with existing applications.

Full eBPF ISA description is in Documentation/networking/filter.txt

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h    | 56 +---------------------------------------
 include/uapi/linux/Kbuild |  1 +
 include/uapi/linux/bpf.h  | 65 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 67 insertions(+), 55 deletions(-)
 create mode 100644 include/uapi/linux/bpf.h

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index bf323da77950..8f82ef3f1cdd 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -10,58 +10,12 @@
 #include <linux/workqueue.h>
 #include <uapi/linux/filter.h>
 #include <asm/cacheflush.h>
+#include <uapi/linux/bpf.h>
 
 struct sk_buff;
 struct sock;
 struct seccomp_data;
 
-/* Internally used and optimized filter representation with extended
- * instruction set based on top of classic BPF.
- */
-
-/* instruction classes */
-#define BPF_ALU64	0x07	/* alu mode in double word width */
-
-/* ld/ldx fields */
-#define BPF_DW		0x18	/* double word */
-#define BPF_XADD	0xc0	/* exclusive add */
-
-/* alu/jmp fields */
-#define BPF_MOV		0xb0	/* mov reg to reg */
-#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */
-
-/* change endianness of a register */
-#define BPF_END		0xd0	/* flags for endianness conversion: */
-#define BPF_TO_LE	0x00	/* convert to little-endian */
-#define BPF_TO_BE	0x08	/* convert to big-endian */
-#define BPF_FROM_LE	BPF_TO_LE
-#define BPF_FROM_BE	BPF_TO_BE
-
-#define BPF_JNE		0x50	/* jump != */
-#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
-#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
-#define BPF_CALL	0x80	/* function call */
-#define BPF_EXIT	0x90	/* function return */
-
-/* Register numbers */
-enum {
-	BPF_REG_0 = 0,
-	BPF_REG_1,
-	BPF_REG_2,
-	BPF_REG_3,
-	BPF_REG_4,
-	BPF_REG_5,
-	BPF_REG_6,
-	BPF_REG_7,
-	BPF_REG_8,
-	BPF_REG_9,
-	BPF_REG_10,
-	__MAX_BPF_REG,
-};
-
-/* BPF has 10 general purpose 64-bit registers and stack frame. */
-#define MAX_BPF_REG	__MAX_BPF_REG
-
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
  * calls in BPF_CALL instruction.
@@ -322,14 +276,6 @@ enum {
 #define SK_RUN_FILTER(filter, ctx) \
 	(*filter->prog->bpf_func)(ctx, filter->prog->insnsi)
 
-struct bpf_insn {
-	__u8	code;		/* opcode */
-	__u8	dst_reg:4;	/* dest register */
-	__u8	src_reg:4;	/* source register */
-	__s16	off;		/* signed offset */
-	__s32	imm;		/* signed immediate constant */
-};
-
 #ifdef CONFIG_COMPAT
 /* A struct sock_filter is architecture independent. */
 struct compat_sock_fprog {
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 24e9033f8b3f..fb3f7b675229 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -67,6 +67,7 @@ header-y += bfs_fs.h
 header-y += binfmts.h
 header-y += blkpg.h
 header-y += blktrace_api.h
+header-y += bpf.h
 header-y += bpqether.h
 header-y += bsg.h
 header-y += btrfs.h
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
new file mode 100644
index 000000000000..479ed0b6be16
--- /dev/null
+++ b/include/uapi/linux/bpf.h
@@ -0,0 +1,65 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_H__
+#define _UAPI__LINUX_BPF_H__
+
+#include <linux/types.h>
+
+/* Extended instruction set based on top of classic BPF */
+
+/* instruction classes */
+#define BPF_ALU64	0x07	/* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW		0x18	/* double word */
+#define BPF_XADD	0xc0	/* exclusive add */
+
+/* alu/jmp fields */
+#define BPF_MOV		0xb0	/* mov reg to reg */
+#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */
+
+/* change endianness of a register */
+#define BPF_END		0xd0	/* flags for endianness conversion: */
+#define BPF_TO_LE	0x00	/* convert to little-endian */
+#define BPF_TO_BE	0x08	/* convert to big-endian */
+#define BPF_FROM_LE	BPF_TO_LE
+#define BPF_FROM_BE	BPF_TO_BE
+
+#define BPF_JNE		0x50	/* jump != */
+#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
+#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
+#define BPF_CALL	0x80	/* function call */
+#define BPF_EXIT	0x90	/* function return */
+
+/* Register numbers */
+enum {
+	BPF_REG_0 = 0,
+	BPF_REG_1,
+	BPF_REG_2,
+	BPF_REG_3,
+	BPF_REG_4,
+	BPF_REG_5,
+	BPF_REG_6,
+	BPF_REG_7,
+	BPF_REG_8,
+	BPF_REG_9,
+	BPF_REG_10,
+	__MAX_BPF_REG,
+};
+
+/* BPF has 10 general purpose 64-bit registers and stack frame. */
+#define MAX_BPF_REG	__MAX_BPF_REG
+
+struct bpf_insn {
+	__u8	code;		/* opcode */
+	__u8	dst_reg:4;	/* dest register */
+	__u8	src_reg:4;	/* source register */
+	__s16	off;		/* signed offset */
+	__s32	imm;		/* signed immediate constant */
+};
+
+#endif /* _UAPI__LINUX_BPF_H__ */
-- 
cgit v1.2.3


From 49a601589caaf0e93194c0cc9b4ecddbe75dd2d5 Mon Sep 17 00:00:00 2001
From: Vincent Bernat <vincent@bernat.im>
Date: Fri, 5 Sep 2014 15:09:03 +0200
Subject: net/ipv4: bind ip_nonlocal_bind to current netns

net.ipv4.ip_nonlocal_bind sysctl was global to all network
namespaces. This patch allows to set a different value for each
network namespace.

Signed-off-by: Vincent Bernat <vincent@bernat.im>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h           |  2 --
 include/net/netns/ipv4.h   |  1 +
 net/ipv4/af_inet.c         |  6 +-----
 net/ipv4/ping.c            |  2 +-
 net/ipv4/sysctl_net_ipv4.c | 14 +++++++-------
 net/ipv6/af_inet6.c        |  2 +-
 net/sctp/protocol.c        |  2 +-
 7 files changed, 12 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index c8fd6112bd0b..14bfc8e1bcf9 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -229,8 +229,6 @@ static inline int inet_is_local_reserved_port(struct net *net, int port)
 }
 #endif
 
-extern int sysctl_ip_nonlocal_bind;
-
 /* From inetpeer.c */
 extern int inet_peer_threshold;
 extern int inet_peer_minttl;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index aec5e12f9f19..24945cefc4fd 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -76,6 +76,7 @@ struct netns_ipv4 {
 	int sysctl_tcp_ecn;
 	int sysctl_ip_no_pmtu_disc;
 	int sysctl_ip_fwd_use_pmtu;
+	int sysctl_ip_nonlocal_bind;
 
 	int sysctl_fwmark_reflect;
 	int sysctl_tcp_fwmark_accept;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d156b3c5f363..b537bd94906c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -418,10 +418,6 @@ int inet_release(struct socket *sock)
 }
 EXPORT_SYMBOL(inet_release);
 
-/* It is off by default, see below. */
-int sysctl_ip_nonlocal_bind __read_mostly;
-EXPORT_SYMBOL(sysctl_ip_nonlocal_bind);
-
 int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
@@ -461,7 +457,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	 *  is temporarily down)
 	 */
 	err = -EADDRNOTAVAIL;
-	if (!sysctl_ip_nonlocal_bind &&
+	if (!net->ipv4.sysctl_ip_nonlocal_bind &&
 	    !(inet->freebind || inet->transparent) &&
 	    addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
 	    chk_addr_ret != RTN_LOCAL &&
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index a3c59a077a5f..57f7c9804139 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -311,7 +311,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
 			chk_addr_ret = RTN_LOCAL;
 
-		if ((sysctl_ip_nonlocal_bind == 0 &&
+		if ((net->ipv4.sysctl_ip_nonlocal_bind == 0 &&
 		    isk->freebind == 0 && isk->transparent == 0 &&
 		     chk_addr_ret != RTN_LOCAL) ||
 		    chk_addr_ret == RTN_MULTICAST ||
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 45d156dacd61..1599966f4639 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -285,13 +285,6 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &ip_ttl_min,
 		.extra2		= &ip_ttl_max,
 	},
-	{
-		.procname	= "ip_nonlocal_bind",
-		.data		= &sysctl_ip_nonlocal_bind,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{
 		.procname	= "tcp_syn_retries",
 		.data		= &sysctl_tcp_syn_retries,
@@ -848,6 +841,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "ip_nonlocal_bind",
+		.data		= &init_net.ipv4.sysctl_ip_nonlocal_bind,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 	{
 		.procname	= "fwmark_reflect",
 		.data		= &init_net.ipv4.sysctl_fwmark_reflect,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index b9393e6a21fe..e4865a3ebe1d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -302,7 +302,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		/* Reproduce AF_INET checks to make the bindings consistent */
 		v4addr = addr->sin6_addr.s6_addr32[3];
 		chk_addr_ret = inet_addr_type(net, v4addr);
-		if (!sysctl_ip_nonlocal_bind &&
+		if (!net->ipv4.sysctl_ip_nonlocal_bind &&
 		    !(inet->freebind || inet->transparent) &&
 		    v4addr != htonl(INADDR_ANY) &&
 		    chk_addr_ret != RTN_LOCAL &&
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6240834f4b95..9d2c6c9facb6 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -366,7 +366,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
 	if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
 	   ret != RTN_LOCAL &&
 	   !sp->inet.freebind &&
-	   !sysctl_ip_nonlocal_bind)
+	   !net->ipv4.sysctl_ip_nonlocal_bind)
 		return 0;
 
 	if (ipv6_only_sock(sctp_opt2sk(sp)))
-- 
cgit v1.2.3


From e5c3ea5c668033b303e7ac835d7d91da32d97958 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 5 Sep 2014 15:51:31 +0200
Subject: bridge: implement rtnl_link_ops->get_size and
 rtnl_link_ops->fill_info

Allow rtnetlink users to get bridge master info in IFLA_INFO_DATA attr
This initial part implements forward_delay, hello_time, max_age options.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h | 12 ++++++++++++
 net/bridge/br_netlink.c      | 25 +++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index ff957604a721..c80f95f6ee78 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -215,6 +215,18 @@ enum in6_addr_gen_mode {
 	IN6_ADDR_GEN_MODE_NONE,
 };
 
+/* Bridge section */
+
+enum {
+	IFLA_BR_UNSPEC,
+	IFLA_BR_FORWARD_DELAY,
+	IFLA_BR_HELLO_TIME,
+	IFLA_BR_MAX_AGE,
+	__IFLA_BR_MAX,
+};
+
+#define IFLA_BR_MAX	(__IFLA_BR_MAX - 1)
+
 enum {
 	BRIDGE_MODE_UNSPEC,
 	BRIDGE_MODE_HAIRPIN,
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 05aeea1222a7..bcac09fe2ac8 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -484,6 +484,29 @@ static size_t br_port_get_slave_size(const struct net_device *brdev,
 	return br_port_info_size();
 }
 
+static size_t br_get_size(const struct net_device *brdev)
+{
+	return nla_total_size(sizeof(u32)) +	/* IFLA_BR_FORWARD_DELAY  */
+	       nla_total_size(sizeof(u32)) +	/* IFLA_BR_HELLO_TIME */
+	       nla_total_size(sizeof(u32)) +	/* IFLA_BR_MAX_AGE */
+	       0;
+}
+
+static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
+{
+	struct net_bridge *br = netdev_priv(brdev);
+	u32 forward_delay = jiffies_to_clock_t(br->forward_delay);
+	u32 hello_time = jiffies_to_clock_t(br->hello_time);
+	u32 age_time = jiffies_to_clock_t(br->max_age);
+
+	if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) ||
+	    nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) ||
+	    nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 static size_t br_get_link_af_size(const struct net_device *dev)
 {
 	struct net_port_vlans *pv;
@@ -514,6 +537,8 @@ struct rtnl_link_ops br_link_ops __read_mostly = {
 	.validate		= br_validate,
 	.newlink		= br_dev_newlink,
 	.dellink		= br_dev_delete,
+	.get_size		= br_get_size,
+	.fill_info		= br_fill_info,
 
 	.slave_maxtype		= IFLA_BRPORT_MAX,
 	.slave_policy		= br_port_policy,
-- 
cgit v1.2.3


From dc8ecdd3a3fccf73fcb07711cde064ce5727f9d1 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Mon, 1 Sep 2014 23:11:06 +0200
Subject: bcma: move bus struct setup into early part of host specific code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This change is important for SoC host. In future we will want to know
chip ID (needed for early MIPS boot) before doing cores scanning.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/host_pci.c   | 3 +++
 drivers/bcma/host_soc.c   | 3 +++
 drivers/bcma/main.c       | 2 --
 drivers/bcma/scan.c       | 7 -------
 include/linux/bcma/bcma.h | 1 -
 5 files changed, 6 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/host_pci.c b/drivers/bcma/host_pci.c
index f032ed6dd459..1e5ac0a79696 100644
--- a/drivers/bcma/host_pci.c
+++ b/drivers/bcma/host_pci.c
@@ -208,6 +208,9 @@ static int bcma_host_pci_probe(struct pci_dev *dev,
 	bus->boardinfo.vendor = bus->host_pci->subsystem_vendor;
 	bus->boardinfo.type = bus->host_pci->subsystem_device;
 
+	/* Initialize struct, detect chip */
+	bcma_init_bus(bus);
+
 	/* Register */
 	err = bcma_bus_register(bus);
 	if (err)
diff --git a/drivers/bcma/host_soc.c b/drivers/bcma/host_soc.c
index 1edd7e064621..379e0d4ebe72 100644
--- a/drivers/bcma/host_soc.c
+++ b/drivers/bcma/host_soc.c
@@ -178,6 +178,9 @@ int __init bcma_host_soc_register(struct bcma_soc *soc)
 	bus->hosttype = BCMA_HOSTTYPE_SOC;
 	bus->ops = &bcma_host_soc_ops;
 
+	/* Initialize struct, detect chip */
+	bcma_init_bus(bus);
+
 	/* Register */
 	err = bcma_bus_early_register(bus, &soc->core_cc, &soc->core_mips);
 	if (err)
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 0ff8d58831ef..9f6b0cb9a12c 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -334,8 +334,6 @@ int __init bcma_bus_early_register(struct bcma_bus *bus,
 	struct bcma_device *core;
 	struct bcma_device_id match;
 
-	bcma_init_bus(bus);
-
 	match.manuf = BCMA_MANUF_BCM;
 	match.id = bcma_cc_core_id(bus);
 	match.class = BCMA_CL_SIM;
diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c
index e9bd77249a4c..e2b990303042 100644
--- a/drivers/bcma/scan.c
+++ b/drivers/bcma/scan.c
@@ -438,9 +438,6 @@ void bcma_init_bus(struct bcma_bus *bus)
 	s32 tmp;
 	struct bcma_chipinfo *chipinfo = &(bus->chipinfo);
 
-	if (bus->init_done)
-		return;
-
 	INIT_LIST_HEAD(&bus->cores);
 	bus->nr_cores = 0;
 
@@ -452,8 +449,6 @@ void bcma_init_bus(struct bcma_bus *bus)
 	chipinfo->pkg = (tmp & BCMA_CC_ID_PKG) >> BCMA_CC_ID_PKG_SHIFT;
 	bcma_info(bus, "Found chip with id 0x%04X, rev 0x%02X and package 0x%02X\n",
 		  chipinfo->id, chipinfo->rev, chipinfo->pkg);
-
-	bus->init_done = true;
 }
 
 int bcma_bus_scan(struct bcma_bus *bus)
@@ -463,8 +458,6 @@ int bcma_bus_scan(struct bcma_bus *bus)
 
 	int err, core_num = 0;
 
-	bcma_init_bus(bus);
-
 	erombase = bcma_scan_read32(bus, 0, BCMA_CC_EROM);
 	if (bus->hosttype == BCMA_HOSTTYPE_SOC) {
 		eromptr = ioremap_nocache(erombase, BCMA_CORE_SIZE);
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index 0272e49135d0..c1ba87d1548e 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -332,7 +332,6 @@ struct bcma_bus {
 	struct bcma_device *mapped_core;
 	struct list_head cores;
 	u8 nr_cores;
-	u8 init_done:1;
 	u8 num;
 
 	struct bcma_drv_cc drv_cc;
-- 
cgit v1.2.3


From a395135ddebb0a06052b84c309eb6cb68b79c797 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Mon, 1 Sep 2014 23:11:07 +0200
Subject: bcma: use separated function to initialize bus on SoC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is required to split SoC bus init into two phases. The later one
(which includes scanning) should be called when kalloc is available.

Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 arch/mips/bcm47xx/setup.c     |  4 ++++
 drivers/bcma/host_soc.c       | 11 +++++++++--
 include/linux/bcma/bcma_soc.h |  1 +
 3 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 2b63e7e7d3d3..fff6ed4978c7 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -201,6 +201,10 @@ static void __init bcm47xx_register_bcma(void)
 		pr_warn("bcm47xx: someone else already registered a bcma SPROM callback handler (err %d)\n", err);
 
 	err = bcma_host_soc_register(&bcm47xx_bus.bcma);
+	if (err)
+		panic("Failed to register BCMA bus (err %d)", err);
+
+	err = bcma_host_soc_init(&bcm47xx_bus.bcma);
 	if (err)
 		panic("Failed to initialize BCMA bus (err %d)", err);
 
diff --git a/drivers/bcma/host_soc.c b/drivers/bcma/host_soc.c
index 379e0d4ebe72..718e054dd727 100644
--- a/drivers/bcma/host_soc.c
+++ b/drivers/bcma/host_soc.c
@@ -165,7 +165,6 @@ static const struct bcma_host_ops bcma_host_soc_ops = {
 int __init bcma_host_soc_register(struct bcma_soc *soc)
 {
 	struct bcma_bus *bus = &soc->bus;
-	int err;
 
 	/* iomap only first core. We have to read some register on this core
 	 * to scan the bus.
@@ -181,7 +180,15 @@ int __init bcma_host_soc_register(struct bcma_soc *soc)
 	/* Initialize struct, detect chip */
 	bcma_init_bus(bus);
 
-	/* Register */
+	return 0;
+}
+
+int __init bcma_host_soc_init(struct bcma_soc *soc)
+{
+	struct bcma_bus *bus = &soc->bus;
+	int err;
+
+	/* Scan bus and initialize it */
 	err = bcma_bus_early_register(bus, &soc->core_cc, &soc->core_mips);
 	if (err)
 		iounmap(bus->mmio);
diff --git a/include/linux/bcma/bcma_soc.h b/include/linux/bcma/bcma_soc.h
index 4203c5593b9f..f24d245f8394 100644
--- a/include/linux/bcma/bcma_soc.h
+++ b/include/linux/bcma/bcma_soc.h
@@ -10,6 +10,7 @@ struct bcma_soc {
 };
 
 int __init bcma_host_soc_register(struct bcma_soc *soc);
+int __init bcma_host_soc_init(struct bcma_soc *soc);
 
 int bcma_bus_register(struct bcma_bus *bus);
 
-- 
cgit v1.2.3


From 23a2f39c8f4035eade7f226eb7ada30c78d9eee3 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Mon, 8 Sep 2014 22:53:35 +0200
Subject: bcma: store more alternative addresses

Each core could have more than one alternative address. There are cores
with 8 alternative addresses for different functions. The PHY control
in the Chip common B core is done through the 2. alternative address
and not the first one.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
CC: linux-usb@vger.kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/scan.c         | 9 +++++----
 drivers/usb/host/bcma-hcd.c | 2 +-
 include/linux/bcma/bcma.h   | 2 +-
 3 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c
index e2b990303042..06be7282cbc4 100644
--- a/drivers/bcma/scan.c
+++ b/drivers/bcma/scan.c
@@ -276,7 +276,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 			      struct bcma_device *core)
 {
 	u32 tmp;
-	u8 i, j;
+	u8 i, j, k;
 	s32 cia, cib;
 	u8 ports[2], wrappers[2];
 
@@ -367,6 +367,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 	core->addr = tmp;
 
 	/* get & parse slave ports */
+	k = 0;
 	for (i = 0; i < ports[1]; i++) {
 		for (j = 0; ; j++) {
 			tmp = bcma_erom_get_addr_desc(bus, eromptr,
@@ -376,9 +377,9 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 				/* pr_debug("erom: slave port %d "
 				 * "has %d descriptors\n", i, j); */
 				break;
-			} else {
-				if (i == 0 && j == 0)
-					core->addr1 = tmp;
+			} else if (k < ARRAY_SIZE(core->addr_s)) {
+				core->addr_s[k] = tmp;
+				k++;
 			}
 		}
 	}
diff --git a/drivers/usb/host/bcma-hcd.c b/drivers/usb/host/bcma-hcd.c
index 205f4a336583..cd6d0afb6b8f 100644
--- a/drivers/usb/host/bcma-hcd.c
+++ b/drivers/usb/host/bcma-hcd.c
@@ -237,7 +237,7 @@ static int bcma_hcd_probe(struct bcma_device *dev)
 	bcma_hcd_init_chip(dev);
 
 	/* In AI chips EHCI is addrspace 0, OHCI is 1 */
-	ohci_addr = dev->addr1;
+	ohci_addr = dev->addr_s[0];
 	if ((chipinfo->id == 0x5357 || chipinfo->id == 0x4749)
 	    && chipinfo->rev == 0)
 		ohci_addr = 0x18009000;
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index c1ba87d1548e..7fc16c991291 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -267,7 +267,7 @@ struct bcma_device {
 	u8 core_unit;
 
 	u32 addr;
-	u32 addr1;
+	u32 addr_s[8];
 	u32 wrap;
 
 	void __iomem *io_addr;
-- 
cgit v1.2.3


From 1716bcf3f76fe71e98d4851a3eb73ea3d93d4773 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Mon, 8 Sep 2014 22:53:36 +0200
Subject: bcma: add support for chipcommon B core

This core is used on BCM4708 to configure the PCIe and USB3 PHYs and it
contains the addresses to the Device Management unit. This will be used
by the PCIe driver first.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/bcma/Makefile                       |  1 +
 drivers/bcma/bcma_private.h                 |  4 ++
 drivers/bcma/driver_chipcommon_b.c          | 61 +++++++++++++++++++++++++++++
 drivers/bcma/main.c                         | 10 +++++
 drivers/bcma/scan.c                         |  1 +
 include/linux/bcma/bcma.h                   |  1 +
 include/linux/bcma/bcma_driver_chipcommon.h |  8 ++++
 7 files changed, 86 insertions(+)
 create mode 100644 drivers/bcma/driver_chipcommon_b.c

(limited to 'include')

diff --git a/drivers/bcma/Makefile b/drivers/bcma/Makefile
index 91290f7f61b8..838b4b9d352f 100644
--- a/drivers/bcma/Makefile
+++ b/drivers/bcma/Makefile
@@ -1,5 +1,6 @@
 bcma-y					+= main.o scan.o core.o sprom.o
 bcma-y					+= driver_chipcommon.o driver_chipcommon_pmu.o
+bcma-y					+= driver_chipcommon_b.o
 bcma-$(CONFIG_BCMA_SFLASH)		+= driver_chipcommon_sflash.o
 bcma-$(CONFIG_BCMA_NFLASH)		+= driver_chipcommon_nflash.o
 bcma-y					+= driver_pci.o
diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index 09b632ad0fe2..b40be43c6f31 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -50,6 +50,10 @@ void bcma_chipco_serial_init(struct bcma_drv_cc *cc);
 extern struct platform_device bcma_pflash_dev;
 #endif /* CONFIG_BCMA_DRIVER_MIPS */
 
+/* driver_chipcommon_b.c */
+int bcma_core_chipcommon_b_init(struct bcma_drv_cc_b *ccb);
+void bcma_core_chipcommon_b_free(struct bcma_drv_cc_b *ccb);
+
 /* driver_chipcommon_pmu.c */
 u32 bcma_pmu_get_alp_clock(struct bcma_drv_cc *cc);
 u32 bcma_pmu_get_cpu_clock(struct bcma_drv_cc *cc);
diff --git a/drivers/bcma/driver_chipcommon_b.c b/drivers/bcma/driver_chipcommon_b.c
new file mode 100644
index 000000000000..c20b5f4ff290
--- /dev/null
+++ b/drivers/bcma/driver_chipcommon_b.c
@@ -0,0 +1,61 @@
+/*
+ * Broadcom specific AMBA
+ * ChipCommon B Unit driver
+ *
+ * Copyright 2014, Hauke Mehrtens <hauke@hauke-m.de>
+ *
+ * Licensed under the GNU/GPL. See COPYING for details.
+ */
+
+#include "bcma_private.h"
+#include <linux/export.h>
+#include <linux/bcma/bcma.h>
+
+static bool bcma_wait_reg(struct bcma_bus *bus, void __iomem *addr, u32 mask,
+			  u32 value, int timeout)
+{
+	unsigned long deadline = jiffies + timeout;
+	u32 val;
+
+	do {
+		val = readl(addr);
+		if ((val & mask) == value)
+			return true;
+		cpu_relax();
+		udelay(10);
+	} while (!time_after_eq(jiffies, deadline));
+
+	bcma_err(bus, "Timeout waiting for register %p\n", addr);
+
+	return false;
+}
+
+void bcma_chipco_b_mii_write(struct bcma_drv_cc_b *ccb, u32 offset, u32 value)
+{
+	struct bcma_bus *bus = ccb->core->bus;
+
+	writel(offset, ccb->mii + 0x00);
+	bcma_wait_reg(bus, ccb->mii + 0x00, 0x0100, 0x0000, 100);
+	writel(value, ccb->mii + 0x04);
+	bcma_wait_reg(bus, ccb->mii + 0x00, 0x0100, 0x0000, 100);
+}
+EXPORT_SYMBOL_GPL(bcma_chipco_b_mii_write);
+
+int bcma_core_chipcommon_b_init(struct bcma_drv_cc_b *ccb)
+{
+	if (ccb->setup_done)
+		return 0;
+
+	ccb->setup_done = 1;
+	ccb->mii = ioremap_nocache(ccb->core->addr_s[1], BCMA_CORE_SIZE);
+	if (!ccb->mii)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void bcma_core_chipcommon_b_free(struct bcma_drv_cc_b *ccb)
+{
+	if (ccb->mii)
+		iounmap(ccb->mii);
+}
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 297a2d46985a..c421403cab43 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -173,6 +173,7 @@ static int bcma_register_devices(struct bcma_bus *bus)
 		switch (core->id.id) {
 		case BCMA_CORE_4706_CHIPCOMMON:
 		case BCMA_CORE_CHIPCOMMON:
+		case BCMA_CORE_NS_CHIPCOMMON_B:
 		case BCMA_CORE_PCI:
 		case BCMA_CORE_PCIE:
 		case BCMA_CORE_PCIE2:
@@ -287,6 +288,13 @@ int bcma_bus_register(struct bcma_bus *bus)
 		bcma_core_chipcommon_init(&bus->drv_cc);
 	}
 
+	/* Init CC core */
+	core = bcma_find_core(bus, BCMA_CORE_NS_CHIPCOMMON_B);
+	if (core) {
+		bus->drv_cc_b.core = core;
+		bcma_core_chipcommon_b_init(&bus->drv_cc_b);
+	}
+
 	/* Init MIPS core */
 	core = bcma_find_core(bus, BCMA_CORE_MIPS_74K);
 	if (core) {
@@ -341,6 +349,8 @@ void bcma_bus_unregister(struct bcma_bus *bus)
 	else if (err)
 		bcma_err(bus, "Can not unregister GPIO driver: %i\n", err);
 
+	bcma_core_chipcommon_b_free(&bus->drv_cc_b);
+
 	cores[0] = bcma_find_core(bus, BCMA_CORE_MIPS_74K);
 	cores[1] = bcma_find_core(bus, BCMA_CORE_PCIE);
 	cores[2] = bcma_find_core(bus, BCMA_CORE_4706_MAC_GBIT_COMMON);
diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c
index 06be7282cbc4..b3a403c136fb 100644
--- a/drivers/bcma/scan.c
+++ b/drivers/bcma/scan.c
@@ -314,6 +314,7 @@ static int bcma_get_next_core(struct bcma_bus *bus, u32 __iomem **eromptr,
 		/* Some specific cores don't need wrappers */
 		switch (core->id.id) {
 		case BCMA_CORE_4706_MAC_GBIT_COMMON:
+		case BCMA_CORE_NS_CHIPCOMMON_B:
 		/* Not used yet: case BCMA_CORE_OOB_ROUTER: */
 			break;
 		default:
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index 7fc16c991291..634597917670 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -335,6 +335,7 @@ struct bcma_bus {
 	u8 num;
 
 	struct bcma_drv_cc drv_cc;
+	struct bcma_drv_cc_b drv_cc_b;
 	struct bcma_drv_pci drv_pci[2];
 	struct bcma_drv_pcie2 drv_pcie2;
 	struct bcma_drv_mips drv_mips;
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index 63d105cd14a3..db6fa217f98b 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -644,6 +644,12 @@ struct bcma_drv_cc {
 #endif
 };
 
+struct bcma_drv_cc_b {
+	struct bcma_device *core;
+	u8 setup_done:1;
+	void __iomem *mii;
+};
+
 /* Register access */
 #define bcma_cc_read32(cc, offset) \
 	bcma_read32((cc)->core, offset)
@@ -699,4 +705,6 @@ extern void bcma_pmu_spuravoid_pllupdate(struct bcma_drv_cc *cc, int spuravoid);
 
 extern u32 bcma_pmu_get_bus_clock(struct bcma_drv_cc *cc);
 
+void bcma_chipco_b_mii_write(struct bcma_drv_cc_b *ccb, u32 offset, u32 value);
+
 #endif /* LINUX_BCMA_DRIVER_CC_H_ */
-- 
cgit v1.2.3


From d0449b90f80f263e17e8b3ce31442e45121dc46c Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 22 Aug 2014 10:18:42 -0400
Subject: locks: Remove unused conf argument from lm_grant

This argument is always NULL so don't pass it around.

[jlayton: remove dependencies on previous patches in series]

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
 fs/dlm/plock.c     |  8 ++++----
 fs/lockd/svclock.c | 12 +++---------
 include/linux/fs.h |  2 +-
 3 files changed, 8 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index f704458ea5f5..e0ab3a93eeff 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -30,7 +30,7 @@ struct plock_op {
 
 struct plock_xop {
 	struct plock_op xop;
-	void *callback;
+	int (*callback)(struct file_lock *fl, int result);
 	void *fl;
 	void *file;
 	struct file_lock flc;
@@ -190,7 +190,7 @@ static int dlm_plock_callback(struct plock_op *op)
 	struct file *file;
 	struct file_lock *fl;
 	struct file_lock *flc;
-	int (*notify)(void *, void *, int) = NULL;
+	int (*notify)(struct file_lock *fl, int result) = NULL;
 	struct plock_xop *xop = (struct plock_xop *)op;
 	int rv = 0;
 
@@ -209,7 +209,7 @@ static int dlm_plock_callback(struct plock_op *op)
 	notify = xop->callback;
 
 	if (op->info.rv) {
-		notify(fl, NULL, op->info.rv);
+		notify(fl, op->info.rv);
 		goto out;
 	}
 
@@ -228,7 +228,7 @@ static int dlm_plock_callback(struct plock_op *op)
 			  (unsigned long long)op->info.number, file, fl);
 	}
 
-	rv = notify(fl, NULL, 0);
+	rv = notify(fl, 0);
 	if (rv) {
 		/* XXX: We need to cancel the fs lock here: */
 		log_print("dlm_plock_callback: lock granted after lock request "
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index ab798a88ec1d..2a6170133c1d 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -667,22 +667,16 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l
  * deferred rpc for GETLK and SETLK.
  */
 static void
-nlmsvc_update_deferred_block(struct nlm_block *block, struct file_lock *conf,
-			     int result)
+nlmsvc_update_deferred_block(struct nlm_block *block, int result)
 {
 	block->b_flags |= B_GOT_CALLBACK;
 	if (result == 0)
 		block->b_granted = 1;
 	else
 		block->b_flags |= B_TIMED_OUT;
-	if (conf) {
-		if (block->b_fl)
-			__locks_copy_lock(block->b_fl, conf);
-	}
 }
 
-static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
-					int result)
+static int nlmsvc_grant_deferred(struct file_lock *fl, int result)
 {
 	struct nlm_block *block;
 	int rc = -ENOENT;
@@ -697,7 +691,7 @@ static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
 					rc = -ENOLCK;
 					break;
 				}
-				nlmsvc_update_deferred_block(block, conf, result);
+				nlmsvc_update_deferred_block(block, result);
 			} else if (result == 0)
 				block->b_granted = 1;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 94187721ad41..908af4f81680 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -869,7 +869,7 @@ struct lock_manager_operations {
 	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
 	unsigned long (*lm_owner_key)(struct file_lock *);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
-	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
+	int (*lm_grant)(struct file_lock *, int);
 	void (*lm_break)(struct file_lock *);
 	int (*lm_change)(struct file_lock **, int);
 };
-- 
cgit v1.2.3


From 3fe0fff18fe87c6a2179837de68d1174903c6367 Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Fri, 22 Aug 2014 10:18:42 -0400
Subject: locks: Rename __locks_copy_lock() to locks_copy_conflock()

Jeff advice, " Right now __locks_copy_lock is only used to copy
conflocks. It would be good to rename that to something more
distinct (i.e.locks_copy_conflock), to make it clear that we're
generating a conflock there."

v5: change order from 3/6 to 2/6
v4: new patch only renaming function name

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
 fs/locks.c         | 10 +++++-----
 include/linux/fs.h |  4 ++--
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index bb08857f90b5..ec9becd02d3d 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -281,7 +281,7 @@ static void locks_copy_private(struct file_lock *new, struct file_lock *fl)
 /*
  * Initialize a new lock from an existing file_lock structure.
  */
-void __locks_copy_lock(struct file_lock *new, const struct file_lock *fl)
+void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	new->fl_owner = fl->fl_owner;
 	new->fl_pid = fl->fl_pid;
@@ -293,14 +293,14 @@ void __locks_copy_lock(struct file_lock *new, const struct file_lock *fl)
 	new->fl_ops = NULL;
 	new->fl_lmops = NULL;
 }
-EXPORT_SYMBOL(__locks_copy_lock);
+EXPORT_SYMBOL(locks_copy_conflock);
 
 void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
 {
 	/* "new" must be a freshly-initialized lock */
 	WARN_ON_ONCE(new->fl_ops);
 
-	__locks_copy_lock(new, fl);
+	locks_copy_conflock(new, fl);
 	new->fl_file = fl->fl_file;
 	new->fl_ops = fl->fl_ops;
 	new->fl_lmops = fl->fl_lmops;
@@ -735,7 +735,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 			break;
 	}
 	if (cfl) {
-		__locks_copy_lock(fl, cfl);
+		locks_copy_conflock(fl, cfl);
 		if (cfl->fl_nspid)
 			fl->fl_pid = pid_vnr(cfl->fl_nspid);
 	} else
@@ -941,7 +941,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			if (!posix_locks_conflict(request, fl))
 				continue;
 			if (conflock)
-				__locks_copy_lock(conflock, fl);
+				locks_copy_conflock(conflock, fl);
 			error = -EAGAIN;
 			if (!(request->fl_flags & FL_SLEEP))
 				goto out;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 908af4f81680..5ab86f44b697 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -966,7 +966,7 @@ void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);
 extern struct file_lock * locks_alloc_lock(void);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);
-extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
+extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
 extern void locks_remove_file(struct file *);
 extern void locks_release_private(struct file_lock *);
@@ -1026,7 +1026,7 @@ static inline void locks_init_lock(struct file_lock *fl)
 	return;
 }
 
-static inline void __locks_copy_lock(struct file_lock *new, struct file_lock *fl)
+static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	return;
 }
-- 
cgit v1.2.3


From 5c97d7b1479982a48cf2129062b880c2555049ac Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Fri, 22 Aug 2014 10:18:43 -0400
Subject: locks: New ops in lock_manager_operations for get/put owner

NFSD or other lockmanager may increase the owner's reference,
so adds two new options for copying and releasing owner.

v5: change order from 2/6 to 3/6
v4: rename lm_copy_owner/lm_release_owner to lm_get_owner/lm_put_owner

Reviewed-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
 fs/locks.c         | 12 ++++++++++--
 include/linux/fs.h |  2 ++
 2 files changed, 12 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index ec9becd02d3d..5e83f3a99377 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -230,8 +230,12 @@ void locks_release_private(struct file_lock *fl)
 			fl->fl_ops->fl_release_private(fl);
 		fl->fl_ops = NULL;
 	}
-	fl->fl_lmops = NULL;
 
+	if (fl->fl_lmops) {
+		if (fl->fl_lmops->lm_put_owner)
+			fl->fl_lmops->lm_put_owner(fl);
+		fl->fl_lmops = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(locks_release_private);
 
@@ -274,8 +278,12 @@ static void locks_copy_private(struct file_lock *new, struct file_lock *fl)
 			fl->fl_ops->fl_copy_lock(new, fl);
 		new->fl_ops = fl->fl_ops;
 	}
-	if (fl->fl_lmops)
+
+	if (fl->fl_lmops) {
+		if (fl->fl_lmops->lm_get_owner)
+			fl->fl_lmops->lm_get_owner(new, fl);
 		new->fl_lmops = fl->fl_lmops;
+	}
 }
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5ab86f44b697..3b07ce2698de 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -868,6 +868,8 @@ struct file_lock_operations {
 struct lock_manager_operations {
 	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
 	unsigned long (*lm_owner_key)(struct file_lock *);
+	void (*lm_get_owner)(struct file_lock *, struct file_lock *);
+	void (*lm_put_owner)(struct file_lock *);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
 	int (*lm_grant)(struct file_lock *, int);
 	void (*lm_break)(struct file_lock *);
-- 
cgit v1.2.3


From 09802fd2a8caea2a2147fca8d7975697c5de573d Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 22 Aug 2014 10:18:44 -0400
Subject: lockd: rip out deferred lock handling from testlock codepath

As Kinglong points out, the nlm_block->b_fl field is no longer used at
all. Also, vfs_test_lock in the generic locking code will only return
FILE_LOCK_DEFERRED if FL_SLEEP is set, and it isn't here.

The only other place that returns that value is the DLM lock code, but
it only does that in dlm_posix_lock, never in dlm_posix_get.

Remove all of the deferred locking code from the testlock codepath
since it doesn't appear to ever be used anyway.

I do have a small concern that this might cause a behavior change in the
case where you have a block already sitting on the list when the
testlock request comes in, but that looks like it doesn't really work
properly anyway. I think it's best to just pass that down to
vfs_test_lock and let the filesystem report that instead of trying to
infer what's going on with the lock by looking at an existing block.

Cc: cluster-devel@redhat.com
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Kinglong Mee <kinglongmee@gmail.com>
---
 fs/lockd/svclock.c          | 55 +++++----------------------------------------
 include/linux/lockd/lockd.h |  1 -
 2 files changed, 6 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index acfa94d5b489..13db95f54176 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -245,7 +245,6 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host,
 	block->b_daemon = rqstp->rq_server;
 	block->b_host   = host;
 	block->b_file   = file;
-	block->b_fl = NULL;
 	file->f_count++;
 
 	/* Add to file's list of blocks */
@@ -295,7 +294,6 @@ static void nlmsvc_free_block(struct kref *kref)
 	nlmsvc_freegrantargs(block->b_call);
 	nlmsvc_release_call(block->b_call);
 	nlm_release_file(block->b_file);
-	kfree(block->b_fl);
 	kfree(block);
 }
 
@@ -508,7 +506,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		struct nlm_host *host, struct nlm_lock *lock,
 		struct nlm_lock *conflock, struct nlm_cookie *cookie)
 {
-	struct nlm_block 	*block = NULL;
 	int			error;
 	__be32			ret;
 
@@ -519,63 +516,26 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
-	/* Get existing block (in case client is busy-waiting) */
-	block = nlmsvc_lookup_block(file, lock);
-
-	if (block == NULL) {
-		struct file_lock *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
-
-		if (conf == NULL)
-			return nlm_granted;
-		block = nlmsvc_create_block(rqstp, host, file, lock, cookie);
-		if (block == NULL) {
-			kfree(conf);
-			return nlm_granted;
-		}
-		block->b_fl = conf;
-	}
-	if (block->b_flags & B_QUEUED) {
-		dprintk("lockd: nlmsvc_testlock deferred block %p flags %d fl %p\n",
-			block, block->b_flags, block->b_fl);
-		if (block->b_flags & B_TIMED_OUT) {
-			nlmsvc_unlink_block(block);
-			ret = nlm_lck_denied;
-			goto out;
-		}
-		if (block->b_flags & B_GOT_CALLBACK) {
-			nlmsvc_unlink_block(block);
-			if (block->b_fl != NULL
-					&& block->b_fl->fl_type != F_UNLCK) {
-				lock->fl = *block->b_fl;
-				goto conf_lock;
-			} else {
-				ret = nlm_granted;
-				goto out;
-			}
-		}
-		ret = nlm_drop_reply;
-		goto out;
-	}
-
 	if (locks_in_grace(SVC_NET(rqstp))) {
 		ret = nlm_lck_denied_grace_period;
 		goto out;
 	}
+
 	error = vfs_test_lock(file->f_file, &lock->fl);
-	if (error == FILE_LOCK_DEFERRED) {
-		ret = nlmsvc_defer_lock_rqst(rqstp, block);
-		goto out;
-	}
 	if (error) {
+		/* We can't currently deal with deferred test requests */
+		if (error == FILE_LOCK_DEFERRED)
+			WARN_ON_ONCE(1);
+
 		ret = nlm_lck_denied_nolocks;
 		goto out;
 	}
+
 	if (lock->fl.fl_type == F_UNLCK) {
 		ret = nlm_granted;
 		goto out;
 	}
 
-conf_lock:
 	dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
 		lock->fl.fl_type, (long long)lock->fl.fl_start,
 		(long long)lock->fl.fl_end);
@@ -589,8 +549,6 @@ conf_lock:
 	locks_release_private(&lock->fl);
 	ret = nlm_lck_denied;
 out:
-	if (block)
-		nlmsvc_release_block(block);
 	return ret;
 }
 
@@ -661,7 +619,6 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l
  * This is a callback from the filesystem for VFS file lock requests.
  * It will be used if lm_grant is defined and the filesystem can not
  * respond to the request immediately.
- * For GETLK request it will copy the reply to the nlm_block.
  * For SETLK or SETLKW request it will get the local posix lock.
  * In all cases it will move the block to the head of nlm_blocked q where
  * nlmsvc_retry_blocked() can send back a reply for SETLKW or revisit the
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 219d79627c05..ff82a32871b5 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -178,7 +178,6 @@ struct nlm_block {
 	unsigned char		b_granted;	/* VFS granted lock */
 	struct nlm_file *	b_file;		/* file in question */
 	struct cache_req *	b_cache_req;	/* deferred request handling */
-	struct file_lock *	b_fl;		/* set for GETLK */
 	struct cache_deferred_req * b_deferred_req;
 	unsigned int		b_flags;	/* block flags */
 #define B_QUEUED		1	/* lock queued */
-- 
cgit v1.2.3


From 699688a416524c3cea9eafaca69fc6c06c13c02e Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 22 Aug 2014 10:18:44 -0400
Subject: locks: remove lock_may_read and lock_may_write

There are no callers of these functions.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
 fs/locks.c         | 80 ------------------------------------------------------
 include/linux/fs.h | 14 ----------
 2 files changed, 94 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index c3991dc80137..5200ffd2ba9b 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2597,86 +2597,6 @@ static int __init proc_locks_init(void)
 module_init(proc_locks_init);
 #endif
 
-/**
- *	lock_may_read - checks that the region is free of locks
- *	@inode: the inode that is being read
- *	@start: the first byte to read
- *	@len: the number of bytes to read
- *
- *	Emulates Windows locking requirements.  Whole-file
- *	mandatory locks (share modes) can prohibit a read and
- *	byte-range POSIX locks can prohibit a read if they overlap.
- *
- *	N.B. this function is only ever called
- *	from knfsd and ownership of locks is never checked.
- */
-int lock_may_read(struct inode *inode, loff_t start, unsigned long len)
-{
-	struct file_lock *fl;
-	int result = 1;
-
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (IS_POSIX(fl)) {
-			if (fl->fl_type == F_RDLCK)
-				continue;
-			if ((fl->fl_end < start) || (fl->fl_start > (start + len)))
-				continue;
-		} else if (IS_FLOCK(fl)) {
-			if (!(fl->fl_type & LOCK_MAND))
-				continue;
-			if (fl->fl_type & LOCK_READ)
-				continue;
-		} else
-			continue;
-		result = 0;
-		break;
-	}
-	spin_unlock(&inode->i_lock);
-	return result;
-}
-
-EXPORT_SYMBOL(lock_may_read);
-
-/**
- *	lock_may_write - checks that the region is free of locks
- *	@inode: the inode that is being written
- *	@start: the first byte to write
- *	@len: the number of bytes to write
- *
- *	Emulates Windows locking requirements.  Whole-file
- *	mandatory locks (share modes) can prohibit a write and
- *	byte-range POSIX locks can prohibit a write if they overlap.
- *
- *	N.B. this function is only ever called
- *	from knfsd and ownership of locks is never checked.
- */
-int lock_may_write(struct inode *inode, loff_t start, unsigned long len)
-{
-	struct file_lock *fl;
-	int result = 1;
-
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (IS_POSIX(fl)) {
-			if ((fl->fl_end < start) || (fl->fl_start > (start + len)))
-				continue;
-		} else if (IS_FLOCK(fl)) {
-			if (!(fl->fl_type & LOCK_MAND))
-				continue;
-			if (fl->fl_type & LOCK_WRITE)
-				continue;
-		} else
-			continue;
-		result = 0;
-		break;
-	}
-	spin_unlock(&inode->i_lock);
-	return result;
-}
-
-EXPORT_SYMBOL(lock_may_write);
-
 static int __init filelock_init(void)
 {
 	int i;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3b07ce2698de..458f733c96bd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -985,8 +985,6 @@ extern void lease_get_mtime(struct inode *, struct timespec *time);
 extern int generic_setlease(struct file *, long, struct file_lock **);
 extern int vfs_setlease(struct file *, long, struct file_lock **);
 extern int lease_modify(struct file_lock **, int);
-extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
-extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
 			      struct flock __user *user)
@@ -1117,18 +1115,6 @@ static inline int lease_modify(struct file_lock **before, int arg)
 {
 	return -EINVAL;
 }
-
-static inline int lock_may_read(struct inode *inode, loff_t start,
-				unsigned long len)
-{
-	return 1;
-}
-
-static inline int lock_may_write(struct inode *inode, loff_t start,
-				 unsigned long len)
-{
-	return 1;
-}
 #endif /* !CONFIG_FILE_LOCKING */
 
 
-- 
cgit v1.2.3


From 1c994a0909a556508c2cc26ab5d9e13c5ce33aa0 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 27 Aug 2014 06:49:41 -0400
Subject: locks: consolidate "nolease" routines

GFS2 and NFS have setlease routines that always just return -EINVAL.
Turn that into a generic routine that can live in fs/libfs.c.

Cc: <linux-nfs@vger.kernel.org>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: <cluster-devel@redhat.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/gfs2/file.c     | 22 +---------------------
 fs/libfs.c         | 16 ++++++++++++++++
 fs/nfs/file.c      | 13 +------------
 fs/nfs/internal.h  |  1 -
 fs/nfs/nfs4file.c  |  2 +-
 include/linux/fs.h |  1 +
 6 files changed, 20 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 26b3f952e6b1..2c02478a86b0 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -912,26 +912,6 @@ out_uninit:
 
 #ifdef CONFIG_GFS2_FS_LOCKING_DLM
 
-/**
- * gfs2_setlease - acquire/release a file lease
- * @file: the file pointer
- * @arg: lease type
- * @fl: file lock
- *
- * We don't currently have a way to enforce a lease across the whole
- * cluster; until we do, disable leases (by just returning -EINVAL),
- * unless the administrator has requested purely local locking.
- *
- * Locking: called under i_lock
- *
- * Returns: errno
- */
-
-static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl)
-{
-	return -EINVAL;
-}
-
 /**
  * gfs2_lock - acquire/release a posix lock on a file
  * @file: the file pointer
@@ -1069,7 +1049,7 @@ const struct file_operations gfs2_file_fops = {
 	.flock		= gfs2_flock,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
-	.setlease	= gfs2_setlease,
+	.setlease	= simple_nosetlease,
 	.fallocate	= gfs2_fallocate,
 };
 
diff --git a/fs/libfs.c b/fs/libfs.c
index 88e3e00e2eca..29012a303ef8 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1075,3 +1075,19 @@ struct inode *alloc_anon_inode(struct super_block *s)
 	return inode;
 }
 EXPORT_SYMBOL(alloc_anon_inode);
+
+/**
+ * simple_nosetlease - generic helper for prohibiting leases
+ * @filp: file pointer
+ * @arg: type of lease to obtain
+ * @flp: new lease supplied for insertion
+ *
+ * Generic helper for filesystems that do not wish to allow leases to be set.
+ * All arguments are ignored and it just returns -EINVAL.
+ */
+int
+simple_nosetlease(struct file *filp, long arg, struct file_lock **flp)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(simple_nosetlease);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 524dd80d1898..8c4048ecdad1 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -891,17 +891,6 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 }
 EXPORT_SYMBOL_GPL(nfs_flock);
 
-/*
- * There is no protocol support for leases, so we have no way to implement
- * them correctly in the face of opens by other clients.
- */
-int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
-{
-	dprintk("NFS: setlease(%pD2, arg=%ld)\n", file, arg);
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(nfs_setlease);
-
 const struct file_operations nfs_file_operations = {
 	.llseek		= nfs_file_llseek,
 	.read		= new_sync_read,
@@ -918,6 +907,6 @@ const struct file_operations nfs_file_operations = {
 	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
+	.setlease	= simple_nosetlease,
 };
 EXPORT_SYMBOL_GPL(nfs_file_operations);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9056622d2230..94d922ebb5ac 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -346,7 +346,6 @@ int nfs_file_release(struct inode *, struct file *);
 int nfs_lock(struct file *, int, struct file_lock *);
 int nfs_flock(struct file *, int, struct file_lock *);
 int nfs_check_flags(int);
-int nfs_setlease(struct file *, long, struct file_lock **);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index a816f0627a6c..3e987ad9ae25 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -131,5 +131,5 @@ const struct file_operations nfs4_file_operations = {
 	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
+	.setlease	= simple_nosetlease,
 };
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 458f733c96bd..435e3d9ec5cf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2599,6 +2599,7 @@ extern int simple_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata);
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
+extern int simple_nosetlease(struct file *, long, struct file_lock **);
 extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
-- 
cgit v1.2.3


From e0b93eddfe17dcb7d644eb5d6ad02a86fc41a977 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 22 Aug 2014 11:27:32 -0400
Subject: security: make security_file_set_fowner, f_setown and __f_setown void
 return

security_file_set_fowner always returns 0, so make it f_setown and
__f_setown void return functions and fix up the error handling in the
callers.

Cc: linux-security-module@vger.kernel.org
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/net/tun.c           |  4 +---
 drivers/tty/tty_io.c        |  3 ++-
 fs/fcntl.c                  | 21 +++++++--------------
 fs/locks.c                  |  2 +-
 fs/notify/dnotify/dnotify.c |  8 +-------
 include/linux/fs.h          |  4 ++--
 include/linux/security.h    |  8 ++++----
 net/socket.c                |  3 ++-
 security/capability.c       |  4 ++--
 security/security.c         |  4 ++--
 security/selinux/hooks.c    |  4 +---
 security/smack/smack_lsm.c  |  3 +--
 12 files changed, 26 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index acaaf6784179..186ce541c657 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2152,9 +2152,7 @@ static int tun_chr_fasync(int fd, struct file *file, int on)
 		goto out;
 
 	if (on) {
-		ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
-		if (ret)
-			goto out;
+		__f_setown(file, task_pid(current), PIDTYPE_PID, 0);
 		tfile->flags |= TUN_FASYNC;
 	} else
 		tfile->flags &= ~TUN_FASYNC;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 8fbad3410c75..aea3b66f7bf2 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2163,8 +2163,9 @@ static int __tty_fasync(int fd, struct file *filp, int on)
 		}
 		get_pid(pid);
 		spin_unlock_irqrestore(&tty->ctrl_lock, flags);
-		retval = __f_setown(filp, pid, type, 0);
+		__f_setown(filp, pid, type, 0);
 		put_pid(pid);
+		retval = 0;
 	}
 out:
 	return retval;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 22d1c3df61ac..99d440a4a6ba 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -98,26 +98,19 @@ static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
 	write_unlock_irq(&filp->f_owner.lock);
 }
 
-int __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
+void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
 		int force)
 {
-	int err;
-
-	err = security_file_set_fowner(filp);
-	if (err)
-		return err;
-
+	security_file_set_fowner(filp);
 	f_modown(filp, pid, type, force);
-	return 0;
 }
 EXPORT_SYMBOL(__f_setown);
 
-int f_setown(struct file *filp, unsigned long arg, int force)
+void f_setown(struct file *filp, unsigned long arg, int force)
 {
 	enum pid_type type;
 	struct pid *pid;
 	int who = arg;
-	int result;
 	type = PIDTYPE_PID;
 	if (who < 0) {
 		type = PIDTYPE_PGID;
@@ -125,9 +118,8 @@ int f_setown(struct file *filp, unsigned long arg, int force)
 	}
 	rcu_read_lock();
 	pid = find_vpid(who);
-	result = __f_setown(filp, pid, type, force);
+	__f_setown(filp, pid, type, force);
 	rcu_read_unlock();
-	return result;
 }
 EXPORT_SYMBOL(f_setown);
 
@@ -181,7 +173,7 @@ static int f_setown_ex(struct file *filp, unsigned long arg)
 	if (owner.pid && !pid)
 		ret = -ESRCH;
 	else
-		ret = __f_setown(filp, pid, type, 1);
+		 __f_setown(filp, pid, type, 1);
 	rcu_read_unlock();
 
 	return ret;
@@ -302,7 +294,8 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		force_successful_syscall_return();
 		break;
 	case F_SETOWN:
-		err = f_setown(filp, arg, 1);
+		f_setown(filp, arg, 1);
+		err = 0;
 		break;
 	case F_GETOWN_EX:
 		err = f_getown_ex(filp, arg);
diff --git a/fs/locks.c b/fs/locks.c
index 5200ffd2ba9b..f5f648e003dd 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1776,7 +1776,7 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 	if (!fasync_insert_entry(fd, filp, &ret->fl_fasync, new))
 		new = NULL;
 
-	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
+	__f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
 out_unlock:
 	spin_unlock(&inode->i_lock);
 	if (fl)
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index abc8cbcfe90e..caaaf9dfe353 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -346,13 +346,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 		goto out;
 	}
 
-	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
-	if (error) {
-		/* if we added, we must shoot */
-		if (dn_mark == new_dn_mark)
-			destroy = 1;
-		goto out;
-	}
+	__f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
 
 	error = attach_dn(dn, dn_mark, id, fd, filp, mask);
 	/* !error means that we attached the dn to the dn_mark, so don't free it */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 435e3d9ec5cf..96528f73dda4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1139,8 +1139,8 @@ extern void fasync_free(struct fasync_struct *);
 /* can be called from interrupts */
 extern void kill_fasync(struct fasync_struct **, int, int);
 
-extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
-extern int f_setown(struct file *filp, unsigned long arg, int force);
+extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
+extern void f_setown(struct file *filp, unsigned long arg, int force);
 extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
 extern int send_sigurg(struct fown_struct *fown);
diff --git a/include/linux/security.h b/include/linux/security.h
index 623f90e5f38d..b10e7af95d3b 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1559,7 +1559,7 @@ struct security_operations {
 	int (*file_lock) (struct file *file, unsigned int cmd);
 	int (*file_fcntl) (struct file *file, unsigned int cmd,
 			   unsigned long arg);
-	int (*file_set_fowner) (struct file *file);
+	void (*file_set_fowner) (struct file *file);
 	int (*file_send_sigiotask) (struct task_struct *tsk,
 				    struct fown_struct *fown, int sig);
 	int (*file_receive) (struct file *file);
@@ -1834,7 +1834,7 @@ int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
 			   unsigned long prot);
 int security_file_lock(struct file *file, unsigned int cmd);
 int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
-int security_file_set_fowner(struct file *file);
+void security_file_set_fowner(struct file *file);
 int security_file_send_sigiotask(struct task_struct *tsk,
 				 struct fown_struct *fown, int sig);
 int security_file_receive(struct file *file);
@@ -2312,9 +2312,9 @@ static inline int security_file_fcntl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
-static inline int security_file_set_fowner(struct file *file)
+static inline void security_file_set_fowner(struct file *file)
 {
-	return 0;
+	return;
 }
 
 static inline int security_file_send_sigiotask(struct task_struct *tsk,
diff --git a/net/socket.c b/net/socket.c
index 95ee7d8682e7..769c9671847e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1069,7 +1069,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			err = -EFAULT;
 			if (get_user(pid, (int __user *)argp))
 				break;
-			err = f_setown(sock->file, pid, 1);
+			f_setown(sock->file, pid, 1);
+			err = 0;
 			break;
 		case FIOGETOWN:
 		case SIOCGPGRP:
diff --git a/security/capability.c b/security/capability.c
index a74fde6a7468..d68c57a62bcf 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -343,9 +343,9 @@ static int cap_file_fcntl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
-static int cap_file_set_fowner(struct file *file)
+static void cap_file_set_fowner(struct file *file)
 {
-	return 0;
+	return;
 }
 
 static int cap_file_send_sigiotask(struct task_struct *tsk,
diff --git a/security/security.c b/security/security.c
index e41b1a8d7644..18b35c63fc0c 100644
--- a/security/security.c
+++ b/security/security.c
@@ -775,9 +775,9 @@ int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 	return security_ops->file_fcntl(file, cmd, arg);
 }
 
-int security_file_set_fowner(struct file *file)
+void security_file_set_fowner(struct file *file)
 {
-	return security_ops->file_set_fowner(file);
+	security_ops->file_set_fowner(file);
 }
 
 int security_file_send_sigiotask(struct task_struct *tsk,
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b0e940497e23..ada0d0bf3463 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3346,14 +3346,12 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd,
 	return err;
 }
 
-static int selinux_file_set_fowner(struct file *file)
+static void selinux_file_set_fowner(struct file *file)
 {
 	struct file_security_struct *fsec;
 
 	fsec = file->f_security;
 	fsec->fown_sid = current_sid();
-
-	return 0;
 }
 
 static int selinux_file_send_sigiotask(struct task_struct *tsk,
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index e6ab307ce86e..69e5635d89e5 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1390,12 +1390,11 @@ static int smack_mmap_file(struct file *file,
  * Returns 0
  * Further research may be required on this one.
  */
-static int smack_file_set_fowner(struct file *file)
+static void smack_file_set_fowner(struct file *file)
 {
 	struct smack_known *skp = smk_of_current();
 
 	file->f_security = skp->smk_known;
-	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 2ae4c673e3cbd69bc2decf6d7f5961f3c7b9b38b Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Tue, 2 Sep 2014 15:43:52 -0700
Subject: f2fs: retain inconsistency information to initiate fsck.f2fs

This patch adds sbi->need_fsck to conduct fsck.f2fs later.
This flag can only be removed by fsck.f2fs.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c    | 3 +++
 fs/f2fs/f2fs.h          | 1 +
 fs/f2fs/super.c         | 1 +
 include/linux/f2fs_fs.h | 1 +
 4 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index cb5cb4ca1814..5af97d99106e 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -882,6 +882,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	else
 		clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 
+	if (sbi->need_fsck)
+		set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+
 	/* update SIT/NAT bitmap */
 	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
 	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 222ff5b4d1e1..210c62df08c3 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -434,6 +434,7 @@ struct f2fs_sb_info {
 	struct buffer_head *raw_super_buf;	/* buffer head of raw sb */
 	struct f2fs_super_block *raw_super;	/* raw super block pointer */
 	int s_dirty;				/* dirty flag for checkpoint */
+	bool need_fsck;				/* need fsck.f2fs to fix */
 
 	/* for node-related operations */
 	struct f2fs_nm_info *nm_info;		/* node manager */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 41bdf511003d..a6923041f41a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -849,6 +849,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 		atomic_set(&sbi->nr_pages[i], 0);
 
 	sbi->dir_level = DEF_DIR_LEVEL;
+	sbi->need_fsck = false;
 }
 
 /*
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 08ed2b0a96e6..9ca1ff3d4662 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -85,6 +85,7 @@ struct f2fs_super_block {
 /*
  * For checkpoint
  */
+#define CP_FSCK_FLAG		0x00000010
 #define CP_ERROR_FLAG		0x00000008
 #define CP_COMPACT_SUM_FLAG	0x00000004
 #define CP_ORPHAN_PRESENT_FLAG	0x00000002
-- 
cgit v1.2.3


From a8a76f563cfa1a4e47b6d8b2bef9c0d44a3fd7b0 Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Date: Mon, 18 Aug 2014 10:32:59 +0200
Subject: clk: max77686: Add DT include for MAX77686 PMIC clock

This patch adds a dt-binding include for Maxim 77686
PMIC clock IDs that can be used by both the max77686
clock driver and Device Tree source files.

Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Reviewed-by: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 drivers/clk/clk-max77686.c                 |  7 +------
 include/dt-bindings/clock/maxim,max77686.h | 23 +++++++++++++++++++++++
 2 files changed, 24 insertions(+), 6 deletions(-)
 create mode 100644 include/dt-bindings/clock/maxim,max77686.h

(limited to 'include')

diff --git a/drivers/clk/clk-max77686.c b/drivers/clk/clk-max77686.c
index 3d7e8dd8fd58..185b611c957e 100644
--- a/drivers/clk/clk-max77686.c
+++ b/drivers/clk/clk-max77686.c
@@ -30,12 +30,7 @@
 #include <linux/mutex.h>
 #include <linux/clkdev.h>
 
-enum {
-	MAX77686_CLK_AP = 0,
-	MAX77686_CLK_CP,
-	MAX77686_CLK_PMIC,
-	MAX77686_CLKS_NUM,
-};
+#include <dt-bindings/clock/maxim,max77686.h>
 
 struct max77686_clk {
 	struct max77686_dev *iodev;
diff --git a/include/dt-bindings/clock/maxim,max77686.h b/include/dt-bindings/clock/maxim,max77686.h
new file mode 100644
index 000000000000..7b28b0905869
--- /dev/null
+++ b/include/dt-bindings/clock/maxim,max77686.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2014 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Device Tree binding constants clocks for the Maxim 77686 PMIC.
+ */
+
+#ifndef _DT_BINDINGS_CLOCK_MAXIM_MAX77686_CLOCK_H
+#define _DT_BINDINGS_CLOCK_MAXIM_MAX77686_CLOCK_H
+
+/* Fixed rate clocks. */
+
+#define MAX77686_CLK_AP		0
+#define MAX77686_CLK_CP		1
+#define MAX77686_CLK_PMIC	2
+
+/* Total number of clocks. */
+#define MAX77686_CLKS_NUM		(MAX77686_CLK_PMIC + 1)
+
+#endif /* _DT_BINDINGS_CLOCK_MAXIM_MAX77686_CLOCK_H */
-- 
cgit v1.2.3


From 83ccf16cb9247b6b657637c31e4c2035fe64ae64 Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Date: Mon, 18 Aug 2014 10:33:03 +0200
Subject: clk: Add driver for Maxim 77802 PMIC clocks

The MAX77802 PMIC has two 32.768kHz Buffered Clock Outputs with
Low Jitter Mode. This patch adds support for these two clocks.

Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 drivers/clk/Kconfig                        |  7 +++
 drivers/clk/Makefile                       |  1 +
 drivers/clk/clk-max77802.c                 | 98 ++++++++++++++++++++++++++++++
 include/dt-bindings/clock/maxim,max77802.h | 22 +++++++
 4 files changed, 128 insertions(+)
 create mode 100644 drivers/clk/clk-max77802.c
 create mode 100644 include/dt-bindings/clock/maxim,max77802.h

(limited to 'include')

diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index d68b14b3c0e6..85131ae0b288 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -42,6 +42,13 @@ config COMMON_CLK_MAX77686
 	---help---
 	  This driver supports Maxim 77686 crystal oscillator clock. 
 
+config COMMON_CLK_MAX77802
+	tristate "Clock driver for Maxim 77802 PMIC"
+	depends on MFD_MAX77686
+	select COMMON_CLK_MAX_GEN
+	---help---
+	  This driver supports Maxim 77802 crystal oscillator clock.
+
 config COMMON_CLK_SI5351
 	tristate "Clock driver for SiLabs 5351A/B/C"
 	depends on I2C
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 9de85f689ff5..27c542ba9e73 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_ARCH_HIGHBANK)		+= clk-highbank.o
 obj-$(CONFIG_MACH_LOONGSON1)		+= clk-ls1x.o
 obj-$(CONFIG_COMMON_CLK_MAX_GEN)	+= clk-max-gen.o
 obj-$(CONFIG_COMMON_CLK_MAX77686)	+= clk-max77686.o
+obj-$(CONFIG_COMMON_CLK_MAX77802)	+= clk-max77802.o
 obj-$(CONFIG_ARCH_MOXART)		+= clk-moxart.o
 obj-$(CONFIG_ARCH_NOMADIK)		+= clk-nomadik.o
 obj-$(CONFIG_ARCH_NSPIRE)		+= clk-nspire.o
diff --git a/drivers/clk/clk-max77802.c b/drivers/clk/clk-max77802.c
new file mode 100644
index 000000000000..8e480c5c2945
--- /dev/null
+++ b/drivers/clk/clk-max77802.c
@@ -0,0 +1,98 @@
+/*
+ * clk-max77802.c - Clock driver for Maxim 77802
+ *
+ * Copyright (C) 2014 Google, Inc
+ *
+ * Copyright (C) 2012 Samsung Electornics
+ * Jonghwa Lee <jonghwa3.lee@samsung.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * This driver is based on clk-max77686.c
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/max77686-private.h>
+#include <linux/clk-provider.h>
+#include <linux/mutex.h>
+#include <linux/clkdev.h>
+
+#include <dt-bindings/clock/maxim,max77802.h>
+#include "clk-max-gen.h"
+
+#define MAX77802_CLOCK_OPMODE_MASK	0x1
+#define MAX77802_CLOCK_LOW_JITTER_SHIFT 0x3
+
+static struct clk_init_data max77802_clks_init[MAX77802_CLKS_NUM] = {
+	[MAX77802_CLK_32K_AP] = {
+		.name = "32khz_ap",
+		.ops = &max_gen_clk_ops,
+		.flags = CLK_IS_ROOT,
+	},
+	[MAX77802_CLK_32K_CP] = {
+		.name = "32khz_cp",
+		.ops = &max_gen_clk_ops,
+		.flags = CLK_IS_ROOT,
+	},
+};
+
+static int max77802_clk_probe(struct platform_device *pdev)
+{
+	struct max77686_dev *iodev = dev_get_drvdata(pdev->dev.parent);
+	int ret;
+
+	ret = max_gen_clk_probe(pdev, iodev->regmap, MAX77802_REG_32KHZ,
+				max77802_clks_init, MAX77802_CLKS_NUM);
+
+	if (ret) {
+		dev_err(&pdev->dev, "generic probe failed %d\n", ret);
+		return ret;
+	}
+
+	/* Enable low-jitter mode on the 32khz clocks. */
+	ret = regmap_update_bits(iodev->regmap, MAX77802_REG_32KHZ,
+				 1 << MAX77802_CLOCK_LOW_JITTER_SHIFT,
+				 1 << MAX77802_CLOCK_LOW_JITTER_SHIFT);
+	if (ret < 0)
+		dev_err(&pdev->dev, "failed to enable low-jitter mode\n");
+
+	return ret;
+}
+
+static int max77802_clk_remove(struct platform_device *pdev)
+{
+	return max_gen_clk_remove(pdev, MAX77802_CLKS_NUM);
+}
+
+static const struct platform_device_id max77802_clk_id[] = {
+	{ "max77802-clk", 0},
+	{ },
+};
+MODULE_DEVICE_TABLE(platform, max77802_clk_id);
+
+static struct platform_driver max77802_clk_driver = {
+	.driver = {
+		.name  = "max77802-clk",
+		.owner = THIS_MODULE,
+	},
+	.probe = max77802_clk_probe,
+	.remove = max77802_clk_remove,
+	.id_table = max77802_clk_id,
+};
+
+module_platform_driver(max77802_clk_driver);
+
+MODULE_DESCRIPTION("MAXIM 77802 Clock Driver");
+MODULE_AUTHOR("Javier Martinez Canillas <javier.martinez@collabora.co.uk>");
+MODULE_LICENSE("GPL");
diff --git a/include/dt-bindings/clock/maxim,max77802.h b/include/dt-bindings/clock/maxim,max77802.h
new file mode 100644
index 000000000000..997312edcbb5
--- /dev/null
+++ b/include/dt-bindings/clock/maxim,max77802.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2014 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Device Tree binding constants clocks for the Maxim 77802 PMIC.
+ */
+
+#ifndef _DT_BINDINGS_CLOCK_MAXIM_MAX77802_CLOCK_H
+#define _DT_BINDINGS_CLOCK_MAXIM_MAX77802_CLOCK_H
+
+/* Fixed rate clocks. */
+
+#define MAX77802_CLK_32K_AP		0
+#define MAX77802_CLK_32K_CP		1
+
+/* Total number of clocks. */
+#define MAX77802_CLKS_NUM		(MAX77802_CLK_32K_CP + 1)
+
+#endif /* _DT_BINDINGS_CLOCK_MAXIM_MAX77802_CLOCK_H */
-- 
cgit v1.2.3


From 87354059881ce9315181604dc17076c535f4d744 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 22 Jul 2014 20:41:42 -0400
Subject: ftrace: Add helper function ftrace_ops_get_func()

Add the helper function to what the mcount trampoline is to call
for a ftrace_ops function. This helper will be used by arch code
in the future to set up dynamic trampolines. But as this does the
same tests that are performed in choosing what function to call for
the default mcount trampoline, might as well use it to clean up
the existing code.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  2 ++
 kernel/trace/ftrace.c  | 47 +++++++++++++++++++++++++++++++++++------------
 2 files changed, 37 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f0b0edbf55a9..ef37286547fc 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -56,6 +56,8 @@ struct ftrace_ops;
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
 			      struct ftrace_ops *op, struct pt_regs *regs);
 
+ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
+
 /*
  * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
  * set in the flags member.
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 17b606362ab4..dabf734f909c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -259,20 +259,12 @@ static void update_ftrace_function(void)
 	 * then have the mcount trampoline call the function directly.
 	 */
 	if (ftrace_ops_list == &ftrace_list_end ||
-	    (ftrace_ops_list->next == &ftrace_list_end &&
-	     !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) &&
-	     !FTRACE_FORCE_LIST_FUNC)) {
+	    (ftrace_ops_list->next == &ftrace_list_end)) {
+
 		/* Set the ftrace_ops that the arch callback uses */
 		set_function_trace_op = ftrace_ops_list;
-		/*
-		 * If the func handles its own recursion, call it directly.
-		 * Otherwise call the recursion protected function that
-		 * will call the ftrace ops function.
-		 */
-		if (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE)
-			func = ftrace_ops_list->func;
-		else
-			func = ftrace_ops_recurs_func;
+
+		func = ftrace_ops_get_func(ftrace_ops_list);
 	} else {
 		/* Just use the default ftrace_ops */
 		set_function_trace_op = &ftrace_list_end;
@@ -4856,6 +4848,37 @@ static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip,
 	trace_clear_recursion(bit);
 }
 
+/**
+ * ftrace_ops_get_func - get the function a trampoline should call
+ * @ops: the ops to get the function for
+ *
+ * Normally the mcount trampoline will call the ops->func, but there
+ * are times that it should not. For example, if the ops does not
+ * have its own recursion protection, then it should call the
+ * ftrace_ops_recurs_func() instead.
+ *
+ * Returns the function that the trampoline should call for @ops.
+ */
+ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
+{
+	/*
+	 * If this is a dynamic ops or we force list func,
+	 * then it needs to call the list anyway.
+	 */
+	if (ops->flags & FTRACE_OPS_FL_DYNAMIC || FTRACE_FORCE_LIST_FUNC)
+		return ftrace_ops_list_func;
+
+	/*
+	 * If the func handles its own recursion, call it directly.
+	 * Otherwise call the recursion protected function that
+	 * will call the ftrace ops function.
+	 */
+	if (!(ops->flags & FTRACE_OPS_FL_RECURSION_SAFE))
+		return ftrace_ops_recurs_func;
+
+	return ops->func;
+}
+
 static void clear_ftrace_swapper(void)
 {
 	struct task_struct *p;
-- 
cgit v1.2.3


From 738cbe72adc5c8f2016c4c68aa5162631d4f27e1 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 8 Sep 2014 08:04:47 +0200
Subject: net: bpf: consolidate JIT binary allocator

Introduced in commit 314beb9bcabf ("x86: bpf_jit_comp: secure bpf jit
against spraying attacks") and later on replicated in aa2d2c73c21f
("s390/bpf,jit: address randomize and write protect jit code") for
s390 architecture, write protection for BPF JIT images got added and
a random start address of the JIT code, so that it's not on a page
boundary anymore.

Since both use a very similar allocator for the BPF binary header,
we can consolidate this code into the BPF core as it's mostly JIT
independant anyway.

This will also allow for future archs that support DEBUG_SET_MODULE_RONX
to just reuse instead of reimplementing it.

JIT tested on x86_64 and s390x with BPF test suite.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/s390/net/bpf_jit_comp.c | 45 ++++++++-------------------------------
 arch/x86/net/bpf_jit_comp.c  | 50 ++++++++++----------------------------------
 include/linux/filter.h       | 13 ++++++++++++
 kernel/bpf/core.c            | 39 ++++++++++++++++++++++++++++++++++
 4 files changed, 72 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index f2833c5b218a..b734f975c22e 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -5,11 +5,9 @@
  *
  * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  */
-#include <linux/moduleloader.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/filter.h>
-#include <linux/random.h>
 #include <linux/init.h>
 #include <asm/cacheflush.h>
 #include <asm/facility.h>
@@ -148,6 +146,12 @@ struct bpf_jit {
 	ret;						\
 })
 
+static void bpf_jit_fill_hole(void *area, unsigned int size)
+{
+	/* Fill whole space with illegal instructions */
+	memset(area, 0, size);
+}
+
 static void bpf_jit_prologue(struct bpf_jit *jit)
 {
 	/* Save registers and create stack frame if necessary */
@@ -780,38 +784,6 @@ out:
 	return -1;
 }
 
-/*
- * Note: for security reasons, bpf code will follow a randomly
- *	 sized amount of illegal instructions.
- */
-struct bpf_binary_header {
-	unsigned int pages;
-	u8 image[];
-};
-
-static struct bpf_binary_header *bpf_alloc_binary(unsigned int bpfsize,
-						  u8 **image_ptr)
-{
-	struct bpf_binary_header *header;
-	unsigned int sz, hole;
-
-	/* Most BPF filters are really small, but if some of them fill a page,
-	 * allow at least 128 extra bytes for illegal instructions.
-	 */
-	sz = round_up(bpfsize + sizeof(*header) + 128, PAGE_SIZE);
-	header = module_alloc(sz);
-	if (!header)
-		return NULL;
-	memset(header, 0, sz);
-	header->pages = sz / PAGE_SIZE;
-	hole = min(sz - (bpfsize + sizeof(*header)), PAGE_SIZE - sizeof(*header));
-	/* Insert random number of illegal instructions before BPF code
-	 * and make sure the first instruction starts at an even address.
-	 */
-	*image_ptr = &header->image[(prandom_u32() % hole) & -2];
-	return header;
-}
-
 void bpf_jit_compile(struct bpf_prog *fp)
 {
 	struct bpf_binary_header *header = NULL;
@@ -850,7 +822,8 @@ void bpf_jit_compile(struct bpf_prog *fp)
 			size = prg_len + lit_len;
 			if (size >= BPF_SIZE_MAX)
 				goto out;
-			header = bpf_alloc_binary(size, &jit.start);
+			header = bpf_jit_binary_alloc(size, &jit.start,
+						      2, bpf_jit_fill_hole);
 			if (!header)
 				goto out;
 			jit.prg = jit.mid = jit.start + prg_len;
@@ -884,7 +857,7 @@ void bpf_jit_free(struct bpf_prog *fp)
 		goto free_filter;
 
 	set_memory_rw(addr, header->pages);
-	module_free(NULL, header);
+	bpf_jit_binary_free(header);
 
 free_filter:
 	bpf_prog_unlock_free(fp);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 06f8c17f5484..9de0b5476b0c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -8,12 +8,10 @@
  * as published by the Free Software Foundation; version 2
  * of the License.
  */
-#include <linux/moduleloader.h>
-#include <asm/cacheflush.h>
 #include <linux/netdevice.h>
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
-#include <linux/random.h>
+#include <asm/cacheflush.h>
 
 int bpf_jit_enable __read_mostly;
 
@@ -109,39 +107,6 @@ static inline void bpf_flush_icache(void *start, void *end)
 #define CHOOSE_LOAD_FUNC(K, func) \
 	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
-struct bpf_binary_header {
-	unsigned int	pages;
-	/* Note : for security reasons, bpf code will follow a randomly
-	 * sized amount of int3 instructions
-	 */
-	u8		image[];
-};
-
-static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen,
-						  u8 **image_ptr)
-{
-	unsigned int sz, hole;
-	struct bpf_binary_header *header;
-
-	/* Most of BPF filters are really small,
-	 * but if some of them fill a page, allow at least
-	 * 128 extra bytes to insert a random section of int3
-	 */
-	sz = round_up(proglen + sizeof(*header) + 128, PAGE_SIZE);
-	header = module_alloc(sz);
-	if (!header)
-		return NULL;
-
-	memset(header, 0xcc, sz); /* fill whole space with int3 instructions */
-
-	header->pages = sz / PAGE_SIZE;
-	hole = min(sz - (proglen + sizeof(*header)), PAGE_SIZE - sizeof(*header));
-
-	/* insert a random number of int3 instructions before BPF code */
-	*image_ptr = &header->image[prandom_u32() % hole];
-	return header;
-}
-
 /* pick a register outside of BPF range for JIT internal work */
 #define AUX_REG (MAX_BPF_REG + 1)
 
@@ -206,6 +171,12 @@ static inline u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
 	return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
 }
 
+static void jit_fill_hole(void *area, unsigned int size)
+{
+	/* fill whole space with int3 instructions */
+	memset(area, 0xcc, size);
+}
+
 struct jit_context {
 	unsigned int cleanup_addr; /* epilogue code offset */
 	bool seen_ld_abs;
@@ -959,7 +930,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 		if (proglen <= 0) {
 			image = NULL;
 			if (header)
-				module_free(NULL, header);
+				bpf_jit_binary_free(header);
 			goto out;
 		}
 		if (image) {
@@ -969,7 +940,8 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 			break;
 		}
 		if (proglen == oldproglen) {
-			header = bpf_alloc_binary(proglen, &image);
+			header = bpf_jit_binary_alloc(proglen, &image,
+						      1, jit_fill_hole);
 			if (!header)
 				goto out;
 		}
@@ -998,7 +970,7 @@ void bpf_jit_free(struct bpf_prog *fp)
 		goto free_filter;
 
 	set_memory_rw(addr, header->pages);
-	module_free(NULL, header);
+	bpf_jit_binary_free(header);
 
 free_filter:
 	bpf_prog_unlock_free(fp);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 8f82ef3f1cdd..868764fcffb8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -289,6 +289,11 @@ struct sock_fprog_kern {
 	struct sock_filter	*filter;
 };
 
+struct bpf_binary_header {
+	unsigned int pages;
+	u8 image[];
+};
+
 struct bpf_work_struct {
 	struct bpf_prog *prog;
 	struct work_struct work;
@@ -358,6 +363,14 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags);
 void __bpf_prog_free(struct bpf_prog *fp);
 
+typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
+
+struct bpf_binary_header *
+bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
+		     unsigned int alignment,
+		     bpf_jit_fill_hole_t bpf_fill_ill_insns);
+void bpf_jit_binary_free(struct bpf_binary_header *hdr);
+
 static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
 {
 	bpf_prog_unlock_ro(fp);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2c2bfaacce66..8ee520f0ec70 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -20,9 +20,12 @@
  * Andi Kleen - Fix a few bad bugs and races.
  * Kris Katterjohn - Added many additional checks in bpf_check_classic()
  */
+
 #include <linux/filter.h>
 #include <linux/skbuff.h>
 #include <linux/vmalloc.h>
+#include <linux/random.h>
+#include <linux/moduleloader.h>
 #include <asm/unaligned.h>
 
 /* Registers */
@@ -125,6 +128,42 @@ void __bpf_prog_free(struct bpf_prog *fp)
 }
 EXPORT_SYMBOL_GPL(__bpf_prog_free);
 
+struct bpf_binary_header *
+bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
+		     unsigned int alignment,
+		     bpf_jit_fill_hole_t bpf_fill_ill_insns)
+{
+	struct bpf_binary_header *hdr;
+	unsigned int size, hole, start;
+
+	/* Most of BPF filters are really small, but if some of them
+	 * fill a page, allow at least 128 extra bytes to insert a
+	 * random section of illegal instructions.
+	 */
+	size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE);
+	hdr = module_alloc(size);
+	if (hdr == NULL)
+		return NULL;
+
+	/* Fill space with illegal/arch-dep instructions. */
+	bpf_fill_ill_insns(hdr, size);
+
+	hdr->pages = size / PAGE_SIZE;
+	hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
+		     PAGE_SIZE - sizeof(*hdr));
+	start = (prandom_u32() % hole) & ~(alignment - 1);
+
+	/* Leave a random number of instructions before BPF code. */
+	*image_ptr = &hdr->image[start];
+
+	return hdr;
+}
+
+void bpf_jit_binary_free(struct bpf_binary_header *hdr)
+{
+	module_free(NULL, hdr);
+}
+
 /* Base function for offset calculation. Needs to go into .text section,
  * therefore keeping it non-static as well; will also be used by JITs
  * anyway later on, so do not let the compiler omit it.
-- 
cgit v1.2.3


From 286aad3c4014ca825c447e07e24f8929e6d266d2 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 8 Sep 2014 08:04:49 +0200
Subject: net: bpf: be friendly to kmemcheck

Reported by Mikulas Patocka, kmemcheck currently barks out a
false positive since we don't have special kmemcheck annotation
for bitfields used in bpf_prog structure.

We currently have jited:1, len:31 and thus when accessing len
while CONFIG_KMEMCHECK enabled, kmemcheck throws a warning that
we're reading uninitialized memory.

As we don't need the whole bit universe for pages member, we
can just split it to u16 and use a bool flag for jited instead
of a bitfield.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/net/bpf_jit_32.c       | 2 +-
 arch/mips/net/bpf_jit.c         | 2 +-
 arch/powerpc/net/bpf_jit_comp.c | 2 +-
 arch/s390/net/bpf_jit_comp.c    | 2 +-
 arch/sparc/net/bpf_jit_comp.c   | 2 +-
 arch/x86/net/bpf_jit_comp.c     | 2 +-
 include/linux/filter.h          | 6 +++---
 net/core/filter.c               | 2 +-
 8 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 2d1a5b93d91c..6b45f649eff0 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -933,7 +933,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 
 	set_memory_ro((unsigned long)header, header->pages);
 	fp->bpf_func = (void *)ctx.target;
-	fp->jited = 1;
+	fp->jited = true;
 out:
 	kfree(ctx.offsets);
 	return;
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index cfa83cf2447d..0e97ccd29fe3 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -1417,7 +1417,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 		bpf_jit_dump(fp->len, alloc_size, 2, ctx.target);
 
 	fp->bpf_func = (void *)ctx.target;
-	fp->jited = 1;
+	fp->jited = true;
 
 out:
 	kfree(ctx.offsets);
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 40c53ff59124..cbae2dfd053c 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -686,7 +686,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 		((u64 *)image)[0] = (u64)code_base;
 		((u64 *)image)[1] = local_paca->kernel_toc;
 		fp->bpf_func = (void *)image;
-		fp->jited = 1;
+		fp->jited = true;
 	}
 out:
 	kfree(addrs);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index b734f975c22e..555f5c7e83ab 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -842,7 +842,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 	if (jit.start) {
 		set_memory_ro((unsigned long)header, header->pages);
 		fp->bpf_func = (void *) jit.start;
-		fp->jited = 1;
+		fp->jited = true;
 	}
 out:
 	kfree(addrs);
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index f7a736b645e8..b2ad9dc5425e 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -801,7 +801,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 	if (image) {
 		bpf_flush_icache(image, image + proglen);
 		fp->bpf_func = (void *)image;
-		fp->jited = 1;
+		fp->jited = true;
 	}
 out:
 	kfree(addrs);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 9de0b5476b0c..d56cd1f515bd 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -955,7 +955,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 		bpf_flush_icache(header, image + proglen);
 		set_memory_ro((unsigned long)header, header->pages);
 		prog->bpf_func = (void *)image;
-		prog->jited = 1;
+		prog->jited = true;
 	}
 out:
 	kfree(addrs);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 868764fcffb8..4b59edead908 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -300,9 +300,9 @@ struct bpf_work_struct {
 };
 
 struct bpf_prog {
-	u32			pages;		/* Number of allocated pages */
-	u32			jited:1,	/* Is our filter JIT'ed? */
-				len:31;		/* Number of filter blocks */
+	u16			pages;		/* Number of allocated pages */
+	bool			jited;		/* Is our filter JIT'ed? */
+	u32			len;		/* Number of filter blocks */
 	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
 	struct bpf_work_struct	*work;		/* Deferred free work struct */
 	unsigned int		(*bpf_func)(const struct sk_buff *skb,
diff --git a/net/core/filter.c b/net/core/filter.c
index fa5b7d0f77ac..dfc716ffa44b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -972,7 +972,7 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp)
 	int err;
 
 	fp->bpf_func = NULL;
-	fp->jited = 0;
+	fp->jited = false;
 
 	err = bpf_check_classic(fp->insns, fp->len);
 	if (err) {
-- 
cgit v1.2.3


From 67cc0d4077951295f42bed63805e91b46c24477b Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 8 Sep 2014 19:58:58 -0400
Subject: net-timestamp: optimize sock_tx_timestamp default path

Few packets have timestamping enabled. Exit sock_tx_timestamp quickly
in this common case.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 10 +++++++++-
 net/socket.c       |  7 ++-----
 2 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 049ab1b732a6..515a4d01e932 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2199,6 +2199,8 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 		sk->sk_stamp = skb->tstamp;
 }
 
+void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags);
+
 /**
  * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
  * @sk:		socket sending this packet
@@ -2206,7 +2208,13 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
  *
  * Note : callers should take care of initial *tx_flags value (usually 0)
  */
-void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags);
+static inline void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
+{
+	if (unlikely(sk->sk_tsflags))
+		__sock_tx_timestamp(sk, tx_flags);
+	if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS)))
+		*tx_flags |= SKBTX_WIFI_STATUS;
+}
 
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
diff --git a/net/socket.c b/net/socket.c
index 2e2586e2dee1..d40f522541aa 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -610,7 +610,7 @@ void sock_release(struct socket *sock)
 }
 EXPORT_SYMBOL(sock_release);
 
-void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
+void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
 {
 	u8 flags = *tx_flags;
 
@@ -626,12 +626,9 @@ void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)
 		flags |= SKBTX_ACK_TSTAMP;
 
-	if (sock_flag(sk, SOCK_WIFI_STATUS))
-		flags |= SKBTX_WIFI_STATUS;
-
 	*tx_flags = flags;
 }
-EXPORT_SYMBOL(sock_tx_timestamp);
+EXPORT_SYMBOL(__sock_tx_timestamp);
 
 static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock,
 				       struct msghdr *msg, size_t size)
-- 
cgit v1.2.3


From 9f50bd8905ab12e3e8ebffd8296d7921bd3976eb Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:27 +0200
Subject: drm/radeon: move drm_buffer to drm/radeon/

Radeon UMS is the last user of drm_buffer. Move it out of sight so radeon
can drop it together with UMS.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/Makefile              |   2 +-
 drivers/gpu/drm/drm_buffer.c          | 181 ----------------------------------
 drivers/gpu/drm/radeon/Makefile       |   2 +-
 drivers/gpu/drm/radeon/drm_buffer.c   | 177 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/radeon/drm_buffer.h   | 148 +++++++++++++++++++++++++++
 drivers/gpu/drm/radeon/r300_cmdbuf.c  |   2 +-
 drivers/gpu/drm/radeon/radeon_state.c |   2 +-
 include/drm/drm_buffer.h              | 148 ---------------------------
 8 files changed, 329 insertions(+), 333 deletions(-)
 delete mode 100644 drivers/gpu/drm/drm_buffer.c
 create mode 100644 drivers/gpu/drm/radeon/drm_buffer.c
 create mode 100644 drivers/gpu/drm/radeon/drm_buffer.h
 delete mode 100644 include/drm/drm_buffer.h

(limited to 'include')

diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 4a55d59ccd22..9b7cb3f76f01 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -4,7 +4,7 @@
 
 ccflags-y := -Iinclude/drm
 
-drm-y       :=	drm_auth.o drm_buffer.o drm_bufs.o drm_cache.o \
+drm-y       :=	drm_auth.o drm_bufs.o drm_cache.o \
 		drm_context.o drm_dma.o \
 		drm_fops.o drm_gem.o drm_ioctl.o drm_irq.o \
 		drm_lock.o drm_memory.o drm_drv.o drm_vm.o \
diff --git a/drivers/gpu/drm/drm_buffer.c b/drivers/gpu/drm/drm_buffer.c
deleted file mode 100644
index 86a4a4a60afc..000000000000
--- a/drivers/gpu/drm/drm_buffer.c
+++ /dev/null
@@ -1,181 +0,0 @@
-/**************************************************************************
- *
- * Copyright 2010 Pauli Nieminen.
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the
- * "Software"), to deal in the Software without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sub license, and/or sell copies of the Software, and to
- * permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice (including the
- * next paragraph) shall be included in all copies or substantial portions
- * of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
- * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
- * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
- * USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- *
- **************************************************************************/
-/*
- * Multipart buffer for coping data which is larger than the page size.
- *
- * Authors:
- * Pauli Nieminen <suokkos-at-gmail-dot-com>
- */
-
-#include <linux/export.h>
-#include <drm/drm_buffer.h>
-
-/**
- * Allocate the drm buffer object.
- *
- *   buf: Pointer to a pointer where the object is stored.
- *   size: The number of bytes to allocate.
- */
-int drm_buffer_alloc(struct drm_buffer **buf, int size)
-{
-	int nr_pages = size / PAGE_SIZE + 1;
-	int idx;
-
-	/* Allocating pointer table to end of structure makes drm_buffer
-	 * variable sized */
-	*buf = kzalloc(sizeof(struct drm_buffer) + nr_pages*sizeof(char *),
-			GFP_KERNEL);
-
-	if (*buf == NULL) {
-		DRM_ERROR("Failed to allocate drm buffer object to hold"
-				" %d bytes in %d pages.\n",
-				size, nr_pages);
-		return -ENOMEM;
-	}
-
-	(*buf)->size = size;
-
-	for (idx = 0; idx < nr_pages; ++idx) {
-
-		(*buf)->data[idx] =
-			kmalloc(min(PAGE_SIZE, size - idx * PAGE_SIZE),
-				GFP_KERNEL);
-
-
-		if ((*buf)->data[idx] == NULL) {
-			DRM_ERROR("Failed to allocate %dth page for drm"
-					" buffer with %d bytes and %d pages.\n",
-					idx + 1, size, nr_pages);
-			goto error_out;
-		}
-
-	}
-
-	return 0;
-
-error_out:
-
-	for (; idx >= 0; --idx)
-		kfree((*buf)->data[idx]);
-
-	kfree(*buf);
-	return -ENOMEM;
-}
-EXPORT_SYMBOL(drm_buffer_alloc);
-
-/**
- * Copy the user data to the begin of the buffer and reset the processing
- * iterator.
- *
- *   user_data: A pointer the data that is copied to the buffer.
- *   size: The Number of bytes to copy.
- */
-int drm_buffer_copy_from_user(struct drm_buffer *buf,
-			      void __user *user_data, int size)
-{
-	int nr_pages = size / PAGE_SIZE + 1;
-	int idx;
-
-	if (size > buf->size) {
-		DRM_ERROR("Requesting to copy %d bytes to a drm buffer with"
-				" %d bytes space\n",
-				size, buf->size);
-		return -EFAULT;
-	}
-
-	for (idx = 0; idx < nr_pages; ++idx) {
-
-		if (copy_from_user(buf->data[idx],
-			user_data + idx * PAGE_SIZE,
-			min(PAGE_SIZE, size - idx * PAGE_SIZE))) {
-			DRM_ERROR("Failed to copy user data (%p) to drm buffer"
-					" (%p) %dth page.\n",
-					user_data, buf, idx);
-			return -EFAULT;
-
-		}
-	}
-	buf->iterator = 0;
-	return 0;
-}
-EXPORT_SYMBOL(drm_buffer_copy_from_user);
-
-/**
- * Free the drm buffer object
- */
-void drm_buffer_free(struct drm_buffer *buf)
-{
-
-	if (buf != NULL) {
-
-		int nr_pages = buf->size / PAGE_SIZE + 1;
-		int idx;
-		for (idx = 0; idx < nr_pages; ++idx)
-			kfree(buf->data[idx]);
-
-		kfree(buf);
-	}
-}
-EXPORT_SYMBOL(drm_buffer_free);
-
-/**
- * Read an object from buffer that may be split to multiple parts. If object
- * is not split function just returns the pointer to object in buffer. But in
- * case of split object data is copied to given stack object that is suplied
- * by caller.
- *
- * The processing location of the buffer is also advanced to the next byte
- * after the object.
- *
- *   objsize: The size of the objet in bytes.
- *   stack_obj: A pointer to a memory location where object can be copied.
- */
-void *drm_buffer_read_object(struct drm_buffer *buf,
-		int objsize, void *stack_obj)
-{
-	int idx = drm_buffer_index(buf);
-	int page = drm_buffer_page(buf);
-	void *obj = NULL;
-
-	if (idx + objsize <= PAGE_SIZE) {
-		obj = &buf->data[page][idx];
-	} else {
-		/* The object is split which forces copy to temporary object.*/
-		int beginsz = PAGE_SIZE - idx;
-		memcpy(stack_obj, &buf->data[page][idx], beginsz);
-
-		memcpy(stack_obj + beginsz, &buf->data[page + 1][0],
-				objsize - beginsz);
-
-		obj = stack_obj;
-	}
-
-	drm_buffer_advance(buf, objsize);
-	return obj;
-}
-EXPORT_SYMBOL(drm_buffer_read_object);
diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index 357f09afd222..7d7aed5357f0 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -60,7 +60,7 @@ radeon-y := radeon_drv.o
 
 # add UMS driver
 radeon-$(CONFIG_DRM_RADEON_UMS)+= radeon_cp.o radeon_state.o radeon_mem.o \
-	radeon_irq.o r300_cmdbuf.o r600_cp.o r600_blit.o
+	radeon_irq.o r300_cmdbuf.o r600_cp.o r600_blit.o drm_buffer.o
 
 # add KMS driver
 radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
diff --git a/drivers/gpu/drm/radeon/drm_buffer.c b/drivers/gpu/drm/radeon/drm_buffer.c
new file mode 100644
index 000000000000..f4e0f3a3d7b1
--- /dev/null
+++ b/drivers/gpu/drm/radeon/drm_buffer.c
@@ -0,0 +1,177 @@
+/**************************************************************************
+ *
+ * Copyright 2010 Pauli Nieminen.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ *
+ **************************************************************************/
+/*
+ * Multipart buffer for coping data which is larger than the page size.
+ *
+ * Authors:
+ * Pauli Nieminen <suokkos-at-gmail-dot-com>
+ */
+
+#include <linux/export.h>
+#include "drm_buffer.h"
+
+/**
+ * Allocate the drm buffer object.
+ *
+ *   buf: Pointer to a pointer where the object is stored.
+ *   size: The number of bytes to allocate.
+ */
+int drm_buffer_alloc(struct drm_buffer **buf, int size)
+{
+	int nr_pages = size / PAGE_SIZE + 1;
+	int idx;
+
+	/* Allocating pointer table to end of structure makes drm_buffer
+	 * variable sized */
+	*buf = kzalloc(sizeof(struct drm_buffer) + nr_pages*sizeof(char *),
+			GFP_KERNEL);
+
+	if (*buf == NULL) {
+		DRM_ERROR("Failed to allocate drm buffer object to hold"
+				" %d bytes in %d pages.\n",
+				size, nr_pages);
+		return -ENOMEM;
+	}
+
+	(*buf)->size = size;
+
+	for (idx = 0; idx < nr_pages; ++idx) {
+
+		(*buf)->data[idx] =
+			kmalloc(min(PAGE_SIZE, size - idx * PAGE_SIZE),
+				GFP_KERNEL);
+
+
+		if ((*buf)->data[idx] == NULL) {
+			DRM_ERROR("Failed to allocate %dth page for drm"
+					" buffer with %d bytes and %d pages.\n",
+					idx + 1, size, nr_pages);
+			goto error_out;
+		}
+
+	}
+
+	return 0;
+
+error_out:
+
+	for (; idx >= 0; --idx)
+		kfree((*buf)->data[idx]);
+
+	kfree(*buf);
+	return -ENOMEM;
+}
+
+/**
+ * Copy the user data to the begin of the buffer and reset the processing
+ * iterator.
+ *
+ *   user_data: A pointer the data that is copied to the buffer.
+ *   size: The Number of bytes to copy.
+ */
+int drm_buffer_copy_from_user(struct drm_buffer *buf,
+			      void __user *user_data, int size)
+{
+	int nr_pages = size / PAGE_SIZE + 1;
+	int idx;
+
+	if (size > buf->size) {
+		DRM_ERROR("Requesting to copy %d bytes to a drm buffer with"
+				" %d bytes space\n",
+				size, buf->size);
+		return -EFAULT;
+	}
+
+	for (idx = 0; idx < nr_pages; ++idx) {
+
+		if (copy_from_user(buf->data[idx],
+			user_data + idx * PAGE_SIZE,
+			min(PAGE_SIZE, size - idx * PAGE_SIZE))) {
+			DRM_ERROR("Failed to copy user data (%p) to drm buffer"
+					" (%p) %dth page.\n",
+					user_data, buf, idx);
+			return -EFAULT;
+
+		}
+	}
+	buf->iterator = 0;
+	return 0;
+}
+
+/**
+ * Free the drm buffer object
+ */
+void drm_buffer_free(struct drm_buffer *buf)
+{
+
+	if (buf != NULL) {
+
+		int nr_pages = buf->size / PAGE_SIZE + 1;
+		int idx;
+		for (idx = 0; idx < nr_pages; ++idx)
+			kfree(buf->data[idx]);
+
+		kfree(buf);
+	}
+}
+
+/**
+ * Read an object from buffer that may be split to multiple parts. If object
+ * is not split function just returns the pointer to object in buffer. But in
+ * case of split object data is copied to given stack object that is suplied
+ * by caller.
+ *
+ * The processing location of the buffer is also advanced to the next byte
+ * after the object.
+ *
+ *   objsize: The size of the objet in bytes.
+ *   stack_obj: A pointer to a memory location where object can be copied.
+ */
+void *drm_buffer_read_object(struct drm_buffer *buf,
+		int objsize, void *stack_obj)
+{
+	int idx = drm_buffer_index(buf);
+	int page = drm_buffer_page(buf);
+	void *obj = NULL;
+
+	if (idx + objsize <= PAGE_SIZE) {
+		obj = &buf->data[page][idx];
+	} else {
+		/* The object is split which forces copy to temporary object.*/
+		int beginsz = PAGE_SIZE - idx;
+		memcpy(stack_obj, &buf->data[page][idx], beginsz);
+
+		memcpy(stack_obj + beginsz, &buf->data[page + 1][0],
+				objsize - beginsz);
+
+		obj = stack_obj;
+	}
+
+	drm_buffer_advance(buf, objsize);
+	return obj;
+}
diff --git a/drivers/gpu/drm/radeon/drm_buffer.h b/drivers/gpu/drm/radeon/drm_buffer.h
new file mode 100644
index 000000000000..c80d3a340b94
--- /dev/null
+++ b/drivers/gpu/drm/radeon/drm_buffer.h
@@ -0,0 +1,148 @@
+/**************************************************************************
+ *
+ * Copyright 2010 Pauli Nieminen.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ *
+ **************************************************************************/
+/*
+ * Multipart buffer for coping data which is larger than the page size.
+ *
+ * Authors:
+ * Pauli Nieminen <suokkos-at-gmail-dot-com>
+ */
+
+#ifndef _DRM_BUFFER_H_
+#define _DRM_BUFFER_H_
+
+#include <drm/drmP.h>
+
+struct drm_buffer {
+	int iterator;
+	int size;
+	char *data[];
+};
+
+
+/**
+ * Return the index of page that buffer is currently pointing at.
+ */
+static inline int drm_buffer_page(struct drm_buffer *buf)
+{
+	return buf->iterator / PAGE_SIZE;
+}
+/**
+ * Return the index of the current byte in the page
+ */
+static inline int drm_buffer_index(struct drm_buffer *buf)
+{
+	return buf->iterator & (PAGE_SIZE - 1);
+}
+/**
+ * Return number of bytes that is left to process
+ */
+static inline int drm_buffer_unprocessed(struct drm_buffer *buf)
+{
+	return buf->size - buf->iterator;
+}
+
+/**
+ * Advance the buffer iterator number of bytes that is given.
+ */
+static inline void drm_buffer_advance(struct drm_buffer *buf, int bytes)
+{
+	buf->iterator += bytes;
+}
+
+/**
+ * Allocate the drm buffer object.
+ *
+ *   buf: A pointer to a pointer where the object is stored.
+ *   size: The number of bytes to allocate.
+ */
+extern int drm_buffer_alloc(struct drm_buffer **buf, int size);
+
+/**
+ * Copy the user data to the begin of the buffer and reset the processing
+ * iterator.
+ *
+ *   user_data: A pointer the data that is copied to the buffer.
+ *   size: The Number of bytes to copy.
+ */
+extern int drm_buffer_copy_from_user(struct drm_buffer *buf,
+		void __user *user_data, int size);
+
+/**
+ * Free the drm buffer object
+ */
+extern void drm_buffer_free(struct drm_buffer *buf);
+
+/**
+ * Read an object from buffer that may be split to multiple parts. If object
+ * is not split function just returns the pointer to object in buffer. But in
+ * case of split object data is copied to given stack object that is suplied
+ * by caller.
+ *
+ * The processing location of the buffer is also advanced to the next byte
+ * after the object.
+ *
+ *   objsize: The size of the objet in bytes.
+ *   stack_obj: A pointer to a memory location where object can be copied.
+ */
+extern void *drm_buffer_read_object(struct drm_buffer *buf,
+		int objsize, void *stack_obj);
+
+/**
+ * Returns the pointer to the dword which is offset number of elements from the
+ * current processing location.
+ *
+ * Caller must make sure that dword is not split in the buffer. This
+ * requirement is easily met if all the sizes of objects in buffer are
+ * multiples of dword and PAGE_SIZE is multiple dword.
+ *
+ * Call to this function doesn't change the processing location.
+ *
+ *   offset: The index of the dword relative to the internat iterator.
+ */
+static inline void *drm_buffer_pointer_to_dword(struct drm_buffer *buffer,
+		int offset)
+{
+	int iter = buffer->iterator + offset * 4;
+	return &buffer->data[iter / PAGE_SIZE][iter & (PAGE_SIZE - 1)];
+}
+/**
+ * Returns the pointer to the dword which is offset number of elements from
+ * the current processing location.
+ *
+ * Call to this function doesn't change the processing location.
+ *
+ *   offset: The index of the byte relative to the internat iterator.
+ */
+static inline void *drm_buffer_pointer_to_byte(struct drm_buffer *buffer,
+		int offset)
+{
+	int iter = buffer->iterator + offset;
+	return &buffer->data[iter / PAGE_SIZE][iter & (PAGE_SIZE - 1)];
+}
+
+#endif
diff --git a/drivers/gpu/drm/radeon/r300_cmdbuf.c b/drivers/gpu/drm/radeon/r300_cmdbuf.c
index 84b1d5367a11..9418e388b045 100644
--- a/drivers/gpu/drm/radeon/r300_cmdbuf.c
+++ b/drivers/gpu/drm/radeon/r300_cmdbuf.c
@@ -34,10 +34,10 @@
  */
 
 #include <drm/drmP.h>
-#include <drm/drm_buffer.h>
 #include <drm/radeon_drm.h>
 #include "radeon_drv.h"
 #include "r300_reg.h"
+#include "drm_buffer.h"
 
 #include <asm/unaligned.h>
 
diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c
index 23bb64fd775f..535403e0c8a2 100644
--- a/drivers/gpu/drm/radeon/radeon_state.c
+++ b/drivers/gpu/drm/radeon/radeon_state.c
@@ -30,9 +30,9 @@
  */
 
 #include <drm/drmP.h>
-#include <drm/drm_buffer.h>
 #include <drm/radeon_drm.h>
 #include "radeon_drv.h"
+#include "drm_buffer.h"
 
 /* ================================================================
  * Helper functions for client state checking and fixup
diff --git a/include/drm/drm_buffer.h b/include/drm/drm_buffer.h
deleted file mode 100644
index c80d3a340b94..000000000000
--- a/include/drm/drm_buffer.h
+++ /dev/null
@@ -1,148 +0,0 @@
-/**************************************************************************
- *
- * Copyright 2010 Pauli Nieminen.
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the
- * "Software"), to deal in the Software without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sub license, and/or sell copies of the Software, and to
- * permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice (including the
- * next paragraph) shall be included in all copies or substantial portions
- * of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
- * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
- * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
- * USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- *
- **************************************************************************/
-/*
- * Multipart buffer for coping data which is larger than the page size.
- *
- * Authors:
- * Pauli Nieminen <suokkos-at-gmail-dot-com>
- */
-
-#ifndef _DRM_BUFFER_H_
-#define _DRM_BUFFER_H_
-
-#include <drm/drmP.h>
-
-struct drm_buffer {
-	int iterator;
-	int size;
-	char *data[];
-};
-
-
-/**
- * Return the index of page that buffer is currently pointing at.
- */
-static inline int drm_buffer_page(struct drm_buffer *buf)
-{
-	return buf->iterator / PAGE_SIZE;
-}
-/**
- * Return the index of the current byte in the page
- */
-static inline int drm_buffer_index(struct drm_buffer *buf)
-{
-	return buf->iterator & (PAGE_SIZE - 1);
-}
-/**
- * Return number of bytes that is left to process
- */
-static inline int drm_buffer_unprocessed(struct drm_buffer *buf)
-{
-	return buf->size - buf->iterator;
-}
-
-/**
- * Advance the buffer iterator number of bytes that is given.
- */
-static inline void drm_buffer_advance(struct drm_buffer *buf, int bytes)
-{
-	buf->iterator += bytes;
-}
-
-/**
- * Allocate the drm buffer object.
- *
- *   buf: A pointer to a pointer where the object is stored.
- *   size: The number of bytes to allocate.
- */
-extern int drm_buffer_alloc(struct drm_buffer **buf, int size);
-
-/**
- * Copy the user data to the begin of the buffer and reset the processing
- * iterator.
- *
- *   user_data: A pointer the data that is copied to the buffer.
- *   size: The Number of bytes to copy.
- */
-extern int drm_buffer_copy_from_user(struct drm_buffer *buf,
-		void __user *user_data, int size);
-
-/**
- * Free the drm buffer object
- */
-extern void drm_buffer_free(struct drm_buffer *buf);
-
-/**
- * Read an object from buffer that may be split to multiple parts. If object
- * is not split function just returns the pointer to object in buffer. But in
- * case of split object data is copied to given stack object that is suplied
- * by caller.
- *
- * The processing location of the buffer is also advanced to the next byte
- * after the object.
- *
- *   objsize: The size of the objet in bytes.
- *   stack_obj: A pointer to a memory location where object can be copied.
- */
-extern void *drm_buffer_read_object(struct drm_buffer *buf,
-		int objsize, void *stack_obj);
-
-/**
- * Returns the pointer to the dword which is offset number of elements from the
- * current processing location.
- *
- * Caller must make sure that dword is not split in the buffer. This
- * requirement is easily met if all the sizes of objects in buffer are
- * multiples of dword and PAGE_SIZE is multiple dword.
- *
- * Call to this function doesn't change the processing location.
- *
- *   offset: The index of the dword relative to the internat iterator.
- */
-static inline void *drm_buffer_pointer_to_dword(struct drm_buffer *buffer,
-		int offset)
-{
-	int iter = buffer->iterator + offset * 4;
-	return &buffer->data[iter / PAGE_SIZE][iter & (PAGE_SIZE - 1)];
-}
-/**
- * Returns the pointer to the dword which is offset number of elements from
- * the current processing location.
- *
- * Call to this function doesn't change the processing location.
- *
- *   offset: The index of the byte relative to the internat iterator.
- */
-static inline void *drm_buffer_pointer_to_byte(struct drm_buffer *buffer,
-		int offset)
-{
-	int iter = buffer->iterator + offset;
-	return &buffer->data[iter / PAGE_SIZE][iter & (PAGE_SIZE - 1)];
-}
-
-#endif
-- 
cgit v1.2.3


From 9fc5cde7fb6699b0a75e90b7cbfee7c912dd94c2 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:28 +0200
Subject: drm: mark drm_buf and drm_map as legacy

Move internal declarations to drm_legacy.h and add drm_legacy_*() prefix
to all legacy functions.

[airlied: add a bit of an explaination to drm_legacy.h]

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_bufs.c          | 90 ++++++++++++++++++-------------------
 drivers/gpu/drm/drm_drv.c           |  4 +-
 drivers/gpu/drm/drm_ioctl.c         | 16 +++----
 drivers/gpu/drm/drm_legacy.h        | 20 +++++++++
 drivers/gpu/drm/i915/i915_dma.c     |  2 +-
 drivers/gpu/drm/mga/mga_dma.c       | 49 ++++++++++----------
 drivers/gpu/drm/r128/r128_cce.c     |  2 +-
 drivers/gpu/drm/radeon/r600_cp.c    |  2 +-
 drivers/gpu/drm/radeon/radeon_cp.c  | 22 ++++-----
 drivers/gpu/drm/savage/savage_bci.c | 19 ++++----
 drivers/gpu/drm/via/via_map.c       |  2 +-
 include/drm/drmP.h                  | 41 +++++------------
 12 files changed, 136 insertions(+), 133 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 61acb8f6756d..9e04d6a43fa4 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -1,18 +1,13 @@
-/**
- * \file drm_bufs.c
- * Generic buffer template
- *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
- * \author Gareth Hughes <gareth@valinux.com>
- */
-
 /*
- * Created: Thu Nov 23 03:10:50 2000 by gareth@valinux.com
+ * Legacy: Generic DRM Buffer Management
  *
  * Copyright 1999, 2000 Precision Insight, Inc., Cedar Park, Texas.
  * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
  * All Rights Reserved.
  *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Gareth Hughes <gareth@valinux.com>
+ *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
  * to deal in the Software without restriction, including without limitation
@@ -39,6 +34,7 @@
 #include <linux/export.h>
 #include <asm/shmparam.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 static struct drm_map_list *drm_find_matching_map(struct drm_device *dev,
 						  struct drm_local_map *map)
@@ -365,9 +361,9 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset,
 	return 0;
 }
 
-int drm_addmap(struct drm_device * dev, resource_size_t offset,
-	       unsigned int size, enum drm_map_type type,
-	       enum drm_map_flags flags, struct drm_local_map ** map_ptr)
+int drm_legacy_addmap(struct drm_device * dev, resource_size_t offset,
+		      unsigned int size, enum drm_map_type type,
+		      enum drm_map_flags flags, struct drm_local_map **map_ptr)
 {
 	struct drm_map_list *list;
 	int rc;
@@ -377,8 +373,7 @@ int drm_addmap(struct drm_device * dev, resource_size_t offset,
 		*map_ptr = list->map;
 	return rc;
 }
-
-EXPORT_SYMBOL(drm_addmap);
+EXPORT_SYMBOL(drm_legacy_addmap);
 
 /**
  * Ioctl to specify a range of memory that is available for mapping by a
@@ -391,8 +386,8 @@ EXPORT_SYMBOL(drm_addmap);
  * \return zero on success or a negative value on error.
  *
  */
-int drm_addmap_ioctl(struct drm_device *dev, void *data,
-		     struct drm_file *file_priv)
+int drm_legacy_addmap_ioctl(struct drm_device *dev, void *data,
+			    struct drm_file *file_priv)
 {
 	struct drm_map *map = data;
 	struct drm_map_list *maplist;
@@ -429,9 +424,9 @@ int drm_addmap_ioctl(struct drm_device *dev, void *data,
  * its being used, and free any associate resource (such as MTRR's) if it's not
  * being on use.
  *
- * \sa drm_addmap
+ * \sa drm_legacy_addmap
  */
-int drm_rmmap_locked(struct drm_device *dev, struct drm_local_map *map)
+int drm_legacy_rmmap_locked(struct drm_device *dev, struct drm_local_map *map)
 {
 	struct drm_map_list *r_list = NULL, *list_t;
 	drm_dma_handle_t dmah;
@@ -485,19 +480,19 @@ int drm_rmmap_locked(struct drm_device *dev, struct drm_local_map *map)
 
 	return 0;
 }
-EXPORT_SYMBOL(drm_rmmap_locked);
+EXPORT_SYMBOL(drm_legacy_rmmap_locked);
 
-int drm_rmmap(struct drm_device *dev, struct drm_local_map *map)
+int drm_legacy_rmmap(struct drm_device *dev, struct drm_local_map *map)
 {
 	int ret;
 
 	mutex_lock(&dev->struct_mutex);
-	ret = drm_rmmap_locked(dev, map);
+	ret = drm_legacy_rmmap_locked(dev, map);
 	mutex_unlock(&dev->struct_mutex);
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_rmmap);
+EXPORT_SYMBOL(drm_legacy_rmmap);
 
 /* The rmmap ioctl appears to be unnecessary.  All mappings are torn down on
  * the last close of the device, and this is necessary for cleanup when things
@@ -514,8 +509,8 @@ EXPORT_SYMBOL(drm_rmmap);
  * \param arg pointer to a struct drm_map structure.
  * \return zero on success or a negative value on error.
  */
-int drm_rmmap_ioctl(struct drm_device *dev, void *data,
-		    struct drm_file *file_priv)
+int drm_legacy_rmmap_ioctl(struct drm_device *dev, void *data,
+			   struct drm_file *file_priv)
 {
 	struct drm_map *request = data;
 	struct drm_local_map *map = NULL;
@@ -546,7 +541,7 @@ int drm_rmmap_ioctl(struct drm_device *dev, void *data,
 		return 0;
 	}
 
-	ret = drm_rmmap_locked(dev, map);
+	ret = drm_legacy_rmmap_locked(dev, map);
 
 	mutex_unlock(&dev->struct_mutex);
 
@@ -599,7 +594,8 @@ static void drm_cleanup_buf_error(struct drm_device * dev,
  * reallocates the buffer list of the same size order to accommodate the new
  * buffers.
  */
-int drm_addbufs_agp(struct drm_device * dev, struct drm_buf_desc * request)
+int drm_legacy_addbufs_agp(struct drm_device *dev,
+			   struct drm_buf_desc *request)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_entry *entry;
@@ -759,10 +755,11 @@ int drm_addbufs_agp(struct drm_device * dev, struct drm_buf_desc * request)
 	atomic_dec(&dev->buf_alloc);
 	return 0;
 }
-EXPORT_SYMBOL(drm_addbufs_agp);
+EXPORT_SYMBOL(drm_legacy_addbufs_agp);
 #endif				/* __OS_HAS_AGP */
 
-int drm_addbufs_pci(struct drm_device * dev, struct drm_buf_desc * request)
+int drm_legacy_addbufs_pci(struct drm_device *dev,
+			   struct drm_buf_desc *request)
 {
 	struct drm_device_dma *dma = dev->dma;
 	int count;
@@ -964,9 +961,10 @@ int drm_addbufs_pci(struct drm_device * dev, struct drm_buf_desc * request)
 	return 0;
 
 }
-EXPORT_SYMBOL(drm_addbufs_pci);
+EXPORT_SYMBOL(drm_legacy_addbufs_pci);
 
-static int drm_addbufs_sg(struct drm_device * dev, struct drm_buf_desc * request)
+static int drm_legacy_addbufs_sg(struct drm_device *dev,
+				 struct drm_buf_desc *request)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_entry *entry;
@@ -1135,8 +1133,8 @@ static int drm_addbufs_sg(struct drm_device * dev, struct drm_buf_desc * request
  * addbufs_sg() or addbufs_pci() for AGP, scatter-gather or consistent
  * PCI memory respectively.
  */
-int drm_addbufs(struct drm_device *dev, void *data,
-		struct drm_file *file_priv)
+int drm_legacy_addbufs(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
 {
 	struct drm_buf_desc *request = data;
 	int ret;
@@ -1149,15 +1147,15 @@ int drm_addbufs(struct drm_device *dev, void *data,
 
 #if __OS_HAS_AGP
 	if (request->flags & _DRM_AGP_BUFFER)
-		ret = drm_addbufs_agp(dev, request);
+		ret = drm_legacy_addbufs_agp(dev, request);
 	else
 #endif
 	if (request->flags & _DRM_SG_BUFFER)
-		ret = drm_addbufs_sg(dev, request);
+		ret = drm_legacy_addbufs_sg(dev, request);
 	else if (request->flags & _DRM_FB_BUFFER)
 		ret = -EINVAL;
 	else
-		ret = drm_addbufs_pci(dev, request);
+		ret = drm_legacy_addbufs_pci(dev, request);
 
 	return ret;
 }
@@ -1179,8 +1177,8 @@ int drm_addbufs(struct drm_device *dev, void *data,
  * lock, preventing of allocating more buffers after this call. Information
  * about each requested buffer is then copied into user space.
  */
-int drm_infobufs(struct drm_device *dev, void *data,
-		 struct drm_file *file_priv)
+int drm_legacy_infobufs(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_info *request = data;
@@ -1260,8 +1258,8 @@ int drm_infobufs(struct drm_device *dev, void *data,
  *
  * \note This ioctl is deprecated and mostly never used.
  */
-int drm_markbufs(struct drm_device *dev, void *data,
-		 struct drm_file *file_priv)
+int drm_legacy_markbufs(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_desc *request = data;
@@ -1307,8 +1305,8 @@ int drm_markbufs(struct drm_device *dev, void *data,
  * Calls free_buffer() for each used buffer.
  * This function is primarily used for debugging.
  */
-int drm_freebufs(struct drm_device *dev, void *data,
-		 struct drm_file *file_priv)
+int drm_legacy_freebufs(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_free *request = data;
@@ -1360,8 +1358,8 @@ int drm_freebufs(struct drm_device *dev, void *data,
  * offset equal to 0, which drm_mmap() interpretes as PCI buffers and calls
  * drm_mmap_dma().
  */
-int drm_mapbufs(struct drm_device *dev, void *data,
-	        struct drm_file *file_priv)
+int drm_legacy_mapbufs(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	int retcode = 0;
@@ -1448,7 +1446,7 @@ int drm_mapbufs(struct drm_device *dev, void *data,
 	return retcode;
 }
 
-int drm_dma_ioctl(struct drm_device *dev, void *data,
+int drm_legacy_dma_ioctl(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
@@ -1460,7 +1458,7 @@ int drm_dma_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 }
 
-struct drm_local_map *drm_getsarea(struct drm_device *dev)
+struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev)
 {
 	struct drm_map_list *entry;
 
@@ -1472,4 +1470,4 @@ struct drm_local_map *drm_getsarea(struct drm_device *dev)
 	}
 	return NULL;
 }
-EXPORT_SYMBOL(drm_getsarea);
+EXPORT_SYMBOL(drm_legacy_getsarea);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 3242e208c0d0..b1587e2e10fc 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -143,7 +143,7 @@ static void drm_master_destroy(struct kref *kref)
 
 	list_for_each_entry_safe(r_list, list_temp, &dev->maplist, head) {
 		if (r_list->master == master) {
-			drm_rmmap_locked(dev, r_list->map);
+			drm_legacy_rmmap_locked(dev, r_list->map);
 			r_list = NULL;
 		}
 	}
@@ -779,7 +779,7 @@ void drm_dev_unregister(struct drm_device *dev)
 	drm_vblank_cleanup(dev);
 
 	list_for_each_entry_safe(r_list, list_temp, &dev->maplist, head)
-		drm_rmmap(dev, r_list->map);
+		drm_legacy_rmmap(dev, r_list->map);
 
 	drm_minor_unregister(dev, DRM_MINOR_LEGACY);
 	drm_minor_unregister(dev, DRM_MINOR_RENDER);
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 40be746b7e68..aa1ac79bccbc 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -62,8 +62,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_UNBLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_AUTH_MAGIC, drm_authmagic, DRM_AUTH|DRM_MASTER),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_MAP, drm_addmap_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_RM_MAP, drm_rmmap_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_MAP, drm_legacy_addmap_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_RM_MAP, drm_legacy_rmmap_ioctl, DRM_AUTH),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_SET_SAREA_CTX, drm_legacy_setsareactx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_SAREA_CTX, drm_legacy_getsareactx, DRM_AUTH),
@@ -87,12 +87,12 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 
 	DRM_IOCTL_DEF(DRM_IOCTL_FINISH, drm_noop, DRM_AUTH),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_BUFS, drm_addbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_MARK_BUFS, drm_markbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_INFO_BUFS, drm_infobufs, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_MAP_BUFS, drm_mapbufs, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_FREE_BUFS, drm_freebufs, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_DMA, drm_dma_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_BUFS, drm_legacy_addbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_MARK_BUFS, drm_legacy_markbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_INFO_BUFS, drm_legacy_infobufs, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_MAP_BUFS, drm_legacy_mapbufs, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_FREE_BUFS, drm_legacy_freebufs, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_DMA, drm_legacy_dma_ioctl, DRM_AUTH),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_CONTROL, drm_control, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 
diff --git a/drivers/gpu/drm/drm_legacy.h b/drivers/gpu/drm/drm_legacy.h
index d34f20a79b7c..47cb9de98fb9 100644
--- a/drivers/gpu/drm/drm_legacy.h
+++ b/drivers/gpu/drm/drm_legacy.h
@@ -23,6 +23,11 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
+/*
+ * This file contains legacy interfaces that modern drm drivers
+ * should no longer be using. They cannot be removed as legacy
+ * drivers use them, and removing them are API breaks.
+ */
 struct drm_device;
 struct drm_file;
 
@@ -48,4 +53,19 @@ int drm_legacy_rmctx(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_setsareactx(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_getsareactx(struct drm_device *d, void *v, struct drm_file *f);
 
+/*
+ * Generic Buffer Management
+ */
+
+#define DRM_MAP_HASH_OFFSET 0x10000000
+
+int drm_legacy_addmap_ioctl(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_rmmap_ioctl(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_addbufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_infobufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_markbufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_freebufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_mapbufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_dma_ioctl(struct drm_device *d, void *v, struct drm_file *f);
+
 #endif /* __DRM_LEGACY_H__ */
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 3f676f904f7e..689c3326636f 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -196,7 +196,7 @@ static int i915_initialize(struct drm_device *dev, drm_i915_init_t *init)
 	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
 	int ret;
 
-	master_priv->sarea = drm_getsarea(dev);
+	master_priv->sarea = drm_legacy_getsarea(dev);
 	if (master_priv->sarea) {
 		master_priv->sarea_priv = (drm_i915_sarea_t *)
 			((u8 *)master_priv->sarea->handle + init->sarea_priv_offset);
diff --git a/drivers/gpu/drm/mga/mga_dma.c b/drivers/gpu/drm/mga/mga_dma.c
index c3bf059ba720..37d80c122483 100644
--- a/drivers/gpu/drm/mga/mga_dma.c
+++ b/drivers/gpu/drm/mga/mga_dma.c
@@ -502,31 +502,31 @@ static int mga_do_agp_dma_bootstrap(struct drm_device *dev,
 		return err;
 	}
 
-	/* Make drm_addbufs happy by not trying to create a mapping for less
-	 * than a page.
+	/* Make drm_legacy_addbufs happy by not trying to create a mapping for
+	 * less than a page.
 	 */
 	if (warp_size < PAGE_SIZE)
 		warp_size = PAGE_SIZE;
 
 	offset = 0;
-	err = drm_addmap(dev, offset, warp_size,
-			 _DRM_AGP, _DRM_READ_ONLY, &dev_priv->warp);
+	err = drm_legacy_addmap(dev, offset, warp_size,
+				_DRM_AGP, _DRM_READ_ONLY, &dev_priv->warp);
 	if (err) {
 		DRM_ERROR("Unable to map WARP microcode: %d\n", err);
 		return err;
 	}
 
 	offset += warp_size;
-	err = drm_addmap(dev, offset, dma_bs->primary_size,
-			 _DRM_AGP, _DRM_READ_ONLY, &dev_priv->primary);
+	err = drm_legacy_addmap(dev, offset, dma_bs->primary_size,
+				_DRM_AGP, _DRM_READ_ONLY, &dev_priv->primary);
 	if (err) {
 		DRM_ERROR("Unable to map primary DMA region: %d\n", err);
 		return err;
 	}
 
 	offset += dma_bs->primary_size;
-	err = drm_addmap(dev, offset, secondary_size,
-			 _DRM_AGP, 0, &dev->agp_buffer_map);
+	err = drm_legacy_addmap(dev, offset, secondary_size,
+				_DRM_AGP, 0, &dev->agp_buffer_map);
 	if (err) {
 		DRM_ERROR("Unable to map secondary DMA region: %d\n", err);
 		return err;
@@ -538,7 +538,7 @@ static int mga_do_agp_dma_bootstrap(struct drm_device *dev,
 	req.flags = _DRM_AGP_BUFFER;
 	req.agp_start = offset;
 
-	err = drm_addbufs_agp(dev, &req);
+	err = drm_legacy_addbufs_agp(dev, &req);
 	if (err) {
 		DRM_ERROR("Unable to add secondary DMA buffers: %d\n", err);
 		return err;
@@ -559,8 +559,8 @@ static int mga_do_agp_dma_bootstrap(struct drm_device *dev,
 	}
 
 	offset += secondary_size;
-	err = drm_addmap(dev, offset, agp_size - offset,
-			 _DRM_AGP, 0, &dev_priv->agp_textures);
+	err = drm_legacy_addmap(dev, offset, agp_size - offset,
+				_DRM_AGP, 0, &dev_priv->agp_textures);
 	if (err) {
 		DRM_ERROR("Unable to map AGP texture region %d\n", err);
 		return err;
@@ -602,7 +602,7 @@ static int mga_do_agp_dma_bootstrap(struct drm_device *dev,
  *
  * \todo
  * Determine whether the maximum address passed to drm_pci_alloc is correct.
- * The same goes for drm_addbufs_pci.
+ * The same goes for drm_legacy_addbufs_pci.
  *
  * \sa mga_do_dma_bootstrap, mga_do_agp_dma_bootstrap
  */
@@ -622,15 +622,15 @@ static int mga_do_pci_dma_bootstrap(struct drm_device *dev,
 		return -EFAULT;
 	}
 
-	/* Make drm_addbufs happy by not trying to create a mapping for less
-	 * than a page.
+	/* Make drm_legacy_addbufs happy by not trying to create a mapping for
+	 * less than a page.
 	 */
 	if (warp_size < PAGE_SIZE)
 		warp_size = PAGE_SIZE;
 
 	/* The proper alignment is 0x100 for this mapping */
-	err = drm_addmap(dev, 0, warp_size, _DRM_CONSISTENT,
-			 _DRM_READ_ONLY, &dev_priv->warp);
+	err = drm_legacy_addmap(dev, 0, warp_size, _DRM_CONSISTENT,
+				_DRM_READ_ONLY, &dev_priv->warp);
 	if (err != 0) {
 		DRM_ERROR("Unable to create mapping for WARP microcode: %d\n",
 			  err);
@@ -645,8 +645,8 @@ static int mga_do_pci_dma_bootstrap(struct drm_device *dev,
 	for (primary_size = dma_bs->primary_size; primary_size != 0;
 	     primary_size >>= 1) {
 		/* The proper alignment for this mapping is 0x04 */
-		err = drm_addmap(dev, 0, primary_size, _DRM_CONSISTENT,
-				 _DRM_READ_ONLY, &dev_priv->primary);
+		err = drm_legacy_addmap(dev, 0, primary_size, _DRM_CONSISTENT,
+					_DRM_READ_ONLY, &dev_priv->primary);
 		if (!err)
 			break;
 	}
@@ -669,7 +669,7 @@ static int mga_do_pci_dma_bootstrap(struct drm_device *dev,
 		req.count = bin_count;
 		req.size = dma_bs->secondary_bin_size;
 
-		err = drm_addbufs_pci(dev, &req);
+		err = drm_legacy_addbufs_pci(dev, &req);
 		if (!err)
 			break;
 	}
@@ -708,15 +708,16 @@ static int mga_do_dma_bootstrap(struct drm_device *dev,
 	/* The first steps are the same for both PCI and AGP based DMA.  Map
 	 * the cards MMIO registers and map a status page.
 	 */
-	err = drm_addmap(dev, dev_priv->mmio_base, dev_priv->mmio_size,
-			 _DRM_REGISTERS, _DRM_READ_ONLY, &dev_priv->mmio);
+	err = drm_legacy_addmap(dev, dev_priv->mmio_base, dev_priv->mmio_size,
+				_DRM_REGISTERS, _DRM_READ_ONLY,
+				&dev_priv->mmio);
 	if (err) {
 		DRM_ERROR("Unable to map MMIO region: %d\n", err);
 		return err;
 	}
 
-	err = drm_addmap(dev, 0, SAREA_MAX, _DRM_SHM,
-			 _DRM_READ_ONLY | _DRM_LOCKED | _DRM_KERNEL,
+	err = drm_legacy_addmap(dev, 0, SAREA_MAX, _DRM_SHM,
+				_DRM_READ_ONLY | _DRM_LOCKED | _DRM_KERNEL,
 			 &dev_priv->status);
 	if (err) {
 		DRM_ERROR("Unable to map status region: %d\n", err);
@@ -809,7 +810,7 @@ static int mga_do_init_dma(struct drm_device *dev, drm_mga_init_t *init)
 	dev_priv->texture_offset = init->texture_offset[0];
 	dev_priv->texture_size = init->texture_size[0];
 
-	dev_priv->sarea = drm_getsarea(dev);
+	dev_priv->sarea = drm_legacy_getsarea(dev);
 	if (!dev_priv->sarea) {
 		DRM_ERROR("failed to find sarea!\n");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/r128/r128_cce.c b/drivers/gpu/drm/r128/r128_cce.c
index 59459fe4e8c5..1fae2f706b01 100644
--- a/drivers/gpu/drm/r128/r128_cce.c
+++ b/drivers/gpu/drm/r128/r128_cce.c
@@ -452,7 +452,7 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 	dev_priv->span_pitch_offset_c = (((dev_priv->depth_pitch / 8) << 21) |
 					 (dev_priv->span_offset >> 5));
 
-	dev_priv->sarea = drm_getsarea(dev);
+	dev_priv->sarea = drm_legacy_getsarea(dev);
 	if (!dev_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		dev->dev_private = (void *)dev_priv;
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index 8c9b7e26533c..639d6681ef5b 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -2052,7 +2052,7 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 	dev_priv->buffers_offset = init->buffers_offset;
 	dev_priv->gart_textures_offset = init->gart_textures_offset;
 
-	master_priv->sarea = drm_getsarea(dev);
+	master_priv->sarea = drm_legacy_getsarea(dev);
 	if (!master_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		r600_do_cleanup_cp(dev);
diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index bb0d5c3a8311..0c388016eecb 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -1298,7 +1298,7 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 	dev_priv->buffers_offset = init->buffers_offset;
 	dev_priv->gart_textures_offset = init->gart_textures_offset;
 
-	master_priv->sarea = drm_getsarea(dev);
+	master_priv->sarea = drm_legacy_getsarea(dev);
 	if (!master_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		radeon_do_cleanup_cp(dev);
@@ -2106,9 +2106,9 @@ int radeon_driver_load(struct drm_device *dev, unsigned long flags)
 	else
 		dev_priv->flags |= RADEON_IS_PCI;
 
-	ret = drm_addmap(dev, pci_resource_start(dev->pdev, 2),
-			 pci_resource_len(dev->pdev, 2), _DRM_REGISTERS,
-			 _DRM_READ_ONLY | _DRM_DRIVER, &dev_priv->mmio);
+	ret = drm_legacy_addmap(dev, pci_resource_start(dev->pdev, 2),
+				pci_resource_len(dev->pdev, 2), _DRM_REGISTERS,
+				_DRM_READ_ONLY | _DRM_DRIVER, &dev_priv->mmio);
 	if (ret != 0)
 		return ret;
 
@@ -2135,8 +2135,8 @@ int radeon_master_create(struct drm_device *dev, struct drm_master *master)
 
 	/* prebuild the SAREA */
 	sareapage = max_t(unsigned long, SAREA_MAX, PAGE_SIZE);
-	ret = drm_addmap(dev, 0, sareapage, _DRM_SHM, _DRM_CONTAINS_LOCK,
-			 &master_priv->sarea);
+	ret = drm_legacy_addmap(dev, 0, sareapage, _DRM_SHM, _DRM_CONTAINS_LOCK,
+				&master_priv->sarea);
 	if (ret) {
 		DRM_ERROR("SAREA setup failed\n");
 		kfree(master_priv);
@@ -2162,7 +2162,7 @@ void radeon_master_destroy(struct drm_device *dev, struct drm_master *master)
 
 	master_priv->sarea_priv = NULL;
 	if (master_priv->sarea)
-		drm_rmmap_locked(dev, master_priv->sarea);
+		drm_legacy_rmmap_locked(dev, master_priv->sarea);
 
 	kfree(master_priv);
 
@@ -2181,9 +2181,9 @@ int radeon_driver_firstopen(struct drm_device *dev)
 	dev_priv->gart_info.table_size = RADEON_PCIGART_TABLE_SIZE;
 
 	dev_priv->fb_aper_offset = pci_resource_start(dev->pdev, 0);
-	ret = drm_addmap(dev, dev_priv->fb_aper_offset,
-			 pci_resource_len(dev->pdev, 0), _DRM_FRAME_BUFFER,
-			 _DRM_WRITE_COMBINING, &map);
+	ret = drm_legacy_addmap(dev, dev_priv->fb_aper_offset,
+				pci_resource_len(dev->pdev, 0),
+				_DRM_FRAME_BUFFER, _DRM_WRITE_COMBINING, &map);
 	if (ret != 0)
 		return ret;
 
@@ -2196,7 +2196,7 @@ int radeon_driver_unload(struct drm_device *dev)
 
 	DRM_DEBUG("\n");
 
-	drm_rmmap(dev, dev_priv->mmio);
+	drm_legacy_rmmap(dev, dev_priv->mmio);
 
 	kfree(dev_priv);
 
diff --git a/drivers/gpu/drm/savage/savage_bci.c b/drivers/gpu/drm/savage/savage_bci.c
index c97cdc9ab239..82a078ca04f7 100644
--- a/drivers/gpu/drm/savage/savage_bci.c
+++ b/drivers/gpu/drm/savage/savage_bci.c
@@ -556,7 +556,7 @@ int savage_driver_load(struct drm_device *dev, unsigned long chipset)
 /*
  * Initialize mappings. On Savage4 and SavageIX the alignment
  * and size of the aperture is not suitable for automatic MTRR setup
- * in drm_addmap. Therefore we add them manually before the maps are
+ * in drm_legacy_addmap. Therefore we add them manually before the maps are
  * initialized, and tear them down on last close.
  */
 int savage_driver_firstopen(struct drm_device *dev)
@@ -624,19 +624,20 @@ int savage_driver_firstopen(struct drm_device *dev)
 		/* Automatic MTRR setup will do the right thing. */
 	}
 
-	ret = drm_addmap(dev, mmio_base, SAVAGE_MMIO_SIZE, _DRM_REGISTERS,
-			 _DRM_READ_ONLY, &dev_priv->mmio);
+	ret = drm_legacy_addmap(dev, mmio_base, SAVAGE_MMIO_SIZE,
+				_DRM_REGISTERS, _DRM_READ_ONLY,
+				&dev_priv->mmio);
 	if (ret)
 		return ret;
 
-	ret = drm_addmap(dev, fb_base, fb_size, _DRM_FRAME_BUFFER,
-			 _DRM_WRITE_COMBINING, &dev_priv->fb);
+	ret = drm_legacy_addmap(dev, fb_base, fb_size, _DRM_FRAME_BUFFER,
+				_DRM_WRITE_COMBINING, &dev_priv->fb);
 	if (ret)
 		return ret;
 
-	ret = drm_addmap(dev, aperture_base, SAVAGE_APERTURE_SIZE,
-			 _DRM_FRAME_BUFFER, _DRM_WRITE_COMBINING,
-			 &dev_priv->aperture);
+	ret = drm_legacy_addmap(dev, aperture_base, SAVAGE_APERTURE_SIZE,
+				_DRM_FRAME_BUFFER, _DRM_WRITE_COMBINING,
+				&dev_priv->aperture);
 	return ret;
 }
 
@@ -698,7 +699,7 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 	dev_priv->texture_offset = init->texture_offset;
 	dev_priv->texture_size = init->texture_size;
 
-	dev_priv->sarea = drm_getsarea(dev);
+	dev_priv->sarea = drm_legacy_getsarea(dev);
 	if (!dev_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		savage_do_cleanup_bci(dev);
diff --git a/drivers/gpu/drm/via/via_map.c b/drivers/gpu/drm/via/via_map.c
index d0ab3fb32acd..67e70e955504 100644
--- a/drivers/gpu/drm/via/via_map.c
+++ b/drivers/gpu/drm/via/via_map.c
@@ -31,7 +31,7 @@ static int via_do_init_map(struct drm_device *dev, drm_via_init_t *init)
 
 	DRM_DEBUG("\n");
 
-	dev_priv->sarea = drm_getsarea(dev);
+	dev_priv->sarea = drm_legacy_getsarea(dev);
 	if (!dev_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		dev->dev_private = (void *)dev_priv;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 6b4fbf3a3263..cea7911265a3 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -153,8 +153,6 @@ int drm_err(const char *func, const char *format, ...);
 
 #define DRM_MAGIC_HASH_ORDER  4  /**< Size of key hash table. Must be power of 2. */
 
-#define DRM_MAP_HASH_OFFSET 0x10000000
-
 /*@}*/
 
 /***********************************************************************/
@@ -1243,31 +1241,6 @@ extern void drm_idlelock_release(struct drm_lock_data *lock_data);
 
 extern int drm_i_have_hw_lock(struct drm_device *dev, struct drm_file *file_priv);
 
-				/* Buffer management support (drm_bufs.h) */
-extern int drm_addbufs_agp(struct drm_device *dev, struct drm_buf_desc * request);
-extern int drm_addbufs_pci(struct drm_device *dev, struct drm_buf_desc * request);
-extern int drm_addmap(struct drm_device *dev, resource_size_t offset,
-		      unsigned int size, enum drm_map_type type,
-		      enum drm_map_flags flags, struct drm_local_map **map_ptr);
-extern int drm_addmap_ioctl(struct drm_device *dev, void *data,
-			    struct drm_file *file_priv);
-extern int drm_rmmap(struct drm_device *dev, struct drm_local_map *map);
-extern int drm_rmmap_locked(struct drm_device *dev, struct drm_local_map *map);
-extern int drm_rmmap_ioctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv);
-extern int drm_addbufs(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
-extern int drm_infobufs(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_markbufs(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_freebufs(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_mapbufs(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
-extern int drm_dma_ioctl(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-
 				/* DMA support (drm_dma.h) */
 extern int drm_legacy_dma_setup(struct drm_device *dev);
 extern void drm_legacy_dma_takedown(struct drm_device *dev);
@@ -1354,8 +1327,6 @@ extern unsigned int drm_timestamp_monotonic;
 
 extern struct class *drm_class;
 
-extern struct drm_local_map *drm_getsarea(struct drm_device *dev);
-
 				/* Debugfs support */
 #if defined(CONFIG_DEBUG_FS)
 extern int drm_debugfs_init(struct drm_minor *minor, int minor_id,
@@ -1466,6 +1437,18 @@ extern int drm_pci_set_unique(struct drm_device *dev,
 			      struct drm_master *master,
 			      struct drm_unique *u);
 
+				/* Legacy Support */
+
+int drm_legacy_addmap(struct drm_device *d, resource_size_t offset,
+		      unsigned int size, enum drm_map_type type,
+		      enum drm_map_flags flags, struct drm_local_map **map_p);
+int drm_legacy_rmmap(struct drm_device *d, struct drm_local_map *map);
+int drm_legacy_rmmap_locked(struct drm_device *d, struct drm_local_map *map);
+struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev);
+
+int drm_legacy_addbufs_agp(struct drm_device *d, struct drm_buf_desc *req);
+int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
+
 			       /* sysfs support (drm_sysfs.c) */
 struct drm_sysfs_class;
 extern struct class *drm_sysfs_create(struct module *owner, char *name);
-- 
cgit v1.2.3


From 03decbe57ac6c9e632f7cde0f7d0a54bbcaf8464 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:29 +0200
Subject: drm: move "struct drm_vma_entry" to drm_vm.c

Make all the drm_vma_entry handling local to drm_vm.c and hide it from
global headers. This requires to extract the inlined legacy drm_vma_entry
cleanup into a small helper and also move a weirdly placed drm_vma_info
helper into drm_vm.c.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_fops.c | 10 +-----
 drivers/gpu/drm/drm_info.c | 59 -----------------------------------
 drivers/gpu/drm/drm_vm.c   | 76 ++++++++++++++++++++++++++++++++++++++++++++++
 include/drm/drmP.h         |  8 ++---
 4 files changed, 79 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 6dbbb0fd54eb..12e6a1cd804d 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -330,8 +330,6 @@ static void drm_legacy_dev_reinit(struct drm_device *dev)
  */
 int drm_lastclose(struct drm_device * dev)
 {
-	struct drm_vma_entry *vma, *vma_temp;
-
 	DRM_DEBUG("\n");
 
 	if (dev->driver->lastclose)
@@ -346,13 +344,7 @@ int drm_lastclose(struct drm_device * dev)
 	drm_agp_clear(dev);
 
 	drm_legacy_sg_cleanup(dev);
-
-	/* Clear vma list (only built for debugging) */
-	list_for_each_entry_safe(vma, vma_temp, &dev->vmalist, head) {
-		list_del(&vma->head);
-		kfree(vma);
-	}
-
+	drm_legacy_vma_flush(dev);
 	drm_legacy_dma_takedown(dev);
 
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index ecaf0fa2eec8..3c99f6f60818 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -223,62 +223,3 @@ int drm_gem_name_info(struct seq_file *m, void *data)
 
 	return 0;
 }
-
-#if DRM_DEBUG_CODE
-
-int drm_vma_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct drm_vma_entry *pt;
-	struct vm_area_struct *vma;
-	unsigned long vma_count = 0;
-#if defined(__i386__)
-	unsigned int pgprot;
-#endif
-
-	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(pt, &dev->vmalist, head)
-		vma_count++;
-
-	seq_printf(m, "vma use count: %lu, high_memory = %pK, 0x%pK\n",
-		   vma_count, high_memory,
-		   (void *)(unsigned long)virt_to_phys(high_memory));
-
-	list_for_each_entry(pt, &dev->vmalist, head) {
-		vma = pt->vma;
-		if (!vma)
-			continue;
-		seq_printf(m,
-			   "\n%5d 0x%pK-0x%pK %c%c%c%c%c%c 0x%08lx000",
-			   pt->pid,
-			   (void *)vma->vm_start, (void *)vma->vm_end,
-			   vma->vm_flags & VM_READ ? 'r' : '-',
-			   vma->vm_flags & VM_WRITE ? 'w' : '-',
-			   vma->vm_flags & VM_EXEC ? 'x' : '-',
-			   vma->vm_flags & VM_MAYSHARE ? 's' : 'p',
-			   vma->vm_flags & VM_LOCKED ? 'l' : '-',
-			   vma->vm_flags & VM_IO ? 'i' : '-',
-			   vma->vm_pgoff);
-
-#if defined(__i386__)
-		pgprot = pgprot_val(vma->vm_page_prot);
-		seq_printf(m, " %c%c%c%c%c%c%c%c%c",
-			   pgprot & _PAGE_PRESENT ? 'p' : '-',
-			   pgprot & _PAGE_RW ? 'w' : 'r',
-			   pgprot & _PAGE_USER ? 'u' : 's',
-			   pgprot & _PAGE_PWT ? 't' : 'b',
-			   pgprot & _PAGE_PCD ? 'u' : 'c',
-			   pgprot & _PAGE_ACCESSED ? 'a' : '-',
-			   pgprot & _PAGE_DIRTY ? 'd' : '-',
-			   pgprot & _PAGE_PSE ? 'm' : 'k',
-			   pgprot & _PAGE_GLOBAL ? 'g' : 'l');
-#endif
-		seq_printf(m, "\n");
-	}
-	mutex_unlock(&dev->struct_mutex);
-	return 0;
-}
-
-#endif
-
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 24e045c4f531..352e3399d18f 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -35,11 +35,18 @@
 
 #include <drm/drmP.h>
 #include <linux/export.h>
+#include <linux/seq_file.h>
 #if defined(__ia64__)
 #include <linux/efi.h>
 #include <linux/slab.h>
 #endif
 
+struct drm_vma_entry {
+	struct list_head head;
+	struct vm_area_struct *vma;
+	pid_t pid;
+};
+
 static void drm_vm_open(struct vm_area_struct *vma);
 static void drm_vm_close(struct vm_area_struct *vma);
 
@@ -662,3 +669,72 @@ int drm_mmap(struct file *filp, struct vm_area_struct *vma)
 	return ret;
 }
 EXPORT_SYMBOL(drm_mmap);
+
+void drm_legacy_vma_flush(struct drm_device *dev)
+{
+	struct drm_vma_entry *vma, *vma_temp;
+
+	/* Clear vma list (only needed for legacy drivers) */
+	list_for_each_entry_safe(vma, vma_temp, &dev->vmalist, head) {
+		list_del(&vma->head);
+		kfree(vma);
+	}
+}
+
+#if DRM_DEBUG_CODE
+
+int drm_vma_info(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_vma_entry *pt;
+	struct vm_area_struct *vma;
+	unsigned long vma_count = 0;
+#if defined(__i386__)
+	unsigned int pgprot;
+#endif
+
+	mutex_lock(&dev->struct_mutex);
+	list_for_each_entry(pt, &dev->vmalist, head)
+		vma_count++;
+
+	seq_printf(m, "vma use count: %lu, high_memory = %pK, 0x%pK\n",
+		   vma_count, high_memory,
+		   (void *)(unsigned long)virt_to_phys(high_memory));
+
+	list_for_each_entry(pt, &dev->vmalist, head) {
+		vma = pt->vma;
+		if (!vma)
+			continue;
+		seq_printf(m,
+			   "\n%5d 0x%pK-0x%pK %c%c%c%c%c%c 0x%08lx000",
+			   pt->pid,
+			   (void *)vma->vm_start, (void *)vma->vm_end,
+			   vma->vm_flags & VM_READ ? 'r' : '-',
+			   vma->vm_flags & VM_WRITE ? 'w' : '-',
+			   vma->vm_flags & VM_EXEC ? 'x' : '-',
+			   vma->vm_flags & VM_MAYSHARE ? 's' : 'p',
+			   vma->vm_flags & VM_LOCKED ? 'l' : '-',
+			   vma->vm_flags & VM_IO ? 'i' : '-',
+			   vma->vm_pgoff);
+
+#if defined(__i386__)
+		pgprot = pgprot_val(vma->vm_page_prot);
+		seq_printf(m, " %c%c%c%c%c%c%c%c%c",
+			   pgprot & _PAGE_PRESENT ? 'p' : '-',
+			   pgprot & _PAGE_RW ? 'w' : 'r',
+			   pgprot & _PAGE_USER ? 'u' : 's',
+			   pgprot & _PAGE_PWT ? 't' : 'b',
+			   pgprot & _PAGE_PCD ? 'u' : 'c',
+			   pgprot & _PAGE_ACCESSED ? 'a' : '-',
+			   pgprot & _PAGE_DIRTY ? 'd' : '-',
+			   pgprot & _PAGE_PSE ? 'm' : 'k',
+			   pgprot & _PAGE_GLOBAL ? 'g' : 'l');
+#endif
+		seq_printf(m, "\n");
+	}
+	mutex_unlock(&dev->struct_mutex);
+	return 0;
+}
+
+#endif
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index cea7911265a3..11c357534581 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -296,12 +296,6 @@ struct drm_magic_entry {
 	struct drm_file *priv;
 };
 
-struct drm_vma_entry {
-	struct list_head head;
-	struct vm_area_struct *vma;
-	pid_t pid;
-};
-
 /**
  * DMA buffer.
  */
@@ -1449,6 +1443,8 @@ struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev);
 int drm_legacy_addbufs_agp(struct drm_device *d, struct drm_buf_desc *req);
 int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
 
+void drm_legacy_vma_flush(struct drm_device *d);
+
 			       /* sysfs support (drm_sysfs.c) */
 struct drm_sysfs_class;
 extern struct class *drm_sysfs_create(struct module *owner, char *name);
-- 
cgit v1.2.3


From 71d39483de474d9513e23d9e21af7483684f4745 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:30 +0200
Subject: drm: move "struct drm_magic_entry" to drm_auth.c

In drm_release(), we currently call drm_remove_magic() if the drm_file
has a drm-magic attached. Therefore, once drm_master_release() is called,
the magic-list _must_ be empty.

By dropping the no-op cleanup, we can move "struct drm_magic_entry" to
drm_auth.c and avoid exposing it to all of DRM.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_auth.c | 6 ++++++
 drivers/gpu/drm/drm_drv.c  | 7 -------
 include/drm/drmP.h         | 6 ------
 3 files changed, 6 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index 3cedae12b3c1..708a2044c631 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -35,6 +35,12 @@
 
 #include <drm/drmP.h>
 
+struct drm_magic_entry {
+	struct list_head head;
+	struct drm_hash_item hash_item;
+	struct drm_file *priv;
+};
+
 /**
  * Find the file with the given magic number.
  *
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index b1587e2e10fc..66456698447e 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -133,7 +133,6 @@ EXPORT_SYMBOL(drm_master_get);
 static void drm_master_destroy(struct kref *kref)
 {
 	struct drm_master *master = container_of(kref, struct drm_master, refcount);
-	struct drm_magic_entry *pt, *next;
 	struct drm_device *dev = master->minor->dev;
 	struct drm_map_list *r_list, *list_temp;
 
@@ -154,12 +153,6 @@ static void drm_master_destroy(struct kref *kref)
 		master->unique_len = 0;
 	}
 
-	list_for_each_entry_safe(pt, next, &master->magicfree, head) {
-		list_del(&pt->head);
-		drm_ht_remove_item(&master->magiclist, &pt->hash_item);
-		kfree(pt);
-	}
-
 	drm_ht_remove(&master->magiclist);
 
 	mutex_unlock(&dev->struct_mutex);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 11c357534581..0fdd813821cd 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -290,12 +290,6 @@ struct drm_ioctl_desc {
 #define DRM_IOCTL_DEF_DRV(ioctl, _func, _flags)			\
 	[DRM_IOCTL_NR(DRM_##ioctl)] = {.cmd = DRM_##ioctl, .func = _func, .flags = _flags, .cmd_drv = DRM_IOCTL_##ioctl, .name = #ioctl}
 
-struct drm_magic_entry {
-	struct list_head head;
-	struct drm_hash_item hash_item;
-	struct drm_file *priv;
-};
-
 /**
  * DMA buffer.
  */
-- 
cgit v1.2.3


From cc33db0a6108d41b94eba0d84b0627cc52585109 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:31 +0200
Subject: drm: drop unused "struct drm_waitlist"

This structure is unused, drop it.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drmP.h | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 0fdd813821cd..0bf66f907f25 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -320,17 +320,6 @@ struct drm_buf {
 	void *dev_private;		 /**< Per-buffer private storage */
 };
 
-/** bufs is one longer than it has to be */
-struct drm_waitlist {
-	int count;			/**< Number of possible buffers */
-	struct drm_buf **bufs;		/**< List of pointers to buffers */
-	struct drm_buf **rp;			/**< Read pointer */
-	struct drm_buf **wp;			/**< Write pointer */
-	struct drm_buf **end;		/**< End pointer */
-	spinlock_t read_lock;
-	spinlock_t write_lock;
-};
-
 typedef struct drm_dma_handle {
 	dma_addr_t busaddr;
 	void *vaddr;
-- 
cgit v1.2.3


From cc5ea5947a52b98cd9a03d4011a5a12b4e5a99c4 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:32 +0200
Subject: drm: move AGP definitions harder

Move drm_agp_head to drm_agpsupport.h and drm_agp_mem into drm_legacy.h.
Unfortunately, drivers still heavily access drm_agp_head so we cannot
move it to drm_legacy.h. However, at least it's no longer visible in
drmP.h now (it's directly included from it, though).

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_agpsupport.c |  1 +
 drivers/gpu/drm/drm_legacy.h     | 15 +++++++++++++++
 drivers/gpu/drm/drm_memory.c     |  1 +
 drivers/gpu/drm/drm_vm.c         |  1 +
 include/drm/drmP.h               | 30 +-----------------------------
 include/drm/drm_agpsupport.h     | 13 +++++++++++++
 6 files changed, 32 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_agpsupport.c b/drivers/gpu/drm/drm_agpsupport.c
index dde205cef384..4b2b4aa5033b 100644
--- a/drivers/gpu/drm/drm_agpsupport.c
+++ b/drivers/gpu/drm/drm_agpsupport.c
@@ -34,6 +34,7 @@
 #include <drm/drmP.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include "drm_legacy.h"
 
 #if __OS_HAS_AGP
 
diff --git a/drivers/gpu/drm/drm_legacy.h b/drivers/gpu/drm/drm_legacy.h
index 47cb9de98fb9..f2d076823b2d 100644
--- a/drivers/gpu/drm/drm_legacy.h
+++ b/drivers/gpu/drm/drm_legacy.h
@@ -28,6 +28,9 @@
  * should no longer be using. They cannot be removed as legacy
  * drivers use them, and removing them are API breaks.
  */
+#include <linux/list.h>
+
+struct agp_memory;
 struct drm_device;
 struct drm_file;
 
@@ -68,4 +71,16 @@ int drm_legacy_freebufs(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_mapbufs(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_dma_ioctl(struct drm_device *d, void *v, struct drm_file *f);
 
+/*
+ * AGP Support
+ */
+
+struct drm_agp_mem {
+	unsigned long handle;
+	struct agp_memory *memory;
+	unsigned long bound;
+	int pages;
+	struct list_head head;
+};
+
 #endif /* __DRM_LEGACY_H__ */
diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c
index 00c67c0f2381..7888dad5ab74 100644
--- a/drivers/gpu/drm/drm_memory.c
+++ b/drivers/gpu/drm/drm_memory.c
@@ -36,6 +36,7 @@
 #include <linux/highmem.h>
 #include <linux/export.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 #if __OS_HAS_AGP
 static void *agp_remap(unsigned long offset, unsigned long size,
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 352e3399d18f..be25174f10e4 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -40,6 +40,7 @@
 #include <linux/efi.h>
 #include <linux/slab.h>
 #endif
+#include "drm_legacy.h"
 
 struct drm_vma_entry {
 	struct list_head head;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 0bf66f907f25..7a3c73c5375d 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -80,6 +80,7 @@ struct module;
 
 struct drm_file;
 struct drm_device;
+struct drm_agp_head;
 
 struct device_node;
 struct videomode;
@@ -439,35 +440,6 @@ struct drm_device_dma {
 
 };
 
-/**
- * AGP memory entry.  Stored as a doubly linked list.
- */
-struct drm_agp_mem {
-	unsigned long handle;		/**< handle */
-	struct agp_memory *memory;
-	unsigned long bound;		/**< address */
-	int pages;
-	struct list_head head;
-};
-
-/**
- * AGP data.
- *
- * \sa drm_agp_init() and drm_device::agp.
- */
-struct drm_agp_head {
-	struct agp_kern_info agp_info;		/**< AGP device information */
-	struct list_head memory;
-	unsigned long mode;		/**< AGP mode */
-	struct agp_bridge_data *bridge;
-	int enabled;			/**< whether the AGP bus as been enabled */
-	int acquired;			/**< whether the AGP device has been acquired */
-	unsigned long base;
-	int agp_mtrr;
-	int cant_use_aperture;
-	unsigned long page_mask;
-};
-
 /**
  * Scatter-gather memory.
  */
diff --git a/include/drm/drm_agpsupport.h b/include/drm/drm_agpsupport.h
index 86a02188074b..3bebeb4af864 100644
--- a/include/drm/drm_agpsupport.h
+++ b/include/drm/drm_agpsupport.h
@@ -8,6 +8,19 @@
 #include <linux/agp_backend.h>
 #include <drm/drmP.h>
 
+struct drm_agp_head {
+	struct agp_kern_info agp_info;
+	struct list_head memory;
+	unsigned long mode;
+	struct agp_bridge_data *bridge;
+	int enabled;
+	int acquired;
+	unsigned long base;
+	int agp_mtrr;
+	int cant_use_aperture;
+	unsigned long page_mask;
+};
+
 #if __OS_HAS_AGP
 
 void drm_free_agp(struct agp_memory * handle, int pages);
-- 
cgit v1.2.3


From 2791ee85e1e9805d600782e554f706458ec6c84e Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:33 +0200
Subject: drm: replace weird conditional includes

pte_wrprotect() is only used by drm_vm.c, so move the include there. Also
include it unconditionally, all architectures provide this header!

Furthermore, replace asm/current.h with sched.h, which includes
asm/current.h unconditionally. This way we get the same effect and avoid
direct asm/ includes. Furthermore, drop the weird __alpha__ protection.
It's safe to include sched.h everywhere (and the wait.h comment doesn't
apply, anyway).

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_vm.c |  1 +
 include/drm/drmP.h       | 10 +---------
 2 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index be25174f10e4..967e570bb0d1 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -40,6 +40,7 @@
 #include <linux/efi.h>
 #include <linux/slab.h>
 #endif
+#include <asm/pgtable.h>
 #include "drm_legacy.h"
 
 struct drm_vma_entry {
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 7a3c73c5375d..31fb30047770 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -36,12 +36,7 @@
 #define _DRM_P_H_
 
 #ifdef __KERNEL__
-#ifdef __alpha__
-/* add include of current.h so that "current" is defined
- * before static inline funcs in wait.h. Doing this so we
- * can build the DRM (part of PI DRI). 4/21/2000 S + B */
-#include <asm/current.h>
-#endif				/* __alpha__ */
+#include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/miscdevice.h>
@@ -58,9 +53,6 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
-#if defined(__alpha__) || defined(__powerpc__)
-#include <asm/pgtable.h>	/* For pte_wrprotect */
-#endif
 #include <asm/mman.h>
 #include <asm/uaccess.h>
 #include <linux/types.h>
-- 
cgit v1.2.3


From 32abc552bc869edcfa7b1c6ee365e0b58a134ec6 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:34 +0200
Subject: drm: drop __KERNEL__ protection in drmP.h

drmP.h is internal to the kernel. No need to keep the __KERNEL__
protection.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drmP.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 31fb30047770..d3504c6ff15e 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -35,7 +35,6 @@
 #ifndef _DRM_P_H_
 #define _DRM_P_H_
 
-#ifdef __KERNEL__
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
@@ -1544,5 +1543,4 @@ static __inline__ bool drm_can_sleep(void)
 	return true;
 }
 
-#endif				/* __KERNEL__ */
 #endif
-- 
cgit v1.2.3


From d6db6564457c5ad617c3bcf44bed58a227f4c702 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:35 +0200
Subject: drm: merge drm_memory.h into drm_memory.c

The drm_memory.h header is only used to define PAGE_AGP, which is only
used in drm_memory.c. Fold the header into drm_memory.c and drop it.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_memory.c | 11 +++++++++
 include/drm/drmP.h           |  6 ++---
 include/drm/drm_memory.h     | 59 --------------------------------------------
 3 files changed, 13 insertions(+), 63 deletions(-)
 delete mode 100644 include/drm/drm_memory.h

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c
index 7888dad5ab74..62fda6aaad90 100644
--- a/drivers/gpu/drm/drm_memory.c
+++ b/drivers/gpu/drm/drm_memory.c
@@ -39,6 +39,17 @@
 #include "drm_legacy.h"
 
 #if __OS_HAS_AGP
+
+#ifdef HAVE_PAGE_AGP
+# include <asm/agp.h>
+#else
+# ifdef __powerpc__
+#  define PAGE_AGP	__pgprot(_PAGE_KERNEL | _PAGE_NO_CACHE)
+# else
+#  define PAGE_AGP	PAGE_KERNEL
+# endif
+#endif
+
 static void *agp_remap(unsigned long offset, unsigned long size,
 		       struct drm_device * dev)
 {
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index d3504c6ff15e..294f7daf543e 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -58,6 +58,8 @@
 #include <linux/agp_backend.h>
 #include <linux/workqueue.h>
 #include <linux/poll.h>
+#include <linux/highmem.h>
+#include <linux/vmalloc.h>
 #include <asm/pgalloc.h>
 #include <drm/drm.h>
 #include <drm/drm_sarea.h>
@@ -1127,10 +1129,6 @@ extern void drm_vm_open_locked(struct drm_device *dev, struct vm_area_struct *vm
 extern void drm_vm_close_locked(struct drm_device *dev, struct vm_area_struct *vma);
 extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
 
-				/* Memory management support (drm_memory.h) */
-#include <drm/drm_memory.h>
-
-
 				/* Misc. IOCTL support (drm_ioctl.h) */
 extern int drm_irq_by_busid(struct drm_device *dev, void *data,
 			    struct drm_file *file_priv);
diff --git a/include/drm/drm_memory.h b/include/drm/drm_memory.h
deleted file mode 100644
index 4baf57a207e7..000000000000
--- a/include/drm/drm_memory.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/**
- * \file drm_memory.h
- * Memory management wrappers for DRM
- *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
- * \author Gareth Hughes <gareth@valinux.com>
- */
-
-/*
- * Created: Thu Feb  4 14:00:34 1999 by faith@valinux.com
- *
- * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
- * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- */
-
-#include <linux/highmem.h>
-#include <linux/vmalloc.h>
-#include <drm/drmP.h>
-
-/**
- * Cut down version of drm_memory_debug.h, which used to be called
- * drm_memory.h.
- */
-
-#if __OS_HAS_AGP
-
-#ifdef HAVE_PAGE_AGP
-#include <asm/agp.h>
-#else
-# ifdef __powerpc__
-#  define PAGE_AGP	__pgprot(_PAGE_KERNEL | _PAGE_NO_CACHE)
-# else
-#  define PAGE_AGP	PAGE_KERNEL
-# endif
-#endif
-
-#else				/* __OS_HAS_AGP */
-
-#endif
-- 
cgit v1.2.3


From 71930d74e4ad5b2cddc03e0a47ad0cc7ba51845c Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:36 +0200
Subject: drm: move __OS_HAS_AGP into drm_agpsupport.h

With drm_memory.h gone, there is no header left that uses __OS_HAS_AGP.
Move it into drm_agpsupport.h (which is itself included from drmP.h) to
hide it harder from public eyes.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drmP.h           | 2 --
 include/drm/drm_agpsupport.h | 3 +++
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 294f7daf543e..c6f337c54d9f 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -67,8 +67,6 @@
 
 #include <linux/idr.h>
 
-#define __OS_HAS_AGP (defined(CONFIG_AGP) || (defined(CONFIG_AGP_MODULE) && defined(MODULE)))
-
 struct module;
 
 struct drm_file;
diff --git a/include/drm/drm_agpsupport.h b/include/drm/drm_agpsupport.h
index 3bebeb4af864..4f1724c7ba8c 100644
--- a/include/drm/drm_agpsupport.h
+++ b/include/drm/drm_agpsupport.h
@@ -8,6 +8,9 @@
 #include <linux/agp_backend.h>
 #include <drm/drmP.h>
 
+#define __OS_HAS_AGP (defined(CONFIG_AGP) || (defined(CONFIG_AGP_MODULE) && \
+					      defined(MODULE)))
+
 struct drm_agp_head {
 	struct agp_kern_info agp_info;
 	struct list_head memory;
-- 
cgit v1.2.3


From 969939087da7aca386ff166a1c67ee9707215feb Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:37 +0200
Subject: drm: order includes alphabetically in drmP.h

It is hardly possible to review the drmP.h includes, anymore. Order them
alphabetically, linux/ first, then asm/ and then local drm/ includes.

Since a long time ago, kernel headers have been converted to include
required headers themselves. No-one cares whether that means the compiler
has to include a header multiple times. In fact, GCC already does some
optimization regarding multiple inclusions if a sorrounding #ifndef is
present.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drmP.h | 46 +++++++++++++++++++++++-----------------------
 1 file changed, 23 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index c6f337c54d9f..8b3f3b7dc2f2 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -35,38 +35,42 @@
 #ifndef _DRM_P_H_
 #define _DRM_P_H_
 
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/kref.h>
-#include <linux/miscdevice.h>
+#include <linux/agp_backend.h>
+#include <linux/cdev.h>
+#include <linux/dma-mapping.h>
+#include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/highmem.h>
+#include <linux/idr.h>
 #include <linux/init.h>
-#include <linux/file.h>
-#include <linux/platform_device.h>
-#include <linux/pci.h>
+#include <linux/io.h>
 #include <linux/jiffies.h>
-#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/kref.h>
+#include <linux/miscdevice.h>
 #include <linux/mm.h>
-#include <linux/cdev.h>
 #include <linux/mutex.h>
-#include <linux/io.h>
-#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/poll.h>
 #include <linux/ratelimit.h>
-#include <asm/mman.h>
-#include <asm/uaccess.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/types.h>
-#include <linux/agp_backend.h>
-#include <linux/workqueue.h>
-#include <linux/poll.h>
-#include <linux/highmem.h>
 #include <linux/vmalloc.h>
+#include <linux/workqueue.h>
+
+#include <asm/mman.h>
 #include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+
 #include <drm/drm.h>
+#include <drm/drm_hashtab.h>
+#include <drm/drm_mm.h>
+#include <drm/drm_os_linux.h>
 #include <drm/drm_sarea.h>
 #include <drm/drm_vma_manager.h>
 
-#include <linux/idr.h>
-
 struct module;
 
 struct drm_file;
@@ -77,10 +81,6 @@ struct device_node;
 struct videomode;
 struct reservation_object;
 
-#include <drm/drm_os_linux.h>
-#include <drm/drm_hashtab.h>
-#include <drm/drm_mm.h>
-
 /*
  * 4 debug categories are defined:
  *
-- 
cgit v1.2.3


From edf0ac7c67ce596f43d66a781660889bbdcc9505 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:38 +0200
Subject: drm: drop DRM_DEBUG_CODE

DRM_DEBUG_CODE is currently always set, so distributions enable it. The
only reason to keep support in code is if developers wanted to disable
debug support. Sounds unlikely.

All the DRM_DEBUG() printks are still guarded by a drm_debug read. So if
its cacheline is read once, they're discarded pretty fast.. There should
hardly be any performance penalty, it's even guarded by unlikely().

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_debugfs.c        |  2 --
 drivers/gpu/drm/drm_vm.c             |  4 ----
 drivers/gpu/drm/radeon/radeon.h      | 17 ++++++++++++-----
 drivers/gpu/drm/radeon/radeon_ring.c | 21 ---------------------
 include/drm/drmP.h                   | 12 ------------
 5 files changed, 12 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index 13bd42923dd4..4491dbda653e 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -49,9 +49,7 @@ static const struct drm_info_list drm_debugfs_list[] = {
 	{"clients", drm_clients_info, 0},
 	{"bufs", drm_bufs_info, 0},
 	{"gem_names", drm_gem_name_info, DRIVER_GEM},
-#if DRM_DEBUG_CODE
 	{"vma", drm_vma_info, 0},
-#endif
 };
 #define DRM_DEBUGFS_ENTRIES ARRAY_SIZE(drm_debugfs_list)
 
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 967e570bb0d1..4b3e9c4754d1 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -683,8 +683,6 @@ void drm_legacy_vma_flush(struct drm_device *dev)
 	}
 }
 
-#if DRM_DEBUG_CODE
-
 int drm_vma_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -738,5 +736,3 @@ int drm_vma_info(struct seq_file *m, void *data)
 	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
-
-#endif
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index d80dc547a105..79c988db79ad 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2776,18 +2776,25 @@ void radeon_atombios_fini(struct radeon_device *rdev);
 /*
  * RING helpers.
  */
-#if DRM_DEBUG_CODE == 0
+
+/**
+ * radeon_ring_write - write a value to the ring
+ *
+ * @ring: radeon_ring structure holding ring information
+ * @v: dword (dw) value to write
+ *
+ * Write a value to the requested ring buffer (all asics).
+ */
 static inline void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
 {
+	if (ring->count_dw <= 0)
+		DRM_ERROR("radeon: writing more dwords to the ring than expected!\n");
+
 	ring->ring[ring->wptr++] = v;
 	ring->wptr &= ring->ptr_mask;
 	ring->count_dw--;
 	ring->ring_free_dw--;
 }
-#else
-/* With debugging this is just too big to inline */
-void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
-#endif
 
 /*
  * ASICs macro.
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index d65607902537..6f2a9bd6bb54 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -44,27 +44,6 @@
  */
 static int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);
 
-/**
- * radeon_ring_write - write a value to the ring
- *
- * @ring: radeon_ring structure holding ring information
- * @v: dword (dw) value to write
- *
- * Write a value to the requested ring buffer (all asics).
- */
-void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
-{
-#if DRM_DEBUG_CODE
-	if (ring->count_dw <= 0) {
-		DRM_ERROR("radeon: writing more dwords to the ring than expected!\n");
-	}
-#endif
-	ring->ring[ring->wptr++] = v;
-	ring->wptr &= ring->ptr_mask;
-	ring->count_dw--;
-	ring->ring_free_dw--;
-}
-
 /**
  * radeon_ring_supports_scratch_reg - check if the ring supports
  * writing to scratch registers
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 8b3f3b7dc2f2..8f55875dafbb 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -140,9 +140,6 @@ int drm_err(const char *func, const char *format, ...);
 /** \name Begin the DRM... */
 /*@{*/
 
-#define DRM_DEBUG_CODE 2	  /**< Include debugging code if > 1, then
-				     also include looping detection. */
-
 #define DRM_MAGIC_HASH_ORDER  4  /**< Size of key hash table. Must be power of 2. */
 
 /*@}*/
@@ -188,7 +185,6 @@ int drm_err(const char *func, const char *format, ...);
  * \param fmt printf() like format string.
  * \param arg arguments
  */
-#if DRM_DEBUG_CODE
 #define DRM_DEBUG(fmt, args...)						\
 	do {								\
 		if (unlikely(drm_debug & DRM_UT_CORE))			\
@@ -210,12 +206,6 @@ int drm_err(const char *func, const char *format, ...);
 		if (unlikely(drm_debug & DRM_UT_PRIME))			\
 			drm_ut_debug_printk(__func__, fmt, ##args);	\
 	} while (0)
-#else
-#define DRM_DEBUG_DRIVER(fmt, args...) do { } while (0)
-#define DRM_DEBUG_KMS(fmt, args...)	do { } while (0)
-#define DRM_DEBUG_PRIME(fmt, args...)	do { } while (0)
-#define DRM_DEBUG(fmt, arg...)		 do { } while (0)
-#endif
 
 /*@}*/
 
@@ -1348,9 +1338,7 @@ void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
 void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
 void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf);
 
-#if DRM_DEBUG_CODE
 extern int drm_vma_info(struct seq_file *m, void *data);
-#endif
 
 				/* Scatter Gather Support (drm_scatter.h) */
 extern void drm_legacy_sg_cleanup(struct drm_device *dev);
-- 
cgit v1.2.3


From 69d516c0a990b42c4d55f7631fa28cc41bfcc8f0 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:39 +0200
Subject: drm: inline "struct drm_sigdata"

The sigdata structure is only used to group two fields in drm_device.
Inline it and make it an unnamed object.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_lock.c | 15 ++++++++-------
 include/drm/drmP.h         | 12 +++++-------
 2 files changed, 13 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index e26b59e385ff..60f148134e6a 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -120,7 +120,7 @@ int drm_lock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 		sigaddset(&dev->sigmask, SIGTTOU);
 		dev->sigdata.context = lock->context;
 		dev->sigdata.lock = master->lock.hw_lock;
-		block_all_signals(drm_notifier, &dev->sigdata, &dev->sigmask);
+		block_all_signals(drm_notifier, dev, &dev->sigmask);
 	}
 
 	if (dev->driver->dma_quiescent && (lock->flags & _DRM_LOCK_QUIESCENT))
@@ -286,26 +286,27 @@ int drm_lock_free(struct drm_lock_data *lock_data, unsigned int context)
  * If the lock is not held, then let the signal proceed as usual.  If the lock
  * is held, then set the contended flag and keep the signal blocked.
  *
- * \param priv pointer to a drm_sigdata structure.
+ * \param priv pointer to a drm_device structure.
  * \return one if the signal should be delivered normally, or zero if the
  * signal should be blocked.
  */
 static int drm_notifier(void *priv)
 {
-	struct drm_sigdata *s = (struct drm_sigdata *) priv;
+	struct drm_device *dev = priv;
+	struct drm_hw_lock *lock = dev->sigdata.lock;
 	unsigned int old, new, prev;
 
 	/* Allow signal delivery if lock isn't held */
-	if (!s->lock || !_DRM_LOCK_IS_HELD(s->lock->lock)
-	    || _DRM_LOCKING_CONTEXT(s->lock->lock) != s->context)
+	if (!lock || !_DRM_LOCK_IS_HELD(lock->lock)
+	    || _DRM_LOCKING_CONTEXT(lock->lock) != dev->sigdata.context)
 		return 1;
 
 	/* Otherwise, set flag to force call to
 	   drmUnlock */
 	do {
-		old = s->lock->lock;
+		old = lock->lock;
 		new = old | _DRM_LOCK_CONT;
-		prev = cmpxchg(&s->lock->lock, old, new);
+		prev = cmpxchg(&lock->lock, old, new);
 	} while (prev != old);
 	return 0;
 }
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 8f55875dafbb..840a3735d3da 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -432,12 +432,6 @@ struct drm_sg_mem {
 	dma_addr_t *busaddr;
 };
 
-struct drm_sigdata {
-	int context;
-	struct drm_hw_lock *lock;
-};
-
-
 /**
  * Kernel side of a mapping
  */
@@ -1035,9 +1029,13 @@ struct drm_device {
 
 	struct drm_sg_mem *sg;	/**< Scatter gather memory */
 	unsigned int num_crtcs;                  /**< Number of CRTCs on this device */
-	struct drm_sigdata sigdata;	   /**< For block_all_signals */
 	sigset_t sigmask;
 
+	struct {
+		int context;
+		struct drm_hw_lock *lock;
+	} sigdata;
+
 	struct drm_local_map *agp_buffer_map;
 	unsigned int agp_buffer_token;
 
-- 
cgit v1.2.3


From d7d2c48e5cfe27dc7378e48d4f22efcf417317d9 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:40 +0200
Subject: drm: move remaining includes in drmP.h to the top

Including headers somewhere else but at the top is ugly, deprecated and
was used in early days only to speed up compile-times. Those days are
over. Make headers independent and then move the inclusions to the top.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drmP.h           | 31 ++++++++++++-------------------
 include/drm/drm_agpsupport.h | 10 ++++++++--
 include/drm/drm_crtc.h       |  4 ++--
 3 files changed, 22 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 840a3735d3da..a8b24fcddb8c 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1,17 +1,14 @@
-/**
- * \file drmP.h
- * Private header for Direct Rendering Manager
- *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
- * \author Gareth Hughes <gareth@valinux.com>
- */
-
 /*
+ * Internal Header for the Direct Rendering Manager
+ *
  * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
  * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
  * Copyright (c) 2009-2010, Code Aurora Forum.
  * All rights reserved.
  *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Gareth Hughes <gareth@valinux.com>
+ *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
  * to deal in the Software without restriction, including without limitation
@@ -64,8 +61,14 @@
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
 
-#include <drm/drm.h>
+#include <uapi/drm/drm.h>
+#include <uapi/drm/drm_mode.h>
+
+#include <drm/drm_agpsupport.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_global.h>
 #include <drm/drm_hashtab.h>
+#include <drm/drm_mem_util.h>
 #include <drm/drm_mm.h>
 #include <drm/drm_os_linux.h>
 #include <drm/drm_sarea.h>
@@ -564,8 +567,6 @@ struct drm_gem_object {
 	struct dma_buf_attachment *import_attach;
 };
 
-#include <drm/drm_crtc.h>
-
 /**
  * struct drm_master - drm master structure
  *
@@ -1228,10 +1229,6 @@ extern void drm_vblank_post_modeset(struct drm_device *dev, int crtc);
 extern int drm_modeset_ctl(struct drm_device *dev, void *data,
 			   struct drm_file *file_priv);
 
-				/* AGP/GART support (drm_agpsupport.h) */
-
-#include <drm/drm_agpsupport.h>
-
 				/* Stub support (drm_stub.h) */
 extern int drm_setmaster_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file_priv);
@@ -1397,8 +1394,6 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
 		     struct vm_area_struct *vma);
 int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
 
-#include <drm/drm_global.h>
-
 static inline void
 drm_gem_object_reference(struct drm_gem_object *obj)
 {
@@ -1472,8 +1467,6 @@ static __inline__ void drm_core_dropmap(struct drm_local_map *map)
 {
 }
 
-#include <drm/drm_mem_util.h>
-
 struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 				 struct device *parent);
 void drm_dev_ref(struct drm_device *dev);
diff --git a/include/drm/drm_agpsupport.h b/include/drm/drm_agpsupport.h
index 4f1724c7ba8c..055dc058d147 100644
--- a/include/drm/drm_agpsupport.h
+++ b/include/drm/drm_agpsupport.h
@@ -1,12 +1,16 @@
 #ifndef _DRM_AGPSUPPORT_H_
 #define _DRM_AGPSUPPORT_H_
 
+#include <linux/agp_backend.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/types.h>
-#include <linux/agp_backend.h>
-#include <drm/drmP.h>
+#include <uapi/drm/drm.h>
+
+struct drm_device;
+struct drm_file;
 
 #define __OS_HAS_AGP (defined(CONFIG_AGP) || (defined(CONFIG_AGP_MODULE) && \
 					      defined(MODULE)))
@@ -61,6 +65,7 @@ int drm_agp_unbind_ioctl(struct drm_device *dev, void *data,
 int drm_agp_bind(struct drm_device *dev, struct drm_agp_binding *request);
 int drm_agp_bind_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
+
 #else /* __OS_HAS_AGP */
 
 static inline void drm_free_agp(struct agp_memory * handle, int pages)
@@ -188,6 +193,7 @@ static inline int drm_agp_bind_ioctl(struct drm_device *dev, void *data,
 {
 	return -ENODEV;
 }
+
 #endif /* __OS_HAS_AGP */
 
 #endif /* _DRM_AGPSUPPORT_H_ */
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 31344bf7887e..c40070a92d6b 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -31,8 +31,8 @@
 #include <linux/idr.h>
 #include <linux/fb.h>
 #include <linux/hdmi.h>
-#include <drm/drm_mode.h>
-#include <drm/drm_fourcc.h>
+#include <uapi/drm/drm_mode.h>
+#include <uapi/drm/drm_fourcc.h>
 #include <drm/drm_modeset_lock.h>
 
 struct drm_device;
-- 
cgit v1.2.3


From 1e444be0ef1bda2b180ecdedfa4c5d32bf236a5d Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:42 +0200
Subject: drm: drop unused drm_master->unique_size

This field is unused and there is really no reason to optimize
unique-allocations. Drop it.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_ioctl.c    | 1 -
 drivers/gpu/drm/drm_pci.c      | 4 +---
 drivers/gpu/drm/drm_platform.c | 1 -
 include/drm/drmP.h             | 2 --
 4 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index aa1ac79bccbc..cb6b54aebd6f 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -189,7 +189,6 @@ drm_unset_busid(struct drm_device *dev,
 	kfree(master->unique);
 	master->unique = NULL;
 	master->unique_len = 0;
-	master->unique_size = 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 8efea6b4602b..e266927bb9f1 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -138,7 +138,6 @@ static int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master)
 		return -ENOMEM;
 
 	master->unique_len = strlen(master->unique);
-	master->unique_size = master->unique_len + 1;
 	return 0;
 }
 
@@ -149,8 +148,7 @@ int drm_pci_set_unique(struct drm_device *dev,
 	int domain, bus, slot, func, ret;
 
 	master->unique_len = u->unique_len;
-	master->unique_size = u->unique_len + 1;
-	master->unique = kmalloc(master->unique_size, GFP_KERNEL);
+	master->unique = kmalloc(master->unique_len + 1, GFP_KERNEL);
 	if (!master->unique) {
 		ret = -ENOMEM;
 		goto err;
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index 0c09ddd50c15..f197a2b6911a 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -82,7 +82,6 @@ static int drm_platform_set_busid(struct drm_device *dev, struct drm_master *mas
 		return -ENOMEM;
 
 	master->unique_len = strlen(master->unique);
-	master->unique_size = master->unique_len;
 	return 0;
 }
 
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index a8b24fcddb8c..98b1eafebc1c 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -574,7 +574,6 @@ struct drm_gem_object {
  * @minor: Link back to minor char device we are master for. Immutable.
  * @unique: Unique identifier: e.g. busid. Protected by drm_global_mutex.
  * @unique_len: Length of unique field. Protected by drm_global_mutex.
- * @unique_size: Amount allocated. Protected by drm_global_mutex.
  * @magiclist: Hash of used authentication tokens. Protected by struct_mutex.
  * @magicfree: List of used authentication tokens. Protected by struct_mutex.
  * @lock: DRI lock information.
@@ -585,7 +584,6 @@ struct drm_master {
 	struct drm_minor *minor;
 	char *unique;
 	int unique_len;
-	int unique_size;
 	struct drm_open_hash magiclist;
 	struct list_head magicfree;
 	struct drm_lock_data lock;
-- 
cgit v1.2.3


From 915b4d11b8b9e7b84ba4a4645b6cc7fbc0c071cf Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:43 +0200
Subject: drm: add driver->set_busid() callback

One step closer to dropping all the drm_bus_* code:
Add a driver->set_busid() callback and make all drivers use the generic
helpers. Nouveau is the only driver that uses two different bus-types with
the same drm_driver. This is totally broken if both buses are available on
the same machine (unlikely, but lets be safe). Therefore, we create two
different drivers for each platform during module_init() and set the
set_busid() callback respectively.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/armada/armada_drv.c      |  1 +
 drivers/gpu/drm/ast/ast_drv.c            |  1 +
 drivers/gpu/drm/bochs/bochs_drv.c        |  1 +
 drivers/gpu/drm/cirrus/cirrus_drv.c      |  1 +
 drivers/gpu/drm/drm_ioctl.c              |  8 +++++++-
 drivers/gpu/drm/drm_pci.c                |  3 ++-
 drivers/gpu/drm/drm_platform.c           |  3 ++-
 drivers/gpu/drm/exynos/exynos_drm_drv.c  |  1 +
 drivers/gpu/drm/gma500/psb_drv.c         |  1 +
 drivers/gpu/drm/i810/i810_drv.c          |  1 +
 drivers/gpu/drm/i915/i915_drv.c          |  1 +
 drivers/gpu/drm/mga/mga_drv.c            |  1 +
 drivers/gpu/drm/mgag200/mgag200_drv.c    |  1 +
 drivers/gpu/drm/msm/msm_drv.c            |  1 +
 drivers/gpu/drm/nouveau/nouveau_drm.c    | 19 +++++++++++++------
 drivers/gpu/drm/omapdrm/omap_drv.c       |  1 +
 drivers/gpu/drm/qxl/qxl_drv.c            |  2 ++
 drivers/gpu/drm/r128/r128_drv.c          |  1 +
 drivers/gpu/drm/radeon/radeon_drv.c      |  2 ++
 drivers/gpu/drm/rcar-du/rcar_du_drv.c    |  1 +
 drivers/gpu/drm/savage/savage_drv.c      |  1 +
 drivers/gpu/drm/shmobile/shmob_drm_drv.c |  1 +
 drivers/gpu/drm/sis/sis_drv.c            |  1 +
 drivers/gpu/drm/tdfx/tdfx_drv.c          |  1 +
 drivers/gpu/drm/tilcdc/tilcdc_drv.c      |  1 +
 drivers/gpu/drm/udl/udl_drv.c            |  6 ++++++
 drivers/gpu/drm/via/via_drv.c            |  1 +
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c      |  1 +
 drivers/staging/imx-drm/imx-drm-core.c   |  1 +
 include/drm/drmP.h                       |  3 +++
 30 files changed, 59 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index e2d5792b140f..f672e6ad8afa 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -308,6 +308,7 @@ static struct drm_driver armada_drm_driver = {
 	.postclose		= NULL,
 	.lastclose		= armada_drm_lastclose,
 	.unload			= armada_drm_unload,
+	.set_busid		= drm_platform_set_busid,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= armada_drm_enable_vblank,
 	.disable_vblank		= armada_drm_disable_vblank,
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index f19682a93c24..9a32d9dfdd26 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -199,6 +199,7 @@ static struct drm_driver driver = {
 
 	.load = ast_driver_load,
 	.unload = ast_driver_unload,
+	.set_busid = drm_pci_set_busid,
 
 	.fops = &ast_fops,
 	.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c
index 9738e9b14708..98837bde2d25 100644
--- a/drivers/gpu/drm/bochs/bochs_drv.c
+++ b/drivers/gpu/drm/bochs/bochs_drv.c
@@ -82,6 +82,7 @@ static struct drm_driver bochs_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET,
 	.load			= bochs_load,
 	.unload			= bochs_unload,
+	.set_busid		= drm_pci_set_busid,
 	.fops			= &bochs_fops,
 	.name			= "bochs-drm",
 	.desc			= "bochs dispi vga interface (qemu stdvga)",
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 919c73b94447..e705335101a5 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -128,6 +128,7 @@ static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM,
 	.load = cirrus_driver_load,
 	.unload = cirrus_driver_unload,
+	.set_busid = drm_pci_set_busid,
 	.fops = &cirrus_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index cb6b54aebd6f..4770bd78b307 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -244,7 +244,13 @@ static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv)
 	if (master->unique != NULL)
 		drm_unset_busid(dev, master);
 
-	if (dev->driver->bus && dev->driver->bus->set_busid) {
+	if (dev->driver->set_busid) {
+		ret = dev->driver->set_busid(dev, master);
+		if (ret) {
+			drm_unset_busid(dev, master);
+			return ret;
+		}
+	} else if (dev->driver->bus && dev->driver->bus->set_busid) {
 		ret = dev->driver->bus->set_busid(dev, master);
 		if (ret) {
 			drm_unset_busid(dev, master);
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index e266927bb9f1..0400c371cbde 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -127,7 +127,7 @@ static int drm_get_pci_domain(struct drm_device *dev)
 	return pci_domain_nr(dev->pdev->bus);
 }
 
-static int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master)
+int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master)
 {
 	master->unique = kasprintf(GFP_KERNEL, "pci:%04x:%02x:%02x.%d",
 					drm_get_pci_domain(dev),
@@ -140,6 +140,7 @@ static int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master)
 	master->unique_len = strlen(master->unique);
 	return 0;
 }
+EXPORT_SYMBOL(drm_pci_set_busid);
 
 int drm_pci_set_unique(struct drm_device *dev,
 		       struct drm_master *master,
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index f197a2b6911a..939cd2272b91 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -68,7 +68,7 @@ err_free:
 	return ret;
 }
 
-static int drm_platform_set_busid(struct drm_device *dev, struct drm_master *master)
+int drm_platform_set_busid(struct drm_device *dev, struct drm_master *master)
 {
 	int id;
 
@@ -84,6 +84,7 @@ static int drm_platform_set_busid(struct drm_device *dev, struct drm_master *mas
 	master->unique_len = strlen(master->unique);
 	return 0;
 }
+EXPORT_SYMBOL(drm_platform_set_busid);
 
 static struct drm_bus drm_platform_bus = {
 	.set_busid = drm_platform_set_busid,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 0d74e9b99c4e..5aae95cf5b23 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -330,6 +330,7 @@ static struct drm_driver exynos_drm_driver = {
 	.preclose		= exynos_drm_preclose,
 	.lastclose		= exynos_drm_lastclose,
 	.postclose		= exynos_drm_postclose,
+	.set_busid		= drm_platform_set_busid,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= exynos_drm_crtc_enable_vblank,
 	.disable_vblank		= exynos_drm_crtc_disable_vblank,
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index eec993f93b1a..6ec3a905fdd2 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -476,6 +476,7 @@ static struct drm_driver driver = {
 	.unload = psb_driver_unload,
 	.lastclose = psb_driver_lastclose,
 	.preclose = psb_driver_preclose,
+	.set_busid = drm_pci_set_busid,
 
 	.num_ioctls = ARRAY_SIZE(psb_ioctls),
 	.device_is_agp = psb_driver_device_is_agp,
diff --git a/drivers/gpu/drm/i810/i810_drv.c b/drivers/gpu/drm/i810/i810_drv.c
index 441ccf8f5bdc..6cb08a1c6b62 100644
--- a/drivers/gpu/drm/i810/i810_drv.c
+++ b/drivers/gpu/drm/i810/i810_drv.c
@@ -63,6 +63,7 @@ static struct drm_driver driver = {
 	.load = i810_driver_load,
 	.lastclose = i810_driver_lastclose,
 	.preclose = i810_driver_preclose,
+	.set_busid = drm_pci_set_busid,
 	.device_is_agp = i810_driver_device_is_agp,
 	.dma_quiescent = i810_driver_dma_quiescent,
 	.ioctls = i810_ioctls,
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index ff4db249cc72..cdd95956811d 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1593,6 +1593,7 @@ static struct drm_driver driver = {
 	.lastclose = i915_driver_lastclose,
 	.preclose = i915_driver_preclose,
 	.postclose = i915_driver_postclose,
+	.set_busid = drm_pci_set_busid,
 
 	/* Used in place of i915_pm_ops for non-DRIVER_MODESET */
 	.suspend = i915_suspend,
diff --git a/drivers/gpu/drm/mga/mga_drv.c b/drivers/gpu/drm/mga/mga_drv.c
index 6b1a87c8aac5..cb5c71f4b28e 100644
--- a/drivers/gpu/drm/mga/mga_drv.c
+++ b/drivers/gpu/drm/mga/mga_drv.c
@@ -64,6 +64,7 @@ static struct drm_driver driver = {
 	.load = mga_driver_load,
 	.unload = mga_driver_unload,
 	.lastclose = mga_driver_lastclose,
+	.set_busid = drm_pci_set_busid,
 	.dma_quiescent = mga_driver_dma_quiescent,
 	.device_is_agp = mga_driver_device_is_agp,
 	.get_vblank_counter = mga_get_vblank_counter,
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index 2d75d6df0789..97745991544d 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -91,6 +91,7 @@ static struct drm_driver driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET,
 	.load = mgag200_driver_load,
 	.unload = mgag200_driver_unload,
+	.set_busid = drm_pci_set_busid,
 	.fops = &mgag200_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index b447c01ad89c..47ccdbf49fa1 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -836,6 +836,7 @@ static struct drm_driver msm_driver = {
 	.open               = msm_open,
 	.preclose           = msm_preclose,
 	.lastclose          = msm_lastclose,
+	.set_busid          = drm_platform_set_busid,
 	.irq_handler        = msm_irq,
 	.irq_preinstall     = msm_irq_preinstall,
 	.irq_postinstall    = msm_irq_postinstall,
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 250a5e88c751..cee1eaf64117 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -73,7 +73,9 @@ MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1
 int nouveau_runtime_pm = -1;
 module_param_named(runpm, nouveau_runtime_pm, int, 0400);
 
-static struct drm_driver driver;
+static struct drm_driver driver_stub;
+static struct drm_driver driver_pci;
+static struct drm_driver driver_platform;
 
 static u64
 nouveau_pci_name(struct pci_dev *pdev)
@@ -322,7 +324,7 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	ret = drm_get_pci_dev(pdev, pent, &driver);
+	ret = drm_get_pci_dev(pdev, pent, &driver_pci);
 	if (ret) {
 		nouveau_object_ref(NULL, (struct nouveau_object **)&device);
 		return ret;
@@ -855,7 +857,7 @@ nouveau_driver_fops = {
 };
 
 static struct drm_driver
-driver = {
+driver_stub = {
 	.driver_features =
 		DRIVER_USE_AGP |
 		DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_RENDER,
@@ -1061,7 +1063,7 @@ nouveau_platform_device_create_(struct platform_device *pdev, int size,
 	if (err)
 		return ERR_PTR(err);
 
-	drm = drm_dev_alloc(&driver, &pdev->dev);
+	drm = drm_dev_alloc(&driver_platform, &pdev->dev);
 	if (!drm) {
 		err = -ENOMEM;
 		goto err_free;
@@ -1086,6 +1088,11 @@ EXPORT_SYMBOL(nouveau_platform_device_create_);
 static int __init
 nouveau_drm_init(void)
 {
+	driver_pci = driver_stub;
+	driver_pci.set_busid = drm_pci_set_busid;
+	driver_platform = driver_stub;
+	driver_platform.set_busid = drm_platform_set_busid;
+
 	if (nouveau_modeset == -1) {
 #ifdef CONFIG_VGA_CONSOLE
 		if (vgacon_text_force())
@@ -1097,7 +1104,7 @@ nouveau_drm_init(void)
 		return 0;
 
 	nouveau_register_dsm_handler();
-	return drm_pci_init(&driver, &nouveau_drm_pci_driver);
+	return drm_pci_init(&driver_pci, &nouveau_drm_pci_driver);
 }
 
 static void __exit
@@ -1106,7 +1113,7 @@ nouveau_drm_exit(void)
 	if (!nouveau_modeset)
 		return;
 
-	drm_pci_exit(&driver, &nouveau_drm_pci_driver);
+	drm_pci_exit(&driver_pci, &nouveau_drm_pci_driver);
 	nouveau_unregister_dsm_handler();
 }
 
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index 002b9721e85a..862ba03c236c 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -629,6 +629,7 @@ static struct drm_driver omap_drm_driver = {
 		.lastclose = dev_lastclose,
 		.preclose = dev_preclose,
 		.postclose = dev_postclose,
+		.set_busid = drm_platform_set_busid,
 		.get_vblank_counter = drm_vblank_count,
 		.enable_vblank = omap_irq_enable_vblank,
 		.disable_vblank = omap_irq_disable_vblank,
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index 4da0105e481a..1d9b80c91a15 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -235,6 +235,8 @@ static struct drm_driver qxl_driver = {
 	.enable_vblank = qxl_noop_enable_vblank,
 	.disable_vblank = qxl_noop_disable_vblank,
 
+	.set_busid = drm_pci_set_busid,
+
 	.dumb_create = qxl_mode_dumb_create,
 	.dumb_map_offset = qxl_mode_dumb_mmap,
 	.dumb_destroy = drm_gem_dumb_destroy,
diff --git a/drivers/gpu/drm/r128/r128_drv.c b/drivers/gpu/drm/r128/r128_drv.c
index 5bd307cd8da1..4a59370eb580 100644
--- a/drivers/gpu/drm/r128/r128_drv.c
+++ b/drivers/gpu/drm/r128/r128_drv.c
@@ -62,6 +62,7 @@ static struct drm_driver driver = {
 	.load = r128_driver_load,
 	.preclose = r128_driver_preclose,
 	.lastclose = r128_driver_lastclose,
+	.set_busid = drm_pci_set_busid,
 	.get_vblank_counter = r128_get_vblank_counter,
 	.enable_vblank = r128_enable_vblank,
 	.disable_vblank = r128_disable_vblank,
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index f1e96e094b00..ec7e963d9bf7 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -328,6 +328,7 @@ static struct drm_driver driver_old = {
 	.preclose = radeon_driver_preclose,
 	.postclose = radeon_driver_postclose,
 	.lastclose = radeon_driver_lastclose,
+	.set_busid = drm_pci_set_busid,
 	.unload = radeon_driver_unload,
 	.suspend = radeon_suspend,
 	.resume = radeon_resume,
@@ -551,6 +552,7 @@ static struct drm_driver kms_driver = {
 	.preclose = radeon_driver_preclose_kms,
 	.postclose = radeon_driver_postclose_kms,
 	.lastclose = radeon_driver_lastclose_kms,
+	.set_busid = drm_pci_set_busid,
 	.unload = radeon_driver_unload_kms,
 	.get_vblank_counter = radeon_get_vblank_counter_kms,
 	.enable_vblank = radeon_enable_vblank_kms,
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index fda64b7b73e8..672d2fcba009 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -158,6 +158,7 @@ static struct drm_driver rcar_du_driver = {
 	.unload			= rcar_du_unload,
 	.preclose		= rcar_du_preclose,
 	.lastclose		= rcar_du_lastclose,
+	.set_busid		= drm_platform_set_busid,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= rcar_du_enable_vblank,
 	.disable_vblank		= rcar_du_disable_vblank,
diff --git a/drivers/gpu/drm/savage/savage_drv.c b/drivers/gpu/drm/savage/savage_drv.c
index 3c030216e888..1b09d2182037 100644
--- a/drivers/gpu/drm/savage/savage_drv.c
+++ b/drivers/gpu/drm/savage/savage_drv.c
@@ -57,6 +57,7 @@ static struct drm_driver driver = {
 	.preclose = savage_reclaim_buffers,
 	.lastclose = savage_driver_lastclose,
 	.unload = savage_driver_unload,
+	.set_busid = drm_pci_set_busid,
 	.ioctls = savage_ioctls,
 	.dma_ioctl = savage_bci_buffers,
 	.fops = &savage_driver_fops,
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
index ff4ba483b602..873d12f851bf 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_drv.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
@@ -267,6 +267,7 @@ static struct drm_driver shmob_drm_driver = {
 	.load			= shmob_drm_load,
 	.unload			= shmob_drm_unload,
 	.preclose		= shmob_drm_preclose,
+	.set_busid		= drm_platform_set_busid,
 	.irq_handler		= shmob_drm_irq,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= shmob_drm_enable_vblank,
diff --git a/drivers/gpu/drm/sis/sis_drv.c b/drivers/gpu/drm/sis/sis_drv.c
index 756f787b7143..54858e6fedaf 100644
--- a/drivers/gpu/drm/sis/sis_drv.c
+++ b/drivers/gpu/drm/sis/sis_drv.c
@@ -108,6 +108,7 @@ static struct drm_driver driver = {
 	.open = sis_driver_open,
 	.preclose = sis_reclaim_buffers_locked,
 	.postclose = sis_driver_postclose,
+	.set_busid = drm_pci_set_busid,
 	.dma_quiescent = sis_idle,
 	.lastclose = sis_lastclose,
 	.ioctls = sis_ioctls,
diff --git a/drivers/gpu/drm/tdfx/tdfx_drv.c b/drivers/gpu/drm/tdfx/tdfx_drv.c
index 3492ca5c46d3..df533ff999a4 100644
--- a/drivers/gpu/drm/tdfx/tdfx_drv.c
+++ b/drivers/gpu/drm/tdfx/tdfx_drv.c
@@ -55,6 +55,7 @@ static const struct file_operations tdfx_driver_fops = {
 };
 
 static struct drm_driver driver = {
+	.set_busid = drm_pci_set_busid,
 	.fops = &tdfx_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index 6be623b4a86f..aea4b7663934 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -502,6 +502,7 @@ static struct drm_driver tilcdc_driver = {
 	.unload             = tilcdc_unload,
 	.preclose           = tilcdc_preclose,
 	.lastclose          = tilcdc_lastclose,
+	.set_busid          = drm_platform_set_busid,
 	.irq_handler        = tilcdc_irq,
 	.irq_preinstall     = tilcdc_irq_preinstall,
 	.irq_postinstall    = tilcdc_irq_postinstall,
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 3ddd6cd98ac1..06675e5d4342 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -34,6 +34,11 @@ MODULE_DEVICE_TABLE(usb, id_table);
 
 MODULE_LICENSE("GPL");
 
+static int udl_driver_set_busid(struct drm_device *d, struct drm_master *m)
+{
+	return 0;
+}
+
 static int udl_usb_probe(struct usb_interface *interface,
 			 const struct usb_device_id *id)
 {
@@ -75,6 +80,7 @@ static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME,
 	.load = udl_driver_load,
 	.unload = udl_driver_unload,
+	.set_busid = udl_driver_set_busid,
 
 	/* gem hooks */
 	.gem_free_object = udl_gem_free_object,
diff --git a/drivers/gpu/drm/via/via_drv.c b/drivers/gpu/drm/via/via_drv.c
index 50abc2adfaee..c16ffa63ded6 100644
--- a/drivers/gpu/drm/via/via_drv.c
+++ b/drivers/gpu/drm/via/via_drv.c
@@ -79,6 +79,7 @@ static struct drm_driver driver = {
 	.open = via_driver_open,
 	.preclose = via_reclaim_buffers_locked,
 	.postclose = via_driver_postclose,
+	.set_busid = drm_pci_set_busid,
 	.context_dtor = via_final_context,
 	.get_vblank_counter = via_get_vblank_counter,
 	.enable_vblank = via_enable_vblank,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 18b54acacfbb..7197af157313 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1418,6 +1418,7 @@ static struct drm_driver driver = {
 	.open = vmw_driver_open,
 	.preclose = vmw_preclose,
 	.postclose = vmw_postclose,
+	.set_busid = drm_pci_set_busid,
 
 	.dumb_create = vmw_dumb_create,
 	.dumb_map_offset = vmw_dumb_map_offset,
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index 6b22106534d8..16392b674d79 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -528,6 +528,7 @@ static struct drm_driver imx_drm_driver = {
 	.unload			= imx_drm_driver_unload,
 	.lastclose		= imx_drm_driver_lastclose,
 	.preclose		= imx_drm_driver_preclose,
+	.set_busid		= drm_platform_set_busid,
 	.gem_free_object	= drm_gem_cma_free_object,
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 	.dumb_create		= drm_gem_cma_dumb_create,
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 98b1eafebc1c..c82f292efcd4 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -627,6 +627,7 @@ struct drm_driver {
 	int (*dma_ioctl) (struct drm_device *dev, void *data, struct drm_file *file_priv);
 	int (*dma_quiescent) (struct drm_device *);
 	int (*context_dtor) (struct drm_device *dev, int context);
+	int (*set_busid)(struct drm_device *dev, struct drm_master *master);
 
 	/**
 	 * get_vblank_counter - get raw hardware vblank counter
@@ -1498,6 +1499,7 @@ extern void drm_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver);
 extern int drm_get_pci_dev(struct pci_dev *pdev,
 			   const struct pci_device_id *ent,
 			   struct drm_driver *driver);
+extern int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master);
 
 #define DRM_PCIE_SPEED_25 1
 #define DRM_PCIE_SPEED_50 2
@@ -1507,6 +1509,7 @@ extern int drm_pcie_get_speed_cap_mask(struct drm_device *dev, u32 *speed_mask);
 
 /* platform section */
 extern int drm_platform_init(struct drm_driver *driver, struct platform_device *platform_device);
+extern int drm_platform_set_busid(struct drm_device *d, struct drm_master *m);
 
 /* returns true if currently okay to sleep */
 static __inline__ bool drm_can_sleep(void)
-- 
cgit v1.2.3


From c5786fe5f1c50941dbe27fc8b4aa1afee46ae893 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:44 +0200
Subject: drm: Goody bye, drm_bus!

..we will not miss you..

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_ioctl.c    |  8 +-------
 drivers/gpu/drm/drm_pci.c      |  6 ------
 drivers/gpu/drm/drm_platform.c |  5 -----
 drivers/gpu/drm/drm_usb.c      | 12 ------------
 include/drm/drmP.h             |  5 -----
 5 files changed, 1 insertion(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 4770bd78b307..3a1349f82b41 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -250,15 +250,9 @@ static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv)
 			drm_unset_busid(dev, master);
 			return ret;
 		}
-	} else if (dev->driver->bus && dev->driver->bus->set_busid) {
-		ret = dev->driver->bus->set_busid(dev, master);
-		if (ret) {
-			drm_unset_busid(dev, master);
-			return ret;
-		}
 	} else {
 		if (WARN(dev->unique == NULL,
-			 "No drm_bus.set_busid() implementation provided by "
+			 "No drm_driver.set_busid() implementation provided by "
 			 "%ps. Use drm_dev_set_unique() to set the unique "
 			 "name explicitly.", dev->driver))
 			return -EINVAL;
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 0400c371cbde..7563130c6b70 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -254,10 +254,6 @@ void drm_pci_agp_destroy(struct drm_device *dev)
 	}
 }
 
-static struct drm_bus drm_pci_bus = {
-	.set_busid = drm_pci_set_busid,
-};
-
 /**
  * drm_get_pci_dev - Register a PCI device with the DRM subsystem
  * @pdev: PCI device
@@ -338,8 +334,6 @@ int drm_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 
 	DRM_DEBUG("\n");
 
-	driver->bus = &drm_pci_bus;
-
 	if (driver->driver_features & DRIVER_MODESET)
 		return pci_register_driver(pdriver);
 
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index 939cd2272b91..5314c9d5fef4 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -86,10 +86,6 @@ int drm_platform_set_busid(struct drm_device *dev, struct drm_master *master)
 }
 EXPORT_SYMBOL(drm_platform_set_busid);
 
-static struct drm_bus drm_platform_bus = {
-	.set_busid = drm_platform_set_busid,
-};
-
 /**
  * drm_platform_init - Register a platform device with the DRM subsystem
  * @driver: DRM device driver
@@ -105,7 +101,6 @@ int drm_platform_init(struct drm_driver *driver, struct platform_device *platfor
 {
 	DRM_DEBUG("\n");
 
-	driver->bus = &drm_platform_bus;
 	return drm_get_platform_dev(platform_device, driver);
 }
 EXPORT_SYMBOL(drm_platform_init);
diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c
index f2fe94aab901..9c434905d37f 100644
--- a/drivers/gpu/drm/drm_usb.c
+++ b/drivers/gpu/drm/drm_usb.c
@@ -36,16 +36,6 @@ err_free:
 }
 EXPORT_SYMBOL(drm_get_usb_dev);
 
-static int drm_usb_set_busid(struct drm_device *dev,
-			       struct drm_master *master)
-{
-	return 0;
-}
-
-static struct drm_bus drm_usb_bus = {
-	.set_busid = drm_usb_set_busid,
-};
-
 /**
  * drm_usb_init - Register matching USB devices with the DRM subsystem
  * @driver: DRM device driver
@@ -61,8 +51,6 @@ int drm_usb_init(struct drm_driver *driver, struct usb_driver *udriver)
 	int res;
 	DRM_DEBUG("\n");
 
-	driver->bus = &drm_usb_bus;
-
 	res = usb_register(udriver);
 	return res;
 }
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index c82f292efcd4..5ae388a9bb98 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -605,10 +605,6 @@ struct drm_master {
 #define DRM_SCANOUTPOS_INVBL        (1 << 1)
 #define DRM_SCANOUTPOS_ACCURATE     (1 << 2)
 
-struct drm_bus {
-	int (*set_busid)(struct drm_device *dev, struct drm_master *master);
-};
-
 /**
  * DRM driver structure. This structure represent the common code for
  * a family of cards. There will one drm_device for each card present
@@ -846,7 +842,6 @@ struct drm_driver {
 	const struct drm_ioctl_desc *ioctls;
 	int num_ioctls;
 	const struct file_operations *fops;
-	struct drm_bus *bus;
 
 	/* List of devices hanging off this driver with stealth attach. */
 	struct list_head legacy_dev_list;
-- 
cgit v1.2.3


From d4f68a7506e924e28a9153933076628002ba8bbc Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:45 +0200
Subject: drm: merge drm_usb into udl

This merges all the remains of drm_usb into its only user, udl. We can
then drop all the drm_usb stuff, including dev->usbdev.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 Documentation/DocBook/drm.tmpl      |   3 +-
 drivers/gpu/drm/Kconfig             |   6 ---
 drivers/gpu/drm/Makefile            |   3 --
 drivers/gpu/drm/drm_usb.c           |  76 ---------------------------
 drivers/gpu/drm/udl/Kconfig         |   3 +-
 drivers/gpu/drm/udl/udl_connector.c |   4 +-
 drivers/gpu/drm/udl/udl_drv.c       | 102 +++++++++++++++++++++---------------
 drivers/gpu/drm/udl/udl_drv.h       |   1 +
 drivers/gpu/drm/udl/udl_main.c      |   8 +--
 include/drm/drmP.h                  |   1 -
 include/drm/drm_usb.h               |  15 ------
 11 files changed, 70 insertions(+), 152 deletions(-)
 delete mode 100644 drivers/gpu/drm/drm_usb.c
 delete mode 100644 include/drm/drm_usb.h

(limited to 'include')

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 58ab4d32c86f..1fce7dc46d87 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -291,10 +291,9 @@ char *date;</synopsis>
       <title>Device Registration</title>
       <para>
         A number of functions are provided to help with device registration.
-        The functions deal with PCI, USB and platform devices, respectively.
+        The functions deal with PCI and platform devices, respectively.
       </para>
 !Edrivers/gpu/drm/drm_pci.c
-!Edrivers/gpu/drm/drm_usb.c
 !Edrivers/gpu/drm/drm_platform.c
       <para>
         New drivers that no longer rely on the services provided by the
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index e3500f9584ec..e3b4b0f02b3d 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -25,12 +25,6 @@ config DRM_MIPI_DSI
 	bool
 	depends on DRM
 
-config DRM_USB
-	tristate
-	depends on DRM
-	depends on USB_SUPPORT && USB_ARCH_HAS_HCD
-	select USB
-
 config DRM_KMS_HELPER
 	tristate
 	depends on DRM
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 9b7cb3f76f01..9292a761ea6d 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -22,8 +22,6 @@ drm-$(CONFIG_PCI) += ati_pcigart.o
 drm-$(CONFIG_DRM_PANEL) += drm_panel.o
 drm-$(CONFIG_OF) += drm_of.o
 
-drm-usb-y   := drm_usb.o
-
 drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_probe_helper.o \
 		drm_plane_helper.o drm_dp_mst_topology.o
 drm_kms_helper-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o
@@ -36,7 +34,6 @@ CFLAGS_drm_trace_points.o := -I$(src)
 
 obj-$(CONFIG_DRM)	+= drm.o
 obj-$(CONFIG_DRM_MIPI_DSI) += drm_mipi_dsi.o
-obj-$(CONFIG_DRM_USB)   += drm_usb.o
 obj-$(CONFIG_DRM_TTM)	+= ttm/
 obj-$(CONFIG_DRM_TDFX)	+= tdfx/
 obj-$(CONFIG_DRM_R128)	+= r128/
diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c
deleted file mode 100644
index 9c434905d37f..000000000000
--- a/drivers/gpu/drm/drm_usb.c
+++ /dev/null
@@ -1,76 +0,0 @@
-#include <drm/drmP.h>
-#include <drm/drm_usb.h>
-#include <linux/usb.h>
-#include <linux/module.h>
-
-int drm_get_usb_dev(struct usb_interface *interface,
-		    const struct usb_device_id *id,
-		    struct drm_driver *driver)
-{
-	struct drm_device *dev;
-	int ret;
-
-	DRM_DEBUG("\n");
-
-	dev = drm_dev_alloc(driver, &interface->dev);
-	if (!dev)
-		return -ENOMEM;
-
-	dev->usbdev = interface_to_usbdev(interface);
-	usb_set_intfdata(interface, dev);
-
-	ret = drm_dev_register(dev, 0);
-	if (ret)
-		goto err_free;
-
-	DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n",
-		 driver->name, driver->major, driver->minor, driver->patchlevel,
-		 driver->date, dev->primary->index);
-
-	return 0;
-
-err_free:
-	drm_dev_unref(dev);
-	return ret;
-
-}
-EXPORT_SYMBOL(drm_get_usb_dev);
-
-/**
- * drm_usb_init - Register matching USB devices with the DRM subsystem
- * @driver: DRM device driver
- * @udriver: USB device driver
- *
- * Registers one or more devices matched by a USB driver with the DRM
- * subsystem.
- *
- * Return: 0 on success or a negative error code on failure.
- */
-int drm_usb_init(struct drm_driver *driver, struct usb_driver *udriver)
-{
-	int res;
-	DRM_DEBUG("\n");
-
-	res = usb_register(udriver);
-	return res;
-}
-EXPORT_SYMBOL(drm_usb_init);
-
-/**
- * drm_usb_exit - Unregister matching USB devices from the DRM subsystem
- * @driver: DRM device driver
- * @udriver: USB device driver
- *
- * Unregisters one or more devices matched by a USB driver from the DRM
- * subsystem.
- */
-void drm_usb_exit(struct drm_driver *driver,
-		  struct usb_driver *udriver)
-{
-	usb_deregister(udriver);
-}
-EXPORT_SYMBOL(drm_usb_exit);
-
-MODULE_AUTHOR("David Airlie");
-MODULE_DESCRIPTION("USB DRM support");
-MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/udl/Kconfig b/drivers/gpu/drm/udl/Kconfig
index f02528686cd5..613ab0622d6e 100644
--- a/drivers/gpu/drm/udl/Kconfig
+++ b/drivers/gpu/drm/udl/Kconfig
@@ -1,8 +1,9 @@
 config DRM_UDL
 	tristate "DisplayLink"
 	depends on DRM
+	depends on USB_SUPPORT
 	depends on USB_ARCH_HAS_HCD
-	select DRM_USB
+	select USB
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA
 	select FB_SYS_IMAGEBLIT
diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c
index e026a9e2942a..0110d95522f3 100644
--- a/drivers/gpu/drm/udl/udl_connector.c
+++ b/drivers/gpu/drm/udl/udl_connector.c
@@ -34,8 +34,8 @@ static u8 *udl_get_edid(struct udl_device *udl)
 		goto error;
 
 	for (i = 0; i < EDID_LENGTH; i++) {
-		ret = usb_control_msg(udl->ddev->usbdev,
-				      usb_rcvctrlpipe(udl->ddev->usbdev, 0), (0x02),
+		ret = usb_control_msg(udl->udev,
+				      usb_rcvctrlpipe(udl->udev, 0), (0x02),
 				      (0x80 | (0x02 << 5)), i << 8, 0xA1, rbuf, 2,
 				      HZ);
 		if (ret < 1) {
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 06675e5d4342..8607e9e513db 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -7,55 +7,15 @@
  */
 
 #include <linux/module.h>
-#include <drm/drm_usb.h>
+#include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include "udl_drv.h"
 
-static struct drm_driver driver;
-
-/*
- * There are many DisplayLink-based graphics products, all with unique PIDs.
- * So we match on DisplayLink's VID + Vendor-Defined Interface Class (0xff)
- * We also require a match on SubClass (0x00) and Protocol (0x00),
- * which is compatible with all known USB 2.0 era graphics chips and firmware,
- * but allows DisplayLink to increment those for any future incompatible chips
- */
-static struct usb_device_id id_table[] = {
-	{.idVendor = 0x17e9, .bInterfaceClass = 0xff,
-	 .bInterfaceSubClass = 0x00,
-	 .bInterfaceProtocol = 0x00,
-	 .match_flags = USB_DEVICE_ID_MATCH_VENDOR |
-			USB_DEVICE_ID_MATCH_INT_CLASS |
-			USB_DEVICE_ID_MATCH_INT_SUBCLASS |
-			USB_DEVICE_ID_MATCH_INT_PROTOCOL,},
-	{},
-};
-MODULE_DEVICE_TABLE(usb, id_table);
-
-MODULE_LICENSE("GPL");
-
 static int udl_driver_set_busid(struct drm_device *d, struct drm_master *m)
 {
 	return 0;
 }
 
-static int udl_usb_probe(struct usb_interface *interface,
-			 const struct usb_device_id *id)
-{
-	return drm_get_usb_dev(interface, id, &driver);
-}
-
-static void udl_usb_disconnect(struct usb_interface *interface)
-{
-	struct drm_device *dev = usb_get_intfdata(interface);
-
-	drm_kms_helper_poll_disable(dev);
-	drm_connector_unplug_all(dev);
-	udl_fbdev_unplug(dev);
-	udl_drop_usb(dev);
-	drm_unplug_dev(dev);
-}
-
 static const struct vm_operations_struct udl_gem_vm_ops = {
 	.fault = udl_gem_fault,
 	.open = drm_gem_vm_open,
@@ -102,6 +62,61 @@ static struct drm_driver driver = {
 	.patchlevel = DRIVER_PATCHLEVEL,
 };
 
+static int udl_usb_probe(struct usb_interface *interface,
+			 const struct usb_device_id *id)
+{
+	struct usb_device *udev = interface_to_usbdev(interface);
+	struct drm_device *dev;
+	int r;
+
+	dev = drm_dev_alloc(&driver, &interface->dev);
+	if (!dev)
+		return -ENOMEM;
+
+	r = drm_dev_register(dev, (unsigned long)udev);
+	if (r)
+		goto err_free;
+
+	usb_set_intfdata(interface, dev);
+	DRM_INFO("Initialized udl on minor %d\n", dev->primary->index);
+
+	return 0;
+
+err_free:
+	drm_dev_unref(dev);
+	return r;
+}
+
+static void udl_usb_disconnect(struct usb_interface *interface)
+{
+	struct drm_device *dev = usb_get_intfdata(interface);
+
+	drm_kms_helper_poll_disable(dev);
+	drm_connector_unplug_all(dev);
+	udl_fbdev_unplug(dev);
+	udl_drop_usb(dev);
+	drm_unplug_dev(dev);
+}
+
+/*
+ * There are many DisplayLink-based graphics products, all with unique PIDs.
+ * So we match on DisplayLink's VID + Vendor-Defined Interface Class (0xff)
+ * We also require a match on SubClass (0x00) and Protocol (0x00),
+ * which is compatible with all known USB 2.0 era graphics chips and firmware,
+ * but allows DisplayLink to increment those for any future incompatible chips
+ */
+static struct usb_device_id id_table[] = {
+	{.idVendor = 0x17e9, .bInterfaceClass = 0xff,
+	 .bInterfaceSubClass = 0x00,
+	 .bInterfaceProtocol = 0x00,
+	 .match_flags = USB_DEVICE_ID_MATCH_VENDOR |
+			USB_DEVICE_ID_MATCH_INT_CLASS |
+			USB_DEVICE_ID_MATCH_INT_SUBCLASS |
+			USB_DEVICE_ID_MATCH_INT_PROTOCOL,},
+	{},
+};
+MODULE_DEVICE_TABLE(usb, id_table);
+
 static struct usb_driver udl_driver = {
 	.name = "udl",
 	.probe = udl_usb_probe,
@@ -111,13 +126,14 @@ static struct usb_driver udl_driver = {
 
 static int __init udl_init(void)
 {
-	return drm_usb_init(&driver, &udl_driver);
+	return usb_register(&udl_driver);
 }
 
 static void __exit udl_exit(void)
 {
-	drm_usb_exit(&driver, &udl_driver);
+	usb_deregister(&udl_driver);
 }
 
 module_init(udl_init);
 module_exit(udl_exit);
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 1fbf7b357f16..51e10ee77f39 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -47,6 +47,7 @@ struct udl_fbdev;
 struct udl_device {
 	struct device *dev;
 	struct drm_device *ddev;
+	struct usb_device *udev;
 
 	int sku_pixel_limit;
 
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index 42795674bc07..33dbfb2c4748 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -202,7 +202,7 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 		}
 		unode->urb = urb;
 
-		buf = usb_alloc_coherent(udl->ddev->usbdev, MAX_TRANSFER, GFP_KERNEL,
+		buf = usb_alloc_coherent(udl->udev, MAX_TRANSFER, GFP_KERNEL,
 					 &urb->transfer_dma);
 		if (!buf) {
 			kfree(unode);
@@ -211,7 +211,7 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 		}
 
 		/* urb->transfer_buffer_length set to actual before submit */
-		usb_fill_bulk_urb(urb, udl->ddev->usbdev, usb_sndbulkpipe(udl->ddev->usbdev, 1),
+		usb_fill_bulk_urb(urb, udl->udev, usb_sndbulkpipe(udl->udev, 1),
 			buf, size, udl_urb_completion, unode);
 		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 
@@ -282,6 +282,7 @@ int udl_submit_urb(struct drm_device *dev, struct urb *urb, size_t len)
 
 int udl_driver_load(struct drm_device *dev, unsigned long flags)
 {
+	struct usb_device *udev = (void*)flags;
 	struct udl_device *udl;
 	int ret = -ENOMEM;
 
@@ -290,10 +291,11 @@ int udl_driver_load(struct drm_device *dev, unsigned long flags)
 	if (!udl)
 		return -ENOMEM;
 
+	udl->udev = udev;
 	udl->ddev = dev;
 	dev->dev_private = udl;
 
-	if (!udl_parse_vendor_descriptor(dev, dev->usbdev)) {
+	if (!udl_parse_vendor_descriptor(dev, udl->udev)) {
 		ret = -ENODEV;
 		DRM_ERROR("firmware not recognized. Assume incompatible device\n");
 		goto err;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 5ae388a9bb98..0e73aad225b2 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1020,7 +1020,6 @@ struct drm_device {
 #endif
 
 	struct platform_device *platformdev; /**< Platform device struture */
-	struct usb_device *usbdev;
 
 	struct drm_sg_mem *sg;	/**< Scatter gather memory */
 	unsigned int num_crtcs;                  /**< Number of CRTCs on this device */
diff --git a/include/drm/drm_usb.h b/include/drm/drm_usb.h
deleted file mode 100644
index 33506c11da8b..000000000000
--- a/include/drm/drm_usb.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef DRM_USB_H
-#define DRM_USB_H
-
-#include <drmP.h>
-
-#include <linux/usb.h>
-
-extern int drm_usb_init(struct drm_driver *driver, struct usb_driver *udriver);
-extern void drm_usb_exit(struct drm_driver *driver, struct usb_driver *udriver);
-
-int drm_get_usb_dev(struct usb_interface *interface,
-		    const struct usb_device_id *id,
-		    struct drm_driver *driver);
-
-#endif
-- 
cgit v1.2.3


From bb6d822ec546603bca01f7ba17c52f0f4f80e329 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Fri, 29 Aug 2014 12:12:46 +0200
Subject: drm: move drm-lock API to drm_legacy.h

Same as the other legacy APIs, most of this is internal, so prefix it with
drm_legacy_* and move into drm_legacy.h.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_fops.c          |  6 +++---
 drivers/gpu/drm/drm_ioctl.c         |  4 ++--
 drivers/gpu/drm/drm_legacy.h        |  9 +++++++++
 drivers/gpu/drm/drm_lock.c          | 20 +++++++++++---------
 drivers/gpu/drm/i810/i810_dma.c     |  4 ++--
 drivers/gpu/drm/savage/savage_bci.c |  4 ++--
 drivers/gpu/drm/sis/sis_mm.c        |  6 +++---
 drivers/gpu/drm/via/via_mm.c        |  6 +++---
 include/drm/drmP.h                  | 14 +++-----------
 9 files changed, 38 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 12e6a1cd804d..b419990042b0 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -268,11 +268,11 @@ static void drm_master_release(struct drm_device *dev, struct file *filp)
 {
 	struct drm_file *file_priv = filp->private_data;
 
-	if (drm_i_have_hw_lock(dev, file_priv)) {
+	if (drm_legacy_i_have_hw_lock(dev, file_priv)) {
 		DRM_DEBUG("File %p released, freeing lock for context %d\n",
 			  filp, _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
-		drm_lock_free(&file_priv->master->lock,
-			      _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
+		drm_legacy_lock_free(&file_priv->master->lock,
+				     _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
 	}
 }
 
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 3a1349f82b41..187dfaaeb491 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -82,8 +82,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_ADD_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_IOCTL_RM_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_LOCK, drm_lock, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_UNLOCK, drm_unlock, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_LOCK, drm_legacy_lock, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_UNLOCK, drm_legacy_unlock, DRM_AUTH),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_FINISH, drm_noop, DRM_AUTH),
 
diff --git a/drivers/gpu/drm/drm_legacy.h b/drivers/gpu/drm/drm_legacy.h
index f2d076823b2d..3049af5a01b3 100644
--- a/drivers/gpu/drm/drm_legacy.h
+++ b/drivers/gpu/drm/drm_legacy.h
@@ -83,4 +83,13 @@ struct drm_agp_mem {
 	struct list_head head;
 };
 
+/*
+ * Generic Userspace Locking-API
+ */
+
+int drm_legacy_i_have_hw_lock(struct drm_device *d, struct drm_file *f);
+int drm_legacy_lock(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_unlock(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_lock_free(struct drm_lock_data *lock, unsigned int ctx);
+
 #endif /* __DRM_LEGACY_H__ */
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index 60f148134e6a..727b032292b4 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -52,7 +52,8 @@ static int drm_lock_take(struct drm_lock_data *lock_data, unsigned int context);
  *
  * Add the current task to the lock wait queue, and attempt to take to lock.
  */
-int drm_lock(struct drm_device *dev, void *data, struct drm_file *file_priv)
+int drm_legacy_lock(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
 {
 	DECLARE_WAITQUEUE(entry, current);
 	struct drm_lock *lock = data;
@@ -146,7 +147,7 @@ int drm_lock(struct drm_device *dev, void *data, struct drm_file *file_priv)
  *
  * Transfer and free the lock.
  */
-int drm_unlock(struct drm_device *dev, void *data, struct drm_file *file_priv)
+int drm_legacy_unlock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_lock *lock = data;
 	struct drm_master *master = file_priv->master;
@@ -157,7 +158,7 @@ int drm_unlock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 		return -EINVAL;
 	}
 
-	if (drm_lock_free(&master->lock, lock->context)) {
+	if (drm_legacy_lock_free(&master->lock, lock->context)) {
 		/* FIXME: Should really bail out here. */
 	}
 
@@ -250,7 +251,7 @@ static int drm_lock_transfer(struct drm_lock_data *lock_data,
  * Marks the lock as not held, via the \p cmpxchg instruction. Wakes any task
  * waiting on the lock queue.
  */
-int drm_lock_free(struct drm_lock_data *lock_data, unsigned int context)
+int drm_legacy_lock_free(struct drm_lock_data *lock_data, unsigned int context)
 {
 	unsigned int old, new, prev;
 	volatile unsigned int *lock = &lock_data->hw_lock->lock;
@@ -324,7 +325,7 @@ static int drm_notifier(void *priv)
  * having to worry about starvation.
  */
 
-void drm_idlelock_take(struct drm_lock_data *lock_data)
+void drm_legacy_idlelock_take(struct drm_lock_data *lock_data)
 {
 	int ret;
 
@@ -341,9 +342,9 @@ void drm_idlelock_take(struct drm_lock_data *lock_data)
 	}
 	spin_unlock_bh(&lock_data->spinlock);
 }
-EXPORT_SYMBOL(drm_idlelock_take);
+EXPORT_SYMBOL(drm_legacy_idlelock_take);
 
-void drm_idlelock_release(struct drm_lock_data *lock_data)
+void drm_legacy_idlelock_release(struct drm_lock_data *lock_data)
 {
 	unsigned int old, prev;
 	volatile unsigned int *lock = &lock_data->hw_lock->lock;
@@ -361,9 +362,10 @@ void drm_idlelock_release(struct drm_lock_data *lock_data)
 	}
 	spin_unlock_bh(&lock_data->spinlock);
 }
-EXPORT_SYMBOL(drm_idlelock_release);
+EXPORT_SYMBOL(drm_legacy_idlelock_release);
 
-int drm_i_have_hw_lock(struct drm_device *dev, struct drm_file *file_priv)
+int drm_legacy_i_have_hw_lock(struct drm_device *dev,
+			      struct drm_file *file_priv)
 {
 	struct drm_master *master = file_priv->master;
 	return (file_priv->lock_count && master->lock.hw_lock &&
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index bae897de9468..c97e2ff6a35a 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -1215,9 +1215,9 @@ void i810_driver_preclose(struct drm_device *dev, struct drm_file *file_priv)
 	}
 
 	if (file_priv->master && file_priv->master->lock.hw_lock) {
-		drm_idlelock_take(&file_priv->master->lock);
+		drm_legacy_idlelock_take(&file_priv->master->lock);
 		i810_driver_reclaim_buffers(dev, file_priv);
-		drm_idlelock_release(&file_priv->master->lock);
+		drm_legacy_idlelock_release(&file_priv->master->lock);
 	} else {
 		/* master disappeared, clean up stuff anyway and hope nothing
 		 * goes wrong */
diff --git a/drivers/gpu/drm/savage/savage_bci.c b/drivers/gpu/drm/savage/savage_bci.c
index 82a078ca04f7..9288d3037ce5 100644
--- a/drivers/gpu/drm/savage/savage_bci.c
+++ b/drivers/gpu/drm/savage/savage_bci.c
@@ -1051,7 +1051,7 @@ void savage_reclaim_buffers(struct drm_device *dev, struct drm_file *file_priv)
 		return;
 
 	if (file_priv->master && file_priv->master->lock.hw_lock) {
-		drm_idlelock_take(&file_priv->master->lock);
+		drm_legacy_idlelock_take(&file_priv->master->lock);
 		release_idlelock = 1;
 	}
 
@@ -1070,7 +1070,7 @@ void savage_reclaim_buffers(struct drm_device *dev, struct drm_file *file_priv)
 	}
 
 	if (release_idlelock)
-		drm_idlelock_release(&file_priv->master->lock);
+		drm_legacy_idlelock_release(&file_priv->master->lock);
 }
 
 const struct drm_ioctl_desc savage_ioctls[] = {
diff --git a/drivers/gpu/drm/sis/sis_mm.c b/drivers/gpu/drm/sis/sis_mm.c
index 77f288e4a0a6..93ad8a5704d1 100644
--- a/drivers/gpu/drm/sis/sis_mm.c
+++ b/drivers/gpu/drm/sis/sis_mm.c
@@ -319,12 +319,12 @@ void sis_reclaim_buffers_locked(struct drm_device *dev,
 	if (!(file->minor->master && file->master->lock.hw_lock))
 		return;
 
-	drm_idlelock_take(&file->master->lock);
+	drm_legacy_idlelock_take(&file->master->lock);
 
 	mutex_lock(&dev->struct_mutex);
 	if (list_empty(&file_priv->obj_list)) {
 		mutex_unlock(&dev->struct_mutex);
-		drm_idlelock_release(&file->master->lock);
+		drm_legacy_idlelock_release(&file->master->lock);
 
 		return;
 	}
@@ -345,7 +345,7 @@ void sis_reclaim_buffers_locked(struct drm_device *dev,
 	}
 	mutex_unlock(&dev->struct_mutex);
 
-	drm_idlelock_release(&file->master->lock);
+	drm_legacy_idlelock_release(&file->master->lock);
 
 	return;
 }
diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c
index d70b1e1544bf..4f20742e7788 100644
--- a/drivers/gpu/drm/via/via_mm.c
+++ b/drivers/gpu/drm/via/via_mm.c
@@ -211,12 +211,12 @@ void via_reclaim_buffers_locked(struct drm_device *dev,
 	if (!(file->minor->master && file->master->lock.hw_lock))
 		return;
 
-	drm_idlelock_take(&file->master->lock);
+	drm_legacy_idlelock_take(&file->master->lock);
 
 	mutex_lock(&dev->struct_mutex);
 	if (list_empty(&file_priv->obj_list)) {
 		mutex_unlock(&dev->struct_mutex);
-		drm_idlelock_release(&file->master->lock);
+		drm_legacy_idlelock_release(&file->master->lock);
 
 		return;
 	}
@@ -231,7 +231,7 @@ void via_reclaim_buffers_locked(struct drm_device *dev,
 	}
 	mutex_unlock(&dev->struct_mutex);
 
-	drm_idlelock_release(&file->master->lock);
+	drm_legacy_idlelock_release(&file->master->lock);
 
 	return;
 }
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 0e73aad225b2..be1160fa5ebc 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1143,22 +1143,11 @@ void drm_clflush_pages(struct page *pages[], unsigned long num_pages);
 void drm_clflush_sg(struct sg_table *st);
 void drm_clflush_virt_range(void *addr, unsigned long length);
 
-				/* Locking IOCTL support (drm_lock.h) */
-extern int drm_lock(struct drm_device *dev, void *data,
-		    struct drm_file *file_priv);
-extern int drm_unlock(struct drm_device *dev, void *data,
-		      struct drm_file *file_priv);
-extern int drm_lock_free(struct drm_lock_data *lock_data, unsigned int context);
-extern void drm_idlelock_take(struct drm_lock_data *lock_data);
-extern void drm_idlelock_release(struct drm_lock_data *lock_data);
-
 /*
  * These are exported to drivers so that they can implement fencing using
  * DMA quiscent + idle. DMA quiescent usually requires the hardware lock.
  */
 
-extern int drm_i_have_hw_lock(struct drm_device *dev, struct drm_file *file_priv);
-
 				/* DMA support (drm_dma.h) */
 extern int drm_legacy_dma_setup(struct drm_device *dev);
 extern void drm_legacy_dma_takedown(struct drm_device *dev);
@@ -1363,6 +1352,9 @@ int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
 
 void drm_legacy_vma_flush(struct drm_device *d);
 
+void drm_legacy_idlelock_take(struct drm_lock_data *lock);
+void drm_legacy_idlelock_release(struct drm_lock_data *lock);
+
 			       /* sysfs support (drm_sysfs.c) */
 struct drm_sysfs_class;
 extern struct class *drm_sysfs_create(struct module *owner, char *name);
-- 
cgit v1.2.3


From a0c7b164ad115ec0556dc0904ee2218cbc5cedfa Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 9 Sep 2014 23:13:57 +0100
Subject: regulator: of: Provide simplified DT parsing method

Currently regulator drivers which support DT all repeat very similar code
to supply a list of known regulator identifiers to be matched with DT,
convert that to platform data which is then matched up with the regulators
as they are registered. This is both fiddly to get right and for devices
which can use the standard helpers to provide their operations is the main
source of code in the driver.

Since this code is essentially identical for most drivers we can factor it
out into the core, moving the identifiers in the match table into the
regulator descriptors and also allowing drivers to pass in the name of the
subnode to search. When a driver provides an of_match string for the
regulator the core will attempt to use that to obtain init_data, allowing
the driver to remove all explicit code for DT parsing and simply provide
data instead.

The current code leaks the phandles for the child nodes, this will be
addressed incrementally and makes no practical difference for FDT anyway
as the DT data structures are never freed.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/core.c         | 10 +++++---
 drivers/regulator/internal.h     |  4 ++++
 drivers/regulator/of_regulator.c | 51 ++++++++++++++++++++++++++++++++++++++++
 include/linux/regulator/driver.h |  4 ++++
 4 files changed, 66 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a3c3785901f5..496002efd961 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -3516,12 +3516,17 @@ regulator_register(const struct regulator_desc *regulator_desc,
 		return ERR_PTR(-EINVAL);
 	}
 
-	init_data = config->init_data;
-
 	rdev = kzalloc(sizeof(struct regulator_dev), GFP_KERNEL);
 	if (rdev == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	init_data = regulator_of_get_init_data(dev, regulator_desc,
+					       &rdev->dev.of_node);
+	if (!init_data) {
+		init_data = config->init_data;
+		rdev->dev.of_node = of_node_get(config->of_node);
+	}
+
 	mutex_lock(&regulator_list_mutex);
 
 	mutex_init(&rdev->mutex);
@@ -3548,7 +3553,6 @@ regulator_register(const struct regulator_desc *regulator_desc,
 
 	/* register with sysfs */
 	rdev->dev.class = &regulator_class;
-	rdev->dev.of_node = of_node_get(config->of_node);
 	rdev->dev.parent = dev;
 	dev_set_name(&rdev->dev, "regulator.%d",
 		     atomic_inc_return(&regulator_no) - 1);
diff --git a/drivers/regulator/internal.h b/drivers/regulator/internal.h
index 84bbda10c396..a6043ad32ead 100644
--- a/drivers/regulator/internal.h
+++ b/drivers/regulator/internal.h
@@ -35,4 +35,8 @@ struct regulator {
 	struct dentry *debugfs;
 };
 
+struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
+			         const struct regulator_desc *desc,
+				 struct device_node **node);
+
 #endif
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index ee5e67bc8d5b..7a51814abdc5 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -14,8 +14,11 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/regulator/machine.h>
+#include <linux/regulator/driver.h>
 #include <linux/regulator/of_regulator.h>
 
+#include "internal.h"
+
 static void of_get_regulation_constraints(struct device_node *np,
 					struct regulator_init_data **init_data)
 {
@@ -189,3 +192,51 @@ int of_regulator_match(struct device *dev, struct device_node *node,
 	return count;
 }
 EXPORT_SYMBOL_GPL(of_regulator_match);
+
+struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
+					    const struct regulator_desc *desc,
+					    struct device_node **node)
+{
+	struct device_node *search, *child;
+	struct regulator_init_data *init_data = NULL;
+	const char *name;
+
+	if (!dev->of_node || !desc->of_match)
+		return NULL;
+
+	if (desc->regulators_node)
+		search = of_get_child_by_name(dev->of_node,
+					      desc->regulators_node);
+	else
+		search = dev->of_node;
+
+	if (!search) {
+		dev_err(dev, "Failed to find regulator container node\n");
+		return NULL;
+	}
+
+	for_each_child_of_node(search, child) {
+		name = of_get_property(child, "regulator-compatible", NULL);
+		if (!name)
+			name = child->name;
+
+		if (strcmp(desc->of_match, name))
+			continue;
+
+		init_data = of_get_regulator_init_data(dev, child);
+		if (!init_data) {
+			dev_err(dev,
+				"failed to parse DT for regulator %s\n",
+				child->name);
+			break;
+		}
+
+		of_node_get(child);
+		*node = child;
+		break;
+	}
+
+	of_node_put(search);
+
+	return init_data;
+}
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index bbe03a1924c0..c35f5f97a147 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -203,6 +203,8 @@ enum regulator_type {
  *
  * @name: Identifying name for the regulator.
  * @supply_name: Identifying the regulator supply
+ * @of_match: Name used to identify regulator in DT.
+ * @regulators_node: Name of node containing regulator definitions in DT.
  * @id: Numerical identifier for the regulator.
  * @ops: Regulator operations table.
  * @irq: Interrupt number for the regulator.
@@ -242,6 +244,8 @@ enum regulator_type {
 struct regulator_desc {
 	const char *name;
 	const char *supply_name;
+	const char *of_match;
+	const char *regulators_node;
 	int id;
 	bool continuous_voltage_range;
 	unsigned n_voltages;
-- 
cgit v1.2.3


From e1effa0144a1ddf5b456c388ffaf784f3c5163fd Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 5 Aug 2014 17:19:38 -0400
Subject: ftrace: Annotate the ops operation on update

Add three new flags for ftrace_ops:

  FTRACE_OPS_FL_ADDING
  FTRACE_OPS_FL_REMOVING
  FTRACE_OPS_FL_MODIFYING

These will be set for the ftrace_ops when they are first added
to the function tracing, being removed from function tracing
or just having their functions changed from function tracing,
respectively.

This will be needed to remove the tramp_hash, which can grow quite
big. The tramp_hash is used to note what functions a ftrace_ops
is using a trampoline for. Denoting which ftrace_ops is being
modified, will allow us to use the ftrace_ops hashes themselves,
which are much smaller as they have a global flag to denote if
a ftrace_ops is tracing all functions, as well as a notrace hash
if the ftrace_ops is tracing all but a few. The tramp_hash just
creates a hash item for every function, which can go into the 10s
of thousands if all functions are using the ftrace_ops trampoline.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  6 ++++++
 kernel/trace/ftrace.c  | 45 +++++++++++++++++++++++++++++++++++++++------
 2 files changed, 45 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ef37286547fc..d9216f6385d9 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -91,6 +91,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  * INITIALIZED - The ftrace_ops has already been initialized (first use time
  *            register_ftrace_function() is called, it will initialized the ops)
  * DELETED - The ops are being deleted, do not let them be registered again.
+ * ADDING  - The ops is in the process of being added.
+ * REMOVING - The ops is in the process of being removed.
+ * MODIFYING - The ops is in the process of changing its filter functions.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -102,6 +105,9 @@ enum {
 	FTRACE_OPS_FL_STUB			= 1 << 6,
 	FTRACE_OPS_FL_INITIALIZED		= 1 << 7,
 	FTRACE_OPS_FL_DELETED			= 1 << 8,
+	FTRACE_OPS_FL_ADDING			= 1 << 9,
+	FTRACE_OPS_FL_REMOVING			= 1 << 10,
+	FTRACE_OPS_FL_MODIFYING			= 1 << 11,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 858ac16f8492..e43c793093e5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1057,6 +1057,12 @@ static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
 static struct ftrace_ops *removed_ops;
 
+/*
+ * Set when doing a global update, like enabling all recs or disabling them.
+ * It is not set when just updating a single ftrace_ops.
+ */
+static bool update_all_ops;
+
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
 # error Dynamic ftrace depends on MCOUNT_RECORD
 #endif
@@ -2366,6 +2372,13 @@ static void ftrace_run_update_code(int command)
 	FTRACE_WARN_ON(ret);
 }
 
+static void ftrace_run_modify_code(struct ftrace_ops *ops, int command)
+{
+	ops->flags |= FTRACE_OPS_FL_MODIFYING;
+	ftrace_run_update_code(command);
+	ops->flags &= ~FTRACE_OPS_FL_MODIFYING;
+}
+
 static ftrace_func_t saved_ftrace_func;
 static int ftrace_start_up;
 
@@ -2387,6 +2400,13 @@ static void ftrace_startup_enable(int command)
 	ftrace_run_update_code(command);
 }
 
+static void ftrace_startup_all(int command)
+{
+	update_all_ops = true;
+	ftrace_startup_enable(command);
+	update_all_ops = false;
+}
+
 static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
 	int ret;
@@ -2401,12 +2421,22 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 	ftrace_start_up++;
 	command |= FTRACE_UPDATE_CALLS;
 
-	ops->flags |= FTRACE_OPS_FL_ENABLED;
+	/*
+	 * Note that ftrace probes uses this to start up
+	 * and modify functions it will probe. But we still
+	 * set the ADDING flag for modification, as probes
+	 * do not have trampolines. If they add them in the
+	 * future, then the probes will need to distinguish
+	 * between adding and updating probes.
+	 */
+	ops->flags |= FTRACE_OPS_FL_ENABLED | FTRACE_OPS_FL_ADDING;
 
 	ftrace_hash_rec_enable(ops, 1);
 
 	ftrace_startup_enable(command);
 
+	ops->flags &= ~FTRACE_OPS_FL_ADDING;
+
 	return 0;
 }
 
@@ -2456,11 +2486,12 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 * If the ops uses a trampoline, then it needs to be
 	 * tested first on update.
 	 */
+	ops->flags |= FTRACE_OPS_FL_REMOVING;
 	removed_ops = ops;
 
 	ftrace_run_update_code(command);
 
-	removed_ops = NULL;
+	ops->flags &= ~FTRACE_OPS_FL_REMOVING;
 
 	/*
 	 * Dynamic ops may be freed, we must make sure that all
@@ -3373,7 +3404,7 @@ static void __enable_ftrace_function_probe(void)
 	if (ftrace_probe_registered) {
 		/* still need to update the function call sites */
 		if (ftrace_enabled)
-			ftrace_run_update_code(FTRACE_UPDATE_CALLS);
+			ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS);
 		return;
 	}
 
@@ -3792,7 +3823,7 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 static void ftrace_ops_update_code(struct ftrace_ops *ops)
 {
 	if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled)
-		ftrace_run_update_code(FTRACE_UPDATE_CALLS);
+		ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS);
 }
 
 static int
@@ -4717,6 +4748,7 @@ core_initcall(ftrace_nodyn_init);
 
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
+static inline void ftrace_startup_all(int command) { }
 /* Keep as macros so we do not need to define the commands */
 # define ftrace_startup(ops, command)					\
 	({								\
@@ -5016,7 +5048,8 @@ static int ftrace_pid_add(int p)
 	set_ftrace_pid_task(pid);
 
 	ftrace_update_pid_func();
-	ftrace_startup_enable(0);
+
+	ftrace_startup_all(0);
 
 	mutex_unlock(&ftrace_lock);
 	return 0;
@@ -5045,7 +5078,7 @@ static void ftrace_pid_reset(void)
 	}
 
 	ftrace_update_pid_func();
-	ftrace_startup_enable(0);
+	ftrace_startup_all(0);
 
 	mutex_unlock(&ftrace_lock);
 }
-- 
cgit v1.2.3


From fef5aeeee9e3717e7aea991a7ae9ff6a7a2d4c85 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Thu, 24 Jul 2014 12:25:47 -0400
Subject: ftrace: Replace tramp_hash with old_*_hash to save space

Allowing function callbacks to declare their own trampolines requires
that each ftrace_ops that has a trampoline must have some sort of
accounting that keeps track of which ops has a trampoline attached
to a record.

The easy way to solve this was to add a "tramp_hash" that created a
hash entry for every function that a ops uses with a trampoline.
But since we can have literally tens of thousands of functions being
traced, that means we need tens of thousands of descriptors to map
the ops to the function in the hash. This is quite expensive and
can cause enabling and disabling the function graph tracer to take
some time to start and stop. It can take up to several seconds to
disable or enable all functions in the function graph tracer for this
reason.

The better approach albeit more complex, is to keep track of how ops
are being enabled and disabled, and use that along with the counting
of the number of ops attached to records, to determive what ops has
a trampoline attached to a record at enabling and disabling of
tracing.

To do this, the tramp_hash has been replaced with an old_filter_hash
and old_notrace_hash, which get the copy of the ops filter_hash and
notrace_hash respectively. The old hashes is kept until the ops has
been modified or removed and the old hashes are used with the logic
of the accounting to determine the ops that have the trampoline of
a record. The reason this has less of a footprint is due to the trick
that an "empty" hash in the filter_hash means "all functions" and
an empty hash in the notrace hash means "no functions" in the hash.

This is much more efficienct, doesn't have the delay, and takes up
much less memory, as we do not need to map all the functions but
just figure out which functions are mapped at the time it is
enabled or disabled.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h |   2 +-
 kernel/trace/ftrace.c  | 239 +++++++++++++++++--------------------------------
 2 files changed, 85 insertions(+), 156 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index d9216f6385d9..662697babd48 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -140,7 +140,7 @@ struct ftrace_ops {
 	int				nr_trampolines;
 	struct ftrace_ops_hash		local_hash;
 	struct ftrace_ops_hash		*func_hash;
-	struct ftrace_hash		*tramp_hash;
+	struct ftrace_ops_hash		old_hash;
 	unsigned long			trampoline;
 #endif
 };
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e43c793093e5..d325a1e76554 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1373,6 +1373,21 @@ update:
 	return 0;
 }
 
+static bool hash_contains_ip(unsigned long ip,
+			     struct ftrace_ops_hash *hash)
+{
+	/*
+	 * The function record is a match if it exists in the filter
+	 * hash and not in the notrace hash. Note, an emty hash is
+	 * considered a match for the filter hash, but an empty
+	 * notrace hash is considered not in the notrace hash.
+	 */
+	return (ftrace_hash_empty(hash->filter_hash) ||
+		ftrace_lookup_ip(hash->filter_hash, ip)) &&
+		(ftrace_hash_empty(hash->notrace_hash) ||
+		 !ftrace_lookup_ip(hash->notrace_hash, ip));
+}
+
 /*
  * Test the hashes for this ops to see if we want to call
  * the ops->func or not.
@@ -1388,8 +1403,7 @@ update:
 static int
 ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 {
-	struct ftrace_hash *filter_hash;
-	struct ftrace_hash *notrace_hash;
+	struct ftrace_ops_hash hash;
 	int ret;
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
@@ -1402,13 +1416,10 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 		return 0;
 #endif
 
-	filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash);
-	notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash);
+	hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash);
+	hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash);
 
-	if ((ftrace_hash_empty(filter_hash) ||
-	     ftrace_lookup_ip(filter_hash, ip)) &&
-	    (ftrace_hash_empty(notrace_hash) ||
-	     !ftrace_lookup_ip(notrace_hash, ip)))
+	if (hash_contains_ip(ip, &hash))
 		ret = 1;
 	else
 		ret = 0;
@@ -1520,46 +1531,6 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
 	return  keep_regs;
 }
 
-static void ftrace_remove_tramp(struct ftrace_ops *ops,
-				struct dyn_ftrace *rec)
-{
-	/* If TRAMP is not set, no ops should have a trampoline for this */
-	if (!(rec->flags & FTRACE_FL_TRAMP))
-		return;
-
-	rec->flags &= ~FTRACE_FL_TRAMP;
-
-	if ((!ftrace_hash_empty(ops->func_hash->filter_hash) &&
-	     !ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip)) ||
-	    ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip))
-		return;
-	/*
-	 * The tramp_hash entry will be removed at time
-	 * of update.
-	 */
-	ops->nr_trampolines--;
-}
-
-static void ftrace_clear_tramps(struct dyn_ftrace *rec, struct ftrace_ops *ops)
-{
-	struct ftrace_ops *op;
-
-	/* If TRAMP is not set, no ops should have a trampoline for this */
-	if (!(rec->flags & FTRACE_FL_TRAMP))
-		return;
-
-	do_for_each_ftrace_op(op, ftrace_ops_list) {
-		/*
-		 * This function is called to clear other tramps
-		 * not the one that is being updated.
-		 */
-		if (op == ops)
-			continue;
-		if (op->nr_trampolines)
-			ftrace_remove_tramp(op, rec);
-	} while_for_each_ftrace_op(op);
-}
-
 static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)
@@ -1648,18 +1619,16 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			 * function, and the ops has a trampoline registered
 			 * for it, then we can call it directly.
 			 */
-			if (ftrace_rec_count(rec) == 1 && ops->trampoline) {
+			if (ftrace_rec_count(rec) == 1 && ops->trampoline)
 				rec->flags |= FTRACE_FL_TRAMP;
-				ops->nr_trampolines++;
-			} else {
+			else
 				/*
 				 * If we are adding another function callback
 				 * to this function, and the previous had a
 				 * custom trampoline in use, then we need to go
 				 * back to the default trampoline.
 				 */
-				ftrace_clear_tramps(rec, ops);
-			}
+				rec->flags &= ~FTRACE_FL_TRAMP;
 
 			/*
 			 * If any ops wants regs saved for this function
@@ -1672,9 +1641,6 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				return;
 			rec->flags--;
 
-			if (ops->trampoline && !ftrace_rec_count(rec))
-				ftrace_remove_tramp(ops, rec);
-
 			/*
 			 * If the rec had REGS enabled and the ops that is
 			 * being removed had REGS set, then see if there is
@@ -1688,6 +1654,17 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 					rec->flags &= ~FTRACE_FL_REGS;
 			}
 
+			/*
+			 * If the rec had TRAMP enabled, then it needs to
+			 * be cleared. As TRAMP can only be enabled iff
+			 * there is only a single ops attached to it.
+			 * In otherwords, always disable it on decrementing.
+			 * In the future, we may set it if rec count is
+			 * decremented to one, and the ops that is left
+			 * has a trampoline.
+			 */
+			rec->flags &= ~FTRACE_FL_TRAMP;
+
 			/*
 			 * flags will be cleared in ftrace_check_record()
 			 * if rec count is zero.
@@ -1910,15 +1887,14 @@ static struct ftrace_ops *
 ftrace_find_tramp_ops_any(struct dyn_ftrace *rec)
 {
 	struct ftrace_ops *op;
+	unsigned long ip = rec->ip;
 
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
 
 		if (!op->trampoline)
 			continue;
 
-		if (ftrace_lookup_ip(op->func_hash->filter_hash, rec->ip) &&
-		    (ftrace_hash_empty(op->func_hash->notrace_hash) ||
-		     !ftrace_lookup_ip(op->func_hash->notrace_hash, rec->ip)))
+		if (hash_contains_ip(ip, op->func_hash))
 			return op;
 	} while_for_each_ftrace_op(op);
 
@@ -1929,18 +1905,51 @@ static struct ftrace_ops *
 ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec)
 {
 	struct ftrace_ops *op;
+	unsigned long ip = rec->ip;
 
-	/* Removed ops need to be tested first */
-	if (removed_ops && removed_ops->tramp_hash) {
-		if (ftrace_lookup_ip(removed_ops->tramp_hash, rec->ip))
+	/*
+	 * Need to check removed ops first.
+	 * If they are being removed, and this rec has a tramp,
+	 * and this rec is in the ops list, then it would be the
+	 * one with the tramp.
+	 */
+	if (removed_ops) {
+		if (hash_contains_ip(ip, &removed_ops->old_hash))
 			return removed_ops;
 	}
 
+	/*
+	 * Need to find the current trampoline for a rec.
+	 * Now, a trampoline is only attached to a rec if there
+	 * was a single 'ops' attached to it. But this can be called
+	 * when we are adding another op to the rec or removing the
+	 * current one. Thus, if the op is being added, we can
+	 * ignore it because it hasn't attached itself to the rec
+	 * yet. That means we just need to find the op that has a
+	 * trampoline and is not beeing added.
+	 */
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
-		if (!op->tramp_hash)
+
+		if (!op->trampoline)
+			continue;
+
+		/*
+		 * If the ops is being added, it hasn't gotten to
+		 * the point to be removed from this tree yet.
+		 */
+		if (op->flags & FTRACE_OPS_FL_ADDING)
 			continue;
 
-		if (ftrace_lookup_ip(op->tramp_hash, rec->ip))
+		/*
+		 * If the ops is not being added and has a trampoline,
+		 * then it must be the one that we want!
+		 */
+		if (hash_contains_ip(ip, op->func_hash))
+			return op;
+
+		/* If the ops is being modified, it may be in the old hash. */
+		if ((op->flags & FTRACE_OPS_FL_MODIFYING) &&
+		    hash_contains_ip(ip, &op->old_hash))
 			return op;
 
 	} while_for_each_ftrace_op(op);
@@ -1952,10 +1961,11 @@ static struct ftrace_ops *
 ftrace_find_tramp_ops_new(struct dyn_ftrace *rec)
 {
 	struct ftrace_ops *op;
+	unsigned long ip = rec->ip;
 
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
 		/* pass rec in as regs to have non-NULL val */
-		if (ftrace_ops_test(op, rec->ip, rec))
+		if (hash_contains_ip(ip, op->func_hash))
 			return op;
 	} while_for_each_ftrace_op(op);
 
@@ -2262,92 +2272,6 @@ void __weak arch_ftrace_update_code(int command)
 	ftrace_run_stop_machine(command);
 }
 
-static int ftrace_save_ops_tramp_hash(struct ftrace_ops *ops)
-{
-	struct ftrace_page *pg;
-	struct dyn_ftrace *rec;
-	int size, bits;
-	int ret;
-
-	size = ops->nr_trampolines;
-	bits = 0;
-	/*
-	 * Make the hash size about 1/2 the # found
-	 */
-	for (size /= 2; size; size >>= 1)
-		bits++;
-
-	ops->tramp_hash = alloc_ftrace_hash(bits);
-	/*
-	 * TODO: a failed allocation is going to screw up
-	 * the accounting of what needs to be modified
-	 * and not. For now, we kill ftrace if we fail
-	 * to allocate here. But there are ways around this,
-	 * but that will take a little more work.
-	 */
-	if (!ops->tramp_hash)
-		return -ENOMEM;
-
-	do_for_each_ftrace_rec(pg, rec) {
-		if (ftrace_rec_count(rec) == 1 &&
-		    ftrace_ops_test(ops, rec->ip, rec)) {
-
-			/*
-			 * If another ops adds to a rec, the rec will
-			 * lose its trampoline and never get it back
-			 * until all ops are off of it.
-			 */
-			if (!(rec->flags & FTRACE_FL_TRAMP))
-				continue;
-
-			/* This record had better have a trampoline */
-			if (FTRACE_WARN_ON(!(rec->flags & FTRACE_FL_TRAMP_EN)))
-				return -1;
-
-			ret = add_hash_entry(ops->tramp_hash, rec->ip);
-			if (ret < 0)
-				return ret;
-		}
-	} while_for_each_ftrace_rec();
-
-	/* The number of recs in the hash must match nr_trampolines */
-	if (FTRACE_WARN_ON(ops->tramp_hash->count != ops->nr_trampolines))
-		pr_warn("count=%ld trampolines=%d\n",
-			ops->tramp_hash->count,
-			ops->nr_trampolines);
-
-	return 0;
-}
-
-static int ftrace_save_tramp_hashes(void)
-{
-	struct ftrace_ops *op;
-	int ret;
-
-	/*
-	 * Now that any trampoline is being used, we need to save the
-	 * hashes for the ops that have them. This allows the mapping
-	 * back from the record to the ops that has the trampoline to
-	 * know what code is being replaced. Modifying code must always
-	 * verify what it is changing.
-	 */
-	do_for_each_ftrace_op(op, ftrace_ops_list) {
-
-		/* The tramp_hash is recreated each time. */
-		free_ftrace_hash(op->tramp_hash);
-		op->tramp_hash = NULL;
-
-		if (op->nr_trampolines) {
-			ret = ftrace_save_ops_tramp_hash(op);
-			if (ret)
-				return ret;
-		}
-
-	} while_for_each_ftrace_op(op);
-
-	return 0;
-}
-
 static void ftrace_run_update_code(int command)
 {
 	int ret;
@@ -2367,9 +2291,6 @@ static void ftrace_run_update_code(int command)
 
 	ret = ftrace_arch_code_modify_post_process();
 	FTRACE_WARN_ON(ret);
-
-	ret = ftrace_save_tramp_hashes();
-	FTRACE_WARN_ON(ret);
 }
 
 static void ftrace_run_modify_code(struct ftrace_ops *ops, int command)
@@ -2489,8 +2410,16 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	ops->flags |= FTRACE_OPS_FL_REMOVING;
 	removed_ops = ops;
 
+	/* The trampoline logic checks the old hashes */
+	ops->old_hash.filter_hash = ops->func_hash->filter_hash;
+	ops->old_hash.notrace_hash = ops->func_hash->notrace_hash;
+
 	ftrace_run_update_code(command);
 
+	ops->old_hash.filter_hash = NULL;
+	ops->old_hash.notrace_hash = NULL;
+
+	removed_ops = NULL;
 	ops->flags &= ~FTRACE_OPS_FL_REMOVING;
 
 	/*
@@ -3017,7 +2946,7 @@ static int t_show(struct seq_file *m, void *v)
 			struct ftrace_ops *ops;
 
 			ops = ftrace_find_tramp_ops_any(rec);
-			if (ops && ops->trampoline)
+			if (ops)
 				seq_printf(m, "\ttramp: %pS",
 					   (void *)ops->trampoline);
 			else
-- 
cgit v1.2.3


From 3a630178fd5f30c285fd7016c5340a176b625913 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 7 Aug 2014 10:52:04 -0700
Subject: tracing: generate RCU warnings even when tracepoints are disabled

Dave Jones reported seeing a bug from one of my TLB tracepoints:

	http://lkml.kernel.org/r/20140806181801.GA4605@redhat.com

I've been running these patches for months and never saw this.
But, a big chunk of my testing, especially with all the debugging
enabled, was in a vm where intel_idle doesn't work.  On the
systems where I was using intel_idle, I never had lockdep enabled
and this tracepoint on at the same time.

This patch ensures that whenever we have lockdep available, we do
_some_ RCU activity at the site of the tracepoint, despite
whether the tracepoint's condition matches or even if the
tracepoint itself is completely disabled.  This is a bit of a
hack, but it is pretty self-contained.

I confirmed that with this patch plus lockdep I get the same
splat as Dave Jones did, but without enabling the tracepoint
explicitly.

Link: http://lkml.kernel.org/p/20140807175204.C257CAC5@viggo.jf.intel.com

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Dave Jones <davej@redhat.com>,
Cc: paulmck@linux.vnet.ibm.com
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/tracepoint.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index b1293f15f592..e08e21e5f601 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -157,6 +157,12 @@ extern void syscall_unregfunc(void);
  * Make sure the alignment of the structure in the __tracepoints section will
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
+ *
+ * When lockdep is enabled, we make sure to always do the RCU portions of
+ * the tracepoint code, regardless of whether tracing is on or we match the
+ * condition.  This lets us find RCU issues triggered with tracepoints even
+ * when this tracepoint is off.  This code has no purpose other than poking
+ * RCU a bit.
  */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
 	extern struct tracepoint __tracepoint_##name;			\
@@ -167,6 +173,11 @@ extern void syscall_unregfunc(void);
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond),,);			\
+		if (IS_ENABLED(CONFIG_LOCKDEP)) {			\
+			rcu_read_lock_sched_notrace();			\
+			rcu_dereference_sched(__tracepoint_##name.funcs);\
+			rcu_read_unlock_sched_notrace();		\
+		}							\
 	}								\
 	__DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args),		\
 		PARAMS(cond), PARAMS(data_proto), PARAMS(data_args))	\
-- 
cgit v1.2.3


From c858403943886a92eece9d0413aa65c48bbe6fa7 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Thu, 28 Aug 2014 15:56:00 +0900
Subject: drm/radeon: Add RADEON_GEM_CPU_ACCESS BO creation flag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This flag is a hint that userspace expects the BO to be accessed by the
CPU. We can use that hint to prevent such BOs from ever being stored in
the CPU inaccessible part of VRAM.

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_object.c | 11 +++++++++--
 include/uapi/drm/radeon_drm.h          |  2 ++
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index aadbd36e64b9..eef60aaf4e64 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -144,7 +144,12 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 
 	for (i = 0; i < c; ++i) {
 		rbo->placements[i].fpfn = 0;
-		rbo->placements[i].lpfn = 0;
+		if ((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
+		    (rbo->placements[i].flags & TTM_PL_FLAG_VRAM))
+			rbo->placements[i].lpfn =
+				rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
+		else
+			rbo->placements[i].lpfn = 0;
 	}
 
 	/*
@@ -152,7 +157,9 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 	 * improve fragmentation quality.
 	 * 512kb was measured as the most optimal number.
 	 */
-	if (rbo->tbo.mem.size > 512 * 1024) {
+	if (!((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
+	      (rbo->placements[i].flags & TTM_PL_FLAG_VRAM)) &&
+	    rbo->tbo.mem.size > 512 * 1024) {
 		for (i = 0; i < c; i++) {
 			rbo->placements[i].flags |= TTM_PL_FLAG_TOPDOWN;
 		}
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 375b6e656c54..f755f20d2b5c 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -801,6 +801,8 @@ struct drm_radeon_gem_info {
 #define RADEON_GEM_NO_BACKING_STORE	(1 << 0)
 #define RADEON_GEM_GTT_UC		(1 << 1)
 #define RADEON_GEM_GTT_WC		(1 << 2)
+/* BO is expected to be accessed by the CPU */
+#define RADEON_GEM_CPU_ACCESS		(1 << 3)
 
 struct drm_radeon_gem_create {
 	uint64_t	size;
-- 
cgit v1.2.3


From f266f04d33e5265e2f61ffc9d2b2f97214804995 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 28 Aug 2014 10:59:05 -0400
Subject: drm/radeon: add RADEON_GEM_NO_CPU_ACCESS BO creation flag (v4)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allows pinning of buffers in the non-CPU visible portion of
vram.

v2: incorporate Michel's comments.
v3: rebase on Michel's patch
v4: rebase on Michel's v2 patch

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
---
 drivers/gpu/drm/radeon/radeon_object.c | 1 +
 include/uapi/drm/radeon_drm.h          | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 3dbbd65336d5..8abee5fa93bd 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -313,6 +313,7 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 	for (i = 0; i < bo->placement.num_placement; i++) {
 		/* force to pin into visible video ram */
 		if ((bo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
+		    !(bo->flags & RADEON_GEM_NO_CPU_ACCESS) &&
 		    (!max_offset || max_offset > bo->rdev->mc.visible_vram_size))
 			bo->placements[i].lpfn =
 				bo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index f755f20d2b5c..50d0fb41a3bf 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -803,6 +803,8 @@ struct drm_radeon_gem_info {
 #define RADEON_GEM_GTT_WC		(1 << 2)
 /* BO is expected to be accessed by the CPU */
 #define RADEON_GEM_CPU_ACCESS		(1 << 3)
+/* CPU access is not expected to work for this BO */
+#define RADEON_GEM_NO_CPU_ACCESS	(1 << 4)
 
 struct drm_radeon_gem_create {
 	uint64_t	size;
-- 
cgit v1.2.3


From b440bde74f043c8ec31081cb59c9a53ade954701 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 10 Sep 2014 13:45:01 -0600
Subject: PCI: Add pci_ignore_hotplug() to ignore hotplug events for a device

Powering off a hot-pluggable device, e.g., with pci_set_power_state(D3cold),
normally generates a hot-remove event that unbinds the driver.

Some drivers expect to remain bound to a device even while they power it
off and back on again.  This can be dangerous, because if the device is
removed or replaced while it is powered off, the driver doesn't know that
anything changed.  But some drivers accept that risk.

Add pci_ignore_hotplug() for use by drivers that know their device cannot
be removed.  Using pci_ignore_hotplug() tells the PCI core that hot-plug
events for the device should be ignored.

The radeon and nouveau drivers use this to switch between a low-power,
integrated GPU and a higher-power, higher-performance discrete GPU.  They
power off the unused GPU, but they want to remain bound to it.

This is a reimplementation of f244d8b623da ("ACPIPHP / radeon / nouveau:
Fix VGA switcheroo problem related to hotplug") but extends it to work with
both acpiphp and pciehp.

This fixes a problem where systems with dual GPUs using the radeon drivers
become unusable, freezing every few seconds (see bugzillas below).  The
resume of the radeon device may also fail, e.g.,

This fixes problems on dual GPU systems where the radeon driver becomes
unusable because of problems while suspending the device, as in bug 79701:

    [drm] radeon: finishing device.
    radeon 0000:01:00.0: Userspace still has active objects !
    radeon 0000:01:00.0: ffff8800cb4ec288 ffff8800cb4ec000 16384 4294967297 force free
    ...
    WARNING: CPU: 0 PID: 67 at /home/apw/COD/linux/drivers/gpu/drm/radeon/radeon_gart.c:234 radeon_gart_unbind+0xd2/0xe0 [radeon]()
    trying to unbind memory from uninitialized GART !

or while resuming it, as in bug 77261:

    radeon 0000:01:00.0: ring 0 stalled for more than 10158msec
    radeon 0000:01:00.0: GPU lockup ...
    radeon 0000:01:00.0: GPU pci config reset
    pciehp 0000:00:01.0:pcie04: Card not present on Slot(1-1)
    radeon 0000:01:00.0: GPU reset succeeded, trying to resume
    *ERROR* radeon: dpm resume failed
    radeon 0000:01:00.0: Wait for MC idle timedout !

Link: https://bugzilla.kernel.org/show_bug.cgi?id=77261
Link: https://bugzilla.kernel.org/show_bug.cgi?id=79701
Reported-by: Shawn Starr <shawn.starr@rogers.com>
Reported-by: Jose P. <lbdkmjdf@sharklasers.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Rajat Jain <rajatxjain@gmail.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Dave Airlie <airlied@redhat.com>
CC: stable@vger.kernel.org	# v3.15+
---
 drivers/gpu/drm/nouveau/nouveau_drm.c |  1 +
 drivers/gpu/drm/radeon/radeon_drv.c   |  1 +
 drivers/pci/hotplug/acpiphp_glue.c    | 16 ++++++----------
 drivers/pci/hotplug/pciehp_hpc.c      | 12 ++++++++++++
 include/linux/pci.h                   |  6 ++++++
 5 files changed, 26 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 250a5e88c751..9c3af96a7153 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -627,6 +627,7 @@ int nouveau_pmops_suspend(struct device *dev)
 
 	pci_save_state(pdev);
 	pci_disable_device(pdev);
+	pci_ignore_hotplug(pdev);
 	pci_set_power_state(pdev, PCI_D3hot);
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 8df888908833..abbd87adfd75 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -440,6 +440,7 @@ static int radeon_pmops_runtime_suspend(struct device *dev)
 	ret = radeon_suspend_kms(drm_dev, false, false);
 	pci_save_state(pdev);
 	pci_disable_device(pdev);
+	pci_ignore_hotplug(pdev);
 	pci_set_power_state(pdev, PCI_D3cold);
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
 
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 70741c8c46a0..6cd5160fc057 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -560,19 +560,15 @@ static void disable_slot(struct acpiphp_slot *slot)
 	slot->flags &= (~SLOT_ENABLED);
 }
 
-static bool acpiphp_no_hotplug(struct acpi_device *adev)
-{
-	return adev && adev->flags.no_hotplug;
-}
-
 static bool slot_no_hotplug(struct acpiphp_slot *slot)
 {
-	struct acpiphp_func *func;
+	struct pci_bus *bus = slot->bus;
+	struct pci_dev *dev;
 
-	list_for_each_entry(func, &slot->funcs, sibling)
-		if (acpiphp_no_hotplug(func_to_acpi_device(func)))
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		if (PCI_SLOT(dev->devfn) == slot->device && dev->ignore_hotplug)
 			return true;
-
+	}
 	return false;
 }
 
@@ -645,7 +641,7 @@ static void trim_stale_devices(struct pci_dev *dev)
 
 		status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta);
 		alive = (ACPI_SUCCESS(status) && device_status_valid(sta))
-			|| acpiphp_no_hotplug(adev);
+			|| dev->ignore_hotplug;
 	}
 	if (!alive)
 		alive = pci_device_is_present(dev);
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 9da84b8b27d8..5e01ae39ec46 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -506,6 +506,8 @@ static irqreturn_t pcie_isr(int irq, void *dev_id)
 {
 	struct controller *ctrl = (struct controller *)dev_id;
 	struct pci_dev *pdev = ctrl_dev(ctrl);
+	struct pci_bus *subordinate = pdev->subordinate;
+	struct pci_dev *dev;
 	struct slot *slot = ctrl->slot;
 	u16 detected, intr_loc;
 
@@ -539,6 +541,16 @@ static irqreturn_t pcie_isr(int irq, void *dev_id)
 		wake_up(&ctrl->queue);
 	}
 
+	if (subordinate) {
+		list_for_each_entry(dev, &subordinate->devices, bus_list) {
+			if (dev->ignore_hotplug) {
+				ctrl_dbg(ctrl, "ignoring hotplug event %#06x (%s requested no hotplug)\n",
+					 intr_loc, pci_name(dev));
+				return IRQ_HANDLED;
+			}
+		}
+	}
+
 	if (!(intr_loc & ~PCI_EXP_SLTSTA_CC))
 		return IRQ_HANDLED;
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 61978a460841..96453f9bc8ba 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -303,6 +303,7 @@ struct pci_dev {
 						   D3cold, not set for devices
 						   powered on/off by the
 						   corresponding bridge */
+	unsigned int	ignore_hotplug:1;	/* Ignore hotplug events */
 	unsigned int	d3_delay;	/* D3->D0 transition time in ms */
 	unsigned int	d3cold_delay;	/* D3cold->D0 transition time in ms */
 
@@ -1021,6 +1022,11 @@ bool pci_dev_run_wake(struct pci_dev *dev);
 bool pci_check_pme_status(struct pci_dev *dev);
 void pci_pme_wakeup_bus(struct pci_bus *bus);
 
+static inline void pci_ignore_hotplug(struct pci_dev *dev)
+{
+	dev->ignore_hotplug = 1;
+}
+
 static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state,
 				  bool enable)
 {
-- 
cgit v1.2.3


From 378520b837cf4da769600b83690d8e825f16a611 Mon Sep 17 00:00:00 2001
From: Peng Tao <tao.peng@primarydata.com>
Date: Thu, 7 Aug 2014 10:15:02 +0800
Subject: nfs41: add a helper function to set layoutcommit after commit

Track lwb in nfs_commit_data so that we can use it to setup
layoutcommit in commit_done callback.

Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/pnfs.c           | 29 +++++++++++++++++++++++++++++
 fs/nfs/pnfs.h           |  1 +
 fs/nfs/write.c          | 15 +++++++++++++++
 include/linux/nfs_xdr.h |  1 +
 4 files changed, 46 insertions(+)

(limited to 'include')

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index a3851debf8a2..a6586cdee211 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1797,6 +1797,35 @@ pnfs_set_layoutcommit(struct nfs_pgio_header *hdr)
 }
 EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
 
+void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data)
+{
+	struct inode *inode = data->inode;
+	struct nfs_inode *nfsi = NFS_I(inode);
+	bool mark_as_dirty = false;
+
+	spin_lock(&inode->i_lock);
+	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
+		mark_as_dirty = true;
+		dprintk("%s: Set layoutcommit for inode %lu ",
+			__func__, inode->i_ino);
+	}
+	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &data->lseg->pls_flags)) {
+		/* references matched in nfs4_layoutcommit_release */
+		pnfs_get_lseg(data->lseg);
+	}
+	if (data->lwb > nfsi->layout->plh_lwb)
+		nfsi->layout->plh_lwb = data->lwb;
+	spin_unlock(&inode->i_lock);
+	dprintk("%s: lseg %p end_pos %llu\n",
+		__func__, data->lseg, nfsi->layout->plh_lwb);
+
+	/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
+	 * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
+	if (mark_as_dirty)
+		mark_inode_dirty_sync(inode);
+}
+EXPORT_SYMBOL_GPL(pnfs_commit_set_layoutcommit);
+
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
 {
 	struct nfs_server *nfss = NFS_SERVER(data->args.inode);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index aca3dff5dae6..79c63114ce77 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -219,6 +219,7 @@ void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task);
 void pnfs_set_layoutcommit(struct nfs_pgio_header *);
+void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 175d5d073ccf..3c5638f381cd 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1538,6 +1538,18 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 }
 EXPORT_SYMBOL_GPL(nfs_initiate_commit);
 
+static loff_t nfs_get_lwb(struct list_head *head)
+{
+	loff_t lwb = 0;
+	struct nfs_page *req;
+
+	list_for_each_entry(req, head, wb_list)
+		if (lwb < (req_offset(req) + req->wb_bytes))
+			lwb = req_offset(req) + req->wb_bytes;
+
+	return lwb;
+}
+
 /*
  * Set up the argument/result storage required for the RPC call.
  */
@@ -1557,6 +1569,9 @@ void nfs_init_commit(struct nfs_commit_data *data,
 	data->inode	  = inode;
 	data->cred	  = first->wb_context->cred;
 	data->lseg	  = lseg; /* reference transferred */
+	/* only set lwb for pnfs commit */
+	if (lseg)
+		data->lwb = nfs_get_lwb(&data->pages);
 	data->mds_ops     = &nfs_commit_ops;
 	data->completion_ops = cinfo->completion_ops;
 	data->dreq	  = cinfo->dreq;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0040629894df..e563b2c976ef 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1328,6 +1328,7 @@ struct nfs_commit_data {
 	struct pnfs_layout_segment *lseg;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
 	int			ds_commit_index;
+	loff_t			lwb;
 	const struct rpc_call_ops *mds_ops;
 	const struct nfs_commit_completion_ops *completion_ops;
 	int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data);
-- 
cgit v1.2.3


From 5f919c9f10c1cf821ee5f414683214a361a1b98c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 21 Aug 2014 11:09:25 -0500
Subject: pnfs: allow splicing pre-encoded pages into the layoutcommit args

Currently there is no XDR buffer space allocated for the per-layout driver
layoutcommit payload, which leads to server buffer overflows in the
blocklayout driver even under simple workloads.  As we can't do per-layout
sizes for XDR operations we'll have to splice a previously encoded list
of pages into the XDR stream, similar to how we handle ACL buffers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/nfs4xdr.c        | 18 +++++++++++++-----
 fs/nfs/pnfs.c           | 15 +++++++++++++++
 fs/nfs/pnfs.h           |  4 ++--
 include/linux/nfs_xdr.h |  3 +++
 4 files changed, 33 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e13b59d8d9aa..f2cd957adb90 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -395,7 +395,10 @@ static int nfs4_stat_to_errno(int);
 				2 /* last byte written */ + \
 				1 /* nt_timechanged (false) */ + \
 				1 /* layoutupdate4 layout type */ + \
-				1 /* NULL filelayout layoutupdate4 payload */)
+				1 /* layoutupdate4 opaqueue len */)
+				  /* the actual content of layoutupdate4 should
+				     be allocated by drivers and spliced in
+				     using xdr_write_pages */
 #define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3)
 #define encode_layoutreturn_maxsz (8 + op_encode_hdr_maxsz + \
 				encode_stateid_maxsz + \
@@ -1990,7 +1993,7 @@ encode_layoutget(struct xdr_stream *xdr,
 static int
 encode_layoutcommit(struct xdr_stream *xdr,
 		    struct inode *inode,
-		    const struct nfs4_layoutcommit_args *args,
+		    struct nfs4_layoutcommit_args *args,
 		    struct compound_hdr *hdr)
 {
 	__be32 *p;
@@ -2011,11 +2014,16 @@ encode_layoutcommit(struct xdr_stream *xdr,
 	*p++ = cpu_to_be32(0); /* Never send time_modify_changed */
 	*p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */
 
-	if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit)
+	if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit) {
 		NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
 			NFS_I(inode)->layout, xdr, args);
-	else
-		encode_uint32(xdr, 0); /* no layout-type payload */
+	} else {
+		encode_uint32(xdr, args->layoutupdate_len);
+		if (args->layoutupdate_pages) {
+			xdr_write_pages(xdr, args->layoutupdate_pages, 0,
+					args->layoutupdate_len);
+		}
+	}
 
 	return 0;
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 57b5728e0b8e..8827ab130ed3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1854,6 +1854,7 @@ void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
 int
 pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 	struct nfs4_layoutcommit_data *data;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	loff_t end_pos;
@@ -1904,6 +1905,20 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	data->args.lastbytewritten = end_pos - 1;
 	data->res.server = NFS_SERVER(inode);
 
+	if (ld->prepare_layoutcommit) {
+		status = ld->prepare_layoutcommit(&data->args);
+		if (status) {
+			spin_lock(&inode->i_lock);
+			if (end_pos < nfsi->layout->plh_lwb)
+				nfsi->layout->plh_lwb = end_pos;
+			spin_unlock(&inode->i_lock);
+			put_rpccred(data->cred);
+			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
+			goto clear_layoutcommitting;
+		}
+	}
+
+
 	status = nfs4_proc_layoutcommit(data, sync);
 out:
 	if (status)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 1dd8a5e96c9f..8835b5a320cc 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -128,8 +128,8 @@ struct pnfs_layoutdriver_type {
 				     const struct nfs4_layoutreturn_args *args);
 
 	void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data);
-
-	void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid,
+	int (*prepare_layoutcommit) (struct nfs4_layoutcommit_args *args);
+	void (*encode_layoutcommit) (struct pnfs_layout_hdr *lo,
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutcommit_args *args);
 };
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index e563b2c976ef..f4092c6b90fb 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -279,6 +279,9 @@ struct nfs4_layoutcommit_args {
 	__u64 lastbytewritten;
 	struct inode *inode;
 	const u32 *bitmask;
+	size_t layoutupdate_len;
+	struct page *layoutupdate_page;
+	struct page **layoutupdate_pages;
 };
 
 struct nfs4_layoutcommit_res {
-- 
cgit v1.2.3


From b954d83421d51d822c42e5ab7b65069b25ad3005 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Wed, 10 Sep 2014 15:01:02 +0200
Subject: net: bpf: only build bpf_jit_binary_{alloc, free}() when jit selected

Since BPF JIT depends on the availability of module_alloc() and
module_free() helpers (HAVE_BPF_JIT and MODULES), we better build
that code only in case we have BPF_JIT in our config enabled, just
like with other JIT code. Fixes builds for arm/marzen_defconfig
and sh/rsk7269_defconfig.

====================
kernel/built-in.o: In function `bpf_jit_binary_alloc':
/home/cwang/linux/kernel/bpf/core.c:144: undefined reference to `module_alloc'
kernel/built-in.o: In function `bpf_jit_binary_free':
/home/cwang/linux/kernel/bpf/core.c:164: undefined reference to `module_free'
make: *** [vmlinux] Error 1
====================

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Fixes: 738cbe72adc5 ("net: bpf: consolidate JIT binary allocator")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h | 78 +++++++++++++++++++++++++-------------------------
 kernel/bpf/core.c      |  2 ++
 2 files changed, 41 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4b59edead908..1a0bc6d134d7 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -4,12 +4,18 @@
 #ifndef __LINUX_FILTER_H__
 #define __LINUX_FILTER_H__
 
+#include <stdarg.h>
+
 #include <linux/atomic.h>
 #include <linux/compat.h>
 #include <linux/skbuff.h>
+#include <linux/linkage.h>
+#include <linux/printk.h>
 #include <linux/workqueue.h>
-#include <uapi/linux/filter.h>
+
 #include <asm/cacheflush.h>
+
+#include <uapi/linux/filter.h>
 #include <uapi/linux/bpf.h>
 
 struct sk_buff;
@@ -363,14 +369,6 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags);
 void __bpf_prog_free(struct bpf_prog *fp);
 
-typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
-
-struct bpf_binary_header *
-bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
-		     unsigned int alignment,
-		     bpf_jit_fill_hole_t bpf_fill_ill_insns);
-void bpf_jit_binary_free(struct bpf_binary_header *hdr);
-
 static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
 {
 	bpf_prog_unlock_ro(fp);
@@ -393,6 +391,38 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 void bpf_int_jit_compile(struct bpf_prog *fp);
 
+#ifdef CONFIG_BPF_JIT
+typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
+
+struct bpf_binary_header *
+bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
+		     unsigned int alignment,
+		     bpf_jit_fill_hole_t bpf_fill_ill_insns);
+void bpf_jit_binary_free(struct bpf_binary_header *hdr);
+
+void bpf_jit_compile(struct bpf_prog *fp);
+void bpf_jit_free(struct bpf_prog *fp);
+
+static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
+				u32 pass, void *image)
+{
+	pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
+	       flen, proglen, pass, image);
+	if (image)
+		print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
+			       16, 1, image, proglen, false);
+}
+#else
+static inline void bpf_jit_compile(struct bpf_prog *fp)
+{
+}
+
+static inline void bpf_jit_free(struct bpf_prog *fp)
+{
+	bpf_prog_unlock_free(fp);
+}
+#endif /* CONFIG_BPF_JIT */
+
 #define BPF_ANC		BIT(15)
 
 static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
@@ -440,36 +470,6 @@ static inline void *bpf_load_pointer(const struct sk_buff *skb, int k,
 	return bpf_internal_load_pointer_neg_helper(skb, k, size);
 }
 
-#ifdef CONFIG_BPF_JIT
-#include <stdarg.h>
-#include <linux/linkage.h>
-#include <linux/printk.h>
-
-void bpf_jit_compile(struct bpf_prog *fp);
-void bpf_jit_free(struct bpf_prog *fp);
-
-static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
-				u32 pass, void *image)
-{
-	pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
-	       flen, proglen, pass, image);
-	if (image)
-		print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
-			       16, 1, image, proglen, false);
-}
-#else
-#include <linux/slab.h>
-
-static inline void bpf_jit_compile(struct bpf_prog *fp)
-{
-}
-
-static inline void bpf_jit_free(struct bpf_prog *fp)
-{
-	bpf_prog_unlock_free(fp);
-}
-#endif /* CONFIG_BPF_JIT */
-
 static inline int bpf_tell_extensions(void)
 {
 	return SKF_AD_MAX;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 8ee520f0ec70..8b7002488251 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -128,6 +128,7 @@ void __bpf_prog_free(struct bpf_prog *fp)
 }
 EXPORT_SYMBOL_GPL(__bpf_prog_free);
 
+#ifdef CONFIG_BPF_JIT
 struct bpf_binary_header *
 bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 		     unsigned int alignment,
@@ -163,6 +164,7 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr)
 {
 	module_free(NULL, hdr);
 }
+#endif /* CONFIG_BPF_JIT */
 
 /* Base function for offset calculation. Needs to go into .text section,
  * therefore keeping it non-static as well; will also be used by JITs
-- 
cgit v1.2.3


From 6314b6796e3c070d4c8086b08dfd453a0aeac4cf Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Thu, 4 Sep 2014 23:37:49 -0700
Subject: clk: Don't hold prepare_lock across debugfs creation

Rob Clark reports a lockdep splat that involves the prepare_lock
chained with the mmap semaphore.

======================================================
[ INFO: possible circular locking dependency detected ]
3.17.0-rc1-00050-g07a489b #802 Tainted: G        W
-------------------------------------------------------
Xorg.bin/5413 is trying to acquire lock:
 (prepare_lock){+.+.+.}, at: [<c0781280>] clk_prepare_lock+0x88/0xfc

but task is already holding lock:
 (qcom_iommu_lock){+.+...}, at: [<c079f664>] qcom_iommu_unmap+0x1c/0x1f0

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #4 (qcom_iommu_lock){+.+...}:
       [<c079f860>] qcom_iommu_map+0x28/0x450
       [<c079eb50>] iommu_map+0xc8/0x12c
       [<c056c1fc>] msm_iommu_map+0xb4/0x130
       [<c05697bc>] msm_gem_get_iova_locked+0x9c/0xe8
       [<c0569854>] msm_gem_get_iova+0x4c/0x64
       [<c0562208>] mdp4_kms_init+0x4c4/0x6c0
       [<c056881c>] msm_load+0x2ac/0x34c
       [<c0545724>] drm_dev_register+0xac/0x108
       [<c0547510>] drm_platform_init+0x50/0xf0
       [<c0578a60>] try_to_bring_up_master.part.3+0xc8/0x108
       [<c0578b48>] component_master_add_with_match+0xa8/0x104
       [<c0568294>] msm_pdev_probe+0x64/0x70
       [<c057e704>] platform_drv_probe+0x2c/0x60
       [<c057cff8>] driver_probe_device+0x108/0x234
       [<c057b65c>] bus_for_each_drv+0x64/0x98
       [<c057cec0>] device_attach+0x78/0x8c
       [<c057c590>] bus_probe_device+0x88/0xac
       [<c057c9b8>] deferred_probe_work_func+0x68/0x9c
       [<c0259db4>] process_one_work+0x1a0/0x40c
       [<c025a710>] worker_thread+0x44/0x4d8
       [<c025ec54>] kthread+0xd8/0xec
       [<c020e9a8>] ret_from_fork+0x14/0x2c

-> #3 (&dev->struct_mutex){+.+.+.}:
       [<c0541188>] drm_gem_mmap+0x38/0xd0
       [<c05695b8>] msm_gem_mmap+0xc/0x5c
       [<c02f0b6c>] mmap_region+0x35c/0x6c8
       [<c02f11ec>] do_mmap_pgoff+0x314/0x398
       [<c02de1e0>] vm_mmap_pgoff+0x84/0xb4
       [<c02ef83c>] SyS_mmap_pgoff+0x94/0xbc
       [<c020e8e0>] ret_fast_syscall+0x0/0x48

-> #2 (&mm->mmap_sem){++++++}:
       [<c0321138>] filldir64+0x68/0x180
       [<c0333fe0>] dcache_readdir+0x188/0x22c
       [<c0320ed0>] iterate_dir+0x9c/0x11c
       [<c03213b0>] SyS_getdents64+0x78/0xe8
       [<c020e8e0>] ret_fast_syscall+0x0/0x48

-> #1 (&sb->s_type->i_mutex_key#3){+.+.+.}:
       [<c03fc544>] __create_file+0x58/0x1dc
       [<c03fc70c>] debugfs_create_dir+0x1c/0x24
       [<c0781c7c>] clk_debug_create_subtree+0x20/0x170
       [<c0be2af8>] clk_debug_init+0xec/0x14c
       [<c0208c70>] do_one_initcall+0x8c/0x1c8
       [<c0b9cce4>] kernel_init_freeable+0x13c/0x1dc
       [<c0877bc4>] kernel_init+0x8/0xe8
       [<c020e9a8>] ret_from_fork+0x14/0x2c

-> #0 (prepare_lock){+.+.+.}:
       [<c087c408>] mutex_lock_nested+0x70/0x3e8
       [<c0781280>] clk_prepare_lock+0x88/0xfc
       [<c0782c50>] clk_prepare+0xc/0x24
       [<c079f474>] __enable_clocks.isra.4+0x18/0xa4
       [<c079f614>] __flush_iotlb_va+0xe0/0x114
       [<c079f6f4>] qcom_iommu_unmap+0xac/0x1f0
       [<c079ea3c>] iommu_unmap+0x9c/0xe8
       [<c056c2fc>] msm_iommu_unmap+0x64/0x84
       [<c0569da4>] msm_gem_free_object+0x11c/0x338
       [<c05413ec>] drm_gem_object_handle_unreference_unlocked+0xfc/0x130
       [<c0541604>] drm_gem_object_release_handle+0x50/0x68
       [<c0447a98>] idr_for_each+0xa8/0xdc
       [<c0541c10>] drm_gem_release+0x1c/0x28
       [<c0540b3c>] drm_release+0x370/0x428
       [<c031105c>] __fput+0x98/0x1e8
       [<c025d73c>] task_work_run+0xb0/0xfc
       [<c02477ec>] do_exit+0x2ec/0x948
       [<c0247ec0>] do_group_exit+0x4c/0xb8
       [<c025180c>] get_signal+0x28c/0x6ac
       [<c0211204>] do_signal+0xc4/0x3e4
       [<c02116cc>] do_work_pending+0xb4/0xc4
       [<c020e938>] work_pending+0xc/0x20

other info that might help us debug this:

Chain exists of:
  prepare_lock --> &dev->struct_mutex --> qcom_iommu_lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(qcom_iommu_lock);
                               lock(&dev->struct_mutex);
                               lock(qcom_iommu_lock);
  lock(prepare_lock);

 *** DEADLOCK ***

3 locks held by Xorg.bin/5413:
 #0:  (drm_global_mutex){+.+.+.}, at: [<c0540800>] drm_release+0x34/0x428
 #1:  (&dev->struct_mutex){+.+.+.}, at: [<c05413bc>] drm_gem_object_handle_unreference_unlocked+0xcc/0x130
 #2:  (qcom_iommu_lock){+.+...}, at: [<c079f664>] qcom_iommu_unmap+0x1c/0x1f0

stack backtrace:
CPU: 1 PID: 5413 Comm: Xorg.bin Tainted: G        W      3.17.0-rc1-00050-g07a489b #802
[<c0216290>] (unwind_backtrace) from [<c0211d8c>] (show_stack+0x10/0x14)
[<c0211d8c>] (show_stack) from [<c087a078>] (dump_stack+0x98/0xb8)
[<c087a078>] (dump_stack) from [<c027f024>] (print_circular_bug+0x218/0x340)
[<c027f024>] (print_circular_bug) from [<c0283e08>] (__lock_acquire+0x1d24/0x20b8)
[<c0283e08>] (__lock_acquire) from [<c0284774>] (lock_acquire+0x9c/0xbc)
[<c0284774>] (lock_acquire) from [<c087c408>] (mutex_lock_nested+0x70/0x3e8)
[<c087c408>] (mutex_lock_nested) from [<c0781280>] (clk_prepare_lock+0x88/0xfc)
[<c0781280>] (clk_prepare_lock) from [<c0782c50>] (clk_prepare+0xc/0x24)
[<c0782c50>] (clk_prepare) from [<c079f474>] (__enable_clocks.isra.4+0x18/0xa4)
[<c079f474>] (__enable_clocks.isra.4) from [<c079f614>] (__flush_iotlb_va+0xe0/0x114)
[<c079f614>] (__flush_iotlb_va) from [<c079f6f4>] (qcom_iommu_unmap+0xac/0x1f0)
[<c079f6f4>] (qcom_iommu_unmap) from [<c079ea3c>] (iommu_unmap+0x9c/0xe8)
[<c079ea3c>] (iommu_unmap) from [<c056c2fc>] (msm_iommu_unmap+0x64/0x84)
[<c056c2fc>] (msm_iommu_unmap) from [<c0569da4>] (msm_gem_free_object+0x11c/0x338)
[<c0569da4>] (msm_gem_free_object) from [<c05413ec>] (drm_gem_object_handle_unreference_unlocked+0xfc/0x130)
[<c05413ec>] (drm_gem_object_handle_unreference_unlocked) from [<c0541604>] (drm_gem_object_release_handle+0x50/0x68)
[<c0541604>] (drm_gem_object_release_handle) from [<c0447a98>] (idr_for_each+0xa8/0xdc)
[<c0447a98>] (idr_for_each) from [<c0541c10>] (drm_gem_release+0x1c/0x28)
[<c0541c10>] (drm_gem_release) from [<c0540b3c>] (drm_release+0x370/0x428)
[<c0540b3c>] (drm_release) from [<c031105c>] (__fput+0x98/0x1e8)
[<c031105c>] (__fput) from [<c025d73c>] (task_work_run+0xb0/0xfc)
[<c025d73c>] (task_work_run) from [<c02477ec>] (do_exit+0x2ec/0x948)
[<c02477ec>] (do_exit) from [<c0247ec0>] (do_group_exit+0x4c/0xb8)
[<c0247ec0>] (do_group_exit) from [<c025180c>] (get_signal+0x28c/0x6ac)
[<c025180c>] (get_signal) from [<c0211204>] (do_signal+0xc4/0x3e4)
[<c0211204>] (do_signal) from [<c02116cc>] (do_work_pending+0xb4/0xc4)
[<c02116cc>] (do_work_pending) from [<c020e938>] (work_pending+0xc/0x20)

We can break this chain if we don't hold the prepare_lock while
creating debugfs directories. We only hold the prepare_lock right
now because we're traversing the clock tree recursively and we
don't want the hierarchy to change during the traversal.
Replacing this traversal with a simple linked list walk allows us
to only grab a list lock instead of the prepare_lock, thus
breaking the lock chain.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 drivers/clk/clk.c           | 73 +++++++++++++++++----------------------------
 include/linux/clk-private.h |  1 +
 2 files changed, 28 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index b76fa69b44cb..8ca28189e4e9 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -100,6 +100,8 @@ static void clk_enable_unlock(unsigned long flags)
 
 static struct dentry *rootdir;
 static int inited = 0;
+static DEFINE_MUTEX(clk_debug_lock);
+static HLIST_HEAD(clk_debug_list);
 
 static struct hlist_head *all_lists[] = {
 	&clk_root_list,
@@ -300,28 +302,6 @@ out:
 	return ret;
 }
 
-/* caller must hold prepare_lock */
-static int clk_debug_create_subtree(struct clk *clk, struct dentry *pdentry)
-{
-	struct clk *child;
-	int ret = -EINVAL;;
-
-	if (!clk || !pdentry)
-		goto out;
-
-	ret = clk_debug_create_one(clk, pdentry);
-
-	if (ret)
-		goto out;
-
-	hlist_for_each_entry(child, &clk->children, child_node)
-		clk_debug_create_subtree(child, pdentry);
-
-	ret = 0;
-out:
-	return ret;
-}
-
 /**
  * clk_debug_register - add a clk node to the debugfs clk tree
  * @clk: the clk being added to the debugfs clk tree
@@ -329,20 +309,21 @@ out:
  * Dynamically adds a clk to the debugfs clk tree if debugfs has been
  * initialized.  Otherwise it bails out early since the debugfs clk tree
  * will be created lazily by clk_debug_init as part of a late_initcall.
- *
- * Caller must hold prepare_lock.  Only clk_init calls this function (so
- * far) so this is taken care.
  */
 static int clk_debug_register(struct clk *clk)
 {
 	int ret = 0;
 
+	mutex_lock(&clk_debug_lock);
+	hlist_add_head(&clk->debug_node, &clk_debug_list);
+
 	if (!inited)
-		goto out;
+		goto unlock;
 
-	ret = clk_debug_create_subtree(clk, rootdir);
+	ret = clk_debug_create_one(clk, rootdir);
+unlock:
+	mutex_unlock(&clk_debug_lock);
 
-out:
 	return ret;
 }
 
@@ -353,12 +334,18 @@ out:
  * Dynamically removes a clk and all it's children clk nodes from the
  * debugfs clk tree if clk->dentry points to debugfs created by
  * clk_debug_register in __clk_init.
- *
- * Caller must hold prepare_lock.
  */
 static void clk_debug_unregister(struct clk *clk)
 {
+	mutex_lock(&clk_debug_lock);
+	if (!clk->dentry)
+		goto out;
+
+	hlist_del_init(&clk->debug_node);
 	debugfs_remove_recursive(clk->dentry);
+	clk->dentry = NULL;
+out:
+	mutex_unlock(&clk_debug_lock);
 }
 
 struct dentry *clk_debugfs_add_file(struct clk *clk, char *name, umode_t mode,
@@ -415,17 +402,12 @@ static int __init clk_debug_init(void)
 	if (!d)
 		return -ENOMEM;
 
-	clk_prepare_lock();
-
-	hlist_for_each_entry(clk, &clk_root_list, child_node)
-		clk_debug_create_subtree(clk, rootdir);
-
-	hlist_for_each_entry(clk, &clk_orphan_list, child_node)
-		clk_debug_create_subtree(clk, rootdir);
+	mutex_lock(&clk_debug_lock);
+	hlist_for_each_entry(clk, &clk_debug_list, debug_node)
+		clk_debug_create_one(clk, rootdir);
 
 	inited = 1;
-
-	clk_prepare_unlock();
+	mutex_unlock(&clk_debug_lock);
 
 	return 0;
 }
@@ -2087,14 +2069,16 @@ void clk_unregister(struct clk *clk)
 {
 	unsigned long flags;
 
-       if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
-               return;
+	if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
+		return;
+
+	clk_debug_unregister(clk);
 
 	clk_prepare_lock();
 
 	if (clk->ops == &clk_nodrv_ops) {
 		pr_err("%s: unregistered clock: %s\n", __func__, clk->name);
-		goto out;
+		return;
 	}
 	/*
 	 * Assign empty clock ops for consumers that might still hold
@@ -2113,16 +2097,13 @@ void clk_unregister(struct clk *clk)
 			clk_set_parent(child, NULL);
 	}
 
-	clk_debug_unregister(clk);
-
 	hlist_del_init(&clk->child_node);
 
 	if (clk->prepare_count)
 		pr_warn("%s: unregistering prepared clock: %s\n",
 					__func__, clk->name);
-
 	kref_put(&clk->ref, __clk_release);
-out:
+
 	clk_prepare_unlock();
 }
 EXPORT_SYMBOL_GPL(clk_unregister);
diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h
index efbf70b9fd84..4ed34105c371 100644
--- a/include/linux/clk-private.h
+++ b/include/linux/clk-private.h
@@ -48,6 +48,7 @@ struct clk {
 	unsigned long		accuracy;
 	struct hlist_head	children;
 	struct hlist_node	child_node;
+	struct hlist_node	debug_node;
 	unsigned int		notifier_count;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry		*dentry;
-- 
cgit v1.2.3


From 09e05c3f78e9e82bda5958eb95bbf719f7a0ed6b Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Wed, 10 Sep 2014 16:41:56 +0300
Subject: net/mlx4: Set vlan stripping policy by the right command

Changing the vlan stripping policy of the QP isn't supported by older
firmware versions for the INIT2RTR command. Nevertheless, we've used it.

Fix that by doing this policy change using INIT2RTR only if the firmware
supports it, otherwise, we call UPDATE_QP command to do the task.

Fixes: 7677fc9 ('net/mlx4: Strengthen VLAN tags/priorities enforcement in VST mode')
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c                     |  2 +-
 drivers/net/ethernet/mellanox/mlx4/qp.c               | 12 ++++++++++--
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 18 ++++++++++++++++--
 include/linux/mlx4/device.h                           |  1 +
 include/linux/mlx4/qp.h                               | 12 ++++++++++--
 5 files changed, 38 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index af8256353c7d..162b82c1dde4 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1680,7 +1680,7 @@ static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev,
 			goto unlock;
 
 		update_params.smac_index = new_smac_index;
-		if (mlx4_update_qp(ibdev->dev, &qp->mqp, MLX4_UPDATE_QP_SMAC,
+		if (mlx4_update_qp(ibdev->dev, qp->mqp.qpn, MLX4_UPDATE_QP_SMAC,
 				   &update_params)) {
 			release_mac = new_smac;
 			goto unlock;
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 0dc31d85fc3b..2301365c79c7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -390,13 +390,14 @@ err_icm:
 EXPORT_SYMBOL_GPL(mlx4_qp_alloc);
 
 #define MLX4_UPDATE_QP_SUPPORTED_ATTRS MLX4_UPDATE_QP_SMAC
-int mlx4_update_qp(struct mlx4_dev *dev, struct mlx4_qp *qp,
+int mlx4_update_qp(struct mlx4_dev *dev, u32 qpn,
 		   enum mlx4_update_qp_attr attr,
 		   struct mlx4_update_qp_params *params)
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	struct mlx4_update_qp_context *cmd;
 	u64 pri_addr_path_mask = 0;
+	u64 qp_mask = 0;
 	int err = 0;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -413,9 +414,16 @@ int mlx4_update_qp(struct mlx4_dev *dev, struct mlx4_qp *qp,
 		cmd->qp_context.pri_path.grh_mylmc = params->smac_index;
 	}
 
+	if (attr & MLX4_UPDATE_QP_VSD) {
+		qp_mask |= 1ULL << MLX4_UPD_QP_MASK_VSD;
+		if (params->flags & MLX4_UPDATE_QP_PARAMS_FLAGS_VSD_ENABLE)
+			cmd->qp_context.param3 |= cpu_to_be32(MLX4_STRIP_VLAN);
+	}
+
 	cmd->primary_addr_path_mask = cpu_to_be64(pri_addr_path_mask);
+	cmd->qp_mask = cpu_to_be64(qp_mask);
 
-	err = mlx4_cmd(dev, mailbox->dma, qp->qpn & 0xffffff, 0,
+	err = mlx4_cmd(dev, mailbox->dma, qpn & 0xffffff, 0,
 		       MLX4_CMD_UPDATE_QP, MLX4_CMD_TIME_CLASS_A,
 		       MLX4_CMD_NATIVE);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 2fe61b6a8e37..5d2498dcf536 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -702,11 +702,13 @@ static int update_vport_qp_param(struct mlx4_dev *dev,
 	struct mlx4_qp_context	*qpc = inbox->buf + 8;
 	struct mlx4_vport_oper_state *vp_oper;
 	struct mlx4_priv *priv;
+	u32 qp_type;
 	int port;
 
 	port = (qpc->pri_path.sched_queue & 0x40) ? 2 : 1;
 	priv = mlx4_priv(dev);
 	vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
+	qp_type	= (be32_to_cpu(qpc->flags) >> 16) & 0xff;
 
 	if (MLX4_VGT != vp_oper->state.default_vlan) {
 		/* the reserved QPs (special, proxy, tunnel)
@@ -715,8 +717,20 @@ static int update_vport_qp_param(struct mlx4_dev *dev,
 		if (mlx4_is_qp_reserved(dev, qpn))
 			return 0;
 
-		/* force strip vlan by clear vsd */
-		qpc->param3 &= ~cpu_to_be32(MLX4_STRIP_VLAN);
+		/* force strip vlan by clear vsd, MLX QP refers to Raw Ethernet */
+		if (qp_type == MLX4_QP_ST_UD ||
+		    (qp_type == MLX4_QP_ST_MLX && mlx4_is_eth(dev, port))) {
+			if (dev->caps.bmme_flags & MLX4_BMME_FLAG_VSD_INIT2RTR) {
+				*(__be32 *)inbox->buf =
+					cpu_to_be32(be32_to_cpu(*(__be32 *)inbox->buf) |
+					MLX4_QP_OPTPAR_VLAN_STRIPPING);
+				qpc->param3 &= ~cpu_to_be32(MLX4_STRIP_VLAN);
+			} else {
+				struct mlx4_update_qp_params params = {.flags = 0};
+
+				mlx4_update_qp(dev, qpn, MLX4_UPDATE_QP_VSD, &params);
+			}
+		}
 
 		if (vp_oper->state.link_state == IFLA_VF_LINK_STATE_DISABLE &&
 		    dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_UPDATE_QP) {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 511c6e0d21a9..a5b7d7cfcedf 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -209,6 +209,7 @@ enum {
 	MLX4_BMME_FLAG_TYPE_2_WIN	= 1 <<  9,
 	MLX4_BMME_FLAG_RESERVED_LKEY	= 1 << 10,
 	MLX4_BMME_FLAG_FAST_REG_WR	= 1 << 11,
+	MLX4_BMME_FLAG_VSD_INIT2RTR	= 1 << 28,
 };
 
 enum mlx4_event {
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 7040dc98ff8b..5f4e36cf0091 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -56,7 +56,8 @@ enum mlx4_qp_optpar {
 	MLX4_QP_OPTPAR_RNR_RETRY		= 1 << 13,
 	MLX4_QP_OPTPAR_ACK_TIMEOUT		= 1 << 14,
 	MLX4_QP_OPTPAR_SCHED_QUEUE		= 1 << 16,
-	MLX4_QP_OPTPAR_COUNTER_INDEX		= 1 << 20
+	MLX4_QP_OPTPAR_COUNTER_INDEX		= 1 << 20,
+	MLX4_QP_OPTPAR_VLAN_STRIPPING		= 1 << 21,
 };
 
 enum mlx4_qp_state {
@@ -423,13 +424,20 @@ struct mlx4_wqe_inline_seg {
 
 enum mlx4_update_qp_attr {
 	MLX4_UPDATE_QP_SMAC		= 1 << 0,
+	MLX4_UPDATE_QP_VSD		= 1 << 2,
+	MLX4_UPDATE_QP_SUPPORTED_ATTRS	= (1 << 2) - 1
+};
+
+enum mlx4_update_qp_params_flags {
+	MLX4_UPDATE_QP_PARAMS_FLAGS_VSD_ENABLE		= 1 << 0,
 };
 
 struct mlx4_update_qp_params {
 	u8	smac_index;
+	u32	flags;
 };
 
-int mlx4_update_qp(struct mlx4_dev *dev, struct mlx4_qp *qp,
+int mlx4_update_qp(struct mlx4_dev *dev, u32 qpn,
 		   enum mlx4_update_qp_attr attr,
 		   struct mlx4_update_qp_params *params);
 int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
-- 
cgit v1.2.3


From b01d072065b6f36550f486fe77f05b092225ba1b Mon Sep 17 00:00:00 2001
From: David Drysdale <drysdale@google.com>
Date: Tue, 9 Sep 2014 14:50:57 -0700
Subject: shm: add memfd.h to UAPI export list

The new header file memfd.h from commit 9183df25fe7b ("shm: add
memfd_create() syscall") should be exported.

Signed-off-by: David Drysdale <drysdale@google.com>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/Kbuild | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 24e9033f8b3f..939df6973102 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -240,6 +240,7 @@ header-y += matroxfb.h
 header-y += mdio.h
 header-y += media.h
 header-y += mei.h
+header-y += memfd.h
 header-y += mempolicy.h
 header-y += meye.h
 header-y += mic_common.h
-- 
cgit v1.2.3


From 184c3fc3f52fb75800deb76deffb70907d1f76ea Mon Sep 17 00:00:00 2001
From: Mark Rustad <mark.d.rustad@intel.com>
Date: Thu, 11 Sep 2014 09:47:23 +0930
Subject: moduleparam: Resolve missing-field-initializer warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Resolve a missing-field-initializer warning, that is produced
by every reference to module_param_call, by using designated
initialization for the first field. That is enough to silence
the complaint.

The message is only seen when doing a W=2 build. I happened to be using gcc
4.8.3, but I think most versions would produce the warning when it is
enabled. It can either be silenced by using even a single designated
initializer as I did here, or providing values for all of the fields. Because
of the number of references to the macro, this change silences many warnings
in W=2 builds.

One instance of the full warning message looks like this:

/home/share/git/nn-mdr/include/linux/moduleparam.h:198:16: warning: missing
initializer for field ‘free’ of ‘struct kernel_param_ops’
[-Wmissing-field-initializers]
  static struct kernel_param_ops __param_ops_##name =  \
		  ^
/home/share/git/nn-mdr/fs/fuse/inode.c:35:1: note: in expansion of macro
‘module_param_call’
 module_param_call(max_user_bgreq, set_global_limit, param_get_uint,
 ^
/home/share/git/nn-mdr/include/linux/moduleparam.h:56:9: note: ‘free’
declared here
  void (*free)(void *arg);

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/moduleparam.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 593501996574..b43f4752304e 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -224,7 +224,7 @@ struct kparam_array
 /* Obsolete - use module_param_cb() */
 #define module_param_call(name, set, get, arg, perm)			\
 	static struct kernel_param_ops __param_ops_##name =		\
-		{ 0, (void *)set, (void *)get };			\
+		{ .flags = 0, (void *)set, (void *)get };		\
 	__module_param_call(MODULE_PARAM_PREFIX,			\
 			    name, &__param_ops_##name, arg,		\
 			    (perm) + sizeof(__check_old_set_param(set))*0, -1, 0)
-- 
cgit v1.2.3


From 3d598f47e804a77208c6bb0a454123018e2f2281 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 19 Aug 2014 20:29:12 +0300
Subject: dmaengine: dw: move dw_dmac.h to where it belongs to

There is a common storage for platform data related structures and definitions
inside kernel source tree. The patch moves file from include/linux to
include/linux/platform_data and renames it acoordingly. The users are also
updated.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
[For the arch/avr32/.* and .*sound/atmel.*]
Acked-by: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 MAINTAINERS                                     |   2 +-
 arch/avr32/mach-at32ap/at32ap700x.c             |   2 +-
 arch/avr32/mach-at32ap/include/mach/atmel-mci.h |   2 +-
 drivers/dma/dw/internal.h                       |   2 +-
 drivers/dma/dw/regs.h                           |   6 +-
 include/linux/dw_dmac.h                         | 111 ------------------------
 include/linux/platform_data/dma-dw.h            | 111 ++++++++++++++++++++++++
 include/sound/atmel-abdac.h                     |   2 +-
 include/sound/atmel-ac97c.h                     |   2 +-
 sound/atmel/abdac.c                             |   2 +-
 sound/atmel/ac97c.c                             |   2 +-
 11 files changed, 122 insertions(+), 122 deletions(-)
 delete mode 100644 include/linux/dw_dmac.h
 create mode 100644 include/linux/platform_data/dma-dw.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index aefa94841ff3..a10072963889 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7875,7 +7875,7 @@ SYNOPSYS DESIGNWARE DMAC DRIVER
 M:	Viresh Kumar <viresh.linux@gmail.com>
 M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 S:	Maintained
-F:	include/linux/dw_dmac.h
+F:	include/linux/platform_data/dma-dw.h
 F:	drivers/dma/dw/
 
 SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index db85b5ec3351..2a1aa712c6e7 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -7,7 +7,7 @@
  */
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
diff --git a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
index 4bba58561d5c..11d7f4b28dc8 100644
--- a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
+++ b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
@@ -1,7 +1,7 @@
 #ifndef __MACH_ATMEL_MCI_H
 #define __MACH_ATMEL_MCI_H
 
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 /**
  * struct mci_dma_data - DMA data for MCI interface
diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h
index 32667f9e0dda..43cc1dfad5c9 100644
--- a/drivers/dma/dw/internal.h
+++ b/drivers/dma/dw/internal.h
@@ -12,7 +12,7 @@
 #define _DW_DMAC_INTERNAL_H
 
 #include <linux/device.h>
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 #include "regs.h"
 
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index bb98d3e91e8b..af02439155e9 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -11,7 +11,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 #define DW_DMA_MAX_NR_CHANNELS	8
 #define DW_DMA_MAX_NR_REQUESTS	16
@@ -161,7 +161,7 @@ struct dw_dma_regs {
 #define DWC_CTLH_DONE		0x00001000
 #define DWC_CTLH_BLOCK_TS_MASK	0x00000fff
 
-/* Bitfields in CFG_LO. Platform-configurable bits are in <linux/dw_dmac.h> */
+/* Bitfields in CFG_LO. Platform-configurable bits are in <linux/platform_data/dma-dw.h> */
 #define DWC_CFGL_CH_PRIOR_MASK	(0x7 << 5)	/* priority mask */
 #define DWC_CFGL_CH_PRIOR(x)	((x) << 5)	/* priority */
 #define DWC_CFGL_CH_SUSP	(1 << 8)	/* pause xfer */
@@ -172,7 +172,7 @@ struct dw_dma_regs {
 #define DWC_CFGL_RELOAD_SAR	(1 << 30)
 #define DWC_CFGL_RELOAD_DAR	(1 << 31)
 
-/* Bitfields in CFG_HI. Platform-configurable bits are in <linux/dw_dmac.h> */
+/* Bitfields in CFG_HI. Platform-configurable bits are in <linux/platform_data/dma-dw.h> */
 #define DWC_CFGH_DS_UPD_EN	(1 << 5)
 #define DWC_CFGH_SS_UPD_EN	(1 << 6)
 
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
deleted file mode 100644
index 68b4024184de..000000000000
--- a/include/linux/dw_dmac.h
+++ /dev/null
@@ -1,111 +0,0 @@
-/*
- * Driver for the Synopsys DesignWare DMA Controller
- *
- * Copyright (C) 2007 Atmel Corporation
- * Copyright (C) 2010-2011 ST Microelectronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef DW_DMAC_H
-#define DW_DMAC_H
-
-#include <linux/dmaengine.h>
-
-/**
- * struct dw_dma_slave - Controller-specific information about a slave
- *
- * @dma_dev: required DMA master device. Depricated.
- * @bus_id: name of this device channel, not just a device name since
- *          devices may have more than one channel e.g. "foo_tx"
- * @cfg_hi: Platform-specific initializer for the CFG_HI register
- * @cfg_lo: Platform-specific initializer for the CFG_LO register
- * @src_master: src master for transfers on allocated channel.
- * @dst_master: dest master for transfers on allocated channel.
- */
-struct dw_dma_slave {
-	struct device		*dma_dev;
-	u32			cfg_hi;
-	u32			cfg_lo;
-	u8			src_master;
-	u8			dst_master;
-};
-
-/**
- * struct dw_dma_platform_data - Controller configuration parameters
- * @nr_channels: Number of channels supported by hardware (max 8)
- * @is_private: The device channels should be marked as private and not for
- *	by the general purpose DMA channel allocator.
- * @chan_allocation_order: Allocate channels starting from 0 or 7
- * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0.
- * @block_size: Maximum block size supported by the controller
- * @nr_masters: Number of AHB masters supported by the controller
- * @data_width: Maximum data width supported by hardware per AHB master
- *		(0 - 8bits, 1 - 16bits, ..., 5 - 256bits)
- */
-struct dw_dma_platform_data {
-	unsigned int	nr_channels;
-	bool		is_private;
-#define CHAN_ALLOCATION_ASCENDING	0	/* zero to seven */
-#define CHAN_ALLOCATION_DESCENDING	1	/* seven to zero */
-	unsigned char	chan_allocation_order;
-#define CHAN_PRIORITY_ASCENDING		0	/* chan0 highest */
-#define CHAN_PRIORITY_DESCENDING	1	/* chan7 highest */
-	unsigned char	chan_priority;
-	unsigned short	block_size;
-	unsigned char	nr_masters;
-	unsigned char	data_width[4];
-};
-
-/* bursts size */
-enum dw_dma_msize {
-	DW_DMA_MSIZE_1,
-	DW_DMA_MSIZE_4,
-	DW_DMA_MSIZE_8,
-	DW_DMA_MSIZE_16,
-	DW_DMA_MSIZE_32,
-	DW_DMA_MSIZE_64,
-	DW_DMA_MSIZE_128,
-	DW_DMA_MSIZE_256,
-};
-
-/* Platform-configurable bits in CFG_HI */
-#define DWC_CFGH_FCMODE		(1 << 0)
-#define DWC_CFGH_FIFO_MODE	(1 << 1)
-#define DWC_CFGH_PROTCTL(x)	((x) << 2)
-#define DWC_CFGH_SRC_PER(x)	((x) << 7)
-#define DWC_CFGH_DST_PER(x)	((x) << 11)
-
-/* Platform-configurable bits in CFG_LO */
-#define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
-#define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
-#define DWC_CFGL_LOCK_CH_XACT	(2 << 12)
-#define DWC_CFGL_LOCK_BUS_XFER	(0 << 14)	/* scope of LOCK_BUS */
-#define DWC_CFGL_LOCK_BUS_BLOCK	(1 << 14)
-#define DWC_CFGL_LOCK_BUS_XACT	(2 << 14)
-#define DWC_CFGL_LOCK_CH	(1 << 15)	/* channel lockout */
-#define DWC_CFGL_LOCK_BUS	(1 << 16)	/* busmaster lockout */
-#define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
-#define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
-
-/* DMA API extensions */
-struct dw_cyclic_desc {
-	struct dw_desc	**desc;
-	unsigned long	periods;
-	void		(*period_callback)(void *param);
-	void		*period_callback_param;
-};
-
-struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
-		dma_addr_t buf_addr, size_t buf_len, size_t period_len,
-		enum dma_transfer_direction direction);
-void dw_dma_cyclic_free(struct dma_chan *chan);
-int dw_dma_cyclic_start(struct dma_chan *chan);
-void dw_dma_cyclic_stop(struct dma_chan *chan);
-
-dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
-
-dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
-
-#endif /* DW_DMAC_H */
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
new file mode 100644
index 000000000000..68b4024184de
--- /dev/null
+++ b/include/linux/platform_data/dma-dw.h
@@ -0,0 +1,111 @@
+/*
+ * Driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2007 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef DW_DMAC_H
+#define DW_DMAC_H
+
+#include <linux/dmaengine.h>
+
+/**
+ * struct dw_dma_slave - Controller-specific information about a slave
+ *
+ * @dma_dev: required DMA master device. Depricated.
+ * @bus_id: name of this device channel, not just a device name since
+ *          devices may have more than one channel e.g. "foo_tx"
+ * @cfg_hi: Platform-specific initializer for the CFG_HI register
+ * @cfg_lo: Platform-specific initializer for the CFG_LO register
+ * @src_master: src master for transfers on allocated channel.
+ * @dst_master: dest master for transfers on allocated channel.
+ */
+struct dw_dma_slave {
+	struct device		*dma_dev;
+	u32			cfg_hi;
+	u32			cfg_lo;
+	u8			src_master;
+	u8			dst_master;
+};
+
+/**
+ * struct dw_dma_platform_data - Controller configuration parameters
+ * @nr_channels: Number of channels supported by hardware (max 8)
+ * @is_private: The device channels should be marked as private and not for
+ *	by the general purpose DMA channel allocator.
+ * @chan_allocation_order: Allocate channels starting from 0 or 7
+ * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0.
+ * @block_size: Maximum block size supported by the controller
+ * @nr_masters: Number of AHB masters supported by the controller
+ * @data_width: Maximum data width supported by hardware per AHB master
+ *		(0 - 8bits, 1 - 16bits, ..., 5 - 256bits)
+ */
+struct dw_dma_platform_data {
+	unsigned int	nr_channels;
+	bool		is_private;
+#define CHAN_ALLOCATION_ASCENDING	0	/* zero to seven */
+#define CHAN_ALLOCATION_DESCENDING	1	/* seven to zero */
+	unsigned char	chan_allocation_order;
+#define CHAN_PRIORITY_ASCENDING		0	/* chan0 highest */
+#define CHAN_PRIORITY_DESCENDING	1	/* chan7 highest */
+	unsigned char	chan_priority;
+	unsigned short	block_size;
+	unsigned char	nr_masters;
+	unsigned char	data_width[4];
+};
+
+/* bursts size */
+enum dw_dma_msize {
+	DW_DMA_MSIZE_1,
+	DW_DMA_MSIZE_4,
+	DW_DMA_MSIZE_8,
+	DW_DMA_MSIZE_16,
+	DW_DMA_MSIZE_32,
+	DW_DMA_MSIZE_64,
+	DW_DMA_MSIZE_128,
+	DW_DMA_MSIZE_256,
+};
+
+/* Platform-configurable bits in CFG_HI */
+#define DWC_CFGH_FCMODE		(1 << 0)
+#define DWC_CFGH_FIFO_MODE	(1 << 1)
+#define DWC_CFGH_PROTCTL(x)	((x) << 2)
+#define DWC_CFGH_SRC_PER(x)	((x) << 7)
+#define DWC_CFGH_DST_PER(x)	((x) << 11)
+
+/* Platform-configurable bits in CFG_LO */
+#define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
+#define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
+#define DWC_CFGL_LOCK_CH_XACT	(2 << 12)
+#define DWC_CFGL_LOCK_BUS_XFER	(0 << 14)	/* scope of LOCK_BUS */
+#define DWC_CFGL_LOCK_BUS_BLOCK	(1 << 14)
+#define DWC_CFGL_LOCK_BUS_XACT	(2 << 14)
+#define DWC_CFGL_LOCK_CH	(1 << 15)	/* channel lockout */
+#define DWC_CFGL_LOCK_BUS	(1 << 16)	/* busmaster lockout */
+#define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
+#define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
+
+/* DMA API extensions */
+struct dw_cyclic_desc {
+	struct dw_desc	**desc;
+	unsigned long	periods;
+	void		(*period_callback)(void *param);
+	void		*period_callback_param;
+};
+
+struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
+		dma_addr_t buf_addr, size_t buf_len, size_t period_len,
+		enum dma_transfer_direction direction);
+void dw_dma_cyclic_free(struct dma_chan *chan);
+int dw_dma_cyclic_start(struct dma_chan *chan);
+void dw_dma_cyclic_stop(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
+
+#endif /* DW_DMAC_H */
diff --git a/include/sound/atmel-abdac.h b/include/sound/atmel-abdac.h
index edff6a8ba1b5..a8f735d677fa 100644
--- a/include/sound/atmel-abdac.h
+++ b/include/sound/atmel-abdac.h
@@ -10,7 +10,7 @@
 #ifndef __INCLUDE_SOUND_ATMEL_ABDAC_H
 #define __INCLUDE_SOUND_ATMEL_ABDAC_H
 
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 /**
  * struct atmel_abdac_pdata - board specific ABDAC configuration
diff --git a/include/sound/atmel-ac97c.h b/include/sound/atmel-ac97c.h
index 00e6c289a936..f2a1cdc37661 100644
--- a/include/sound/atmel-ac97c.h
+++ b/include/sound/atmel-ac97c.h
@@ -10,7 +10,7 @@
 #ifndef __INCLUDE_SOUND_ATMEL_AC97C_H
 #define __INCLUDE_SOUND_ATMEL_AC97C_H
 
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 #define AC97C_CAPTURE	0x01
 #define AC97C_PLAYBACK	0x02
diff --git a/sound/atmel/abdac.c b/sound/atmel/abdac.c
index edf2ca72d518..154a7c44e38d 100644
--- a/sound/atmel/abdac.c
+++ b/sound/atmel/abdac.c
@@ -9,7 +9,7 @@
  */
 #include <linux/clk.h>
 #include <linux/bitmap.h>
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/init.h>
diff --git a/sound/atmel/ac97c.c b/sound/atmel/ac97c.c
index a04d23174dc2..1dfb35afef8f 100644
--- a/sound/atmel/ac97c.c
+++ b/sound/atmel/ac97c.c
@@ -31,7 +31,7 @@
 #include <sound/atmel-ac97c.h>
 #include <sound/memalloc.h>
 
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 #include <mach/cpu.h>
 
-- 
cgit v1.2.3


From 7e1e2f27c5508518e58e5cbb11e26cbb815f4c56 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 19 Aug 2014 20:29:14 +0300
Subject: dmaengine: dw: convert dw_dma_slave to use explicit HS interfaces

Instead of exposing the possibility to set DMA registers CFG_HI and CFG_LO
strict user to provide handshake interfaces explicitly.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 arch/avr32/mach-at32ap/at32ap700x.c  | 15 +++++----------
 drivers/dma/dw/core.c                |  4 ++--
 include/linux/platform_data/dma-dw.h | 10 ++++------
 3 files changed, 11 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index ec7be287a97e..37b75602adf6 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -1356,10 +1356,8 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 		goto fail;
 
 	slave->sdata.dma_dev = &dw_dmac0_device.dev;
-	slave->sdata.cfg_hi = (DWC_CFGH_SRC_PER(0)
-				| DWC_CFGH_DST_PER(1));
-	slave->sdata.cfg_lo &= ~(DWC_CFGL_HS_DST_POL
-				| DWC_CFGL_HS_SRC_POL);
+	slave->sdata.src_id = 0;
+	slave->sdata.dst_id = 1;
 	slave->sdata.src_master = 1;
 	slave->sdata.dst_master = 0;
 
@@ -2054,8 +2052,7 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 	/* Check if DMA slave interface for capture should be configured. */
 	if (flags & AC97C_CAPTURE) {
 		rx_dws->dma_dev = &dw_dmac0_device.dev;
-		rx_dws->cfg_hi = DWC_CFGH_SRC_PER(3);
-		rx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+		rx_dws->src_id = 3;
 		rx_dws->src_master = 0;
 		rx_dws->dst_master = 1;
 	}
@@ -2063,8 +2060,7 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 	/* Check if DMA slave interface for playback should be configured. */
 	if (flags & AC97C_PLAYBACK) {
 		tx_dws->dma_dev = &dw_dmac0_device.dev;
-		tx_dws->cfg_hi = DWC_CFGH_DST_PER(4);
-		tx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+		tx_dws->dst_id = 4;
 		tx_dws->src_master = 0;
 		tx_dws->dst_master = 1;
 	}
@@ -2136,8 +2132,7 @@ at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
 	dws = &data->dws;
 
 	dws->dma_dev = &dw_dmac0_device.dev;
-	dws->cfg_hi = DWC_CFGH_DST_PER(2);
-	dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+	dws->dst_id = 2;
 	dws->src_master = 0;
 	dws->dst_master = 1;
 
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 1af731b83b3f..0a9c052d437c 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -155,8 +155,8 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 		 */
 		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
 
-		cfghi = dws->cfg_hi;
-		cfglo |= dws->cfg_lo & ~DWC_CFGL_CH_PRIOR_MASK;
+		cfghi |= DWC_CFGH_DST_PER(dws->dst_id);
+		cfghi |= DWC_CFGH_SRC_PER(dws->src_id);
 	} else {
 		if (dwc->direction == DMA_MEM_TO_DEV)
 			cfghi = DWC_CFGH_DST_PER(dwc->request_line);
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
index 68b4024184de..bc411a1bf8e7 100644
--- a/include/linux/platform_data/dma-dw.h
+++ b/include/linux/platform_data/dma-dw.h
@@ -17,17 +17,15 @@
  * struct dw_dma_slave - Controller-specific information about a slave
  *
  * @dma_dev: required DMA master device. Depricated.
- * @bus_id: name of this device channel, not just a device name since
- *          devices may have more than one channel e.g. "foo_tx"
- * @cfg_hi: Platform-specific initializer for the CFG_HI register
- * @cfg_lo: Platform-specific initializer for the CFG_LO register
+ * @src_id:	src request line
+ * @dst_id:	dst request line
  * @src_master: src master for transfers on allocated channel.
  * @dst_master: dest master for transfers on allocated channel.
  */
 struct dw_dma_slave {
 	struct device		*dma_dev;
-	u32			cfg_hi;
-	u32			cfg_lo;
+	u8			src_id;
+	u8			dst_id;
 	u8			src_master;
 	u8			dst_master;
 };
-- 
cgit v1.2.3


From 78f686cae0c67a2edd167cbbe2f36017f0fa4b30 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 10 Sep 2014 22:28:06 +0300
Subject: cfg80211: don't put kek/kck/replay counter on the stack

There's no need to put the values on the stack, just pass a
pointer to the data in the nl80211 message. This reduces stack
usage and avoids potential issues with putting sensitive data
on the stack.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 10 ++++------
 net/wireless/nl80211.c | 10 +++-------
 2 files changed, 7 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 0d17ec9df692..c2c710c14a50 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1980,14 +1980,12 @@ struct cfg80211_wowlan_wakeup {
 
 /**
  * struct cfg80211_gtk_rekey_data - rekey data
- * @kek: key encryption key
- * @kck: key confirmation key
- * @replay_ctr: replay counter
+ * @kek: key encryption key (NL80211_KEK_LEN bytes)
+ * @kck: key confirmation key (NL80211_KCK_LEN bytes)
+ * @replay_ctr: replay counter (NL80211_REPLAY_CTR_LEN bytes)
  */
 struct cfg80211_gtk_rekey_data {
-	u8 kek[NL80211_KEK_LEN];
-	u8 kck[NL80211_KCK_LEN];
-	u8 replay_ctr[NL80211_REPLAY_CTR_LEN];
+	const u8 *kek, *kck, *replay_ctr;
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e388a9f28895..bebdf3d0ae75 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -8959,13 +8959,9 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info)
 	if (nla_len(tb[NL80211_REKEY_DATA_KCK]) != NL80211_KCK_LEN)
 		return -ERANGE;
 
-	memcpy(rekey_data.kek, nla_data(tb[NL80211_REKEY_DATA_KEK]),
-	       NL80211_KEK_LEN);
-	memcpy(rekey_data.kck, nla_data(tb[NL80211_REKEY_DATA_KCK]),
-	       NL80211_KCK_LEN);
-	memcpy(rekey_data.replay_ctr,
-	       nla_data(tb[NL80211_REKEY_DATA_REPLAY_CTR]),
-	       NL80211_REPLAY_CTR_LEN);
+	rekey_data.kek = nla_data(tb[NL80211_REKEY_DATA_KEK]);
+	rekey_data.kck = nla_data(tb[NL80211_REKEY_DATA_KCK]);
+	rekey_data.replay_ctr = nla_data(tb[NL80211_REKEY_DATA_REPLAY_CTR]);
 
 	wdev_lock(wdev);
 	if (!wdev->current_bss) {
-- 
cgit v1.2.3


From 960d01acf62747d6518694f92be5b06f67473833 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 9 Sep 2014 22:55:35 +0300
Subject: cfg80211: add WMM traffic stream API

Add nl80211 and driver API to validate, add and delete traffic
streams with appropriate settings.

The API calls for userspace doing the action frame handshake
with the peer, and then allows only to set up the parameters
in the driver. To avoid setting up a session only to tear it
down again, the validate API is provided, but the real usage
later can still fail so userspace must be prepared for that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h    |   4 ++
 include/net/cfg80211.h       |  23 ++++++++-
 include/uapi/linux/nl80211.h |  28 +++++++++++
 net/wireless/nl80211.c       | 109 +++++++++++++++++++++++++++++++++++++++++++
 net/wireless/rdev-ops.h      |  31 ++++++++++++
 net/wireless/trace.h         |  45 ++++++++++++++++++
 6 files changed, 239 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 61a09f0644aa..b1be39c76931 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -166,8 +166,12 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
 
 #define IEEE80211_MAX_MESH_ID_LEN	32
 
+#define IEEE80211_FIRST_TSPEC_TSID	8
 #define IEEE80211_NUM_TIDS		16
 
+/* number of user priorities 802.11 uses */
+#define IEEE80211_NUM_UPS		8
+
 #define IEEE80211_QOS_CTL_LEN		2
 /* 1d tag mask */
 #define IEEE80211_QOS_CTL_TAG1D_MASK		0x0007
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c2c710c14a50..a13beab123dc 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2318,6 +2318,17 @@ struct cfg80211_qos_map {
  * @set_ap_chanwidth: Set the AP (including P2P GO) mode channel width for the
  *	given interface This is used e.g. for dynamic HT 20/40 MHz channel width
  *	changes during the lifetime of the BSS.
+ *
+ * @add_tx_ts: validate (if admitted_time is 0) or add a TX TS to the device
+ *	with the given parameters; action frame exchange has been handled by
+ *	userspace so this just has to modify the TX path to take the TS into
+ *	account.
+ *	If the admitted time is 0 just validate the parameters to make sure
+ *	the session can be created at all; it is valid to just always return
+ *	success for that but that may result in inefficient behaviour (handshake
+ *	with the peer followed by immediate teardown when the addition is later
+ *	rejected)
+ * @del_tx_ts: remove an existing TX TS
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -2558,6 +2569,12 @@ struct cfg80211_ops {
 
 	int	(*set_ap_chanwidth)(struct wiphy *wiphy, struct net_device *dev,
 				    struct cfg80211_chan_def *chandef);
+
+	int	(*add_tx_ts)(struct wiphy *wiphy, struct net_device *dev,
+			     u8 tsid, const u8 *peer, u8 user_prio,
+			     u16 admitted_time);
+	int	(*del_tx_ts)(struct wiphy *wiphy, struct net_device *dev,
+			     u8 tsid, const u8 *peer);
 };
 
 /*
@@ -2604,9 +2621,13 @@ struct cfg80211_ops {
  * @WIPHY_FLAG_SUPPORTS_5_10_MHZ: Device supports 5 MHz and 10 MHz channels.
  * @WIPHY_FLAG_HAS_CHANNEL_SWITCH: Device supports channel switch in
  *	beaconing mode (AP, IBSS, Mesh, ...).
+ * @WIPHY_FLAG_SUPPORTS_WMM_ADMISSION: the device supports setting up WMM
+ *	TSPEC sessions (TID aka TSID 0-7) with the NL80211_CMD_ADD_TX_TS
+ *	command. Standard IEEE 802.11 TSPEC setup is not yet supported, it
+ *	needs to be able to handle Block-Ack agreements and other things.
  */
 enum wiphy_flags {
-	/* use hole at 0 */
+	WIPHY_FLAG_SUPPORTS_WMM_ADMISSION	= BIT(0),
 	/* use hole at 1 */
 	/* use hole at 2 */
 	WIPHY_FLAG_NETNS_OK			= BIT(3),
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 29c4399e08b9..e5b8caf5e466 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -722,6 +722,22 @@
  *	QoS mapping is relevant for IP packets, it is only valid during an
  *	association. This is cleared on disassociation and AP restart.
  *
+ * @NL80211_CMD_ADD_TX_TS: Ask the kernel to add a traffic stream for the given
+ *	%NL80211_ATTR_TSID and %NL80211_ATTR_MAC with %NL80211_ATTR_USER_PRIO
+ *	and %NL80211_ATTR_ADMITTED_TIME parameters.
+ *	Note that the action frame handshake with the AP shall be handled by
+ *	userspace via the normal management RX/TX framework, this only sets
+ *	up the TX TS in the driver/device.
+ *	If the admitted time attribute is not added then the request just checks
+ *	if a subsequent setup could be successful, the intent is to use this to
+ *	avoid setting up a session with the AP when local restrictions would
+ *	make that impossible. However, the subsequent "real" setup may still
+ *	fail even if the check was successful.
+ * @NL80211_CMD_DEL_TX_TS: Remove an existing TS with the %NL80211_ATTR_TSID
+ *	and %NL80211_ATTR_MAC parameters. It isn't necessary to call this
+ *	before removing a station entry entirely, or before disassociating
+ *	or similar, cleanup will happen in the driver/device in this case.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -893,6 +909,9 @@ enum nl80211_commands {
 
 	NL80211_CMD_SET_QOS_MAP,
 
+	NL80211_CMD_ADD_TX_TS,
+	NL80211_CMD_DEL_TX_TS,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -1611,6 +1630,11 @@ enum nl80211_commands {
  *	drivers to indicate dynack capability. Dynack is automatically disabled
  *	setting valid value for coverage class.
  *
+ * @NL80211_ATTR_TSID: a TSID value (u8 attribute)
+ * @NL80211_ATTR_USER_PRIO: user priority value (u8 attribute)
+ * @NL80211_ATTR_ADMITTED_TIME: admitted time in units of 32 microseconds
+ *	(per second) (u16 attribute)
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1957,6 +1981,10 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_WIPHY_DYN_ACK,
 
+	NL80211_ATTR_TSID,
+	NL80211_ATTR_USER_PRIO,
+	NL80211_ATTR_ADMITTED_TIME,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e9fbd4f4ddb0..ab7ee4893e40 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -391,6 +391,9 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_IFACE_SOCKET_OWNER] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CSA_C_OFFSETS_TX] = { .type = NLA_BINARY },
 	[NL80211_ATTR_USE_RRM] = { .type = NLA_FLAG },
+	[NL80211_ATTR_TSID] = { .type = NLA_U8 },
+	[NL80211_ATTR_USER_PRIO] = { .type = NLA_U8 },
+	[NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 },
 };
 
 /* policy for the key attributes */
@@ -1510,6 +1513,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			if (rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)
 				CMD(channel_switch, CHANNEL_SWITCH);
 			CMD(set_qos_map, SET_QOS_MAP);
+			if (rdev->wiphy.flags &
+					WIPHY_FLAG_SUPPORTS_WMM_ADMISSION)
+				CMD(add_tx_ts, ADD_TX_TS);
 		}
 		/* add into the if now */
 #undef CMD
@@ -9390,6 +9396,93 @@ static int nl80211_set_qos_map(struct sk_buff *skb,
 	return ret;
 }
 
+static int nl80211_add_tx_ts(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	const u8 *peer;
+	u8 tsid, up;
+	u16 admitted_time = 0;
+	int err;
+
+	if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_WMM_ADMISSION))
+		return -EOPNOTSUPP;
+
+	if (!info->attrs[NL80211_ATTR_TSID] || !info->attrs[NL80211_ATTR_MAC] ||
+	    !info->attrs[NL80211_ATTR_USER_PRIO])
+		return -EINVAL;
+
+	tsid = nla_get_u8(info->attrs[NL80211_ATTR_TSID]);
+	if (tsid >= IEEE80211_NUM_TIDS)
+		return -EINVAL;
+
+	up = nla_get_u8(info->attrs[NL80211_ATTR_USER_PRIO]);
+	if (up >= IEEE80211_NUM_UPS)
+		return -EINVAL;
+
+	/* WMM uses TIDs 0-7 even for TSPEC */
+	if (tsid < IEEE80211_FIRST_TSPEC_TSID) {
+		if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_WMM_ADMISSION))
+			return -EINVAL;
+	} else {
+		/* TODO: handle 802.11 TSPEC/admission control
+		 * need more attributes for that (e.g. BA session requirement)
+		 */
+		return -EINVAL;
+	}
+
+	peer = nla_data(info->attrs[NL80211_ATTR_MAC]);
+
+	if (info->attrs[NL80211_ATTR_ADMITTED_TIME]) {
+		admitted_time =
+			nla_get_u16(info->attrs[NL80211_ATTR_ADMITTED_TIME]);
+		if (!admitted_time)
+			return -EINVAL;
+	}
+
+	wdev_lock(wdev);
+	switch (wdev->iftype) {
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+		if (wdev->current_bss)
+			break;
+		err = -ENOTCONN;
+		goto out;
+	default:
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	err = rdev_add_tx_ts(rdev, dev, tsid, peer, up, admitted_time);
+
+ out:
+	wdev_unlock(wdev);
+	return err;
+}
+
+static int nl80211_del_tx_ts(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	const u8 *peer;
+	u8 tsid;
+	int err;
+
+	if (!info->attrs[NL80211_ATTR_TSID] || !info->attrs[NL80211_ATTR_MAC])
+		return -EINVAL;
+
+	tsid = nla_get_u8(info->attrs[NL80211_ATTR_TSID]);
+	peer = nla_data(info->attrs[NL80211_ATTR_MAC]);
+
+	wdev_lock(wdev);
+	err = rdev_del_tx_ts(rdev, dev, tsid, peer);
+	wdev_unlock(wdev);
+
+	return err;
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -10147,6 +10240,22 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_ADD_TX_TS,
+		.doit = nl80211_add_tx_ts,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL80211_CMD_DEL_TX_TS,
+		.doit = nl80211_del_tx_ts,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 /* notification functions */
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 56c2240c30ce..f6d457d6a558 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -915,4 +915,35 @@ rdev_set_ap_chanwidth(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int
+rdev_add_tx_ts(struct cfg80211_registered_device *rdev,
+	       struct net_device *dev, u8 tsid, const u8 *peer,
+	       u8 user_prio, u16 admitted_time)
+{
+	int ret = -EOPNOTSUPP;
+
+	trace_rdev_add_tx_ts(&rdev->wiphy, dev, tsid, peer,
+			     user_prio, admitted_time);
+	if (rdev->ops->add_tx_ts)
+		ret = rdev->ops->add_tx_ts(&rdev->wiphy, dev, tsid, peer,
+					   user_prio, admitted_time);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+
+	return ret;
+}
+
+static inline int
+rdev_del_tx_ts(struct cfg80211_registered_device *rdev,
+	       struct net_device *dev, u8 tsid, const u8 *peer)
+{
+	int ret = -EOPNOTSUPP;
+
+	trace_rdev_del_tx_ts(&rdev->wiphy, dev, tsid, peer);
+	if (rdev->ops->del_tx_ts)
+		ret = rdev->ops->del_tx_ts(&rdev->wiphy, dev, tsid, peer);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+
+	return ret;
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 0c524cd76c83..625a6e6d1168 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1896,6 +1896,51 @@ TRACE_EVENT(rdev_set_ap_chanwidth,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG)
 );
 
+TRACE_EVENT(rdev_add_tx_ts,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 u8 tsid, const u8 *peer, u8 user_prio, u16 admitted_time),
+	TP_ARGS(wiphy, netdev, tsid, peer, user_prio, admitted_time),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(peer)
+		__field(u8, tsid)
+		__field(u8, user_prio)
+		__field(u16, admitted_time)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(peer, peer);
+		__entry->tsid = tsid;
+		__entry->user_prio = user_prio;
+		__entry->admitted_time = admitted_time;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT ", TSID %d, UP %d, time %d",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer),
+		  __entry->tsid, __entry->user_prio, __entry->admitted_time)
+);
+
+TRACE_EVENT(rdev_del_tx_ts,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 u8 tsid, const u8 *peer),
+	TP_ARGS(wiphy, netdev, tsid, peer),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(peer)
+		__field(u8, tsid)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(peer, peer);
+		__entry->tsid = tsid;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT ", TSID %d",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->tsid)
+);
+
 /*************************************************************
  *	     cfg80211 exported functions traces		     *
  *************************************************************/
-- 
cgit v1.2.3


From b0b6aa2c8e0d0e34f7658d5cc1e4fbb59f701c42 Mon Sep 17 00:00:00 2001
From: Eliad Peller <eliad@wizery.com>
Date: Tue, 9 Sep 2014 17:09:45 +0300
Subject: cfg80211/mac80211: add wmm info to assoc event

Userspace might need to know what queues are configured
for uapsd (e.g. for setting proper default values in tspecs).

Add this bitmap to the association event (inside wmm
nested attribute)

Add additional parameter to cfg80211_rx_assoc_resp,
and update its callers.

Signed-off-by: Eliad Peller <eliadx.peller@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  4 +++-
 net/mac80211/mlme.c    |  9 ++++++++-
 net/wireless/mlme.c    |  4 ++--
 net/wireless/nl80211.c | 28 +++++++++++++++++++++-------
 net/wireless/nl80211.h |  3 ++-
 5 files changed, 36 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index a13beab123dc..2ed1f80f7eb6 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3944,6 +3944,7 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr);
  *	moves to cfg80211 in this call
  * @buf: authentication frame (header + body)
  * @len: length of the frame data
+ * @uapsd_queues: bitmap of ACs configured to uapsd. -1 if n/a.
  *
  * After being asked to associate via cfg80211_ops::assoc() the driver must
  * call either this function or cfg80211_auth_timeout().
@@ -3952,7 +3953,8 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr);
  */
 void cfg80211_rx_assoc_resp(struct net_device *dev,
 			    struct cfg80211_bss *bss,
-			    const u8 *buf, size_t len);
+			    const u8 *buf, size_t len,
+			    int uapsd_queues);
 
 /**
  * cfg80211_assoc_timeout - notification of timed out association
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a7b92f5f7161..efa41fc66c1f 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2817,6 +2817,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data;
 	u16 capab_info, status_code, aid;
 	struct ieee802_11_elems elems;
+	int ac, uapsd_queues = -1;
 	u8 *pos;
 	bool reassoc;
 	struct cfg80211_bss *bss;
@@ -2886,9 +2887,15 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		 * is set can cause the interface to go idle
 		 */
 		ieee80211_destroy_assoc_data(sdata, true);
+
+		/* get uapsd queues configuration */
+		uapsd_queues = 0;
+		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
+			if (sdata->tx_conf[ac].uapsd)
+				uapsd_queues |= BIT(ac);
 	}
 
-	cfg80211_rx_assoc_resp(sdata->dev, bss, (u8 *)mgmt, len);
+	cfg80211_rx_assoc_resp(sdata->dev, bss, (u8 *)mgmt, len, uapsd_queues);
 }
 
 static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 369fc334fdad..2c52b59e43f3 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -19,7 +19,7 @@
 
 
 void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
-			    const u8 *buf, size_t len)
+			    const u8 *buf, size_t len, int uapsd_queues)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
@@ -43,7 +43,7 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 		return;
 	}
 
-	nl80211_send_rx_assoc(rdev, dev, buf, len, GFP_KERNEL);
+	nl80211_send_rx_assoc(rdev, dev, buf, len, GFP_KERNEL, uapsd_queues);
 	/* update current_bss etc., consumes the bss reference */
 	__cfg80211_connect_result(dev, mgmt->bssid, NULL, 0, ie, len - ieoffs,
 				  status_code,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ab7ee4893e40..e8114c7a37e3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -10524,7 +10524,8 @@ nla_put_failure:
 static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev,
 				    struct net_device *netdev,
 				    const u8 *buf, size_t len,
-				    enum nl80211_commands cmd, gfp_t gfp)
+				    enum nl80211_commands cmd, gfp_t gfp,
+				    int uapsd_queues)
 {
 	struct sk_buff *msg;
 	void *hdr;
@@ -10544,6 +10545,19 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev,
 	    nla_put(msg, NL80211_ATTR_FRAME, len, buf))
 		goto nla_put_failure;
 
+	if (uapsd_queues >= 0) {
+		struct nlattr *nla_wmm =
+			nla_nest_start(msg, NL80211_ATTR_STA_WME);
+		if (!nla_wmm)
+			goto nla_put_failure;
+
+		if (nla_put_u8(msg, NL80211_STA_WME_UAPSD_QUEUES,
+			       uapsd_queues))
+			goto nla_put_failure;
+
+		nla_nest_end(msg, nla_wmm);
+	}
+
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
@@ -10560,15 +10574,15 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev,
 			  size_t len, gfp_t gfp)
 {
 	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_AUTHENTICATE, gfp);
+				NL80211_CMD_AUTHENTICATE, gfp, -1);
 }
 
 void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev,
 			   struct net_device *netdev, const u8 *buf,
-			   size_t len, gfp_t gfp)
+			   size_t len, gfp_t gfp, int uapsd_queues)
 {
 	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_ASSOCIATE, gfp);
+				NL80211_CMD_ASSOCIATE, gfp, uapsd_queues);
 }
 
 void nl80211_send_deauth(struct cfg80211_registered_device *rdev,
@@ -10576,7 +10590,7 @@ void nl80211_send_deauth(struct cfg80211_registered_device *rdev,
 			 size_t len, gfp_t gfp)
 {
 	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_DEAUTHENTICATE, gfp);
+				NL80211_CMD_DEAUTHENTICATE, gfp, -1);
 }
 
 void nl80211_send_disassoc(struct cfg80211_registered_device *rdev,
@@ -10584,7 +10598,7 @@ void nl80211_send_disassoc(struct cfg80211_registered_device *rdev,
 			   size_t len, gfp_t gfp)
 {
 	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_DISASSOCIATE, gfp);
+				NL80211_CMD_DISASSOCIATE, gfp, -1);
 }
 
 void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf,
@@ -10605,7 +10619,7 @@ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf,
 		cmd = NL80211_CMD_UNPROT_DISASSOCIATE;
 
 	trace_cfg80211_rx_unprot_mlme_mgmt(dev, buf, len);
-	nl80211_send_mlme_event(rdev, dev, buf, len, cmd, GFP_ATOMIC);
+	nl80211_send_mlme_event(rdev, dev, buf, len, cmd, GFP_ATOMIC, -1);
 }
 EXPORT_SYMBOL(cfg80211_rx_unprot_mlme_mgmt);
 
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 49c9a482dd12..7ad70d6f0cc6 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -23,7 +23,8 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev,
 			  const u8 *buf, size_t len, gfp_t gfp);
 void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev,
 			   struct net_device *netdev,
-			   const u8 *buf, size_t len, gfp_t gfp);
+			   const u8 *buf, size_t len, gfp_t gfp,
+			   int uapsd_queues);
 void nl80211_send_deauth(struct cfg80211_registered_device *rdev,
 			 struct net_device *netdev,
 			 const u8 *buf, size_t len, gfp_t gfp);
-- 
cgit v1.2.3


From 18998c381b19bfc3c285361ff6200ded7444aa2c Mon Sep 17 00:00:00 2001
From: Eliad Peller <eliad@wizery.com>
Date: Wed, 10 Sep 2014 14:07:34 +0300
Subject: cfg80211: allow requesting SMPS mode on ap start

Add feature bits to indicate device support for
static-smps and dynamic-smps modes.

Add a new NL80211_ATTR_SMPS_MODE attribue to allow
configuring the smps mode to be used by the ap
(e.g. configuring to ap to dynamic smps mode will
reduce power consumption while having minor effect
on throughput)

Signed-off-by: Eliad Peller <eliad@wizery.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  2 ++
 include/uapi/linux/nl80211.h | 33 +++++++++++++++++++++++++++++++++
 net/wireless/nl80211.c       | 24 ++++++++++++++++++++++++
 3 files changed, 59 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 2ed1f80f7eb6..a2ddcf2398fd 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -664,6 +664,7 @@ struct cfg80211_acl_data {
  * @crypto: crypto settings
  * @privacy: the BSS uses privacy
  * @auth_type: Authentication type (algorithm)
+ * @smps_mode: SMPS mode
  * @inactivity_timeout: time in seconds to determine station's inactivity.
  * @p2p_ctwindow: P2P CT Window
  * @p2p_opp_ps: P2P opportunistic PS
@@ -682,6 +683,7 @@ struct cfg80211_ap_settings {
 	struct cfg80211_crypto_settings crypto;
 	bool privacy;
 	enum nl80211_auth_type auth_type;
+	enum nl80211_smps_mode smps_mode;
 	int inactivity_timeout;
 	u8 p2p_ctwindow;
 	bool p2p_opp_ps;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index e5b8caf5e466..4b28dc07bcb1 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1635,6 +1635,9 @@ enum nl80211_commands {
  * @NL80211_ATTR_ADMITTED_TIME: admitted time in units of 32 microseconds
  *	(per second) (u16 attribute)
  *
+ * @NL80211_ATTR_SMPS_MODE: SMPS mode to use (ap mode). see
+ *	&enum nl80211_smps_mode.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1985,6 +1988,8 @@ enum nl80211_attrs {
 	NL80211_ATTR_USER_PRIO,
 	NL80211_ATTR_ADMITTED_TIME,
 
+	NL80211_ATTR_SMPS_MODE,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -4030,6 +4035,13 @@ enum nl80211_ap_sme_features {
  * @NL80211_FEATURE_ACKTO_ESTIMATION: This driver supports dynamic ACK timeout
  *	estimation (dynack). %NL80211_ATTR_WIPHY_DYN_ACK flag attribute is used
  *	to enable dynack.
+ * @NL80211_FEATURE_STATIC_SMPS: Device supports static spatial
+ *	multiplexing powersave, ie. can turn off all but one chain
+ *	even on HT connections that should be using more chains.
+ * @NL80211_FEATURE_DYNAMIC_SMPS: Device supports dynamic spatial
+ *	multiplexing powersave, ie. can turn off all but one chain
+ *	and then wake the rest up as required after, for example,
+ *	rts/cts handshake.
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -4056,6 +4068,8 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_QUIET				= 1 << 21,
 	NL80211_FEATURE_TX_POWER_INSERTION		= 1 << 22,
 	NL80211_FEATURE_ACKTO_ESTIMATION		= 1 << 23,
+	NL80211_FEATURE_STATIC_SMPS			= 1 << 24,
+	NL80211_FEATURE_DYNAMIC_SMPS			= 1 << 25,
 };
 
 /**
@@ -4129,6 +4143,25 @@ enum nl80211_acl_policy {
 	NL80211_ACL_POLICY_DENY_UNLESS_LISTED,
 };
 
+/**
+ * enum nl80211_smps_mode - SMPS mode
+ *
+ * Requested SMPS mode (for AP mode)
+ *
+ * @NL80211_SMPS_OFF: SMPS off (use all antennas).
+ * @NL80211_SMPS_STATIC: static SMPS (use a single antenna)
+ * @NL80211_SMPS_DYNAMIC: dynamic smps (start with a single antenna and
+ *	turn on other antennas after CTS/RTS).
+ */
+enum nl80211_smps_mode {
+	NL80211_SMPS_OFF,
+	NL80211_SMPS_STATIC,
+	NL80211_SMPS_DYNAMIC,
+
+	__NL80211_SMPS_AFTER_LAST,
+	NL80211_SMPS_MAX = __NL80211_SMPS_AFTER_LAST - 1
+};
+
 /**
  * enum nl80211_radar_event - type of radar event for DFS operation
  *
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e8114c7a37e3..4cce3e17964d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -394,6 +394,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_TSID] = { .type = NLA_U8 },
 	[NL80211_ATTR_USER_PRIO] = { .type = NLA_U8 },
 	[NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 },
+	[NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 },
 };
 
 /* policy for the key attributes */
@@ -3345,6 +3346,29 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 			return PTR_ERR(params.acl);
 	}
 
+	if (info->attrs[NL80211_ATTR_SMPS_MODE]) {
+		params.smps_mode =
+			nla_get_u8(info->attrs[NL80211_ATTR_SMPS_MODE]);
+		switch (params.smps_mode) {
+		case NL80211_SMPS_OFF:
+			break;
+		case NL80211_SMPS_STATIC:
+			if (!(rdev->wiphy.features &
+			      NL80211_FEATURE_STATIC_SMPS))
+				return -EINVAL;
+			break;
+		case NL80211_SMPS_DYNAMIC:
+			if (!(rdev->wiphy.features &
+			      NL80211_FEATURE_DYNAMIC_SMPS))
+				return -EINVAL;
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else {
+		params.smps_mode = NL80211_SMPS_OFF;
+	}
+
 	wdev_lock(wdev);
 	err = rdev_start_ap(rdev, dev, &params);
 	if (!err) {
-- 
cgit v1.2.3


From 0d8614b4b926d0f657d15d7eb5125bcb24b9fd41 Mon Sep 17 00:00:00 2001
From: Eliad Peller <eliad@wizery.com>
Date: Wed, 10 Sep 2014 14:07:36 +0300
Subject: mac80211: replace SMPS hw flags with wiphy feature bits

Use the new static_smps / dynamic_smps feature bits
instead of mac80211-internal hw flags.

Signed-off-by: Eliad Peller <eliad@wizery.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath10k/mac.c       |  5 +++--
 drivers/net/wireless/iwlegacy/4965-mac.c    |  5 ++---
 drivers/net/wireless/iwlwifi/dvm/mac80211.c |  4 ++--
 drivers/net/wireless/iwlwifi/mvm/mac80211.c |  8 ++++----
 drivers/net/wireless/mac80211_hwsim.c       |  8 ++++----
 include/net/mac80211.h                      | 13 +------------
 net/mac80211/debugfs.c                      |  5 -----
 net/mac80211/debugfs_netdev.c               |  4 ++--
 net/mac80211/mlme.c                         |  2 +-
 9 files changed, 19 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 9d61bb157189..4b5f0011ab5d 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4759,7 +4759,6 @@ int ath10k_mac_register(struct ath10k *ar)
 			IEEE80211_HW_MFP_CAPABLE |
 			IEEE80211_HW_REPORTS_TX_ACK_STATUS |
 			IEEE80211_HW_HAS_RATE_CONTROL |
-			IEEE80211_HW_SUPPORTS_STATIC_SMPS |
 			IEEE80211_HW_AP_LINK_PS |
 			IEEE80211_HW_SPECTRUM_MGMT;
 
@@ -4767,8 +4766,10 @@ int ath10k_mac_register(struct ath10k *ar)
 	 * bytes is used for padding/alignment if necessary. */
 	ar->hw->extra_tx_headroom += sizeof(struct htt_data_tx_desc_frag)*2 + 4;
 
+	ar->hw->wiphy->features |= NL80211_FEATURE_STATIC_SMPS;
+
 	if (ar->ht_cap_info & WMI_HT_CAP_DYNAMIC_SMPS)
-		ar->hw->flags |= IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS;
+		ar->hw->wiphy->features |= NL80211_FEATURE_DYNAMIC_SMPS;
 
 	if (ar->ht_cap_info & WMI_HT_CAP_ENABLED) {
 		ar->hw->flags |= IEEE80211_HW_AMPDU_AGGREGATION;
diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c
index 3dcbe2cd2b28..9f930a0cba09 100644
--- a/drivers/net/wireless/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/iwlegacy/4965-mac.c
@@ -5757,9 +5757,8 @@ il4965_mac_setup_register(struct il_priv *il, u32 max_probe_length)
 	    IEEE80211_HW_REPORTS_TX_ACK_STATUS | IEEE80211_HW_SUPPORTS_PS |
 	    IEEE80211_HW_SUPPORTS_DYNAMIC_PS;
 	if (il->cfg->sku & IL_SKU_N)
-		hw->flags |=
-		    IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS |
-		    IEEE80211_HW_SUPPORTS_STATIC_SMPS;
+		hw->wiphy->features |= NL80211_FEATURE_DYNAMIC_SMPS |
+				       NL80211_FEATURE_STATIC_SMPS;
 
 	hw->sta_data_size = sizeof(struct il_station_priv);
 	hw->vif_data_size = sizeof(struct il_vif_priv);
diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
index afb98f4fdaf3..2364a3c09b9e 100644
--- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
@@ -125,8 +125,8 @@ int iwlagn_mac_setup_register(struct iwl_priv *priv,
 	 */
 
 	if (priv->nvm_data->sku_cap_11n_enable)
-		hw->flags |= IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS |
-			     IEEE80211_HW_SUPPORTS_STATIC_SMPS;
+		hw->wiphy->features |= NL80211_FEATURE_DYNAMIC_SMPS |
+				       NL80211_FEATURE_STATIC_SMPS;
 
 	/*
 	 * Enable 11w if advertised by firmware and software crypto
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index 7c8796584c25..395fc05638c2 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -301,9 +301,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 		    IEEE80211_HW_AMPDU_AGGREGATION |
 		    IEEE80211_HW_TIMING_BEACON_ONLY |
 		    IEEE80211_HW_CONNECTION_MONITOR |
-		    IEEE80211_HW_CHANCTX_STA_CSA |
-		    IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS |
-		    IEEE80211_HW_SUPPORTS_STATIC_SMPS;
+		    IEEE80211_HW_CHANCTX_STA_CSA;
 
 	hw->queues = mvm->first_agg_queue;
 	hw->offchannel_tx_hw_queue = IWL_MVM_OFFCHANNEL_QUEUE;
@@ -405,7 +403,9 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 
 	hw->wiphy->features |= NL80211_FEATURE_P2P_GO_CTWIN |
 			       NL80211_FEATURE_LOW_PRIORITY_SCAN |
-			       NL80211_FEATURE_P2P_GO_OPPPS;
+			       NL80211_FEATURE_P2P_GO_OPPPS |
+			       NL80211_FEATURE_DYNAMIC_SMPS |
+			       NL80211_FEATURE_STATIC_SMPS;
 
 	mvm->rts_threshold = IEEE80211_MAX_RTS_THRESHOLD;
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 1326f6121835..babbdc1ce741 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2045,8 +2045,6 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2,
 
 	hw->flags = IEEE80211_HW_MFP_CAPABLE |
 		    IEEE80211_HW_SIGNAL_DBM |
-		    IEEE80211_HW_SUPPORTS_STATIC_SMPS |
-		    IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS |
 		    IEEE80211_HW_AMPDU_AGGREGATION |
 		    IEEE80211_HW_WANT_MONITOR_VIF |
 		    IEEE80211_HW_QUEUE_CONTROL |
@@ -2059,8 +2057,10 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2,
 			    WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL |
 			    WIPHY_FLAG_AP_UAPSD |
 			    WIPHY_FLAG_HAS_CHANNEL_SWITCH;
-	hw->wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR;
-	hw->wiphy->features |= NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE;
+	hw->wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR |
+			       NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE |
+			       NL80211_FEATURE_STATIC_SMPS |
+			       NL80211_FEATURE_DYNAMIC_SMPS;
 
 	/* ask mac80211 to reserve space for magic */
 	hw->vif_data_size = sizeof(struct hwsim_vif_priv);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index c6e6a6804ee4..0ad1f47d2dc7 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1537,16 +1537,6 @@ struct ieee80211_tx_control {
  * @IEEE80211_HW_MFP_CAPABLE:
  *	Hardware supports management frame protection (MFP, IEEE 802.11w).
  *
- * @IEEE80211_HW_SUPPORTS_STATIC_SMPS:
- *	Hardware supports static spatial multiplexing powersave,
- *	ie. can turn off all but one chain even on HT connections
- *	that should be using more chains.
- *
- * @IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS:
- *	Hardware supports dynamic spatial multiplexing powersave,
- *	ie. can turn off all but one chain and then wake the rest
- *	up as required after, for example, rts/cts handshake.
- *
  * @IEEE80211_HW_SUPPORTS_UAPSD:
  *	Hardware supports Unscheduled Automatic Power Save Delivery
  *	(U-APSD) in managed mode. The mode is configured with
@@ -1632,8 +1622,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_SUPPORTS_DYNAMIC_PS		= 1<<12,
 	IEEE80211_HW_MFP_CAPABLE			= 1<<13,
 	IEEE80211_HW_WANT_MONITOR_VIF			= 1<<14,
-	IEEE80211_HW_SUPPORTS_STATIC_SMPS		= 1<<15,
-	IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS		= 1<<16,
+	/* free slots */
 	IEEE80211_HW_SUPPORTS_UAPSD			= 1<<17,
 	IEEE80211_HW_REPORTS_TX_ACK_STATUS		= 1<<18,
 	IEEE80211_HW_CONNECTION_MONITOR			= 1<<19,
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 574656174f91..54a189f0393e 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -303,11 +303,6 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf,
 		sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_DYNAMIC_PS\n");
 	if (local->hw.flags & IEEE80211_HW_MFP_CAPABLE)
 		sf += scnprintf(buf + sf, mxln - sf, "MFP_CAPABLE\n");
-	if (local->hw.flags & IEEE80211_HW_SUPPORTS_STATIC_SMPS)
-		sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_STATIC_SMPS\n");
-	if (local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS)
-		sf += scnprintf(buf + sf, mxln - sf,
-				"SUPPORTS_DYNAMIC_SMPS\n");
 	if (local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)
 		sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_UAPSD\n");
 	if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index e205ebabfa50..c68896adfa96 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -226,12 +226,12 @@ static int ieee80211_set_smps(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_local *local = sdata->local;
 	int err;
 
-	if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_STATIC_SMPS) &&
+	if (!(local->hw.wiphy->features & NL80211_FEATURE_STATIC_SMPS) &&
 	    smps_mode == IEEE80211_SMPS_STATIC)
 		return -EINVAL;
 
 	/* auto should be dynamic if in PS mode */
-	if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS) &&
+	if (!(local->hw.wiphy->features & NL80211_FEATURE_DYNAMIC_SMPS) &&
 	    (smps_mode == IEEE80211_SMPS_DYNAMIC ||
 	     smps_mode == IEEE80211_SMPS_AUTOMATIC))
 		return -EINVAL;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index efa41fc66c1f..9d4ccb2cf3c9 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3805,7 +3805,7 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata)
 	ifmgd->uapsd_max_sp_len = sdata->local->hw.uapsd_max_sp_len;
 	ifmgd->p2p_noa_index = -1;
 
-	if (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS)
+	if (sdata->local->hw.wiphy->features & NL80211_FEATURE_DYNAMIC_SMPS)
 		ifmgd->req_smps = IEEE80211_SMPS_AUTOMATIC;
 	else
 		ifmgd->req_smps = IEEE80211_SMPS_OFF;
-- 
cgit v1.2.3


From fb446a1acdb981921de06bfde3a2178da7174481 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 17:36:10 +0200
Subject: drm: Simplify return value of drm_get_last_vbltimestamp
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Imo u32 hints at a register value, but in reality all callers only
care whether the sampled timestamp is precise or not. So give them
just a bool.

Also move the declaration out of drmP.h, it's only used in drm_irq.c.

v2: Also drop the EXPORT_SYMBOL, spotted by Mario.

Cc: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
---
 drivers/gpu/drm/drm_irq.c | 25 +++++++++++++++----------
 include/drm/drmP.h        |  2 --
 2 files changed, 15 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index ad699b729278..15f748c7fa7e 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -55,6 +55,10 @@
  */
 #define DRM_REDUNDANT_VBLIRQ_THRESH_NS 1000000
 
+static bool
+drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
+			  struct timeval *tvblank, unsigned flags);
+
 /**
  * drm_update_vblank_count - update the master vblank counter
  * @dev: DRM device
@@ -74,7 +78,8 @@
 static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
-	u32 cur_vblank, diff, tslot, rc;
+	u32 cur_vblank, diff, tslot;
+	bool rc;
 	struct timeval t_vblank;
 
 	/*
@@ -132,7 +137,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	unsigned long irqflags;
 	u32 vblcount;
 	s64 diff_ns;
-	int vblrc;
+	bool vblrc;
 	struct timeval tvblank;
 	int count = DRM_TIMESTAMP_MAXRETRIES;
 
@@ -156,7 +161,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 * vblank interrupt is disabled.
 	 */
 	if (!vblank->enabled &&
-	    drm_get_last_vbltimestamp(dev, crtc, &tvblank, 0) > 0) {
+	    drm_get_last_vbltimestamp(dev, crtc, &tvblank, 0)) {
 		drm_update_vblank_count(dev, crtc);
 		spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
 		return;
@@ -204,7 +209,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 * available. In that case we can't account for this and just
 	 * hope for the best.
 	 */
-	if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) {
+	if (vblrc && (abs64(diff_ns) > 1000000)) {
 		/* Store new timestamp in ringbuffer. */
 		vblanktimestamp(dev, crtc, vblcount + 1) = tvblank;
 
@@ -781,10 +786,11 @@ static struct timeval get_drm_timestamp(void)
  * call, i.e., it isn't very precisely locked to the true vblank.
  *
  * Returns:
- * Non-zero if timestamp is considered to be very precise, zero otherwise.
+ * True if timestamp is considered to be very precise, false otherwise.
  */
-u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
-			      struct timeval *tvblank, unsigned flags)
+static bool
+drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
+			  struct timeval *tvblank, unsigned flags)
 {
 	int ret;
 
@@ -796,7 +802,7 @@ u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
 		ret = dev->driver->get_vblank_timestamp(dev, crtc, &max_error,
 							tvblank, flags);
 		if (ret > 0)
-			return (u32) ret;
+			return true;
 	}
 
 	/* GPU high precision timestamp query unsupported or failed.
@@ -804,9 +810,8 @@ u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
 	 */
 	*tvblank = get_drm_timestamp();
 
-	return 0;
+	return false;
 }
-EXPORT_SYMBOL(drm_get_last_vbltimestamp);
 
 /**
  * drm_vblank_count - retrieve "cooked" vblank counter value
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 17a5c10474bd..a97307525c2d 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1320,8 +1320,6 @@ extern void drm_crtc_vblank_off(struct drm_crtc *crtc);
 extern void drm_crtc_vblank_on(struct drm_crtc *crtc);
 extern void drm_vblank_cleanup(struct drm_device *dev);
 
-extern u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
-				     struct timeval *tvblank, unsigned flags);
 extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,
 						 int crtc, int *max_error,
 						 struct timeval *vblank_time,
-- 
cgit v1.2.3


From 3d3cbd84300e7be1e53083cac0f6f9c12978ecb4 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 17:36:11 +0200
Subject: drm: Clarify vblank ts/scanoutpos sampling #defines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I've read INVBL as "invalid backlight" and got mightly confused.
The #defines are already fairly long and we can afford to extend
them a bit more without resulting in ugly code all over.

I'm not sure how useful the complicated bitmask return value of these
functions really are since no one checks them. But for now let's keep
things as is.

Cc: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_irq.c                 | 4 ++--
 drivers/gpu/drm/i915/i915_irq.c           | 2 +-
 drivers/gpu/drm/nouveau/nouveau_display.c | 2 +-
 drivers/gpu/drm/radeon/radeon_display.c   | 2 +-
 drivers/gpu/drm/radeon/radeon_pm.c        | 2 +-
 include/drm/drmP.h                        | 4 ++--
 6 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 15f748c7fa7e..79836594030c 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -721,7 +721,7 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 	 * within vblank area, counting down the number of lines until
 	 * start of scanout.
 	 */
-	invbl = vbl_status & DRM_SCANOUTPOS_INVBL;
+	invbl = vbl_status & DRM_SCANOUTPOS_IN_VBLANK;
 
 	/* Convert scanout position into elapsed time at raw_time query
 	 * since start of scanout at first display scanline. delta_ns
@@ -751,7 +751,7 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 
 	vbl_status = DRM_VBLANKTIME_SCANOUTPOS_METHOD;
 	if (invbl)
-		vbl_status |= DRM_VBLANKTIME_INVBL;
+		vbl_status |= DRM_VBLANKTIME_IN_VBLANK;
 
 	return vbl_status;
 }
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 845f0f6c1eeb..20dd9e233fc6 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1020,7 +1020,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 
 	/* In vblank? */
 	if (in_vbl)
-		ret |= DRM_SCANOUTPOS_INVBL;
+		ret |= DRM_SCANOUTPOS_IN_VBLANK;
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 47ad74255bf1..37a6ab8a97f8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -111,7 +111,7 @@ nouveau_display_scanoutpos_head(struct drm_crtc *crtc, int *vpos, int *hpos,
 	if (etime) *etime = ns_to_ktime(args.time[1]);
 
 	if (*vpos < 0)
-		ret |= DRM_SCANOUTPOS_INVBL;
+		ret |= DRM_SCANOUTPOS_IN_VBLANK;
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 3fdf87318069..fd8cd0c3600f 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1917,7 +1917,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int fl
 
 	/* In vblank? */
 	if (in_vbl)
-		ret |= DRM_SCANOUTPOS_INVBL;
+		ret |= DRM_SCANOUTPOS_IN_VBLANK;
 
 	/* Is vpos outside nominal vblank area, but less than
 	 * 1/100 of a frame height away from start of vblank?
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 23314be49480..7fd665a22908 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1560,7 +1560,7 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev)
 		if (rdev->pm.active_crtcs & (1 << crtc)) {
 			vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, crtc, 0, &vpos, &hpos, NULL, NULL);
 			if ((vbl_status & DRM_SCANOUTPOS_VALID) &&
-			    !(vbl_status & DRM_SCANOUTPOS_INVBL))
+			    !(vbl_status & DRM_SCANOUTPOS_IN_VBLANK))
 				in_vbl = false;
 		}
 	}
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index a97307525c2d..7b87fccff183 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -674,11 +674,11 @@ struct drm_master {
 /* Flags and return codes for get_vblank_timestamp() driver function. */
 #define DRM_CALLED_FROM_VBLIRQ 1
 #define DRM_VBLANKTIME_SCANOUTPOS_METHOD (1 << 0)
-#define DRM_VBLANKTIME_INVBL             (1 << 1)
+#define DRM_VBLANKTIME_IN_VBLANK         (1 << 1)
 
 /* get_scanout_position() return flags */
 #define DRM_SCANOUTPOS_VALID        (1 << 0)
-#define DRM_SCANOUTPOS_INVBL        (1 << 1)
+#define DRM_SCANOUTPOS_IN_VBLANK    (1 << 1)
 #define DRM_SCANOUTPOS_ACCURATE     (1 << 2)
 
 struct drm_bus {
-- 
cgit v1.2.3


From ae9c0af2c0ea92e57013ab2dd7271ba7d6b2a833 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 4 Sep 2014 20:01:52 +0200
Subject: drm/ttm: allow fence to be added as shared
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds a new flag to the ttm_validate_buffer list to
add the fence as shared to the reservation object.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/qxl/qxl_release.c        |  1 +
 drivers/gpu/drm/radeon/radeon_cs.c       |  1 +
 drivers/gpu/drm/radeon/radeon_vm.c       |  3 +++
 drivers/gpu/drm/ttm/ttm_execbuf_util.c   | 18 +++++++++++++++---
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c  |  3 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c |  5 +++++
 include/drm/ttm/ttm_execbuf_util.h       |  2 ++
 7 files changed, 30 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index a6e19c83143e..446e71ca36cb 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -226,6 +226,7 @@ int qxl_release_list_add(struct qxl_release *release, struct qxl_bo *bo)
 
 	qxl_bo_ref(bo);
 	entry->tv.bo = &bo->tbo;
+	entry->tv.shared = false;
 	list_add_tail(&entry->tv.head, &release->bos);
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 6e3d1c8f3483..cd517ab93608 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -183,6 +183,7 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		}
 
 		p->relocs[i].tv.bo = &p->relocs[i].robj->tbo;
+		p->relocs[i].tv.shared = false;
 		p->relocs[i].handle = r->handle;
 
 		radeon_cs_buckets_add(&buckets, &p->relocs[i].tv.head,
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 671ee566aa51..1cce4468cd75 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -143,6 +143,7 @@ struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev,
 	list[0].prefered_domains = RADEON_GEM_DOMAIN_VRAM;
 	list[0].allowed_domains = RADEON_GEM_DOMAIN_VRAM;
 	list[0].tv.bo = &vm->page_directory->tbo;
+	list[0].tv.shared = false;
 	list[0].tiling_flags = 0;
 	list[0].handle = 0;
 	list_add(&list[0].tv.head, head);
@@ -156,6 +157,7 @@ struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev,
 		list[idx].prefered_domains = RADEON_GEM_DOMAIN_VRAM;
 		list[idx].allowed_domains = RADEON_GEM_DOMAIN_VRAM;
 		list[idx].tv.bo = &list[idx].robj->tbo;
+		list[idx].tv.shared = false;
 		list[idx].tiling_flags = 0;
 		list[idx].handle = 0;
 		list_add(&list[idx++].tv.head, head);
@@ -395,6 +397,7 @@ static int radeon_vm_clear_bo(struct radeon_device *rdev,
 
         memset(&tv, 0, sizeof(tv));
         tv.bo = &bo->tbo;
+	tv.shared = false;
 
         INIT_LIST_HEAD(&head);
         list_add(&tv.head, &head);
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index adafc0f8ec06..8ce508e76208 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -119,8 +119,14 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 			ret = -EBUSY;
 		}
 
-		if (!ret)
-			continue;
+		if (!ret) {
+			if (!entry->shared)
+				continue;
+
+			ret = reservation_object_reserve_shared(bo->resv);
+			if (!ret)
+				continue;
+		}
 
 		/* uh oh, we lost out, drop every reservation and try
 		 * to only reserve this buffer, then start over if
@@ -136,6 +142,9 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 			ret = 0;
 		}
 
+		if (!ret && entry->shared)
+			ret = reservation_object_reserve_shared(bo->resv);
+
 		if (unlikely(ret != 0)) {
 			if (ret == -EINTR)
 				ret = -ERESTARTSYS;
@@ -183,7 +192,10 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 
 	list_for_each_entry(entry, list, head) {
 		bo = entry->bo;
-		reservation_object_add_excl_fence(bo->resv, fence);
+		if (entry->shared)
+			reservation_object_add_shared_fence(bo->resv, fence);
+		else
+			reservation_object_add_excl_fence(bo->resv, fence);
 		ttm_bo_add_to_lru(bo);
 		__ttm_bo_unreserve(bo);
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 0ceaddc8e4f7..b4de3b2a7cc5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -346,6 +346,7 @@ static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
 		++sw_context->cur_val_buf;
 		val_buf = &vval_buf->base;
 		val_buf->bo = ttm_bo_reference(bo);
+		val_buf->shared = false;
 		list_add_tail(&val_buf->head, &sw_context->validate_nodes);
 		vval_buf->validate_as_mob = validate_as_mob;
 	}
@@ -2670,9 +2671,11 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv,
 	INIT_LIST_HEAD(&validate_list);
 
 	pinned_val.bo = ttm_bo_reference(dev_priv->pinned_bo);
+	pinned_val.shared = false;
 	list_add_tail(&pinned_val.head, &validate_list);
 
 	query_val.bo = ttm_bo_reference(dev_priv->dummy_query_bo);
+	query_val.shared = false;
 	list_add_tail(&query_val.head, &validate_list);
 
 	ret = ttm_eu_reserve_buffers(&ticket, &validate_list, false);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index ff0e03b97753..26584316cb78 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -133,6 +133,7 @@ static void vmw_resource_release(struct kref *kref)
 			struct ttm_validate_buffer val_buf;
 
 			val_buf.bo = bo;
+			val_buf.shared = false;
 			res->func->unbind(res, false, &val_buf);
 		}
 		res->backup_dirty = false;
@@ -1219,6 +1220,7 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 
 	INIT_LIST_HEAD(&val_list);
 	val_buf->bo = ttm_bo_reference(&res->backup->base);
+	val_buf->shared = false;
 	list_add_tail(&val_buf->head, &val_list);
 	ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible);
 	if (unlikely(ret != 0))
@@ -1312,6 +1314,7 @@ int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
 	BUG_ON(!func->may_evict);
 
 	val_buf.bo = NULL;
+	val_buf.shared = false;
 	ret = vmw_resource_check_buffer(res, interruptible, &val_buf);
 	if (unlikely(ret != 0))
 		return ret;
@@ -1357,6 +1360,7 @@ int vmw_resource_validate(struct vmw_resource *res)
 		return 0;
 
 	val_buf.bo = NULL;
+	val_buf.shared = false;
 	if (res->backup)
 		val_buf.bo = &res->backup->base;
 	do {
@@ -1474,6 +1478,7 @@ void vmw_resource_move_notify(struct ttm_buffer_object *bo,
 		struct ttm_validate_buffer val_buf;
 
 		val_buf.bo = bo;
+		val_buf.shared = false;
 
 		list_for_each_entry_safe(res, n, &dma_buf->res_list, mob_head) {
 
diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index ff11a424f752..460441714413 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -39,11 +39,13 @@
  *
  * @head:           list head for thread-private list.
  * @bo:             refcounted buffer object pointer.
+ * @shared:         should the fence be added shared?
  */
 
 struct ttm_validate_buffer {
 	struct list_head head;
 	struct ttm_buffer_object *bo;
+	bool shared;
 };
 
 /**
-- 
cgit v1.2.3


From 67981fefb20e717cea55b42f9081a833fa46b3be Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 11 Sep 2014 16:55:04 +0200
Subject: netfilter: fix compilation of masquerading without
 IP_NF_TARGET_MASQUERADE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

 CONFIG_NF_NAT_MASQUERADE_IPV6=m
 # CONFIG_IP6_NF_TARGET_MASQUERADE is not set

results in:

net/ipv6/netfilter/nf_nat_masquerade_ipv6.c: In function ‘nf_nat_masquerade_ipv6’:
net/ipv6/netfilter/nf_nat_masquerade_ipv6.c:41:14: error: ‘struct nf_conn_nat’ has no member named ‘masq_index’
  nfct_nat(ct)->masq_index = out->ifindex;
              ^
net/ipv6/netfilter/nf_nat_masquerade_ipv6.c: In function ‘device_cmp’:
net/ipv6/netfilter/nf_nat_masquerade_ipv6.c:61:12: error: ‘const struct nf_conn_nat’ has no member named ‘masq_index’
  return nat->masq_index == (int)(long)ifindex;
            ^
net/ipv6/netfilter/nf_nat_masquerade_ipv6.c:62:1: warning: control
reaches end of non-void function [-Wreturn-type]
 }
 ^
make[3]: *** [net/ipv6/netfilter/nf_nat_masquerade_ipv6.o] Error 1

Fix this by using the new NF_NAT_MASQUERADE_IPV4 and _IPV6 symbols
in include/net/netfilter/nf_nat.h.

Reported-by: Jim Davis <jim.epost@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat.h | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index a71dd333ac68..344b1ab19220 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -32,10 +32,8 @@ struct nf_conn_nat {
 	struct hlist_node bysource;
 	struct nf_conn *ct;
 	union nf_conntrack_nat_help help;
-#if defined(CONFIG_IP_NF_TARGET_MASQUERADE) || \
-    defined(CONFIG_IP_NF_TARGET_MASQUERADE_MODULE) || \
-    defined(CONFIG_IP6_NF_TARGET_MASQUERADE) || \
-    defined(CONFIG_IP6_NF_TARGET_MASQUERADE_MODULE)
+#if IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV4) || \
+    IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV6)
 	int masq_index;
 #endif
 };
@@ -68,8 +66,8 @@ static inline bool nf_nat_oif_changed(unsigned int hooknum,
 				      struct nf_conn_nat *nat,
 				      const struct net_device *out)
 {
-#if IS_ENABLED(CONFIG_IP_NF_TARGET_MASQUERADE) || \
-    IS_ENABLED(CONFIG_IP6_NF_TARGET_MASQUERADE)
+#if IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV4) || \
+    IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV6)
 	return nat->masq_index && hooknum == NF_INET_POST_ROUTING &&
 	       CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL &&
 	       nat->masq_index != out->ifindex;
-- 
cgit v1.2.3


From 39e393bb4f653d38aea40190e1aa9a49062eed4d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 11 Sep 2014 11:02:39 +0200
Subject: netfilter: nf_tables: add NFTA_MASQ_UNSPEC to nft_masq_attributes

To keep this consistent with other nft_*_attributes.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index eeec0ae845ef..66d66dd3ff79 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -806,6 +806,7 @@ enum nft_nat_attributes {
  * @NFTA_MASQ_FLAGS: NAT flags (see NF_NAT_RANGE_* in linux/netfilter/nf_nat.h) (NLA_U32)
  */
 enum nft_masq_attributes {
+	NFTA_MASQ_UNSPEC,
 	NFTA_MASQ_FLAGS,
 	__NFTA_MASQ_MAX
 };
-- 
cgit v1.2.3


From 5ebc77de83c7b74543de774afa7395b3b790e65e Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Wed, 10 Sep 2014 22:49:30 +0000
Subject: xen/arm: introduce XENFEAT_grant_map_identity

The flag tells us that the hypervisor maps a grant page to guest
physical address == machine address of the page in addition to the
normal grant mapping address. It is needed to properly issue cache
maintenance operation at the completion of a DMA operation involving a
foreign grant.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Tested-by: Denis Schneider <v1ne2go@gmail.com>
---
 arch/arm/xen/enlighten.c         | 6 ++++++
 include/xen/interface/features.h | 3 +++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 98544c5f86e9..0e15f011f9c8 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -260,6 +260,12 @@ static int __init xen_guest_init(void)
 	xen_domain_type = XEN_HVM_DOMAIN;
 
 	xen_setup_features();
+
+	if (!xen_feature(XENFEAT_grant_map_identity)) {
+		pr_warn("Please upgrade your Xen.\n"
+				"If your platform has any non-coherent DMA devices, they won't work properly.\n");
+	}
+
 	if (xen_feature(XENFEAT_dom0))
 		xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
 	else
diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h
index 131a6ccdba25..14334d0161d5 100644
--- a/include/xen/interface/features.h
+++ b/include/xen/interface/features.h
@@ -53,6 +53,9 @@
 /* operation as Dom0 is supported */
 #define XENFEAT_dom0                      11
 
+/* Xen also maps grant references at pfn = mfn */
+#define XENFEAT_grant_map_identity        12
+
 #define XENFEAT_NR_SUBMAPS 1
 
 #endif /* __XEN_PUBLIC_FEATURES_H__ */
-- 
cgit v1.2.3


From e351943b081f4d9e6f692ce1a6117e8d2e71f478 Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@fedoraproject.org>
Date: Fri, 5 Sep 2014 13:19:59 -0400
Subject: drm/vmwgfx: Fix drm.h include

The userspace drm.h include doesn't prefix the drm directory.  This can lead
to compile failures as /usr/include/drm/ isn't in the standard gcc include
paths.  Fix it to be <drm/drm.h>, which matches the rest of the driver drm
header files that get installed into /usr/include/drm.

Red Hat Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1138759

Fixes: 1d7a5cbf8f74e
Reported-by: Jeffrey Bastian <jbastian@redhat.com>
Signed-off-by: Josh Boyer <jwboyer@fedoraproject.org>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/uapi/drm/vmwgfx_drm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 4fc66f6b12ce..c472bedbe38e 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -29,7 +29,7 @@
 #define __VMWGFX_DRM_H__
 
 #ifndef __KERNEL__
-#include <drm.h>
+#include <drm/drm.h>
 #endif
 
 #define DRM_VMW_MAX_SURFACE_FACES 6
-- 
cgit v1.2.3


From fd7e0d719260259f6e4e7711bd63a4175557d559 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Wed, 10 Sep 2014 18:23:07 +1000
Subject: drm: split ati_pcigart.h out of drmP.h

Just move this into a separate header file, and make the
two users use it.

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ati_pcigart.c       |  2 ++
 drivers/gpu/drm/r128/r128_drv.h     |  1 +
 drivers/gpu/drm/radeon/radeon_drv.h |  1 +
 include/drm/ati_pcigart.h           | 28 ++++++++++++++++++++++++++++
 include/drm/drmP.h                  | 23 -----------------------
 5 files changed, 32 insertions(+), 23 deletions(-)
 create mode 100644 include/drm/ati_pcigart.h

(limited to 'include')

diff --git a/drivers/gpu/drm/ati_pcigart.c b/drivers/gpu/drm/ati_pcigart.c
index c399dea27a3b..6c4d4b6eba80 100644
--- a/drivers/gpu/drm/ati_pcigart.c
+++ b/drivers/gpu/drm/ati_pcigart.c
@@ -34,6 +34,8 @@
 #include <linux/export.h>
 #include <drm/drmP.h>
 
+#include <drm/ati_pcigart.h>
+
 # define ATI_PCIGART_PAGE_SIZE		4096	/**< PCI GART page size */
 
 static int drm_ati_alloc_pcigart_table(struct drm_device *dev,
diff --git a/drivers/gpu/drm/r128/r128_drv.h b/drivers/gpu/drm/r128/r128_drv.h
index 5bf3f5ff805d..49fe02670c2e 100644
--- a/drivers/gpu/drm/r128/r128_drv.h
+++ b/drivers/gpu/drm/r128/r128_drv.h
@@ -35,6 +35,7 @@
 #ifndef __R128_DRV_H__
 #define __R128_DRV_H__
 
+#include <drm/ati_pcigart.h>
 /* General customization:
  */
 #define DRIVER_AUTHOR		"Gareth Hughes, VA Linux Systems Inc."
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index dafd812e4571..3590cb47a22e 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -34,6 +34,7 @@
 #include <linux/firmware.h>
 #include <linux/platform_device.h>
 
+#include <drm/ati_pcigart.h>
 #include "radeon_family.h"
 
 /* General customization:
diff --git a/include/drm/ati_pcigart.h b/include/drm/ati_pcigart.h
new file mode 100644
index 000000000000..da4bfcd81a37
--- /dev/null
+++ b/include/drm/ati_pcigart.h
@@ -0,0 +1,28 @@
+#ifndef DRM_ATI_PCIGART_H
+#define DRM_ATI_PCIGART_H
+
+/* location of GART table */
+#define DRM_ATI_GART_MAIN 1
+#define DRM_ATI_GART_FB   2
+
+#define DRM_ATI_GART_PCI 1
+#define DRM_ATI_GART_PCIE 2
+#define DRM_ATI_GART_IGP 3
+
+struct drm_ati_pcigart_info {
+	int gart_table_location;
+	int gart_reg_if;
+	void *addr;
+	dma_addr_t bus_addr;
+	dma_addr_t table_mask;
+	struct drm_dma_handle *table_handle;
+	struct drm_local_map mapping;
+	int table_size;
+};
+
+extern int drm_ati_pcigart_init(struct drm_device *dev,
+				struct drm_ati_pcigart_info * gart_info);
+extern int drm_ati_pcigart_cleanup(struct drm_device *dev,
+				   struct drm_ati_pcigart_info * gart_info);
+
+#endif
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index be1160fa5ebc..e4ba3de22601 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -461,24 +461,6 @@ struct drm_map_list {
 	struct drm_master *master;
 };
 
-/* location of GART table */
-#define DRM_ATI_GART_MAIN 1
-#define DRM_ATI_GART_FB   2
-
-#define DRM_ATI_GART_PCI 1
-#define DRM_ATI_GART_PCIE 2
-#define DRM_ATI_GART_IGP 3
-
-struct drm_ati_pcigart_info {
-	int gart_table_location;
-	int gart_reg_if;
-	void *addr;
-	dma_addr_t bus_addr;
-	dma_addr_t table_mask;
-	struct drm_dma_handle *table_handle;
-	struct drm_local_map mapping;
-	int table_size;
-};
 
 /**
  * This structure defines the drm_mm memory object, which will be used by the
@@ -1324,11 +1306,6 @@ extern int drm_sg_alloc(struct drm_device *dev, void *data,
 extern int drm_sg_free(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
 
-			       /* ATI PCIGART support (ati_pcigart.h) */
-extern int drm_ati_pcigart_init(struct drm_device *dev,
-				struct drm_ati_pcigart_info * gart_info);
-extern int drm_ati_pcigart_cleanup(struct drm_device *dev,
-				   struct drm_ati_pcigart_info * gart_info);
 
 extern drm_dma_handle_t *drm_pci_alloc(struct drm_device *dev, size_t size,
 				       size_t align);
-- 
cgit v1.2.3


From a3b3ca753cdc92c7d5f57404afed3115b3b79cc6 Mon Sep 17 00:00:00 2001
From: Jaewon Kim <jaewon02.kim@samsung.com>
Date: Thu, 11 Sep 2014 23:15:01 -0700
Subject: Input: add haptic driver on max77693

This driver to supports the haptic controller on MAX77693 Multifunction
device with PMIC, CHARGER, LED, MUIC, HAPTIC.

This driver supports external pwm and LRA (Linear Resonant Actuator) motor.
User can control the haptic device via force feedback framework.

Signed-off-by: Jaewon Kim <jaewon02.kim@samsung.com>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/Kconfig           |  11 ++
 drivers/input/misc/Makefile          |   1 +
 drivers/input/misc/max77693-haptic.c | 357 +++++++++++++++++++++++++++++++++++
 include/linux/mfd/max77693-private.h |   9 +
 4 files changed, 378 insertions(+)
 create mode 100644 drivers/input/misc/max77693-haptic.c

(limited to 'include')

diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 36382e5b7703..23297ab6163f 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -144,6 +144,17 @@ config INPUT_M68K_BEEP
 	tristate "M68k Beeper support"
 	depends on M68K
 
+config INPUT_MAX77693_HAPTIC
+	tristate "MAXIM MAX77693 haptic controller support"
+	depends on MFD_MAX77693 && PWM
+	select INPUT_FF_MEMLESS
+	help
+	  This option enables support for the haptic controller on
+	  MAXIM MAX77693 chip.
+
+	  To compile this driver as module, choose M here: the
+	  module will be called max77693-haptic.
+
 config INPUT_MAX8925_ONKEY
 	tristate "MAX8925 ONKEY support"
 	depends on MFD_MAX8925
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index e8b84d2c845f..19c760361f80 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_INPUT_IXP4XX_BEEPER)	+= ixp4xx-beeper.o
 obj-$(CONFIG_INPUT_KEYSPAN_REMOTE)	+= keyspan_remote.o
 obj-$(CONFIG_INPUT_KXTJ9)		+= kxtj9.o
 obj-$(CONFIG_INPUT_M68K_BEEP)		+= m68kspkr.o
+obj-$(CONFIG_INPUT_MAX77693_HAPTIC)	+= max77693-haptic.o
 obj-$(CONFIG_INPUT_MAX8925_ONKEY)	+= max8925_onkey.o
 obj-$(CONFIG_INPUT_MAX8997_HAPTIC)	+= max8997_haptic.o
 obj-$(CONFIG_INPUT_MC13783_PWRBUTTON)	+= mc13783-pwrbutton.o
diff --git a/drivers/input/misc/max77693-haptic.c b/drivers/input/misc/max77693-haptic.c
new file mode 100644
index 000000000000..d605db4d2f39
--- /dev/null
+++ b/drivers/input/misc/max77693-haptic.c
@@ -0,0 +1,357 @@
+/*
+ * MAXIM MAX77693 Haptic device driver
+ *
+ * Copyright (C) 2014 Samsung Electronics
+ * Jaewon Kim <jaewon02.kim@samsung.com>
+ *
+ * This program is not provided / owned by Maxim Integrated Products.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+#include <linux/input.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pwm.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/regulator/consumer.h>
+#include <linux/mfd/max77693.h>
+#include <linux/mfd/max77693-private.h>
+
+#define MAX_MAGNITUDE_SHIFT	16
+
+enum max77693_haptic_motor_type {
+	MAX77693_HAPTIC_ERM = 0,
+	MAX77693_HAPTIC_LRA,
+};
+
+enum max77693_haptic_pulse_mode {
+	MAX77693_HAPTIC_EXTERNAL_MODE = 0,
+	MAX77693_HAPTIC_INTERNAL_MODE,
+};
+
+enum max77693_haptic_pwm_divisor {
+	MAX77693_HAPTIC_PWM_DIVISOR_32 = 0,
+	MAX77693_HAPTIC_PWM_DIVISOR_64,
+	MAX77693_HAPTIC_PWM_DIVISOR_128,
+	MAX77693_HAPTIC_PWM_DIVISOR_256,
+};
+
+struct max77693_haptic {
+	struct regmap *regmap_pmic;
+	struct regmap *regmap_haptic;
+	struct device *dev;
+	struct input_dev *input_dev;
+	struct pwm_device *pwm_dev;
+	struct regulator *motor_reg;
+
+	bool enabled;
+	bool suspend_state;
+	unsigned int magnitude;
+	unsigned int pwm_duty;
+	enum max77693_haptic_motor_type type;
+	enum max77693_haptic_pulse_mode mode;
+	enum max77693_haptic_pwm_divisor pwm_divisor;
+
+	struct work_struct work;
+};
+
+static int max77693_haptic_set_duty_cycle(struct max77693_haptic *haptic)
+{
+	int delta = (haptic->pwm_dev->period + haptic->pwm_duty) / 2;
+	int error;
+
+	error = pwm_config(haptic->pwm_dev, delta, haptic->pwm_dev->period);
+	if (error) {
+		dev_err(haptic->dev, "failed to configure pwm: %d\n", error);
+		return error;
+	}
+
+	return 0;
+}
+
+static int max77693_haptic_configure(struct max77693_haptic *haptic,
+				     bool enable)
+{
+	unsigned int value;
+	int error;
+
+	value = ((haptic->type << MAX77693_CONFIG2_MODE) |
+		(enable << MAX77693_CONFIG2_MEN) |
+		(haptic->mode << MAX77693_CONFIG2_HTYP) |
+		(haptic->pwm_divisor));
+
+	error = regmap_write(haptic->regmap_haptic,
+			     MAX77693_HAPTIC_REG_CONFIG2, value);
+	if (error) {
+		dev_err(haptic->dev,
+			"failed to update haptic config: %d\n", error);
+		return error;
+	}
+
+	return 0;
+}
+
+static int max77693_haptic_lowsys(struct max77693_haptic *haptic, bool enable)
+{
+	int error;
+
+	error = regmap_update_bits(haptic->regmap_pmic,
+				   MAX77693_PMIC_REG_LSCNFG,
+				   MAX77693_PMIC_LOW_SYS_MASK,
+				   enable << MAX77693_PMIC_LOW_SYS_SHIFT);
+	if (error) {
+		dev_err(haptic->dev, "cannot update pmic regmap: %d\n", error);
+		return error;
+	}
+
+	return 0;
+}
+
+static void max77693_haptic_enable(struct max77693_haptic *haptic)
+{
+	int error;
+
+	if (haptic->enabled)
+		return;
+
+	error = pwm_enable(haptic->pwm_dev);
+	if (error) {
+		dev_err(haptic->dev,
+			"failed to enable haptic pwm device: %d\n", error);
+		return;
+	}
+
+	error = max77693_haptic_lowsys(haptic, true);
+	if (error)
+		goto err_enable_lowsys;
+
+	error = max77693_haptic_configure(haptic, true);
+	if (error)
+		goto err_enable_config;
+
+	haptic->enabled = true;
+
+	return;
+
+err_enable_config:
+	max77693_haptic_lowsys(haptic, false);
+err_enable_lowsys:
+	pwm_disable(haptic->pwm_dev);
+}
+
+static void max77693_haptic_disable(struct max77693_haptic *haptic)
+{
+	int error;
+
+	if (haptic->enabled)
+		return;
+
+	error = max77693_haptic_configure(haptic, false);
+	if (error)
+		return;
+
+	error = max77693_haptic_lowsys(haptic, false);
+	if (error)
+		goto err_disable_lowsys;
+
+	pwm_disable(haptic->pwm_dev);
+	haptic->enabled = false;
+
+	return;
+
+err_disable_lowsys:
+	max77693_haptic_configure(haptic, true);
+}
+
+static void max77693_haptic_play_work(struct work_struct *work)
+{
+	struct max77693_haptic *haptic =
+			container_of(work, struct max77693_haptic, work);
+	int error;
+
+	error = max77693_haptic_set_duty_cycle(haptic);
+	if (error) {
+		dev_err(haptic->dev, "failed to set duty cycle: %d\n", error);
+		return;
+	}
+
+	if (haptic->magnitude)
+		max77693_haptic_enable(haptic);
+	else
+		max77693_haptic_disable(haptic);
+}
+
+static int max77693_haptic_play_effect(struct input_dev *dev, void *data,
+				       struct ff_effect *effect)
+{
+	struct max77693_haptic *haptic = input_get_drvdata(dev);
+	uint64_t period_mag_multi;
+
+	haptic->magnitude = effect->u.rumble.strong_magnitude;
+	if (!haptic->magnitude)
+		haptic->magnitude = effect->u.rumble.weak_magnitude;
+
+	/*
+	 * The magnitude comes from force-feedback interface.
+	 * The formula to convert magnitude to pwm_duty as follows:
+	 * - pwm_duty = (magnitude * pwm_period) / MAX_MAGNITUDE(0xFFFF)
+	 */
+	period_mag_multi = (int64_t)(haptic->pwm_dev->period *
+						haptic->magnitude);
+	haptic->pwm_duty = (unsigned int)(period_mag_multi >>
+						MAX_MAGNITUDE_SHIFT);
+
+	schedule_work(&haptic->work);
+
+	return 0;
+}
+
+static int max77693_haptic_open(struct input_dev *dev)
+{
+	struct max77693_haptic *haptic = input_get_drvdata(dev);
+	int error;
+
+	error = regulator_enable(haptic->motor_reg);
+	if (error) {
+		dev_err(haptic->dev,
+			"failed to enable regulator: %d\n", error);
+		return error;
+	}
+
+	return 0;
+}
+
+static void max77693_haptic_close(struct input_dev *dev)
+{
+	struct max77693_haptic *haptic = input_get_drvdata(dev);
+	int error;
+
+	cancel_work_sync(&haptic->work);
+	max77693_haptic_disable(haptic);
+
+	error = regulator_disable(haptic->motor_reg);
+	if (error)
+		dev_err(haptic->dev,
+			"failed to disable regulator: %d\n", error);
+}
+
+static int max77693_haptic_probe(struct platform_device *pdev)
+{
+	struct max77693_dev *max77693 = dev_get_drvdata(pdev->dev.parent);
+	struct max77693_haptic *haptic;
+	int error;
+
+	haptic = devm_kzalloc(&pdev->dev, sizeof(*haptic), GFP_KERNEL);
+	if (!haptic)
+		return -ENOMEM;
+
+	haptic->regmap_pmic = max77693->regmap;
+	haptic->regmap_haptic = max77693->regmap_haptic;
+	haptic->dev = &pdev->dev;
+	haptic->type = MAX77693_HAPTIC_LRA;
+	haptic->mode = MAX77693_HAPTIC_EXTERNAL_MODE;
+	haptic->pwm_divisor = MAX77693_HAPTIC_PWM_DIVISOR_128;
+	haptic->suspend_state = false;
+
+	INIT_WORK(&haptic->work, max77693_haptic_play_work);
+
+	/* Get pwm and regulatot for haptic device */
+	haptic->pwm_dev = devm_pwm_get(&pdev->dev, NULL);
+	if (IS_ERR(haptic->pwm_dev)) {
+		dev_err(&pdev->dev, "failed to get pwm device\n");
+		return PTR_ERR(haptic->pwm_dev);
+	}
+
+	haptic->motor_reg = devm_regulator_get(&pdev->dev, "haptic");
+	if (IS_ERR(haptic->motor_reg)) {
+		dev_err(&pdev->dev, "failed to get regulator\n");
+		return PTR_ERR(haptic->motor_reg);
+	}
+
+	/* Initialize input device for haptic device */
+	haptic->input_dev = devm_input_allocate_device(&pdev->dev);
+	if (!haptic->input_dev) {
+		dev_err(&pdev->dev, "failed to allocate input device\n");
+		return -ENOMEM;
+	}
+
+	haptic->input_dev->name = "max77693-haptic";
+	haptic->input_dev->id.version = 1;
+	haptic->input_dev->dev.parent = &pdev->dev;
+	haptic->input_dev->open = max77693_haptic_open;
+	haptic->input_dev->close = max77693_haptic_close;
+	input_set_drvdata(haptic->input_dev, haptic);
+	input_set_capability(haptic->input_dev, EV_FF, FF_RUMBLE);
+
+	error = input_ff_create_memless(haptic->input_dev, NULL,
+				max77693_haptic_play_effect);
+	if (error) {
+		dev_err(&pdev->dev, "failed to create force-feedback\n");
+		return error;
+	}
+
+	error = input_register_device(haptic->input_dev);
+	if (error) {
+		dev_err(&pdev->dev, "failed to register input device\n");
+		return error;
+	}
+
+	platform_set_drvdata(pdev, haptic);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int max77693_haptic_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct max77693_haptic *haptic = platform_get_drvdata(pdev);
+
+	if (haptic->enabled) {
+		max77693_haptic_disable(haptic);
+		haptic->suspend_state = true;
+	}
+
+	return 0;
+}
+
+static int max77693_haptic_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct max77693_haptic *haptic = platform_get_drvdata(pdev);
+
+	if (haptic->suspend_state) {
+		max77693_haptic_enable(haptic);
+		haptic->suspend_state = false;
+	}
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(max77693_haptic_pm_ops,
+			 max77693_haptic_suspend, max77693_haptic_resume);
+
+static struct platform_driver max77693_haptic_driver = {
+	.driver		= {
+		.name	= "max77693-haptic",
+		.owner	= THIS_MODULE,
+		.pm	= &max77693_haptic_pm_ops,
+	},
+	.probe		= max77693_haptic_probe,
+};
+module_platform_driver(max77693_haptic_driver);
+
+MODULE_AUTHOR("Jaewon Kim <jaewon02.kim@samsung.com>");
+MODULE_DESCRIPTION("MAXIM MAX77693 Haptic driver");
+MODULE_ALIAS("platform:max77693-haptic");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index c466ff3e16b8..d0e578fd7053 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -251,6 +251,15 @@ enum max77693_haptic_reg {
 	MAX77693_HAPTIC_REG_END,
 };
 
+/* max77693-pmic LSCNFG configuraton register */
+#define MAX77693_PMIC_LOW_SYS_MASK      0x80
+#define MAX77693_PMIC_LOW_SYS_SHIFT     7
+
+/* max77693-haptic configuration register */
+#define MAX77693_CONFIG2_MODE           7
+#define MAX77693_CONFIG2_MEN            6
+#define MAX77693_CONFIG2_HTYP           5
+
 enum max77693_irq_source {
 	LED_INT = 0,
 	TOPSYS_INT,
-- 
cgit v1.2.3


From a266162aef4f43307d18c88fb5ecaffd8e9303af Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 11 Sep 2014 07:41:51 +0200
Subject: drm: Move dma functions into drm_legacy.h

Also drop the unneeded EXPORT_SYMBOL and sprinkle drm_legacy_ prefixes
where missing.

v2: Drop the confusing _core_ and drop extern, both suggested by
David.

Cc: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_bufs.c   |  2 +-
 drivers/gpu/drm/drm_dma.c    | 10 ++++------
 drivers/gpu/drm/drm_fops.c   |  2 +-
 drivers/gpu/drm/drm_legacy.h |  8 ++++++++
 include/drm/drmP.h           |  7 -------
 5 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 9e04d6a43fa4..70ba89f66199 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -1338,7 +1338,7 @@ int drm_legacy_freebufs(struct drm_device *dev, void *data,
 				  task_pid_nr(current));
 			return -EINVAL;
 		}
-		drm_free_buffer(dev, buf);
+		drm_legacy_free_buffer(dev, buf);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/drm_dma.c b/drivers/gpu/drm/drm_dma.c
index 8a140a953754..1b1dd356a1e4 100644
--- a/drivers/gpu/drm/drm_dma.c
+++ b/drivers/gpu/drm/drm_dma.c
@@ -124,7 +124,7 @@ void drm_legacy_dma_takedown(struct drm_device *dev)
  *
  * Resets the fields of \p buf.
  */
-void drm_free_buffer(struct drm_device *dev, struct drm_buf * buf)
+void drm_legacy_free_buffer(struct drm_device *dev, struct drm_buf * buf)
 {
 	if (!buf)
 		return;
@@ -142,8 +142,8 @@ void drm_free_buffer(struct drm_device *dev, struct drm_buf * buf)
  *
  * Frees each buffer associated with \p file_priv not already on the hardware.
  */
-void drm_core_reclaim_buffers(struct drm_device *dev,
-			      struct drm_file *file_priv)
+void drm_legacy_reclaim_buffers(struct drm_device *dev,
+				struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	int i;
@@ -154,7 +154,7 @@ void drm_core_reclaim_buffers(struct drm_device *dev,
 		if (dma->buflist[i]->file_priv == file_priv) {
 			switch (dma->buflist[i]->list) {
 			case DRM_LIST_NONE:
-				drm_free_buffer(dev, dma->buflist[i]);
+				drm_legacy_free_buffer(dev, dma->buflist[i]);
 				break;
 			case DRM_LIST_WAIT:
 				dma->buflist[i]->list = DRM_LIST_RECLAIM;
@@ -166,5 +166,3 @@ void drm_core_reclaim_buffers(struct drm_device *dev,
 		}
 	}
 }
-
-EXPORT_SYMBOL(drm_core_reclaim_buffers);
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index b419990042b0..3bb6234d072a 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -404,7 +404,7 @@ int drm_release(struct inode *inode, struct file *filp)
 		drm_master_release(dev, filp);
 
 	if (drm_core_check_feature(dev, DRIVER_HAVE_DMA))
-		drm_core_reclaim_buffers(dev, file_priv);
+		drm_legacy_reclaim_buffers(dev, file_priv);
 
 	drm_events_release(file_priv);
 
diff --git a/drivers/gpu/drm/drm_legacy.h b/drivers/gpu/drm/drm_legacy.h
index 3049af5a01b3..0e0df225dec6 100644
--- a/drivers/gpu/drm/drm_legacy.h
+++ b/drivers/gpu/drm/drm_legacy.h
@@ -92,4 +92,12 @@ int drm_legacy_lock(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_unlock(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_lock_free(struct drm_lock_data *lock, unsigned int ctx);
 
+/* DMA support */
+int drm_legacy_dma_setup(struct drm_device *dev);
+void drm_legacy_dma_takedown(struct drm_device *dev);
+void drm_legacy_free_buffer(struct drm_device *dev,
+			    struct drm_buf * buf);
+void drm_legacy_reclaim_buffers(struct drm_device *dev,
+				struct drm_file *filp);
+
 #endif /* __DRM_LEGACY_H__ */
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 027e4c5dbf03..caf29af2dd54 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1140,13 +1140,6 @@ void drm_clflush_virt_range(void *addr, unsigned long length);
  * DMA quiscent + idle. DMA quiescent usually requires the hardware lock.
  */
 
-				/* DMA support (drm_dma.h) */
-extern int drm_legacy_dma_setup(struct drm_device *dev);
-extern void drm_legacy_dma_takedown(struct drm_device *dev);
-extern void drm_free_buffer(struct drm_device *dev, struct drm_buf * buf);
-extern void drm_core_reclaim_buffers(struct drm_device *dev,
-				     struct drm_file *filp);
-
 				/* IRQ support (drm_irq.h) */
 extern int drm_control(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
-- 
cgit v1.2.3


From 9ec4e2ff3e269756a253282c784776e2166be7bc Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 11 Sep 2014 07:42:43 +0200
Subject: drm: Move sg functions into drm_legacy.h

Also sprinkle the drm_legacy_ prefix where missing.

v2: Drop extern from function declarations and include "drm_legacy.h"
in drm_scatter.c, spotted by David.

Cc: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_ioctl.c   | 4 ++--
 drivers/gpu/drm/drm_legacy.h  | 7 +++++++
 drivers/gpu/drm/drm_scatter.c | 9 +++++----
 include/drm/drmP.h            | 7 -------
 4 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 187dfaaeb491..4c0822973db4 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -107,8 +107,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_AGP_UNBIND, drm_agp_unbind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 #endif
 
-	DRM_IOCTL_DEF(DRM_IOCTL_SG_ALLOC, drm_sg_alloc, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_SG_FREE, drm_sg_free, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_SG_ALLOC, drm_legacy_sg_alloc, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_SG_FREE, drm_legacy_sg_free, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank, DRM_UNLOCKED),
 
diff --git a/drivers/gpu/drm/drm_legacy.h b/drivers/gpu/drm/drm_legacy.h
index 0e0df225dec6..3cc0efa7304a 100644
--- a/drivers/gpu/drm/drm_legacy.h
+++ b/drivers/gpu/drm/drm_legacy.h
@@ -100,4 +100,11 @@ void drm_legacy_free_buffer(struct drm_device *dev,
 void drm_legacy_reclaim_buffers(struct drm_device *dev,
 				struct drm_file *filp);
 
+/* Scatter Gather Support */
+void drm_legacy_sg_cleanup(struct drm_device *dev);
+int drm_legacy_sg_alloc(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_legacy_sg_free(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv);
+
 #endif /* __DRM_LEGACY_H__ */
diff --git a/drivers/gpu/drm/drm_scatter.c b/drivers/gpu/drm/drm_scatter.c
index 1c78406f6e71..4f0f3b36d537 100644
--- a/drivers/gpu/drm/drm_scatter.c
+++ b/drivers/gpu/drm/drm_scatter.c
@@ -34,6 +34,7 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 #define DEBUG_SCATTER 0
 
@@ -78,8 +79,8 @@ void drm_legacy_sg_cleanup(struct drm_device *dev)
 # define ScatterHandle(x) (unsigned int)(x)
 #endif
 
-int drm_sg_alloc(struct drm_device *dev, void *data,
-		 struct drm_file *file_priv)
+int drm_legacy_sg_alloc(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
 {
 	struct drm_scatter_gather *request = data;
 	struct drm_sg_mem *entry;
@@ -194,8 +195,8 @@ int drm_sg_alloc(struct drm_device *dev, void *data,
 	return -ENOMEM;
 }
 
-int drm_sg_free(struct drm_device *dev, void *data,
-		struct drm_file *file_priv)
+int drm_legacy_sg_free(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
 {
 	struct drm_scatter_gather *request = data;
 	struct drm_sg_mem *entry;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index caf29af2dd54..cd35bc902925 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1300,13 +1300,6 @@ void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpr
 
 extern int drm_vma_info(struct seq_file *m, void *data);
 
-				/* Scatter Gather Support (drm_scatter.h) */
-extern void drm_legacy_sg_cleanup(struct drm_device *dev);
-extern int drm_sg_alloc(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_sg_free(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
-
 
 extern drm_dma_handle_t *drm_pci_alloc(struct drm_device *dev, size_t size,
 				       size_t align);
-- 
cgit v1.2.3


From a677f4cc88b2b7491c0c400e07b6630852971e32 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:48 +0200
Subject: drm: Move drm_legacy_vma_flush into drm_legacy.h

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
---
 drivers/gpu/drm/drm_legacy.h | 2 ++
 include/drm/drmP.h           | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_legacy.h b/drivers/gpu/drm/drm_legacy.h
index 3cc0efa7304a..011dc6f1ad94 100644
--- a/drivers/gpu/drm/drm_legacy.h
+++ b/drivers/gpu/drm/drm_legacy.h
@@ -71,6 +71,8 @@ int drm_legacy_freebufs(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_mapbufs(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_dma_ioctl(struct drm_device *d, void *v, struct drm_file *f);
 
+void drm_legacy_vma_flush(struct drm_device *d);
+
 /*
  * AGP Support
  */
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index cd35bc902925..2b6d5241fe59 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1321,8 +1321,6 @@ struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev);
 int drm_legacy_addbufs_agp(struct drm_device *d, struct drm_buf_desc *req);
 int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
 
-void drm_legacy_vma_flush(struct drm_device *d);
-
 void drm_legacy_idlelock_take(struct drm_lock_data *lock);
 void drm_legacy_idlelock_release(struct drm_lock_data *lock);
 
-- 
cgit v1.2.3


From 4f03b1fc1eb286b73d453c03cdb45a3827726a44 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:49 +0200
Subject: drm: Create drm legacy driver header

And move a few legayc functions to start things over there.

It compiles ...

Inspired by a patch from Dave Airlie, but with a split between drm.ko
private legacy functions and stuff used by drivers.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_legacy.h        |  1 +
 drivers/gpu/drm/i810/i810_drv.h     |  2 ++
 drivers/gpu/drm/i915/i915_dma.c     |  1 +
 drivers/gpu/drm/mga/mga_drv.h       |  2 ++
 drivers/gpu/drm/r128/r128_drv.h     |  2 ++
 drivers/gpu/drm/radeon/radeon_drv.h |  1 +
 drivers/gpu/drm/savage/savage_drv.h |  2 ++
 drivers/gpu/drm/sis/sis_drv.h       |  2 ++
 drivers/gpu/drm/via/via_drv.h       |  2 ++
 include/drm/drmP.h                  | 15 ----------
 include/drm/drm_legacy.h            | 58 +++++++++++++++++++++++++++++++++++++
 11 files changed, 73 insertions(+), 15 deletions(-)
 create mode 100644 include/drm/drm_legacy.h

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_legacy.h b/drivers/gpu/drm/drm_legacy.h
index 011dc6f1ad94..c1dc61473db5 100644
--- a/drivers/gpu/drm/drm_legacy.h
+++ b/drivers/gpu/drm/drm_legacy.h
@@ -29,6 +29,7 @@
  * drivers use them, and removing them are API breaks.
  */
 #include <linux/list.h>
+#include <drm/drm_legacy.h>
 
 struct agp_memory;
 struct drm_device;
diff --git a/drivers/gpu/drm/i810/i810_drv.h b/drivers/gpu/drm/i810/i810_drv.h
index d4d16eddd651..93ec5dc4e7d3 100644
--- a/drivers/gpu/drm/i810/i810_drv.h
+++ b/drivers/gpu/drm/i810/i810_drv.h
@@ -32,6 +32,8 @@
 #ifndef _I810_DRV_H_
 #define _I810_DRV_H_
 
+#include <drm/drm_legacy.h>
+
 /* General customization:
  */
 
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 689c3326636f..8535f96f2c59 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -31,6 +31,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_legacy.h>
 #include "intel_drv.h"
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h
index fe453213600a..b4a2014917e5 100644
--- a/drivers/gpu/drm/mga/mga_drv.h
+++ b/drivers/gpu/drm/mga/mga_drv.h
@@ -31,6 +31,8 @@
 #ifndef __MGA_DRV_H__
 #define __MGA_DRV_H__
 
+#include <drm/drm_legacy.h>
+
 /* General customization:
  */
 
diff --git a/drivers/gpu/drm/r128/r128_drv.h b/drivers/gpu/drm/r128/r128_drv.h
index 49fe02670c2e..723e5d6f10a4 100644
--- a/drivers/gpu/drm/r128/r128_drv.h
+++ b/drivers/gpu/drm/r128/r128_drv.h
@@ -36,6 +36,8 @@
 #define __R128_DRV_H__
 
 #include <drm/ati_pcigart.h>
+#include <drm/drm_legacy.h>
+
 /* General customization:
  */
 #define DRIVER_AUTHOR		"Gareth Hughes, VA Linux Systems Inc."
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index 3590cb47a22e..46bd3938282c 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -33,6 +33,7 @@
 
 #include <linux/firmware.h>
 #include <linux/platform_device.h>
+#include <drm/drm_legacy.h>
 
 #include <drm/ati_pcigart.h>
 #include "radeon_family.h"
diff --git a/drivers/gpu/drm/savage/savage_drv.h b/drivers/gpu/drm/savage/savage_drv.h
index 335f8fcf1041..37b699571ad0 100644
--- a/drivers/gpu/drm/savage/savage_drv.h
+++ b/drivers/gpu/drm/savage/savage_drv.h
@@ -26,6 +26,8 @@
 #ifndef __SAVAGE_DRV_H__
 #define __SAVAGE_DRV_H__
 
+#include <drm/drm_legacy.h>
+
 #define DRIVER_AUTHOR	"Felix Kuehling"
 
 #define DRIVER_NAME	"savage"
diff --git a/drivers/gpu/drm/sis/sis_drv.h b/drivers/gpu/drm/sis/sis_drv.h
index c31c0253054d..16f972b2a76a 100644
--- a/drivers/gpu/drm/sis/sis_drv.h
+++ b/drivers/gpu/drm/sis/sis_drv.h
@@ -28,6 +28,8 @@
 #ifndef _SIS_DRV_H_
 #define _SIS_DRV_H_
 
+#include <drm/drm_legacy.h>
+
 /* General customization:
  */
 
diff --git a/drivers/gpu/drm/via/via_drv.h b/drivers/gpu/drm/via/via_drv.h
index ad0273256beb..ef8c500b4a00 100644
--- a/drivers/gpu/drm/via/via_drv.h
+++ b/drivers/gpu/drm/via/via_drv.h
@@ -25,6 +25,8 @@
 #define _VIA_DRV_H_
 
 #include <drm/drm_mm.h>
+#include <drm/drm_legacy.h>
+
 #define DRIVER_AUTHOR	"Various"
 
 #define DRIVER_NAME		"via"
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 2b6d5241fe59..fe6db4cc0db2 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1309,21 +1309,6 @@ extern int drm_pci_set_unique(struct drm_device *dev,
 			      struct drm_master *master,
 			      struct drm_unique *u);
 
-				/* Legacy Support */
-
-int drm_legacy_addmap(struct drm_device *d, resource_size_t offset,
-		      unsigned int size, enum drm_map_type type,
-		      enum drm_map_flags flags, struct drm_local_map **map_p);
-int drm_legacy_rmmap(struct drm_device *d, struct drm_local_map *map);
-int drm_legacy_rmmap_locked(struct drm_device *d, struct drm_local_map *map);
-struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev);
-
-int drm_legacy_addbufs_agp(struct drm_device *d, struct drm_buf_desc *req);
-int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
-
-void drm_legacy_idlelock_take(struct drm_lock_data *lock);
-void drm_legacy_idlelock_release(struct drm_lock_data *lock);
-
 			       /* sysfs support (drm_sysfs.c) */
 struct drm_sysfs_class;
 extern struct class *drm_sysfs_create(struct module *owner, char *name);
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
new file mode 100644
index 000000000000..605d66081e3f
--- /dev/null
+++ b/include/drm/drm_legacy.h
@@ -0,0 +1,58 @@
+#ifndef __DRM_DRM_LEGACY_H__
+#define __DRM_DRM_LEGACY_H__
+
+/*
+ * Legacy driver interfaces for the Direct Rendering Manager
+ *
+ * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
+ * Copyright (c) 2009-2010, Code Aurora Forum.
+ * All rights reserved.
+ * Copyright © 2014 Intel Corporation
+ *   Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Gareth Hughes <gareth@valinux.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+
+/*
+ * Legacy Support for palateontologic DRM drivers
+ *
+ * If you add a new driver and it uses any of these functions or structures,
+ * you're doing it terribly wrong.
+ */
+
+int drm_legacy_addmap(struct drm_device *d, resource_size_t offset,
+		      unsigned int size, enum drm_map_type type,
+		      enum drm_map_flags flags, struct drm_local_map **map_p);
+int drm_legacy_rmmap(struct drm_device *d, struct drm_local_map *map);
+int drm_legacy_rmmap_locked(struct drm_device *d, struct drm_local_map *map);
+struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev);
+
+int drm_legacy_addbufs_agp(struct drm_device *d, struct drm_buf_desc *req);
+int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
+
+void drm_legacy_idlelock_take(struct drm_lock_data *lock);
+void drm_legacy_idlelock_release(struct drm_lock_data *lock);
+
+#endif /* __DRM_DRM_LEGACY_H__ */
-- 
cgit v1.2.3


From 1c96e84ee486d5dbf4a3850441f3c1f95b1343e4 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:51 +0200
Subject: drm: Move __drm_pci_free to drm_legacy.h

Also sprinkle the customary legacy_ prefix.

Unfortunately we can't move the other functions since i915 is still
using them. Shame on me for that one :(

v2: Fix patch subject as spotted by David Herrmann.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_bufs.c | 2 +-
 drivers/gpu/drm/drm_pci.c  | 4 ++--
 drivers/gpu/drm/drm_vm.c   | 2 +-
 include/drm/drmP.h         | 1 -
 include/drm/drm_legacy.h   | 3 +++
 5 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 70ba89f66199..569064a00693 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -473,7 +473,7 @@ int drm_legacy_rmmap_locked(struct drm_device *dev, struct drm_local_map *map)
 		dmah.vaddr = map->handle;
 		dmah.busaddr = map->offset;
 		dmah.size = map->size;
-		__drm_pci_free(dev, &dmah);
+		__drm_legacy_pci_free(dev, &dmah);
 		break;
 	}
 	kfree(map);
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 7563130c6b70..02ab8c52f311 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -81,7 +81,7 @@ EXPORT_SYMBOL(drm_pci_alloc);
  *
  * This function is for internal use in the Linux-specific DRM core code.
  */
-void __drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
+void __drm_legacy_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 {
 	unsigned long addr;
 	size_t sz;
@@ -105,7 +105,7 @@ void __drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
  */
 void drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 {
-	__drm_pci_free(dev, dmah);
+	__drm_legacy_pci_free(dev, dmah);
 	kfree(dmah);
 }
 
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 4b3e9c4754d1..06cad0323699 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -272,7 +272,7 @@ static void drm_vm_shm_close(struct vm_area_struct *vma)
 				dmah.vaddr = map->handle;
 				dmah.busaddr = map->offset;
 				dmah.size = map->size;
-				__drm_pci_free(dev, &dmah);
+				__drm_legacy_pci_free(dev, &dmah);
 				break;
 			}
 			kfree(map);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index fe6db4cc0db2..90b379cd07ad 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1303,7 +1303,6 @@ extern int drm_vma_info(struct seq_file *m, void *data);
 
 extern drm_dma_handle_t *drm_pci_alloc(struct drm_device *dev, size_t size,
 				       size_t align);
-extern void __drm_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
 extern void drm_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
 extern int drm_pci_set_unique(struct drm_device *dev,
 			      struct drm_master *master,
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
index 605d66081e3f..98626317e48b 100644
--- a/include/drm/drm_legacy.h
+++ b/include/drm/drm_legacy.h
@@ -55,4 +55,7 @@ int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
 void drm_legacy_idlelock_take(struct drm_lock_data *lock);
 void drm_legacy_idlelock_release(struct drm_lock_data *lock);
 
+/* drm_pci.c dma alloc wrappers */
+void __drm_legacy_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
+
 #endif /* __DRM_DRM_LEGACY_H__ */
-- 
cgit v1.2.3


From 7610a04c008768abf8a372d2358e7629877b8305 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:52 +0200
Subject: drm: Drop drm_sysfs_class from drmP.h

No user at all.

My guess is that this is a leftover from ttm before it used
the more abstract helpers to register/unregister its sysfs
objects (see drm_sysfs.h). At least in the existing history
it was never used.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drmP.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 90b379cd07ad..3ca7b14f4f45 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1309,7 +1309,6 @@ extern int drm_pci_set_unique(struct drm_device *dev,
 			      struct drm_unique *u);
 
 			       /* sysfs support (drm_sysfs.c) */
-struct drm_sysfs_class;
 extern struct class *drm_sysfs_create(struct module *owner, char *name);
 extern void drm_sysfs_destroy(void);
 extern struct device *drm_sysfs_minor_alloc(struct drm_minor *minor);
-- 
cgit v1.2.3


From 18882995713d2ebdd24d6b07f1853a866a7e1b66 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 08:16:10 +0200
Subject: drm: Move vblank related module options into drm_irq.c

This allows us to drop 2 header declarations from drmP.h. The 3rd one
is also used in drm_ioctl.c, so for that create a new drm_internal.h
header for non-legacy non-kms (since we have internal headers for
those parts already) declarations private to drm.ko.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_drv.c      | 13 -------------
 drivers/gpu/drm/drm_internal.h | 24 ++++++++++++++++++++++++
 drivers/gpu/drm/drm_ioctl.c    |  1 +
 drivers/gpu/drm/drm_irq.c      | 15 +++++++++++++++
 include/drm/drmP.h             |  4 ----
 5 files changed, 40 insertions(+), 17 deletions(-)
 create mode 100644 drivers/gpu/drm/drm_internal.h

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 970613c5a1eb..175cbbdac8c1 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -39,16 +39,6 @@
 unsigned int drm_debug = 0;	/* 1 to enable debug output */
 EXPORT_SYMBOL(drm_debug);
 
-int drm_vblank_offdelay = 5000;    /* Default to 5000 msecs. */
-
-unsigned int drm_timestamp_precision = 20;  /* Default to 20 usecs. */
-
-/*
- * Default to use monotonic timestamps for wait-for-vblank and page-flip
- * complete events.
- */
-unsigned int drm_timestamp_monotonic = 1;
-
 MODULE_AUTHOR(CORE_AUTHOR);
 MODULE_DESCRIPTION(CORE_DESC);
 MODULE_LICENSE("GPL and additional rights");
@@ -58,9 +48,6 @@ MODULE_PARM_DESC(timestamp_precision_usec, "Max. error on timestamps [usecs]");
 MODULE_PARM_DESC(timestamp_monotonic, "Use monotonic timestamps");
 
 module_param_named(debug, drm_debug, int, 0600);
-module_param_named(vblankoffdelay, drm_vblank_offdelay, int, 0600);
-module_param_named(timestamp_precision_usec, drm_timestamp_precision, int, 0600);
-module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
 
 static DEFINE_SPINLOCK(drm_minor_lock);
 static struct idr drm_minors_idr;
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
new file mode 100644
index 000000000000..5fbf36bcc0b0
--- /dev/null
+++ b/drivers/gpu/drm/drm_internal.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *   Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+extern unsigned int drm_timestamp_monotonic;
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 4c0822973db4..7d6df78bb25d 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -31,6 +31,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_core.h>
 #include "drm_legacy.h"
+#include "drm_internal.h"
 
 #include <linux/pci.h>
 #include <linux/export.h>
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 034297640b48..80ff94ada75e 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -34,6 +34,7 @@
 
 #include <drm/drmP.h>
 #include "drm_trace.h"
+#include "drm_internal.h"
 
 #include <linux/interrupt.h>	/* For task queue support */
 #include <linux/slab.h>
@@ -59,6 +60,20 @@ static bool
 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
 			  struct timeval *tvblank, unsigned flags);
 
+static unsigned int drm_timestamp_precision = 20;  /* Default to 20 usecs. */
+
+/*
+ * Default to use monotonic timestamps for wait-for-vblank and page-flip
+ * complete events.
+ */
+unsigned int drm_timestamp_monotonic = 1;
+
+static int drm_vblank_offdelay = 5000;    /* Default to 5000 msecs. */
+
+module_param_named(vblankoffdelay, drm_vblank_offdelay, int, 0600);
+module_param_named(timestamp_precision_usec, drm_timestamp_precision, int, 0600);
+module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
+
 /**
  * drm_update_vblank_count - update the master vblank counter
  * @dev: DRM device
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 3ca7b14f4f45..90ae120b2c29 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1207,10 +1207,6 @@ extern void drm_put_dev(struct drm_device *dev);
 extern void drm_unplug_dev(struct drm_device *dev);
 extern unsigned int drm_debug;
 
-extern int drm_vblank_offdelay;
-extern unsigned int drm_timestamp_precision;
-extern unsigned int drm_timestamp_monotonic;
-
 extern struct class *drm_class;
 
 				/* Debugfs support */
-- 
cgit v1.2.3


From 67d0ec4e885cd2af861a14bb9bd59fd23e9644ae Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:53 +0200
Subject: drm: Move piles of functions from drmP.h to drm_internal.h

This way drivers can't grow crazy ideas any more, and it also
helps a bit in reviewing EXPORT_SYMBOLS.

v2: Even more stuff. Unfortunately we can't move drm_vm_open_locked
because exynos does some horrible stuff with it.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_auth.c     |  1 +
 drivers/gpu/drm/drm_crtc.c     |  1 +
 drivers/gpu/drm/drm_debugfs.c  |  1 +
 drivers/gpu/drm/drm_drv.c      |  1 +
 drivers/gpu/drm/drm_fops.c     |  1 +
 drivers/gpu/drm/drm_gem.c      |  1 +
 drivers/gpu/drm/drm_internal.h | 68 ++++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/drm_prime.c    |  1 +
 drivers/gpu/drm/drm_sysfs.c    |  1 +
 include/drm/drmP.h             | 55 ----------------------------------
 10 files changed, 76 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index 708a2044c631..fc8e8aaa34fb 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -34,6 +34,7 @@
  */
 
 #include <drm/drmP.h>
+#include "drm_internal.h"
 
 struct drm_magic_entry {
 	struct list_head head;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 7d7c1fd15443..3a1801b8fc2f 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -40,6 +40,7 @@
 #include <drm/drm_modeset_lock.h>
 
 #include "drm_crtc_internal.h"
+#include "drm_internal.h"
 
 static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
 							struct drm_mode_fb_cmd2 *r,
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index 4491dbda653e..3bcf8e6a85b3 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -36,6 +36,7 @@
 #include <linux/export.h>
 #include <drm/drmP.h>
 #include <drm/drm_edid.h>
+#include "drm_internal.h"
 
 #if defined(CONFIG_DEBUG_FS)
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 175cbbdac8c1..fcc9d7d81a02 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -35,6 +35,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_core.h>
 #include "drm_legacy.h"
+#include "drm_internal.h"
 
 unsigned int drm_debug = 0;	/* 1 to enable debug output */
 EXPORT_SYMBOL(drm_debug);
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 3bb6234d072a..51a77a767e66 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -39,6 +39,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include "drm_legacy.h"
+#include "drm_internal.h"
 
 /* from BKL pushdown */
 DEFINE_MUTEX(drm_global_mutex);
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 6adee4c2afc0..55fd65002926 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -38,6 +38,7 @@
 #include <linux/dma-buf.h>
 #include <drm/drmP.h>
 #include <drm/drm_vma_manager.h>
+#include "drm_internal.h"
 
 /** @file drm_gem.c
  *
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 5fbf36bcc0b0..a71cf4b839f2 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -21,4 +21,72 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
+/* drm_irq.c */
 extern unsigned int drm_timestamp_monotonic;
+
+/* drm_fops.c */
+int drm_lastclose(struct drm_device *dev);
+
+/* drm_pci.c */
+int drm_pci_set_unique(struct drm_device *dev,
+		       struct drm_master *master,
+		       struct drm_unique *u);
+int drm_irq_by_busid(struct drm_device *dev, void *data,
+		     struct drm_file *file_priv);
+
+/* drm_vm.c */
+int drm_vma_info(struct seq_file *m, void *data);
+int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma);
+void drm_vm_close_locked(struct drm_device *dev, struct vm_area_struct *vma);
+
+/* drm_prime.c */
+int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);
+int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);
+
+void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
+void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
+void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
+					struct dma_buf *dma_buf);
+
+/* drm_info.c */
+int drm_name_info(struct seq_file *m, void *data);
+int drm_vm_info(struct seq_file *m, void *data);
+int drm_bufs_info(struct seq_file *m, void *data);
+int drm_vblank_info(struct seq_file *m, void *data);
+int drm_clients_info(struct seq_file *m, void* data);
+int drm_gem_name_info(struct seq_file *m, void *data);
+
+/* drm_irq.c */
+int drm_control(struct drm_device *dev, void *data,
+		struct drm_file *file_priv);
+
+/* drm_auth.c */
+int drm_getmagic(struct drm_device *dev, void *data,
+		 struct drm_file *file_priv);
+int drm_authmagic(struct drm_device *dev, void *data,
+		  struct drm_file *file_priv);
+int drm_remove_magic(struct drm_master *master, drm_magic_t magic);
+
+/* drm_sysfs.c */
+struct class *drm_sysfs_create(struct module *owner, char *name);
+void drm_sysfs_destroy(void);
+struct device *drm_sysfs_minor_alloc(struct drm_minor *minor);
+int drm_sysfs_connector_add(struct drm_connector *connector);
+void drm_sysfs_connector_remove(struct drm_connector *connector);
+
+/* drm_gem.c */
+int drm_gem_init(struct drm_device *dev);
+void drm_gem_destroy(struct drm_device *dev);
+int drm_gem_handle_create_tail(struct drm_file *file_priv,
+			       struct drm_gem_object *obj,
+			       u32 *handlep);
+int drm_gem_close_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_gem_flink_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_gem_open_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv);
+void drm_gem_open(struct drm_device *dev, struct drm_file *file_private);
+void drm_gem_release(struct drm_device *dev, struct drm_file *file_private);
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 99d578bad17e..2807a771f505 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -29,6 +29,7 @@
 #include <linux/export.h>
 #include <linux/dma-buf.h>
 #include <drm/drmP.h>
+#include "drm_internal.h"
 
 /*
  * DMA-BUF/GEM Object references and lifetime overview:
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index ab1a5f6dde8a..cc3d6d6d67e0 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -21,6 +21,7 @@
 #include <drm/drm_sysfs.h>
 #include <drm/drm_core.h>
 #include <drm/drmP.h>
+#include "drm_internal.h"
 
 #define to_drm_minor(d) dev_get_drvdata(d)
 #define to_drm_connector(d) dev_get_drvdata(d)
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 90ae120b2c29..52198870bba7 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1084,7 +1084,6 @@ extern long drm_ioctl(struct file *filp,
 		      unsigned int cmd, unsigned long arg);
 extern long drm_compat_ioctl(struct file *filp,
 			     unsigned int cmd, unsigned long arg);
-extern int drm_lastclose(struct drm_device *dev);
 extern bool drm_ioctl_flags(unsigned int nr, unsigned int *flags);
 
 				/* Device support (drm_fops.h) */
@@ -1096,14 +1095,10 @@ extern int drm_release(struct inode *inode, struct file *filp);
 
 				/* Mapping support (drm_vm.h) */
 extern int drm_mmap(struct file *filp, struct vm_area_struct *vma);
-extern int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma);
 extern void drm_vm_open_locked(struct drm_device *dev, struct vm_area_struct *vma);
-extern void drm_vm_close_locked(struct drm_device *dev, struct vm_area_struct *vma);
 extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
 
 				/* Misc. IOCTL support (drm_ioctl.h) */
-extern int drm_irq_by_busid(struct drm_device *dev, void *data,
-			    struct drm_file *file_priv);
 extern int drm_getunique(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 extern int drm_setunique(struct drm_device *dev, void *data,
@@ -1123,13 +1118,6 @@ extern int drm_setversion(struct drm_device *dev, void *data,
 extern int drm_noop(struct drm_device *dev, void *data,
 		    struct drm_file *file_priv);
 
-				/* Authentication IOCTL support (drm_auth.h) */
-extern int drm_getmagic(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_authmagic(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-extern int drm_remove_magic(struct drm_master *master, drm_magic_t magic);
-
 /* Cache management (drm_cache.c) */
 void drm_clflush_pages(struct page *pages[], unsigned long num_pages);
 void drm_clflush_sg(struct sg_table *st);
@@ -1141,8 +1129,6 @@ void drm_clflush_virt_range(void *addr, unsigned long length);
  */
 
 				/* IRQ support (drm_irq.h) */
-extern int drm_control(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
 extern int drm_irq_install(struct drm_device *dev, int irq);
 extern int drm_irq_uninstall(struct drm_device *dev);
 
@@ -1256,15 +1242,6 @@ static inline void drm_debugfs_connector_remove(struct drm_connector *connector)
 
 #endif
 
-				/* Info file support */
-extern int drm_name_info(struct seq_file *m, void *data);
-extern int drm_vm_info(struct seq_file *m, void *data);
-extern int drm_bufs_info(struct seq_file *m, void *data);
-extern int drm_vblank_info(struct seq_file *m, void *data);
-extern int drm_clients_info(struct seq_file *m, void* data);
-extern int drm_gem_name_info(struct seq_file *m, void *data);
-
-
 extern struct dma_buf *drm_gem_prime_export(struct drm_device *dev,
 		struct drm_gem_object *obj, int flags);
 extern int drm_gem_prime_handle_to_fd(struct drm_device *dev,
@@ -1276,11 +1253,6 @@ extern int drm_gem_prime_fd_to_handle(struct drm_device *dev,
 		struct drm_file *file_priv, int prime_fd, uint32_t *handle);
 extern void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
 
-extern int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
-					struct drm_file *file_priv);
-extern int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
-					struct drm_file *file_priv);
-
 extern int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages,
 					    dma_addr_t *addrs, int max_pages);
 extern struct sg_table *drm_prime_pages_to_sg(struct page **pages, int nr_pages);
@@ -1290,31 +1262,15 @@ int drm_gem_dumb_destroy(struct drm_file *file,
 			 struct drm_device *dev,
 			 uint32_t handle);
 
-void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
-void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf);
-
-extern int drm_vma_info(struct seq_file *m, void *data);
-
 
 extern drm_dma_handle_t *drm_pci_alloc(struct drm_device *dev, size_t size,
 				       size_t align);
 extern void drm_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
-extern int drm_pci_set_unique(struct drm_device *dev,
-			      struct drm_master *master,
-			      struct drm_unique *u);
 
 			       /* sysfs support (drm_sysfs.c) */
-extern struct class *drm_sysfs_create(struct module *owner, char *name);
-extern void drm_sysfs_destroy(void);
-extern struct device *drm_sysfs_minor_alloc(struct drm_minor *minor);
 extern void drm_sysfs_hotplug_event(struct drm_device *dev);
-extern int drm_sysfs_connector_add(struct drm_connector *connector);
-extern void drm_sysfs_connector_remove(struct drm_connector *connector);
 
 /* Graphics Execution Manager library functions (drm_gem.c) */
-int drm_gem_init(struct drm_device *dev);
-void drm_gem_destroy(struct drm_device *dev);
 void drm_gem_object_release(struct drm_gem_object *obj);
 void drm_gem_object_free(struct kref *kref);
 int drm_gem_object_init(struct drm_device *dev,
@@ -1353,9 +1309,6 @@ drm_gem_object_unreference_unlocked(struct drm_gem_object *obj)
 	}
 }
 
-int drm_gem_handle_create_tail(struct drm_file *file_priv,
-			       struct drm_gem_object *obj,
-			       u32 *handlep);
 int drm_gem_handle_create(struct drm_file *file_priv,
 			  struct drm_gem_object *obj,
 			  u32 *handlep);
@@ -1373,14 +1326,6 @@ void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages,
 struct drm_gem_object *drm_gem_object_lookup(struct drm_device *dev,
 					     struct drm_file *filp,
 					     u32 handle);
-int drm_gem_close_ioctl(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-int drm_gem_flink_ioctl(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-int drm_gem_open_ioctl(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
-void drm_gem_open(struct drm_device *dev, struct drm_file *file_private);
-void drm_gem_release(struct drm_device *dev, struct drm_file *file_private);
 
 extern void drm_core_ioremap(struct drm_local_map *map, struct drm_device *dev);
 extern void drm_core_ioremap_wc(struct drm_local_map *map, struct drm_device *dev);
-- 
cgit v1.2.3


From 44af3f5c6a2dc0358121b5ecf272361b3290649e Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:54 +0200
Subject: drm: unexport drm_global_mutex

Drivers really, really have no business even looking at this lock. And
thankfully they don't.

So unexport it and move the declaration to drm_internal.h.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_fops.c     | 1 -
 drivers/gpu/drm/drm_internal.h | 1 +
 drivers/gpu/drm/drm_lock.c     | 1 +
 include/drm/drmP.h             | 1 -
 4 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 51a77a767e66..3e6694633f42 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -43,7 +43,6 @@
 
 /* from BKL pushdown */
 DEFINE_MUTEX(drm_global_mutex);
-EXPORT_SYMBOL(drm_global_mutex);
 
 static int drm_open_helper(struct file *filp, struct drm_minor *minor);
 
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index a71cf4b839f2..d6dc75534304 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -25,6 +25,7 @@
 extern unsigned int drm_timestamp_monotonic;
 
 /* drm_fops.c */
+extern struct mutex drm_global_mutex;
 int drm_lastclose(struct drm_device *dev);
 
 /* drm_pci.c */
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index 727b032292b4..f861361a635e 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -36,6 +36,7 @@
 #include <linux/export.h>
 #include <drm/drmP.h>
 #include "drm_legacy.h"
+#include "drm_internal.h"
 
 static int drm_notifier(void *priv);
 
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 52198870bba7..ef675dbaccee 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1087,7 +1087,6 @@ extern long drm_compat_ioctl(struct file *filp,
 extern bool drm_ioctl_flags(unsigned int nr, unsigned int *flags);
 
 				/* Device support (drm_fops.h) */
-extern struct mutex drm_global_mutex;
 extern int drm_open(struct inode *inode, struct file *filp);
 extern ssize_t drm_read(struct file *filp, char __user *buffer,
 			size_t count, loff_t *offset);
-- 
cgit v1.2.3


From 78238757ebab54bf0d546dabe119f3a158d418b4 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:55 +0200
Subject: drm: Purge ioctl forward declarations from drmP.h

If we push down the ioctl table in drm_ioctl.c all the forward
declarations in drmP.h are not required any more.

v2: Fold in fixup from Fenugguang Wu to declare functions as static.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_ioctl.c | 246 ++++++++++++++++++++++----------------------
 include/drm/drmP.h          |  22 +---
 2 files changed, 126 insertions(+), 142 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 7d6df78bb25d..00587a1e3c83 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -42,121 +42,6 @@
 static int drm_version(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
 
-#define DRM_IOCTL_DEF(ioctl, _func, _flags) \
-	[DRM_IOCTL_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0, .name = #ioctl}
-
-/** Ioctl table */
-static const struct drm_ioctl_desc drm_ioctls[] = {
-	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0),
-	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAP, drm_getmap, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_CLIENT, drm_getclient, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_STATS, drm_getstats, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_CAP, drm_getcap, DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_CLIENT_CAP, drm_setclientcap, 0),
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_VERSION, drm_setversion, DRM_MASTER),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_UNIQUE, drm_setunique, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_BLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_UNBLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AUTH_MAGIC, drm_authmagic, DRM_AUTH|DRM_MASTER),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_MAP, drm_legacy_addmap_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_RM_MAP, drm_legacy_rmmap_ioctl, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_SAREA_CTX, drm_legacy_setsareactx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_SAREA_CTX, drm_legacy_getsareactx, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_MASTER, drm_setmaster_ioctl, DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_DROP_MASTER, drm_dropmaster_ioctl, DRM_ROOT_ONLY),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_CTX, drm_legacy_addctx, DRM_AUTH|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_RM_CTX, drm_legacy_rmctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_MOD_CTX, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_CTX, drm_legacy_getctx, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_SWITCH_CTX, drm_legacy_switchctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_NEW_CTX, drm_legacy_newctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_RES_CTX, drm_legacy_resctx, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_RM_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_LOCK, drm_legacy_lock, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_UNLOCK, drm_legacy_unlock, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_FINISH, drm_noop, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_BUFS, drm_legacy_addbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_MARK_BUFS, drm_legacy_markbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_INFO_BUFS, drm_legacy_infobufs, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_MAP_BUFS, drm_legacy_mapbufs, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_FREE_BUFS, drm_legacy_freebufs, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_DMA, drm_legacy_dma_ioctl, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_CONTROL, drm_control, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-
-#if __OS_HAS_AGP
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ACQUIRE, drm_agp_acquire_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_RELEASE, drm_agp_release_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ENABLE, drm_agp_enable_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_INFO, drm_agp_info_ioctl, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ALLOC, drm_agp_alloc_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_FREE, drm_agp_free_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_BIND, drm_agp_bind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_UNBIND, drm_agp_unbind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-#endif
-
-	DRM_IOCTL_DEF(DRM_IOCTL_SG_ALLOC, drm_legacy_sg_alloc, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_SG_FREE, drm_legacy_sg_free, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank, DRM_UNLOCKED),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_MODESET_CTL, drm_modeset_ctl, 0),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_UPDATE_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_GEM_CLOSE, drm_gem_close_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_GEM_FLINK, drm_gem_flink_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH|DRM_UNLOCKED),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETCRTC, drm_mode_setcrtc, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANE, drm_mode_getplane, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPLANE, drm_mode_setplane, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR, drm_mode_cursor_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETGAMMA, drm_mode_gamma_get_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETGAMMA, drm_mode_gamma_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETENCODER, drm_mode_getencoder, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCONNECTOR, drm_mode_getconnector, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB2, drm_mode_addfb2, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_PAGE_FLIP, drm_mode_page_flip_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DIRTYFB, drm_mode_dirtyfb_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_DUMB, drm_mode_create_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_MAP_DUMB, drm_mode_mmap_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROY_DUMB, drm_mode_destroy_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_GETPROPERTIES, drm_mode_obj_get_properties_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_SETPROPERTY, drm_mode_obj_set_property_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR2, drm_mode_cursor2_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-};
-
-#define DRM_CORE_IOCTL_COUNT	ARRAY_SIZE( drm_ioctls )
-
 /**
  * Get the bus id.
  *
@@ -168,7 +53,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
  *
  * Copies the bus id from drm_device::unique into user space.
  */
-int drm_getunique(struct drm_device *dev, void *data,
+static int drm_getunique(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
 	struct drm_unique *u = data;
@@ -207,7 +92,7 @@ drm_unset_busid(struct drm_device *dev,
  * version 1.1 or greater. Also note that KMS is all version 1.1 and later and
  * UMS was only ever supported on pci devices.
  */
-int drm_setunique(struct drm_device *dev, void *data,
+static int drm_setunique(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
 	struct drm_unique *u = data;
@@ -279,7 +164,7 @@ static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv)
  * Searches for the mapping with the specified offset and copies its information
  * into userspace
  */
-int drm_getmap(struct drm_device *dev, void *data,
+static int drm_getmap(struct drm_device *dev, void *data,
 	       struct drm_file *file_priv)
 {
 	struct drm_map *map = data;
@@ -340,7 +225,7 @@ int drm_getmap(struct drm_device *dev, void *data,
  * Searches for the client with the specified index and copies its information
  * into userspace
  */
-int drm_getclient(struct drm_device *dev, void *data,
+static int drm_getclient(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
 	struct drm_client *client = data;
@@ -380,7 +265,7 @@ int drm_getclient(struct drm_device *dev, void *data,
  *
  * \return zero on success or a negative number on failure.
  */
-int drm_getstats(struct drm_device *dev, void *data,
+static int drm_getstats(struct drm_device *dev, void *data,
 		 struct drm_file *file_priv)
 {
 	struct drm_stats *stats = data;
@@ -394,7 +279,7 @@ int drm_getstats(struct drm_device *dev, void *data,
 /**
  * Get device/driver capabilities
  */
-int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
+static int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_get_cap *req = data;
 
@@ -444,7 +329,7 @@ int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 /**
  * Set device/driver capabilities
  */
-int
+static int
 drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_set_client_cap *req = data;
@@ -478,7 +363,7 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
  *
  * Sets the requested interface version
  */
-int drm_setversion(struct drm_device *dev, void *data, struct drm_file *file_priv)
+static int drm_setversion(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_set_version *sv = data;
 	int if_version, retcode = 0;
@@ -624,6 +509,121 @@ static int drm_ioctl_permit(u32 flags, struct drm_file *file_priv)
 	return 0;
 }
 
+#define DRM_IOCTL_DEF(ioctl, _func, _flags) \
+	[DRM_IOCTL_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0, .name = #ioctl}
+
+/** Ioctl table */
+static const struct drm_ioctl_desc drm_ioctls[] = {
+	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0),
+	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAP, drm_getmap, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_CLIENT, drm_getclient, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_STATS, drm_getstats, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_CAP, drm_getcap, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_CLIENT_CAP, drm_setclientcap, 0),
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_VERSION, drm_setversion, DRM_MASTER),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_UNIQUE, drm_setunique, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_BLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_UNBLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AUTH_MAGIC, drm_authmagic, DRM_AUTH|DRM_MASTER),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_MAP, drm_legacy_addmap_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_RM_MAP, drm_legacy_rmmap_ioctl, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_SAREA_CTX, drm_legacy_setsareactx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_SAREA_CTX, drm_legacy_getsareactx, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_MASTER, drm_setmaster_ioctl, DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_DROP_MASTER, drm_dropmaster_ioctl, DRM_ROOT_ONLY),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_CTX, drm_legacy_addctx, DRM_AUTH|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_RM_CTX, drm_legacy_rmctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_MOD_CTX, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_CTX, drm_legacy_getctx, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_SWITCH_CTX, drm_legacy_switchctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_NEW_CTX, drm_legacy_newctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_RES_CTX, drm_legacy_resctx, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_RM_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_LOCK, drm_legacy_lock, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_UNLOCK, drm_legacy_unlock, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_FINISH, drm_noop, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_BUFS, drm_legacy_addbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_MARK_BUFS, drm_legacy_markbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_INFO_BUFS, drm_legacy_infobufs, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_MAP_BUFS, drm_legacy_mapbufs, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_FREE_BUFS, drm_legacy_freebufs, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_DMA, drm_legacy_dma_ioctl, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_CONTROL, drm_control, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+#if __OS_HAS_AGP
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ACQUIRE, drm_agp_acquire_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_RELEASE, drm_agp_release_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ENABLE, drm_agp_enable_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_INFO, drm_agp_info_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ALLOC, drm_agp_alloc_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_FREE, drm_agp_free_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_BIND, drm_agp_bind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_UNBIND, drm_agp_unbind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+#endif
+
+	DRM_IOCTL_DEF(DRM_IOCTL_SG_ALLOC, drm_legacy_sg_alloc, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_SG_FREE, drm_legacy_sg_free, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank, DRM_UNLOCKED),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_MODESET_CTL, drm_modeset_ctl, 0),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_UPDATE_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_CLOSE, drm_gem_close_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_FLINK, drm_gem_flink_ioctl, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH|DRM_UNLOCKED),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETCRTC, drm_mode_setcrtc, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANE, drm_mode_getplane, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPLANE, drm_mode_setplane, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR, drm_mode_cursor_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETGAMMA, drm_mode_gamma_get_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETGAMMA, drm_mode_gamma_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETENCODER, drm_mode_getencoder, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCONNECTOR, drm_mode_getconnector, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB2, drm_mode_addfb2, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_PAGE_FLIP, drm_mode_page_flip_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DIRTYFB, drm_mode_dirtyfb_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_DUMB, drm_mode_create_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_MAP_DUMB, drm_mode_mmap_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROY_DUMB, drm_mode_destroy_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_GETPROPERTIES, drm_mode_obj_get_properties_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_SETPROPERTY, drm_mode_obj_set_property_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR2, drm_mode_cursor2_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+};
+
+#define DRM_CORE_IOCTL_COUNT	ARRAY_SIZE( drm_ioctls )
+
 /**
  * Called whenever a process performs an ioctl on /dev/drm.
  *
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index ef675dbaccee..ac4ca4b59fdf 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1097,25 +1097,9 @@ extern int drm_mmap(struct file *filp, struct vm_area_struct *vma);
 extern void drm_vm_open_locked(struct drm_device *dev, struct vm_area_struct *vma);
 extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
 
-				/* Misc. IOCTL support (drm_ioctl.h) */
-extern int drm_getunique(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-extern int drm_setunique(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-extern int drm_getmap(struct drm_device *dev, void *data,
-		      struct drm_file *file_priv);
-extern int drm_getclient(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-extern int drm_getstats(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_getcap(struct drm_device *dev, void *data,
-		      struct drm_file *file_priv);
-extern int drm_setclientcap(struct drm_device *dev, void *data,
-			    struct drm_file *file_priv);
-extern int drm_setversion(struct drm_device *dev, void *data,
-			  struct drm_file *file_priv);
-extern int drm_noop(struct drm_device *dev, void *data,
-		    struct drm_file *file_priv);
+/* Misc. IOCTL support (drm_ioctl.c) */
+int drm_noop(struct drm_device *dev, void *data,
+	     struct drm_file *file_priv);
 
 /* Cache management (drm_cache.c) */
 void drm_clflush_pages(struct page *pages[], unsigned long num_pages);
-- 
cgit v1.2.3


From 86c1fbd55c6abc72496a45b7cbf1940324983977 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:56 +0200
Subject: drm: Move drm_memory.c map support declarations to <drm/drm_legacy.h>

And replace the drm_core_ prefix with drm_legacy_ since really, this
isn't core stuff.

Also drop drm_core_dropmap since it's unused.

v2: Fix up i810.ko fully which somehow slipped through.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_memory.c        | 12 ++++++------
 drivers/gpu/drm/i810/i810_dma.c     | 12 ++++++------
 drivers/gpu/drm/mga/mga_dma.c       | 28 ++++++++++++++--------------
 drivers/gpu/drm/r128/r128_cce.c     | 22 +++++++++++-----------
 drivers/gpu/drm/radeon/r600_cp.c    | 24 ++++++++++++------------
 drivers/gpu/drm/radeon/radeon_cp.c  | 24 ++++++++++++------------
 drivers/gpu/drm/savage/savage_bci.c | 16 ++++++++--------
 drivers/gpu/drm/via/via_dma.c       |  4 ++--
 drivers/gpu/drm/via/via_map.c       |  4 ++--
 include/drm/drmP.h                  | 18 ------------------
 include/drm/drm_legacy.h            | 15 +++++++++++++++
 11 files changed, 88 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c
index 62fda6aaad90..a521ef6ff807 100644
--- a/drivers/gpu/drm/drm_memory.c
+++ b/drivers/gpu/drm/drm_memory.c
@@ -120,25 +120,25 @@ static inline void *agp_remap(unsigned long offset, unsigned long size,
 
 #endif				/* agp */
 
-void drm_core_ioremap(struct drm_local_map *map, struct drm_device *dev)
+void drm_legacy_ioremap(struct drm_local_map *map, struct drm_device *dev)
 {
 	if (dev->agp && dev->agp->cant_use_aperture && map->type == _DRM_AGP)
 		map->handle = agp_remap(map->offset, map->size, dev);
 	else
 		map->handle = ioremap(map->offset, map->size);
 }
-EXPORT_SYMBOL(drm_core_ioremap);
+EXPORT_SYMBOL(drm_legacy_ioremap);
 
-void drm_core_ioremap_wc(struct drm_local_map *map, struct drm_device *dev)
+void drm_legacy_ioremap_wc(struct drm_local_map *map, struct drm_device *dev)
 {
 	if (dev->agp && dev->agp->cant_use_aperture && map->type == _DRM_AGP)
 		map->handle = agp_remap(map->offset, map->size, dev);
 	else
 		map->handle = ioremap_wc(map->offset, map->size);
 }
-EXPORT_SYMBOL(drm_core_ioremap_wc);
+EXPORT_SYMBOL(drm_legacy_ioremap_wc);
 
-void drm_core_ioremapfree(struct drm_local_map *map, struct drm_device *dev)
+void drm_legacy_ioremapfree(struct drm_local_map *map, struct drm_device *dev)
 {
 	if (!map->handle || !map->size)
 		return;
@@ -148,4 +148,4 @@ void drm_core_ioremapfree(struct drm_local_map *map, struct drm_device *dev)
 	else
 		iounmap(map->handle);
 }
-EXPORT_SYMBOL(drm_core_ioremapfree);
+EXPORT_SYMBOL(drm_legacy_ioremapfree);
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index c97e2ff6a35a..d91856779beb 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -213,7 +213,7 @@ static int i810_dma_cleanup(struct drm_device *dev)
 		    (drm_i810_private_t *) dev->dev_private;
 
 		if (dev_priv->ring.virtual_start)
-			drm_core_ioremapfree(&dev_priv->ring.map, dev);
+			drm_legacy_ioremapfree(&dev_priv->ring.map, dev);
 		if (dev_priv->hw_status_page) {
 			pci_free_consistent(dev->pdev, PAGE_SIZE,
 					    dev_priv->hw_status_page,
@@ -227,7 +227,7 @@ static int i810_dma_cleanup(struct drm_device *dev)
 			drm_i810_buf_priv_t *buf_priv = buf->dev_private;
 
 			if (buf_priv->kernel_virtual && buf->total)
-				drm_core_ioremapfree(&buf_priv->map, dev);
+				drm_legacy_ioremapfree(&buf_priv->map, dev);
 		}
 	}
 	return 0;
@@ -306,7 +306,7 @@ static int i810_freelist_init(struct drm_device *dev, drm_i810_private_t *dev_pr
 		buf_priv->map.flags = 0;
 		buf_priv->map.mtrr = 0;
 
-		drm_core_ioremap(&buf_priv->map, dev);
+		drm_legacy_ioremap(&buf_priv->map, dev);
 		buf_priv->kernel_virtual = buf_priv->map.handle;
 
 	}
@@ -334,7 +334,7 @@ static int i810_dma_initialize(struct drm_device *dev,
 		DRM_ERROR("can not find sarea!\n");
 		return -EINVAL;
 	}
-	dev_priv->mmio_map = drm_core_findmap(dev, init->mmio_offset);
+	dev_priv->mmio_map = drm_legacy_findmap(dev, init->mmio_offset);
 	if (!dev_priv->mmio_map) {
 		dev->dev_private = (void *)dev_priv;
 		i810_dma_cleanup(dev);
@@ -342,7 +342,7 @@ static int i810_dma_initialize(struct drm_device *dev,
 		return -EINVAL;
 	}
 	dev->agp_buffer_token = init->buffers_offset;
-	dev->agp_buffer_map = drm_core_findmap(dev, init->buffers_offset);
+	dev->agp_buffer_map = drm_legacy_findmap(dev, init->buffers_offset);
 	if (!dev->agp_buffer_map) {
 		dev->dev_private = (void *)dev_priv;
 		i810_dma_cleanup(dev);
@@ -363,7 +363,7 @@ static int i810_dma_initialize(struct drm_device *dev,
 	dev_priv->ring.map.flags = 0;
 	dev_priv->ring.map.mtrr = 0;
 
-	drm_core_ioremap(&dev_priv->ring.map, dev);
+	drm_legacy_ioremap(&dev_priv->ring.map, dev);
 
 	if (dev_priv->ring.map.handle == NULL) {
 		dev->dev_private = (void *)dev_priv;
diff --git a/drivers/gpu/drm/mga/mga_dma.c b/drivers/gpu/drm/mga/mga_dma.c
index 37d80c122483..8cfa9cb74c86 100644
--- a/drivers/gpu/drm/mga/mga_dma.c
+++ b/drivers/gpu/drm/mga/mga_dma.c
@@ -566,9 +566,9 @@ static int mga_do_agp_dma_bootstrap(struct drm_device *dev,
 		return err;
 	}
 
-	drm_core_ioremap(dev_priv->warp, dev);
-	drm_core_ioremap(dev_priv->primary, dev);
-	drm_core_ioremap(dev->agp_buffer_map, dev);
+	drm_legacy_ioremap(dev_priv->warp, dev);
+	drm_legacy_ioremap(dev_priv->primary, dev);
+	drm_legacy_ioremap(dev->agp_buffer_map, dev);
 
 	if (!dev_priv->warp->handle ||
 	    !dev_priv->primary->handle || !dev->agp_buffer_map->handle) {
@@ -821,37 +821,37 @@ static int mga_do_init_dma(struct drm_device *dev, drm_mga_init_t *init)
 		dev_priv->dma_access = MGA_PAGPXFER;
 		dev_priv->wagp_enable = MGA_WAGP_ENABLE;
 
-		dev_priv->status = drm_core_findmap(dev, init->status_offset);
+		dev_priv->status = drm_legacy_findmap(dev, init->status_offset);
 		if (!dev_priv->status) {
 			DRM_ERROR("failed to find status page!\n");
 			return -EINVAL;
 		}
-		dev_priv->mmio = drm_core_findmap(dev, init->mmio_offset);
+		dev_priv->mmio = drm_legacy_findmap(dev, init->mmio_offset);
 		if (!dev_priv->mmio) {
 			DRM_ERROR("failed to find mmio region!\n");
 			return -EINVAL;
 		}
-		dev_priv->warp = drm_core_findmap(dev, init->warp_offset);
+		dev_priv->warp = drm_legacy_findmap(dev, init->warp_offset);
 		if (!dev_priv->warp) {
 			DRM_ERROR("failed to find warp microcode region!\n");
 			return -EINVAL;
 		}
-		dev_priv->primary = drm_core_findmap(dev, init->primary_offset);
+		dev_priv->primary = drm_legacy_findmap(dev, init->primary_offset);
 		if (!dev_priv->primary) {
 			DRM_ERROR("failed to find primary dma region!\n");
 			return -EINVAL;
 		}
 		dev->agp_buffer_token = init->buffers_offset;
 		dev->agp_buffer_map =
-		    drm_core_findmap(dev, init->buffers_offset);
+		    drm_legacy_findmap(dev, init->buffers_offset);
 		if (!dev->agp_buffer_map) {
 			DRM_ERROR("failed to find dma buffer region!\n");
 			return -EINVAL;
 		}
 
-		drm_core_ioremap(dev_priv->warp, dev);
-		drm_core_ioremap(dev_priv->primary, dev);
-		drm_core_ioremap(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap(dev_priv->warp, dev);
+		drm_legacy_ioremap(dev_priv->primary, dev);
+		drm_legacy_ioremap(dev->agp_buffer_map, dev);
 	}
 
 	dev_priv->sarea_priv =
@@ -937,14 +937,14 @@ static int mga_do_cleanup_dma(struct drm_device *dev, int full_cleanup)
 
 		if ((dev_priv->warp != NULL)
 		    && (dev_priv->warp->type != _DRM_CONSISTENT))
-			drm_core_ioremapfree(dev_priv->warp, dev);
+			drm_legacy_ioremapfree(dev_priv->warp, dev);
 
 		if ((dev_priv->primary != NULL)
 		    && (dev_priv->primary->type != _DRM_CONSISTENT))
-			drm_core_ioremapfree(dev_priv->primary, dev);
+			drm_legacy_ioremapfree(dev_priv->primary, dev);
 
 		if (dev->agp_buffer_map != NULL)
-			drm_core_ioremapfree(dev->agp_buffer_map, dev);
+			drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 
 		if (dev_priv->used_new_dma_init) {
 #if __OS_HAS_AGP
diff --git a/drivers/gpu/drm/r128/r128_cce.c b/drivers/gpu/drm/r128/r128_cce.c
index 1fae2f706b01..2c45ac9c1dc3 100644
--- a/drivers/gpu/drm/r128/r128_cce.c
+++ b/drivers/gpu/drm/r128/r128_cce.c
@@ -460,21 +460,21 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 		return -EINVAL;
 	}
 
-	dev_priv->mmio = drm_core_findmap(dev, init->mmio_offset);
+	dev_priv->mmio = drm_legacy_findmap(dev, init->mmio_offset);
 	if (!dev_priv->mmio) {
 		DRM_ERROR("could not find mmio region!\n");
 		dev->dev_private = (void *)dev_priv;
 		r128_do_cleanup_cce(dev);
 		return -EINVAL;
 	}
-	dev_priv->cce_ring = drm_core_findmap(dev, init->ring_offset);
+	dev_priv->cce_ring = drm_legacy_findmap(dev, init->ring_offset);
 	if (!dev_priv->cce_ring) {
 		DRM_ERROR("could not find cce ring region!\n");
 		dev->dev_private = (void *)dev_priv;
 		r128_do_cleanup_cce(dev);
 		return -EINVAL;
 	}
-	dev_priv->ring_rptr = drm_core_findmap(dev, init->ring_rptr_offset);
+	dev_priv->ring_rptr = drm_legacy_findmap(dev, init->ring_rptr_offset);
 	if (!dev_priv->ring_rptr) {
 		DRM_ERROR("could not find ring read pointer!\n");
 		dev->dev_private = (void *)dev_priv;
@@ -482,7 +482,7 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 		return -EINVAL;
 	}
 	dev->agp_buffer_token = init->buffers_offset;
-	dev->agp_buffer_map = drm_core_findmap(dev, init->buffers_offset);
+	dev->agp_buffer_map = drm_legacy_findmap(dev, init->buffers_offset);
 	if (!dev->agp_buffer_map) {
 		DRM_ERROR("could not find dma buffer region!\n");
 		dev->dev_private = (void *)dev_priv;
@@ -492,7 +492,7 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 
 	if (!dev_priv->is_pci) {
 		dev_priv->agp_textures =
-		    drm_core_findmap(dev, init->agp_textures_offset);
+		    drm_legacy_findmap(dev, init->agp_textures_offset);
 		if (!dev_priv->agp_textures) {
 			DRM_ERROR("could not find agp texture region!\n");
 			dev->dev_private = (void *)dev_priv;
@@ -507,9 +507,9 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 
 #if __OS_HAS_AGP
 	if (!dev_priv->is_pci) {
-		drm_core_ioremap_wc(dev_priv->cce_ring, dev);
-		drm_core_ioremap_wc(dev_priv->ring_rptr, dev);
-		drm_core_ioremap_wc(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap_wc(dev_priv->cce_ring, dev);
+		drm_legacy_ioremap_wc(dev_priv->ring_rptr, dev);
+		drm_legacy_ioremap_wc(dev->agp_buffer_map, dev);
 		if (!dev_priv->cce_ring->handle ||
 		    !dev_priv->ring_rptr->handle ||
 		    !dev->agp_buffer_map->handle) {
@@ -603,11 +603,11 @@ int r128_do_cleanup_cce(struct drm_device *dev)
 #if __OS_HAS_AGP
 		if (!dev_priv->is_pci) {
 			if (dev_priv->cce_ring != NULL)
-				drm_core_ioremapfree(dev_priv->cce_ring, dev);
+				drm_legacy_ioremapfree(dev_priv->cce_ring, dev);
 			if (dev_priv->ring_rptr != NULL)
-				drm_core_ioremapfree(dev_priv->ring_rptr, dev);
+				drm_legacy_ioremapfree(dev_priv->ring_rptr, dev);
 			if (dev->agp_buffer_map != NULL) {
-				drm_core_ioremapfree(dev->agp_buffer_map, dev);
+				drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 				dev->agp_buffer_map = NULL;
 			}
 		} else
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index 639d6681ef5b..09e3f39925fa 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -1949,15 +1949,15 @@ int r600_do_cleanup_cp(struct drm_device *dev)
 #if __OS_HAS_AGP
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		if (dev_priv->cp_ring != NULL) {
-			drm_core_ioremapfree(dev_priv->cp_ring, dev);
+			drm_legacy_ioremapfree(dev_priv->cp_ring, dev);
 			dev_priv->cp_ring = NULL;
 		}
 		if (dev_priv->ring_rptr != NULL) {
-			drm_core_ioremapfree(dev_priv->ring_rptr, dev);
+			drm_legacy_ioremapfree(dev_priv->ring_rptr, dev);
 			dev_priv->ring_rptr = NULL;
 		}
 		if (dev->agp_buffer_map != NULL) {
-			drm_core_ioremapfree(dev->agp_buffer_map, dev);
+			drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 			dev->agp_buffer_map = NULL;
 		}
 	} else
@@ -1968,7 +1968,7 @@ int r600_do_cleanup_cp(struct drm_device *dev)
 			r600_page_table_cleanup(dev, &dev_priv->gart_info);
 
 		if (dev_priv->gart_info.gart_table_location == DRM_ATI_GART_FB) {
-			drm_core_ioremapfree(&dev_priv->gart_info.mapping, dev);
+			drm_legacy_ioremapfree(&dev_priv->gart_info.mapping, dev);
 			dev_priv->gart_info.addr = NULL;
 		}
 	}
@@ -2059,20 +2059,20 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 		return -EINVAL;
 	}
 
-	dev_priv->cp_ring = drm_core_findmap(dev, init->ring_offset);
+	dev_priv->cp_ring = drm_legacy_findmap(dev, init->ring_offset);
 	if (!dev_priv->cp_ring) {
 		DRM_ERROR("could not find cp ring region!\n");
 		r600_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
-	dev_priv->ring_rptr = drm_core_findmap(dev, init->ring_rptr_offset);
+	dev_priv->ring_rptr = drm_legacy_findmap(dev, init->ring_rptr_offset);
 	if (!dev_priv->ring_rptr) {
 		DRM_ERROR("could not find ring read pointer!\n");
 		r600_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
 	dev->agp_buffer_token = init->buffers_offset;
-	dev->agp_buffer_map = drm_core_findmap(dev, init->buffers_offset);
+	dev->agp_buffer_map = drm_legacy_findmap(dev, init->buffers_offset);
 	if (!dev->agp_buffer_map) {
 		DRM_ERROR("could not find dma buffer region!\n");
 		r600_do_cleanup_cp(dev);
@@ -2081,7 +2081,7 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 
 	if (init->gart_textures_offset) {
 		dev_priv->gart_textures =
-		    drm_core_findmap(dev, init->gart_textures_offset);
+		    drm_legacy_findmap(dev, init->gart_textures_offset);
 		if (!dev_priv->gart_textures) {
 			DRM_ERROR("could not find GART texture region!\n");
 			r600_do_cleanup_cp(dev);
@@ -2092,9 +2092,9 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 #if __OS_HAS_AGP
 	/* XXX */
 	if (dev_priv->flags & RADEON_IS_AGP) {
-		drm_core_ioremap_wc(dev_priv->cp_ring, dev);
-		drm_core_ioremap_wc(dev_priv->ring_rptr, dev);
-		drm_core_ioremap_wc(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap_wc(dev_priv->cp_ring, dev);
+		drm_legacy_ioremap_wc(dev_priv->ring_rptr, dev);
+		drm_legacy_ioremap_wc(dev->agp_buffer_map, dev);
 		if (!dev_priv->cp_ring->handle ||
 		    !dev_priv->ring_rptr->handle ||
 		    !dev->agp_buffer_map->handle) {
@@ -2235,7 +2235,7 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 		dev_priv->gart_info.mapping.size =
 			dev_priv->gart_info.table_size;
 
-		drm_core_ioremap_wc(&dev_priv->gart_info.mapping, dev);
+		drm_legacy_ioremap_wc(&dev_priv->gart_info.mapping, dev);
 		if (!dev_priv->gart_info.mapping.handle) {
 			DRM_ERROR("ioremap failed.\n");
 			r600_do_cleanup_cp(dev);
diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index 0c388016eecb..ea134a7d51a5 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -1305,20 +1305,20 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 		return -EINVAL;
 	}
 
-	dev_priv->cp_ring = drm_core_findmap(dev, init->ring_offset);
+	dev_priv->cp_ring = drm_legacy_findmap(dev, init->ring_offset);
 	if (!dev_priv->cp_ring) {
 		DRM_ERROR("could not find cp ring region!\n");
 		radeon_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
-	dev_priv->ring_rptr = drm_core_findmap(dev, init->ring_rptr_offset);
+	dev_priv->ring_rptr = drm_legacy_findmap(dev, init->ring_rptr_offset);
 	if (!dev_priv->ring_rptr) {
 		DRM_ERROR("could not find ring read pointer!\n");
 		radeon_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
 	dev->agp_buffer_token = init->buffers_offset;
-	dev->agp_buffer_map = drm_core_findmap(dev, init->buffers_offset);
+	dev->agp_buffer_map = drm_legacy_findmap(dev, init->buffers_offset);
 	if (!dev->agp_buffer_map) {
 		DRM_ERROR("could not find dma buffer region!\n");
 		radeon_do_cleanup_cp(dev);
@@ -1327,7 +1327,7 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 
 	if (init->gart_textures_offset) {
 		dev_priv->gart_textures =
-		    drm_core_findmap(dev, init->gart_textures_offset);
+		    drm_legacy_findmap(dev, init->gart_textures_offset);
 		if (!dev_priv->gart_textures) {
 			DRM_ERROR("could not find GART texture region!\n");
 			radeon_do_cleanup_cp(dev);
@@ -1337,9 +1337,9 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 
 #if __OS_HAS_AGP
 	if (dev_priv->flags & RADEON_IS_AGP) {
-		drm_core_ioremap_wc(dev_priv->cp_ring, dev);
-		drm_core_ioremap_wc(dev_priv->ring_rptr, dev);
-		drm_core_ioremap_wc(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap_wc(dev_priv->cp_ring, dev);
+		drm_legacy_ioremap_wc(dev_priv->ring_rptr, dev);
+		drm_legacy_ioremap_wc(dev->agp_buffer_map, dev);
 		if (!dev_priv->cp_ring->handle ||
 		    !dev_priv->ring_rptr->handle ||
 		    !dev->agp_buffer_map->handle) {
@@ -1475,7 +1475,7 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 			dev_priv->gart_info.mapping.size =
 			    dev_priv->gart_info.table_size;
 
-			drm_core_ioremap_wc(&dev_priv->gart_info.mapping, dev);
+			drm_legacy_ioremap_wc(&dev_priv->gart_info.mapping, dev);
 			dev_priv->gart_info.addr =
 			    dev_priv->gart_info.mapping.handle;
 
@@ -1569,15 +1569,15 @@ static int radeon_do_cleanup_cp(struct drm_device * dev)
 #if __OS_HAS_AGP
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		if (dev_priv->cp_ring != NULL) {
-			drm_core_ioremapfree(dev_priv->cp_ring, dev);
+			drm_legacy_ioremapfree(dev_priv->cp_ring, dev);
 			dev_priv->cp_ring = NULL;
 		}
 		if (dev_priv->ring_rptr != NULL) {
-			drm_core_ioremapfree(dev_priv->ring_rptr, dev);
+			drm_legacy_ioremapfree(dev_priv->ring_rptr, dev);
 			dev_priv->ring_rptr = NULL;
 		}
 		if (dev->agp_buffer_map != NULL) {
-			drm_core_ioremapfree(dev->agp_buffer_map, dev);
+			drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 			dev->agp_buffer_map = NULL;
 		}
 	} else
@@ -1597,7 +1597,7 @@ static int radeon_do_cleanup_cp(struct drm_device * dev)
 
 		if (dev_priv->gart_info.gart_table_location == DRM_ATI_GART_FB)
 		{
-			drm_core_ioremapfree(&dev_priv->gart_info.mapping, dev);
+			drm_legacy_ioremapfree(&dev_priv->gart_info.mapping, dev);
 			dev_priv->gart_info.addr = NULL;
 		}
 	}
diff --git a/drivers/gpu/drm/savage/savage_bci.c b/drivers/gpu/drm/savage/savage_bci.c
index 9288d3037ce5..d47dff95fe52 100644
--- a/drivers/gpu/drm/savage/savage_bci.c
+++ b/drivers/gpu/drm/savage/savage_bci.c
@@ -706,7 +706,7 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 		return -EINVAL;
 	}
 	if (init->status_offset != 0) {
-		dev_priv->status = drm_core_findmap(dev, init->status_offset);
+		dev_priv->status = drm_legacy_findmap(dev, init->status_offset);
 		if (!dev_priv->status) {
 			DRM_ERROR("could not find shadow status region!\n");
 			savage_do_cleanup_bci(dev);
@@ -717,14 +717,14 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 	}
 	if (dev_priv->dma_type == SAVAGE_DMA_AGP && init->buffers_offset) {
 		dev->agp_buffer_token = init->buffers_offset;
-		dev->agp_buffer_map = drm_core_findmap(dev,
+		dev->agp_buffer_map = drm_legacy_findmap(dev,
 						       init->buffers_offset);
 		if (!dev->agp_buffer_map) {
 			DRM_ERROR("could not find DMA buffer region!\n");
 			savage_do_cleanup_bci(dev);
 			return -EINVAL;
 		}
-		drm_core_ioremap(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap(dev->agp_buffer_map, dev);
 		if (!dev->agp_buffer_map->handle) {
 			DRM_ERROR("failed to ioremap DMA buffer region!\n");
 			savage_do_cleanup_bci(dev);
@@ -733,7 +733,7 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 	}
 	if (init->agp_textures_offset) {
 		dev_priv->agp_textures =
-		    drm_core_findmap(dev, init->agp_textures_offset);
+		    drm_legacy_findmap(dev, init->agp_textures_offset);
 		if (!dev_priv->agp_textures) {
 			DRM_ERROR("could not find agp texture region!\n");
 			savage_do_cleanup_bci(dev);
@@ -756,7 +756,7 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 			savage_do_cleanup_bci(dev);
 			return -EINVAL;
 		}
-		dev_priv->cmd_dma = drm_core_findmap(dev, init->cmd_dma_offset);
+		dev_priv->cmd_dma = drm_legacy_findmap(dev, init->cmd_dma_offset);
 		if (!dev_priv->cmd_dma) {
 			DRM_ERROR("could not find command DMA region!\n");
 			savage_do_cleanup_bci(dev);
@@ -769,7 +769,7 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 				savage_do_cleanup_bci(dev);
 				return -EINVAL;
 			}
-			drm_core_ioremap(dev_priv->cmd_dma, dev);
+			drm_legacy_ioremap(dev_priv->cmd_dma, dev);
 			if (!dev_priv->cmd_dma->handle) {
 				DRM_ERROR("failed to ioremap command "
 					  "DMA region!\n");
@@ -895,11 +895,11 @@ static int savage_do_cleanup_bci(struct drm_device * dev)
 	} else if (dev_priv->cmd_dma && dev_priv->cmd_dma->handle &&
 		   dev_priv->cmd_dma->type == _DRM_AGP &&
 		   dev_priv->dma_type == SAVAGE_DMA_AGP)
-		drm_core_ioremapfree(dev_priv->cmd_dma, dev);
+		drm_legacy_ioremapfree(dev_priv->cmd_dma, dev);
 
 	if (dev_priv->dma_type == SAVAGE_DMA_AGP &&
 	    dev->agp_buffer_map && dev->agp_buffer_map->handle) {
-		drm_core_ioremapfree(dev->agp_buffer_map, dev);
+		drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 		/* make sure the next instance (which may be running
 		 * in PCI mode) doesn't try to use an old
 		 * agp_buffer_map. */
diff --git a/drivers/gpu/drm/via/via_dma.c b/drivers/gpu/drm/via/via_dma.c
index 6fc0648dd37f..d17d8f245c1a 100644
--- a/drivers/gpu/drm/via/via_dma.c
+++ b/drivers/gpu/drm/via/via_dma.c
@@ -161,7 +161,7 @@ int via_dma_cleanup(struct drm_device *dev)
 		if (dev_priv->ring.virtual_start) {
 			via_cmdbuf_reset(dev_priv);
 
-			drm_core_ioremapfree(&dev_priv->ring.map, dev);
+			drm_legacy_ioremapfree(&dev_priv->ring.map, dev);
 			dev_priv->ring.virtual_start = NULL;
 		}
 
@@ -200,7 +200,7 @@ static int via_initialize(struct drm_device *dev,
 	dev_priv->ring.map.flags = 0;
 	dev_priv->ring.map.mtrr = 0;
 
-	drm_core_ioremap(&dev_priv->ring.map, dev);
+	drm_legacy_ioremap(&dev_priv->ring.map, dev);
 
 	if (dev_priv->ring.map.handle == NULL) {
 		via_dma_cleanup(dev);
diff --git a/drivers/gpu/drm/via/via_map.c b/drivers/gpu/drm/via/via_map.c
index 67e70e955504..0b3522dba6e8 100644
--- a/drivers/gpu/drm/via/via_map.c
+++ b/drivers/gpu/drm/via/via_map.c
@@ -39,14 +39,14 @@ static int via_do_init_map(struct drm_device *dev, drm_via_init_t *init)
 		return -EINVAL;
 	}
 
-	dev_priv->fb = drm_core_findmap(dev, init->fb_offset);
+	dev_priv->fb = drm_legacy_findmap(dev, init->fb_offset);
 	if (!dev_priv->fb) {
 		DRM_ERROR("could not find framebuffer!\n");
 		dev->dev_private = (void *)dev_priv;
 		via_do_cleanup_map(dev);
 		return -EINVAL;
 	}
-	dev_priv->mmio = drm_core_findmap(dev, init->mmio_offset);
+	dev_priv->mmio = drm_legacy_findmap(dev, init->mmio_offset);
 	if (!dev_priv->mmio) {
 		DRM_ERROR("could not find mmio region!\n");
 		dev->dev_private = (void *)dev_priv;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index ac4ca4b59fdf..4a72db4b4329 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1310,24 +1310,6 @@ struct drm_gem_object *drm_gem_object_lookup(struct drm_device *dev,
 					     struct drm_file *filp,
 					     u32 handle);
 
-extern void drm_core_ioremap(struct drm_local_map *map, struct drm_device *dev);
-extern void drm_core_ioremap_wc(struct drm_local_map *map, struct drm_device *dev);
-extern void drm_core_ioremapfree(struct drm_local_map *map, struct drm_device *dev);
-
-static __inline__ struct drm_local_map *drm_core_findmap(struct drm_device *dev,
-							 unsigned int token)
-{
-	struct drm_map_list *_entry;
-	list_for_each_entry(_entry, &dev->maplist, head)
-	    if (_entry->user_token == token)
-		return _entry->map;
-	return NULL;
-}
-
-static __inline__ void drm_core_dropmap(struct drm_local_map *map)
-{
-}
-
 struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 				 struct device *parent);
 void drm_dev_ref(struct drm_device *dev);
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
index 98626317e48b..cc6e528069a8 100644
--- a/include/drm/drm_legacy.h
+++ b/include/drm/drm_legacy.h
@@ -58,4 +58,19 @@ void drm_legacy_idlelock_release(struct drm_lock_data *lock);
 /* drm_pci.c dma alloc wrappers */
 void __drm_legacy_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
 
+/* drm_memory.c */
+void drm_legacy_ioremap(struct drm_local_map *map, struct drm_device *dev);
+void drm_legacy_ioremap_wc(struct drm_local_map *map, struct drm_device *dev);
+void drm_legacy_ioremapfree(struct drm_local_map *map, struct drm_device *dev);
+
+static __inline__ struct drm_local_map *drm_legacy_findmap(struct drm_device *dev,
+							   unsigned int token)
+{
+	struct drm_map_list *_entry;
+	list_for_each_entry(_entry, &dev->maplist, head)
+	    if (_entry->user_token == token)
+		return _entry->map;
+	return NULL;
+}
+
 #endif /* __DRM_DRM_LEGACY_H__ */
-- 
cgit v1.2.3


From ba8286fab52652e431784d066b075c1bb4933ea1 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 11 Sep 2014 07:43:25 +0200
Subject: drm: Move legacy buffer structures to <drm/drm_legacy.h>

A few odd cases:
- mgag200 someho had a totally unused drm_dma_handle_t. Remove it.
- i915 still uses the legacy pci dma alloc api, so grows an include.

Everything else fairly standard.

v2: Include "drm_legacy.h" in drm.ko source files for consistency.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dma.c             |   1 +
 drivers/gpu/drm/drm_info.c            |   1 +
 drivers/gpu/drm/drm_pci.c             |   1 +
 drivers/gpu/drm/i915/i915_drv.h       |   9 ++-
 drivers/gpu/drm/mgag200/mgag200_drv.h |   2 -
 drivers/gpu/drm/via/via_verifier.c    |   1 +
 include/drm/ati_pcigart.h             |   2 +
 include/drm/drmP.h                    | 119 ++--------------------------------
 include/drm/drm_legacy.h              | 109 +++++++++++++++++++++++++++++++
 9 files changed, 127 insertions(+), 118 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dma.c b/drivers/gpu/drm/drm_dma.c
index 1b1dd356a1e4..ea481800ef56 100644
--- a/drivers/gpu/drm/drm_dma.c
+++ b/drivers/gpu/drm/drm_dma.c
@@ -35,6 +35,7 @@
 
 #include <linux/export.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 /**
  * Initialize the DMA data.
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index 3c99f6f60818..7a8e5a9d8f54 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -35,6 +35,7 @@
 
 #include <linux/seq_file.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 /**
  * Called when "/proc/dri/.../name" is read.
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 02ab8c52f311..fd29f03645b8 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -27,6 +27,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/export.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 /**
  * drm_pci_alloc - Allocate a PCI consistent memory block, for DMA.
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index bcf8783dbc2e..ec33fe58ed22 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -41,6 +41,7 @@
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 #include <drm/intel-gtt.h>
+#include <drm/drm_legacy.h> /* for struct drm_dma_handle */
 #include <linux/backlight.h>
 #include <linux/hashtable.h>
 #include <linux/intel-iommu.h>
@@ -285,8 +286,10 @@ struct intel_opregion {
 struct intel_overlay;
 struct intel_overlay_error_state;
 
+struct drm_local_map;
+
 struct drm_i915_master_private {
-	drm_local_map_t *sarea;
+	struct drm_local_map *sarea;
 	struct _drm_i915_sarea *sarea_priv;
 };
 #define I915_FENCE_REG_NONE -1
@@ -1447,7 +1450,7 @@ struct drm_i915_private {
 	struct drm_i915_gem_object *semaphore_obj;
 	uint32_t last_seqno, next_seqno;
 
-	drm_dma_handle_t *status_page_dmah;
+	struct drm_dma_handle *status_page_dmah;
 	struct resource mch_res;
 
 	/* protects the irq masks */
@@ -1834,7 +1837,7 @@ struct drm_i915_gem_object {
 	struct drm_file *pin_filp;
 
 	/** for phy allocated objects */
-	drm_dma_handle_t *phys_handle;
+	struct drm_dma_handle *phys_handle;
 
 	union {
 		struct i915_gem_userptr {
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 2e2b76aa4e17..c03e347f3ffd 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -190,8 +190,6 @@ struct mga_device {
 	resource_size_t			rmmio_size;
 	void __iomem			*rmmio;
 
-	drm_local_map_t			*framebuffer;
-
 	struct mga_mc			mc;
 	struct mga_mode_info		mode_info;
 
diff --git a/drivers/gpu/drm/via/via_verifier.c b/drivers/gpu/drm/via/via_verifier.c
index 9dbc92bd1512..0677bbf4ec7e 100644
--- a/drivers/gpu/drm/via/via_verifier.c
+++ b/drivers/gpu/drm/via/via_verifier.c
@@ -31,6 +31,7 @@
 #include "via_3d_reg.h"
 #include <drm/drmP.h>
 #include <drm/via_drm.h>
+#include <drm/drm_legacy.h>
 #include "via_verifier.h"
 #include "via_drv.h"
 
diff --git a/include/drm/ati_pcigart.h b/include/drm/ati_pcigart.h
index da4bfcd81a37..5765648b5ef7 100644
--- a/include/drm/ati_pcigart.h
+++ b/include/drm/ati_pcigart.h
@@ -1,6 +1,8 @@
 #ifndef DRM_ATI_PCIGART_H
 #define DRM_ATI_PCIGART_H
 
+#include <drm/drm_legacy.h>
+
 /* location of GART table */
 #define DRM_ATI_GART_MAIN 1
 #define DRM_ATI_GART_FB   2
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 4a72db4b4329..0d68ecdb447a 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -79,6 +79,9 @@ struct module;
 struct drm_file;
 struct drm_device;
 struct drm_agp_head;
+struct drm_local_map;
+struct drm_device_dma;
+struct drm_dma_handle;
 
 struct device_node;
 struct videomode;
@@ -275,57 +278,6 @@ struct drm_ioctl_desc {
 #define DRM_IOCTL_DEF_DRV(ioctl, _func, _flags)			\
 	[DRM_IOCTL_NR(DRM_##ioctl)] = {.cmd = DRM_##ioctl, .func = _func, .flags = _flags, .cmd_drv = DRM_IOCTL_##ioctl, .name = #ioctl}
 
-/**
- * DMA buffer.
- */
-struct drm_buf {
-	int idx;		       /**< Index into master buflist */
-	int total;		       /**< Buffer size */
-	int order;		       /**< log-base-2(total) */
-	int used;		       /**< Amount of buffer in use (for DMA) */
-	unsigned long offset;	       /**< Byte offset (used internally) */
-	void *address;		       /**< Address of buffer */
-	unsigned long bus_address;     /**< Bus address of buffer */
-	struct drm_buf *next;	       /**< Kernel-only: used for free list */
-	__volatile__ int waiting;      /**< On kernel DMA queue */
-	__volatile__ int pending;      /**< On hardware DMA queue */
-	struct drm_file *file_priv;    /**< Private of holding file descr */
-	int context;		       /**< Kernel queue for this buffer */
-	int while_locked;	       /**< Dispatch this buffer while locked */
-	enum {
-		DRM_LIST_NONE = 0,
-		DRM_LIST_FREE = 1,
-		DRM_LIST_WAIT = 2,
-		DRM_LIST_PEND = 3,
-		DRM_LIST_PRIO = 4,
-		DRM_LIST_RECLAIM = 5
-	} list;			       /**< Which list we're on */
-
-	int dev_priv_size;		 /**< Size of buffer private storage */
-	void *dev_private;		 /**< Per-buffer private storage */
-};
-
-typedef struct drm_dma_handle {
-	dma_addr_t busaddr;
-	void *vaddr;
-	size_t size;
-} drm_dma_handle_t;
-
-/**
- * Buffer entry.  There is one of this for each buffer size order.
- */
-struct drm_buf_entry {
-	int buf_size;			/**< size */
-	int buf_count;			/**< number of buffers */
-	struct drm_buf *buflist;		/**< buffer list */
-	int seg_count;
-	int page_order;
-	struct drm_dma_handle **seglist;
-
-	int low_mark;			/**< Low water mark */
-	int high_mark;			/**< High water mark */
-};
-
 /* Event queued up for userspace to read */
 struct drm_pending_event {
 	struct drm_event *event;
@@ -403,65 +355,6 @@ struct drm_lock_data {
 	int idle_has_lock;
 };
 
-/**
- * DMA data.
- */
-struct drm_device_dma {
-
-	struct drm_buf_entry bufs[DRM_MAX_ORDER + 1];	/**< buffers, grouped by their size order */
-	int buf_count;			/**< total number of buffers */
-	struct drm_buf **buflist;		/**< Vector of pointers into drm_device_dma::bufs */
-	int seg_count;
-	int page_count;			/**< number of pages */
-	unsigned long *pagelist;	/**< page list */
-	unsigned long byte_count;
-	enum {
-		_DRM_DMA_USE_AGP = 0x01,
-		_DRM_DMA_USE_SG = 0x02,
-		_DRM_DMA_USE_FB = 0x04,
-		_DRM_DMA_USE_PCI_RO = 0x08
-	} flags;
-
-};
-
-/**
- * Scatter-gather memory.
- */
-struct drm_sg_mem {
-	unsigned long handle;
-	void *virtual;
-	int pages;
-	struct page **pagelist;
-	dma_addr_t *busaddr;
-};
-
-/**
- * Kernel side of a mapping
- */
-struct drm_local_map {
-	resource_size_t offset;	 /**< Requested physical address (0 for SAREA)*/
-	unsigned long size;	 /**< Requested physical size (bytes) */
-	enum drm_map_type type;	 /**< Type of memory to map */
-	enum drm_map_flags flags;	 /**< Flags */
-	void *handle;		 /**< User-space: "Handle" to pass to mmap() */
-				 /**< Kernel-space: kernel-virtual address */
-	int mtrr;		 /**< MTRR slot used */
-};
-
-typedef struct drm_local_map drm_local_map_t;
-
-/**
- * Mappings list
- */
-struct drm_map_list {
-	struct list_head head;		/**< list head */
-	struct drm_hash_item hash;
-	struct drm_local_map *map;	/**< mapping */
-	uint64_t user_token;
-	struct drm_master *master;
-};
-
-
 /**
  * This structure defines the drm_mm memory object, which will be used by the
  * DRM for its buffer objects.
@@ -1246,9 +1139,9 @@ int drm_gem_dumb_destroy(struct drm_file *file,
 			 uint32_t handle);
 
 
-extern drm_dma_handle_t *drm_pci_alloc(struct drm_device *dev, size_t size,
-				       size_t align);
-extern void drm_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
+extern struct drm_dma_handle *drm_pci_alloc(struct drm_device *dev, size_t size,
+					    size_t align);
+extern void drm_pci_free(struct drm_device *dev, struct drm_dma_handle * dmah);
 
 			       /* sysfs support (drm_sysfs.c) */
 extern void drm_sysfs_hotplug_event(struct drm_device *dev);
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
index cc6e528069a8..a0fabf7624ea 100644
--- a/include/drm/drm_legacy.h
+++ b/include/drm/drm_legacy.h
@@ -42,6 +42,115 @@
  * you're doing it terribly wrong.
  */
 
+/**
+ * DMA buffer.
+ */
+struct drm_buf {
+	int idx;		       /**< Index into master buflist */
+	int total;		       /**< Buffer size */
+	int order;		       /**< log-base-2(total) */
+	int used;		       /**< Amount of buffer in use (for DMA) */
+	unsigned long offset;	       /**< Byte offset (used internally) */
+	void *address;		       /**< Address of buffer */
+	unsigned long bus_address;     /**< Bus address of buffer */
+	struct drm_buf *next;	       /**< Kernel-only: used for free list */
+	__volatile__ int waiting;      /**< On kernel DMA queue */
+	__volatile__ int pending;      /**< On hardware DMA queue */
+	struct drm_file *file_priv;    /**< Private of holding file descr */
+	int context;		       /**< Kernel queue for this buffer */
+	int while_locked;	       /**< Dispatch this buffer while locked */
+	enum {
+		DRM_LIST_NONE = 0,
+		DRM_LIST_FREE = 1,
+		DRM_LIST_WAIT = 2,
+		DRM_LIST_PEND = 3,
+		DRM_LIST_PRIO = 4,
+		DRM_LIST_RECLAIM = 5
+	} list;			       /**< Which list we're on */
+
+	int dev_priv_size;		 /**< Size of buffer private storage */
+	void *dev_private;		 /**< Per-buffer private storage */
+};
+
+typedef struct drm_dma_handle {
+	dma_addr_t busaddr;
+	void *vaddr;
+	size_t size;
+} drm_dma_handle_t;
+
+/**
+ * Buffer entry.  There is one of this for each buffer size order.
+ */
+struct drm_buf_entry {
+	int buf_size;			/**< size */
+	int buf_count;			/**< number of buffers */
+	struct drm_buf *buflist;		/**< buffer list */
+	int seg_count;
+	int page_order;
+	struct drm_dma_handle **seglist;
+
+	int low_mark;			/**< Low water mark */
+	int high_mark;			/**< High water mark */
+};
+
+/**
+ * DMA data.
+ */
+struct drm_device_dma {
+
+	struct drm_buf_entry bufs[DRM_MAX_ORDER + 1];	/**< buffers, grouped by their size order */
+	int buf_count;			/**< total number of buffers */
+	struct drm_buf **buflist;		/**< Vector of pointers into drm_device_dma::bufs */
+	int seg_count;
+	int page_count;			/**< number of pages */
+	unsigned long *pagelist;	/**< page list */
+	unsigned long byte_count;
+	enum {
+		_DRM_DMA_USE_AGP = 0x01,
+		_DRM_DMA_USE_SG = 0x02,
+		_DRM_DMA_USE_FB = 0x04,
+		_DRM_DMA_USE_PCI_RO = 0x08
+	} flags;
+
+};
+
+/**
+ * Scatter-gather memory.
+ */
+struct drm_sg_mem {
+	unsigned long handle;
+	void *virtual;
+	int pages;
+	struct page **pagelist;
+	dma_addr_t *busaddr;
+};
+
+/**
+ * Kernel side of a mapping
+ */
+struct drm_local_map {
+	resource_size_t offset;	 /**< Requested physical address (0 for SAREA)*/
+	unsigned long size;	 /**< Requested physical size (bytes) */
+	enum drm_map_type type;	 /**< Type of memory to map */
+	enum drm_map_flags flags;	 /**< Flags */
+	void *handle;		 /**< User-space: "Handle" to pass to mmap() */
+				 /**< Kernel-space: kernel-virtual address */
+	int mtrr;		 /**< MTRR slot used */
+};
+
+typedef struct drm_local_map drm_local_map_t;
+
+/**
+ * Mappings list
+ */
+struct drm_map_list {
+	struct list_head head;		/**< list head */
+	struct drm_hash_item hash;
+	struct drm_local_map *map;	/**< mapping */
+	uint64_t user_token;
+	struct drm_master *master;
+};
+
 int drm_legacy_addmap(struct drm_device *d, resource_size_t offset,
 		      unsigned int size, enum drm_map_type type,
 		      enum drm_map_flags flags, struct drm_local_map **map_p);
-- 
cgit v1.2.3


From 8f1a2c8dc0dc5c2842e08f304ebdd34b5ddb982c Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:58 +0200
Subject: drm: Move LOCK_TEST_WITH_RETURN to <drm/drm_legacy.h>

Unfortunately we can't move struct drm_lock_data easily since
it's embedded into struct drm_master. And figuring out where exactly
this struct should be allocated isn't that simple ...

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drmP.h       | 17 -----------------
 include/drm/drm_legacy.h | 17 +++++++++++++++++
 2 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 0d68ecdb447a..0308214a6f83 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -221,23 +221,6 @@ int drm_err(const char *func, const char *format, ...);
 
 #define DRM_IF_VERSION(maj, min) (maj << 16 | min)
 
-/**
- * Test that the hardware lock is held by the caller, returning otherwise.
- *
- * \param dev DRM device.
- * \param filp file pointer of the caller.
- */
-#define LOCK_TEST_WITH_RETURN( dev, _file_priv )				\
-do {										\
-	if (!_DRM_LOCK_IS_HELD(_file_priv->master->lock.hw_lock->lock) ||	\
-	    _file_priv->master->lock.file_priv != _file_priv)	{		\
-		DRM_ERROR( "%s called without lock held, held  %d owner %p %p\n",\
-			   __func__, _DRM_LOCK_IS_HELD(_file_priv->master->lock.hw_lock->lock),\
-			   _file_priv->master->lock.file_priv, _file_priv);	\
-		return -EINVAL;							\
-	}									\
-} while (0)
-
 /**
  * Ioctl function type.
  *
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
index a0fabf7624ea..6486306beb0d 100644
--- a/include/drm/drm_legacy.h
+++ b/include/drm/drm_legacy.h
@@ -161,6 +161,23 @@ struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev);
 int drm_legacy_addbufs_agp(struct drm_device *d, struct drm_buf_desc *req);
 int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
 
+/**
+ * Test that the hardware lock is held by the caller, returning otherwise.
+ *
+ * \param dev DRM device.
+ * \param filp file pointer of the caller.
+ */
+#define LOCK_TEST_WITH_RETURN( dev, _file_priv )				\
+do {										\
+	if (!_DRM_LOCK_IS_HELD(_file_priv->master->lock.hw_lock->lock) ||	\
+	    _file_priv->master->lock.file_priv != _file_priv)	{		\
+		DRM_ERROR( "%s called without lock held, held  %d owner %p %p\n",\
+			   __func__, _DRM_LOCK_IS_HELD(_file_priv->master->lock.hw_lock->lock),\
+			   _file_priv->master->lock.file_priv, _file_priv);	\
+		return -EINVAL;							\
+	}									\
+} while (0)
+
 void drm_legacy_idlelock_take(struct drm_lock_data *lock);
 void drm_legacy_idlelock_release(struct drm_lock_data *lock);
 
-- 
cgit v1.2.3


From 00285be8ff2c07379d4809ed2750f8244f0c23fa Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:43:59 +0200
Subject: drm: Move drm_class to drm_internal.h

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_internal.h | 2 ++
 include/drm/drmP.h             | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index d6dc75534304..7e459bf38c26 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -71,6 +71,8 @@ int drm_authmagic(struct drm_device *dev, void *data,
 int drm_remove_magic(struct drm_master *master, drm_magic_t magic);
 
 /* drm_sysfs.c */
+extern struct class *drm_class;
+
 struct class *drm_sysfs_create(struct module *owner, char *name);
 void drm_sysfs_destroy(void);
 struct device *drm_sysfs_minor_alloc(struct drm_minor *minor);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 0308214a6f83..b603cb42e347 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1052,8 +1052,6 @@ extern void drm_put_dev(struct drm_device *dev);
 extern void drm_unplug_dev(struct drm_device *dev);
 extern unsigned int drm_debug;
 
-extern struct class *drm_class;
-
 				/* Debugfs support */
 #if defined(CONFIG_DEBUG_FS)
 extern int drm_debugfs_init(struct drm_minor *minor, int minor_id,
-- 
cgit v1.2.3


From 6865b20ad354548a045c74a388eb37afe1ad5174 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 10 Sep 2014 12:44:00 +0200
Subject: drm: Move DRM_MAGIC_HASH_ORDER into drm_drv.c

Only used in one place ever, so put it right next to that.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_drv.c | 2 ++
 include/drm/drmP.h        | 8 --------
 2 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index fcc9d7d81a02..6a119026a76b 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -90,6 +90,8 @@ void drm_ut_debug_printk(const char *function_name, const char *format, ...)
 }
 EXPORT_SYMBOL(drm_ut_debug_printk);
 
+#define DRM_MAGIC_HASH_ORDER  4  /**< Size of key hash table. Must be power of 2. */
+
 struct drm_master *drm_master_create(struct drm_minor *minor)
 {
 	struct drm_master *master;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index b603cb42e347..5c60d384b37b 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -142,14 +142,6 @@ int drm_err(const char *func, const char *format, ...);
 #define DRIVER_PRIME       0x4000
 #define DRIVER_RENDER      0x8000
 
-/***********************************************************************/
-/** \name Begin the DRM... */
-/*@{*/
-
-#define DRM_MAGIC_HASH_ORDER  4  /**< Size of key hash table. Must be power of 2. */
-
-/*@}*/
-
 /***********************************************************************/
 /** \name Macros to make printk easier */
 /*@{*/
-- 
cgit v1.2.3


From 974a70bdecea5296db1b643e4046ef208e99c592 Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@freescale.com>
Date: Fri, 12 Sep 2014 09:32:41 +0800
Subject: usb: gadget: udc-core: add utility for bus reset

The udc driver can notify the udc core that bus reset occurs by
calling this utility, the core will notify gadget driver this
information and update gadget state accordingly.

Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/gadget/udc/udc-core.c | 17 +++++++++++++++++
 include/linux/usb/gadget.h        |  6 ++++++
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index b0d98172bc07..ba661c6da54a 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -123,6 +123,23 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state);
 
 /* ------------------------------------------------------------------------- */
 
+/**
+ * usb_gadget_udc_reset - notifies the udc core that bus reset occurs
+ * @gadget: The gadget which bus reset occurs
+ * @driver: The gadget driver we want to notify
+ *
+ * If the udc driver has bus reset handler, it needs to call this when the bus
+ * reset occurs, it notifies the gadget driver that the bus reset occurs as
+ * well as updates gadget state.
+ */
+void usb_gadget_udc_reset(struct usb_gadget *gadget,
+		struct usb_gadget_driver *driver)
+{
+	driver->reset(gadget);
+	usb_gadget_set_state(gadget, USB_STATE_DEFAULT);
+}
+EXPORT_SYMBOL_GPL(usb_gadget_udc_reset);
+
 /**
  * usb_gadget_udc_start - tells usb device controller to start up
  * @gadget: The gadget we want to get started
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 598a6e9b2850..d18811433324 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -1017,6 +1017,12 @@ extern void usb_gadget_set_state(struct usb_gadget *gadget,
 
 /*-------------------------------------------------------------------------*/
 
+/* utility to tell udc core that the bus reset occurs */
+extern void usb_gadget_udc_reset(struct usb_gadget *gadget,
+		struct usb_gadget_driver *driver);
+
+/*-------------------------------------------------------------------------*/
+
 /* utility wrapping a simple endpoint selection policy */
 
 extern struct usb_ep *usb_ep_autoconfig(struct usb_gadget *,
-- 
cgit v1.2.3


From f3a808817fdb48a9fa3e4ed40e7f8a8dec50014c Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 16 Aug 2014 14:15:34 -0700
Subject: drm: fix drm_modeset_lock.h kernel-doc notation

Fix drm kernel-doc notation to squelch these warnings:

Warning(..//include/drm/drm_modeset_lock.h:41): cannot understand function prototype: 'struct drm_modeset_acquire_ctx '
Warning(..//include/drm/drm_modeset_lock.h:66): cannot understand function prototype: 'struct drm_modeset_lock '

Need to include the keyword 'struct' for structure descriptions.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_modeset_lock.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h
index a3f736d24382..75a5c45e21c7 100644
--- a/include/drm/drm_modeset_lock.h
+++ b/include/drm/drm_modeset_lock.h
@@ -29,7 +29,7 @@
 struct drm_modeset_lock;
 
 /**
- * drm_modeset_acquire_ctx - locking context (see ww_acquire_ctx)
+ * struct drm_modeset_acquire_ctx - locking context (see ww_acquire_ctx)
  * @ww_ctx: base acquire ctx
  * @contended: used internally for -EDEADLK handling
  * @locked: list of held locks
@@ -61,7 +61,7 @@ struct drm_modeset_acquire_ctx {
 };
 
 /**
- * drm_modeset_lock - used for locking modeset resources.
+ * struct drm_modeset_lock - used for locking modeset resources.
  * @mutex: resource locking
  * @head: used to hold it's place on state->locked list when
  *    part of an atomic update
-- 
cgit v1.2.3


From d4b18c3e00b8d18fbd316abe9639b91ad416e1f3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 10 Sep 2014 17:36:31 -0700
Subject: pnfs: remove GETDEVICELIST implementation

The current GETDEVICELIST implementation is buggy in that it doesn't handle
cursors correctly, and in that it returns an error if the server returns
NFSERR_NOTSUPP.  Given that there is no actual need for GETDEVICELIST,
it has various issues and might get removed for NFSv4.2 stop using it in
the blocklayout driver, and thus the Linux NFS client as whole.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/blocklayout/blocklayout.c |   2 +-
 fs/nfs/nfs4proc.c                |  48 ---------------
 fs/nfs/nfs4xdr.c                 | 130 ---------------------------------------
 fs/nfs/pnfs.h                    |   5 --
 fs/nfs/pnfs_dev.c                |  30 ---------
 include/linux/nfs_xdr.h          |  11 ----
 6 files changed, 1 insertion(+), 225 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 25ba9e0e6fff..3e1f1afc6db4 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -532,7 +532,7 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
 		return -EINVAL;
 	}
 
-	return nfs4_deviceid_getdevicelist(server, fh);
+	return 0;
 }
 
 static bool
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 47fa67a3a8cf..0b711227cfa5 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7808,54 +7808,6 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
 	return status;
 }
 
-/*
- * Retrieve the list of Data Server devices from the MDS.
- */
-static int _nfs4_getdevicelist(struct nfs_server *server,
-				    const struct nfs_fh *fh,
-				    struct pnfs_devicelist *devlist)
-{
-	struct nfs4_getdevicelist_args args = {
-		.fh = fh,
-		.layoutclass = server->pnfs_curr_ld->id,
-	};
-	struct nfs4_getdevicelist_res res = {
-		.devlist = devlist,
-	};
-	struct rpc_message msg = {
-		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICELIST],
-		.rpc_argp = &args,
-		.rpc_resp = &res,
-	};
-	int status;
-
-	dprintk("--> %s\n", __func__);
-	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args,
-				&res.seq_res, 0);
-	dprintk("<-- %s status=%d\n", __func__, status);
-	return status;
-}
-
-int nfs4_proc_getdevicelist(struct nfs_server *server,
-			    const struct nfs_fh *fh,
-			    struct pnfs_devicelist *devlist)
-{
-	struct nfs4_exception exception = { };
-	int err;
-
-	do {
-		err = nfs4_handle_exception(server,
-				_nfs4_getdevicelist(server, fh, devlist),
-				&exception);
-	} while (exception.retry);
-
-	dprintk("%s: err=%d, num_devs=%u\n", __func__,
-		err, devlist->num_devs);
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(nfs4_proc_getdevicelist);
-
 static int
 _nfs4_proc_getdeviceinfo(struct nfs_server *server,
 		struct pnfs_device *pdev,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index f2cd957adb90..b8165eab0a32 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -362,17 +362,6 @@ static int nfs4_stat_to_errno(int);
 				XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5)
 #define encode_reclaim_complete_maxsz	(op_encode_hdr_maxsz + 4)
 #define decode_reclaim_complete_maxsz	(op_decode_hdr_maxsz + 4)
-#define encode_getdevicelist_maxsz (op_encode_hdr_maxsz + 4 + \
-				encode_verifier_maxsz)
-#define decode_getdevicelist_maxsz (op_decode_hdr_maxsz + \
-				2 /* nfs_cookie4 gdlr_cookie */ + \
-				decode_verifier_maxsz \
-				  /* verifier4 gdlr_verifier */ + \
-				1 /* gdlr_deviceid_list count */ + \
-				XDR_QUADLEN(NFS4_PNFS_GETDEVLIST_MAXNUM * \
-					    NFS4_DEVICEID4_SIZE) \
-				  /* gdlr_deviceid_list */ + \
-				1 /* bool gdlr_eof */)
 #define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \
 				XDR_QUADLEN(NFS4_DEVICEID4_SIZE))
 #define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \
@@ -812,14 +801,6 @@ static int nfs4_stat_to_errno(int);
 #define NFS4_dec_reclaim_complete_sz	(compound_decode_hdr_maxsz + \
 					 decode_sequence_maxsz + \
 					 decode_reclaim_complete_maxsz)
-#define NFS4_enc_getdevicelist_sz (compound_encode_hdr_maxsz + \
-				encode_sequence_maxsz + \
-				encode_putfh_maxsz + \
-				encode_getdevicelist_maxsz)
-#define NFS4_dec_getdevicelist_sz (compound_decode_hdr_maxsz + \
-				decode_sequence_maxsz + \
-				decode_putfh_maxsz + \
-				decode_getdevicelist_maxsz)
 #define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz +    \
 				encode_sequence_maxsz +\
 				encode_getdeviceinfo_maxsz)
@@ -1929,24 +1910,6 @@ static void encode_sequence(struct xdr_stream *xdr,
 }
 
 #ifdef CONFIG_NFS_V4_1
-static void
-encode_getdevicelist(struct xdr_stream *xdr,
-		     const struct nfs4_getdevicelist_args *args,
-		     struct compound_hdr *hdr)
-{
-	__be32 *p;
-	nfs4_verifier dummy = {
-		.data = "dummmmmy",
-	};
-
-	encode_op_hdr(xdr, OP_GETDEVICELIST, decode_getdevicelist_maxsz, hdr);
-	p = reserve_space(xdr, 16);
-	*p++ = cpu_to_be32(args->layoutclass);
-	*p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM);
-	xdr_encode_hyper(p, 0ULL);                          /* cookie */
-	encode_nfs4_verifier(xdr, &dummy);
-}
-
 static void
 encode_getdeviceinfo(struct xdr_stream *xdr,
 		     const struct nfs4_getdeviceinfo_args *args,
@@ -2900,24 +2863,6 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
-/*
- * Encode GETDEVICELIST request
- */
-static void nfs4_xdr_enc_getdevicelist(struct rpc_rqst *req,
-				       struct xdr_stream *xdr,
-				       struct nfs4_getdevicelist_args *args)
-{
-	struct compound_hdr hdr = {
-		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
-	};
-
-	encode_compound_hdr(xdr, req, &hdr);
-	encode_sequence(xdr, &args->seq_args, &hdr);
-	encode_putfh(xdr, args->fh, &hdr);
-	encode_getdevicelist(xdr, args, &hdr);
-	encode_nops(&hdr);
-}
-
 /*
  * Encode GETDEVICEINFO request
  */
@@ -5773,54 +5718,6 @@ out_overflow:
 }
 
 #if defined(CONFIG_NFS_V4_1)
-/*
- * TODO: Need to handle case when EOF != true;
- */
-static int decode_getdevicelist(struct xdr_stream *xdr,
-				struct pnfs_devicelist *res)
-{
-	__be32 *p;
-	int status, i;
-	nfs4_verifier verftemp;
-
-	status = decode_op_hdr(xdr, OP_GETDEVICELIST);
-	if (status)
-		return status;
-
-	p = xdr_inline_decode(xdr, 8 + 8 + 4);
-	if (unlikely(!p))
-		goto out_overflow;
-
-	/* TODO: Skip cookie for now */
-	p += 2;
-
-	/* Read verifier */
-	p = xdr_decode_opaque_fixed(p, verftemp.data, NFS4_VERIFIER_SIZE);
-
-	res->num_devs = be32_to_cpup(p);
-
-	dprintk("%s: num_dev %d\n", __func__, res->num_devs);
-
-	if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) {
-		printk(KERN_ERR "NFS: %s too many result dev_num %u\n",
-				__func__, res->num_devs);
-		return -EIO;
-	}
-
-	p = xdr_inline_decode(xdr,
-			      res->num_devs * NFS4_DEVICEID4_SIZE + 4);
-	if (unlikely(!p))
-		goto out_overflow;
-	for (i = 0; i < res->num_devs; i++)
-		p = xdr_decode_opaque_fixed(p, res->dev_id[i].data,
-					    NFS4_DEVICEID4_SIZE);
-	res->eof = be32_to_cpup(p);
-	return 0;
-out_overflow:
-	print_overflow_msg(__func__, xdr);
-	return -EIO;
-}
-
 static int decode_getdeviceinfo(struct xdr_stream *xdr,
 				struct pnfs_device *pdev)
 {
@@ -7104,32 +7001,6 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp,
 	return status;
 }
 
-/*
- * Decode GETDEVICELIST response
- */
-static int nfs4_xdr_dec_getdevicelist(struct rpc_rqst *rqstp,
-				      struct xdr_stream *xdr,
-				      struct nfs4_getdevicelist_res *res)
-{
-	struct compound_hdr hdr;
-	int status;
-
-	dprintk("encoding getdevicelist!\n");
-
-	status = decode_compound_hdr(xdr, &hdr);
-	if (status != 0)
-		goto out;
-	status = decode_sequence(xdr, &res->seq_res, rqstp);
-	if (status != 0)
-		goto out;
-	status = decode_putfh(xdr);
-	if (status != 0)
-		goto out;
-	status = decode_getdevicelist(xdr, res->devlist);
-out:
-	return status;
-}
-
 /*
  * Decode GETDEVINFO response
  */
@@ -7498,7 +7369,6 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
 	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
 	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
-	PROC(GETDEVICELIST,	enc_getdevicelist,	dec_getdevicelist),
 	PROC(BIND_CONN_TO_SESSION,
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
 	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index d84fe29fc88b..b10f12fc6818 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -180,9 +180,6 @@ extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
 extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
 
 /* nfs4proc.c */
-extern int nfs4_proc_getdevicelist(struct nfs_server *server,
-				   const struct nfs_fh *fh,
-				   struct pnfs_devicelist *devlist);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev,
 				   struct rpc_cred *cred);
@@ -277,8 +274,6 @@ bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
 void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
 bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
-int nfs4_deviceid_getdevicelist(struct nfs_server *server,
-		const struct nfs_fh *fh);
 
 static inline struct nfs4_deviceid_node *
 nfs4_get_deviceid(struct nfs4_deviceid_node *d)
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index 82c2836fdb38..aa2ec0015183 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -358,33 +358,3 @@ nfs4_deviceid_mark_client_invalid(struct nfs_client *clp)
 	}
 	rcu_read_unlock();
 }
-
-int
-nfs4_deviceid_getdevicelist(struct nfs_server *server,
-		const struct nfs_fh *fh)
-{
-	struct pnfs_devicelist *dlist;
-	struct nfs4_deviceid_node *d;
-	int error = 0, i;
-
-	dlist = kzalloc(sizeof(struct pnfs_devicelist), GFP_NOFS);
-	if (!dlist)
-		return -ENOMEM;
-
-	while (!dlist->eof) {
-		error = nfs4_proc_getdevicelist(server, fh, dlist);
-		if (error)
-			break;
-
-		for (i = 0; i < dlist->num_devs; i++) {
-			d = nfs4_find_get_deviceid(server, &dlist->dev_id[i],
-					NULL, GFP_NOFS);
-			if (d)
-				nfs4_put_deviceid_node(d);
-		}
-	}
-
-	kfree(dlist);
-	return error;
-}
-EXPORT_SYMBOL_GPL(nfs4_deviceid_getdevicelist);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index f4092c6b90fb..7ae249ccb78d 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -252,17 +252,6 @@ struct nfs4_layoutget {
 	gfp_t gfp_flags;
 };
 
-struct nfs4_getdevicelist_args {
-	struct nfs4_sequence_args seq_args;
-	const struct nfs_fh *fh;
-	u32 layoutclass;
-};
-
-struct nfs4_getdevicelist_res {
-	struct nfs4_sequence_res seq_res;
-	struct pnfs_devicelist *devlist;
-};
-
 struct nfs4_getdeviceinfo_args {
 	struct nfs4_sequence_args seq_args;
 	struct pnfs_device *pdev;
-- 
cgit v1.2.3


From f418c64b71590bac8fdebd0969a1eeaffaf036d2 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Wed, 3 Sep 2014 12:19:07 -0400
Subject: NFS: Unconditionally enable commit code

The goal is to create a generic NFS module with code that does not
depend on what versions of NFS are enabled.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/direct.c        | 14 ------------
 fs/nfs/write.c         | 61 --------------------------------------------------
 include/linux/nfs_fs.h |  8 -------
 3 files changed, 83 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 65ef6e00deee..dda4b8667c02 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -178,7 +178,6 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
 	return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
 }
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 /*
  * nfs_direct_cmp_commit_data_verf - compare verifier for commit data
  * @dreq - direct request possibly spanning multiple servers
@@ -197,7 +196,6 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
 	WARN_ON_ONCE(verfp->committed < 0);
 	return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
 }
-#endif
 
 /**
  * nfs_direct_IO - NFS address space operation for direct I/O
@@ -576,7 +574,6 @@ out:
 	return result;
 }
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
 	struct nfs_pageio_descriptor desc;
@@ -700,17 +697,6 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
 	schedule_work(&dreq->work); /* Calls nfs_direct_write_schedule_work */
 }
 
-#else
-static void nfs_direct_write_schedule_work(struct work_struct *work)
-{
-}
-
-static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
-{
-	nfs_direct_complete(dreq, true);
-}
-#endif
-
 static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_direct_req *dreq = hdr->dreq;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 128d97f01d1c..6786873a2901 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -720,7 +720,6 @@ nfs_mark_request_dirty(struct nfs_page *req)
 	__set_page_dirty_nobuffers(req->wb_page);
 }
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 /*
  * nfs_page_search_commits_for_head_request_locked
  *
@@ -870,43 +869,6 @@ int nfs_write_need_commit(struct nfs_pgio_header *hdr)
 	return hdr->verf.committed != NFS_FILE_SYNC;
 }
 
-#else
-static struct nfs_page *
-nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
-						struct page *page)
-{
-	return NULL;
-}
-
-static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
-				      struct inode *inode)
-{
-}
-
-void nfs_init_cinfo(struct nfs_commit_info *cinfo,
-		    struct inode *inode,
-		    struct nfs_direct_req *dreq)
-{
-}
-
-void
-nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			struct nfs_commit_info *cinfo)
-{
-}
-
-static void
-nfs_clear_request_commit(struct nfs_page *req)
-{
-}
-
-int nfs_write_need_commit(struct nfs_pgio_header *hdr)
-{
-	return 0;
-}
-
-#endif
-
 static void nfs_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_commit_info cinfo;
@@ -942,7 +904,6 @@ out:
 	hdr->release(hdr);
 }
 
-#if  IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 unsigned long
 nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
 {
@@ -999,19 +960,6 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst,
 	return ret;
 }
 
-#else
-unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
-{
-	return 0;
-}
-
-int nfs_scan_commit(struct inode *inode, struct list_head *dst,
-		    struct nfs_commit_info *cinfo)
-{
-	return 0;
-}
-#endif
-
 /*
  * Search for an existing write request, and attempt to update
  * it to reflect a new dirty region on a given page.
@@ -1404,7 +1352,6 @@ static int nfs_writeback_done(struct rpc_task *task,
 		return status;
 	nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count);
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 	if (hdr->res.verf->committed < hdr->args.stable &&
 	    task->tk_status >= 0) {
 		/* We tried a write call, but the server did not
@@ -1426,7 +1373,6 @@ static int nfs_writeback_done(struct rpc_task *task,
 			complain = jiffies + 300 * HZ;
 		}
 	}
-#endif
 
 	/* Deal with the suid/sgid bit corner case */
 	if (nfs_should_remove_suid(inode))
@@ -1479,7 +1425,6 @@ static void nfs_writeback_result(struct rpc_task *task,
 }
 
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
 {
 	int ret;
@@ -1803,12 +1748,6 @@ out_mark_dirty:
 	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 	return ret;
 }
-#else
-static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_control *wbc)
-{
-	return 0;
-}
-#endif
 
 int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 5180a7ededec..fd334d4b0d41 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -529,17 +529,9 @@ extern int  nfs_updatepage(struct file *, struct page *, unsigned int, unsigned
 extern int nfs_wb_all(struct inode *inode);
 extern int nfs_wb_page(struct inode *inode, struct page* page);
 extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 extern int  nfs_commit_inode(struct inode *, int);
 extern struct nfs_commit_data *nfs_commitdata_alloc(void);
 extern void nfs_commit_free(struct nfs_commit_data *data);
-#else
-static inline int
-nfs_commit_inode(struct inode *inode, int how)
-{
-	return 0;
-}
-#endif
 
 static inline int
 nfs_have_writebacks(struct inode *inode)
-- 
cgit v1.2.3


From cb8c20fa53ec28602793ee43ddc7e8883be62e69 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Wed, 3 Sep 2014 12:19:10 -0400
Subject: NFS: Move NFS v3 acl functions to nfs3_fs.h

This code is internal to the v3 module, so other parts of the client
shouldn't have any knowledge of it.

nfs3_getxattr(), nfs3_setxattr(), and nfs3_removexattr() no longer exist
anywhere so I remove the declarations while I'm here.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/nfs3_fs.h       | 19 +++++++++++++++++++
 fs/nfs/nfs3super.c     |  1 +
 include/linux/nfs_fs.h | 33 ---------------------------------
 3 files changed, 20 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h
index 6599e0dcd69f..333ae4068506 100644
--- a/fs/nfs/nfs3_fs.h
+++ b/fs/nfs/nfs3_fs.h
@@ -6,6 +6,25 @@
 #ifndef __LINUX_FS_NFS_NFS3_FS_H
 #define __LINUX_FS_NFS_NFS3_FS_H
 
+/*
+ * nfs3acl.c
+ */
+#ifdef CONFIG_NFS_V3_ACL
+extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type);
+extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+		struct posix_acl *dfacl);
+extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t);
+extern const struct xattr_handler *nfs3_xattr_handlers[];
+#else
+static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+		struct posix_acl *dfacl)
+{
+	return 0;
+}
+#define nfs3_listxattr NULL
+#endif /* CONFIG_NFS_V3_ACL */
+
 /* nfs3client.c */
 struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *);
 struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c
index d6a98949af19..6af29c2da352 100644
--- a/fs/nfs/nfs3super.c
+++ b/fs/nfs/nfs3super.c
@@ -4,6 +4,7 @@
 #include <linux/module.h>
 #include <linux/nfs_fs.h>
 #include "internal.h"
+#include "nfs3_fs.h"
 #include "nfs.h"
 
 static struct nfs_subversion nfs_v3 = {
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index fd334d4b0d41..28d649054d5f 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -442,22 +442,6 @@ static inline struct rpc_cred *nfs_file_cred(struct file *file)
 	return NULL;
 }
 
-/*
- * linux/fs/nfs/xattr.c
- */
-#ifdef CONFIG_NFS_V3_ACL
-extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t);
-extern ssize_t nfs3_getxattr(struct dentry *, const char *, void *, size_t);
-extern int nfs3_setxattr(struct dentry *, const char *,
-			const void *, size_t, int);
-extern int nfs3_removexattr (struct dentry *, const char *name);
-#else
-# define nfs3_listxattr NULL
-# define nfs3_getxattr NULL
-# define nfs3_setxattr NULL
-# define nfs3_removexattr NULL
-#endif
-
 /*
  * linux/fs/nfs/direct.c
  */
@@ -548,23 +532,6 @@ extern int  nfs_readpages(struct file *, struct address_space *,
 extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
 			       struct page *);
 
-/*
- * linux/fs/nfs3proc.c
- */
-#ifdef CONFIG_NFS_V3_ACL
-extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type);
-extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
-		struct posix_acl *dfacl);
-extern const struct xattr_handler *nfs3_xattr_handlers[];
-#else
-static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
-		struct posix_acl *dfacl)
-{
-	return 0;
-}
-#endif /* CONFIG_NFS_V3_ACL */
-
 /*
  * inline functions
  */
-- 
cgit v1.2.3


From e09c2c295468476a239d13324ce9042ec4de05eb Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 13 Sep 2014 04:14:30 +0900
Subject: workqueue: apply __WQ_ORDERED to create_singlethread_workqueue()

create_singlethread_workqueue() is a compat interface for single
threaded workqueue which maps to ordered workqueue w/ rescuer in the
current implementation.  create_singlethread_workqueue() currently
implemented by invoking alloc_workqueue() w/ appropriate parameters.

8719dceae2f9 ("workqueue: reject adjusting max_active or applying
attrs to ordered workqueues") introduced __WQ_ORDERED to protect
ordered workqueues against dynamic attribute changes which can break
ordering guarantees but forgot to apply it to
create_singlethread_workqueue().  This in itself is okay as nobody
currently uses dynamic attribute change on workqueues created with
create_singlethread_workqueue().

However, 4c16bd327c ("workqueue: implement NUMA affinity for unbound
workqueues") broke singlethreaded guarantee for ordered workqueues
through allocating a separate pool_workqueue on each NUMA node by
default.  A later change 8a2b75384444 ("workqueue: fix ordered
workqueues in NUMA setups") fixed it by allocating only one global
pool_workqueue if __WQ_ORDERED is set.

Combined, the __WQ_ORDERED omission in create_singlethread_workqueue()
became critical breaking its single threadedness and ordering
guarantee.

Let's make create_singlethread_workqueue() wrap
alloc_ordered_workqueue() instead so that it inherits __WQ_ORDERED and
can implicitly track future ordered_workqueue changes.

v2: I missed that __WQ_ORDERED now protects against pwq splitting
    across NUMA nodes and incorrectly described the patch as a
    nice-to-have fix to protect against future dynamic attribute
    usages.  Oleg pointed out that this is actually a critical
    breakage due to 8a2b75384444 ("workqueue: fix ordered workqueues
    in NUMA setups").

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Mike Anderson <mike.anderson@us.ibm.com>
Cc: Oleg Nesterov <onestero@redhat.com>
Cc: Gustavo Luiz Duarte <gduarte@redhat.com>
Cc: Tomas Henzl <thenzl@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 4c16bd327c ("workqueue: implement NUMA affinity for unbound workqueues")
---
 include/linux/workqueue.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index a0cc2e95ed1b..b996e6cde6bb 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -419,7 +419,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 	alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
 			1, (name))
 #define create_singlethread_workqueue(name)				\
-	alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, (name))
+	alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
-- 
cgit v1.2.3


From d78c9300c51d6ceed9f6d078d4e9366f259de28c Mon Sep 17 00:00:00 2001
From: Andrew Hunter <ahh@google.com>
Date: Thu, 4 Sep 2014 14:17:16 -0700
Subject: jiffies: Fix timeval conversion to jiffies

timeval_to_jiffies tried to round a timeval up to an integral number
of jiffies, but the logic for doing so was incorrect: intervals
corresponding to exactly N jiffies would become N+1. This manifested
itself particularly repeatedly stopping/starting an itimer:

setitimer(ITIMER_PROF, &val, NULL);
setitimer(ITIMER_PROF, NULL, &val);

would add a full tick to val, _even if it was exactly representable in
terms of jiffies_ (say, the result of a previous rounding.)  Doing
this repeatedly would cause unbounded growth in val.  So fix the math.

Here's what was wrong with the conversion: we essentially computed
(eliding seconds)

jiffies = usec  * (NSEC_PER_USEC/TICK_NSEC)

by using scaling arithmetic, which took the best approximation of
NSEC_PER_USEC/TICK_NSEC with denominator of 2^USEC_JIFFIE_SC =
x/(2^USEC_JIFFIE_SC), and computed:

jiffies = (usec * x) >> USEC_JIFFIE_SC

and rounded this calculation up in the intermediate form (since we
can't necessarily exactly represent TICK_NSEC in usec.) But the
scaling arithmetic is a (very slight) *over*approximation of the true
value; that is, instead of dividing by (1 usec/ 1 jiffie), we
effectively divided by (1 usec/1 jiffie)-epsilon (rounding
down). This would normally be fine, but we want to round timeouts up,
and we did so by adding 2^USEC_JIFFIE_SC - 1 before the shift; this
would be fine if our division was exact, but dividing this by the
slightly smaller factor was equivalent to adding just _over_ 1 to the
final result (instead of just _under_ 1, as desired.)

In particular, with HZ=1000, we consistently computed that 10000 usec
was 11 jiffies; the same was true for any exact multiple of
TICK_NSEC.

We could possibly still round in the intermediate form, adding
something less than 2^USEC_JIFFIE_SC - 1, but easier still is to
convert usec->nsec, round in nanoseconds, and then convert using
time*spec*_to_jiffies.  This adds one constant multiplication, and is
not observably slower in microbenchmarks on recent x86 hardware.

Tested: the following program:

int main() {
  struct itimerval zero = {{0, 0}, {0, 0}};
  /* Initially set to 10 ms. */
  struct itimerval initial = zero;
  initial.it_interval.tv_usec = 10000;
  setitimer(ITIMER_PROF, &initial, NULL);
  /* Save and restore several times. */
  for (size_t i = 0; i < 10; ++i) {
    struct itimerval prev;
    setitimer(ITIMER_PROF, &zero, &prev);
    /* on old kernels, this goes up by TICK_USEC every iteration */
    printf("previous value: %ld %ld %ld %ld\n",
           prev.it_interval.tv_sec, prev.it_interval.tv_usec,
           prev.it_value.tv_sec, prev.it_value.tv_usec);
    setitimer(ITIMER_PROF, &prev, NULL);
  }
    return 0;
}

Cc: stable@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Paul Turner <pjt@google.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Reviewed-by: Paul Turner <pjt@google.com>
Reported-by: Aaron Jacobs <jacobsa@google.com>
Signed-off-by: Andrew Hunter <ahh@google.com>
[jstultz: Tweaked to apply to 3.17-rc]
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/jiffies.h | 12 -----------
 kernel/time/time.c      | 56 +++++++++++++++++++++++++++----------------------
 2 files changed, 31 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 1f44466c1e9d..c367cbdf73ab 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -258,23 +258,11 @@ extern unsigned long preset_lpj;
 #define SEC_JIFFIE_SC (32 - SHIFT_HZ)
 #endif
 #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29)
-#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19)
 #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\
                                 TICK_NSEC -1) / (u64)TICK_NSEC))
 
 #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\
                                         TICK_NSEC -1) / (u64)TICK_NSEC))
-#define USEC_CONVERSION  \
-                    ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\
-                                        TICK_NSEC -1) / (u64)TICK_NSEC))
-/*
- * USEC_ROUND is used in the timeval to jiffie conversion.  See there
- * for more details.  It is the scaled resolution rounding value.  Note
- * that it is a 64-bit value.  Since, when it is applied, we are already
- * in jiffies (albit scaled), it is nothing but the bits we will shift
- * off.
- */
-#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1)
 /*
  * The maximum jiffie value is (MAX_INT >> 1).  Here we translate that
  * into seconds.  The 64-bit case will overflow if we are not careful,
diff --git a/kernel/time/time.c b/kernel/time/time.c
index f0294ba14634..a9ae20fb0b11 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -559,17 +559,20 @@ EXPORT_SYMBOL(usecs_to_jiffies);
  * that a remainder subtract here would not do the right thing as the
  * resolution values don't fall on second boundries.  I.e. the line:
  * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
  *
  * Rather, we just shift the bits off the right.
  *
  * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
  * value to a scaled second value.
  */
-unsigned long
-timespec_to_jiffies(const struct timespec *value)
+static unsigned long
+__timespec_to_jiffies(unsigned long sec, long nsec)
 {
-	unsigned long sec = value->tv_sec;
-	long nsec = value->tv_nsec + TICK_NSEC - 1;
+	nsec = nsec + TICK_NSEC - 1;
 
 	if (sec >= MAX_SEC_IN_JIFFIES){
 		sec = MAX_SEC_IN_JIFFIES;
@@ -580,6 +583,13 @@ timespec_to_jiffies(const struct timespec *value)
 		 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 
 }
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+	return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
 EXPORT_SYMBOL(timespec_to_jiffies);
 
 void
@@ -596,31 +606,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
-/* Same for "timeval"
- *
- * Well, almost.  The problem here is that the real system resolution is
- * in nanoseconds and the value being converted is in micro seconds.
- * Also for some machines (those that use HZ = 1024, in-particular),
- * there is a LARGE error in the tick size in microseconds.
-
- * The solution we use is to do the rounding AFTER we convert the
- * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
- * Instruction wise, this should cost only an additional add with carry
- * instruction above the way it was done above.
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
+ *
+ * We could instead round in the intermediate scaled representation
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
+ * perilous: the scaling introduces a small positive error, which
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
+ * units to the intermediate before shifting) leads to accidental
+ * overflow and overestimates.
+ *
+ * At the cost of one additional multiplication by a constant, just
+ * use the timespec implementation.
  */
 unsigned long
 timeval_to_jiffies(const struct timeval *value)
 {
-	unsigned long sec = value->tv_sec;
-	long usec = value->tv_usec;
-
-	if (sec >= MAX_SEC_IN_JIFFIES){
-		sec = MAX_SEC_IN_JIFFIES;
-		usec = 0;
-	}
-	return (((u64)sec * SEC_CONVERSION) +
-		(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
-		 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+	return __timespec_to_jiffies(value->tv_sec,
+				     value->tv_usec * NSEC_PER_USEC);
 }
 EXPORT_SYMBOL(timeval_to_jiffies);
 
-- 
cgit v1.2.3


From 381f4dca48d23e155b936b86ccd3ff12f073cf0f Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 10 Sep 2014 23:23:02 +0200
Subject: ipv6: clean up anycast when an interface is destroyed

If we try to rmmod the driver for an interface while sockets with
setsockopt(JOIN_ANYCAST) are alive, some refcounts aren't cleaned up
and we get stuck on:

  unregister_netdevice: waiting for ens3 to become free. Usage count = 1

If we LEAVE_ANYCAST/close everything before rmmod'ing, there is no
problem.

We need to perform a cleanup similar to the one for multicast in
addrconf_ifdown(how == 1).

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h |  1 +
 net/ipv6/addrconf.c    |  8 +++++---
 net/ipv6/anycast.c     | 21 +++++++++++++++++++++
 3 files changed, 27 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f679877bb601..ec51e673b4b6 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -204,6 +204,7 @@ void ipv6_sock_ac_close(struct sock *sk);
 
 int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr);
 int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr);
+void ipv6_ac_destroy_dev(struct inet6_dev *idev);
 bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 			 const struct in6_addr *addr);
 bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fc1fac2a0528..3342ee64f2e3 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3094,11 +3094,13 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 
 	write_unlock_bh(&idev->lock);
 
-	/* Step 5: Discard multicast list */
-	if (how)
+	/* Step 5: Discard anycast and multicast list */
+	if (how) {
+		ipv6_ac_destroy_dev(idev);
 		ipv6_mc_destroy_dev(idev);
-	else
+	} else {
 		ipv6_mc_down(idev);
+	}
 
 	idev->tstamp = jiffies;
 
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index ff2de7d9d8e6..9a386842fd62 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -351,6 +351,27 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
 	return __ipv6_dev_ac_dec(idev, addr);
 }
 
+void ipv6_ac_destroy_dev(struct inet6_dev *idev)
+{
+	struct ifacaddr6 *aca;
+
+	write_lock_bh(&idev->lock);
+	while ((aca = idev->ac_list) != NULL) {
+		idev->ac_list = aca->aca_next;
+		write_unlock_bh(&idev->lock);
+
+		addrconf_leave_solict(idev, &aca->aca_addr);
+
+		dst_hold(&aca->aca_rt->dst);
+		ip6_del_rt(aca->aca_rt);
+
+		aca_put(aca);
+
+		write_lock_bh(&idev->lock);
+	}
+	write_unlock_bh(&idev->lock);
+}
+
 /*
  *	check if the interface has this anycast address
  *	called with rcu_read_lock()
-- 
cgit v1.2.3


From fbfa398b84a5fc6e085dedba5ec3e94f21815d05 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 28 Aug 2014 12:21:44 -0600
Subject: PCI: Remove unused pci_configure_slot()

All pci_configure_slot() uses have been removed, so remove the definition
as well.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Yinghai Lu <yinghai@kernel.org>
---
 drivers/pci/probe.c         | 28 ----------------------------
 include/linux/pci_hotplug.h |  2 --
 2 files changed, 30 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index e9482867555b..4b3b29bc7a82 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1358,34 +1358,6 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp)
 	 */
 }
 
-void pci_configure_slot(struct pci_dev *dev)
-{
-	struct pci_dev *cdev;
-	struct hotplug_params hpp;
-	int ret;
-
-	if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL ||
-			(dev->hdr_type == PCI_HEADER_TYPE_BRIDGE &&
-			(dev->class >> 8) == PCI_CLASS_BRIDGE_PCI)))
-		return;
-
-	pcie_bus_configure_settings(dev->bus);
-
-	memset(&hpp, 0, sizeof(hpp));
-	ret = pci_get_hp_params(dev, &hpp);
-
-	program_hpp_type2(dev, hpp.t2);
-	program_hpp_type1(dev, hpp.t1);
-	program_hpp_type0(dev, hpp.t0);
-
-	if (dev->subordinate) {
-		list_for_each_entry(cdev, &dev->subordinate->devices,
-				    bus_list)
-			pci_configure_slot(cdev);
-	}
-}
-EXPORT_SYMBOL_GPL(pci_configure_slot);
-
 static void pci_configure_device(struct pci_dev *dev)
 {
 	struct hotplug_params hpp;
diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h
index 5f2e559af6b0..2706ee9a4327 100644
--- a/include/linux/pci_hotplug.h
+++ b/include/linux/pci_hotplug.h
@@ -187,6 +187,4 @@ static inline int pci_get_hp_params(struct pci_dev *dev,
 	return -ENODEV;
 }
 #endif
-
-void pci_configure_slot(struct pci_dev *dev);
 #endif
-- 
cgit v1.2.3


From 46e5da40aec256155cfedee96dd21a75da941f2c Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 12 Sep 2014 20:04:52 -0700
Subject: net: qdisc: use rcu prefix and silence sparse warnings

Add __rcu notation to qdisc handling by doing this we can make
smatch output more legible. And anyways some of the cases should
be using rcu_dereference() see qdisc_all_tx_empty(),
qdisc_tx_chainging(), and so on.

Also *wake_queue() API is commonly called from driver timer routines
without rcu lock or rtnl lock. So I added rcu_read_lock() blocks
around netif_wake_subqueue and netif_tx_wake_queue.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 29 ++++-----------------------
 include/net/sch_generic.h | 21 +++++++++++++------
 net/core/dev.c            | 51 +++++++++++++++++++++++++++++++++++++++++++++--
 net/sched/sch_generic.c   |  4 ++--
 net/sched/sch_mqprio.c    |  6 ++++--
 net/sched/sch_teql.c      | 13 +++++++-----
 6 files changed, 82 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ba72f6baae1a..ae721f53739e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -543,7 +543,7 @@ struct netdev_queue {
  * read mostly part
  */
 	struct net_device	*dev;
-	struct Qdisc		*qdisc;
+	struct Qdisc __rcu	*qdisc;
 	struct Qdisc		*qdisc_sleeping;
 #ifdef CONFIG_SYSFS
 	struct kobject		kobj;
@@ -2356,12 +2356,7 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd,
 DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 
 void __netif_schedule(struct Qdisc *q);
-
-static inline void netif_schedule_queue(struct netdev_queue *txq)
-{
-	if (!(txq->state & QUEUE_STATE_ANY_XOFF))
-		__netif_schedule(txq->qdisc);
-}
+void netif_schedule_queue(struct netdev_queue *txq);
 
 static inline void netif_tx_schedule_all(struct net_device *dev)
 {
@@ -2397,11 +2392,7 @@ static inline void netif_tx_start_all_queues(struct net_device *dev)
 	}
 }
 
-static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue)
-{
-	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state))
-		__netif_schedule(dev_queue->qdisc);
-}
+void netif_tx_wake_queue(struct netdev_queue *dev_queue);
 
 /**
  *	netif_wake_queue - restart transmit
@@ -2673,19 +2664,7 @@ static inline bool netif_subqueue_stopped(const struct net_device *dev,
 	return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb));
 }
 
-/**
- *	netif_wake_subqueue - allow sending packets on subqueue
- *	@dev: network device
- *	@queue_index: sub queue index
- *
- * Resume individual transmit queue of a device with multiple transmit queues.
- */
-static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
-{
-	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
-	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state))
-		__netif_schedule(txq->qdisc);
-}
+void netif_wake_subqueue(struct net_device *dev, u16 queue_index);
 
 #ifdef CONFIG_XPS
 int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index a3cfb8ebeb53..56838ab29b42 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -259,7 +259,9 @@ static inline spinlock_t *qdisc_lock(struct Qdisc *qdisc)
 
 static inline struct Qdisc *qdisc_root(const struct Qdisc *qdisc)
 {
-	return qdisc->dev_queue->qdisc;
+	struct Qdisc *q = rcu_dereference_rtnl(qdisc->dev_queue->qdisc);
+
+	return q;
 }
 
 static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc)
@@ -384,7 +386,7 @@ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
 	struct Qdisc *qdisc;
 
 	for (; i < dev->num_tx_queues; i++) {
-		qdisc = netdev_get_tx_queue(dev, i)->qdisc;
+		qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
 		if (qdisc) {
 			spin_lock_bh(qdisc_lock(qdisc));
 			qdisc_reset(qdisc);
@@ -402,13 +404,18 @@ static inline void qdisc_reset_all_tx(struct net_device *dev)
 static inline bool qdisc_all_tx_empty(const struct net_device *dev)
 {
 	unsigned int i;
+
+	rcu_read_lock();
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
-		const struct Qdisc *q = txq->qdisc;
+		const struct Qdisc *q = rcu_dereference(txq->qdisc);
 
-		if (q->q.qlen)
+		if (q->q.qlen) {
+			rcu_read_unlock();
 			return false;
+		}
 	}
+	rcu_read_unlock();
 	return true;
 }
 
@@ -416,9 +423,10 @@ static inline bool qdisc_all_tx_empty(const struct net_device *dev)
 static inline bool qdisc_tx_changing(const struct net_device *dev)
 {
 	unsigned int i;
+
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
-		if (txq->qdisc != txq->qdisc_sleeping)
+		if (rcu_access_pointer(txq->qdisc) != txq->qdisc_sleeping)
 			return true;
 	}
 	return false;
@@ -428,9 +436,10 @@ static inline bool qdisc_tx_changing(const struct net_device *dev)
 static inline bool qdisc_tx_is_noop(const struct net_device *dev)
 {
 	unsigned int i;
+
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
-		if (txq->qdisc != &noop_qdisc)
+		if (rcu_access_pointer(txq->qdisc) != &noop_qdisc)
 			return false;
 	}
 	return true;
diff --git a/net/core/dev.c b/net/core/dev.c
index 3c6a967e5830..b3d6dbc0c696 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2177,6 +2177,53 @@ static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
 	return (struct dev_kfree_skb_cb *)skb->cb;
 }
 
+void netif_schedule_queue(struct netdev_queue *txq)
+{
+	rcu_read_lock();
+	if (!(txq->state & QUEUE_STATE_ANY_XOFF)) {
+		struct Qdisc *q = rcu_dereference(txq->qdisc);
+
+		__netif_schedule(q);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(netif_schedule_queue);
+
+/**
+ *	netif_wake_subqueue - allow sending packets on subqueue
+ *	@dev: network device
+ *	@queue_index: sub queue index
+ *
+ * Resume individual transmit queue of a device with multiple transmit queues.
+ */
+void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
+{
+	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
+
+	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) {
+		struct Qdisc *q;
+
+		rcu_read_lock();
+		q = rcu_dereference(txq->qdisc);
+		__netif_schedule(q);
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(netif_wake_subqueue);
+
+void netif_tx_wake_queue(struct netdev_queue *dev_queue)
+{
+	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) {
+		struct Qdisc *q;
+
+		rcu_read_lock();
+		q = rcu_dereference(dev_queue->qdisc);
+		__netif_schedule(q);
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(netif_tx_wake_queue);
+
 void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
 {
 	unsigned long flags;
@@ -3432,7 +3479,7 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
 	skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
 	skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
 
-	q = rxq->qdisc;
+	q = rcu_dereference(rxq->qdisc);
 	if (q != &noop_qdisc) {
 		spin_lock(qdisc_lock(q));
 		if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
@@ -3449,7 +3496,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb,
 {
 	struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
 
-	if (!rxq || rxq->qdisc == &noop_qdisc)
+	if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc)
 		goto out;
 
 	if (*pt_prev) {
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 19696ebe9ebc..346ef85617d3 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -783,7 +783,7 @@ static void dev_deactivate_queue(struct net_device *dev,
 	struct Qdisc *qdisc_default = _qdisc_default;
 	struct Qdisc *qdisc;
 
-	qdisc = dev_queue->qdisc;
+	qdisc = rtnl_dereference(dev_queue->qdisc);
 	if (qdisc) {
 		spin_lock_bh(qdisc_lock(qdisc));
 
@@ -876,7 +876,7 @@ static void dev_init_scheduler_queue(struct net_device *dev,
 {
 	struct Qdisc *qdisc = _qdisc;
 
-	dev_queue->qdisc = qdisc;
+	rcu_assign_pointer(dev_queue->qdisc, qdisc);
 	dev_queue->qdisc_sleeping = qdisc;
 }
 
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 6749e2f540d0..37e7d25d21f1 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -231,7 +231,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 	memset(&sch->qstats, 0, sizeof(sch->qstats));
 
 	for (i = 0; i < dev->num_tx_queues; i++) {
-		qdisc = netdev_get_tx_queue(dev, i)->qdisc;
+		qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
 		spin_lock_bh(qdisc_lock(qdisc));
 		sch->q.qlen		+= qdisc->q.qlen;
 		sch->bstats.bytes	+= qdisc->bstats.bytes;
@@ -340,7 +340,9 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		spin_unlock_bh(d->lock);
 
 		for (i = tc.offset; i < tc.offset + tc.count; i++) {
-			qdisc = netdev_get_tx_queue(dev, i)->qdisc;
+			struct netdev_queue *q = netdev_get_tx_queue(dev, i);
+
+			qdisc = rtnl_dereference(q->qdisc);
 			spin_lock_bh(qdisc_lock(qdisc));
 			bstats.bytes      += qdisc->bstats.bytes;
 			bstats.packets    += qdisc->bstats.packets;
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index aaa8d03ed054..5cd291bd00e4 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -96,11 +96,14 @@ teql_dequeue(struct Qdisc *sch)
 	struct teql_sched_data *dat = qdisc_priv(sch);
 	struct netdev_queue *dat_queue;
 	struct sk_buff *skb;
+	struct Qdisc *q;
 
 	skb = __skb_dequeue(&dat->q);
 	dat_queue = netdev_get_tx_queue(dat->m->dev, 0);
+	q = rcu_dereference_bh(dat_queue->qdisc);
+
 	if (skb == NULL) {
-		struct net_device *m = qdisc_dev(dat_queue->qdisc);
+		struct net_device *m = qdisc_dev(q);
 		if (m) {
 			dat->m->slaves = sch;
 			netif_wake_queue(m);
@@ -108,7 +111,7 @@ teql_dequeue(struct Qdisc *sch)
 	} else {
 		qdisc_bstats_update(sch, skb);
 	}
-	sch->q.qlen = dat->q.qlen + dat_queue->qdisc->q.qlen;
+	sch->q.qlen = dat->q.qlen + q->q.qlen;
 	return skb;
 }
 
@@ -157,9 +160,9 @@ teql_destroy(struct Qdisc *sch)
 						txq = netdev_get_tx_queue(master->dev, 0);
 						master->slaves = NULL;
 
-						root_lock = qdisc_root_sleeping_lock(txq->qdisc);
+						root_lock = qdisc_root_sleeping_lock(rtnl_dereference(txq->qdisc));
 						spin_lock_bh(root_lock);
-						qdisc_reset(txq->qdisc);
+						qdisc_reset(rtnl_dereference(txq->qdisc));
 						spin_unlock_bh(root_lock);
 					}
 				}
@@ -266,7 +269,7 @@ static inline int teql_resolve(struct sk_buff *skb,
 	struct dst_entry *dst = skb_dst(skb);
 	int res;
 
-	if (txq->qdisc == &noop_qdisc)
+	if (rcu_access_pointer(txq->qdisc) == &noop_qdisc)
 		return -ENODEV;
 
 	if (!dev->header_ops || !dst)
-- 
cgit v1.2.3


From 25d8c0d55f241ce2d360df1bea48e23a55836ee6 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 12 Sep 2014 20:05:27 -0700
Subject: net: rcu-ify tcf_proto

rcu'ify tcf_proto this allows calling tc_classify() without holding
any locks. Updaters are protected by RTNL.

This patch prepares the core net_sched infrastracture for running
the classifier/action chains without holding the qdisc lock however
it does nothing to ensure cls_xxx and act_xxx types also work without
locking. Additional patches are required to address the fall out.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  9 +++++----
 net/sched/cls_api.c       | 30 +++++++++++++++---------------
 net/sched/sch_api.c       | 10 +++++-----
 net/sched/sch_atm.c       | 20 +++++++++++---------
 net/sched/sch_cbq.c       | 11 +++++++----
 net/sched/sch_choke.c     | 15 +++++++++------
 net/sched/sch_drr.c       |  9 ++++++---
 net/sched/sch_dsmark.c    |  9 +++++----
 net/sched/sch_fq_codel.c  | 11 +++++++----
 net/sched/sch_hfsc.c      |  8 ++++----
 net/sched/sch_htb.c       | 15 ++++++++-------
 net/sched/sch_ingress.c   |  8 +++++---
 net/sched/sch_multiq.c    |  8 +++++---
 net/sched/sch_prio.c      | 11 +++++++----
 net/sched/sch_qfq.c       |  9 ++++++---
 net/sched/sch_sfb.c       | 15 +++++++++------
 net/sched/sch_sfq.c       | 11 +++++++----
 17 files changed, 121 insertions(+), 88 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 56838ab29b42..1e89b9ad3a4c 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -143,7 +143,7 @@ struct Qdisc_class_ops {
 	void			(*walk)(struct Qdisc *, struct qdisc_walker * arg);
 
 	/* Filter manipulation */
-	struct tcf_proto **	(*tcf_chain)(struct Qdisc *, unsigned long);
+	struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long);
 	unsigned long		(*bind_tcf)(struct Qdisc *, unsigned long,
 					u32 classid);
 	void			(*unbind_tcf)(struct Qdisc *, unsigned long);
@@ -212,8 +212,8 @@ struct tcf_proto_ops {
 
 struct tcf_proto {
 	/* Fast access part */
-	struct tcf_proto	*next;
-	void			*root;
+	struct tcf_proto __rcu	*next;
+	void __rcu		*root;
 	int			(*classify)(struct sk_buff *,
 					    const struct tcf_proto *,
 					    struct tcf_result *);
@@ -225,6 +225,7 @@ struct tcf_proto {
 	struct Qdisc		*q;
 	void			*data;
 	const struct tcf_proto_ops	*ops;
+	struct rcu_head		rcu;
 };
 
 struct qdisc_skb_cb {
@@ -378,7 +379,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
 void __qdisc_calculate_pkt_len(struct sk_buff *skb,
 			       const struct qdisc_size_table *stab);
 void tcf_destroy(struct tcf_proto *tp);
-void tcf_destroy_chain(struct tcf_proto **fl);
+void tcf_destroy_chain(struct tcf_proto __rcu **fl);
 
 /* Reset all TX qdiscs greater then index of a device.  */
 static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c28b0d327b12..e547efdaba9d 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -117,7 +117,6 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_MAX + 1];
-	spinlock_t *root_lock;
 	struct tcmsg *t;
 	u32 protocol;
 	u32 prio;
@@ -125,7 +124,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 parent;
 	struct net_device *dev;
 	struct Qdisc  *q;
-	struct tcf_proto **back, **chain;
+	struct tcf_proto __rcu **back;
+	struct tcf_proto __rcu **chain;
 	struct tcf_proto *tp;
 	const struct tcf_proto_ops *tp_ops;
 	const struct Qdisc_class_ops *cops;
@@ -197,7 +197,9 @@ replay:
 		goto errout;
 
 	/* Check the chain for existence of proto-tcf with this priority */
-	for (back = chain; (tp = *back) != NULL; back = &tp->next) {
+	for (back = chain;
+	     (tp = rtnl_dereference(*back)) != NULL;
+	     back = &tp->next) {
 		if (tp->prio >= prio) {
 			if (tp->prio == prio) {
 				if (!nprio ||
@@ -209,8 +211,6 @@ replay:
 		}
 	}
 
-	root_lock = qdisc_root_sleeping_lock(q);
-
 	if (tp == NULL) {
 		/* Proto-tcf does not exist, create new one */
 
@@ -259,7 +259,8 @@ replay:
 		}
 		tp->ops = tp_ops;
 		tp->protocol = protocol;
-		tp->prio = nprio ? : TC_H_MAJ(tcf_auto_prio(*back));
+		tp->prio = nprio ? :
+			       TC_H_MAJ(tcf_auto_prio(rtnl_dereference(*back)));
 		tp->q = q;
 		tp->classify = tp_ops->classify;
 		tp->classid = parent;
@@ -280,9 +281,9 @@ replay:
 
 	if (fh == 0) {
 		if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
-			spin_lock_bh(root_lock);
-			*back = tp->next;
-			spin_unlock_bh(root_lock);
+			struct tcf_proto *next = rtnl_dereference(tp->next);
+
+			RCU_INIT_POINTER(*back, next);
 
 			tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
 			tcf_destroy(tp);
@@ -322,10 +323,8 @@ replay:
 			      n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE);
 	if (err == 0) {
 		if (tp_created) {
-			spin_lock_bh(root_lock);
-			tp->next = *back;
-			*back = tp;
-			spin_unlock_bh(root_lock);
+			RCU_INIT_POINTER(tp->next, rtnl_dereference(*back));
+			rcu_assign_pointer(*back, tp);
 		}
 		tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER);
 	} else {
@@ -420,7 +419,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 	int s_t;
 	struct net_device *dev;
 	struct Qdisc *q;
-	struct tcf_proto *tp, **chain;
+	struct tcf_proto *tp, __rcu **chain;
 	struct tcmsg *tcm = nlmsg_data(cb->nlh);
 	unsigned long cl = 0;
 	const struct Qdisc_class_ops *cops;
@@ -454,7 +453,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 
 	s_t = cb->args[0];
 
-	for (tp = *chain, t = 0; tp; tp = tp->next, t++) {
+	for (tp = rtnl_dereference(*chain), t = 0;
+	     tp; tp = rtnl_dereference(tp->next), t++) {
 		if (t < s_t)
 			continue;
 		if (TC_H_MAJ(tcm->tcm_info) &&
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 58bed7599db7..ca6248345937 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1781,7 +1781,7 @@ int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp,
 	__be16 protocol = skb->protocol;
 	int err;
 
-	for (; tp; tp = tp->next) {
+	for (; tp; tp = rcu_dereference_bh(tp->next)) {
 		if (tp->protocol != protocol &&
 		    tp->protocol != htons(ETH_P_ALL))
 			continue;
@@ -1833,15 +1833,15 @@ void tcf_destroy(struct tcf_proto *tp)
 {
 	tp->ops->destroy(tp);
 	module_put(tp->ops->owner);
-	kfree(tp);
+	kfree_rcu(tp, rcu);
 }
 
-void tcf_destroy_chain(struct tcf_proto **fl)
+void tcf_destroy_chain(struct tcf_proto __rcu **fl)
 {
 	struct tcf_proto *tp;
 
-	while ((tp = *fl) != NULL) {
-		*fl = tp->next;
+	while ((tp = rtnl_dereference(*fl)) != NULL) {
+		RCU_INIT_POINTER(*fl, tp->next);
 		tcf_destroy(tp);
 	}
 }
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 8449b337f9e3..c398f9c3dbdd 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -41,7 +41,7 @@
 
 struct atm_flow_data {
 	struct Qdisc		*q;	/* FIFO, TBF, etc. */
-	struct tcf_proto	*filter_list;
+	struct tcf_proto __rcu	*filter_list;
 	struct atm_vcc		*vcc;	/* VCC; NULL if VCC is closed */
 	void			(*old_pop)(struct atm_vcc *vcc,
 					   struct sk_buff *skb); /* chaining */
@@ -273,7 +273,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent,
 		error = -ENOBUFS;
 		goto err_out;
 	}
-	flow->filter_list = NULL;
+	RCU_INIT_POINTER(flow->filter_list, NULL);
 	flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid);
 	if (!flow->q)
 		flow->q = &noop_qdisc;
@@ -311,7 +311,7 @@ static int atm_tc_delete(struct Qdisc *sch, unsigned long arg)
 	pr_debug("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow);
 	if (list_empty(&flow->list))
 		return -EINVAL;
-	if (flow->filter_list || flow == &p->link)
+	if (rcu_access_pointer(flow->filter_list) || flow == &p->link)
 		return -EBUSY;
 	/*
 	 * Reference count must be 2: one for "keepalive" (set at class
@@ -345,7 +345,8 @@ static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 	}
 }
 
-static struct tcf_proto **atm_tc_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **atm_tc_find_tcf(struct Qdisc *sch,
+						unsigned long cl)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
 	struct atm_flow_data *flow = (struct atm_flow_data *)cl;
@@ -369,11 +370,12 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	flow = NULL;
 	if (TC_H_MAJ(skb->priority) != sch->handle ||
 	    !(flow = (struct atm_flow_data *)atm_tc_get(sch, skb->priority))) {
+		struct tcf_proto *fl;
+
 		list_for_each_entry(flow, &p->flows, list) {
-			if (flow->filter_list) {
-				result = tc_classify_compat(skb,
-							    flow->filter_list,
-							    &res);
+			fl = rcu_dereference_bh(flow->filter_list);
+			if (fl) {
+				result = tc_classify_compat(skb, fl, &res);
 				if (result < 0)
 					continue;
 				flow = (struct atm_flow_data *)res.class;
@@ -544,7 +546,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!p->link.q)
 		p->link.q = &noop_qdisc;
 	pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q);
-	p->link.filter_list = NULL;
+	RCU_INIT_POINTER(p->link.filter_list, NULL);
 	p->link.vcc = NULL;
 	p->link.sock = NULL;
 	p->link.classid = sch->handle;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 762a04bb8f6d..a3244a800501 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -133,7 +133,7 @@ struct cbq_class {
 	struct gnet_stats_rate_est64 rate_est;
 	struct tc_cbq_xstats	xstats;
 
-	struct tcf_proto	*filter_list;
+	struct tcf_proto __rcu	*filter_list;
 
 	int			refcnt;
 	int			filters;
@@ -221,6 +221,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	struct cbq_class **defmap;
 	struct cbq_class *cl = NULL;
 	u32 prio = skb->priority;
+	struct tcf_proto *fl;
 	struct tcf_result res;
 
 	/*
@@ -235,11 +236,12 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 		int result = 0;
 		defmap = head->defaults;
 
+		fl = rcu_dereference_bh(head->filter_list);
 		/*
 		 * Step 2+n. Apply classifier.
 		 */
-		if (!head->filter_list ||
-		    (result = tc_classify_compat(skb, head->filter_list, &res)) < 0)
+		result = tc_classify_compat(skb, fl, &res);
+		if (!fl || result < 0)
 			goto fallback;
 
 		cl = (void *)res.class;
@@ -1954,7 +1956,8 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 	return 0;
 }
 
-static struct tcf_proto **cbq_find_tcf(struct Qdisc *sch, unsigned long arg)
+static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch,
+					     unsigned long arg)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index ed30e436128b..74813e6b6ff6 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -57,7 +57,7 @@ struct choke_sched_data {
 
 /* Variables */
 	struct red_vars  vars;
-	struct tcf_proto *filter_list;
+	struct tcf_proto __rcu *filter_list;
 	struct {
 		u32	prob_drop;	/* Early probability drops */
 		u32	prob_mark;	/* Early probability marks */
@@ -193,9 +193,11 @@ static bool choke_classify(struct sk_buff *skb,
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
 	struct tcf_result res;
+	struct tcf_proto *fl;
 	int result;
 
-	result = tc_classify(skb, q->filter_list, &res);
+	fl = rcu_dereference_bh(q->filter_list);
+	result = tc_classify(skb, fl, &res);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -249,7 +251,7 @@ static bool choke_match_random(const struct choke_sched_data *q,
 		return false;
 
 	oskb = choke_peek_random(q, pidx);
-	if (q->filter_list)
+	if (rcu_access_pointer(q->filter_list))
 		return choke_get_classid(nskb) == choke_get_classid(oskb);
 
 	return choke_match_flow(oskb, nskb);
@@ -257,11 +259,11 @@ static bool choke_match_random(const struct choke_sched_data *q,
 
 static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
+	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	struct choke_sched_data *q = qdisc_priv(sch);
 	const struct red_parms *p = &q->parms;
-	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 
-	if (q->filter_list) {
+	if (rcu_access_pointer(q->filter_list)) {
 		/* If using external classifiers, get result and record it. */
 		if (!choke_classify(skb, sch, &ret))
 			goto other_drop;	/* Packet was eaten by filter */
@@ -554,7 +556,8 @@ static unsigned long choke_bind(struct Qdisc *sch, unsigned long parent,
 	return 0;
 }
 
-static struct tcf_proto **choke_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **choke_find_tcf(struct Qdisc *sch,
+					       unsigned long cl)
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 7bbbfe112192..d8b5ccfd248a 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -35,7 +35,7 @@ struct drr_class {
 
 struct drr_sched {
 	struct list_head		active;
-	struct tcf_proto		*filter_list;
+	struct tcf_proto __rcu		*filter_list;
 	struct Qdisc_class_hash		clhash;
 };
 
@@ -184,7 +184,8 @@ static void drr_put_class(struct Qdisc *sch, unsigned long arg)
 		drr_destroy_class(sch, cl);
 }
 
-static struct tcf_proto **drr_tcf_chain(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **drr_tcf_chain(struct Qdisc *sch,
+					      unsigned long cl)
 {
 	struct drr_sched *q = qdisc_priv(sch);
 
@@ -319,6 +320,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
 	struct drr_sched *q = qdisc_priv(sch);
 	struct drr_class *cl;
 	struct tcf_result res;
+	struct tcf_proto *fl;
 	int result;
 
 	if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) {
@@ -328,7 +330,8 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	result = tc_classify(skb, q->filter_list, &res);
+	fl = rcu_dereference_bh(q->filter_list);
+	result = tc_classify(skb, fl, &res);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 49d6ef338b55..485e456c8139 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -37,7 +37,7 @@
 
 struct dsmark_qdisc_data {
 	struct Qdisc		*q;
-	struct tcf_proto	*filter_list;
+	struct tcf_proto __rcu	*filter_list;
 	u8			*mask;	/* "owns" the array */
 	u8			*value;
 	u16			indices;
@@ -186,8 +186,8 @@ ignore:
 	}
 }
 
-static inline struct tcf_proto **dsmark_find_tcf(struct Qdisc *sch,
-						 unsigned long cl)
+static inline struct tcf_proto __rcu **dsmark_find_tcf(struct Qdisc *sch,
+						       unsigned long cl)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 	return &p->filter_list;
@@ -229,7 +229,8 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		skb->tc_index = TC_H_MIN(skb->priority);
 	else {
 		struct tcf_result res;
-		int result = tc_classify(skb, p->filter_list, &res);
+		struct tcf_proto *fl = rcu_dereference_bh(p->filter_list);
+		int result = tc_classify(skb, fl, &res);
 
 		pr_debug("result %d class 0x%04x\n", result, res.classid);
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index cc56c8bb9bed..105cf5557630 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -52,7 +52,7 @@ struct fq_codel_flow {
 }; /* please try to keep this structure <= 64 bytes */
 
 struct fq_codel_sched_data {
-	struct tcf_proto *filter_list;	/* optional external classifier */
+	struct tcf_proto __rcu *filter_list; /* optional external classifier */
 	struct fq_codel_flow *flows;	/* Flows table [flows_cnt] */
 	u32		*backlogs;	/* backlog table [flows_cnt] */
 	u32		flows_cnt;	/* number of flows */
@@ -85,6 +85,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
 				      int *qerr)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
+	struct tcf_proto *filter;
 	struct tcf_result res;
 	int result;
 
@@ -93,11 +94,12 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
 	    TC_H_MIN(skb->priority) <= q->flows_cnt)
 		return TC_H_MIN(skb->priority);
 
-	if (!q->filter_list)
+	filter = rcu_dereference(q->filter_list);
+	if (!filter)
 		return fq_codel_hash(q, skb) + 1;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	result = tc_classify(skb, q->filter_list, &res);
+	result = tc_classify(skb, filter, &res);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -496,7 +498,8 @@ static void fq_codel_put(struct Qdisc *q, unsigned long cl)
 {
 }
 
-static struct tcf_proto **fq_codel_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **fq_codel_find_tcf(struct Qdisc *sch,
+						  unsigned long cl)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index ec8aeaac1dd7..04b0de4c68b5 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -116,7 +116,7 @@ struct hfsc_class {
 	struct gnet_stats_queue qstats;
 	struct gnet_stats_rate_est64 rate_est;
 	unsigned int	level;		/* class level in hierarchy */
-	struct tcf_proto *filter_list;	/* filter list */
+	struct tcf_proto __rcu *filter_list; /* filter list */
 	unsigned int	filter_cnt;	/* filter count */
 
 	struct hfsc_sched *sched;	/* scheduler data */
@@ -1161,7 +1161,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	head = &q->root;
-	tcf = q->root.filter_list;
+	tcf = rcu_dereference_bh(q->root.filter_list);
 	while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -1185,7 +1185,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 			return cl; /* hit leaf class */
 
 		/* apply inner filter chain */
-		tcf = cl->filter_list;
+		tcf = rcu_dereference_bh(cl->filter_list);
 		head = cl;
 	}
 
@@ -1285,7 +1285,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg)
 	cl->filter_cnt--;
 }
 
-static struct tcf_proto **
+static struct tcf_proto __rcu **
 hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg)
 {
 	struct hfsc_sched *q = qdisc_priv(sch);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index aea942ce6008..6d16b9b81c28 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -103,7 +103,7 @@ struct htb_class {
 	u32			prio;		/* these two are used only by leaves... */
 	int			quantum;	/* but stored for parent-to-leaf return */
 
-	struct tcf_proto	*filter_list;	/* class attached filters */
+	struct tcf_proto __rcu	*filter_list;	/* class attached filters */
 	int			filter_cnt;
 	int			refcnt;		/* usage count of this class */
 
@@ -153,7 +153,7 @@ struct htb_sched {
 	int			rate2quantum;	/* quant = rate / rate2quantum */
 
 	/* filters for qdisc itself */
-	struct tcf_proto	*filter_list;
+	struct tcf_proto __rcu	*filter_list;
 
 #define HTB_WARN_TOOMANYEVENTS	0x1
 	unsigned int		warned;	/* only one warning */
@@ -223,9 +223,9 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
 		if (cl->level == 0)
 			return cl;
 		/* Start with inner filter chain if a non-leaf class is selected */
-		tcf = cl->filter_list;
+		tcf = rcu_dereference_bh(cl->filter_list);
 	} else {
-		tcf = q->filter_list;
+		tcf = rcu_dereference_bh(q->filter_list);
 	}
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
@@ -251,7 +251,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
 			return cl;	/* we hit leaf; return it */
 
 		/* we have got inner class; apply inner filter chain */
-		tcf = cl->filter_list;
+		tcf = rcu_dereference_bh(cl->filter_list);
 	}
 	/* classification failed; try to use default class */
 	cl = htb_find(TC_H_MAKE(TC_H_MAJ(sch->handle), q->defcls), sch);
@@ -1519,11 +1519,12 @@ failure:
 	return err;
 }
 
-static struct tcf_proto **htb_find_tcf(struct Qdisc *sch, unsigned long arg)
+static struct tcf_proto __rcu **htb_find_tcf(struct Qdisc *sch,
+					     unsigned long arg)
 {
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = (struct htb_class *)arg;
-	struct tcf_proto **fl = cl ? &cl->filter_list : &q->filter_list;
+	struct tcf_proto __rcu **fl = cl ? &cl->filter_list : &q->filter_list;
 
 	return fl;
 }
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 62871c14e1f9..b351125f3849 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -17,7 +17,7 @@
 
 
 struct ingress_qdisc_data {
-	struct tcf_proto	*filter_list;
+	struct tcf_proto __rcu	*filter_list;
 };
 
 /* ------------------------- Class/flow operations ------------------------- */
@@ -46,7 +46,8 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 {
 }
 
-static struct tcf_proto **ingress_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch,
+						 unsigned long cl)
 {
 	struct ingress_qdisc_data *p = qdisc_priv(sch);
 
@@ -59,9 +60,10 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct ingress_qdisc_data *p = qdisc_priv(sch);
 	struct tcf_result res;
+	struct tcf_proto *fl = rcu_dereference_bh(p->filter_list);
 	int result;
 
-	result = tc_classify(skb, p->filter_list, &res);
+	result = tc_classify(skb, fl, &res);
 
 	qdisc_bstats_update(sch, skb);
 	switch (result) {
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index afb050a735fa..c0466c1840f3 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -31,7 +31,7 @@ struct multiq_sched_data {
 	u16 bands;
 	u16 max_bands;
 	u16 curband;
-	struct tcf_proto *filter_list;
+	struct tcf_proto __rcu *filter_list;
 	struct Qdisc **queues;
 };
 
@@ -42,10 +42,11 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	struct multiq_sched_data *q = qdisc_priv(sch);
 	u32 band;
 	struct tcf_result res;
+	struct tcf_proto *fl = rcu_dereference_bh(q->filter_list);
 	int err;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	err = tc_classify(skb, q->filter_list, &res);
+	err = tc_classify(skb, fl, &res);
 #ifdef CONFIG_NET_CLS_ACT
 	switch (err) {
 	case TC_ACT_STOLEN:
@@ -388,7 +389,8 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 	}
 }
 
-static struct tcf_proto **multiq_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **multiq_find_tcf(struct Qdisc *sch,
+						unsigned long cl)
 {
 	struct multiq_sched_data *q = qdisc_priv(sch);
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 79359b69ad8d..03ef99e52a5c 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -24,7 +24,7 @@
 
 struct prio_sched_data {
 	int bands;
-	struct tcf_proto *filter_list;
+	struct tcf_proto __rcu *filter_list;
 	u8  prio2band[TC_PRIO_MAX+1];
 	struct Qdisc *queues[TCQ_PRIO_BANDS];
 };
@@ -36,11 +36,13 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	struct prio_sched_data *q = qdisc_priv(sch);
 	u32 band = skb->priority;
 	struct tcf_result res;
+	struct tcf_proto *fl;
 	int err;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	if (TC_H_MAJ(skb->priority) != sch->handle) {
-		err = tc_classify(skb, q->filter_list, &res);
+		fl = rcu_dereference_bh(q->filter_list);
+		err = tc_classify(skb, fl, &res);
 #ifdef CONFIG_NET_CLS_ACT
 		switch (err) {
 		case TC_ACT_STOLEN:
@@ -50,7 +52,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 			return NULL;
 		}
 #endif
-		if (!q->filter_list || err < 0) {
+		if (!fl || err < 0) {
 			if (TC_H_MAJ(band))
 				band = 0;
 			return q->queues[q->prio2band[band & TC_PRIO_MAX]];
@@ -351,7 +353,8 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 	}
 }
 
-static struct tcf_proto **prio_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **prio_find_tcf(struct Qdisc *sch,
+					      unsigned long cl)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 8056fb4e618a..602ea01a4ddd 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -181,7 +181,7 @@ struct qfq_group {
 };
 
 struct qfq_sched {
-	struct tcf_proto *filter_list;
+	struct tcf_proto __rcu *filter_list;
 	struct Qdisc_class_hash clhash;
 
 	u64			oldV, V;	/* Precise virtual times. */
@@ -576,7 +576,8 @@ static void qfq_put_class(struct Qdisc *sch, unsigned long arg)
 		qfq_destroy_class(sch, cl);
 }
 
-static struct tcf_proto **qfq_tcf_chain(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **qfq_tcf_chain(struct Qdisc *sch,
+					      unsigned long cl)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
 
@@ -704,6 +705,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl;
 	struct tcf_result res;
+	struct tcf_proto *fl;
 	int result;
 
 	if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) {
@@ -714,7 +716,8 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	result = tc_classify(skb, q->filter_list, &res);
+	fl = rcu_dereference_bh(q->filter_list);
+	result = tc_classify(skb, fl, &res);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 9b0f7093d970..1562fb2b3f46 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -55,7 +55,7 @@ struct sfb_bins {
 
 struct sfb_sched_data {
 	struct Qdisc	*qdisc;
-	struct tcf_proto *filter_list;
+	struct tcf_proto __rcu *filter_list;
 	unsigned long	rehash_interval;
 	unsigned long	warmup_time;	/* double buffering warmup time in jiffies */
 	u32		max;
@@ -253,13 +253,13 @@ static bool sfb_rate_limit(struct sk_buff *skb, struct sfb_sched_data *q)
 	return false;
 }
 
-static bool sfb_classify(struct sk_buff *skb, struct sfb_sched_data *q,
+static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl,
 			 int *qerr, u32 *salt)
 {
 	struct tcf_result res;
 	int result;
 
-	result = tc_classify(skb, q->filter_list, &res);
+	result = tc_classify(skb, fl, &res);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -281,6 +281,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	struct sfb_sched_data *q = qdisc_priv(sch);
 	struct Qdisc *child = q->qdisc;
+	struct tcf_proto *fl;
 	int i;
 	u32 p_min = ~0;
 	u32 minqlen = ~0;
@@ -306,9 +307,10 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		}
 	}
 
-	if (q->filter_list) {
+	fl = rcu_dereference_bh(q->filter_list);
+	if (fl) {
 		/* If using external classifiers, get result and record it. */
-		if (!sfb_classify(skb, q, &ret, &salt))
+		if (!sfb_classify(skb, fl, &ret, &salt))
 			goto other_drop;
 		keys.src = salt;
 		keys.dst = 0;
@@ -660,7 +662,8 @@ static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 	}
 }
 
-static struct tcf_proto **sfb_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **sfb_find_tcf(struct Qdisc *sch,
+					     unsigned long cl)
 {
 	struct sfb_sched_data *q = qdisc_priv(sch);
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 211db9017c35..80c36bd54abc 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -125,7 +125,7 @@ struct sfq_sched_data {
 	u8		cur_depth;	/* depth of longest slot */
 	u8		flags;
 	unsigned short  scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
-	struct tcf_proto *filter_list;
+	struct tcf_proto __rcu *filter_list;
 	sfq_index	*ht;		/* Hash table ('divisor' slots) */
 	struct sfq_slot	*slots;		/* Flows table ('maxflows' entries) */
 
@@ -187,6 +187,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	struct tcf_result res;
+	struct tcf_proto *fl;
 	int result;
 
 	if (TC_H_MAJ(skb->priority) == sch->handle &&
@@ -194,13 +195,14 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 	    TC_H_MIN(skb->priority) <= q->divisor)
 		return TC_H_MIN(skb->priority);
 
-	if (!q->filter_list) {
+	fl = rcu_dereference_bh(q->filter_list);
+	if (!fl) {
 		skb_flow_dissect(skb, &sfq_skb_cb(skb)->keys);
 		return sfq_hash(q, skb) + 1;
 	}
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	result = tc_classify(skb, q->filter_list, &res);
+	result = tc_classify(skb, fl, &res);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -836,7 +838,8 @@ static void sfq_put(struct Qdisc *q, unsigned long cl)
 {
 }
 
-static struct tcf_proto **sfq_find_tcf(struct Qdisc *sch, unsigned long cl)
+static struct tcf_proto __rcu **sfq_find_tcf(struct Qdisc *sch,
+					     unsigned long cl)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 
-- 
cgit v1.2.3


From 331b72922c5f58d48fd5500acadc91777cc31970 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 12 Sep 2014 20:08:20 -0700
Subject: net: sched: RCU cls_tcindex

Make cls_tcindex RCU safe.

This patch addds a new RCU routine rcu_dereference_bh_rtnl() to check
caller either holds the rcu read lock or RTNL. This is needed to
handle the case where tcindex_lookup() is being called in both cases.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rtnetlink.h |  10 ++
 net/sched/cls_tcindex.c   | 248 ++++++++++++++++++++++++++++------------------
 2 files changed, 164 insertions(+), 94 deletions(-)

(limited to 'include')

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 167bae7bdfa4..6cacbce1a06c 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -46,6 +46,16 @@ static inline int lockdep_rtnl_is_held(void)
 #define rcu_dereference_rtnl(p)					\
 	rcu_dereference_check(p, lockdep_rtnl_is_held())
 
+/**
+ * rcu_dereference_bh_rtnl - rcu_dereference_bh with debug checking
+ * @p: The pointer to read, prior to dereference
+ *
+ * Do an rcu_dereference_bh(p), but check caller either holds rcu_read_lock_bh()
+ * or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference_bh()
+ */
+#define rcu_dereference_bh_rtnl(p)				\
+	rcu_dereference_bh_check(p, lockdep_rtnl_is_held())
+
 /**
  * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL
  * @p: The pointer to read, prior to dereferencing
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 3e9f76413b3b..a9f4279fbd69 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -32,19 +32,21 @@ struct tcindex_filter_result {
 struct tcindex_filter {
 	u16 key;
 	struct tcindex_filter_result result;
-	struct tcindex_filter *next;
+	struct tcindex_filter __rcu *next;
+	struct rcu_head rcu;
 };
 
 
 struct tcindex_data {
 	struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */
-	struct tcindex_filter **h; /* imperfect hash; only used if !perfect;
-				      NULL if unused */
+	struct tcindex_filter __rcu **h; /* imperfect hash; */
+	struct tcf_proto *tp;
 	u16 mask;		/* AND key with mask */
-	int shift;		/* shift ANDed key to the right */
-	int hash;		/* hash table size; 0 if undefined */
-	int alloc_hash;		/* allocated size */
-	int fall_through;	/* 0: only classify if explicit match */
+	u32 shift;		/* shift ANDed key to the right */
+	u32 hash;		/* hash table size; 0 if undefined */
+	u32 alloc_hash;		/* allocated size */
+	u32 fall_through;	/* 0: only classify if explicit match */
+	struct rcu_head rcu;
 };
 
 static inline int
@@ -56,13 +58,18 @@ tcindex_filter_is_set(struct tcindex_filter_result *r)
 static struct tcindex_filter_result *
 tcindex_lookup(struct tcindex_data *p, u16 key)
 {
-	struct tcindex_filter *f;
+	if (p->perfect) {
+		struct tcindex_filter_result *f = p->perfect + key;
+
+		return tcindex_filter_is_set(f) ? f : NULL;
+	} else if (p->h) {
+		struct tcindex_filter __rcu **fp;
+		struct tcindex_filter *f;
 
-	if (p->perfect)
-		return tcindex_filter_is_set(p->perfect + key) ?
-			p->perfect + key : NULL;
-	else if (p->h) {
-		for (f = p->h[key % p->hash]; f; f = f->next)
+		fp = &p->h[key % p->hash];
+		for (f = rcu_dereference_bh_rtnl(*fp);
+		     f;
+		     fp = &f->next, f = rcu_dereference_bh_rtnl(*fp))
 			if (f->key == key)
 				return &f->result;
 	}
@@ -74,7 +81,7 @@ tcindex_lookup(struct tcindex_data *p, u16 key)
 static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			    struct tcf_result *res)
 {
-	struct tcindex_data *p = tp->root;
+	struct tcindex_data *p = rcu_dereference(tp->root);
 	struct tcindex_filter_result *f;
 	int key = (skb->tc_index & p->mask) >> p->shift;
 
@@ -99,7 +106,7 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle)
 {
-	struct tcindex_data *p = tp->root;
+	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcindex_filter_result *r;
 
 	pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle);
@@ -129,49 +136,59 @@ static int tcindex_init(struct tcf_proto *tp)
 	p->hash = DEFAULT_HASH_SIZE;
 	p->fall_through = 1;
 
-	tp->root = p;
+	rcu_assign_pointer(tp->root, p);
 	return 0;
 }
 
-
 static int
-__tcindex_delete(struct tcf_proto *tp, unsigned long arg, int lock)
+tcindex_delete(struct tcf_proto *tp, unsigned long arg)
 {
-	struct tcindex_data *p = tp->root;
+	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg;
+	struct tcindex_filter __rcu **walk;
 	struct tcindex_filter *f = NULL;
 
-	pr_debug("tcindex_delete(tp %p,arg 0x%lx),p %p,f %p\n", tp, arg, p, f);
+	pr_debug("tcindex_delete(tp %p,arg 0x%lx),p %p\n", tp, arg, p);
 	if (p->perfect) {
 		if (!r->res.class)
 			return -ENOENT;
 	} else {
 		int i;
-		struct tcindex_filter **walk = NULL;
 
-		for (i = 0; i < p->hash; i++)
-			for (walk = p->h+i; *walk; walk = &(*walk)->next)
-				if (&(*walk)->result == r)
+		for (i = 0; i < p->hash; i++) {
+			walk = p->h + i;
+			for (f = rtnl_dereference(*walk); f;
+			     walk = &f->next, f = rtnl_dereference(*walk)) {
+				if (&f->result == r)
 					goto found;
+			}
+		}
 		return -ENOENT;
 
 found:
-		f = *walk;
-		if (lock)
-			tcf_tree_lock(tp);
-		*walk = f->next;
-		if (lock)
-			tcf_tree_unlock(tp);
+		rcu_assign_pointer(*walk, rtnl_dereference(f->next));
 	}
 	tcf_unbind_filter(tp, &r->res);
 	tcf_exts_destroy(tp, &r->exts);
-	kfree(f);
+	if (f)
+		kfree_rcu(f, rcu);
 	return 0;
 }
 
-static int tcindex_delete(struct tcf_proto *tp, unsigned long arg)
+static int tcindex_destroy_element(struct tcf_proto *tp,
+				   unsigned long arg,
+				   struct tcf_walker *walker)
 {
-	return __tcindex_delete(tp, arg, 1);
+	return tcindex_delete(tp, arg);
+}
+
+static void __tcindex_destroy(struct rcu_head *head)
+{
+	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+
+	kfree(p->perfect);
+	kfree(p->h);
+	kfree(p);
 }
 
 static inline int
@@ -194,6 +211,14 @@ static void tcindex_filter_result_init(struct tcindex_filter_result *r)
 	tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 }
 
+static void __tcindex_partial_destroy(struct rcu_head *head)
+{
+	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+
+	kfree(p->perfect);
+	kfree(p);
+}
+
 static int
 tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		  u32 handle, struct tcindex_data *p,
@@ -203,7 +228,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	int err, balloc = 0;
 	struct tcindex_filter_result new_filter_result, *old_r = r;
 	struct tcindex_filter_result cr;
-	struct tcindex_data cp;
+	struct tcindex_data *cp, *oldp;
 	struct tcindex_filter *f = NULL; /* make gcc behave */
 	struct tcf_exts e;
 
@@ -212,84 +237,118 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (err < 0)
 		return err;
 
-	memcpy(&cp, p, sizeof(cp));
-	tcindex_filter_result_init(&new_filter_result);
+	/* tcindex_data attributes must look atomic to classifier/lookup so
+	 * allocate new tcindex data and RCU assign it onto root. Keeping
+	 * perfect hash and hash pointers from old data.
+	 */
+	cp = kzalloc(sizeof(cp), GFP_KERNEL);
+	if (!cp)
+		return -ENOMEM;
+
+	cp->mask = p->mask;
+	cp->shift = p->shift;
+	cp->hash = p->hash;
+	cp->alloc_hash = p->alloc_hash;
+	cp->fall_through = p->fall_through;
+	cp->tp = tp;
+
+	if (p->perfect) {
+		cp->perfect = kmemdup(p->perfect,
+				      sizeof(*r) * cp->hash, GFP_KERNEL);
+		if (!cp->perfect)
+			goto errout;
+	}
+	cp->h = p->h;
+
+	memset(&new_filter_result, 0, sizeof(new_filter_result));
+	tcf_exts_init(&new_filter_result.exts,
+		      TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 
 	tcindex_filter_result_init(&cr);
 	if (old_r)
 		cr.res = r->res;
 
 	if (tb[TCA_TCINDEX_HASH])
-		cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
+		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
 
 	if (tb[TCA_TCINDEX_MASK])
-		cp.mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
+		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
 
 	if (tb[TCA_TCINDEX_SHIFT])
-		cp.shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
+		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
 
 	err = -EBUSY;
+
 	/* Hash already allocated, make sure that we still meet the
 	 * requirements for the allocated hash.
 	 */
-	if (cp.perfect) {
-		if (!valid_perfect_hash(&cp) ||
-		    cp.hash > cp.alloc_hash)
+	if (cp->perfect) {
+		if (!valid_perfect_hash(cp) ||
+		    cp->hash > cp->alloc_hash)
 			goto errout;
-	} else if (cp.h && cp.hash != cp.alloc_hash)
+	} else if (cp->h && cp->hash != cp->alloc_hash) {
 		goto errout;
+	}
 
 	err = -EINVAL;
 	if (tb[TCA_TCINDEX_FALL_THROUGH])
-		cp.fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
+		cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
 
-	if (!cp.hash) {
+	if (!cp->hash) {
 		/* Hash not specified, use perfect hash if the upper limit
 		 * of the hashing index is below the threshold.
 		 */
-		if ((cp.mask >> cp.shift) < PERFECT_HASH_THRESHOLD)
-			cp.hash = (cp.mask >> cp.shift) + 1;
+		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
+			cp->hash = (cp->mask >> cp->shift) + 1;
 		else
-			cp.hash = DEFAULT_HASH_SIZE;
+			cp->hash = DEFAULT_HASH_SIZE;
 	}
 
-	if (!cp.perfect && !cp.h)
-		cp.alloc_hash = cp.hash;
+	if (!cp->perfect && cp->h)
+		cp->alloc_hash = cp->hash;
 
 	/* Note: this could be as restrictive as if (handle & ~(mask >> shift))
 	 * but then, we'd fail handles that may become valid after some future
 	 * mask change. While this is extremely unlikely to ever matter,
 	 * the check below is safer (and also more backwards-compatible).
 	 */
-	if (cp.perfect || valid_perfect_hash(&cp))
-		if (handle >= cp.alloc_hash)
+	if (cp->perfect || valid_perfect_hash(cp))
+		if (handle >= cp->alloc_hash)
 			goto errout;
 
 
 	err = -ENOMEM;
-	if (!cp.perfect && !cp.h) {
-		if (valid_perfect_hash(&cp)) {
+	if (!cp->perfect && !cp->h) {
+		if (valid_perfect_hash(cp)) {
 			int i;
 
-			cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL);
-			if (!cp.perfect)
+			cp->perfect = kcalloc(cp->hash, sizeof(*r), GFP_KERNEL);
+			if (!cp->perfect)
 				goto errout;
-			for (i = 0; i < cp.hash; i++)
-				tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT,
+			for (i = 0; i < cp->hash; i++)
+				tcf_exts_init(&cp->perfect[i].exts,
+					      TCA_TCINDEX_ACT,
 					      TCA_TCINDEX_POLICE);
 			balloc = 1;
 		} else {
-			cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL);
-			if (!cp.h)
+			struct tcindex_filter __rcu **hash;
+
+			hash = kcalloc(cp->hash,
+				       sizeof(struct tcindex_filter *),
+				       GFP_KERNEL);
+
+			if (!hash)
 				goto errout;
+
+			cp->h = hash;
 			balloc = 2;
 		}
 	}
 
-	if (cp.perfect)
-		r = cp.perfect + handle;
+	if (cp->perfect)
+		r = cp->perfect + handle;
 	else
-		r = tcindex_lookup(&cp, handle) ? : &new_filter_result;
+		r = tcindex_lookup(cp, handle) ? : &new_filter_result;
 
 	if (r == &new_filter_result) {
 		f = kzalloc(sizeof(*f), GFP_KERNEL);
@@ -307,33 +366,41 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	else
 		tcf_exts_change(tp, &cr.exts, &e);
 
-	tcf_tree_lock(tp);
 	if (old_r && old_r != r)
 		tcindex_filter_result_init(old_r);
 
-	memcpy(p, &cp, sizeof(cp));
+	oldp = p;
 	r->res = cr.res;
+	rcu_assign_pointer(tp->root, cp);
 
 	if (r == &new_filter_result) {
-		struct tcindex_filter **fp;
+		struct tcindex_filter *nfp;
+		struct tcindex_filter __rcu **fp;
 
 		f->key = handle;
 		f->result = new_filter_result;
 		f->next = NULL;
-		for (fp = p->h+(handle % p->hash); *fp; fp = &(*fp)->next)
-			/* nothing */;
-		*fp = f;
+
+		fp = p->h + (handle % p->hash);
+		for (nfp = rtnl_dereference(*fp);
+		     nfp;
+		     fp = &nfp->next, nfp = rtnl_dereference(*fp))
+				; /* nothing */
+
+		rcu_assign_pointer(*fp, f);
 	}
-	tcf_tree_unlock(tp);
 
+	if (oldp)
+		call_rcu(&oldp->rcu, __tcindex_partial_destroy);
 	return 0;
 
 errout_alloc:
 	if (balloc == 1)
-		kfree(cp.perfect);
+		kfree(cp->perfect);
 	else if (balloc == 2)
-		kfree(cp.h);
+		kfree(cp->h);
 errout:
+	kfree(cp);
 	tcf_exts_destroy(tp, &e);
 	return err;
 }
@@ -345,7 +412,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb,
 {
 	struct nlattr *opt = tca[TCA_OPTIONS];
 	struct nlattr *tb[TCA_TCINDEX_MAX + 1];
-	struct tcindex_data *p = tp->root;
+	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcindex_filter_result *r = (struct tcindex_filter_result *) *arg;
 	int err;
 
@@ -364,10 +431,9 @@ tcindex_change(struct net *net, struct sk_buff *in_skb,
 				 tca[TCA_RATE], ovr);
 }
 
-
 static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
 {
-	struct tcindex_data *p = tp->root;
+	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcindex_filter *f, *next;
 	int i;
 
@@ -390,8 +456,8 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
 	if (!p->h)
 		return;
 	for (i = 0; i < p->hash; i++) {
-		for (f = p->h[i]; f; f = next) {
-			next = f->next;
+		for (f = rtnl_dereference(p->h[i]); f; f = next) {
+			next = rtnl_dereference(f->next);
 			if (walker->count >= walker->skip) {
 				if (walker->fn(tp, (unsigned long) &f->result,
 				    walker) < 0) {
@@ -404,17 +470,9 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
 	}
 }
 
-
-static int tcindex_destroy_element(struct tcf_proto *tp,
-    unsigned long arg, struct tcf_walker *walker)
-{
-	return __tcindex_delete(tp, arg, 0);
-}
-
-
 static void tcindex_destroy(struct tcf_proto *tp)
 {
-	struct tcindex_data *p = tp->root;
+	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcf_walker walker;
 
 	pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
@@ -422,17 +480,16 @@ static void tcindex_destroy(struct tcf_proto *tp)
 	walker.skip = 0;
 	walker.fn = tcindex_destroy_element;
 	tcindex_walk(tp, &walker);
-	kfree(p->perfect);
-	kfree(p->h);
-	kfree(p);
-	tp->root = NULL;
+
+	RCU_INIT_POINTER(tp->root, NULL);
+	call_rcu(&p->rcu, __tcindex_destroy);
 }
 
 
 static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
     struct sk_buff *skb, struct tcmsg *t)
 {
-	struct tcindex_data *p = tp->root;
+	struct tcindex_data *p = rtnl_dereference(tp->root);
 	struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh;
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
@@ -455,15 +512,18 @@ static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		nla_nest_end(skb, nest);
 	} else {
 		if (p->perfect) {
-			t->tcm_handle = r-p->perfect;
+			t->tcm_handle = r - p->perfect;
 		} else {
 			struct tcindex_filter *f;
+			struct tcindex_filter __rcu **fp;
 			int i;
 
 			t->tcm_handle = 0;
 			for (i = 0; !t->tcm_handle && i < p->hash; i++) {
-				for (f = p->h[i]; !t->tcm_handle && f;
-				     f = f->next) {
+				fp = &p->h[i];
+				for (f = rtnl_dereference(*fp);
+				     !t->tcm_handle && f;
+				     fp = &f->next, f = rtnl_dereference(*fp)) {
 					if (&f->result == r)
 						t->tcm_handle = f->key;
 				}
-- 
cgit v1.2.3


From a80e49e2cc3145af014a8ae44f575829cc236192 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Sat, 16 Aug 2014 17:47:18 +0200
Subject: nohz: Move nohz full init call to tick init

This way we unbloat a bit main.c and more importantly we initialize
nohz full after init_IRQ(). This dependency will be needed in further
patches because nohz full needs irq work to raise its own IRQ.
Information about the support for this ability on ARM64 is obtained on
init_IRQ() which initialize the pointer to __smp_call_function.

Since tick_init() is called right after init_IRQ(), this is a good place
to call tick_nohz_init() and prepare for that dependency.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 include/linux/tick.h        | 2 --
 init/main.c                 | 1 -
 kernel/time/tick-common.c   | 1 +
 kernel/time/tick-internal.h | 7 +++++++
 4 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/tick.h b/include/linux/tick.h
index 9a82c7dc3fdd..595ee86f5e0d 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -181,14 +181,12 @@ static inline bool tick_nohz_full_cpu(int cpu)
 	return cpumask_test_cpu(cpu, tick_nohz_full_mask);
 }
 
-extern void tick_nohz_init(void);
 extern void __tick_nohz_full_check(void);
 extern void tick_nohz_full_kick(void);
 extern void tick_nohz_full_kick_cpu(int cpu);
 extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(struct task_struct *tsk);
 #else
-static inline void tick_nohz_init(void) { }
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void __tick_nohz_full_check(void) { }
diff --git a/init/main.c b/init/main.c
index bb1aed928f21..8af2f1abfe38 100644
--- a/init/main.c
+++ b/init/main.c
@@ -577,7 +577,6 @@ asmlinkage __visible void __init start_kernel(void)
 		local_irq_disable();
 	idr_init_cache();
 	rcu_init();
-	tick_nohz_init();
 	context_tracking_init();
 	radix_tree_init();
 	/* init some links before init_ISA_irqs() */
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 0a0608edeb26..052b4b53c3d6 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -400,4 +400,5 @@ void tick_resume(void)
 void __init tick_init(void)
 {
 	tick_broadcast_init();
+	tick_nohz_init();
 }
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index c19c1d84b6f3..366aeb4f2c66 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -99,6 +99,13 @@ static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline bool tick_broadcast_oneshot_available(void) { return false; }
 #endif /* !TICK_ONESHOT */
 
+/* NO_HZ_FULL internal */
+#ifdef CONFIG_NO_HZ_FULL
+extern void tick_nohz_init(void);
+# else
+static inline void tick_nohz_init(void) { }
+#endif
+
 /*
  * Broadcasting support
  */
-- 
cgit v1.2.3


From c5c38ef3d70377dc504a6a3f611a3ec814bc757b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 6 Sep 2014 15:43:02 +0200
Subject: irq_work: Introduce arch_irq_work_has_interrupt()

The nohz full code needs irq work to trigger its own interrupt so that
the subsystem can work even when the tick is stopped.

Lets introduce arch_irq_work_has_interrupt() that archs can override to
tell about their support for this ability.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 arch/alpha/include/asm/Kbuild      |  1 +
 arch/arc/include/asm/Kbuild        |  1 +
 arch/arm/include/asm/Kbuild        |  1 +
 arch/arm64/include/asm/Kbuild      |  3 ++-
 arch/avr32/include/asm/Kbuild      |  1 +
 arch/blackfin/include/asm/Kbuild   |  1 +
 arch/c6x/include/asm/Kbuild        |  1 +
 arch/cris/include/asm/Kbuild       |  1 +
 arch/frv/include/asm/Kbuild        |  1 +
 arch/hexagon/include/asm/Kbuild    |  1 +
 arch/ia64/include/asm/Kbuild       |  1 +
 arch/m32r/include/asm/Kbuild       |  1 +
 arch/m68k/include/asm/Kbuild       |  1 +
 arch/metag/include/asm/Kbuild      |  1 +
 arch/microblaze/include/asm/Kbuild |  1 +
 arch/mips/include/asm/Kbuild       |  1 +
 arch/mn10300/include/asm/Kbuild    |  1 +
 arch/openrisc/include/asm/Kbuild   |  1 +
 arch/parisc/include/asm/Kbuild     |  1 +
 arch/powerpc/include/asm/Kbuild    |  1 +
 arch/s390/include/asm/Kbuild       |  1 +
 arch/score/include/asm/Kbuild      |  1 +
 arch/sh/include/asm/Kbuild         |  1 +
 arch/sparc/include/asm/Kbuild      |  1 +
 arch/tile/include/asm/Kbuild       |  1 +
 arch/um/include/asm/Kbuild         |  1 +
 arch/unicore32/include/asm/Kbuild  |  1 +
 arch/x86/include/asm/Kbuild        |  1 +
 arch/xtensa/include/asm/Kbuild     |  1 +
 include/asm-generic/irq_work.h     | 10 ++++++++++
 include/linux/irq_work.h           |  2 ++
 31 files changed, 42 insertions(+), 1 deletion(-)
 create mode 100644 include/asm-generic/irq_work.h

(limited to 'include')

diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index e858aa0ad8af..a52cbf178c3a 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -4,6 +4,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index e76fd79f32b0..b8fffc1a2ac2 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -18,6 +18,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 70cd84eb7fda..202905e7ea0c 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -11,6 +11,7 @@ generic-y += hash.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += local.h
 generic-y += local64.h
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 0b3fcf86e6ba..d617789b1ebd 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -9,8 +9,8 @@ generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
-generic-y += emergency-restart.h
 generic-y += early_ioremap.h
+generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += ftrace.h
 generic-y += hash.h
@@ -19,6 +19,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 00a0f3ccd6eb..2a71b1cb9848 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += exec.h
 generic-y += futex.h
 generic-y += hash.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 0d93b9a79ca9..46ed6bb9c679 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -15,6 +15,7 @@ generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 8dbdce8421b0..e77e0c1dbe75 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -22,6 +22,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 31742dfadff9..802b94c4ca86 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -8,6 +8,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += linkage.h
 generic-y += mcs_spinlock.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 5b73921b6e9d..3caf05cabfc5 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -3,6 +3,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 0e69796b58c7..5f234a5a2320 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -23,6 +23,7 @@ generic-y += ioctls.h
 generic-y += iomap.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index e8317d2d6c8d..747320be9d0e 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -2,6 +2,7 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index accc10a3dc78..e02448b0648b 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -3,6 +3,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += module.h
 generic-y += preempt.h
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index c67c94a2d672..dbaf9f3065e8 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -11,6 +11,7 @@ generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index c29ead89a317..7b8111c8f937 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -19,6 +19,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 27a3acda6c19..448143b8cabd 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -5,6 +5,7 @@ generic-y += cputime.h
 generic-y += device.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 335e5290ec75..57012ef1f51e 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -3,6 +3,7 @@ generic-y += cputime.h
 generic-y += current.h
 generic-y += emergency-restart.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mutex.h
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index ecbd6676bd33..77eb1a68d13b 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -4,6 +4,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 480af0d9c2f5..89b61d7dc790 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -31,6 +31,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index ecf25e6678ad..ffb024b8423f 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -10,6 +10,7 @@ generic-y += exec.h
 generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kvm_para.h
 generic-y += local.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 7f23f162ce9c..31e8f59aff38 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,6 +1,7 @@
 
 generic-y += clkdev.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += rwsem.h
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index b3fea0722ff1..773f86676588 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -2,6 +2,7 @@
 
 generic-y += clkdev.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index aad209199f7e..1909d2a5b82f 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -6,6 +6,7 @@ generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index c19e47dacb31..5a6c9acff0d2 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -12,6 +12,7 @@ generic-y += hash.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index cdd1b447bb6c..f5f94ce1692c 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -8,6 +8,7 @@ generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += hash.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 0aa5675e7025..e6462b8a6284 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -17,6 +17,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 7bd64aa2e94a..244b12c8cb39 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -14,6 +14,7 @@ generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += io.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mutex.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 1e5fb872a4aa..5a2bb53faa42 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -22,6 +22,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 3bf000fab0ae..8fa909cc6553 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -7,5 +7,6 @@ genhdr-y += unistd_x32.h
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += early_ioremap.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += scatterlist.h
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index c3d20ba6eb86..105d38922c44 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -12,6 +12,7 @@ generic-y += hardirq.h
 generic-y += hash.h
 generic-y += ioctl.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/include/asm-generic/irq_work.h b/include/asm-generic/irq_work.h
new file mode 100644
index 000000000000..a44f452c6590
--- /dev/null
+++ b/include/asm-generic/irq_work.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_IRQ_WORK_H
+#define __ASM_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return false;
+}
+
+#endif /* __ASM_IRQ_WORK_H */
+
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index bf9422c3aefe..6b47b2ede405 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -42,6 +42,8 @@ void irq_work_run(void);
 void irq_work_sync(struct irq_work *work);
 
 #ifdef CONFIG_IRQ_WORK
+#include <asm/irq_work.h>
+
 bool irq_work_needs_cpu(void);
 #else
 static inline bool irq_work_needs_cpu(void) { return false; }
-- 
cgit v1.2.3


From 76a33061b9323b7fdb220ae5fa116c10833ec22e Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Sat, 16 Aug 2014 18:37:19 +0200
Subject: irq_work: Force raised irq work to run on irq work interrupt

The nohz full kick, which restarts the tick when any resource depend
on it, can't be executed anywhere given the operation it does on timers.
If it is called from the scheduler or timers code, chances are that
we run into a deadlock.

This is why we run the nohz full kick from an irq work. That way we make
sure that the kick runs on a virgin context.

However if that's the case when irq work runs in its own dedicated
self-ipi, things are different for the big bunch of archs that don't
support the self triggered way. In order to support them, irq works are
also handled by the timer interrupt as fallback.

Now when irq works run on the timer interrupt, the context isn't blank.
More precisely, they can run in the context of the hrtimer that runs the
tick. But the nohz kick cancels and restarts this hrtimer and cancelling
an hrtimer from itself isn't allowed. This is why we run in an endless
loop:

	Kernel panic - not syncing: Watchdog detected hard LOCKUP on cpu 2
	CPU: 2 PID: 7538 Comm: kworker/u8:8 Not tainted 3.16.0+ #34
	Workqueue: btrfs-endio-write normal_work_helper [btrfs]
	 ffff880244c06c88 000000001b486fe1 ffff880244c06bf0 ffffffff8a7f1e37
	 ffffffff8ac52a18 ffff880244c06c78 ffffffff8a7ef928 0000000000000010
	 ffff880244c06c88 ffff880244c06c20 000000001b486fe1 0000000000000000
	Call Trace:
	 <NMI[<ffffffff8a7f1e37>] dump_stack+0x4e/0x7a
	 [<ffffffff8a7ef928>] panic+0xd4/0x207
	 [<ffffffff8a1450e8>] watchdog_overflow_callback+0x118/0x120
	 [<ffffffff8a186b0e>] __perf_event_overflow+0xae/0x350
	 [<ffffffff8a184f80>] ? perf_event_task_disable+0xa0/0xa0
	 [<ffffffff8a01a4cf>] ? x86_perf_event_set_period+0xbf/0x150
	 [<ffffffff8a187934>] perf_event_overflow+0x14/0x20
	 [<ffffffff8a020386>] intel_pmu_handle_irq+0x206/0x410
	 [<ffffffff8a01937b>] perf_event_nmi_handler+0x2b/0x50
	 [<ffffffff8a007b72>] nmi_handle+0xd2/0x390
	 [<ffffffff8a007aa5>] ? nmi_handle+0x5/0x390
	 [<ffffffff8a0cb7f8>] ? match_held_lock+0x8/0x1b0
	 [<ffffffff8a008062>] default_do_nmi+0x72/0x1c0
	 [<ffffffff8a008268>] do_nmi+0xb8/0x100
	 [<ffffffff8a7ff66a>] end_repeat_nmi+0x1e/0x2e
	 [<ffffffff8a0cb7f8>] ? match_held_lock+0x8/0x1b0
	 [<ffffffff8a0cb7f8>] ? match_held_lock+0x8/0x1b0
	 [<ffffffff8a0cb7f8>] ? match_held_lock+0x8/0x1b0
	 <<EOE><IRQ[<ffffffff8a0ccd2f>] lock_acquired+0xaf/0x450
	 [<ffffffff8a0f74c5>] ? lock_hrtimer_base.isra.20+0x25/0x50
	 [<ffffffff8a7fc678>] _raw_spin_lock_irqsave+0x78/0x90
	 [<ffffffff8a0f74c5>] ? lock_hrtimer_base.isra.20+0x25/0x50
	 [<ffffffff8a0f74c5>] lock_hrtimer_base.isra.20+0x25/0x50
	 [<ffffffff8a0f7723>] hrtimer_try_to_cancel+0x33/0x1e0
	 [<ffffffff8a0f78ea>] hrtimer_cancel+0x1a/0x30
	 [<ffffffff8a109237>] tick_nohz_restart+0x17/0x90
	 [<ffffffff8a10a213>] __tick_nohz_full_check+0xc3/0x100
	 [<ffffffff8a10a25e>] nohz_full_kick_work_func+0xe/0x10
	 [<ffffffff8a17c884>] irq_work_run_list+0x44/0x70
	 [<ffffffff8a17c8da>] irq_work_run+0x2a/0x50
	 [<ffffffff8a0f700b>] update_process_times+0x5b/0x70
	 [<ffffffff8a109005>] tick_sched_handle.isra.21+0x25/0x60
	 [<ffffffff8a109b81>] tick_sched_timer+0x41/0x60
	 [<ffffffff8a0f7aa2>] __run_hrtimer+0x72/0x470
	 [<ffffffff8a109b40>] ? tick_sched_do_timer+0xb0/0xb0
	 [<ffffffff8a0f8707>] hrtimer_interrupt+0x117/0x270
	 [<ffffffff8a034357>] local_apic_timer_interrupt+0x37/0x60
	 [<ffffffff8a80010f>] smp_apic_timer_interrupt+0x3f/0x50
	 [<ffffffff8a7fe52f>] apic_timer_interrupt+0x6f/0x80

To fix this we force non-lazy irq works to run on irq work self-IPIs
when available. That ability of the arch to trigger irq work self IPIs
is available with arch_irq_work_has_interrupt().

Reported-by: Catalin Iacob <iacobcatalin@gmail.com>
Reported-by: Dave Jones <davej@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 include/linux/irq_work.h |  1 +
 kernel/irq_work.c        | 15 +++++++++++++--
 kernel/time/timer.c      |  2 +-
 3 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 6b47b2ede405..bf3fe719c7ce 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -39,6 +39,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu);
 #endif
 
 void irq_work_run(void);
+void irq_work_tick(void);
 void irq_work_sync(struct irq_work *work);
 
 #ifdef CONFIG_IRQ_WORK
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index e6bcbe756663..385b85aded19 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -115,8 +115,10 @@ bool irq_work_needs_cpu(void)
 
 	raised = &__get_cpu_var(raised_list);
 	lazy = &__get_cpu_var(lazy_list);
-	if (llist_empty(raised) && llist_empty(lazy))
-		return false;
+
+	if (llist_empty(raised) || arch_irq_work_has_interrupt())
+		if (llist_empty(lazy))
+			return false;
 
 	/* All work should have been flushed before going offline */
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
@@ -171,6 +173,15 @@ void irq_work_run(void)
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
+void irq_work_tick(void)
+{
+	struct llist_head *raised = &__get_cpu_var(raised_list);
+
+	if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
+		irq_work_run_list(raised);
+	irq_work_run_list(&__get_cpu_var(lazy_list));
+}
+
 /*
  * Synchronize against the irq_work @entry, ensures the entry is not
  * currently in use.
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index aca5dfe2fa3d..9bbb8344ed3b 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1385,7 +1385,7 @@ void update_process_times(int user_tick)
 	rcu_check_callbacks(cpu, user_tick);
 #ifdef CONFIG_IRQ_WORK
 	if (in_irq())
-		irq_work_run();
+		irq_work_tick();
 #endif
 	scheduler_tick();
 	run_posix_cpu_timers(p);
-- 
cgit v1.2.3


From 23d0db76ffa13ffb95229946e4648568c3c29db5 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 13 Sep 2014 11:24:03 -0700
Subject: Make hash_64() use a 64-bit multiply when appropriate

The hash_64() function historically does the multiply by the
GOLDEN_RATIO_PRIME_64 number with explicit shifts and adds, because
unlike the 32-bit case, gcc seems unable to turn the constant multiply
into the more appropriate shift and adds when required.

However, that means that we generate those shifts and adds even when the
architecture has a fast multiplier, and could just do it better in
hardware.

Use the now-cleaned-up CONFIG_ARCH_HAS_FAST_MULTIPLIER (together with
"is it a 64-bit architecture") to decide whether to use an integer
multiply or the explicit sequence of shift/add instructions.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hash.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/hash.h b/include/linux/hash.h
index bd1754c7ecef..d0494c399392 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -37,6 +37,9 @@ static __always_inline u64 hash_64(u64 val, unsigned int bits)
 {
 	u64 hash = val;
 
+#if defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64
+	hash = hash * GOLDEN_RATIO_PRIME_64;
+#else
 	/*  Sigh, gcc can't optimise this alone like it does for 32 bits. */
 	u64 n = hash;
 	n <<= 18;
@@ -51,6 +54,7 @@ static __always_inline u64 hash_64(u64 val, unsigned int bits)
 	hash += n;
 	n <<= 2;
 	hash += n;
+#endif
 
 	/* High bits are more random, so use them. */
 	return hash >> (64 - bits);
-- 
cgit v1.2.3


From 6c555490e0ce885a9caf0a045db69382a3ccbc9c Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 11 Sep 2014 15:35:09 -0700
Subject: ipv6: drop useless rcu_read_lock() in anycast

These code is now protected by rtnl lock, rcu read lock
is useless now.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  4 ++--
 net/core/dev.c            | 14 ++++++++------
 net/ipv6/anycast.c        | 18 ++++++------------
 3 files changed, 16 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ae721f53739e..ee38b948d9a0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2083,8 +2083,8 @@ void __dev_remove_pack(struct packet_type *pt);
 void dev_add_offload(struct packet_offload *po);
 void dev_remove_offload(struct packet_offload *po);
 
-struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags,
-					unsigned short mask);
+struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
+				      unsigned short mask);
 struct net_device *dev_get_by_name(struct net *net, const char *name);
 struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
 struct net_device *__dev_get_by_name(struct net *net, const char *name);
diff --git a/net/core/dev.c b/net/core/dev.c
index b3d6dbc0c696..e916ba8caccf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -897,23 +897,25 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 EXPORT_SYMBOL(dev_getfirstbyhwtype);
 
 /**
- *	dev_get_by_flags_rcu - find any device with given flags
+ *	__dev_get_by_flags - find any device with given flags
  *	@net: the applicable net namespace
  *	@if_flags: IFF_* values
  *	@mask: bitmask of bits in if_flags to check
  *
  *	Search for any interface with the given flags. Returns NULL if a device
  *	is not found or a pointer to the device. Must be called inside
- *	rcu_read_lock(), and result refcount is unchanged.
+ *	rtnl_lock(), and result refcount is unchanged.
  */
 
-struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,
-				    unsigned short mask)
+struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags,
+				      unsigned short mask)
 {
 	struct net_device *dev, *ret;
 
+	ASSERT_RTNL();
+
 	ret = NULL;
-	for_each_netdev_rcu(net, dev) {
+	for_each_netdev(net, dev) {
 		if (((dev->flags ^ if_flags) & mask) == 0) {
 			ret = dev;
 			break;
@@ -921,7 +923,7 @@ struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags
 	}
 	return ret;
 }
-EXPORT_SYMBOL(dev_get_by_flags_rcu);
+EXPORT_SYMBOL(__dev_get_by_flags);
 
 /**
  *	dev_valid_name - check if name is okay for network device
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index ff2de7d9d8e6..3b0429bc6b5a 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -78,7 +78,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	pac->acl_addr = *addr;
 
 	rtnl_lock();
-	rcu_read_lock();
 	if (ifindex == 0) {
 		struct rt6_info *rt;
 
@@ -91,11 +90,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			goto error;
 		} else {
 			/* router, no matching interface: just pick one */
-			dev = dev_get_by_flags_rcu(net, IFF_UP,
-						   IFF_UP | IFF_LOOPBACK);
+			dev = __dev_get_by_flags(net, IFF_UP,
+						 IFF_UP | IFF_LOOPBACK);
 		}
 	} else
-		dev = dev_get_by_index_rcu(net, ifindex);
+		dev = __dev_get_by_index(net, ifindex);
 
 	if (dev == NULL) {
 		err = -ENODEV;
@@ -137,7 +136,6 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	}
 
 error:
-	rcu_read_unlock();
 	rtnl_unlock();
 	if (pac)
 		sock_kfree_s(sk, pac, sizeof(*pac));
@@ -174,11 +172,9 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	spin_unlock_bh(&ipv6_sk_ac_lock);
 
 	rtnl_lock();
-	rcu_read_lock();
-	dev = dev_get_by_index_rcu(net, pac->acl_ifindex);
+	dev = __dev_get_by_index(net, pac->acl_ifindex);
 	if (dev)
 		ipv6_dev_ac_dec(dev, &pac->acl_addr);
-	rcu_read_unlock();
 	rtnl_unlock();
 
 	sock_kfree_s(sk, pac, sizeof(*pac));
@@ -203,12 +199,11 @@ void ipv6_sock_ac_close(struct sock *sk)
 
 	prev_index = 0;
 	rtnl_lock();
-	rcu_read_lock();
 	while (pac) {
 		struct ipv6_ac_socklist *next = pac->acl_next;
 
 		if (pac->acl_ifindex != prev_index) {
-			dev = dev_get_by_index_rcu(net, pac->acl_ifindex);
+			dev = __dev_get_by_index(net, pac->acl_ifindex);
 			prev_index = pac->acl_ifindex;
 		}
 		if (dev)
@@ -216,7 +211,6 @@ void ipv6_sock_ac_close(struct sock *sk)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 		pac = next;
 	}
-	rcu_read_unlock();
 	rtnl_unlock();
 }
 
@@ -341,7 +335,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 	return 0;
 }
 
-/* called with rcu_read_lock() */
+/* called with rtnl_lock() */
 static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct inet6_dev *idev = __in6_dev_get(dev);
-- 
cgit v1.2.3


From 013b4d90387a5dca54281263e0d4650db97bd67c Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 11 Sep 2014 15:35:11 -0700
Subject: ipv6: clean up ipv6_dev_ac_inc()

Make it accept inet6_dev, and rename it to __ipv6_dev_ac_inc()
to reflect this change.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h |  2 +-
 net/ipv6/addrconf.c    |  2 +-
 net/ipv6/anycast.c     | 13 ++++---------
 3 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f679877bb601..9b1d42e66cca 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -202,7 +202,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 void ipv6_sock_ac_close(struct sock *sk);
 
-int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr);
+int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr);
 int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr);
 bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 			 const struct in6_addr *addr);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ad4598fcc416..6b6a373a30b2 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1725,7 +1725,7 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
 	if (ipv6_addr_any(&addr))
 		return;
-	ipv6_dev_ac_inc(ifp->idev->dev, &addr);
+	__ipv6_dev_ac_inc(ifp->idev, &addr);
 }
 
 /* caller must hold RTNL */
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index d10f2e2b49c6..66c19320119a 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -122,7 +122,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			goto error;
 	}
 
-	err = ipv6_dev_ac_inc(dev, addr);
+	err = __ipv6_dev_ac_inc(idev, addr);
 	if (!err) {
 		pac->acl_next = np->ipv6_ac_list;
 		np->ipv6_ac_list = pac;
@@ -215,20 +215,15 @@ static void aca_put(struct ifacaddr6 *ac)
 /*
  *	device anycast group inc (add if not found)
  */
-int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr)
+int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct ifacaddr6 *aca;
-	struct inet6_dev *idev;
 	struct rt6_info *rt;
 	int err;
 
 	ASSERT_RTNL();
 
-	idev = in6_dev_get(dev);
-
-	if (idev == NULL)
-		return -EINVAL;
-
+	in6_dev_hold(idev);
 	write_lock_bh(&idev->lock);
 	if (idev->dead) {
 		err = -ENODEV;
@@ -276,7 +271,7 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr)
 
 	ip6_ins_rt(rt);
 
-	addrconf_join_solict(dev, &aca->aca_addr);
+	addrconf_join_solict(idev->dev, &aca->aca_addr);
 
 	aca_put(aca);
 	return 0;
-- 
cgit v1.2.3


From ac7a04c33dd7f8e429df4b929ba3a3e8e729cc89 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 11 Sep 2014 21:18:09 -0700
Subject: net: dsa: change tag_protocol to an enum

Now that we introduced an additional multiplexing/demultiplexing layer
with commit 3e8a72d1dae37 ("net: dsa: reduce number of protocol hooks")
that lives within the DSA code, we no longer need to have a given switch
driver tag_protocol be an actual ethertype value, instead, we can
replace it with an enum: dsa_tag_protocol.

Do this replacement in the drivers, which allows us to get rid of the
cpu_to_be16()/htons() dance, and remove ETH_P_BRCMTAG since we do not
need it anymore.

Suggested-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c         |  2 +-
 drivers/net/dsa/mv88e6060.c       |  2 +-
 drivers/net/dsa/mv88e6123_61_65.c |  4 ++--
 drivers/net/dsa/mv88e6131.c       |  2 +-
 include/net/dsa.h                 | 17 ++++++++++-------
 net/dsa/slave.c                   |  8 ++++----
 net/dsa/tag_brcm.c                |  1 -
 7 files changed, 19 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index bb7cb8e283b1..e9918c7f1792 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -592,7 +592,7 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 }
 
 static struct dsa_switch_driver bcm_sf2_switch_driver = {
-	.tag_protocol		= htons(ETH_P_BRCMTAG),
+	.tag_protocol		= DSA_TAG_PROTO_BRCM,
 	.priv_size		= sizeof(struct bcm_sf2_priv),
 	.probe			= bcm_sf2_sw_probe,
 	.setup			= bcm_sf2_sw_setup,
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index 7a54ec04b418..d8037c1055ac 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -258,7 +258,7 @@ static void mv88e6060_poll_link(struct dsa_switch *ds)
 }
 
 static struct dsa_switch_driver mv88e6060_switch_driver = {
-	.tag_protocol	= htons(ETH_P_TRAILER),
+	.tag_protocol	= DSA_TAG_PROTO_TRAILER,
 	.probe		= mv88e6060_probe,
 	.setup		= mv88e6060_setup,
 	.set_addr	= mv88e6060_set_addr,
diff --git a/drivers/net/dsa/mv88e6123_61_65.c b/drivers/net/dsa/mv88e6123_61_65.c
index 69c42513dd72..975774f338c2 100644
--- a/drivers/net/dsa/mv88e6123_61_65.c
+++ b/drivers/net/dsa/mv88e6123_61_65.c
@@ -207,7 +207,7 @@ static int mv88e6123_61_65_setup_port(struct dsa_switch *ds, int p)
 	 */
 	val = 0x0433;
 	if (dsa_is_cpu_port(ds, p)) {
-		if (ds->dst->tag_protocol == htons(ETH_P_EDSA))
+		if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA)
 			val |= 0x3300;
 		else
 			val |= 0x0100;
@@ -391,7 +391,7 @@ static int mv88e6123_61_65_get_sset_count(struct dsa_switch *ds)
 }
 
 struct dsa_switch_driver mv88e6123_61_65_switch_driver = {
-	.tag_protocol		= cpu_to_be16(ETH_P_EDSA),
+	.tag_protocol		= DSA_TAG_PROTO_EDSA,
 	.priv_size		= sizeof(struct mv88e6xxx_priv_state),
 	.probe			= mv88e6123_61_65_probe,
 	.setup			= mv88e6123_61_65_setup,
diff --git a/drivers/net/dsa/mv88e6131.c b/drivers/net/dsa/mv88e6131.c
index 953bc6a49e59..35541f2ceca3 100644
--- a/drivers/net/dsa/mv88e6131.c
+++ b/drivers/net/dsa/mv88e6131.c
@@ -379,7 +379,7 @@ static int mv88e6131_get_sset_count(struct dsa_switch *ds)
 }
 
 struct dsa_switch_driver mv88e6131_switch_driver = {
-	.tag_protocol		= cpu_to_be16(ETH_P_DSA),
+	.tag_protocol		= DSA_TAG_PROTO_DSA,
 	.priv_size		= sizeof(struct mv88e6xxx_priv_state),
 	.probe			= mv88e6131_probe,
 	.setup			= mv88e6131_setup,
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 97712927a9d2..8a8a5d976f97 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -19,10 +19,13 @@
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
 
-/* Not an official ethertype value, used only internally for DSA
- * demultiplexing
- */
-#define ETH_P_BRCMTAG		(ETH_P_XDSA + 1)
+enum dsa_tag_protocol {
+	DSA_TAG_PROTO_NONE = 0,
+	DSA_TAG_PROTO_DSA,
+	DSA_TAG_PROTO_TRAILER,
+	DSA_TAG_PROTO_EDSA,
+	DSA_TAG_PROTO_BRCM,
+};
 
 #define DSA_MAX_SWITCHES	4
 #define DSA_MAX_PORTS		12
@@ -89,7 +92,7 @@ struct dsa_switch_tree {
 	 */
 	struct net_device	*master_netdev;
 	const struct dsa_device_ops	*ops;
-	__be16			tag_protocol;
+	enum dsa_tag_protocol	tag_protocol;
 
 	/*
 	 * The switch and port to which the CPU is attached.
@@ -166,7 +169,7 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds)
 struct dsa_switch_driver {
 	struct list_head	list;
 
-	__be16			tag_protocol;
+	enum dsa_tag_protocol	tag_protocol;
 	int			priv_size;
 
 	/*
@@ -215,7 +218,7 @@ static inline void *ds_to_priv(struct dsa_switch *ds)
 
 static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst)
 {
-	return dst->tag_protocol != 0;
+	return dst->tag_protocol != DSA_TAG_PROTO_NONE;
 }
 
 #endif
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 7333a4aebb7d..809eeb13eb12 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -437,22 +437,22 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 
 	switch (ds->dst->tag_protocol) {
 #ifdef CONFIG_NET_DSA_TAG_DSA
-	case htons(ETH_P_DSA):
+	case DSA_TAG_PROTO_DSA:
 		ds->dst->ops = &dsa_netdev_ops;
 		break;
 #endif
 #ifdef CONFIG_NET_DSA_TAG_EDSA
-	case htons(ETH_P_EDSA):
+	case DSA_TAG_PROTO_EDSA:
 		ds->dst->ops = &edsa_netdev_ops;
 		break;
 #endif
 #ifdef CONFIG_NET_DSA_TAG_TRAILER
-	case htons(ETH_P_TRAILER):
+	case DSA_TAG_PROTO_TRAILER:
 		ds->dst->ops = &trailer_netdev_ops;
 		break;
 #endif
 #ifdef CONFIG_NET_DSA_TAG_BRCM
-	case htons(ETH_P_BRCMTAG):
+	case DSA_TAG_PROTO_BRCM:
 		ds->dst->ops = &brcm_netdev_ops;
 		break;
 #endif
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index e0b759ec209e..8fbc21c0de78 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -91,7 +91,6 @@ static netdev_tx_t brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Queue the SKB for transmission on the parent interface, but
 	 * do not modify its EtherType
 	 */
-	skb->protocol = htons(ETH_P_BRCMTAG);
 	skb->dev = p->parent->dst->master_netdev;
 	dev_queue_xmit(skb);
 
-- 
cgit v1.2.3


From 233577a22089facf5271ab5e845b2262047c971f Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Fri, 12 Sep 2014 14:04:43 +0200
Subject: net: filter: constify detection of pkt_type_offset

Currently we have 2 pkt_type_offset functions doing the same thing and
spread across the architecture files. Remove those and replace them
with a PKT_TYPE_OFFSET macro helper which gets the constant value from a
zero sized sk_buff member right in front of the bitfield with offsetof.
This new offset marker does not change size of struct sk_buff.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Markos Chandras <markos.chandras@imgtec.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Daniel Borkmann <dborkman@redhat.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Denis Kirjanov <kda@linux-powerpc.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/mips/net/bpf_jit.c      | 27 +--------------------------
 arch/s390/net/bpf_jit_comp.c | 35 +----------------------------------
 include/linux/skbuff.h       | 10 ++++++++++
 net/core/filter.c            | 31 ++-----------------------------
 4 files changed, 14 insertions(+), 89 deletions(-)

(limited to 'include')

diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 0e97ccd29fe3..7edc08398c4a 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -765,27 +765,6 @@ static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
 	return (u64)err << 32 | ntohl(ret);
 }
 
-#ifdef __BIG_ENDIAN_BITFIELD
-#define PKT_TYPE_MAX	(7 << 5)
-#else
-#define PKT_TYPE_MAX	7
-#endif
-static int pkt_type_offset(void)
-{
-	struct sk_buff skb_probe = {
-		.pkt_type = ~0,
-	};
-	u8 *ct = (u8 *)&skb_probe;
-	unsigned int off;
-
-	for (off = 0; off < sizeof(struct sk_buff); off++) {
-		if (ct[off] == PKT_TYPE_MAX)
-			return off;
-	}
-	pr_err_once("Please fix pkt_type_offset(), as pkt_type couldn't be found\n");
-	return -1;
-}
-
 static int build_body(struct jit_ctx *ctx)
 {
 	void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w};
@@ -1332,11 +1311,7 @@ jmp_cmp:
 		case BPF_ANC | SKF_AD_PKTTYPE:
 			ctx->flags |= SEEN_SKB;
 
-			off = pkt_type_offset();
-
-			if (off < 0)
-				return -1;
-			emit_load_byte(r_tmp, r_skb, off, ctx);
+			emit_load_byte(r_tmp, r_skb, PKT_TYPE_OFFSET(), ctx);
 			/* Keep only the last 3 bits */
 			emit_andi(r_A, r_tmp, PKT_TYPE_MAX, ctx);
 #ifdef __BIG_ENDIAN_BITFIELD
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 555f5c7e83ab..c52ac77408ca 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -227,37 +227,6 @@ static void bpf_jit_epilogue(struct bpf_jit *jit)
 	EMIT2(0x07fe);
 }
 
-/* Helper to find the offset of pkt_type in sk_buff
- * Make sure its still a 3bit field starting at the MSBs within a byte.
- */
-#define PKT_TYPE_MAX 0xe0
-static int pkt_type_offset;
-
-static int __init bpf_pkt_type_offset_init(void)
-{
-	struct sk_buff skb_probe = {
-		.pkt_type = ~0,
-	};
-	char *ct = (char *)&skb_probe;
-	int off;
-
-	pkt_type_offset = -1;
-	for (off = 0; off < sizeof(struct sk_buff); off++) {
-		if (!ct[off])
-			continue;
-		if (ct[off] == PKT_TYPE_MAX)
-			pkt_type_offset = off;
-		else {
-			/* Found non matching bit pattern, fix needed. */
-			WARN_ON_ONCE(1);
-			pkt_type_offset = -1;
-			return -1;
-		}
-	}
-	return 0;
-}
-device_initcall(bpf_pkt_type_offset_init);
-
 /*
  * make sure we dont leak kernel information to user
  */
@@ -757,12 +726,10 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		}
 		break;
 	case BPF_ANC | SKF_AD_PKTTYPE:
-		if (pkt_type_offset < 0)
-			goto out;
 		/* lhi %r5,0 */
 		EMIT4(0xa7580000);
 		/* ic %r5,<d(pkt_type_offset)>(%r2) */
-		EMIT4_DISP(0x43502000, pkt_type_offset);
+		EMIT4_DISP(0x43502000, PKT_TYPE_OFFSET());
 		/* srl %r5,5 */
 		EMIT4_DISP(0x88500000, 5);
 		break;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 07c9fdd0c126..756e3d057e84 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -548,6 +548,16 @@ struct sk_buff {
 				ip_summed:2,
 				nohdr:1,
 				nfctinfo:3;
+
+/* if you move pkt_type around you also must adapt those constants */
+#ifdef __BIG_ENDIAN_BITFIELD
+#define PKT_TYPE_MAX	(7 << 5)
+#else
+#define PKT_TYPE_MAX	7
+#endif
+#define PKT_TYPE_OFFSET()	offsetof(struct sk_buff, __pkt_type_offset)
+
+	__u8			__pkt_type_offset[0];
 	__u8			pkt_type:3,
 				fclone:2,
 				ipvs_property:1,
diff --git a/net/core/filter.c b/net/core/filter.c
index dfc716ffa44b..601f28de7311 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -87,30 +87,6 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sk_filter);
 
-/* Helper to find the offset of pkt_type in sk_buff structure. We want
- * to make sure its still a 3bit field starting at a byte boundary;
- * taken from arch/x86/net/bpf_jit_comp.c.
- */
-#ifdef __BIG_ENDIAN_BITFIELD
-#define PKT_TYPE_MAX	(7 << 5)
-#else
-#define PKT_TYPE_MAX	7
-#endif
-static unsigned int pkt_type_offset(void)
-{
-	struct sk_buff skb_probe = { .pkt_type = ~0, };
-	u8 *ct = (u8 *) &skb_probe;
-	unsigned int off;
-
-	for (off = 0; off < sizeof(struct sk_buff); off++) {
-		if (ct[off] == PKT_TYPE_MAX)
-			return off;
-	}
-
-	pr_err_once("Please fix %s, as pkt_type couldn't be found!\n", __func__);
-	return -1;
-}
-
 static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {
 	return skb_get_poff((struct sk_buff *)(unsigned long) ctx);
@@ -190,11 +166,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
 		break;
 
 	case SKF_AD_OFF + SKF_AD_PKTTYPE:
-		*insn = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX,
-				    pkt_type_offset());
-		if (insn->off < 0)
-			return false;
-		insn++;
+		*insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX,
+				      PKT_TYPE_OFFSET());
 		*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX);
 #ifdef __BIG_ENDIAN_BITFIELD
 		insn++;
-- 
cgit v1.2.3


From 3fc8867740b4a0bf56f372c6f5ddd14970962fb1 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Fri, 12 Sep 2014 23:12:46 -0700
Subject: netdevice: Support DSA tagging when DSA is built as a module

This change corrects an error seen when DSA tagging is built as a module.
Without this change it is not possible to get XDSA tagged frames as the
test for tagging is stripped by the #ifdef check.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ee38b948d9a0..f9e81d10a3b9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1789,7 +1789,7 @@ void dev_net_set(struct net_device *dev, struct net *net)
 
 static inline bool netdev_uses_dsa(struct net_device *dev)
 {
-#ifdef CONFIG_NET_DSA
+#if IS_ENABLED(CONFIG_NET_DSA)
 	if (dev->dsa_ptr != NULL)
 		return dsa_uses_tagged_protocol(dev->dsa_ptr);
 #endif
-- 
cgit v1.2.3


From 9226b5b440f2b4fbb3b797f3cb74a9a627220660 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 14 Sep 2014 17:28:32 -0700
Subject: vfs: avoid non-forwarding large load after small store in path lookup

The performance regression that Josef Bacik reported in the pathname
lookup (see commit 99d263d4c5b2 "vfs: fix bad hashing of dentries") made
me look at performance stability of the dcache code, just to verify that
the problem was actually fixed.  That turned up a few other problems in
this area.

There are a few cases where we exit RCU lookup mode and go to the slow
serializing case when we shouldn't, Al has fixed those and they'll come
in with the next VFS pull.

But my performance verification also shows that link_path_walk() turns
out to have a very unfortunate 32-bit store of the length and hash of
the name we look up, followed by a 64-bit read of the combined hash_len
field.  That screws up the processor store to load forwarding, causing
an unnecessary hickup in this critical routine.

It's caused by the ugly calling convention for the "hash_name()"
function, and easily fixed by just making hash_name() fill in the whole
'struct qstr' rather than passing it a pointer to just the hash value.

With that, the profile for this function looks much smoother.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/namei.c             | 19 ++++++++++---------
 include/linux/dcache.h |  1 +
 2 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 229235862e50..2be5120b81b3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1669,13 +1669,14 @@ EXPORT_SYMBOL(full_name_hash);
 
 /*
  * Calculate the length and hash of the path component, and
- * return the length of the component;
+ * fill in the qstr. return the "len" as the result.
  */
-static inline unsigned long hash_name(const char *name, unsigned int *hashp)
+static inline unsigned long hash_name(const char *name, struct qstr *res)
 {
 	unsigned long a, b, adata, bdata, mask, hash, len;
 	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
 
+	res->name = name;
 	hash = a = 0;
 	len = -sizeof(unsigned long);
 	do {
@@ -1691,9 +1692,10 @@ static inline unsigned long hash_name(const char *name, unsigned int *hashp)
 	mask = create_zero_mask(adata | bdata);
 
 	hash += a & zero_bytemask(mask);
-	*hashp = fold_hash(hash);
+	len += find_zero(mask);
+	res->hash_len = hashlen_create(fold_hash(hash), len);
 
-	return len + find_zero(mask);
+	return len;
 }
 
 #else
@@ -1711,18 +1713,19 @@ EXPORT_SYMBOL(full_name_hash);
  * We know there's a real path component here of at least
  * one character.
  */
-static inline unsigned long hash_name(const char *name, unsigned int *hashp)
+static inline long hash_name(const char *name, struct qstr *res)
 {
 	unsigned long hash = init_name_hash();
 	unsigned long len = 0, c;
 
+	res->name = name;
 	c = (unsigned char)*name;
 	do {
 		len++;
 		hash = partial_name_hash(c, hash);
 		c = (unsigned char)name[len];
 	} while (c && c != '/');
-	*hashp = end_name_hash(hash);
+	res->hash_len = hashlen_create(end_name_hash(hash), len);
 	return len;
 }
 
@@ -1756,9 +1759,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
  		if (err)
 			break;
 
-		len = hash_name(name, &this.hash);
-		this.name = name;
-		this.len = len;
+		len = hash_name(name, &this);
 
 		type = LAST_NORM;
 		if (name[0] == '.') switch (len) {
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index e4ae2ad48d07..75a227cc7ce2 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -55,6 +55,7 @@ struct qstr {
 #define QSTR_INIT(n,l) { { { .len = l } }, .name = n }
 #define hashlen_hash(hashlen) ((u32) (hashlen))
 #define hashlen_len(hashlen)  ((u32)((hashlen) >> 32))
+#define hashlen_create(hash,len) (((u64)(len)<<32)|(u32)(hash))
 
 struct dentry_stat_t {
 	long nr_dentry;
-- 
cgit v1.2.3


From 43e73e4e2ad05d9bf3b438cfbe1e71b57a85f26c Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 14 Sep 2014 23:06:28 +0200
Subject: Bluetooth: Provide HCI command opcode information to driver

The Bluetooth core already does processing of the HCI command header
and puts it together before sending it to the driver. It is not really
efficient for the driver to look at the HCI command header again in
case it has to make certain decisions about certain commands. To make
this easier, just provide the opcode as part of the SKB control buffer
information. The extra information about the opcode is optional and
only provided for HCI commands.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/bluetooth.h | 1 +
 net/bluetooth/hci_core.c          | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 373000de610d..7e666d06b97f 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -284,6 +284,7 @@ struct hci_req_ctrl {
 struct bt_skb_cb {
 	__u8 pkt_type;
 	__u8 incoming;
+	__u16 opcode;
 	__u16 expect;
 	__u8 force_active;
 	struct l2cap_chan *chan;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 067526d9680d..41948678f514 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -4547,6 +4547,7 @@ static struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode,
 	BT_DBG("skb len %d", skb->len);
 
 	bt_cb(skb)->pkt_type = HCI_COMMAND_PKT;
+	bt_cb(skb)->opcode = opcode;
 
 	return skb;
 }
-- 
cgit v1.2.3


From 1d46fea7d091f9dc2d4fd3fcb9f0117ca288f9a5 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Wed, 27 Aug 2014 00:42:56 +0200
Subject: drm/rcar-du: Use struct videomode in platform data

In preparation for DT support where panel timings will be described by a
DRM-agnostic video mode, replace the struct drm_mode_modeinfo instance
in the panel platform data with a struct videomode.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
 arch/arm/mach-shmobile/board-koelsch-reference.c | 19 +++++++++----------
 arch/arm/mach-shmobile/board-koelsch.c           | 19 +++++++++----------
 arch/arm/mach-shmobile/board-lager-reference.c   | 19 +++++++++----------
 arch/arm/mach-shmobile/board-lager.c             | 19 +++++++++----------
 arch/arm/mach-shmobile/board-marzen.c            | 19 +++++++++----------
 drivers/gpu/drm/rcar-du/Kconfig                  |  1 +
 drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c        | 15 +++------------
 include/linux/platform_data/rcar-du.h            |  4 ++--
 8 files changed, 51 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-shmobile/board-koelsch-reference.c b/arch/arm/mach-shmobile/board-koelsch-reference.c
index 3ff88c138896..364e69bf85d4 100644
--- a/arch/arm/mach-shmobile/board-koelsch-reference.c
+++ b/arch/arm/mach-shmobile/board-koelsch-reference.c
@@ -41,16 +41,15 @@ static struct rcar_du_encoder_data koelsch_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-koelsch.c b/arch/arm/mach-shmobile/board-koelsch.c
index b7d5bc7659cd..ad10ddb6a321 100644
--- a/arch/arm/mach-shmobile/board-koelsch.c
+++ b/arch/arm/mach-shmobile/board-koelsch.c
@@ -63,16 +63,15 @@ static struct rcar_du_encoder_data koelsch_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-lager-reference.c b/arch/arm/mach-shmobile/board-lager-reference.c
index 41c808e56005..12a53a1c3d02 100644
--- a/arch/arm/mach-shmobile/board-lager-reference.c
+++ b/arch/arm/mach-shmobile/board-lager-reference.c
@@ -43,16 +43,15 @@ static struct rcar_du_encoder_data lager_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index e1d8215da0b0..80576c2ee668 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -99,16 +99,15 @@ static struct rcar_du_encoder_data lager_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index e5cf4201e769..ce33d7825c49 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -192,16 +192,15 @@ static struct rcar_du_encoder_data du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index 2e3d7b5b0ad7..c96f6089f8bf 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -6,6 +6,7 @@ config DRM_RCAR_DU
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_FB_HELPER
+	select VIDEOMODE_HELPERS
 	help
 	  Choose this option if you have an R-Car chipset.
 	  If M is selected the module will be called rcar-du-drm.
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
index cfcf6e74ad0a..d29544121658 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
@@ -40,18 +40,9 @@ static int rcar_du_lvds_connector_get_modes(struct drm_connector *connector)
 		return 0;
 
 	mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER;
-	mode->clock = lvdscon->panel->mode.clock;
-	mode->hdisplay = lvdscon->panel->mode.hdisplay;
-	mode->hsync_start = lvdscon->panel->mode.hsync_start;
-	mode->hsync_end = lvdscon->panel->mode.hsync_end;
-	mode->htotal = lvdscon->panel->mode.htotal;
-	mode->vdisplay = lvdscon->panel->mode.vdisplay;
-	mode->vsync_start = lvdscon->panel->mode.vsync_start;
-	mode->vsync_end = lvdscon->panel->mode.vsync_end;
-	mode->vtotal = lvdscon->panel->mode.vtotal;
-	mode->flags = lvdscon->panel->mode.flags;
-
-	drm_mode_set_name(mode);
+
+	drm_display_mode_from_videomode(&lvdscon->panel->mode, mode);
+
 	drm_mode_probed_add(connector, mode);
 
 	return 1;
diff --git a/include/linux/platform_data/rcar-du.h b/include/linux/platform_data/rcar-du.h
index 1a2e9901a22e..a5f045e1d8fe 100644
--- a/include/linux/platform_data/rcar-du.h
+++ b/include/linux/platform_data/rcar-du.h
@@ -14,7 +14,7 @@
 #ifndef __RCAR_DU_H__
 #define __RCAR_DU_H__
 
-#include <drm/drm_mode.h>
+#include <video/videomode.h>
 
 enum rcar_du_output {
 	RCAR_DU_OUTPUT_DPAD0,
@@ -35,7 +35,7 @@ enum rcar_du_encoder_type {
 struct rcar_du_panel_data {
 	unsigned int width_mm;		/* Panel width in mm */
 	unsigned int height_mm;		/* Panel height in mm */
-	struct drm_mode_modeinfo mode;
+	struct videomode mode;
 };
 
 struct rcar_du_connector_lvds_data {
-- 
cgit v1.2.3


From db0a5214b8d6cc7a90ce3336d24a85b90cbb4e67 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 9 Sep 2014 17:17:20 +0200
Subject: ALSA: vx: Use nonatomic PCM ops

Rewrite VXpocket and VX222 drivers to use the new PCM nonatomic ops.
The former irq tasklet is replaced with a threaded irq handler, and
the tasklet for the PCM delayed start is simply merged into the normal
PCM trigger, as well as the replacement of spinlock with mutex.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/vx_core.h     |  7 ++---
 sound/drivers/vx/vx_core.c  | 49 +++++++++++++++-----------------
 sound/drivers/vx/vx_mixer.c | 12 +++-----
 sound/drivers/vx/vx_pcm.c   | 68 +++++++++++++++------------------------------
 sound/drivers/vx/vx_uer.c   | 23 +++++++--------
 sound/pci/vx222/vx222.c     |  5 ++--
 sound/pcmcia/vx/vxp_ops.c   | 10 +++----
 sound/pcmcia/vx/vxpocket.c  | 13 ++++++---
 8 files changed, 78 insertions(+), 109 deletions(-)

(limited to 'include')

diff --git a/include/sound/vx_core.h b/include/sound/vx_core.h
index f634f8f85db5..cae9c9d4ef22 100644
--- a/include/sound/vx_core.h
+++ b/include/sound/vx_core.h
@@ -80,8 +80,6 @@ struct vx_pipe {
 
 	unsigned int references;     /* an output pipe may be used for monitoring and/or playback */
 	struct vx_pipe *monitoring_pipe;  /* pointer to the monitoring pipe (capture pipe only)*/
-
-	struct tasklet_struct start_tq;
 };
 
 struct vx_core;
@@ -165,9 +163,7 @@ struct vx_core {
 	struct snd_vx_hardware *hw;
 	struct snd_vx_ops *ops;
 
-	spinlock_t lock;
-	spinlock_t irq_lock;
-	struct tasklet_struct tq;
+	struct mutex lock;
 
 	unsigned int chip_status;
 	unsigned int pcm_running;
@@ -223,6 +219,7 @@ void snd_vx_free_firmware(struct vx_core *chip);
  * interrupt handler; exported for pcmcia
  */
 irqreturn_t snd_vx_irq_handler(int irq, void *dev);
+irqreturn_t snd_vx_threaded_irq_handler(int irq, void *dev);
 
 /*
  * lowlevel functions
diff --git a/sound/drivers/vx/vx_core.c b/sound/drivers/vx/vx_core.c
index 83596891cde4..e8cc16993903 100644
--- a/sound/drivers/vx/vx_core.c
+++ b/sound/drivers/vx/vx_core.c
@@ -117,7 +117,7 @@ static int vx_reset_chk(struct vx_core *chip)
  *
  * returns 0 if successful, or a negative error code.
  * the error code can be VX-specific, retrieved via vx_get_error().
- * NB: call with spinlock held!
+ * NB: call with mutex held!
  */
 static int vx_transfer_end(struct vx_core *chip, int cmd)
 {
@@ -155,7 +155,7 @@ static int vx_transfer_end(struct vx_core *chip, int cmd)
  *
  * returns 0 if successful, or a negative error code.
  * the error code can be VX-specific, retrieved via vx_get_error().
- * NB: call with spinlock held!
+ * NB: call with mutex held!
  */
 static int vx_read_status(struct vx_core *chip, struct vx_rmh *rmh)
 {
@@ -236,7 +236,7 @@ static int vx_read_status(struct vx_core *chip, struct vx_rmh *rmh)
  * returns 0 if successful, or a negative error code.
  * the error code can be VX-specific, retrieved via vx_get_error().
  * 
- * this function doesn't call spinlock at all.
+ * this function doesn't call mutex lock at all.
  */
 int vx_send_msg_nolock(struct vx_core *chip, struct vx_rmh *rmh)
 {
@@ -337,7 +337,7 @@ int vx_send_msg_nolock(struct vx_core *chip, struct vx_rmh *rmh)
 
 
 /*
- * vx_send_msg - send a DSP message with spinlock
+ * vx_send_msg - send a DSP message with mutex
  * @rmh: the rmh record to send and receive
  *
  * returns 0 if successful, or a negative error code.
@@ -345,12 +345,11 @@ int vx_send_msg_nolock(struct vx_core *chip, struct vx_rmh *rmh)
  */
 int vx_send_msg(struct vx_core *chip, struct vx_rmh *rmh)
 {
-	unsigned long flags;
 	int err;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	err = vx_send_msg_nolock(chip, rmh);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 	return err;
 }
 
@@ -362,7 +361,7 @@ int vx_send_msg(struct vx_core *chip, struct vx_rmh *rmh)
  * returns 0 if successful, or a negative error code.
  * the error code can be VX-specific, retrieved via vx_get_error().
  *
- * this function doesn't call spinlock at all.
+ * this function doesn't call mutex at all.
  *
  * unlike RMH, no command is sent to DSP.
  */
@@ -398,19 +397,18 @@ int vx_send_rih_nolock(struct vx_core *chip, int cmd)
 
 
 /*
- * vx_send_rih - send an RIH with spinlock
+ * vx_send_rih - send an RIH with mutex
  * @cmd: the command to send
  *
  * see vx_send_rih_nolock().
  */
 int vx_send_rih(struct vx_core *chip, int cmd)
 {
-	unsigned long flags;
 	int err;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	err = vx_send_rih_nolock(chip, cmd);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 	return err;
 }
 
@@ -482,30 +480,30 @@ static int vx_test_irq_src(struct vx_core *chip, unsigned int *ret)
 	int err;
 
 	vx_init_rmh(&chip->irq_rmh, CMD_TEST_IT);
-	spin_lock(&chip->lock);
+	mutex_lock(&chip->lock);
 	err = vx_send_msg_nolock(chip, &chip->irq_rmh);
 	if (err < 0)
 		*ret = 0;
 	else
 		*ret = chip->irq_rmh.Stat[0];
-	spin_unlock(&chip->lock);
+	mutex_unlock(&chip->lock);
 	return err;
 }
 
 
 /*
- * vx_interrupt - soft irq handler
+ * snd_vx_threaded_irq_handler - threaded irq handler
  */
-static void vx_interrupt(unsigned long private_data)
+irqreturn_t snd_vx_threaded_irq_handler(int irq, void *dev)
 {
-	struct vx_core *chip = (struct vx_core *) private_data;
+	struct vx_core *chip = dev;
 	unsigned int events;
 		
 	if (chip->chip_status & VX_STAT_IS_STALE)
-		return;
+		return IRQ_HANDLED;
 
 	if (vx_test_irq_src(chip, &events) < 0)
-		return;
+		return IRQ_HANDLED;
     
 #if 0
 	if (events & 0x000800)
@@ -519,7 +517,7 @@ static void vx_interrupt(unsigned long private_data)
 	 */
 	if (events & FATAL_DSP_ERROR) {
 		snd_printk(KERN_ERR "vx_core: fatal DSP error!!\n");
-		return;
+		return IRQ_HANDLED;
 	}
 
 	/* The start on time code conditions are filled (ie the time code
@@ -534,8 +532,9 @@ static void vx_interrupt(unsigned long private_data)
 
 	/* update the pcm streams */
 	vx_pcm_update_intr(chip, events);
+	return IRQ_HANDLED;
 }
-
+EXPORT_SYMBOL(snd_vx_threaded_irq_handler);
 
 /**
  * snd_vx_irq_handler - interrupt handler
@@ -548,8 +547,8 @@ irqreturn_t snd_vx_irq_handler(int irq, void *dev)
 	    (chip->chip_status & VX_STAT_IS_STALE))
 		return IRQ_NONE;
 	if (! vx_test_and_ack(chip))
-		tasklet_schedule(&chip->tq);
-	return IRQ_HANDLED;
+		return IRQ_WAKE_THREAD;
+	return IRQ_NONE;
 }
 
 EXPORT_SYMBOL(snd_vx_irq_handler);
@@ -790,13 +789,11 @@ struct vx_core *snd_vx_create(struct snd_card *card, struct snd_vx_hardware *hw,
 		snd_printk(KERN_ERR "vx_core: no memory\n");
 		return NULL;
 	}
-	spin_lock_init(&chip->lock);
-	spin_lock_init(&chip->irq_lock);
+	mutex_init(&chip->lock);
 	chip->irq = -1;
 	chip->hw = hw;
 	chip->type = hw->type;
 	chip->ops = ops;
-	tasklet_init(&chip->tq, vx_interrupt, (unsigned long)chip);
 	mutex_init(&chip->mixer_mutex);
 
 	chip->card = card;
diff --git a/sound/drivers/vx/vx_mixer.c b/sound/drivers/vx/vx_mixer.c
index c71b8d148d7f..3b6823fc0606 100644
--- a/sound/drivers/vx/vx_mixer.c
+++ b/sound/drivers/vx/vx_mixer.c
@@ -32,17 +32,15 @@
  */
 static void vx_write_codec_reg(struct vx_core *chip, int codec, unsigned int data)
 {
-	unsigned long flags;
-
 	if (snd_BUG_ON(!chip->ops->write_codec))
 		return;
 
 	if (chip->chip_status & VX_STAT_IS_STALE)
 		return;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	chip->ops->write_codec(chip, codec, data);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 /*
@@ -178,14 +176,12 @@ void vx_reset_codec(struct vx_core *chip, int cold_reset)
  */
 static void vx_change_audio_source(struct vx_core *chip, int src)
 {
-	unsigned long flags;
-
 	if (chip->chip_status & VX_STAT_IS_STALE)
 		return;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	chip->ops->change_audio_source(chip, src);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 
diff --git a/sound/drivers/vx/vx_pcm.c b/sound/drivers/vx/vx_pcm.c
index deed5efff33c..11467272089e 100644
--- a/sound/drivers/vx/vx_pcm.c
+++ b/sound/drivers/vx/vx_pcm.c
@@ -229,7 +229,7 @@ static int vx_get_pipe_state(struct vx_core *chip, struct vx_pipe *pipe, int *st
 
 	vx_init_rmh(&rmh, CMD_PIPE_STATE);
 	vx_set_pipe_cmd_params(&rmh, pipe->is_capture, pipe->number, 0);
-	err = vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	err = vx_send_msg(chip, &rmh);
 	if (! err)
 		*state = (rmh.Stat[0] & (1 << pipe->number)) ? 1 : 0;
 	return err;
@@ -280,7 +280,7 @@ static int vx_pipe_can_start(struct vx_core *chip, struct vx_pipe *pipe)
 	vx_set_pipe_cmd_params(&rmh, pipe->is_capture, pipe->number, 0);
 	rmh.Cmd[0] |= 1;
 
-	err = vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	err = vx_send_msg(chip, &rmh);
 	if (! err) {
 		if (rmh.Stat[0])
 			err = 1;
@@ -300,7 +300,7 @@ static int vx_conf_pipe(struct vx_core *chip, struct vx_pipe *pipe)
 	if (pipe->is_capture)
 		rmh.Cmd[0] |= COMMAND_RECORD_MASK;
 	rmh.Cmd[1] = 1 << pipe->number;
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */
+	return vx_send_msg(chip, &rmh);
 }
 
 /*
@@ -311,7 +311,7 @@ static int vx_send_irqa(struct vx_core *chip)
 	struct vx_rmh rmh;
 
 	vx_init_rmh(&rmh, CMD_SEND_IRQA);
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	return vx_send_msg(chip, &rmh);
 }
 
 
@@ -389,7 +389,7 @@ static int vx_stop_pipe(struct vx_core *chip, struct vx_pipe *pipe)
 	struct vx_rmh rmh;
 	vx_init_rmh(&rmh, CMD_STOP_PIPE);
 	vx_set_pipe_cmd_params(&rmh, pipe->is_capture, pipe->number, 0);
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	return vx_send_msg(chip, &rmh);
 }
 
 
@@ -477,7 +477,7 @@ static int vx_start_stream(struct vx_core *chip, struct vx_pipe *pipe)
 	vx_init_rmh(&rmh, CMD_START_ONE_STREAM);
 	vx_set_stream_cmd_params(&rmh, pipe->is_capture, pipe->number);
 	vx_set_differed_time(chip, &rmh, pipe);
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	return vx_send_msg(chip, &rmh);
 }
 
 
@@ -492,7 +492,7 @@ static int vx_stop_stream(struct vx_core *chip, struct vx_pipe *pipe)
 
 	vx_init_rmh(&rmh, CMD_STOP_STREAM);
 	vx_set_stream_cmd_params(&rmh, pipe->is_capture, pipe->number);
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	return vx_send_msg(chip, &rmh);
 }
 
 
@@ -520,8 +520,6 @@ static struct snd_pcm_hardware vx_pcm_playback_hw = {
 };
 
 
-static void vx_pcm_delayed_start(unsigned long arg);
-
 /*
  * vx_pcm_playback_open - open callback for playback
  */
@@ -553,7 +551,6 @@ static int vx_pcm_playback_open(struct snd_pcm_substream *subs)
 	pipe->references++;
 
 	pipe->substream = subs;
-	tasklet_init(&pipe->start_tq, vx_pcm_delayed_start, (unsigned long)subs);
 	chip->playback_pipes[audio] = pipe;
 
 	runtime->hw = vx_pcm_playback_hw;
@@ -646,12 +643,12 @@ static int vx_pcm_playback_transfer_chunk(struct vx_core *chip,
 	/* we don't need irqsave here, because this function
 	 * is called from either trigger callback or irq handler
 	 */
-	spin_lock(&chip->lock); 
+	mutex_lock(&chip->lock);
 	vx_pseudo_dma_write(chip, runtime, pipe, size);
 	err = vx_notify_end_of_buffer(chip, pipe);
 	/* disconnect the host, SIZE_HBUF command always switches to the stream mode */
 	vx_send_rih_nolock(chip, IRQ_CONNECT_STREAM_NEXT);
-	spin_unlock(&chip->lock);
+	mutex_unlock(&chip->lock);
 	return err;
 }
 
@@ -727,31 +724,6 @@ static void vx_pcm_playback_update(struct vx_core *chip,
 	}
 }
 
-/*
- * start the stream and pipe.
- * this function is called from tasklet, which is invoked by the trigger
- * START callback.
- */
-static void vx_pcm_delayed_start(unsigned long arg)
-{
-	struct snd_pcm_substream *subs = (struct snd_pcm_substream *)arg;
-	struct vx_core *chip = subs->pcm->private_data;
-	struct vx_pipe *pipe = subs->runtime->private_data;
-	int err;
-
-	/*  printk( KERN_DEBUG "DDDD tasklet delayed start jiffies = %ld\n", jiffies);*/
-
-	if ((err = vx_start_stream(chip, pipe)) < 0) {
-		snd_printk(KERN_ERR "vx: cannot start stream\n");
-		return;
-	}
-	if ((err = vx_toggle_pipe(chip, pipe, 1)) < 0) {
-		snd_printk(KERN_ERR "vx: cannot start pipe\n");
-		return;
-	}
-	/*   printk( KERN_DEBUG "dddd tasklet delayed start jiffies = %ld \n", jiffies);*/
-}
-
 /*
  * vx_pcm_playback_trigger - trigger callback for playback
  */
@@ -769,11 +741,17 @@ static int vx_pcm_trigger(struct snd_pcm_substream *subs, int cmd)
 	case SNDRV_PCM_TRIGGER_RESUME:
 		if (! pipe->is_capture)
 			vx_pcm_playback_transfer(chip, subs, pipe, 2);
-		/* FIXME:
-		 * we trigger the pipe using tasklet, so that the interrupts are
-		 * issued surely after the trigger is completed.
-		 */ 
-		tasklet_schedule(&pipe->start_tq);
+		err = vx_start_stream(chip, pipe);
+		if (err < 0) {
+			pr_debug("vx: cannot start stream\n");
+			return err;
+		}
+		err = vx_toggle_pipe(chip, pipe, 1);
+		if (err < 0) {
+			pr_debug("vx: cannot start pipe\n");
+			vx_stop_stream(chip, pipe);
+			return err;
+		}
 		chip->pcm_running++;
 		pipe->running = 1;
 		break;
@@ -955,7 +933,6 @@ static int vx_pcm_capture_open(struct snd_pcm_substream *subs)
 	if (err < 0)
 		return err;
 	pipe->substream = subs;
-	tasklet_init(&pipe->start_tq, vx_pcm_delayed_start, (unsigned long)subs);
 	chip->capture_pipes[audio] = pipe;
 
 	/* check if monitoring is needed */
@@ -1082,7 +1059,7 @@ static void vx_pcm_capture_update(struct vx_core *chip, struct snd_pcm_substream
 		count -= 3;
 	}
 	/* disconnect the host, SIZE_HBUF command always switches to the stream mode */
-	vx_send_rih_nolock(chip, IRQ_CONNECT_STREAM_NEXT);
+	vx_send_rih(chip, IRQ_CONNECT_STREAM_NEXT);
 	/* read the last pending 6 bytes */
 	count = DMA_READ_ALIGN;
 	while (count > 0) {
@@ -1099,7 +1076,7 @@ static void vx_pcm_capture_update(struct vx_core *chip, struct snd_pcm_substream
 
  _error:
 	/* disconnect the host, SIZE_HBUF command always switches to the stream mode */
-	vx_send_rih_nolock(chip, IRQ_CONNECT_STREAM_NEXT);
+	vx_send_rih(chip, IRQ_CONNECT_STREAM_NEXT);
 	return;
 }
 
@@ -1275,6 +1252,7 @@ int snd_vx_pcm_new(struct vx_core *chip)
 		pcm->private_data = chip;
 		pcm->private_free = snd_vx_pcm_free;
 		pcm->info_flags = 0;
+		pcm->nonatomic = true;
 		strcpy(pcm->name, chip->card->shortname);
 		chip->pcm[i] = pcm;
 	}
diff --git a/sound/drivers/vx/vx_uer.c b/sound/drivers/vx/vx_uer.c
index b0560fec6bba..ef0b40c0a594 100644
--- a/sound/drivers/vx/vx_uer.c
+++ b/sound/drivers/vx/vx_uer.c
@@ -60,9 +60,9 @@ static int vx_modify_board_inputs(struct vx_core *chip)
  */
 static int vx_read_one_cbit(struct vx_core *chip, int index)
 {
-	unsigned long flags;
 	int val;
-	spin_lock_irqsave(&chip->lock, flags);
+
+	mutex_lock(&chip->lock);
 	if (chip->type >= VX_TYPE_VXPOCKET) {
 		vx_outb(chip, CSUER, 1); /* read */
 		vx_outb(chip, RUER, index & XX_UER_CBITS_OFFSET_MASK);
@@ -72,7 +72,7 @@ static int vx_read_one_cbit(struct vx_core *chip, int index)
 		vx_outl(chip, RUER, index & XX_UER_CBITS_OFFSET_MASK);
 		val = (vx_inl(chip, RUER) >> 7) & 0x01;
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 	return val;
 }
 
@@ -83,9 +83,8 @@ static int vx_read_one_cbit(struct vx_core *chip, int index)
  */
 static void vx_write_one_cbit(struct vx_core *chip, int index, int val)
 {
-	unsigned long flags;
 	val = !!val;	/* 0 or 1 */
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	if (vx_is_pcmcia(chip)) {
 		vx_outb(chip, CSUER, 0); /* write */
 		vx_outb(chip, RUER, (val << 7) | (index & XX_UER_CBITS_OFFSET_MASK));
@@ -93,7 +92,7 @@ static void vx_write_one_cbit(struct vx_core *chip, int index, int val)
 		vx_outl(chip, CSUER, 0); /* write */
 		vx_outl(chip, RUER, (val << 7) | (index & XX_UER_CBITS_OFFSET_MASK));
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 /*
@@ -190,14 +189,12 @@ static int vx_calc_clock_from_freq(struct vx_core *chip, int freq)
  */
 static void vx_change_clock_source(struct vx_core *chip, int source)
 {
-	unsigned long flags;
-
 	/* we mute DAC to prevent clicks */
 	vx_toggle_dac_mute(chip, 1);
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	chip->ops->set_clock_source(chip, source);
 	chip->clock_source = source;
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 	/* unmute */
 	vx_toggle_dac_mute(chip, 0);
 }
@@ -209,11 +206,11 @@ static void vx_change_clock_source(struct vx_core *chip, int source)
 void vx_set_internal_clock(struct vx_core *chip, unsigned int freq)
 {
 	int clock;
-	unsigned long flags;
+
 	/* Get real clock value */
 	clock = vx_calc_clock_from_freq(chip, freq);
 	snd_printdd(KERN_DEBUG "set internal clock to 0x%x from freq %d\n", clock, freq);
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	if (vx_is_pcmcia(chip)) {
 		vx_outb(chip, HIFREQ, (clock >> 8) & 0x0f);
 		vx_outb(chip, LOFREQ, clock & 0xff);
@@ -221,7 +218,7 @@ void vx_set_internal_clock(struct vx_core *chip, unsigned int freq)
 		vx_outl(chip, HIFREQ, (clock >> 8) & 0x0f);
 		vx_outl(chip, LOFREQ, clock & 0xff);
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 
diff --git a/sound/pci/vx222/vx222.c b/sound/pci/vx222/vx222.c
index 3dc4732142ee..c5a25e39e3a8 100644
--- a/sound/pci/vx222/vx222.c
+++ b/sound/pci/vx222/vx222.c
@@ -168,8 +168,9 @@ static int snd_vx222_create(struct snd_card *card, struct pci_dev *pci,
 	for (i = 0; i < 2; i++)
 		vx->port[i] = pci_resource_start(pci, i + 1);
 
-	if (request_irq(pci->irq, snd_vx_irq_handler, IRQF_SHARED,
-			KBUILD_MODNAME, chip)) {
+	if (request_threaded_irq(pci->irq, snd_vx_irq_handler,
+				 snd_vx_threaded_irq_handler, IRQF_SHARED,
+				 KBUILD_MODNAME, chip)) {
 		dev_err(card->dev, "unable to grab IRQ %d\n", pci->irq);
 		snd_vx222_free(chip);
 		return -EBUSY;
diff --git a/sound/pcmcia/vx/vxp_ops.c b/sound/pcmcia/vx/vxp_ops.c
index fe33e122e372..281972913c32 100644
--- a/sound/pcmcia/vx/vxp_ops.c
+++ b/sound/pcmcia/vx/vxp_ops.c
@@ -468,12 +468,11 @@ static void vxp_write_codec_reg(struct vx_core *chip, int codec, unsigned int da
 void vx_set_mic_boost(struct vx_core *chip, int boost)
 {
 	struct snd_vxpocket *pchip = (struct snd_vxpocket *)chip;
-	unsigned long flags;
 
 	if (chip->chip_status & VX_STAT_IS_STALE)
 		return;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	if (pchip->regCDSP & P24_CDSP_MICS_SEL_MASK) {
 		if (boost) {
 			/* boost: 38 dB */
@@ -486,7 +485,7 @@ void vx_set_mic_boost(struct vx_core *chip, int boost)
                 }
 		vx_outb(chip, CDSP, pchip->regCDSP);
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 /*
@@ -511,17 +510,16 @@ static int vx_compute_mic_level(int level)
 void vx_set_mic_level(struct vx_core *chip, int level)
 {
 	struct snd_vxpocket *pchip = (struct snd_vxpocket *)chip;
-	unsigned long flags;
 
 	if (chip->chip_status & VX_STAT_IS_STALE)
 		return;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	if (pchip->regCDSP & VXP_CDSP_MIC_SEL_MASK) {
 		level = vx_compute_mic_level(level);
 		vx_outb(chip, MICRO, level);
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 
diff --git a/sound/pcmcia/vx/vxpocket.c b/sound/pcmcia/vx/vxpocket.c
index 786e7e139c9e..92ec11456e3a 100644
--- a/sound/pcmcia/vx/vxpocket.c
+++ b/sound/pcmcia/vx/vxpocket.c
@@ -62,6 +62,7 @@ static unsigned int card_alloc;
  */
 static void vxpocket_release(struct pcmcia_device *link)
 {
+	free_irq(link->irq, link->priv);
 	pcmcia_disable_device(link);
 }
 
@@ -227,11 +228,13 @@ static int vxpocket_config(struct pcmcia_device *link)
 
 	ret = pcmcia_request_io(link);
 	if (ret)
-		goto failed;
+		goto failed_preirq;
 
-	ret = pcmcia_request_irq(link, snd_vx_irq_handler);
+	ret = request_threaded_irq(link->irq, snd_vx_irq_handler,
+				   snd_vx_threaded_irq_handler,
+				   IRQF_SHARED, link->devname, link->priv);
 	if (ret)
-		goto failed;
+		goto failed_preirq;
 
 	ret = pcmcia_enable_device(link);
 	if (ret)
@@ -245,7 +248,9 @@ static int vxpocket_config(struct pcmcia_device *link)
 
 	return 0;
 
-failed:
+ failed:
+	free_irq(link->irq, link->priv);
+failed_preirq:
 	pcmcia_disable_device(link);
 	return -ENODEV;
 }
-- 
cgit v1.2.3


From f91ce35e471ae17552ce7bfe355cfd997e3ad781 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 10 Sep 2014 15:30:08 -0600
Subject: ACPIPHP / radeon / nouveau: Remove acpi_bus_no_hotplug()

Revert parts of f244d8b623da ("ACPIPHP / radeon / nouveau: Fix VGA
switcheroo problem related to hotplug").

A previous commit 5493b31f0b55 ("PCI: Add pci_ignore_hotplug() to ignore
hotplug events for a device") added equivalent functionality implemented in
a different way for both acpiphp and pciehp.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Acked-by: Rajat Jain <rajatxjain@gmail.com>
---
 drivers/acpi/bus.c                           | 10 ----------
 drivers/gpu/drm/nouveau/nouveau_acpi.c       | 16 ++--------------
 drivers/gpu/drm/radeon/radeon_atpx_handler.c | 16 ++--------------
 include/acpi/acpi_bus.h                      |  4 +---
 4 files changed, 5 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 8581f5b84f48..8b67bd0f6bb5 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -177,16 +177,6 @@ void acpi_bus_detach_private_data(acpi_handle handle)
 }
 EXPORT_SYMBOL_GPL(acpi_bus_detach_private_data);
 
-void acpi_bus_no_hotplug(acpi_handle handle)
-{
-	struct acpi_device *adev = NULL;
-
-	acpi_bus_get_device(handle, &adev);
-	if (adev)
-		adev->flags.no_hotplug = true;
-}
-EXPORT_SYMBOL_GPL(acpi_bus_no_hotplug);
-
 static void acpi_print_osc_error(acpi_handle handle,
 	struct acpi_osc_context *context, char *error)
 {
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 279206997e5c..622424692b3b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -46,7 +46,6 @@ static struct nouveau_dsm_priv {
 	bool dsm_detected;
 	bool optimus_detected;
 	acpi_handle dhandle;
-	acpi_handle other_handle;
 	acpi_handle rom_handle;
 } nouveau_dsm_priv;
 
@@ -222,10 +221,9 @@ static int nouveau_dsm_pci_probe(struct pci_dev *pdev)
 	if (!dhandle)
 		return false;
 
-	if (!acpi_has_method(dhandle, "_DSM")) {
-		nouveau_dsm_priv.other_handle = dhandle;
+	if (!acpi_has_method(dhandle, "_DSM"))
 		return false;
-	}
+
 	if (acpi_check_dsm(dhandle, nouveau_dsm_muid, 0x00000102,
 			   1 << NOUVEAU_DSM_POWER))
 		retval |= NOUVEAU_DSM_HAS_MUX;
@@ -301,16 +299,6 @@ static bool nouveau_dsm_detect(void)
 		printk(KERN_INFO "VGA switcheroo: detected DSM switching method %s handle\n",
 			acpi_method_name);
 		nouveau_dsm_priv.dsm_detected = true;
-		/*
-		 * On some systems hotplug events are generated for the device
-		 * being switched off when _DSM is executed.  They cause ACPI
-		 * hotplug to trigger and attempt to remove the device from
-		 * the system, which causes it to break down.  Prevent that from
-		 * happening by setting the no_hotplug flag for the involved
-		 * ACPI device objects.
-		 */
-		acpi_bus_no_hotplug(nouveau_dsm_priv.dhandle);
-		acpi_bus_no_hotplug(nouveau_dsm_priv.other_handle);
 		ret = true;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index a9fb0d016d38..8bc7d0bbd3c8 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -33,7 +33,6 @@ static struct radeon_atpx_priv {
 	bool atpx_detected;
 	/* handle for device - and atpx */
 	acpi_handle dhandle;
-	acpi_handle other_handle;
 	struct radeon_atpx atpx;
 } radeon_atpx_priv;
 
@@ -453,10 +452,9 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
 		return false;
 
 	status = acpi_get_handle(dhandle, "ATPX", &atpx_handle);
-	if (ACPI_FAILURE(status)) {
-		radeon_atpx_priv.other_handle = dhandle;
+	if (ACPI_FAILURE(status))
 		return false;
-	}
+
 	radeon_atpx_priv.dhandle = dhandle;
 	radeon_atpx_priv.atpx.handle = atpx_handle;
 	return true;
@@ -540,16 +538,6 @@ static bool radeon_atpx_detect(void)
 		printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
 		       acpi_method_name);
 		radeon_atpx_priv.atpx_detected = true;
-		/*
-		 * On some systems hotplug events are generated for the device
-		 * being switched off when ATPX is executed.  They cause ACPI
-		 * hotplug to trigger and attempt to remove the device from
-		 * the system, which causes it to break down.  Prevent that from
-		 * happening by setting the no_hotplug flag for the involved
-		 * ACPI device objects.
-		 */
-		acpi_bus_no_hotplug(radeon_atpx_priv.dhandle);
-		acpi_bus_no_hotplug(radeon_atpx_priv.other_handle);
 		return true;
 	}
 	return false;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index bcfd808b1098..95c506961a13 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -204,10 +204,9 @@ struct acpi_device_flags {
 	u32 match_driver:1;
 	u32 initialized:1;
 	u32 visited:1;
-	u32 no_hotplug:1;
 	u32 hotplug_notify:1;
 	u32 is_dock_station:1;
-	u32 reserved:22;
+	u32 reserved:23;
 };
 
 /* File System */
@@ -412,7 +411,6 @@ void acpi_bus_private_data_handler(acpi_handle, void *);
 int acpi_bus_get_private_data(acpi_handle, void **);
 int acpi_bus_attach_private_data(acpi_handle, void *);
 void acpi_bus_detach_private_data(acpi_handle);
-void acpi_bus_no_hotplug(acpi_handle handle);
 extern int acpi_notifier_call_chain(struct acpi_device *, u32, u32);
 extern int register_acpi_notifier(struct notifier_block *);
 extern int unregister_acpi_notifier(struct notifier_block *);
-- 
cgit v1.2.3


From 0e9871e3f79fd17c691b50a9669220c54ff084a2 Mon Sep 17 00:00:00 2001
From: Anton Danilov <littlesmilingcloud@gmail.com>
Date: Thu, 28 Aug 2014 10:11:27 +0400
Subject: netfilter: ipset: Add skbinfo extension kernel support in the ipset
 core.

Skbinfo extension provides mapping of metainformation with lookup in the ipset tables.
This patch defines the flags, the constants, the functions and the structures
for the data type independent support of the extension.
Note the firewall mark stores in the kernel structures as two 32bit values,
but transfered through netlink as one 64bit value.

Signed-off-by: Anton Danilov <littlesmilingcloud@gmail.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h      | 56 ++++++++++++++++++++++++++++-
 include/uapi/linux/netfilter/ipset/ip_set.h | 12 +++++++
 net/netfilter/ipset/ip_set_core.c           | 27 +++++++++++++-
 3 files changed, 93 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 96afc29184be..b97aac5142ed 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -57,6 +57,8 @@ enum ip_set_extension {
 	IPSET_EXT_COUNTER = (1 << IPSET_EXT_BIT_COUNTER),
 	IPSET_EXT_BIT_COMMENT = 2,
 	IPSET_EXT_COMMENT = (1 << IPSET_EXT_BIT_COMMENT),
+	IPSET_EXT_BIT_SKBINFO = 3,
+	IPSET_EXT_SKBINFO = (1 << IPSET_EXT_BIT_SKBINFO),
 	/* Mark set with an extension which needs to call destroy */
 	IPSET_EXT_BIT_DESTROY = 7,
 	IPSET_EXT_DESTROY = (1 << IPSET_EXT_BIT_DESTROY),
@@ -65,12 +67,14 @@ enum ip_set_extension {
 #define SET_WITH_TIMEOUT(s)	((s)->extensions & IPSET_EXT_TIMEOUT)
 #define SET_WITH_COUNTER(s)	((s)->extensions & IPSET_EXT_COUNTER)
 #define SET_WITH_COMMENT(s)	((s)->extensions & IPSET_EXT_COMMENT)
+#define SET_WITH_SKBINFO(s)	((s)->extensions & IPSET_EXT_SKBINFO)
 #define SET_WITH_FORCEADD(s)	((s)->flags & IPSET_CREATE_FLAG_FORCEADD)
 
 /* Extension id, in size order */
 enum ip_set_ext_id {
 	IPSET_EXT_ID_COUNTER = 0,
 	IPSET_EXT_ID_TIMEOUT,
+	IPSET_EXT_ID_SKBINFO,
 	IPSET_EXT_ID_COMMENT,
 	IPSET_EXT_ID_MAX,
 };
@@ -92,6 +96,10 @@ struct ip_set_ext {
 	u64 packets;
 	u64 bytes;
 	u32 timeout;
+	u32 skbmark;
+	u32 skbmarkmask;
+	u32 skbprio;
+	u16 skbqueue;
 	char *comment;
 };
 
@@ -104,6 +112,13 @@ struct ip_set_comment {
 	char *str;
 };
 
+struct ip_set_skbinfo {
+	u32 skbmark;
+	u32 skbmarkmask;
+	u32 skbprio;
+	u16 skbqueue;
+};
+
 struct ip_set;
 
 #define ext_timeout(e, s)	\
@@ -112,7 +127,8 @@ struct ip_set;
 (struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER])
 #define ext_comment(e, s)	\
 (struct ip_set_comment *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COMMENT])
-
+#define ext_skbinfo(e, s)	\
+(struct ip_set_skbinfo *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_SKBINFO])
 
 typedef int (*ipset_adtfn)(struct ip_set *set, void *value,
 			   const struct ip_set_ext *ext,
@@ -256,6 +272,8 @@ ip_set_put_flags(struct sk_buff *skb, struct ip_set *set)
 		cadt_flags |= IPSET_FLAG_WITH_COUNTERS;
 	if (SET_WITH_COMMENT(set))
 		cadt_flags |= IPSET_FLAG_WITH_COMMENT;
+	if (SET_WITH_SKBINFO(set))
+		cadt_flags |= IPSET_FLAG_WITH_SKBINFO;
 	if (SET_WITH_FORCEADD(set))
 		cadt_flags |= IPSET_FLAG_WITH_FORCEADD;
 
@@ -304,6 +322,39 @@ ip_set_update_counter(struct ip_set_counter *counter,
 	}
 }
 
+static inline void
+ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo,
+		      const struct ip_set_ext *ext,
+		      struct ip_set_ext *mext, u32 flags)
+{
+		mext->skbmark = skbinfo->skbmark;
+		mext->skbmarkmask = skbinfo->skbmarkmask;
+		mext->skbprio = skbinfo->skbprio;
+		mext->skbqueue = skbinfo->skbqueue;
+}
+static inline bool
+ip_set_put_skbinfo(struct sk_buff *skb, struct ip_set_skbinfo *skbinfo)
+{
+	return nla_put_net64(skb, IPSET_ATTR_SKBMARK,
+			     cpu_to_be64((u64)skbinfo->skbmark << 32 |
+					 skbinfo->skbmarkmask)) ||
+	       nla_put_net32(skb, IPSET_ATTR_SKBPRIO,
+			     cpu_to_be32(skbinfo->skbprio)) ||
+	       nla_put_net16(skb, IPSET_ATTR_SKBQUEUE,
+			     cpu_to_be16(skbinfo->skbqueue));
+
+}
+
+static inline void
+ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo,
+		    const struct ip_set_ext *ext)
+{
+	skbinfo->skbmark = ext->skbmark;
+	skbinfo->skbmarkmask = ext->skbmarkmask;
+	skbinfo->skbprio = ext->skbprio;
+	skbinfo->skbqueue = ext->skbqueue;
+}
+
 static inline bool
 ip_set_put_counter(struct sk_buff *skb, struct ip_set_counter *counter)
 {
@@ -497,6 +548,9 @@ ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
 	if (SET_WITH_COMMENT(set) &&
 	    ip_set_put_comment(skb, ext_comment(e, set)))
 		return -EMSGSIZE;
+	if (SET_WITH_SKBINFO(set) &&
+	    ip_set_put_skbinfo(skb, ext_skbinfo(e, set)))
+		return -EMSGSIZE;
 	return 0;
 }
 
diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index 78c2f2e79920..ca03119111a2 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -115,6 +115,9 @@ enum {
 	IPSET_ATTR_BYTES,
 	IPSET_ATTR_PACKETS,
 	IPSET_ATTR_COMMENT,
+	IPSET_ATTR_SKBMARK,
+	IPSET_ATTR_SKBPRIO,
+	IPSET_ATTR_SKBQUEUE,
 	__IPSET_ATTR_ADT_MAX,
 };
 #define IPSET_ATTR_ADT_MAX	(__IPSET_ATTR_ADT_MAX - 1)
@@ -147,6 +150,7 @@ enum ipset_errno {
 	IPSET_ERR_COUNTER,
 	IPSET_ERR_COMMENT,
 	IPSET_ERR_INVALID_MARKMASK,
+	IPSET_ERR_SKBINFO,
 
 	/* Type specific error codes */
 	IPSET_ERR_TYPE_SPECIFIC = 4352,
@@ -170,6 +174,12 @@ enum ipset_cmd_flags {
 	IPSET_FLAG_MATCH_COUNTERS = (1 << IPSET_FLAG_BIT_MATCH_COUNTERS),
 	IPSET_FLAG_BIT_RETURN_NOMATCH = 7,
 	IPSET_FLAG_RETURN_NOMATCH = (1 << IPSET_FLAG_BIT_RETURN_NOMATCH),
+	IPSET_FLAG_BIT_MAP_SKBMARK = 8,
+	IPSET_FLAG_MAP_SKBMARK = (1 << IPSET_FLAG_BIT_MAP_SKBMARK),
+	IPSET_FLAG_BIT_MAP_SKBPRIO = 9,
+	IPSET_FLAG_MAP_SKBPRIO = (1 << IPSET_FLAG_BIT_MAP_SKBPRIO),
+	IPSET_FLAG_BIT_MAP_SKBQUEUE = 10,
+	IPSET_FLAG_MAP_SKBQUEUE = (1 << IPSET_FLAG_BIT_MAP_SKBQUEUE),
 	IPSET_FLAG_CMD_MAX = 15,
 };
 
@@ -187,6 +197,8 @@ enum ipset_cadt_flags {
 	IPSET_FLAG_WITH_COMMENT = (1 << IPSET_FLAG_BIT_WITH_COMMENT),
 	IPSET_FLAG_BIT_WITH_FORCEADD = 5,
 	IPSET_FLAG_WITH_FORCEADD = (1 << IPSET_FLAG_BIT_WITH_FORCEADD),
+	IPSET_FLAG_BIT_WITH_SKBINFO = 6,
+	IPSET_FLAG_WITH_SKBINFO = (1 << IPSET_FLAG_BIT_WITH_SKBINFO),
 	IPSET_FLAG_CADT_MAX	= 15,
 };
 
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 4ca4e5ca6f57..26c795e6b57f 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -337,6 +337,12 @@ const struct ip_set_ext_type ip_set_extensions[] = {
 		.len	= sizeof(unsigned long),
 		.align	= __alignof__(unsigned long),
 	},
+	[IPSET_EXT_ID_SKBINFO] = {
+		.type	= IPSET_EXT_SKBINFO,
+		.flag	= IPSET_FLAG_WITH_SKBINFO,
+		.len	= sizeof(struct ip_set_skbinfo),
+		.align	= __alignof__(struct ip_set_skbinfo),
+	},
 	[IPSET_EXT_ID_COMMENT] = {
 		.type	 = IPSET_EXT_COMMENT | IPSET_EXT_DESTROY,
 		.flag	 = IPSET_FLAG_WITH_COMMENT,
@@ -382,6 +388,7 @@ int
 ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
 		      struct ip_set_ext *ext)
 {
+	u64 fullmark;
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		if (!(set->extensions & IPSET_EXT_TIMEOUT))
 			return -IPSET_ERR_TIMEOUT;
@@ -402,7 +409,25 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
 			return -IPSET_ERR_COMMENT;
 		ext->comment = ip_set_comment_uget(tb[IPSET_ATTR_COMMENT]);
 	}
-
+	if (tb[IPSET_ATTR_SKBMARK]) {
+		if (!(set->extensions & IPSET_EXT_SKBINFO))
+			return -IPSET_ERR_SKBINFO;
+		fullmark = be64_to_cpu(nla_get_be64(tb[IPSET_ATTR_SKBMARK]));
+		ext->skbmark = fullmark >> 32;
+		ext->skbmarkmask = fullmark & 0xffffffff;
+	}
+	if (tb[IPSET_ATTR_SKBPRIO]) {
+		if (!(set->extensions & IPSET_EXT_SKBINFO))
+			return -IPSET_ERR_SKBINFO;
+		ext->skbprio = be32_to_cpu(nla_get_be32(
+					    tb[IPSET_ATTR_SKBPRIO]));
+	}
+	if (tb[IPSET_ATTR_SKBQUEUE]) {
+		if (!(set->extensions & IPSET_EXT_SKBINFO))
+			return -IPSET_ERR_SKBINFO;
+		ext->skbqueue = be16_to_cpu(nla_get_be16(
+					    tb[IPSET_ATTR_SKBQUEUE]));
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_set_get_extensions);
-- 
cgit v1.2.3


From 76cea4109ca89dea218fdc652d2e1535fd9b5fc7 Mon Sep 17 00:00:00 2001
From: Anton Danilov <littlesmilingcloud@gmail.com>
Date: Tue, 2 Sep 2014 14:21:20 +0400
Subject: netfilter: ipset: Add skbinfo extension support to SET target.

Signed-off-by: Anton Danilov <littlesmilingcloud@gmail.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/uapi/linux/netfilter/xt_set.h |  10 +++
 net/netfilter/xt_set.c                | 155 ++++++++++++++++++++++++++++++++++
 2 files changed, 165 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/xt_set.h b/include/uapi/linux/netfilter/xt_set.h
index 964d3d42f874..d6a1df1f2947 100644
--- a/include/uapi/linux/netfilter/xt_set.h
+++ b/include/uapi/linux/netfilter/xt_set.h
@@ -71,4 +71,14 @@ struct xt_set_info_match_v3 {
 	__u32 flags;
 };
 
+/* Revision 3 target */
+
+struct xt_set_info_target_v3 {
+	struct xt_set_info add_set;
+	struct xt_set_info del_set;
+	struct xt_set_info map_set;
+	__u32 flags;
+	__u32 timeout;
+};
+
 #endif /*_XT_SET_H*/
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index cb70f6ec5695..5732cd64acc0 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -366,6 +366,140 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par)
 #define set_target_v2_checkentry	set_target_v1_checkentry
 #define set_target_v2_destroy		set_target_v1_destroy
 
+/* Revision 3 target */
+
+static unsigned int
+set_target_v3(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct xt_set_info_target_v3 *info = par->targinfo;
+	ADT_OPT(add_opt, par->family, info->add_set.dim,
+		info->add_set.flags, info->flags, info->timeout);
+	ADT_OPT(del_opt, par->family, info->del_set.dim,
+		info->del_set.flags, 0, UINT_MAX);
+	ADT_OPT(map_opt, par->family, info->map_set.dim,
+		info->map_set.flags, 0, UINT_MAX);
+
+	int ret;
+
+	/* Normalize to fit into jiffies */
+	if (add_opt.ext.timeout != IPSET_NO_TIMEOUT &&
+	    add_opt.ext.timeout > UINT_MAX/MSEC_PER_SEC)
+		add_opt.ext.timeout = UINT_MAX/MSEC_PER_SEC;
+	if (info->add_set.index != IPSET_INVALID_ID)
+		ip_set_add(info->add_set.index, skb, par, &add_opt);
+	if (info->del_set.index != IPSET_INVALID_ID)
+		ip_set_del(info->del_set.index, skb, par, &del_opt);
+	if (info->map_set.index != IPSET_INVALID_ID) {
+		map_opt.cmdflags |= info->flags & (IPSET_FLAG_MAP_SKBMARK |
+						   IPSET_FLAG_MAP_SKBPRIO |
+						   IPSET_FLAG_MAP_SKBQUEUE);
+		ret = match_set(info->map_set.index, skb, par, &map_opt,
+				info->map_set.flags & IPSET_INV_MATCH);
+		if (!ret)
+			return XT_CONTINUE;
+		if (map_opt.cmdflags & IPSET_FLAG_MAP_SKBMARK)
+			skb->mark = (skb->mark & ~(map_opt.ext.skbmarkmask))
+				    ^ (map_opt.ext.skbmark);
+		if (map_opt.cmdflags & IPSET_FLAG_MAP_SKBPRIO)
+			skb->priority = map_opt.ext.skbprio;
+		if ((map_opt.cmdflags & IPSET_FLAG_MAP_SKBQUEUE) &&
+		    skb->dev &&
+		    skb->dev->real_num_tx_queues > map_opt.ext.skbqueue)
+			skb_set_queue_mapping(skb, map_opt.ext.skbqueue);
+	}
+	return XT_CONTINUE;
+}
+
+
+static int
+set_target_v3_checkentry(const struct xt_tgchk_param *par)
+{
+	const struct xt_set_info_target_v3 *info = par->targinfo;
+	ip_set_id_t index;
+
+	if (info->add_set.index != IPSET_INVALID_ID) {
+		index = ip_set_nfnl_get_byindex(par->net,
+						info->add_set.index);
+		if (index == IPSET_INVALID_ID) {
+			pr_warn("Cannot find add_set index %u as target\n",
+				info->add_set.index);
+			return -ENOENT;
+		}
+	}
+
+	if (info->del_set.index != IPSET_INVALID_ID) {
+		index = ip_set_nfnl_get_byindex(par->net,
+						info->del_set.index);
+		if (index == IPSET_INVALID_ID) {
+			pr_warn("Cannot find del_set index %u as target\n",
+				info->del_set.index);
+			if (info->add_set.index != IPSET_INVALID_ID)
+				ip_set_nfnl_put(par->net,
+						info->add_set.index);
+			return -ENOENT;
+		}
+	}
+
+	if (info->map_set.index != IPSET_INVALID_ID) {
+		if (strncmp(par->table, "mangle", 7)) {
+			pr_warn("--map-set only usable from mangle table\n");
+			return -EINVAL;
+		}
+		if (((info->flags & IPSET_FLAG_MAP_SKBPRIO) |
+		     (info->flags & IPSET_FLAG_MAP_SKBQUEUE)) &&
+		     !(par->hook_mask & (1 << NF_INET_FORWARD |
+					 1 << NF_INET_LOCAL_OUT |
+					 1 << NF_INET_POST_ROUTING))) {
+			pr_warn("mapping of prio or/and queue is allowed only"
+				"from OUTPUT/FORWARD/POSTROUTING chains\n");
+			return -EINVAL;
+		}
+		index = ip_set_nfnl_get_byindex(par->net,
+						info->map_set.index);
+		if (index == IPSET_INVALID_ID) {
+			pr_warn("Cannot find map_set index %u as target\n",
+				info->map_set.index);
+			if (info->add_set.index != IPSET_INVALID_ID)
+				ip_set_nfnl_put(par->net,
+						info->add_set.index);
+			if (info->del_set.index != IPSET_INVALID_ID)
+				ip_set_nfnl_put(par->net,
+						info->del_set.index);
+			return -ENOENT;
+		}
+	}
+
+	if (info->add_set.dim > IPSET_DIM_MAX ||
+	    info->del_set.dim > IPSET_DIM_MAX ||
+	    info->map_set.dim > IPSET_DIM_MAX) {
+		pr_warn("Protocol error: SET target dimension "
+			"is over the limit!\n");
+		if (info->add_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(par->net, info->add_set.index);
+		if (info->del_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(par->net, info->del_set.index);
+		if (info->map_set.index != IPSET_INVALID_ID)
+			ip_set_nfnl_put(par->net, info->map_set.index);
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
+static void
+set_target_v3_destroy(const struct xt_tgdtor_param *par)
+{
+	const struct xt_set_info_target_v3 *info = par->targinfo;
+
+	if (info->add_set.index != IPSET_INVALID_ID)
+		ip_set_nfnl_put(par->net, info->add_set.index);
+	if (info->del_set.index != IPSET_INVALID_ID)
+		ip_set_nfnl_put(par->net, info->del_set.index);
+	if (info->map_set.index != IPSET_INVALID_ID)
+		ip_set_nfnl_put(par->net, info->map_set.index);
+}
+
+
 static struct xt_match set_matches[] __read_mostly = {
 	{
 		.name		= "set",
@@ -493,6 +627,27 @@ static struct xt_target set_targets[] __read_mostly = {
 		.destroy	= set_target_v2_destroy,
 		.me		= THIS_MODULE
 	},
+	/* --map-set support */
+	{
+		.name		= "SET",
+		.revision	= 3,
+		.family		= NFPROTO_IPV4,
+		.target		= set_target_v3,
+		.targetsize	= sizeof(struct xt_set_info_target_v3),
+		.checkentry	= set_target_v3_checkentry,
+		.destroy	= set_target_v3_destroy,
+		.me		= THIS_MODULE
+	},
+	{
+		.name		= "SET",
+		.revision	= 3,
+		.family		= NFPROTO_IPV6,
+		.target		= set_target_v3,
+		.targetsize	= sizeof(struct xt_set_info_target_v3),
+		.checkentry	= set_target_v3_checkentry,
+		.destroy	= set_target_v3_destroy,
+		.me		= THIS_MODULE
+	},
 };
 
 static int __init xt_set_init(void)
-- 
cgit v1.2.3


From aef96193fe7b2791c4a3b19fe75426b929769471 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Mon, 15 Sep 2014 17:30:54 +0200
Subject: netfilter: ipset: send nonzero skbinfo extensions only

Do not send zero valued skbinfo extensions to userspace at listing.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index b97aac5142ed..f1606fa6132d 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -335,13 +335,17 @@ ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo,
 static inline bool
 ip_set_put_skbinfo(struct sk_buff *skb, struct ip_set_skbinfo *skbinfo)
 {
-	return nla_put_net64(skb, IPSET_ATTR_SKBMARK,
-			     cpu_to_be64((u64)skbinfo->skbmark << 32 |
-					 skbinfo->skbmarkmask)) ||
-	       nla_put_net32(skb, IPSET_ATTR_SKBPRIO,
-			     cpu_to_be32(skbinfo->skbprio)) ||
-	       nla_put_net16(skb, IPSET_ATTR_SKBQUEUE,
-			     cpu_to_be16(skbinfo->skbqueue));
+	/* Send nonzero parameters only */
+	return ((skbinfo->skbmark || skbinfo->skbmarkmask) &&
+		nla_put_net64(skb, IPSET_ATTR_SKBMARK,
+			      cpu_to_be64((u64)skbinfo->skbmark << 32 |
+					  skbinfo->skbmarkmask))) ||
+	       (skbinfo->skbprio &&
+	        nla_put_net32(skb, IPSET_ATTR_SKBPRIO,
+			      cpu_to_be32(skbinfo->skbprio))) ||
+	       (skbinfo->skbqueue &&
+	        nla_put_net16(skb, IPSET_ATTR_SKBQUEUE,
+			     cpu_to_be16(skbinfo->skbqueue)));
 
 }
 
-- 
cgit v1.2.3


From 4b8c6ba616deab7ddf2725f5833cf027a149987f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Fri, 12 Sep 2014 16:00:32 -0700
Subject: scsi: fix regression that accidentally disabled block-based tcq

Please try the fix below, looks like the commit broke TCQ for all drivers
using block-level tagging.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/scsi/scsi_tcq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index cdcc90b07ecb..e64583560701 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -68,7 +68,7 @@ static inline void scsi_activate_tcq(struct scsi_device *sdev, int depth)
 		return;
 
 	if (!shost_use_blk_mq(sdev->host) &&
-	    blk_queue_tagged(sdev->request_queue))
+	    !blk_queue_tagged(sdev->request_queue))
 		blk_queue_init_tags(sdev->request_queue, depth,
 				    sdev->host->bqt);
 
-- 
cgit v1.2.3


From 5075314e4e4b559cc37675ad8a721a89bccd6284 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 15 Sep 2014 13:00:19 -0400
Subject: dsa: Split ops up, and avoid assigning tag_protocol and receive
 separately

This change addresses several issues.

First, it was possible to set tag_protocol without setting the ops pointer.
To correct that I have reordered things so that rcv is now populated before
we set tag_protocol.

Second, it didn't make much sense to keep setting the device ops each time a
new slave was registered.  So by moving the receive portion out into root
switch initialization that issue should be addressed.

Third, I wanted to avoid sending tags if the rcv pointer was not registered
so I changed the tag check to verify if the rcv function pointer is set on
the root tree.  If it is then we start sending DSA tagged frames.

Finally I split the device ops pointer in the structures into two spots.  I
placed the rcv function pointer in the root switch since this makes it
easiest to access from there, and I placed the xmit function pointer in the
slave for the same reason.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  7 -------
 include/net/dsa.h         | 10 ++++++----
 net/dsa/dsa.c             | 32 ++++++++++++++++++++++++++++----
 net/dsa/dsa_priv.h        | 11 ++++++++++-
 net/dsa/slave.c           | 37 +++++++++++++++----------------------
 net/dsa/tag_brcm.c        |  1 -
 net/dsa/tag_dsa.c         |  1 -
 net/dsa/tag_edsa.c        |  1 -
 net/dsa/tag_trailer.c     |  1 -
 9 files changed, 59 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f9e81d10a3b9..28d4378615e5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1928,13 +1928,6 @@ struct udp_offload {
 	struct offload_callbacks callbacks;
 };
 
-struct dsa_device_ops {
-	netdev_tx_t (*xmit)(struct sk_buff *skb, struct net_device *dev);
-	int (*rcv)(struct sk_buff *skb, struct net_device *dev,
-		   struct packet_type *pt, struct net_device *orig_dev);
-};
-
-
 /* often modified stats are per cpu, other are shared (netdev->stats) */
 struct pcpu_sw_netstats {
 	u64     rx_packets;
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 8a8a5d976f97..a55c4e6a4f0f 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -77,7 +77,7 @@ struct dsa_platform_data {
 	struct dsa_chip_data	*chip;
 };
 
-struct dsa_device_ops;
+struct packet_type;
 
 struct dsa_switch_tree {
 	/*
@@ -91,7 +91,10 @@ struct dsa_switch_tree {
 	 * protocol to use.
 	 */
 	struct net_device	*master_netdev;
-	const struct dsa_device_ops	*ops;
+	int			(*rcv)(struct sk_buff *skb,
+				       struct net_device *dev,
+				       struct packet_type *pt,
+				       struct net_device *orig_dev);
 	enum dsa_tag_protocol	tag_protocol;
 
 	/*
@@ -218,7 +221,6 @@ static inline void *ds_to_priv(struct dsa_switch *ds)
 
 static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst)
 {
-	return dst->tag_protocol != DSA_TAG_PROTO_NONE;
+	return dst->rcv != NULL;
 }
-
 #endif
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 61f145c44555..1df0a7cf1e9e 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/list.h>
-#include <linux/netdevice.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -154,9 +153,34 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
 	 * tagging protocol to the preferred tagging format of this
 	 * switch.
 	 */
-	if (ds->dst->cpu_switch == index)
-		ds->dst->tag_protocol = drv->tag_protocol;
+	if (dst->cpu_switch == index) {
+		switch (drv->tag_protocol) {
+#ifdef CONFIG_NET_DSA_TAG_DSA
+		case DSA_TAG_PROTO_DSA:
+			dst->rcv = dsa_netdev_ops.rcv;
+			break;
+#endif
+#ifdef CONFIG_NET_DSA_TAG_EDSA
+		case DSA_TAG_PROTO_EDSA:
+			dst->rcv = edsa_netdev_ops.rcv;
+			break;
+#endif
+#ifdef CONFIG_NET_DSA_TAG_TRAILER
+		case DSA_TAG_PROTO_TRAILER:
+			dst->rcv = trailer_netdev_ops.rcv;
+			break;
+#endif
+#ifdef CONFIG_NET_DSA_TAG_BRCM
+		case DSA_TAG_PROTO_BRCM:
+			dst->rcv = brcm_netdev_ops.rcv;
+			break;
+#endif
+		default:
+			break;
+		}
 
+		dst->tag_protocol = drv->tag_protocol;
+	}
 
 	/*
 	 * Do basic register setup.
@@ -626,7 +650,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 		return 0;
 	}
 
-	return dst->ops->rcv(skb, dev, pt, orig_dev);
+	return dst->rcv(skb, dev, pt, orig_dev);
 }
 
 static struct packet_type dsa_pack_type __read_mostly = {
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 98afed4d92ba..f90899e8ab5a 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -12,7 +12,13 @@
 #define __DSA_PRIV_H
 
 #include <linux/phy.h>
-#include <net/dsa.h>
+#include <linux/netdevice.h>
+
+struct dsa_device_ops {
+	netdev_tx_t (*xmit)(struct sk_buff *skb, struct net_device *dev);
+	int (*rcv)(struct sk_buff *skb, struct net_device *dev,
+		   struct packet_type *pt, struct net_device *orig_dev);
+};
 
 struct dsa_slave_priv {
 	/*
@@ -20,6 +26,8 @@ struct dsa_slave_priv {
 	 * switch port.
 	 */
 	struct net_device	*dev;
+	netdev_tx_t		(*xmit)(struct sk_buff *skb,
+					struct net_device *dev);
 
 	/*
 	 * Which switch this port is a part of, and the port index
@@ -43,6 +51,7 @@ struct dsa_slave_priv {
 extern char dsa_driver_version[];
 
 /* slave.c */
+extern const struct dsa_device_ops notag_netdev_ops;
 void dsa_slave_mii_bus_init(struct dsa_switch *ds);
 struct net_device *dsa_slave_create(struct dsa_switch *ds,
 				    struct device *parent,
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 809eeb13eb12..e38a331111c0 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -9,7 +9,6 @@
  */
 
 #include <linux/list.h>
-#include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/phy.h>
 #include <linux/of_net.h>
@@ -176,9 +175,8 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct dsa_switch_tree *dst = p->parent->dst;
 
-	return dst->ops->xmit(skb, dev);
+	return p->xmit(skb, dev);
 }
 
 static netdev_tx_t dsa_slave_notag_xmit(struct sk_buff *skb,
@@ -325,11 +323,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_do_ioctl		= dsa_slave_ioctl,
 };
 
-static const struct dsa_device_ops notag_netdev_ops = {
-	.xmit	= dsa_slave_notag_xmit,
-	.rcv	= NULL,
-};
-
 static void dsa_slave_adjust_link(struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -435,41 +428,41 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	slave_dev->tx_queue_len = 0;
 	slave_dev->netdev_ops = &dsa_slave_netdev_ops;
 
+	SET_NETDEV_DEV(slave_dev, parent);
+	slave_dev->dev.of_node = ds->pd->port_dn[port];
+	slave_dev->vlan_features = master->vlan_features;
+
+	p = netdev_priv(slave_dev);
+	p->dev = slave_dev;
+	p->parent = ds;
+	p->port = port;
+
 	switch (ds->dst->tag_protocol) {
 #ifdef CONFIG_NET_DSA_TAG_DSA
 	case DSA_TAG_PROTO_DSA:
-		ds->dst->ops = &dsa_netdev_ops;
+		p->xmit = dsa_netdev_ops.xmit;
 		break;
 #endif
 #ifdef CONFIG_NET_DSA_TAG_EDSA
 	case DSA_TAG_PROTO_EDSA:
-		ds->dst->ops = &edsa_netdev_ops;
+		p->xmit = edsa_netdev_ops.xmit;
 		break;
 #endif
 #ifdef CONFIG_NET_DSA_TAG_TRAILER
 	case DSA_TAG_PROTO_TRAILER:
-		ds->dst->ops = &trailer_netdev_ops;
+		p->xmit = trailer_netdev_ops.xmit;
 		break;
 #endif
 #ifdef CONFIG_NET_DSA_TAG_BRCM
 	case DSA_TAG_PROTO_BRCM:
-		ds->dst->ops = &brcm_netdev_ops;
+		p->xmit = brcm_netdev_ops.xmit;
 		break;
 #endif
 	default:
-		ds->dst->ops = &notag_netdev_ops;
+		p->xmit	= dsa_slave_notag_xmit;
 		break;
 	}
 
-	SET_NETDEV_DEV(slave_dev, parent);
-	slave_dev->dev.of_node = ds->pd->port_dn[port];
-	slave_dev->vlan_features = master->vlan_features;
-
-	p = netdev_priv(slave_dev);
-	p->dev = slave_dev;
-	p->parent = ds;
-	p->port = port;
-
 	p->old_pause = -1;
 	p->old_link = -1;
 	p->old_duplex = -1;
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 8fbc21c0de78..83d3572cdb20 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -11,7 +11,6 @@
 
 #include <linux/etherdevice.h>
 #include <linux/list.h>
-#include <linux/netdevice.h>
 #include <linux/slab.h>
 #include "dsa_priv.h"
 
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index d7dbc5bda5c0..ce90c8bdc658 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -10,7 +10,6 @@
 
 #include <linux/etherdevice.h>
 #include <linux/list.h>
-#include <linux/netdevice.h>
 #include <linux/slab.h>
 #include "dsa_priv.h"
 
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 6b30abe89183..94fcce778679 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -10,7 +10,6 @@
 
 #include <linux/etherdevice.h>
 #include <linux/list.h>
-#include <linux/netdevice.h>
 #include <linux/slab.h>
 #include "dsa_priv.h"
 
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 5fe9444842c5..115fdca34077 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -10,7 +10,6 @@
 
 #include <linux/etherdevice.h>
 #include <linux/list.h>
-#include <linux/netdevice.h>
 #include <linux/slab.h>
 #include "dsa_priv.h"
 
-- 
cgit v1.2.3


From b4d2394d01bc642e95b2cba956d908423c1bef77 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 15 Sep 2014 13:00:27 -0400
Subject: dsa: Replace mii_bus with a generic host device

This change makes it so that instead of passing and storing a mii_bus we
instead pass and store a host_dev.  From there we can test to determine the
exact type of device, and can verify it is the correct device for our switch.

So for example it would be possible to pass a device pointer from a pci_dev
and instead of checking for a PHY ID we could check for a vendor and/or device
ID.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/plat-orion/common.c      |  2 +-
 drivers/net/dsa/bcm_sf2.c         |  2 +-
 drivers/net/dsa/mv88e6060.c       | 13 +++++++++----
 drivers/net/dsa/mv88e6123_61_65.c |  6 +++++-
 drivers/net/dsa/mv88e6131.c       |  6 +++++-
 drivers/net/dsa/mv88e6171.c       |  6 +++++-
 drivers/net/dsa/mv88e6xxx.c       |  4 ++--
 include/net/dsa.h                 |  9 +++++----
 net/dsa/dsa.c                     | 24 ++++++++----------------
 net/dsa/slave.c                   |  2 +-
 10 files changed, 42 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 3ec6e8e8d368..f5b00f41c4f6 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -499,7 +499,7 @@ void __init orion_ge00_switch_init(struct dsa_platform_data *d, int irq)
 
 	d->netdev = &orion_ge00.dev;
 	for (i = 0; i < d->nr_chips; i++)
-		d->chip[i].mii_bus = &orion_ge00_shared.dev;
+		d->chip[i].host_dev = &orion_ge00_shared.dev;
 	orion_switch_device.dev.platform_data = d;
 
 	platform_device_register(&orion_switch_device);
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index e9918c7f1792..02d7db320d90 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -129,7 +129,7 @@ static int bcm_sf2_sw_get_sset_count(struct dsa_switch *ds)
 	return BCM_SF2_STATS_SIZE;
 }
 
-static char *bcm_sf2_sw_probe(struct mii_bus *bus, int sw_addr)
+static char *bcm_sf2_sw_probe(struct device *host_dev, int sw_addr)
 {
 	return "Broadcom Starfighter 2";
 }
diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index d8037c1055ac..776e965dc9f4 100644
--- a/drivers/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -21,7 +21,8 @@
 
 static int reg_read(struct dsa_switch *ds, int addr, int reg)
 {
-	return mdiobus_read(ds->master_mii_bus, ds->pd->sw_addr + addr, reg);
+	return mdiobus_read(to_mii_bus(ds->master_dev),
+			    ds->pd->sw_addr + addr, reg);
 }
 
 #define REG_READ(addr, reg)					\
@@ -37,8 +38,8 @@ static int reg_read(struct dsa_switch *ds, int addr, int reg)
 
 static int reg_write(struct dsa_switch *ds, int addr, int reg, u16 val)
 {
-	return mdiobus_write(ds->master_mii_bus, ds->pd->sw_addr + addr,
-			     reg, val);
+	return mdiobus_write(to_mii_bus(ds->master_dev),
+			     ds->pd->sw_addr + addr, reg, val);
 }
 
 #define REG_WRITE(addr, reg, val)				\
@@ -50,10 +51,14 @@ static int reg_write(struct dsa_switch *ds, int addr, int reg, u16 val)
 			return __ret;				\
 	})
 
-static char *mv88e6060_probe(struct mii_bus *bus, int sw_addr)
+static char *mv88e6060_probe(struct device *host_dev, int sw_addr)
 {
+	struct mii_bus *bus = dsa_host_dev_to_mii_bus(host_dev);
 	int ret;
 
+	if (bus == NULL)
+		return NULL;
+
 	ret = mdiobus_read(bus, sw_addr + REG_PORT(0), 0x03);
 	if (ret >= 0) {
 		ret &= 0xfff0;
diff --git a/drivers/net/dsa/mv88e6123_61_65.c b/drivers/net/dsa/mv88e6123_61_65.c
index 975774f338c2..a332c53ff955 100644
--- a/drivers/net/dsa/mv88e6123_61_65.c
+++ b/drivers/net/dsa/mv88e6123_61_65.c
@@ -17,10 +17,14 @@
 #include <net/dsa.h>
 #include "mv88e6xxx.h"
 
-static char *mv88e6123_61_65_probe(struct mii_bus *bus, int sw_addr)
+static char *mv88e6123_61_65_probe(struct device *host_dev, int sw_addr)
 {
+	struct mii_bus *bus = dsa_host_dev_to_mii_bus(host_dev);
 	int ret;
 
+	if (bus == NULL)
+		return NULL;
+
 	ret = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), 0x03);
 	if (ret >= 0) {
 		if (ret == 0x1212)
diff --git a/drivers/net/dsa/mv88e6131.c b/drivers/net/dsa/mv88e6131.c
index 35541f2ceca3..244c735014fa 100644
--- a/drivers/net/dsa/mv88e6131.c
+++ b/drivers/net/dsa/mv88e6131.c
@@ -22,10 +22,14 @@
 #define ID_6095		0x0950
 #define ID_6131		0x1060
 
-static char *mv88e6131_probe(struct mii_bus *bus, int sw_addr)
+static char *mv88e6131_probe(struct device *host_dev, int sw_addr)
 {
+	struct mii_bus *bus = dsa_host_dev_to_mii_bus(host_dev);
 	int ret;
 
+	if (bus == NULL)
+		return NULL;
+
 	ret = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), 0x03);
 	if (ret >= 0) {
 		ret &= 0xfff0;
diff --git a/drivers/net/dsa/mv88e6171.c b/drivers/net/dsa/mv88e6171.c
index 03a70069a8c6..6365e30138af 100644
--- a/drivers/net/dsa/mv88e6171.c
+++ b/drivers/net/dsa/mv88e6171.c
@@ -17,10 +17,14 @@
 #include <net/dsa.h>
 #include "mv88e6xxx.h"
 
-static char *mv88e6171_probe(struct mii_bus *bus, int sw_addr)
+static char *mv88e6171_probe(struct device *host_dev, int sw_addr)
 {
+	struct mii_bus *bus = dsa_host_dev_to_mii_bus(host_dev);
 	int ret;
 
+	if (bus == NULL)
+		return NULL;
+
 	ret = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), 0x03);
 	if (ret >= 0) {
 		if ((ret & 0xfff0) == 0x1710)
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index 901d2a9704ef..d6f6428b27dc 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -78,7 +78,7 @@ int mv88e6xxx_reg_read(struct dsa_switch *ds, int addr, int reg)
 	int ret;
 
 	mutex_lock(&ps->smi_mutex);
-	ret = __mv88e6xxx_reg_read(ds->master_mii_bus,
+	ret = __mv88e6xxx_reg_read(to_mii_bus(ds->master_dev),
 				   ds->pd->sw_addr, addr, reg);
 	mutex_unlock(&ps->smi_mutex);
 
@@ -122,7 +122,7 @@ int mv88e6xxx_reg_write(struct dsa_switch *ds, int addr, int reg, u16 val)
 	int ret;
 
 	mutex_lock(&ps->smi_mutex);
-	ret = __mv88e6xxx_reg_write(ds->master_mii_bus,
+	ret = __mv88e6xxx_reg_write(to_mii_bus(ds->master_dev),
 				    ds->pd->sw_addr, addr, reg, val);
 	mutex_unlock(&ps->smi_mutex);
 
diff --git a/include/net/dsa.h b/include/net/dsa.h
index a55c4e6a4f0f..c779e9bba1b3 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -34,7 +34,7 @@ struct dsa_chip_data {
 	/*
 	 * How to access the switch configuration registers.
 	 */
-	struct device	*mii_bus;
+	struct device	*host_dev;
 	int		sw_addr;
 
 	/* Device tree node pointer for this specific switch chip
@@ -134,9 +134,9 @@ struct dsa_switch {
 	struct dsa_switch_driver	*drv;
 
 	/*
-	 * Reference to mii bus to use.
+	 * Reference to host device to use.
 	 */
-	struct mii_bus		*master_mii_bus;
+	struct device		*master_dev;
 
 	/*
 	 * Slave mii_bus and devices for the individual ports.
@@ -178,7 +178,7 @@ struct dsa_switch_driver {
 	/*
 	 * Probing and setup.
 	 */
-	char	*(*probe)(struct mii_bus *bus, int sw_addr);
+	char	*(*probe)(struct device *host_dev, int sw_addr);
 	int	(*setup)(struct dsa_switch *ds);
 	int	(*set_addr)(struct dsa_switch *ds, u8 *addr);
 
@@ -213,6 +213,7 @@ struct dsa_switch_driver {
 
 void register_switch_driver(struct dsa_switch_driver *type);
 void unregister_switch_driver(struct dsa_switch_driver *type);
+struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev);
 
 static inline void *ds_to_priv(struct dsa_switch *ds)
 {
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 1df0a7cf1e9e..b34d6978d773 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -43,7 +43,7 @@ void unregister_switch_driver(struct dsa_switch_driver *drv)
 EXPORT_SYMBOL_GPL(unregister_switch_driver);
 
 static struct dsa_switch_driver *
-dsa_switch_probe(struct mii_bus *bus, int sw_addr, char **_name)
+dsa_switch_probe(struct device *host_dev, int sw_addr, char **_name)
 {
 	struct dsa_switch_driver *ret;
 	struct list_head *list;
@@ -58,7 +58,7 @@ dsa_switch_probe(struct mii_bus *bus, int sw_addr, char **_name)
 
 		drv = list_entry(list, struct dsa_switch_driver, list);
 
-		name = drv->probe(bus, sw_addr);
+		name = drv->probe(host_dev, sw_addr);
 		if (name != NULL) {
 			ret = drv;
 			break;
@@ -75,7 +75,7 @@ dsa_switch_probe(struct mii_bus *bus, int sw_addr, char **_name)
 /* basic switch operations **************************************************/
 static struct dsa_switch *
 dsa_switch_setup(struct dsa_switch_tree *dst, int index,
-		 struct device *parent, struct mii_bus *bus)
+		 struct device *parent, struct device *host_dev)
 {
 	struct dsa_chip_data *pd = dst->pd->chip + index;
 	struct dsa_switch_driver *drv;
@@ -88,7 +88,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
 	/*
 	 * Probe for switch model.
 	 */
-	drv = dsa_switch_probe(bus, pd->sw_addr, &name);
+	drv = dsa_switch_probe(host_dev, pd->sw_addr, &name);
 	if (drv == NULL) {
 		printk(KERN_ERR "%s[%d]: could not detect attached switch\n",
 		       dst->master_netdev->name, index);
@@ -109,8 +109,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
 	ds->index = index;
 	ds->pd = dst->pd->chip + index;
 	ds->drv = drv;
-	ds->master_mii_bus = bus;
-
+	ds->master_dev = host_dev;
 
 	/*
 	 * Validate supplied switch configuration.
@@ -285,7 +284,7 @@ static struct device *dev_find_class(struct device *parent, char *class)
 	return device_find_child(parent, class, dev_is_class);
 }
 
-static struct mii_bus *dev_to_mii_bus(struct device *dev)
+struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev)
 {
 	struct device *d;
 
@@ -301,6 +300,7 @@ static struct mii_bus *dev_to_mii_bus(struct device *dev)
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(dsa_host_dev_to_mii_bus);
 
 static struct net_device *dev_to_net_device(struct device *dev)
 {
@@ -566,17 +566,9 @@ static int dsa_probe(struct platform_device *pdev)
 	dst->cpu_port = -1;
 
 	for (i = 0; i < pd->nr_chips; i++) {
-		struct mii_bus *bus;
 		struct dsa_switch *ds;
 
-		bus = dev_to_mii_bus(pd->chip[i].mii_bus);
-		if (bus == NULL) {
-			printk(KERN_ERR "%s[%d]: no mii bus found for "
-				"dsa switch\n", dev->name, i);
-			continue;
-		}
-
-		ds = dsa_switch_setup(dst, i, &pdev->dev, bus);
+		ds = dsa_switch_setup(dst, i, &pdev->dev, pd->chip[i].host_dev);
 		if (IS_ERR(ds)) {
 			printk(KERN_ERR "%s[%d]: couldn't create dsa switch "
 				"instance (error %ld)\n", dev->name, i,
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index e38a331111c0..90c9689ed362 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -44,7 +44,7 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds)
 	ds->slave_mii_bus->write = dsa_slave_phy_write;
 	snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d:%.2x",
 			ds->index, ds->pd->sw_addr);
-	ds->slave_mii_bus->parent = &ds->master_mii_bus->dev;
+	ds->slave_mii_bus->parent = ds->master_dev;
 }
 
 
-- 
cgit v1.2.3


From 64bdcbc449105377dd60c8da97cfc1663b39562c Mon Sep 17 00:00:00 2001
From: "Kashyap.Desai@avagotech.com" <Kashyap.Desai@avagotech.com>
Date: Wed, 20 Aug 2014 19:24:33 +0530
Subject: scsi: add use_cmd_list flag

Add a use_cmd_list flag in struct Scsi_Host to request keeping track of
all outstanding commands per device.

Default behaviour is not to keep track of cmd_list per sdev, as this may
introduce lock contention. (overhead is more on multi-node NUMA.), and
only enable it on the two drivers that need it.

Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/aacraid/linit.c |  1 +
 drivers/scsi/dpt_i2o.c       |  1 +
 drivers/scsi/scsi_lib.c      | 24 ++++++++++++------------
 include/scsi/scsi_host.h     |  1 +
 4 files changed, 15 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 63f576c9300a..a759cb2d4b15 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -1152,6 +1152,7 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	shost->irq = pdev->irq;
 	shost->unique_id = unique_id;
 	shost->max_cmd_len = 16;
+	shost->use_cmd_list = 1;
 
 	aac = (struct aac_dev *)shost->hostdata;
 	aac->base_start = pci_resource_start(pdev, 0);
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index 67283ef418ac..072f0ec2851e 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -2363,6 +2363,7 @@ static s32 adpt_scsi_host_alloc(adpt_hba* pHba, struct scsi_host_template *sht)
 	host->unique_id = (u32)sys_tbl_pa + pHba->unit;
 	host->sg_tablesize = pHba->sg_tablesize;
 	host->can_queue = pHba->post_fifo_size;
+	host->use_cmd_list = 1;
 
 	return 0;
 }
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index d837dc180522..b9a8ddd77eef 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -645,16 +645,18 @@ static void scsi_mq_free_sgtables(struct scsi_cmnd *cmd)
 static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd)
 {
 	struct scsi_device *sdev = cmd->device;
+	struct Scsi_Host *shost = sdev->host;
 	unsigned long flags;
 
-	BUG_ON(list_empty(&cmd->list));
-
 	scsi_mq_free_sgtables(cmd);
 	scsi_uninit_cmd(cmd);
 
-	spin_lock_irqsave(&sdev->list_lock, flags);
-	list_del_init(&cmd->list);
-	spin_unlock_irqrestore(&sdev->list_lock, flags);
+	if (shost->use_cmd_list) {
+		BUG_ON(list_empty(&cmd->list));
+		spin_lock_irqsave(&sdev->list_lock, flags);
+		list_del_init(&cmd->list);
+		spin_unlock_irqrestore(&sdev->list_lock, flags);
+	}
 }
 
 /*
@@ -1815,13 +1817,11 @@ static int scsi_mq_prep_fn(struct request *req)
 	INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler);
 	cmd->jiffies_at_alloc = jiffies;
 
-	/*
-	 * XXX: cmd_list lookups are only used by two drivers, try to get
-	 * rid of this list in common code.
-	 */
-	spin_lock_irq(&sdev->list_lock);
-	list_add_tail(&cmd->list, &sdev->cmd_list);
-	spin_unlock_irq(&sdev->list_lock);
+	if (shost->use_cmd_list) {
+		spin_lock_irq(&sdev->list_lock);
+		list_add_tail(&cmd->list, &sdev->cmd_list);
+		spin_unlock_irq(&sdev->list_lock);
+	}
 
 	sg = (void *)cmd + sizeof(struct scsi_cmnd) + shost->hostt->cmd_size;
 	cmd->sdb.table.sgl = sg;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index ba2034779961..cafb260ef2d3 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -680,6 +680,7 @@ struct Scsi_Host {
 	unsigned no_write_same:1;
 
 	unsigned use_blk_mq:1;
+	unsigned use_cmd_list:1;
 
 	/*
 	 * Optional work queue to be utilized by the transport
-- 
cgit v1.2.3


From 50c4e96411a6cd728f04cf70d8d6def57828b320 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 2 Sep 2014 11:35:50 -0400
Subject: scsi: don't store LUN bits in CDB[1] for USB mass-storage devices

The SCSI specification requires that the second Command Data Byte
should contain the LUN value in its high-order bits if the recipient
device reports SCSI level 2 or below.  Nevertheless, some USB
mass-storage devices use those bits for other purposes in
vendor-specific commands.  Currently Linux has no way to send such
commands, because the SCSI stack always overwrites the LUN bits.

Testing shows that Windows 7 and XP do not store the LUN bits in the
CDB when sending commands to a USB device.  This doesn't matter if the
device uses the Bulk-Only or UAS transports (which virtually all
modern USB mass-storage devices do), as these have a separate
mechanism for sending the LUN value.

Therefore this patch introduces a flag in the Scsi_Host structure to
inform the SCSI midlayer that a transport does not require the LUN
bits to be stored in the CDB, and it makes usb-storage set this flag
for all devices using the Bulk-Only transport.  (UAS is handled by a
separate driver, but it doesn't really matter because no SCSI-2 or
lower device is at all likely to use UAS.)

The patch also cleans up the code responsible for storing the LUN
value by adding a bitflag to the scsi_device structure.  The test for
whether to stick the LUN value in the CDB can be made when the device
is probed, and stored for future use rather than being made over and
over in the fast path.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-by: Tiziano Bacocco <tiziano.bacocco@gmail.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/scsi.c        |  8 ++------
 drivers/scsi/scsi_scan.c   | 10 ++++++++++
 drivers/scsi/scsi_sysfs.c  | 12 ++++++++++++
 drivers/usb/storage/usb.c  |  8 ++++++++
 include/scsi/scsi_device.h |  1 +
 include/scsi/scsi_host.h   |  3 +++
 6 files changed, 36 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index d81f3cc43ff1..1423cb17fbfd 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -670,14 +670,10 @@ int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
 		return SCSI_MLQUEUE_DEVICE_BUSY;
 	}
 
-	/*
-	 * If SCSI-2 or lower, store the LUN value in cmnd.
-	 */
-	if (cmd->device->scsi_level <= SCSI_2 &&
-	    cmd->device->scsi_level != SCSI_UNKNOWN) {
+	/* Store the LUN value in cmnd, if needed. */
+	if (cmd->device->lun_in_cdb)
 		cmd->cmnd[1] = (cmd->cmnd[1] & 0x1f) |
 			       (cmd->device->lun << 5 & 0xe0);
-	}
 
 	scsi_log_send(cmd);
 
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 56675dbbf681..f84c40188478 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -736,6 +736,16 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
 		sdev->scsi_level++;
 	sdev->sdev_target->scsi_level = sdev->scsi_level;
 
+	/*
+	 * If SCSI-2 or lower, and if the transport requires it,
+	 * store the LUN value in CDB[1].
+	 */
+	sdev->lun_in_cdb = 0;
+	if (sdev->scsi_level <= SCSI_2 &&
+	    sdev->scsi_level != SCSI_UNKNOWN &&
+	    !sdev->host->no_scsi2_lun_in_cdb)
+		sdev->lun_in_cdb = 1;
+
 	return 0;
 }
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 8b4105a22ac2..85e36f3a5585 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1263,7 +1263,19 @@ void scsi_sysfs_device_initialize(struct scsi_device *sdev)
 	sdev->sdev_dev.class = &sdev_class;
 	dev_set_name(&sdev->sdev_dev, "%d:%d:%d:%llu",
 		     sdev->host->host_no, sdev->channel, sdev->id, sdev->lun);
+	/*
+	 * Get a default scsi_level from the target (derived from sibling
+	 * devices).  This is the best we can do for guessing how to set
+	 * sdev->lun_in_cdb for the initial INQUIRY command.  For LUN 0 the
+	 * setting doesn't matter, because all the bits are zero anyway.
+	 * But it does matter for higher LUNs.
+	 */
 	sdev->scsi_level = starget->scsi_level;
+	if (sdev->scsi_level <= SCSI_2 &&
+			sdev->scsi_level != SCSI_UNKNOWN &&
+			!shost->no_scsi2_lun_in_cdb)
+		sdev->lun_in_cdb = 1;
+
 	transport_setup_device(&sdev->sdev_gendev);
 	spin_lock_irqsave(shost->host_lock, flags);
 	list_add_tail(&sdev->same_target_siblings, &starget->devices);
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index cedb29252a92..bf3f8e2de046 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -983,6 +983,14 @@ int usb_stor_probe2(struct us_data *us)
 	if (!(us->fflags & US_FL_SCM_MULT_TARG))
 		us_to_host(us)->max_id = 1;
 
+	/*
+	 * Like Windows, we won't store the LUN bits in CDB[1] for SCSI-2
+	 * devices using the Bulk-Only transport (even though this violates
+	 * the SCSI spec).
+	 */
+	if (us->transport == usb_stor_Bulk_transport)
+		us_to_host(us)->no_scsi2_lun_in_cdb = 1;
+
 	/* Find the endpoints and calculate pipe values */
 	result = get_pipes(us);
 	if (result)
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 1a0d1842962e..27ecee73bd72 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -174,6 +174,7 @@ struct scsi_device {
 	unsigned wce_default_on:1;	/* Cache is ON by default */
 	unsigned no_dif:1;	/* T10 PI (DIF) should be disabled */
 	unsigned broken_fua:1;		/* Don't set FUA bit */
+	unsigned lun_in_cdb:1;		/* Store LUN bits in CDB[1] */
 
 	atomic_t disk_events_disable_depth; /* disable depth for disk events */
 
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index cafb260ef2d3..d0f69a3210df 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -693,6 +693,9 @@ struct Scsi_Host {
 	 */
 	struct workqueue_struct *tmf_work_q;
 
+	/* The transport requires the LUN bits NOT to be stored in CDB[1] */
+	unsigned no_scsi2_lun_in_cdb:1;
+
 	/*
 	 * Value host_blocked counts down from
 	 */
-- 
cgit v1.2.3


From 6cff339bbd5f9eda7a5e8a521f91a88d046e6d0c Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:20 -0700
Subject: ipvs: Add destination address family to netlink interface

This is necessary to support heterogeneous pools.  For example, if you have
an ipv6 addressed network, you'll want to be able to forward ipv4 traffic
into it.

This patch enforces that destination address family is the same as service
family, as none of the forwarding mechanisms support anything else.

For the old setsockopt mechanism, we simply set the dest address family to
AF_INET as we do with the service.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  3 +++
 include/uapi/linux/ip_vs.h     |  3 +++
 net/netfilter/ipvs/ip_vs_ctl.c | 45 +++++++++++++++++++++++++++++++++++-------
 3 files changed, 44 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 624a8a54806d..b7e2b624d58e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -648,6 +648,9 @@ struct ip_vs_dest_user_kern {
 	/* thresholds for active connections */
 	u32			u_threshold;	/* upper threshold */
 	u32			l_threshold;	/* lower threshold */
+
+	/* Address family of addr */
+	u16			af;
 };
 
 
diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h
index fbcffe8041f7..cabe95d5b461 100644
--- a/include/uapi/linux/ip_vs.h
+++ b/include/uapi/linux/ip_vs.h
@@ -384,6 +384,9 @@ enum {
 	IPVS_DEST_ATTR_PERSIST_CONNS,	/* persistent connections */
 
 	IPVS_DEST_ATTR_STATS,		/* nested attribute for dest stats */
+
+	IPVS_DEST_ATTR_ADDR_FAMILY,	/* Address family of address */
+
 	__IPVS_DEST_ATTR_MAX,
 };
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index bd2b208ba56c..594cec7ebc43 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -816,6 +816,8 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	dest->u_threshold = udest->u_threshold;
 	dest->l_threshold = udest->l_threshold;
 
+	dest->af = udest->af;
+
 	spin_lock_bh(&dest->dst_lock);
 	__ip_vs_dst_cache_reset(dest);
 	spin_unlock_bh(&dest->dst_lock);
@@ -846,8 +848,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 
 	EnterFunction(2);
 
+	/* Temporary for consistency */
+	if (udest->af != svc->af)
+		return -EINVAL;
+
 #ifdef CONFIG_IP_VS_IPV6
-	if (svc->af == AF_INET6) {
+	if (udest->af == AF_INET6) {
 		atype = ipv6_addr_type(&udest->addr.in6);
 		if ((!(atype & IPV6_ADDR_UNICAST) ||
 			atype & IPV6_ADDR_LINKLOCAL) &&
@@ -875,12 +881,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 		u64_stats_init(&ip_vs_dest_stats->syncp);
 	}
 
-	dest->af = svc->af;
+	dest->af = udest->af;
 	dest->protocol = svc->protocol;
 	dest->vaddr = svc->addr;
 	dest->vport = svc->port;
 	dest->vfwmark = svc->fwmark;
-	ip_vs_addr_copy(svc->af, &dest->addr, &udest->addr);
+	ip_vs_addr_copy(udest->af, &dest->addr, &udest->addr);
 	dest->port = udest->port;
 
 	atomic_set(&dest->activeconns, 0);
@@ -928,7 +934,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 		return -ERANGE;
 	}
 
-	ip_vs_addr_copy(svc->af, &daddr, &udest->addr);
+	ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
@@ -949,7 +955,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 	if (dest != NULL) {
 		IP_VS_DBG_BUF(3, "Get destination %s:%u from trash, "
 			      "dest->refcnt=%d, service %u/%s:%u\n",
-			      IP_VS_DBG_ADDR(svc->af, &daddr), ntohs(dport),
+			      IP_VS_DBG_ADDR(udest->af, &daddr), ntohs(dport),
 			      atomic_read(&dest->refcnt),
 			      dest->vfwmark,
 			      IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
@@ -992,7 +998,7 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 		return -ERANGE;
 	}
 
-	ip_vs_addr_copy(svc->af, &daddr, &udest->addr);
+	ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
@@ -2244,6 +2250,7 @@ static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
 	udest->weight		= udest_compat->weight;
 	udest->u_threshold	= udest_compat->u_threshold;
 	udest->l_threshold	= udest_compat->l_threshold;
+	udest->af		= AF_INET;
 }
 
 static int
@@ -2480,6 +2487,12 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
 			if (count >= get->num_dests)
 				break;
 
+			/* Cannot expose heterogeneous members via sockopt
+			 * interface
+			 */
+			if (dest->af != svc->af)
+				continue;
+
 			entry.addr = dest->addr.ip;
 			entry.port = dest->port;
 			entry.conn_flags = atomic_read(&dest->conn_flags);
@@ -2777,6 +2790,7 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
 	[IPVS_DEST_ATTR_INACT_CONNS]	= { .type = NLA_U32 },
 	[IPVS_DEST_ATTR_PERSIST_CONNS]	= { .type = NLA_U32 },
 	[IPVS_DEST_ATTR_STATS]		= { .type = NLA_NESTED },
+	[IPVS_DEST_ATTR_ADDR_FAMILY]	= { .type = NLA_U16 },
 };
 
 static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
@@ -3032,7 +3046,8 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
 	    nla_put_u32(skb, IPVS_DEST_ATTR_INACT_CONNS,
 			atomic_read(&dest->inactconns)) ||
 	    nla_put_u32(skb, IPVS_DEST_ATTR_PERSIST_CONNS,
-			atomic_read(&dest->persistconns)))
+			atomic_read(&dest->persistconns)) ||
+	    nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af))
 		goto nla_put_failure;
 	if (ip_vs_genl_fill_stats(skb, IPVS_DEST_ATTR_STATS, &dest->stats))
 		goto nla_put_failure;
@@ -3113,6 +3128,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 {
 	struct nlattr *attrs[IPVS_DEST_ATTR_MAX + 1];
 	struct nlattr *nla_addr, *nla_port;
+	struct nlattr *nla_addr_family;
 
 	/* Parse mandatory identifying destination fields first */
 	if (nla == NULL ||
@@ -3121,6 +3137,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 
 	nla_addr	= attrs[IPVS_DEST_ATTR_ADDR];
 	nla_port	= attrs[IPVS_DEST_ATTR_PORT];
+	nla_addr_family	= attrs[IPVS_DEST_ATTR_ADDR_FAMILY];
 
 	if (!(nla_addr && nla_port))
 		return -EINVAL;
@@ -3130,6 +3147,11 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 	nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr));
 	udest->port = nla_get_be16(nla_port);
 
+	if (nla_addr_family)
+		udest->af = nla_get_u16(nla_addr_family);
+	else
+		udest->af = 0;
+
 	/* If a full entry was requested, check for the additional fields */
 	if (full_entry) {
 		struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh,
@@ -3357,6 +3379,15 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
 					    need_full_dest);
 		if (ret)
 			goto out;
+
+		/* Old protocols did not allow the user to specify address
+		 * family, so we set it to zero instead.  We also didn't
+		 * allow heterogeneous pools in the old code, so it's safe
+		 * to assume that this will have the same address family as
+		 * the service.
+		 */
+		if (udest.af == 0)
+			udest.af = svc->af;
 	}
 
 	switch (cmd) {
-- 
cgit v1.2.3


From 655eef103d0bd99f540a52f7ede032e120756846 Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:21 -0700
Subject: ipvs: Supply destination addr family to ip_vs_{lookup_dest,find_dest}

We need to remove the assumption that virtual address family is the same as
real address family in order to support heterogeneous services (that is,
services with v4 vips and v6 backends or the opposite).

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |  5 +++--
 net/netfilter/ipvs/ip_vs_conn.c |  8 +++++++-
 net/netfilter/ipvs/ip_vs_ctl.c  | 24 ++++++++++++------------
 net/netfilter/ipvs/ip_vs_sync.c | 10 ++++++++--
 4 files changed, 30 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index b7e2b624d58e..2fa1155b24f7 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1399,8 +1399,9 @@ void ip_vs_unregister_nl_ioctl(void);
 int ip_vs_control_init(void);
 void ip_vs_control_cleanup(void);
 struct ip_vs_dest *
-ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
-		__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
+ip_vs_find_dest(struct net *net, int svc_af, int dest_af,
+		const union nf_inet_addr *daddr, __be16 dport,
+		const union nf_inet_addr *vaddr, __be16 vport,
 		__u16 protocol, __u32 fwmark, __u32 flags);
 void ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 610e19c0e13f..8f4c602bb34b 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -616,7 +616,13 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	struct ip_vs_dest *dest;
 
 	rcu_read_lock();
-	dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr,
+
+	/* This function is only invoked by the synchronization code. We do
+	 * not currently support heterogeneous pools with synchronization,
+	 * so we can make the assumption that the svc_af is the same as the
+	 * dest_af
+	 */
+	dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, cp->af, &cp->daddr,
 			       cp->dport, &cp->vaddr, cp->vport,
 			       cp->protocol, cp->fwmark, cp->flags);
 	if (dest) {
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 594cec7ebc43..c840d895bd1a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -574,8 +574,8 @@ bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol,
  * Called under RCU lock.
  */
 static struct ip_vs_dest *
-ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
-		  __be16 dport)
+ip_vs_lookup_dest(struct ip_vs_service *svc, int dest_af,
+		  const union nf_inet_addr *daddr, __be16 dport)
 {
 	struct ip_vs_dest *dest;
 
@@ -583,9 +583,9 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
 	 * Find the destination for the given service
 	 */
 	list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
-		if ((dest->af == svc->af)
-		    && ip_vs_addr_equal(svc->af, &dest->addr, daddr)
-		    && (dest->port == dport)) {
+		if ((dest->af == dest_af) &&
+		    ip_vs_addr_equal(dest_af, &dest->addr, daddr) &&
+		    (dest->port == dport)) {
 			/* HIT */
 			return dest;
 		}
@@ -602,7 +602,7 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
  * on the backup.
  * Called under RCU lock, no refcnt is returned.
  */
-struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int af,
+struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int svc_af, int dest_af,
 				   const union nf_inet_addr *daddr,
 				   __be16 dport,
 				   const union nf_inet_addr *vaddr,
@@ -613,14 +613,14 @@ struct ip_vs_dest *ip_vs_find_dest(struct net  *net, int af,
 	struct ip_vs_service *svc;
 	__be16 port = dport;
 
-	svc = ip_vs_service_find(net, af, fwmark, protocol, vaddr, vport);
+	svc = ip_vs_service_find(net, svc_af, fwmark, protocol, vaddr, vport);
 	if (!svc)
 		return NULL;
 	if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ)
 		port = 0;
-	dest = ip_vs_lookup_dest(svc, daddr, port);
+	dest = ip_vs_lookup_dest(svc, dest_af, daddr, port);
 	if (!dest)
-		dest = ip_vs_lookup_dest(svc, daddr, port ^ dport);
+		dest = ip_vs_lookup_dest(svc, dest_af, daddr, port ^ dport);
 	return dest;
 }
 
@@ -938,7 +938,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
-	dest = ip_vs_lookup_dest(svc, &daddr, dport);
+	dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport);
 	rcu_read_unlock();
 
 	if (dest != NULL) {
@@ -1002,7 +1002,7 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
-	dest = ip_vs_lookup_dest(svc, &daddr, dport);
+	dest = ip_vs_lookup_dest(svc, udest->af, &daddr, dport);
 	rcu_read_unlock();
 
 	if (dest == NULL) {
@@ -1084,7 +1084,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 
 	/* We use function that requires RCU lock */
 	rcu_read_lock();
-	dest = ip_vs_lookup_dest(svc, &udest->addr, dport);
+	dest = ip_vs_lookup_dest(svc, udest->af, &udest->addr, dport);
 	rcu_read_unlock();
 
 	if (dest == NULL) {
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index eadffb29dec0..edd266414b7d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -880,8 +880,14 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 		 * but still handled.
 		 */
 		rcu_read_lock();
-		dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr,
-				       param->vport, protocol, fwmark, flags);
+		/* This function is only invoked by the synchronization
+		 * code. We do not currently support heterogeneous pools
+		 * with synchronization, so we can make the assumption that
+		 * the svc_af is the same as the dest_af
+		 */
+		dest = ip_vs_find_dest(net, type, type, daddr, dport,
+				       param->vaddr, param->vport, protocol,
+				       fwmark, flags);
 
 		cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark);
 		rcu_read_unlock();
-- 
cgit v1.2.3


From ba38528aae6ee2d22226c6a78727ddc13512b068 Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:23 -0700
Subject: ipvs: Supply destination address family to ip_vs_conn_new

The assumption that dest af is equal to service af is now unreliable, so we
must specify it manually so as not to copy just the first 4 bytes of a v6
address or doing an illegal read of 16 butes on a v6 address.

We "lie" in two places: for synchronization (which we will explicitly
disallow from happening when we have heterogeneous pools) and for black
hole addresses where there's no real dest.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             | 3 ++-
 net/netfilter/ipvs/ip_vs_conn.c | 5 +++--
 net/netfilter/ipvs/ip_vs_core.c | 9 +++++----
 net/netfilter/ipvs/ip_vs_ftp.c  | 6 ++++--
 net/netfilter/ipvs/ip_vs_sync.c | 3 ++-
 5 files changed, 16 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 2fa1155b24f7..7600dbe5780e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -535,6 +535,7 @@ struct ip_vs_conn {
 	union nf_inet_addr      daddr;          /* destination address */
 	volatile __u32          flags;          /* status flags */
 	__u16                   protocol;       /* Which protocol (TCP/UDP) */
+	__u16			daf;		/* Address family of the dest */
 #ifdef CONFIG_NET_NS
 	struct net              *net;           /* Name space */
 #endif
@@ -1213,7 +1214,7 @@ static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
 void ip_vs_conn_put(struct ip_vs_conn *cp);
 void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
 
-struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p,
+struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
 				  const union nf_inet_addr *daddr,
 				  __be16 dport, unsigned int flags,
 				  struct ip_vs_dest *dest, __u32 fwmark);
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 8f4c602bb34b..fdb4880a3a79 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -854,7 +854,7 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
  *	Create a new connection entry and hash it into the ip_vs_conn_tab
  */
 struct ip_vs_conn *
-ip_vs_conn_new(const struct ip_vs_conn_param *p,
+ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
 	       const union nf_inet_addr *daddr, __be16 dport, unsigned int flags,
 	       struct ip_vs_dest *dest, __u32 fwmark)
 {
@@ -873,6 +873,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
 	ip_vs_conn_net_set(cp, p->net);
 	cp->af		   = p->af;
+	cp->daf		   = dest_af;
 	cp->protocol	   = p->protocol;
 	ip_vs_addr_set(p->af, &cp->caddr, p->caddr);
 	cp->cport	   = p->cport;
@@ -880,7 +881,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
 		       &cp->vaddr, p->vaddr);
 	cp->vport	   = p->vport;
-	ip_vs_addr_set(p->af, &cp->daddr, daddr);
+	ip_vs_addr_set(cp->daf, &cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
 	cp->fwmark         = fwmark;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5c34e8d42e01..1f6ecb74821f 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -328,7 +328,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * This adds param.pe_data to the template,
 		 * and thus param.pe_data will be destroyed
 		 * when the template expires */
-		ct = ip_vs_conn_new(&param, &dest->addr, dport,
+		ct = ip_vs_conn_new(&param, dest->af, &dest->addr, dport,
 				    IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
 		if (ct == NULL) {
 			kfree(param.pe_data);
@@ -357,7 +357,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, &iph->saddr,
 			      src_port, &iph->daddr, dst_port, &param);
 
-	cp = ip_vs_conn_new(&param, &dest->addr, dport, flags, dest, skb->mark);
+	cp = ip_vs_conn_new(&param, dest->af, &dest->addr, dport, flags, dest,
+			    skb->mark);
 	if (cp == NULL) {
 		ip_vs_conn_put(ct);
 		*ignored = -1;
@@ -479,7 +480,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 		ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
 				      &iph->saddr, pptr[0], &iph->daddr,
 				      pptr[1], &p);
-		cp = ip_vs_conn_new(&p, &dest->addr,
+		cp = ip_vs_conn_new(&p, dest->af, &dest->addr,
 				    dest->port ? dest->port : pptr[1],
 				    flags, dest, skb->mark);
 		if (!cp) {
@@ -550,7 +551,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 			ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
 					      &iph->saddr, pptr[0],
 					      &iph->daddr, pptr[1], &p);
-			cp = ip_vs_conn_new(&p, &daddr, 0,
+			cp = ip_vs_conn_new(&p, svc->af, &daddr, 0,
 					    IP_VS_CONN_F_BYPASS | flags,
 					    NULL, skb->mark);
 			if (!cp)
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 77c173282f38..a64fa15790e5 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -233,7 +233,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 			ip_vs_conn_fill_param(ip_vs_conn_net(cp),
 					      AF_INET, IPPROTO_TCP, &cp->caddr,
 					      0, &cp->vaddr, port, &p);
-			n_cp = ip_vs_conn_new(&p, &from, port,
+			/* As above, this is ipv4 only */
+			n_cp = ip_vs_conn_new(&p, AF_INET, &from, port,
 					      IP_VS_CONN_F_NO_CPORT |
 					      IP_VS_CONN_F_NFCT,
 					      cp->dest, skb->mark);
@@ -396,7 +397,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 				      htons(ntohs(cp->vport)-1), &p);
 		n_cp = ip_vs_conn_in_get(&p);
 		if (!n_cp) {
-			n_cp = ip_vs_conn_new(&p, &cp->daddr,
+			/* This is ipv4 only */
+			n_cp = ip_vs_conn_new(&p, AF_INET, &cp->daddr,
 					      htons(ntohs(cp->dport)-1),
 					      IP_VS_CONN_F_NFCT, cp->dest,
 					      skb->mark);
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index edd266414b7d..7162c86fd50d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -889,7 +889,8 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
 				       param->vaddr, param->vport, protocol,
 				       fwmark, flags);
 
-		cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark);
+		cp = ip_vs_conn_new(param, type, daddr, dport, flags, dest,
+				    fwmark);
 		rcu_read_unlock();
 		if (!cp) {
 			kfree(param->pe_data);
-- 
cgit v1.2.3


From 391f503d69779867f05e9296ae523e9002c2d7ee Mon Sep 17 00:00:00 2001
From: Alex Gartrell <agartrell@fb.com>
Date: Tue, 9 Sep 2014 16:40:24 -0700
Subject: ipvs: prevent mixing heterogeneous pools and synchronization

The synchronization protocol is not compatible with heterogeneous pools, so
we need to verify that we're not turning both on at the same time.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h            |  4 ++++
 net/netfilter/ipvs/ip_vs_ctl.c | 15 +++++++++++++++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 7600dbe5780e..576d7f0bed5d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -990,6 +990,10 @@ struct netns_ipvs {
 	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 	/* net name space ptr */
 	struct net		*net;            /* Needed by timer routines */
+	/* Number of heterogeneous destinations, needed because
+	 * heterogeneous are not supported when synchronization is
+	 * enabled */
+	unsigned int		mixed_address_family_dests;
 };
 
 #define DEFAULT_SYNC_THRESHOLD	3
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 6bd2cc682137..462760eded94 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -779,6 +779,12 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	struct ip_vs_scheduler *sched;
 	int conn_flags;
 
+	/* We cannot modify an address and change the address family */
+	BUG_ON(!add && udest->af != dest->af);
+
+	if (add && udest->af != svc->af)
+		ipvs->mixed_address_family_dests++;
+
 	/* set the weight and the flags */
 	atomic_set(&dest->weight, udest->weight);
 	conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
@@ -1061,6 +1067,9 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
 	list_del_rcu(&dest->n_list);
 	svc->num_dests--;
 
+	if (dest->af != svc->af)
+		net_ipvs(svc->net)->mixed_address_family_dests--;
+
 	if (svcupd) {
 		struct ip_vs_scheduler *sched;
 
@@ -3256,6 +3265,12 @@ static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs)
 	      attrs[IPVS_DAEMON_ATTR_SYNC_ID]))
 		return -EINVAL;
 
+	/* The synchronization protocol is incompatible with mixed family
+	 * services
+	 */
+	if (net_ipvs(net)->mixed_address_family_dests > 0)
+		return -EINVAL;
+
 	return start_sync_thread(net,
 				 nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]),
 				 nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]),
-- 
cgit v1.2.3


From 2e151c70dfb0075ff83bec305c52a9da1ba49089 Mon Sep 17 00:00:00 2001
From: Peter Neubauer <pneubauer@bluerwhite.org>
Date: Fri, 12 Sep 2014 13:06:13 +0200
Subject: x86: HPET force enable for e6xx based systems

As the Soekris net6501 and other e6xx based systems do not have
any ACPI implementation, HPET won't get enabled.
This patch enables HPET on such platforms.

[    0.430149] pci 0000:00:01.0: Force enabled HPET at 0xfed00000
[    0.644838] HPET: 3 timers in total, 0 timers will be used for per-cpu timer

Original patch by Peter Neubauer (http://www.mail-archive.com/soekris-tech@lists.soekris.com/msg06462.html)
slightly modified by Conrad Kostecki <ck@conrad-kostecki.de> and massaged
accoring to Thomas Gleixners <tglx@linutronix.de> by me.

Suggested-by: Conrad Kostecki <ck@conrad-kostecki.de>
Signed-off-by: Eric Sesterhenn <eric.sesterhenn@lsexperts.de>
Cc: Peter Neubauer <pneubauer@bluerwhite.org>
Link: http://lkml.kernel.org/r/5412D3A5.2030909@lsexperts.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/quirks.c | 18 ++++++++++++++++++
 include/linux/pci_ids.h  |  1 +
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index ff898bbf579d..176a0f99d4da 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -497,6 +497,24 @@ void force_hpet_resume(void)
 	}
 }
 
+/*
+ * According to the datasheet e6xx systems have the HPET hardwired to
+ * 0xfed00000
+ */
+static void e6xx_force_enable_hpet(struct pci_dev *dev)
+{
+	if (hpet_address || force_hpet_address)
+		return;
+
+	force_hpet_address = 0xFED00000;
+	force_hpet_resume_type = NONE_FORCE_HPET_RESUME;
+	dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at "
+		"0x%lx\n", force_hpet_address);
+	return;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU,
+			 e6xx_force_enable_hpet);
+
 /*
  * HPET MSI on some boards (ATI SB700/SB800) has side effect on
  * floppy DMA. Disable HPET MSI on such platforms.
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 6ed0bb73a864..aa0d39073e9c 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2860,6 +2860,7 @@
 #define PCI_DEVICE_ID_INTEL_82372FB_1	0x7601
 #define PCI_DEVICE_ID_INTEL_SCH_LPC	0x8119
 #define PCI_DEVICE_ID_INTEL_SCH_IDE	0x811a
+#define PCI_DEVICE_ID_INTEL_E6XX_CU	0x8183
 #define PCI_DEVICE_ID_INTEL_ITC_LPC	0x8186
 #define PCI_DEVICE_ID_INTEL_82454GX	0x84c4
 #define PCI_DEVICE_ID_INTEL_82450GX	0x84c5
-- 
cgit v1.2.3


From 21231f81f13db2883f11664b67fc6fb2690e6af2 Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Mon, 18 Aug 2014 22:07:12 +0200
Subject: ARM: imx: clk-vf610: Add USBPHY clocks

This commit adds PLL7 which is required for USBPHY1. It also adds
the USB PHY and USB Controller clocks and the gates to enable them.

Acked-by: Jingchang Lu <jingchang.lu@freescale.com>
Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-vf610.c           | 12 ++++++++++--
 include/dt-bindings/clock/vf610-clock.h |  5 ++++-
 2 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-vf610.c b/arch/arm/mach-imx/clk-vf610.c
index a41ed73219da..a17818475050 100644
--- a/arch/arm/mach-imx/clk-vf610.c
+++ b/arch/arm/mach-imx/clk-vf610.c
@@ -58,6 +58,8 @@
 #define PFD_PLL1_BASE		(anatop_base + 0x2b0)
 #define PFD_PLL2_BASE		(anatop_base + 0x100)
 #define PFD_PLL3_BASE		(anatop_base + 0xf0)
+#define PLL3_CTRL		(anatop_base + 0x10)
+#define PLL7_CTRL		(anatop_base + 0x20)
 
 static void __iomem *anatop_base;
 static void __iomem *ccm_base;
@@ -154,6 +156,9 @@ static void __init vf610_clocks_init(struct device_node *ccm_node)
 	clk[VF610_CLK_PLL5_MAIN] = imx_clk_fixed_factor("pll5_main", "fast_clk_sel", 125, 6);
 	/* pll6: default 960Mhz */
 	clk[VF610_CLK_PLL6_MAIN] = imx_clk_fixed_factor("pll6_main", "fast_clk_sel", 40, 1);
+	/* pll7: USB1 PLL at 480MHz */
+	clk[VF610_CLK_PLL7_MAIN] = imx_clk_pllv3(IMX_PLLV3_USB,	"pll7_main", "fast_clk_sel", PLL7_CTRL, 0x2);
+
 	clk[VF610_CLK_PLL1_PFD_SEL] = imx_clk_mux("pll1_pfd_sel", CCM_CCSR, 16, 3, pll1_sels, 5);
 	clk[VF610_CLK_PLL2_PFD_SEL] = imx_clk_mux("pll2_pfd_sel", CCM_CCSR, 19, 3, pll2_sels, 5);
 	clk[VF610_CLK_SYS_SEL] = imx_clk_mux("sys_sel", CCM_CCSR, 0, 3, sys_sels, ARRAY_SIZE(sys_sels));
@@ -166,8 +171,11 @@ static void __init vf610_clocks_init(struct device_node *ccm_node)
 	clk[VF610_CLK_PLL4_MAIN_DIV] = clk_register_divider_table(NULL, "pll4_main_div", "pll4_main", 0, CCM_CACRR, 6, 3, 0, pll4_main_div_table, &imx_ccm_lock);
 	clk[VF610_CLK_PLL6_MAIN_DIV] = imx_clk_divider("pll6_main_div", "pll6_main", CCM_CACRR, 21, 1);
 
-	clk[VF610_CLK_USBC0] = imx_clk_gate2("usbc0", "pll3_main", CCM_CCGR1, CCM_CCGRx_CGn(4));
-	clk[VF610_CLK_USBC1] = imx_clk_gate2("usbc1", "pll3_main", CCM_CCGR7, CCM_CCGRx_CGn(4));
+	clk[VF610_CLK_USBPHY0] = imx_clk_gate("usbphy0", "pll3_main", PLL3_CTRL, 6);
+	clk[VF610_CLK_USBPHY1] = imx_clk_gate("usbphy1", "pll7_main", PLL7_CTRL, 6);
+
+	clk[VF610_CLK_USBC0] = imx_clk_gate2("usbc0", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(4));
+	clk[VF610_CLK_USBC1] = imx_clk_gate2("usbc1", "ipg_bus", CCM_CCGR7, CCM_CCGRx_CGn(4));
 
 	clk[VF610_CLK_QSPI0_SEL] = imx_clk_mux("qspi0_sel", CCM_CSCMR1, 22, 2, qspi_sels, 4);
 	clk[VF610_CLK_QSPI0_EN] = imx_clk_gate("qspi0_en", "qspi0_sel", CCM_CSCDR3, 4);
diff --git a/include/dt-bindings/clock/vf610-clock.h b/include/dt-bindings/clock/vf610-clock.h
index 00953d9484cb..d6b56b21539b 100644
--- a/include/dt-bindings/clock/vf610-clock.h
+++ b/include/dt-bindings/clock/vf610-clock.h
@@ -166,6 +166,9 @@
 #define VF610_CLK_DMAMUX3		153
 #define VF610_CLK_FLEXCAN0_EN		154
 #define VF610_CLK_FLEXCAN1_EN		155
-#define VF610_CLK_END			156
+#define VF610_CLK_PLL7_MAIN		156
+#define VF610_CLK_USBPHY0		157
+#define VF610_CLK_USBPHY1		158
+#define VF610_CLK_END			159
 
 #endif /* __DT_BINDINGS_CLOCK_VF610_H */
-- 
cgit v1.2.3


From 7bce3d23ecfd327bd277598d67e93655fb4cc0ed Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@freescale.com>
Date: Fri, 8 Aug 2014 15:02:47 +0800
Subject: ARM: clk-imx6q: refine clock tree for ESAI

There are three clock for ESAI, esai_extal, esai_ipg, esai_mem. Rename
'esai' to 'esai_extal', 'esai_ahb' to 'esai_mem', and add 'esai_ipg'.
Make the clock for ESAI more clear and align them with imx6sx.

Signed-off-by: Shengjiu Wang <shengjiu.wang@freescale.com>
Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-imx6q.c             | 7 ++++---
 include/dt-bindings/clock/imx6qdl-clock.h | 7 ++++---
 2 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 29d412975aff..2edcebf67cee 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -64,7 +64,7 @@ static const char *cko2_sels[] = {
 	"ipu2", "vdo_axi", "osc", "gpu2d_core",
 	"gpu3d_core", "usdhc2", "ssi1", "ssi2",
 	"ssi3", "gpu3d_shader", "vpu_axi", "can_root",
-	"ldb_di0", "ldb_di1", "esai", "eim_slow",
+	"ldb_di0", "ldb_di1", "esai_extal", "eim_slow",
 	"uart_serial", "spdif", "asrc", "hsi_tx",
 };
 static const char *cko_sels[] = { "cko1", "cko2", };
@@ -331,8 +331,9 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	else
 		clk[IMX6Q_CLK_ECSPI5] = imx_clk_gate2("ecspi5",        "ecspi_root",        base + 0x6c, 8);
 	clk[IMX6QDL_CLK_ENET]         = imx_clk_gate2("enet",          "ipg",               base + 0x6c, 10);
-	clk[IMX6QDL_CLK_ESAI]         = imx_clk_gate2_shared("esai",   "esai_podf",         base + 0x6c, 16, &share_count_esai);
-	clk[IMX6QDL_CLK_ESAI_AHB]     = imx_clk_gate2_shared("esai_ahb", "ahb",             base + 0x6c, 16, &share_count_esai);
+	clk[IMX6QDL_CLK_ESAI_EXTAL]   = imx_clk_gate2_shared("esai_extal",   "esai_podf",   base + 0x6c, 16, &share_count_esai);
+	clk[IMX6QDL_CLK_ESAI_IPG]     = imx_clk_gate2_shared("esai_ipg",   "ipg",           base + 0x6c, 16, &share_count_esai);
+	clk[IMX6QDL_CLK_ESAI_MEM]     = imx_clk_gate2_shared("esai_mem", "ahb",             base + 0x6c, 16, &share_count_esai);
 	clk[IMX6QDL_CLK_GPT_IPG]      = imx_clk_gate2("gpt_ipg",       "ipg",               base + 0x6c, 20);
 	clk[IMX6QDL_CLK_GPT_IPG_PER]  = imx_clk_gate2("gpt_ipg_per",   "ipg_per",           base + 0x6c, 22);
 	if (cpu_is_imx6dl())
diff --git a/include/dt-bindings/clock/imx6qdl-clock.h b/include/dt-bindings/clock/imx6qdl-clock.h
index 654151e24288..323e8650f198 100644
--- a/include/dt-bindings/clock/imx6qdl-clock.h
+++ b/include/dt-bindings/clock/imx6qdl-clock.h
@@ -128,7 +128,7 @@
 #define IMX6Q_CLK_ECSPI5			116
 #define IMX6DL_CLK_I2C4				116
 #define IMX6QDL_CLK_ENET			117
-#define IMX6QDL_CLK_ESAI			118
+#define IMX6QDL_CLK_ESAI_EXTAL			118
 #define IMX6QDL_CLK_GPT_IPG			119
 #define IMX6QDL_CLK_GPT_IPG_PER			120
 #define IMX6QDL_CLK_GPU2D_CORE			121
@@ -218,7 +218,8 @@
 #define IMX6QDL_CLK_LVDS2_SEL			205
 #define IMX6QDL_CLK_LVDS1_GATE			206
 #define IMX6QDL_CLK_LVDS2_GATE			207
-#define IMX6QDL_CLK_ESAI_AHB			208
-#define IMX6QDL_CLK_END				209
+#define IMX6QDL_CLK_ESAI_IPG			208
+#define IMX6QDL_CLK_ESAI_MEM			209
+#define IMX6QDL_CLK_END				210
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6QDL_H */
-- 
cgit v1.2.3


From aec247d4ac578693ee75ac2bf10eac1c29299c45 Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@freescale.com>
Date: Thu, 4 Sep 2014 17:48:58 +0800
Subject: ARM: clk-imx6q: refine clock tree for ASRC

ASRC has "asrc", "asrc_ipg", "asrc_mem" clocks, and they share
the same gate bits.

Signed-off-by: Shengjiu Wang <shengjiu.wang@freescale.com>
Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-imx6q.c             | 5 ++++-
 include/dt-bindings/clock/imx6qdl-clock.h | 4 +++-
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 2edcebf67cee..d5bf1e2940bf 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -107,6 +107,7 @@ static struct clk_div_table video_div_table[] = {
 };
 
 static unsigned int share_count_esai;
+static unsigned int share_count_asrc;
 
 static void __init imx6q_clocks_init(struct device_node *ccm_node)
 {
@@ -317,7 +318,9 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 
 	/*                                            name             parent_name          reg         shift */
 	clk[IMX6QDL_CLK_APBH_DMA]     = imx_clk_gate2("apbh_dma",      "usdhc3",            base + 0x68, 4);
-	clk[IMX6QDL_CLK_ASRC]         = imx_clk_gate2("asrc",          "asrc_podf",         base + 0x68, 6);
+	clk[IMX6QDL_CLK_ASRC]         = imx_clk_gate2_shared("asrc",         "asrc_podf",   base + 0x68, 6, &share_count_asrc);
+	clk[IMX6QDL_CLK_ASRC_IPG]     = imx_clk_gate2_shared("asrc_ipg",     "ahb",         base + 0x68, 6, &share_count_asrc);
+	clk[IMX6QDL_CLK_ASRC_MEM]     = imx_clk_gate2_shared("asrc_mem",     "ahb",         base + 0x68, 6, &share_count_asrc);
 	clk[IMX6QDL_CLK_CAN1_IPG]     = imx_clk_gate2("can1_ipg",      "ipg",               base + 0x68, 14);
 	clk[IMX6QDL_CLK_CAN1_SERIAL]  = imx_clk_gate2("can1_serial",   "can_root",          base + 0x68, 16);
 	clk[IMX6QDL_CLK_CAN2_IPG]     = imx_clk_gate2("can2_ipg",      "ipg",               base + 0x68, 18);
diff --git a/include/dt-bindings/clock/imx6qdl-clock.h b/include/dt-bindings/clock/imx6qdl-clock.h
index 323e8650f198..1e996135cfc7 100644
--- a/include/dt-bindings/clock/imx6qdl-clock.h
+++ b/include/dt-bindings/clock/imx6qdl-clock.h
@@ -220,6 +220,8 @@
 #define IMX6QDL_CLK_LVDS2_GATE			207
 #define IMX6QDL_CLK_ESAI_IPG			208
 #define IMX6QDL_CLK_ESAI_MEM			209
-#define IMX6QDL_CLK_END				210
+#define IMX6QDL_CLK_ASRC_IPG			210
+#define IMX6QDL_CLK_ASRC_MEM			211
+#define IMX6QDL_CLK_END				212
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6QDL_H */
-- 
cgit v1.2.3


From b1f156db47ae914a308488ce28e84f3d4ad4f667 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@freescale.com>
Date: Mon, 1 Sep 2014 14:17:48 +0800
Subject: ARM: imx6q: add BYPASS support for PLL clocks

The imx6q clock driver currently hard-codes all PLL clocks to source
from OSC24M without BYPASS support.  The patch adds the missing lvds_in
clock which is mutually exclusive with lvds_gate, and implements BYPASS
and BYPASS_CLK_SRC selection for PLL clocks as per Figure 10-3. Primary
Clock Generation in IMX6DQRM, i.e. both BYPASS_CLK_SRC and BYPASS bits
are implemented as mux clocks, and ENABLE bit of PLL clocks is
implemented as a gate clock after BYPASS mux.

Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-imx6q.c             | 67 ++++++++++++++++++++++++++-----
 include/dt-bindings/clock/imx6qdl-clock.h | 27 ++++++++++++-
 2 files changed, 83 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 013d3cda790e..4ee6e77a0fdf 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -73,6 +73,14 @@ static const char *lvds_sels[] = {
 	"pll4_audio", "pll5_video", "pll8_mlb", "enet_ref",
 	"pcie_ref_125m", "sata_ref_100m",
 };
+static const char *pll_bypass_src_sels[] = { "osc", "lvds1_in", "lvds2_in", "dummy", };
+static const char *pll1_bypass_sels[] = { "pll1", "pll1_bypass_src", };
+static const char *pll2_bypass_sels[] = { "pll2", "pll2_bypass_src", };
+static const char *pll3_bypass_sels[] = { "pll3", "pll3_bypass_src", };
+static const char *pll4_bypass_sels[] = { "pll4", "pll4_bypass_src", };
+static const char *pll5_bypass_sels[] = { "pll5", "pll5_bypass_src", };
+static const char *pll6_bypass_sels[] = { "pll6", "pll6_bypass_src", };
+static const char *pll7_bypass_sels[] = { "pll7", "pll7_bypass_src", };
 
 static struct clk *clk[IMX6QDL_CLK_END];
 static struct clk_onecell_data clk_data;
@@ -123,6 +131,9 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_CKIL] = imx_obtain_fixed_clock("ckil", 0);
 	clk[IMX6QDL_CLK_CKIH] = imx_obtain_fixed_clock("ckih1", 0);
 	clk[IMX6QDL_CLK_OSC] = imx_obtain_fixed_clock("osc", 0);
+	/* Clock source from external clock via CLK1/2 PADs */
+	clk[IMX6QDL_CLK_ANACLK1] = imx_obtain_fixed_clock("anaclk1", 0);
+	clk[IMX6QDL_CLK_ANACLK2] = imx_obtain_fixed_clock("anaclk2", 0);
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-anatop");
 	base = of_iomap(np, 0);
@@ -136,14 +147,47 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 		video_div_table[2].div = 1;
 	};
 
-	/*                                             type             name         parent_name  base     div_mask */
-	clk[IMX6QDL_CLK_PLL1_SYS]      = imx_clk_pllv3(IMX_PLLV3_SYS,	"pll1_sys",	"osc", base,        0x7f);
-	clk[IMX6QDL_CLK_PLL2_BUS]      = imx_clk_pllv3(IMX_PLLV3_GENERIC,	"pll2_bus",	"osc", base + 0x30, 0x1);
-	clk[IMX6QDL_CLK_PLL3_USB_OTG]  = imx_clk_pllv3(IMX_PLLV3_USB,	"pll3_usb_otg",	"osc", base + 0x10, 0x3);
-	clk[IMX6QDL_CLK_PLL4_AUDIO]    = imx_clk_pllv3(IMX_PLLV3_AV,	"pll4_audio",	"osc", base + 0x70, 0x7f);
-	clk[IMX6QDL_CLK_PLL5_VIDEO]    = imx_clk_pllv3(IMX_PLLV3_AV,	"pll5_video",	"osc", base + 0xa0, 0x7f);
-	clk[IMX6QDL_CLK_PLL6_ENET]     = imx_clk_pllv3(IMX_PLLV3_ENET,	"pll6_enet",	"osc", base + 0xe0, 0x3);
-	clk[IMX6QDL_CLK_PLL7_USB_HOST] = imx_clk_pllv3(IMX_PLLV3_USB,	"pll7_usb_host","osc", base + 0x20, 0x3);
+	clk[IMX6QDL_PLL1_BYPASS_SRC] = imx_clk_mux("pll1_bypass_src", base + 0x00, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clk[IMX6QDL_PLL2_BYPASS_SRC] = imx_clk_mux("pll2_bypass_src", base + 0x30, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clk[IMX6QDL_PLL3_BYPASS_SRC] = imx_clk_mux("pll3_bypass_src", base + 0x10, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clk[IMX6QDL_PLL4_BYPASS_SRC] = imx_clk_mux("pll4_bypass_src", base + 0x70, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clk[IMX6QDL_PLL5_BYPASS_SRC] = imx_clk_mux("pll5_bypass_src", base + 0xa0, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clk[IMX6QDL_PLL6_BYPASS_SRC] = imx_clk_mux("pll6_bypass_src", base + 0xe0, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clk[IMX6QDL_PLL7_BYPASS_SRC] = imx_clk_mux("pll7_bypass_src", base + 0x20, 14, 2, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+
+	/*                                    type               name    parent_name        base         div_mask */
+	clk[IMX6QDL_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1", "pll1_bypass_src", base + 0x00, 0x7f);
+	clk[IMX6QDL_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "pll2_bypass_src", base + 0x30, 0x1);
+	clk[IMX6QDL_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3", "pll3_bypass_src", base + 0x10, 0x3);
+	clk[IMX6QDL_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4", "pll4_bypass_src", base + 0x70, 0x7f);
+	clk[IMX6QDL_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5", "pll5_bypass_src", base + 0xa0, 0x7f);
+	clk[IMX6QDL_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6", "pll6_bypass_src", base + 0xe0, 0x3);
+	clk[IMX6QDL_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7", "pll7_bypass_src", base + 0x20, 0x3);
+
+	clk[IMX6QDL_PLL1_BYPASS] = imx_clk_mux_flags("pll1_bypass", base + 0x00, 16, 1, pll1_bypass_sels, ARRAY_SIZE(pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	clk[IMX6QDL_PLL2_BYPASS] = imx_clk_mux_flags("pll2_bypass", base + 0x30, 16, 1, pll2_bypass_sels, ARRAY_SIZE(pll2_bypass_sels), CLK_SET_RATE_PARENT);
+	clk[IMX6QDL_PLL3_BYPASS] = imx_clk_mux_flags("pll3_bypass", base + 0x10, 16, 1, pll3_bypass_sels, ARRAY_SIZE(pll3_bypass_sels), CLK_SET_RATE_PARENT);
+	clk[IMX6QDL_PLL4_BYPASS] = imx_clk_mux_flags("pll4_bypass", base + 0x70, 16, 1, pll4_bypass_sels, ARRAY_SIZE(pll4_bypass_sels), CLK_SET_RATE_PARENT);
+	clk[IMX6QDL_PLL5_BYPASS] = imx_clk_mux_flags("pll5_bypass", base + 0xa0, 16, 1, pll5_bypass_sels, ARRAY_SIZE(pll5_bypass_sels), CLK_SET_RATE_PARENT);
+	clk[IMX6QDL_PLL6_BYPASS] = imx_clk_mux_flags("pll6_bypass", base + 0xe0, 16, 1, pll6_bypass_sels, ARRAY_SIZE(pll6_bypass_sels), CLK_SET_RATE_PARENT);
+	clk[IMX6QDL_PLL7_BYPASS] = imx_clk_mux_flags("pll7_bypass", base + 0x20, 16, 1, pll7_bypass_sels, ARRAY_SIZE(pll7_bypass_sels), CLK_SET_RATE_PARENT);
+
+	/* Do not bypass PLLs initially */
+	clk_set_parent(clk[IMX6QDL_PLL1_BYPASS], clk[IMX6QDL_CLK_PLL1]);
+	clk_set_parent(clk[IMX6QDL_PLL2_BYPASS], clk[IMX6QDL_CLK_PLL2]);
+	clk_set_parent(clk[IMX6QDL_PLL3_BYPASS], clk[IMX6QDL_CLK_PLL3]);
+	clk_set_parent(clk[IMX6QDL_PLL4_BYPASS], clk[IMX6QDL_CLK_PLL4]);
+	clk_set_parent(clk[IMX6QDL_PLL5_BYPASS], clk[IMX6QDL_CLK_PLL5]);
+	clk_set_parent(clk[IMX6QDL_PLL6_BYPASS], clk[IMX6QDL_CLK_PLL6]);
+	clk_set_parent(clk[IMX6QDL_PLL7_BYPASS], clk[IMX6QDL_CLK_PLL7]);
+
+	clk[IMX6QDL_CLK_PLL1_SYS]      = imx_clk_gate("pll1_sys",      "pll1_bypass", base + 0x00, 13);
+	clk[IMX6QDL_CLK_PLL2_BUS]      = imx_clk_gate("pll2_bus",      "pll2_bypass", base + 0x30, 13);
+	clk[IMX6QDL_CLK_PLL3_USB_OTG]  = imx_clk_gate("pll3_usb_otg",  "pll3_bypass", base + 0x10, 13);
+	clk[IMX6QDL_CLK_PLL4_AUDIO]    = imx_clk_gate("pll4_audio",    "pll4_bypass", base + 0x70, 13);
+	clk[IMX6QDL_CLK_PLL5_VIDEO]    = imx_clk_gate("pll5_video",    "pll5_bypass", base + 0xa0, 13);
+	clk[IMX6QDL_CLK_PLL6_ENET]     = imx_clk_gate("pll6_enet",     "pll6_bypass", base + 0xe0, 13);
+	clk[IMX6QDL_CLK_PLL7_USB_HOST] = imx_clk_gate("pll7_usb_host", "pll7_bypass", base + 0xe0, 13);
 
 	/*
 	 * Bit 20 is the reserved and read-only bit, we do this only for:
@@ -180,8 +224,11 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	 * the "output_enable" bit as a gate, even though it's really just
 	 * enabling clock output.
 	 */
-	clk[IMX6QDL_CLK_LVDS1_GATE] = imx_clk_gate("lvds1_gate", "lvds1_sel", base + 0x160, 10);
-	clk[IMX6QDL_CLK_LVDS2_GATE] = imx_clk_gate("lvds2_gate", "lvds2_sel", base + 0x160, 11);
+	clk[IMX6QDL_CLK_LVDS1_GATE] = imx_clk_gate_exclusive("lvds1_gate", "lvds1_sel", base + 0x160, 10, BIT(12));
+	clk[IMX6QDL_CLK_LVDS2_GATE] = imx_clk_gate_exclusive("lvds2_gate", "lvds2_sel", base + 0x160, 11, BIT(13));
+
+	clk[IMX6QDL_CLK_LVDS1_IN] = imx_clk_gate_exclusive("lvds1_in", "anaclk1", base + 0x160, 12, BIT(10));
+	clk[IMX6QDL_CLK_LVDS2_IN] = imx_clk_gate_exclusive("lvds2_in", "anaclk2", base + 0x160, 13, BIT(11));
 
 	/*                                            name              parent_name        reg       idx */
 	clk[IMX6QDL_CLK_PLL2_PFD0_352M] = imx_clk_pfd("pll2_pfd0_352m", "pll2_bus",     base + 0x100, 0);
diff --git a/include/dt-bindings/clock/imx6qdl-clock.h b/include/dt-bindings/clock/imx6qdl-clock.h
index 1e996135cfc7..c0d88ab013b4 100644
--- a/include/dt-bindings/clock/imx6qdl-clock.h
+++ b/include/dt-bindings/clock/imx6qdl-clock.h
@@ -222,6 +222,31 @@
 #define IMX6QDL_CLK_ESAI_MEM			209
 #define IMX6QDL_CLK_ASRC_IPG			210
 #define IMX6QDL_CLK_ASRC_MEM			211
-#define IMX6QDL_CLK_END				212
+#define IMX6QDL_CLK_LVDS1_IN			212
+#define IMX6QDL_CLK_LVDS2_IN			213
+#define IMX6QDL_CLK_ANACLK1			214
+#define IMX6QDL_CLK_ANACLK2			215
+#define IMX6QDL_PLL1_BYPASS_SRC			216
+#define IMX6QDL_PLL2_BYPASS_SRC			217
+#define IMX6QDL_PLL3_BYPASS_SRC			218
+#define IMX6QDL_PLL4_BYPASS_SRC			219
+#define IMX6QDL_PLL5_BYPASS_SRC			220
+#define IMX6QDL_PLL6_BYPASS_SRC			221
+#define IMX6QDL_PLL7_BYPASS_SRC			222
+#define IMX6QDL_CLK_PLL1			223
+#define IMX6QDL_CLK_PLL2			224
+#define IMX6QDL_CLK_PLL3			225
+#define IMX6QDL_CLK_PLL4			226
+#define IMX6QDL_CLK_PLL5			227
+#define IMX6QDL_CLK_PLL6			228
+#define IMX6QDL_CLK_PLL7			229
+#define IMX6QDL_PLL1_BYPASS			230
+#define IMX6QDL_PLL2_BYPASS			231
+#define IMX6QDL_PLL3_BYPASS			232
+#define IMX6QDL_PLL4_BYPASS			233
+#define IMX6QDL_PLL5_BYPASS			234
+#define IMX6QDL_PLL6_BYPASS			235
+#define IMX6QDL_PLL7_BYPASS			236
+#define IMX6QDL_CLK_END				237
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6QDL_H */
-- 
cgit v1.2.3


From e90f41990dce3557e345410ef33b0a47e8cb49fc Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@freescale.com>
Date: Mon, 1 Sep 2014 14:29:53 +0800
Subject: ARM: imx6sl: add BYPASS support for PLL clocks

This is the same change for imx6sl clock driver as "ARM: imx6q: add BYPASS
support for PLL clocks" for imx6q.  The difference is that only anaclk1
is available on imx6sl.

Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-imx6sl.c           | 69 ++++++++++++++++++++++++++++----
 include/dt-bindings/clock/imx6sl-clock.h | 27 ++++++++++++-
 2 files changed, 87 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c
index f4d732661d6d..6791ff3e8914 100644
--- a/arch/arm/mach-imx/clk-imx6sl.c
+++ b/arch/arm/mach-imx/clk-imx6sl.c
@@ -57,6 +57,20 @@ static const char *epdc_pix_sels[]	= { "pll2_bus", "pll3_usb_otg", "pll5_video_d
 static const char *audio_sels[]		= { "pll4_audio_div", "pll3_pfd2", "pll3_pfd3", "pll3_usb_otg", };
 static const char *ecspi_sels[]		= { "pll3_60m", "osc", };
 static const char *uart_sels[]		= { "pll3_80m", "osc", };
+static const char *lvds_sels[]		= {
+	"pll1_sys", "pll2_bus", "pll2_pfd0", "pll2_pfd1", "pll2_pfd2", "dummy", "pll4_audio", "pll5_video",
+	"dummy", "enet_ref", "dummy", "dummy", "pll3_usb_otg", "pll7_usb_host", "pll3_pfd0", "pll3_pfd1",
+	"pll3_pfd2", "pll3_pfd3", "osc", "dummy", "dummy", "dummy", "dummy", "dummy",
+	 "dummy", "dummy", "dummy", "dummy", "dummy", "dummy", "dummy", "dummy",
+};
+static const char *pll_bypass_src_sels[] = { "osc", "lvds1_in", };
+static const char *pll1_bypass_sels[]	= { "pll1", "pll1_bypass_src", };
+static const char *pll2_bypass_sels[]	= { "pll2", "pll2_bypass_src", };
+static const char *pll3_bypass_sels[]	= { "pll3", "pll3_bypass_src", };
+static const char *pll4_bypass_sels[]	= { "pll4", "pll4_bypass_src", };
+static const char *pll5_bypass_sels[]	= { "pll5", "pll5_bypass_src", };
+static const char *pll6_bypass_sels[]	= { "pll6", "pll6_bypass_src", };
+static const char *pll7_bypass_sels[]	= { "pll7", "pll7_bypass_src", };
 
 static struct clk_div_table clk_enet_ref_table[] = {
 	{ .val = 0, .div = 20, },
@@ -177,20 +191,59 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SL_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
 	clks[IMX6SL_CLK_CKIL] = imx_obtain_fixed_clock("ckil", 0);
 	clks[IMX6SL_CLK_OSC] = imx_obtain_fixed_clock("osc", 0);
+	/* Clock source from external clock via CLK1 PAD */
+	clks[IMX6SL_CLK_ANACLK1] = imx_obtain_fixed_clock("anaclk1", 0);
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6sl-anatop");
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
 	anatop_base = base;
 
-	/*                                             type               name            parent  base         div_mask */
-	clks[IMX6SL_CLK_PLL1_SYS]      = imx_clk_pllv3(IMX_PLLV3_SYS,	  "pll1_sys",	   "osc", base,        0x7f);
-	clks[IMX6SL_CLK_PLL2_BUS]      = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2_bus",	   "osc", base + 0x30, 0x1);
-	clks[IMX6SL_CLK_PLL3_USB_OTG]  = imx_clk_pllv3(IMX_PLLV3_USB,	  "pll3_usb_otg",  "osc", base + 0x10, 0x3);
-	clks[IMX6SL_CLK_PLL4_AUDIO]    = imx_clk_pllv3(IMX_PLLV3_AV,	  "pll4_audio",	   "osc", base + 0x70, 0x7f);
-	clks[IMX6SL_CLK_PLL5_VIDEO]    = imx_clk_pllv3(IMX_PLLV3_AV,	  "pll5_video",	   "osc", base + 0xa0, 0x7f);
-	clks[IMX6SL_CLK_PLL6_ENET]     = imx_clk_pllv3(IMX_PLLV3_ENET,	  "pll6_enet",	   "osc", base + 0xe0, 0x3);
-	clks[IMX6SL_CLK_PLL7_USB_HOST] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7_usb_host", "osc", base + 0x20, 0x3);
+	clks[IMX6SL_PLL1_BYPASS_SRC] = imx_clk_mux("pll1_bypass_src", base + 0x00, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SL_PLL2_BYPASS_SRC] = imx_clk_mux("pll2_bypass_src", base + 0x30, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SL_PLL3_BYPASS_SRC] = imx_clk_mux("pll3_bypass_src", base + 0x10, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SL_PLL4_BYPASS_SRC] = imx_clk_mux("pll4_bypass_src", base + 0x70, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SL_PLL5_BYPASS_SRC] = imx_clk_mux("pll5_bypass_src", base + 0xa0, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SL_PLL6_BYPASS_SRC] = imx_clk_mux("pll6_bypass_src", base + 0xe0, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SL_PLL7_BYPASS_SRC] = imx_clk_mux("pll7_bypass_src", base + 0x20, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+
+	/*                                    type               name    parent_name        base         div_mask */
+	clks[IMX6SL_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1", "pll1_bypass_src", base + 0x00, 0x7f);
+	clks[IMX6SL_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "pll2_bypass_src", base + 0x30, 0x1);
+	clks[IMX6SL_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3", "pll3_bypass_src", base + 0x10, 0x3);
+	clks[IMX6SL_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4", "pll4_bypass_src", base + 0x70, 0x7f);
+	clks[IMX6SL_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5", "pll5_bypass_src", base + 0xa0, 0x7f);
+	clks[IMX6SL_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6", "pll6_bypass_src", base + 0xe0, 0x3);
+	clks[IMX6SL_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7", "pll7_bypass_src", base + 0x20, 0x3);
+
+	clks[IMX6SL_PLL1_BYPASS] = imx_clk_mux_flags("pll1_bypass", base + 0x00, 16, 1, pll1_bypass_sels, ARRAY_SIZE(pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SL_PLL2_BYPASS] = imx_clk_mux_flags("pll2_bypass", base + 0x30, 16, 1, pll2_bypass_sels, ARRAY_SIZE(pll2_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SL_PLL3_BYPASS] = imx_clk_mux_flags("pll3_bypass", base + 0x10, 16, 1, pll3_bypass_sels, ARRAY_SIZE(pll3_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SL_PLL4_BYPASS] = imx_clk_mux_flags("pll4_bypass", base + 0x70, 16, 1, pll4_bypass_sels, ARRAY_SIZE(pll4_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SL_PLL5_BYPASS] = imx_clk_mux_flags("pll5_bypass", base + 0xa0, 16, 1, pll5_bypass_sels, ARRAY_SIZE(pll5_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SL_PLL6_BYPASS] = imx_clk_mux_flags("pll6_bypass", base + 0xe0, 16, 1, pll6_bypass_sels, ARRAY_SIZE(pll6_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SL_PLL7_BYPASS] = imx_clk_mux_flags("pll7_bypass", base + 0x20, 16, 1, pll7_bypass_sels, ARRAY_SIZE(pll7_bypass_sels), CLK_SET_RATE_PARENT);
+
+	/* Do not bypass PLLs initially */
+	clk_set_parent(clks[IMX6SL_PLL1_BYPASS], clks[IMX6SL_CLK_PLL1]);
+	clk_set_parent(clks[IMX6SL_PLL2_BYPASS], clks[IMX6SL_CLK_PLL2]);
+	clk_set_parent(clks[IMX6SL_PLL3_BYPASS], clks[IMX6SL_CLK_PLL3]);
+	clk_set_parent(clks[IMX6SL_PLL4_BYPASS], clks[IMX6SL_CLK_PLL4]);
+	clk_set_parent(clks[IMX6SL_PLL5_BYPASS], clks[IMX6SL_CLK_PLL5]);
+	clk_set_parent(clks[IMX6SL_PLL6_BYPASS], clks[IMX6SL_CLK_PLL6]);
+	clk_set_parent(clks[IMX6SL_PLL7_BYPASS], clks[IMX6SL_CLK_PLL7]);
+
+	clks[IMX6SL_CLK_PLL1_SYS]      = imx_clk_gate("pll1_sys",      "pll1_bypass", base + 0x00, 13);
+	clks[IMX6SL_CLK_PLL2_BUS]      = imx_clk_gate("pll2_bus",      "pll2_bypass", base + 0x30, 13);
+	clks[IMX6SL_CLK_PLL3_USB_OTG]  = imx_clk_gate("pll3_usb_otg",  "pll3_bypass", base + 0x10, 13);
+	clks[IMX6SL_CLK_PLL4_AUDIO]    = imx_clk_gate("pll4_audio",    "pll4_bypass", base + 0x70, 13);
+	clks[IMX6SL_CLK_PLL5_VIDEO]    = imx_clk_gate("pll5_video",    "pll5_bypass", base + 0xa0, 13);
+	clks[IMX6SL_CLK_PLL6_ENET]     = imx_clk_gate("pll6_enet",     "pll6_bypass", base + 0xe0, 13);
+	clks[IMX6SL_CLK_PLL7_USB_HOST] = imx_clk_gate("pll7_usb_host", "pll7_bypass", base + 0xe0, 13);
+
+	clks[IMX6SL_CLK_LVDS1_SEL] = imx_clk_mux("lvds1_sel", base + 0x160, 0, 5, lvds_sels, ARRAY_SIZE(lvds_sels));
+	clks[IMX6SL_CLK_LVDS1_OUT] = imx_clk_gate_exclusive("lvds1_out", "lvds1_sel", base + 0x160, 10, BIT(12));
+	clks[IMX6SL_CLK_LVDS1_IN] = imx_clk_gate_exclusive("lvds1_in", "anaclk1", base + 0x160, 12, BIT(10));
 
 	/*
 	 * usbphy1 and usbphy2 are implemented as dummy gates using reserve
diff --git a/include/dt-bindings/clock/imx6sl-clock.h b/include/dt-bindings/clock/imx6sl-clock.h
index b91dd462ba85..f10a928fe2dd 100644
--- a/include/dt-bindings/clock/imx6sl-clock.h
+++ b/include/dt-bindings/clock/imx6sl-clock.h
@@ -146,6 +146,31 @@
 #define IMX6SL_CLK_PLL4_AUDIO_DIV	133
 #define IMX6SL_CLK_SPBA			134
 #define IMX6SL_CLK_ENET			135
-#define IMX6SL_CLK_END			136
+#define IMX6SL_CLK_LVDS1_SEL		136
+#define IMX6SL_CLK_LVDS1_OUT		137
+#define IMX6SL_CLK_LVDS1_IN		138
+#define IMX6SL_CLK_ANACLK1		139
+#define IMX6SL_PLL1_BYPASS_SRC		140
+#define IMX6SL_PLL2_BYPASS_SRC		141
+#define IMX6SL_PLL3_BYPASS_SRC		142
+#define IMX6SL_PLL4_BYPASS_SRC		143
+#define IMX6SL_PLL5_BYPASS_SRC		144
+#define IMX6SL_PLL6_BYPASS_SRC		145
+#define IMX6SL_PLL7_BYPASS_SRC		146
+#define IMX6SL_CLK_PLL1			147
+#define IMX6SL_CLK_PLL2			148
+#define IMX6SL_CLK_PLL3			149
+#define IMX6SL_CLK_PLL4			150
+#define IMX6SL_CLK_PLL5			151
+#define IMX6SL_CLK_PLL6			152
+#define IMX6SL_CLK_PLL7			153
+#define IMX6SL_PLL1_BYPASS		154
+#define IMX6SL_PLL2_BYPASS		155
+#define IMX6SL_PLL3_BYPASS		156
+#define IMX6SL_PLL4_BYPASS		157
+#define IMX6SL_PLL5_BYPASS		158
+#define IMX6SL_PLL6_BYPASS		159
+#define IMX6SL_PLL7_BYPASS		160
+#define IMX6SL_CLK_END			161
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6SL_H */
-- 
cgit v1.2.3


From db7c0659452c5f490ea5048390ad94de786f4b85 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@freescale.com>
Date: Mon, 1 Sep 2014 15:15:57 +0800
Subject: ARM: imx6sx: add BYPASS support for PLL clocks

This is the same change for imx6sx clock driver as "ARM: imx6q: add BYPASS
support for PLL clocks" for imx6q.  The difference is that only anaclk1
is available on imx6sx.

Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-imx6sx.c           | 63 +++++++++++++++++++++++++++-----
 include/dt-bindings/clock/imx6sx-clock.h | 25 ++++++++++++-
 2 files changed, 78 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx6sx.c b/arch/arm/mach-imx/clk-imx6sx.c
index ecde72bdfe88..27070a716935 100644
--- a/arch/arm/mach-imx/clk-imx6sx.c
+++ b/arch/arm/mach-imx/clk-imx6sx.c
@@ -81,6 +81,14 @@ static const char *lvds_sels[]	= {
 	"arm", "pll1_sys", "dummy", "dummy", "dummy", "dummy", "dummy", "pll5_video_div",
 	"dummy", "dummy", "pcie_ref_125m", "dummy", "usbphy1", "usbphy2",
 };
+static const char *pll_bypass_src_sels[] = { "osc", "lvds1_in", };
+static const char *pll1_bypass_sels[] = { "pll1", "pll1_bypass_src", };
+static const char *pll2_bypass_sels[] = { "pll2", "pll2_bypass_src", };
+static const char *pll3_bypass_sels[] = { "pll3", "pll3_bypass_src", };
+static const char *pll4_bypass_sels[] = { "pll4", "pll4_bypass_src", };
+static const char *pll5_bypass_sels[] = { "pll5", "pll5_bypass_src", };
+static const char *pll6_bypass_sels[] = { "pll6", "pll6_bypass_src", };
+static const char *pll7_bypass_sels[] = { "pll7", "pll7_bypass_src", };
 
 static struct clk *clks[IMX6SX_CLK_CLK_END];
 static struct clk_onecell_data clk_data;
@@ -143,18 +151,54 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_IPP_DI0] = of_clk_get_by_name(ccm_node, "ipp_di0");
 	clks[IMX6SX_CLK_IPP_DI1] = of_clk_get_by_name(ccm_node, "ipp_di1");
 
+	/* Clock source from external clock via CLK1 PAD */
+	clks[IMX6SX_CLK_ANACLK1] = imx_obtain_fixed_clock("anaclk1", 0);
+
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6sx-anatop");
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
 
-	/*                                              type               name             parent_name   base         div_mask */
-	clks[IMX6SX_CLK_PLL1_SYS]       = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1_sys",      "osc",        base,        0x7f);
-	clks[IMX6SX_CLK_PLL2_BUS]       = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2_bus",      "osc",        base + 0x30, 0x1);
-	clks[IMX6SX_CLK_PLL3_USB_OTG]   = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3_usb_otg",  "osc",        base + 0x10, 0x3);
-	clks[IMX6SX_CLK_PLL4_AUDIO]     = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4_audio",    "osc",        base + 0x70, 0x7f);
-	clks[IMX6SX_CLK_PLL5_VIDEO]     = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5_video",    "osc",        base + 0xa0, 0x7f);
-	clks[IMX6SX_CLK_PLL6_ENET]      = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6_enet",     "osc",        base + 0xe0, 0x3);
-	clks[IMX6SX_CLK_PLL7_USB_HOST]  = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7_usb_host", "osc",        base + 0x20, 0x3);
+	clks[IMX6SX_PLL1_BYPASS_SRC] = imx_clk_mux("pll1_bypass_src", base + 0x00, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SX_PLL2_BYPASS_SRC] = imx_clk_mux("pll2_bypass_src", base + 0x30, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SX_PLL3_BYPASS_SRC] = imx_clk_mux("pll3_bypass_src", base + 0x10, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SX_PLL4_BYPASS_SRC] = imx_clk_mux("pll4_bypass_src", base + 0x70, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SX_PLL5_BYPASS_SRC] = imx_clk_mux("pll5_bypass_src", base + 0xa0, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SX_PLL6_BYPASS_SRC] = imx_clk_mux("pll6_bypass_src", base + 0xe0, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+	clks[IMX6SX_PLL7_BYPASS_SRC] = imx_clk_mux("pll7_bypass_src", base + 0x20, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
+
+	/*                                    type               name    parent_name        base         div_mask */
+	clks[IMX6SX_CLK_PLL1] = imx_clk_pllv3(IMX_PLLV3_SYS,     "pll1", "pll1_bypass_src", base + 0x00, 0x7f);
+	clks[IMX6SX_CLK_PLL2] = imx_clk_pllv3(IMX_PLLV3_GENERIC, "pll2", "pll2_bypass_src", base + 0x30, 0x1);
+	clks[IMX6SX_CLK_PLL3] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll3", "pll3_bypass_src", base + 0x10, 0x3);
+	clks[IMX6SX_CLK_PLL4] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll4", "pll4_bypass_src", base + 0x70, 0x7f);
+	clks[IMX6SX_CLK_PLL5] = imx_clk_pllv3(IMX_PLLV3_AV,      "pll5", "pll5_bypass_src", base + 0xa0, 0x7f);
+	clks[IMX6SX_CLK_PLL6] = imx_clk_pllv3(IMX_PLLV3_ENET,    "pll6", "pll6_bypass_src", base + 0xe0, 0x3);
+	clks[IMX6SX_CLK_PLL7] = imx_clk_pllv3(IMX_PLLV3_USB,     "pll7", "pll7_bypass_src", base + 0x20, 0x3);
+
+	clks[IMX6SX_PLL1_BYPASS] = imx_clk_mux_flags("pll1_bypass", base + 0x00, 16, 1, pll1_bypass_sels, ARRAY_SIZE(pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SX_PLL2_BYPASS] = imx_clk_mux_flags("pll2_bypass", base + 0x30, 16, 1, pll2_bypass_sels, ARRAY_SIZE(pll2_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SX_PLL3_BYPASS] = imx_clk_mux_flags("pll3_bypass", base + 0x10, 16, 1, pll3_bypass_sels, ARRAY_SIZE(pll3_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SX_PLL4_BYPASS] = imx_clk_mux_flags("pll4_bypass", base + 0x70, 16, 1, pll4_bypass_sels, ARRAY_SIZE(pll4_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SX_PLL5_BYPASS] = imx_clk_mux_flags("pll5_bypass", base + 0xa0, 16, 1, pll5_bypass_sels, ARRAY_SIZE(pll5_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SX_PLL6_BYPASS] = imx_clk_mux_flags("pll6_bypass", base + 0xe0, 16, 1, pll6_bypass_sels, ARRAY_SIZE(pll6_bypass_sels), CLK_SET_RATE_PARENT);
+	clks[IMX6SX_PLL7_BYPASS] = imx_clk_mux_flags("pll7_bypass", base + 0x20, 16, 1, pll7_bypass_sels, ARRAY_SIZE(pll7_bypass_sels), CLK_SET_RATE_PARENT);
+
+	/* Do not bypass PLLs initially */
+	clk_set_parent(clks[IMX6SX_PLL1_BYPASS], clks[IMX6SX_CLK_PLL1]);
+	clk_set_parent(clks[IMX6SX_PLL2_BYPASS], clks[IMX6SX_CLK_PLL2]);
+	clk_set_parent(clks[IMX6SX_PLL3_BYPASS], clks[IMX6SX_CLK_PLL3]);
+	clk_set_parent(clks[IMX6SX_PLL4_BYPASS], clks[IMX6SX_CLK_PLL4]);
+	clk_set_parent(clks[IMX6SX_PLL5_BYPASS], clks[IMX6SX_CLK_PLL5]);
+	clk_set_parent(clks[IMX6SX_PLL6_BYPASS], clks[IMX6SX_CLK_PLL6]);
+	clk_set_parent(clks[IMX6SX_PLL7_BYPASS], clks[IMX6SX_CLK_PLL7]);
+
+	clks[IMX6SX_CLK_PLL1_SYS]      = imx_clk_gate("pll1_sys",      "pll1_bypass", base + 0x00, 13);
+	clks[IMX6SX_CLK_PLL2_BUS]      = imx_clk_gate("pll2_bus",      "pll2_bypass", base + 0x30, 13);
+	clks[IMX6SX_CLK_PLL3_USB_OTG]  = imx_clk_gate("pll3_usb_otg",  "pll3_bypass", base + 0x10, 13);
+	clks[IMX6SX_CLK_PLL4_AUDIO]    = imx_clk_gate("pll4_audio",    "pll4_bypass", base + 0x70, 13);
+	clks[IMX6SX_CLK_PLL5_VIDEO]    = imx_clk_gate("pll5_video",    "pll5_bypass", base + 0xa0, 13);
+	clks[IMX6SX_CLK_PLL6_ENET]     = imx_clk_gate("pll6_enet",     "pll6_bypass", base + 0xe0, 13);
+	clks[IMX6SX_CLK_PLL7_USB_HOST] = imx_clk_gate("pll7_usb_host", "pll7_bypass", base + 0xe0, 13);
 
 	/*
 	 * Bit 20 is the reserved and read-only bit, we do this only for:
@@ -176,7 +220,8 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_PCIE_REF] = imx_clk_fixed_factor("pcie_ref", "pll6_enet", 1, 5);
 	clks[IMX6SX_CLK_PCIE_REF_125M] = imx_clk_gate("pcie_ref_125m", "pcie_ref", base + 0xe0, 19);
 
-	clks[IMX6SX_CLK_LVDS1_OUT] = imx_clk_gate("lvds1_out", "lvds1_sel", base + 0x160, 10);
+	clks[IMX6SX_CLK_LVDS1_OUT] = imx_clk_gate_exclusive("lvds1_out", "lvds1_sel", base + 0x160, 10, BIT(12));
+	clks[IMX6SX_CLK_LVDS1_IN]  = imx_clk_gate_exclusive("lvds1_in",  "anaclk1",   base + 0x160, 12, BIT(10));
 
 	clks[IMX6SX_CLK_ENET_REF] = clk_register_divider_table(NULL, "enet_ref", "pll6_enet", 0,
 			base + 0xe0, 0, 2, 0, clk_enet_ref_table,
diff --git a/include/dt-bindings/clock/imx6sx-clock.h b/include/dt-bindings/clock/imx6sx-clock.h
index 421d8bb76f2f..995709119ec5 100644
--- a/include/dt-bindings/clock/imx6sx-clock.h
+++ b/include/dt-bindings/clock/imx6sx-clock.h
@@ -251,6 +251,29 @@
 #define IMX6SX_CLK_SAI2_IPG		238
 #define IMX6SX_CLK_ESAI_IPG		239
 #define IMX6SX_CLK_ESAI_MEM		240
-#define IMX6SX_CLK_CLK_END		241
+#define IMX6SX_CLK_LVDS1_IN		241
+#define IMX6SX_CLK_ANACLK1		242
+#define IMX6SX_PLL1_BYPASS_SRC		243
+#define IMX6SX_PLL2_BYPASS_SRC		244
+#define IMX6SX_PLL3_BYPASS_SRC		245
+#define IMX6SX_PLL4_BYPASS_SRC		246
+#define IMX6SX_PLL5_BYPASS_SRC		247
+#define IMX6SX_PLL6_BYPASS_SRC		248
+#define IMX6SX_PLL7_BYPASS_SRC		249
+#define IMX6SX_CLK_PLL1			250
+#define IMX6SX_CLK_PLL2			251
+#define IMX6SX_CLK_PLL3			252
+#define IMX6SX_CLK_PLL4			253
+#define IMX6SX_CLK_PLL5			254
+#define IMX6SX_CLK_PLL6			255
+#define IMX6SX_CLK_PLL7			256
+#define IMX6SX_PLL1_BYPASS		257
+#define IMX6SX_PLL2_BYPASS		258
+#define IMX6SX_PLL3_BYPASS		259
+#define IMX6SX_PLL4_BYPASS		260
+#define IMX6SX_PLL5_BYPASS		261
+#define IMX6SX_PLL6_BYPASS		262
+#define IMX6SX_PLL7_BYPASS		263
+#define IMX6SX_CLK_CLK_END		264
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6SX_H */
-- 
cgit v1.2.3


From dbaf381ffbf3acd4ac9a987f567a2b1a5edf6e62 Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@freescale.com>
Date: Tue, 9 Sep 2014 17:13:25 +0800
Subject: ARM: clk-imx6sl: refine clock tree for SSI

Each SSI has "ssi", "ssi_ipg" clocks, and they share same gate bits.

Signed-off-by: Shengjiu Wang <shengjiu.wang@freescale.com>
Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-imx6sl.c           | 13 ++++++++++---
 include/dt-bindings/clock/imx6sl-clock.h |  5 ++++-
 2 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c
index 6791ff3e8914..c8de87bc617f 100644
--- a/arch/arm/mach-imx/clk-imx6sl.c
+++ b/arch/arm/mach-imx/clk-imx6sl.c
@@ -95,6 +95,10 @@ static struct clk_div_table video_div_table[] = {
 	{ }
 };
 
+static unsigned int share_count_ssi1;
+static unsigned int share_count_ssi2;
+static unsigned int share_count_ssi3;
+
 static struct clk *clks[IMX6SL_CLK_END];
 static struct clk_onecell_data clk_data;
 static void __iomem *ccm_base;
@@ -392,9 +396,12 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SL_CLK_SDMA]         = imx_clk_gate2("sdma",         "ipg",               base + 0x7c, 6);
 	clks[IMX6SL_CLK_SPBA]         = imx_clk_gate2("spba",         "ipg",               base + 0x7c, 12);
 	clks[IMX6SL_CLK_SPDIF]        = imx_clk_gate2("spdif",        "spdif0_podf",       base + 0x7c, 14);
-	clks[IMX6SL_CLK_SSI1]         = imx_clk_gate2("ssi1",         "ssi1_podf",         base + 0x7c, 18);
-	clks[IMX6SL_CLK_SSI2]         = imx_clk_gate2("ssi2",         "ssi2_podf",         base + 0x7c, 20);
-	clks[IMX6SL_CLK_SSI3]         = imx_clk_gate2("ssi3",         "ssi3_podf",         base + 0x7c, 22);
+	clks[IMX6SL_CLK_SSI1_IPG]     = imx_clk_gate2_shared("ssi1_ipg",     "ipg",        base + 0x7c, 18, &share_count_ssi1);
+	clks[IMX6SL_CLK_SSI2_IPG]     = imx_clk_gate2_shared("ssi2_ipg",     "ipg",        base + 0x7c, 20, &share_count_ssi2);
+	clks[IMX6SL_CLK_SSI3_IPG]     = imx_clk_gate2_shared("ssi3_ipg",     "ipg",        base + 0x7c, 22, &share_count_ssi3);
+	clks[IMX6SL_CLK_SSI1]         = imx_clk_gate2_shared("ssi1",         "ssi1_podf",  base + 0x7c, 18, &share_count_ssi1);
+	clks[IMX6SL_CLK_SSI2]         = imx_clk_gate2_shared("ssi2",         "ssi2_podf",  base + 0x7c, 20, &share_count_ssi2);
+	clks[IMX6SL_CLK_SSI3]         = imx_clk_gate2_shared("ssi3",         "ssi3_podf",  base + 0x7c, 22, &share_count_ssi3);
 	clks[IMX6SL_CLK_UART]         = imx_clk_gate2("uart",         "ipg",               base + 0x7c, 24);
 	clks[IMX6SL_CLK_UART_SERIAL]  = imx_clk_gate2("uart_serial",  "uart_root",         base + 0x7c, 26);
 	clks[IMX6SL_CLK_USBOH3]       = imx_clk_gate2("usboh3",       "ipg",               base + 0x80, 0);
diff --git a/include/dt-bindings/clock/imx6sl-clock.h b/include/dt-bindings/clock/imx6sl-clock.h
index f10a928fe2dd..9ce4e421096f 100644
--- a/include/dt-bindings/clock/imx6sl-clock.h
+++ b/include/dt-bindings/clock/imx6sl-clock.h
@@ -171,6 +171,9 @@
 #define IMX6SL_PLL5_BYPASS		158
 #define IMX6SL_PLL6_BYPASS		159
 #define IMX6SL_PLL7_BYPASS		160
-#define IMX6SL_CLK_END			161
+#define IMX6SL_CLK_SSI1_IPG		161
+#define IMX6SL_CLK_SSI2_IPG		162
+#define IMX6SL_CLK_SSI3_IPG		163
+#define IMX6SL_CLK_END			164
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6SL_H */
-- 
cgit v1.2.3


From 6f11c69d35d5b1db0ec4cfccd0188b00eada3ad3 Mon Sep 17 00:00:00 2001
From: Anson Huang <b20788@freescale.com>
Date: Thu, 11 Sep 2014 11:29:40 +0800
Subject: ARM: imx: add gpt_3m clk for i.mx6qdl

Add gpt_3m clock for i.mx6qdl, as gpt can source clock
from OSC, some i.MX6 series SOCs has fixed divider of
8 for gpt clock, so here add a fix clk of gpt_3m.

i.MX6Q TO1.0 has no gpt_3m option, so force it to be
from ipg_per.

Signed-off-by: Anson Huang <b20788@freescale.com>
Signed-off-by: Shawn Guo <shawn.guo@freescale.com>
---
 arch/arm/mach-imx/clk-imx6q.c             | 8 ++++++++
 include/dt-bindings/clock/imx6qdl-clock.h | 3 ++-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 4f8ce60a2e90..1412daf4a714 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -245,6 +245,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_PLL3_80M]  = imx_clk_fixed_factor("pll3_80m",  "pll3_usb_otg",   1, 6);
 	clk[IMX6QDL_CLK_PLL3_60M]  = imx_clk_fixed_factor("pll3_60m",  "pll3_usb_otg",   1, 8);
 	clk[IMX6QDL_CLK_TWD]       = imx_clk_fixed_factor("twd",       "arm",            1, 2);
+	clk[IMX6QDL_CLK_GPT_3M]    = imx_clk_fixed_factor("gpt_3m",    "osc",            1, 8);
 	if (cpu_is_imx6dl()) {
 		clk[IMX6QDL_CLK_GPU2D_AXI] = imx_clk_fixed_factor("gpu2d_axi", "mmdc_ch0_axi_podf", 1, 1);
 		clk[IMX6QDL_CLK_GPU3D_AXI] = imx_clk_fixed_factor("gpu3d_axi", "mmdc_ch0_axi_podf", 1, 1);
@@ -461,6 +462,13 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_CKO1]         = imx_clk_gate("cko1",           "cko1_podf",         base + 0x60, 7);
 	clk[IMX6QDL_CLK_CKO2]         = imx_clk_gate("cko2",           "cko2_podf",         base + 0x60, 24);
 
+	/*
+	 * The gpt_3m clock is not available on i.MX6Q TO1.0.  Let's point it
+	 * to clock gpt_ipg_per to ease the gpt driver code.
+	 */
+	if (cpu_is_imx6q() && imx_get_soc_revision() == IMX_CHIP_REVISION_1_0)
+		clk[IMX6QDL_CLK_GPT_3M] = clk[IMX6QDL_CLK_GPT_IPG_PER];
+
 	imx_check_clocks(clk, ARRAY_SIZE(clk));
 
 	clk_data.clks = clk;
diff --git a/include/dt-bindings/clock/imx6qdl-clock.h b/include/dt-bindings/clock/imx6qdl-clock.h
index c0d88ab013b4..ddaef8620b2c 100644
--- a/include/dt-bindings/clock/imx6qdl-clock.h
+++ b/include/dt-bindings/clock/imx6qdl-clock.h
@@ -247,6 +247,7 @@
 #define IMX6QDL_PLL5_BYPASS			234
 #define IMX6QDL_PLL6_BYPASS			235
 #define IMX6QDL_PLL7_BYPASS			236
-#define IMX6QDL_CLK_END				237
+#define IMX6QDL_CLK_GPT_3M			237
+#define IMX6QDL_CLK_END				238
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6QDL_H */
-- 
cgit v1.2.3


From 971427f353f3c42c8dcef62e7124440df68eb809 Mon Sep 17 00:00:00 2001
From: Andy Zhou <azhou@nicira.com>
Date: Mon, 15 Sep 2014 19:37:25 -0700
Subject: openvswitch: Add recirc and hash action.

Recirc action allows a packet to reenter openvswitch processing.
currently openvswitch lookup flow for packet received and execute
set of actions on that packet, with help of recirc action we can
process/modify the packet and recirculate it back in openvswitch
for another pass.

OVS hash action calculates 5-tupple hash and set hash in flow-key
hash. This can be used along with recirculation for distributing
packets among different ports for bond devices.
For example:
OVS bonding can use following actions:
Match on: bond flow; Action: hash, recirc(id)
Match on: recirc-id == id and hash lower bits == a;
          Action: output port_bond_a

Signed-off-by: Andy Zhou <azhou@nicira.com>
Acked-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
---
 include/uapi/linux/openvswitch.h |  26 +++++
 net/openvswitch/actions.c        | 203 +++++++++++++++++++++++++++++++++++++--
 net/openvswitch/datapath.c       |  11 ++-
 net/openvswitch/datapath.h       |   7 +-
 net/openvswitch/flow.c           |   7 +-
 net/openvswitch/flow.h           |   3 +
 net/openvswitch/flow_netlink.c   |  43 ++++++++-
 7 files changed, 288 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index a794d1dd7b40..f7fc507d82ab 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -289,6 +289,9 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_TUNNEL,    /* Nested set of ovs_tunnel attributes */
 	OVS_KEY_ATTR_SCTP,      /* struct ovs_key_sctp */
 	OVS_KEY_ATTR_TCP_FLAGS,	/* be16 TCP flags. */
+	OVS_KEY_ATTR_DP_HASH,      /* u32 hash value. Value 0 indicates the hash
+				   is not computed by the datapath. */
+	OVS_KEY_ATTR_RECIRC_ID, /* u32 recirc id */
 
 #ifdef __KERNEL__
 	OVS_KEY_ATTR_IPV4_TUNNEL,  /* struct ovs_key_ipv4_tunnel */
@@ -493,6 +496,27 @@ struct ovs_action_push_vlan {
 	__be16 vlan_tci;	/* 802.1Q TCI (VLAN ID and priority). */
 };
 
+/* Data path hash algorithm for computing Datapath hash.
+ *
+ * The algorithm type only specifies the fields in a flow
+ * will be used as part of the hash. Each datapath is free
+ * to use its own hash algorithm. The hash value will be
+ * opaque to the user space daemon.
+ */
+enum ovs_hash_alg {
+	OVS_HASH_ALG_L4,
+};
+
+/*
+ * struct ovs_action_hash - %OVS_ACTION_ATTR_HASH action argument.
+ * @hash_alg: Algorithm used to compute hash prior to recirculation.
+ * @hash_basis: basis used for computing hash.
+ */
+struct ovs_action_hash {
+	uint32_t  hash_alg;     /* One of ovs_hash_alg. */
+	uint32_t  hash_basis;
+};
+
 /**
  * enum ovs_action_attr - Action types.
  *
@@ -521,6 +545,8 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_PUSH_VLAN,    /* struct ovs_action_push_vlan. */
 	OVS_ACTION_ATTR_POP_VLAN,     /* No argument. */
 	OVS_ACTION_ATTR_SAMPLE,       /* Nested OVS_SAMPLE_ATTR_*. */
+	OVS_ACTION_ATTR_RECIRC,       /* u32 recirc_id. */
+	OVS_ACTION_ATTR_HASH,	      /* struct ovs_action_hash. */
 	__OVS_ACTION_ATTR_MAX
 };
 
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index c31bb80c984f..6932a42e41a2 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -35,12 +35,78 @@
 #include <net/sctp/checksum.h>
 
 #include "datapath.h"
+#include "flow.h"
 #include "vport.h"
 
 static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			      struct sw_flow_key *key,
 			      const struct nlattr *attr, int len);
 
+struct deferred_action {
+	struct sk_buff *skb;
+	const struct nlattr *actions;
+
+	/* Store pkt_key clone when creating deferred action. */
+	struct sw_flow_key pkt_key;
+};
+
+#define DEFERRED_ACTION_FIFO_SIZE 10
+struct action_fifo {
+	int head;
+	int tail;
+	/* Deferred action fifo queue storage. */
+	struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
+};
+
+static struct action_fifo __percpu *action_fifos;
+static DEFINE_PER_CPU(int, exec_actions_level);
+
+static void action_fifo_init(struct action_fifo *fifo)
+{
+	fifo->head = 0;
+	fifo->tail = 0;
+}
+
+static bool action_fifo_is_empty(struct action_fifo *fifo)
+{
+	return (fifo->head == fifo->tail);
+}
+
+static struct deferred_action *action_fifo_get(struct action_fifo *fifo)
+{
+	if (action_fifo_is_empty(fifo))
+		return NULL;
+
+	return &fifo->fifo[fifo->tail++];
+}
+
+static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
+{
+	if (fifo->head >= DEFERRED_ACTION_FIFO_SIZE - 1)
+		return NULL;
+
+	return &fifo->fifo[fifo->head++];
+}
+
+/* Return true if fifo is not full */
+static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
+						    struct sw_flow_key *key,
+						    const struct nlattr *attr)
+{
+	struct action_fifo *fifo;
+	struct deferred_action *da;
+
+	fifo = this_cpu_ptr(action_fifos);
+	da = action_fifo_put(fifo);
+	if (da) {
+		da->skb = skb;
+		da->actions = attr;
+		da->pkt_key = *key;
+	}
+
+	return da;
+}
+
 static int make_writable(struct sk_buff *skb, int write_len)
 {
 	if (!pskb_may_pull(skb, write_len))
@@ -485,8 +551,29 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 		/* Skip the sample action when out of memory. */
 		return 0;
 
-	/* do_execute_actions() will consume the cloned skb. */
-	return do_execute_actions(dp, skb, key, a, rem);
+	if (!add_deferred_actions(skb, key, a)) {
+		if (net_ratelimit())
+			pr_warn("%s: deferred actions limit reached, dropping sample action\n",
+				ovs_dp_name(dp));
+
+		kfree_skb(skb);
+	}
+	return 0;
+}
+
+static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
+			 const struct nlattr *attr)
+{
+	struct ovs_action_hash *hash_act = nla_data(attr);
+	u32 hash = 0;
+
+	/* OVS_HASH_ALG_L4 is the only possible hash algorithm.  */
+	hash = skb_get_hash(skb);
+	hash = jhash_1word(hash, hash_act->hash_basis);
+	if (!hash)
+		hash = 0x1;
+
+	key->ovs_flow_hash = hash;
 }
 
 static int execute_set_action(struct sk_buff *skb,
@@ -535,6 +622,44 @@ static int execute_set_action(struct sk_buff *skb,
 	return err;
 }
 
+static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
+			  struct sw_flow_key *key,
+			  const struct nlattr *a, int rem)
+{
+	struct deferred_action *da;
+	int err;
+
+	err = ovs_flow_key_update(skb, key);
+	if (err)
+		return err;
+
+	if (!last_action(a, rem)) {
+		/* Recirc action is the not the last action
+		 * of the action list, need to clone the skb.
+		 */
+		skb = skb_clone(skb, GFP_ATOMIC);
+
+		/* Skip the recirc action when out of memory, but
+		 * continue on with the rest of the action list.
+		 */
+		if (!skb)
+			return 0;
+	}
+
+	da = add_deferred_actions(skb, key, NULL);
+	if (da) {
+		da->pkt_key.recirc_id = nla_get_u32(a);
+	} else {
+		kfree_skb(skb);
+
+		if (net_ratelimit())
+			pr_warn("%s: deferred action limit reached, drop recirc action\n",
+				ovs_dp_name(dp));
+	}
+
+	return 0;
+}
+
 /* Execute a list of actions against 'skb'. */
 static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			      struct sw_flow_key *key,
@@ -566,6 +691,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			output_userspace(dp, skb, key, a);
 			break;
 
+		case OVS_ACTION_ATTR_HASH:
+			execute_hash(skb, key, a);
+			break;
+
 		case OVS_ACTION_ATTR_PUSH_VLAN:
 			err = push_vlan(skb, nla_data(a));
 			if (unlikely(err)) /* skb already freed. */
@@ -576,6 +705,17 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			err = pop_vlan(skb);
 			break;
 
+		case OVS_ACTION_ATTR_RECIRC:
+			err = execute_recirc(dp, skb, key, a, rem);
+			if (last_action(a, rem)) {
+				/* If this is the last action, the skb has
+				 * been consumed or freed.
+				 * Return immediately.
+				 */
+				return err;
+			}
+			break;
+
 		case OVS_ACTION_ATTR_SET:
 			err = execute_set_action(skb, nla_data(a));
 			break;
@@ -601,12 +741,63 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	return 0;
 }
 
+static void process_deferred_actions(struct datapath *dp)
+{
+	struct action_fifo *fifo = this_cpu_ptr(action_fifos);
+
+	/* Do not touch the FIFO in case there is no deferred actions. */
+	if (action_fifo_is_empty(fifo))
+		return;
+
+	/* Finishing executing all deferred actions. */
+	do {
+		struct deferred_action *da = action_fifo_get(fifo);
+		struct sk_buff *skb = da->skb;
+		struct sw_flow_key *key = &da->pkt_key;
+		const struct nlattr *actions = da->actions;
+
+		if (actions)
+			do_execute_actions(dp, skb, key, actions,
+					   nla_len(actions));
+		else
+			ovs_dp_process_packet(skb, key);
+	} while (!action_fifo_is_empty(fifo));
+
+	/* Reset FIFO for the next packet.  */
+	action_fifo_init(fifo);
+}
+
 /* Execute a list of actions against 'skb'. */
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			struct sw_flow_key *key)
 {
-	struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+	int level = this_cpu_read(exec_actions_level);
+	struct sw_flow_actions *acts;
+	int err;
+
+	acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+
+	this_cpu_inc(exec_actions_level);
+	err = do_execute_actions(dp, skb, key,
+				 acts->actions, acts->actions_len);
+
+	if (!level)
+		process_deferred_actions(dp);
+
+	this_cpu_dec(exec_actions_level);
+	return err;
+}
+
+int action_fifos_init(void)
+{
+	action_fifos = alloc_percpu(struct action_fifo);
+	if (!action_fifos)
+		return -ENOMEM;
 
-	return do_execute_actions(dp, skb, key,
-				  acts->actions, acts->actions_len);
+	return 0;
+}
+
+void action_fifos_exit(void)
+{
+	free_percpu(action_fifos);
 }
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 7e0819919b8a..16cad14fa81e 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -156,7 +156,7 @@ static struct datapath *get_dp(struct net *net, int dp_ifindex)
 }
 
 /* Must be called with rcu_read_lock or ovs_mutex. */
-static const char *ovs_dp_name(const struct datapath *dp)
+const char *ovs_dp_name(const struct datapath *dp)
 {
 	struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL);
 	return vport->ops->get_name(vport);
@@ -2065,10 +2065,14 @@ static int __init dp_init(void)
 
 	pr_info("Open vSwitch switching datapath\n");
 
-	err = ovs_internal_dev_rtnl_link_register();
+	err = action_fifos_init();
 	if (err)
 		goto error;
 
+	err = ovs_internal_dev_rtnl_link_register();
+	if (err)
+		goto error_action_fifos_exit;
+
 	err = ovs_flow_init();
 	if (err)
 		goto error_unreg_rtnl_link;
@@ -2101,6 +2105,8 @@ error_flow_exit:
 	ovs_flow_exit();
 error_unreg_rtnl_link:
 	ovs_internal_dev_rtnl_link_unregister();
+error_action_fifos_exit:
+	action_fifos_exit();
 error:
 	return err;
 }
@@ -2114,6 +2120,7 @@ static void dp_cleanup(void)
 	ovs_vport_exit();
 	ovs_flow_exit();
 	ovs_internal_dev_rtnl_link_unregister();
+	action_fifos_exit();
 }
 
 module_init(dp_init);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 25b0e888cb27..ac3f3df96961 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2012 Nicira, Inc.
+ * Copyright (c) 2007-2014 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -189,13 +189,18 @@ void ovs_dp_detach_port(struct vport *);
 int ovs_dp_upcall(struct datapath *, struct sk_buff *,
 		  const struct dp_upcall_info *);
 
+const char *ovs_dp_name(const struct datapath *dp);
 struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
 					 u8 cmd);
 
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			struct sw_flow_key *);
+
 void ovs_dp_notify_wq(struct work_struct *work);
 
+int action_fifos_init(void);
+void action_fifos_exit(void);
+
 #define OVS_NLERR(fmt, ...)					\
 do {								\
 	if (net_ratelimit())					\
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index bf8442071d75..4010423f2831 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -606,6 +606,11 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 	return 0;
 }
 
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	return key_extract(skb, key);
+}
+
 int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key,
 			 struct sk_buff *skb, struct sw_flow_key *key)
 {
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 3869a540365c..0f5db4ec565d 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -72,6 +72,8 @@ struct sw_flow_key {
 		u32	skb_mark;	/* SKB mark. */
 		u16	in_port;	/* Input switch port (or DP_MAX_PORTS). */
 	} __packed phy; /* Safe when right after 'tun_key'. */
+	u32 ovs_flow_hash;		/* Datapath computed hash value.  */
+	u32 recirc_id;			/* Recirculation ID.  */
 	struct {
 		u8     src[ETH_ALEN];	/* Ethernet source address. */
 		u8     dst[ETH_ALEN];	/* Ethernet destination address. */
@@ -187,6 +189,7 @@ void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
 void ovs_flow_stats_clear(struct sw_flow *);
 u64 ovs_flow_used_time(unsigned long flow_jiffies);
 
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
 int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key,
 			 struct sk_buff *skb, struct sw_flow_key *key);
 /* Extract key from packet coming from userspace. */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 630b320fbf3e..f4c8daa73965 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -251,6 +251,8 @@ static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 	[OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6),
 	[OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp),
 	[OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd),
+	[OVS_KEY_ATTR_RECIRC_ID] = sizeof(u32),
+	[OVS_KEY_ATTR_DP_HASH] = sizeof(u32),
 	[OVS_KEY_ATTR_TUNNEL] = -1,
 };
 
@@ -454,6 +456,20 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
 static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 				 const struct nlattr **a, bool is_mask)
 {
+	if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) {
+		u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]);
+
+		SW_FLOW_KEY_PUT(match, ovs_flow_hash, hash_val, is_mask);
+		*attrs &= ~(1 << OVS_KEY_ATTR_DP_HASH);
+	}
+
+	if (*attrs & (1 << OVS_KEY_ATTR_RECIRC_ID)) {
+		u32 recirc_id = nla_get_u32(a[OVS_KEY_ATTR_RECIRC_ID]);
+
+		SW_FLOW_KEY_PUT(match, recirc_id, recirc_id, is_mask);
+		*attrs &= ~(1 << OVS_KEY_ATTR_RECIRC_ID);
+	}
+
 	if (*attrs & (1 << OVS_KEY_ATTR_PRIORITY)) {
 		SW_FLOW_KEY_PUT(match, phy.priority,
 			  nla_get_u32(a[OVS_KEY_ATTR_PRIORITY]), is_mask);
@@ -873,6 +889,12 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 	struct nlattr *nla, *encap;
 	bool is_mask = (swkey != output);
 
+	if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, OVS_KEY_ATTR_DP_HASH, output->ovs_flow_hash))
+		goto nla_put_failure;
+
 	if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
 		goto nla_put_failure;
 
@@ -1401,11 +1423,13 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 		/* Expected argument lengths, (u32)-1 for variable length. */
 		static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
 			[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
+			[OVS_ACTION_ATTR_RECIRC] = sizeof(u32),
 			[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
 			[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
 			[OVS_ACTION_ATTR_POP_VLAN] = 0,
 			[OVS_ACTION_ATTR_SET] = (u32)-1,
-			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1
+			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
+			[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash)
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -1432,6 +1456,18 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 				return -EINVAL;
 			break;
 
+		case OVS_ACTION_ATTR_HASH: {
+			const struct ovs_action_hash *act_hash = nla_data(a);
+
+			switch (act_hash->hash_alg) {
+			case OVS_HASH_ALG_L4:
+				break;
+			default:
+				return  -EINVAL;
+			}
+
+			break;
+		}
 
 		case OVS_ACTION_ATTR_POP_VLAN:
 			break;
@@ -1444,6 +1480,9 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
 				return -EINVAL;
 			break;
 
+		case OVS_ACTION_ATTR_RECIRC:
+			break;
+
 		case OVS_ACTION_ATTR_SET:
 			err = validate_set(a, key, sfa, &skip_copy);
 			if (err)
-- 
cgit v1.2.3


From f92ee61982d6da15a9e49664ecd6405a15a2ee56 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 16 Sep 2014 10:08:40 +0200
Subject: xfrm: Generate blackhole routes only from route lookup functions

Currently we genarate a blackhole route route whenever we have
matching policies but can not resolve the states. Here we assume
that dst_output() is called to kill the balckholed packets.
Unfortunately this assumption is not true in all cases, so
it is possible that these packets leave the system unwanted.

We fix this by generating blackhole routes only from the
route lookup functions, here we can guarantee a call to
dst_output() afterwards.

Fixes: 2774c131b1d ("xfrm: Handle blackhole route creation via afinfo.")
Reported-by: Konstantinos Kolelis <k.kolelis@sirrix.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/dst.h      | 15 ++++++++++++++-
 net/ipv4/route.c       |  6 +++---
 net/ipv6/ip6_output.c  |  4 ++--
 net/xfrm/xfrm_policy.c | 18 +++++++++++++++++-
 4 files changed, 36 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 71c60f42be48..fa11c904d219 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -490,7 +490,16 @@ static inline struct dst_entry *xfrm_lookup(struct net *net,
 					    int flags)
 {
 	return dst_orig;
-} 
+}
+
+static inline struct dst_entry *xfrm_lookup_route(struct net *net,
+						  struct dst_entry *dst_orig,
+						  const struct flowi *fl,
+						  struct sock *sk,
+						  int flags)
+{
+	return dst_orig;
+}
 
 static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
 {
@@ -502,6 +511,10 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 			      const struct flowi *fl, struct sock *sk,
 			      int flags);
 
+struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
+				    const struct flowi *fl, struct sock *sk,
+				    int flags);
+
 /* skb attached with this dst needs transformation if dst->xfrm is valid */
 static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
 {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index eaa4b000c7b4..173e7ea54c70 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2265,9 +2265,9 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 		return rt;
 
 	if (flp4->flowi4_proto)
-		rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
-						   flowi4_to_flowi(flp4),
-						   sk, 0);
+		rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst,
+							flowi4_to_flowi(flp4),
+							sk, 0);
 
 	return rt;
 }
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 315a55d66079..0a3448b2888f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1009,7 +1009,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 	if (final_dst)
 		fl6->daddr = *final_dst;
 
-	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
 
@@ -1041,7 +1041,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 	if (final_dst)
 		fl6->daddr = *final_dst;
 
-	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index beeed602aeb3..7505674c9faa 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2138,7 +2138,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 			xfrm_pols_put(pols, drop_pols);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
 
-			return make_blackhole(net, family, dst_orig);
+			return ERR_PTR(-EREMOTE);
 		}
 
 		err = -EAGAIN;
@@ -2195,6 +2195,22 @@ dropdst:
 }
 EXPORT_SYMBOL(xfrm_lookup);
 
+/* Callers of xfrm_lookup_route() must ensure a call to dst_output().
+ * Otherwise we may send out blackholed packets.
+ */
+struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
+				    const struct flowi *fl,
+				    struct sock *sk, int flags)
+{
+	struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, flags);
+
+	if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
+		return make_blackhole(net, dst_orig->ops->family, dst_orig);
+
+	return dst;
+}
+EXPORT_SYMBOL(xfrm_lookup_route);
+
 static inline int
 xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl)
 {
-- 
cgit v1.2.3


From b8c203b2d2fc961bafd53b41d5396bbcdec55998 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 16 Sep 2014 10:08:49 +0200
Subject: xfrm: Generate queueing routes only from route lookup functions

Currently we genarate a queueing route if we have matching policies
but can not resolve the states and the sysctl xfrm_larval_drop is
disabled. Here we assume that dst_output() is called to kill the
queued packets. Unfortunately this assumption is not true in all
cases, so it is possible that these packets leave the system unwanted.

We fix this by generating queueing routes only from the
route lookup functions, here we can guarantee a call to
dst_output() afterwards.

Fixes: a0073fe18e71 ("xfrm: Add a state resolution packet queue")
Reported-by: Konstantinos Kolelis <k.kolelis@sirrix.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/dst.h      |  1 +
 net/xfrm/xfrm_policy.c | 32 ++++++++++++++++++++++++--------
 2 files changed, 25 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index fa11c904d219..a8ae4e760778 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -480,6 +480,7 @@ void dst_init(void);
 /* Flags for xfrm_lookup flags argument. */
 enum {
 	XFRM_LOOKUP_ICMP = 1 << 0,
+	XFRM_LOOKUP_QUEUE = 1 << 1,
 };
 
 struct flowi;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 7505674c9faa..fdde51f4271a 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -39,6 +39,11 @@
 #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
 #define XFRM_MAX_QUEUE_LEN	100
 
+struct xfrm_flo {
+	struct dst_entry *dst_orig;
+	u8 flags;
+};
+
 static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
 static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO]
 						__read_mostly;
@@ -1877,13 +1882,14 @@ static int xdst_queue_output(struct sock *sk, struct sk_buff *skb)
 }
 
 static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
-						 struct dst_entry *dst,
+						 struct xfrm_flo *xflo,
 						 const struct flowi *fl,
 						 int num_xfrms,
 						 u16 family)
 {
 	int err;
 	struct net_device *dev;
+	struct dst_entry *dst;
 	struct dst_entry *dst1;
 	struct xfrm_dst *xdst;
 
@@ -1891,9 +1897,12 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
 	if (IS_ERR(xdst))
 		return xdst;
 
-	if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0)
+	if (!(xflo->flags & XFRM_LOOKUP_QUEUE) ||
+	    net->xfrm.sysctl_larval_drop ||
+	    num_xfrms <= 0)
 		return xdst;
 
+	dst = xflo->dst_orig;
 	dst1 = &xdst->u.dst;
 	dst_hold(dst);
 	xdst->route = dst;
@@ -1935,7 +1944,7 @@ static struct flow_cache_object *
 xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
 		   struct flow_cache_object *oldflo, void *ctx)
 {
-	struct dst_entry *dst_orig = (struct dst_entry *)ctx;
+	struct xfrm_flo *xflo = (struct xfrm_flo *)ctx;
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	struct xfrm_dst *xdst, *new_xdst;
 	int num_pols = 0, num_xfrms = 0, i, err, pol_dead;
@@ -1976,7 +1985,8 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
 			goto make_dummy_bundle;
 	}
 
-	new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig);
+	new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
+						  xflo->dst_orig);
 	if (IS_ERR(new_xdst)) {
 		err = PTR_ERR(new_xdst);
 		if (err != -EAGAIN)
@@ -2010,7 +2020,7 @@ make_dummy_bundle:
 	/* We found policies, but there's no bundles to instantiate:
 	 * either because the policy blocks, has no transformations or
 	 * we could not build template (no xfrm_states).*/
-	xdst = xfrm_create_dummy_bundle(net, dst_orig, fl, num_xfrms, family);
+	xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family);
 	if (IS_ERR(xdst)) {
 		xfrm_pols_put(pols, num_pols);
 		return ERR_CAST(xdst);
@@ -2104,13 +2114,18 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 	}
 
 	if (xdst == NULL) {
+		struct xfrm_flo xflo;
+
+		xflo.dst_orig = dst_orig;
+		xflo.flags = flags;
+
 		/* To accelerate a bit...  */
 		if ((dst_orig->flags & DST_NOXFRM) ||
 		    !net->xfrm.policy_count[XFRM_POLICY_OUT])
 			goto nopol;
 
 		flo = flow_cache_lookup(net, fl, family, dir,
-					xfrm_bundle_lookup, dst_orig);
+					xfrm_bundle_lookup, &xflo);
 		if (flo == NULL)
 			goto nopol;
 		if (IS_ERR(flo)) {
@@ -2202,7 +2217,8 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
 				    const struct flowi *fl,
 				    struct sock *sk, int flags)
 {
-	struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, flags);
+	struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk,
+					    flags | XFRM_LOOKUP_QUEUE);
 
 	if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
 		return make_blackhole(net, dst_orig->ops->family, dst_orig);
@@ -2476,7 +2492,7 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
 
 	skb_dst_force(skb);
 
-	dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, 0);
+	dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE);
 	if (IS_ERR(dst)) {
 		res = 0;
 		dst = NULL;
-- 
cgit v1.2.3


From 3c5f8853469d3e549799808b9bf639b5d32751f0 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 4 Sep 2014 17:31:25 +0530
Subject: power-supply: Forward declare structs together

power_supply.h requires to forward declare few structures. One of them is done
at the top of the file and other one just before it is used. Declare them
together for better readability.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Sebastian Reichel <sre@kernel.org>
---
 include/linux/power_supply.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index de59a28b1b5b..3ed049673022 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -18,8 +18,6 @@
 #include <linux/spinlock.h>
 #include <linux/notifier.h>
 
-struct device;
-
 /*
  * All voltages, currents, charges, energies, time and temperatures in uV,
  * µA, µAh, µWh, seconds and tenths of degree Celsius unless otherwise
@@ -175,6 +173,7 @@ union power_supply_propval {
 	const char *strval;
 };
 
+struct device;
 struct device_node;
 
 struct power_supply {
-- 
cgit v1.2.3


From 184564efae4d775225c8fe3b762a56956fb1f827 Mon Sep 17 00:00:00 2001
From: Zhang Haoyu <zhanghy@sangfor.com>
Date: Thu, 11 Sep 2014 16:47:04 +0800
Subject: kvm: ioapic: conditionally delay irq delivery duringeoi broadcast

Currently, we call ioapic_service() immediately when we find the irq is still
active during eoi broadcast. But for real hardware, there's some delay between
the EOI writing and irq delivery.  If we do not emulate this behavior, and
re-inject the interrupt immediately after the guest sends an EOI and re-enables
interrupts, a guest might spend all its time in the ISR if it has a broken
handler for a level-triggered interrupt.

Such livelock actually happens with Windows guests when resuming from
hibernation.

As there's no way to recognize the broken handle from new raised ones, this patch
delays an interrupt if 10.000 consecutive EOIs found that the interrupt was
still high.  The guest can then make a little forward progress, until a proper
IRQ handler is set or until some detection routine in the guest (such as
Linux's note_interrupt()) recognizes the situation.

Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Zhang Haoyu <zhanghy@sangfor.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/trace/events/kvm.h | 20 ++++++++++++++++++++
 virt/kvm/ioapic.c          | 46 ++++++++++++++++++++++++++++++++++++++++++++--
 virt/kvm/ioapic.h          |  2 ++
 3 files changed, 66 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 908925ace776..ab679c395042 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -95,6 +95,26 @@ TRACE_EVENT(kvm_ioapic_set_irq,
 		  __entry->coalesced ? " (coalesced)" : "")
 );
 
+TRACE_EVENT(kvm_ioapic_delayed_eoi_inj,
+	    TP_PROTO(__u64 e),
+	    TP_ARGS(e),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		e		)
+	),
+
+	TP_fast_assign(
+		__entry->e		= e;
+	),
+
+	TP_printk("dst %x vec=%u (%s|%s|%s%s)",
+		  (u8)(__entry->e >> 56), (u8)__entry->e,
+		  __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
+		  (__entry->e & (1<<11)) ? "logical" : "physical",
+		  (__entry->e & (1<<15)) ? "level" : "edge",
+		  (__entry->e & (1<<16)) ? "|masked" : "")
+);
+
 TRACE_EVENT(kvm_msi_set_irq,
 	    TP_PROTO(__u64 address, __u64 data),
 	    TP_ARGS(address, data),
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index e8ce34c9db32..0ba4057d271b 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -405,6 +405,26 @@ void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
 	spin_unlock(&ioapic->lock);
 }
 
+static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
+{
+	int i;
+	struct kvm_ioapic *ioapic = container_of(work, struct kvm_ioapic,
+						 eoi_inject.work);
+	spin_lock(&ioapic->lock);
+	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
+
+		if (ent->fields.trig_mode != IOAPIC_LEVEL_TRIG)
+			continue;
+
+		if (ioapic->irr & (1 << i) && !ent->fields.remote_irr)
+			ioapic_service(ioapic, i, false);
+	}
+	spin_unlock(&ioapic->lock);
+}
+
+#define IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT 10000
+
 static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
 {
@@ -435,8 +455,26 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
 		ent->fields.remote_irr = 0;
-		if (ioapic->irr & (1 << i))
-			ioapic_service(ioapic, i, false);
+		if (!ent->fields.mask && (ioapic->irr & (1 << i))) {
+			++ioapic->irq_eoi[i];
+			if (ioapic->irq_eoi[i] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) {
+				/*
+				 * Real hardware does not deliver the interrupt
+				 * immediately during eoi broadcast, and this
+				 * lets a buggy guest make slow progress
+				 * even if it does not correctly handle a
+				 * level-triggered interrupt.  Emulate this
+				 * behavior if we detect an interrupt storm.
+				 */
+				schedule_delayed_work(&ioapic->eoi_inject, HZ / 100);
+				ioapic->irq_eoi[i] = 0;
+				trace_kvm_ioapic_delayed_eoi_inj(ent->bits);
+			} else {
+				ioapic_service(ioapic, i, false);
+			}
+		} else {
+			ioapic->irq_eoi[i] = 0;
+		}
 	}
 }
 
@@ -565,12 +603,14 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
 {
 	int i;
 
+	cancel_delayed_work_sync(&ioapic->eoi_inject);
 	for (i = 0; i < IOAPIC_NUM_PINS; i++)
 		ioapic->redirtbl[i].fields.mask = 1;
 	ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS;
 	ioapic->ioregsel = 0;
 	ioapic->irr = 0;
 	ioapic->id = 0;
+	memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
 	rtc_irq_eoi_tracking_reset(ioapic);
 	update_handled_vectors(ioapic);
 }
@@ -589,6 +629,7 @@ int kvm_ioapic_init(struct kvm *kvm)
 	if (!ioapic)
 		return -ENOMEM;
 	spin_lock_init(&ioapic->lock);
+	INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work);
 	kvm->arch.vioapic = ioapic;
 	kvm_ioapic_reset(ioapic);
 	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
@@ -609,6 +650,7 @@ void kvm_ioapic_destroy(struct kvm *kvm)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 
+	cancel_delayed_work_sync(&ioapic->eoi_inject);
 	if (ioapic) {
 		kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
 		kvm->arch.vioapic = NULL;
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 90d43e95dcf8..e23b70634f1e 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -59,6 +59,8 @@ struct kvm_ioapic {
 	spinlock_t lock;
 	DECLARE_BITMAP(handled_vectors, 256);
 	struct rtc_status rtc_status;
+	struct delayed_work eoi_inject;
+	u32 irq_eoi[IOAPIC_NUM_PINS];
 };
 
 #ifdef DEBUG
-- 
cgit v1.2.3


From 1b0bf88fd8b845aef4300c7c0feca774265dd1c4 Mon Sep 17 00:00:00 2001
From: Robert Baldyga <r.baldyga@samsung.com>
Date: Tue, 9 Sep 2014 08:23:17 +0200
Subject: usb: gadget: f_fs: virtual endpoint address mapping

This patch introduces virtual endpoint address mapping. It separates
function logic form physical endpoint addresses making it more hardware
independent.

Following modifications changes user space API, so to enable them user
have to switch on the FUNCTIONFS_VIRTUAL_ADDR flag in descriptors.

Endpoints are now refered using virtual endpoint addresses chosen by
user in endpoint descpriptors. This applies to each context when endpoint
address can be used:
- when accessing endpoint files in FunctionFS filesystemi (in file name),
- in setup requests directed to specific endpoint (in wIndex field),
- in descriptors returned by FUNCTIONFS_ENDPOINT_DESC ioctl.

In endpoint file names the endpoint address number is formatted as
double-digit hexadecimal value ("ep%02x") which has few advantages -
it is easy to parse, allows to easly recognize endpoint direction basing
on its name (IN endpoint number starts with digit 8, and OUT with 0)
which can be useful for debugging purpose, and it makes easier to introduce
further features allowing to use each endpoint number in both directions
to have more endpoints available for function if hardware supports this
(for example we could have ep01 which is endpoint 1 with OUT direction,
and ep81 which is endpoint 1 with IN direction).

Physical endpoint address can be still obtained using ioctl named
FUNCTIONFS_ENDPOINT_REVMAP, but now it's not neccesary to handle
USB transactions properly.

Signed-off-by: Robert Baldyga <r.baldyga@samsung.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/gadget/function/f_fs.c  | 23 +++++++++++++++++++++--
 drivers/usb/gadget/function/u_fs.h  |  2 ++
 include/uapi/linux/usb/functionfs.h |  1 +
 3 files changed, 24 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index e4afe8df5553..4ad11e03cf54 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1557,7 +1557,10 @@ static int ffs_epfiles_create(struct ffs_data *ffs)
 		epfile->ffs = ffs;
 		mutex_init(&epfile->mutex);
 		init_waitqueue_head(&epfile->wait);
-		sprintf(epfiles->name, "ep%u",  i);
+		if (ffs->user_flags & FUNCTIONFS_VIRTUAL_ADDR)
+			sprintf(epfiles->name, "ep%02x", ffs->eps_addrmap[i]);
+		else
+			sprintf(epfiles->name, "ep%u", i);
 		if (!unlikely(ffs_sb_create_file(ffs->sb, epfiles->name, epfile,
 						 &ffs_epfile_operations,
 						 &epfile->dentry))) {
@@ -2106,10 +2109,12 @@ static int __ffs_data_got_descs(struct ffs_data *ffs,
 		break;
 	case FUNCTIONFS_DESCRIPTORS_MAGIC_V2:
 		flags = get_unaligned_le32(data + 8);
+		ffs->user_flags = flags;
 		if (flags & ~(FUNCTIONFS_HAS_FS_DESC |
 			      FUNCTIONFS_HAS_HS_DESC |
 			      FUNCTIONFS_HAS_SS_DESC |
-			      FUNCTIONFS_HAS_MS_OS_DESC)) {
+			      FUNCTIONFS_HAS_MS_OS_DESC |
+			      FUNCTIONFS_VIRTUAL_ADDR)) {
 			ret = -ENOSYS;
 			goto error;
 		}
@@ -2466,7 +2471,13 @@ static int __ffs_func_bind_do_descs(enum ffs_entity_type type, u8 *valuep,
 	} else {
 		struct usb_request *req;
 		struct usb_ep *ep;
+		u8 bEndpointAddress;
 
+		/*
+		 * We back up bEndpointAddress because autoconfig overwrites
+		 * it with physical endpoint address.
+		 */
+		bEndpointAddress = ds->bEndpointAddress;
 		pr_vdebug("autoconfig\n");
 		ep = usb_ep_autoconfig(func->gadget, ds);
 		if (unlikely(!ep))
@@ -2481,6 +2492,12 @@ static int __ffs_func_bind_do_descs(enum ffs_entity_type type, u8 *valuep,
 		ffs_ep->req = req;
 		func->eps_revmap[ds->bEndpointAddress &
 				 USB_ENDPOINT_NUMBER_MASK] = idx + 1;
+		/*
+		 * If we use virtual address mapping, we restore
+		 * original bEndpointAddress value.
+		 */
+		if (func->ffs->user_flags & FUNCTIONFS_VIRTUAL_ADDR)
+			ds->bEndpointAddress = bEndpointAddress;
 	}
 	ffs_dump_mem(": Rewritten ep desc", ds, ds->bLength);
 
@@ -2925,6 +2942,8 @@ static int ffs_func_setup(struct usb_function *f,
 		ret = ffs_func_revmap_ep(func, le16_to_cpu(creq->wIndex));
 		if (unlikely(ret < 0))
 			return ret;
+		if (func->ffs->user_flags & FUNCTIONFS_VIRTUAL_ADDR)
+			ret = func->ffs->eps_addrmap[ret];
 		break;
 
 	default:
diff --git a/drivers/usb/gadget/function/u_fs.h b/drivers/usb/gadget/function/u_fs.h
index d48897e8ffeb..cd128e31f808 100644
--- a/drivers/usb/gadget/function/u_fs.h
+++ b/drivers/usb/gadget/function/u_fs.h
@@ -224,6 +224,8 @@ struct ffs_data {
 	void				*ms_os_descs_ext_prop_name_avail;
 	void				*ms_os_descs_ext_prop_data_avail;
 
+	unsigned			user_flags;
+
 	u8				eps_addrmap[15];
 
 	unsigned short			strings_count;
diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index 7c7a2feb0e6e..295ba299e7bd 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -19,6 +19,7 @@ enum functionfs_flags {
 	FUNCTIONFS_HAS_HS_DESC = 2,
 	FUNCTIONFS_HAS_SS_DESC = 4,
 	FUNCTIONFS_HAS_MS_OS_DESC = 8,
+	FUNCTIONFS_VIRTUAL_ADDR = 16,
 };
 
 /* Descriptor of an non-audio endpoint */
-- 
cgit v1.2.3


From 53d91c5ce0cb8945b55e8bb54e551cabc51eb28d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 16 Sep 2014 17:36:01 +0100
Subject: Provide a binary to hex conversion function

Provide a function to convert a buffer of binary data into an unterminated
ascii hex string representation of that data.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
---
 include/linux/kernel.h |  1 +
 lib/hexdump.c          | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 4c52907a6d8b..89a0b8e5a952 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -500,6 +500,7 @@ static inline char * __deprecated pack_hex_byte(char *buf, u8 byte)
 
 extern int hex_to_bin(char ch);
 extern int __must_check hex2bin(u8 *dst, const char *src, size_t count);
+extern char *bin2hex(char *dst, const void *src, size_t count);
 
 int mac_pton(const char *s, u8 *mac);
 
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 8499c810909a..270773b91923 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -58,6 +58,22 @@ int hex2bin(u8 *dst, const char *src, size_t count)
 }
 EXPORT_SYMBOL(hex2bin);
 
+/**
+ * bin2hex - convert binary data to an ascii hexadecimal string
+ * @dst: ascii hexadecimal result
+ * @src: binary data
+ * @count: binary data length
+ */
+char *bin2hex(char *dst, const void *src, size_t count)
+{
+	const unsigned char *_src = src;
+
+	while (count--)
+		dst = hex_byte_pack(dst, *_src++);
+	return dst;
+}
+EXPORT_SYMBOL(bin2hex);
+
 /**
  * hex_dump_to_buffer - convert a blob of data to "hex ASCII" in memory
  * @buf: data blob to dump
-- 
cgit v1.2.3


From 462919591a1791e76042dc5c1e0148715df59beb Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 16 Sep 2014 17:36:02 +0100
Subject: KEYS: Preparse match data

Preparse the match data.  This provides several advantages:

 (1) The preparser can reject invalid criteria up front.

 (2) The preparser can convert the criteria to binary data if necessary (the
     asymmetric key type really wants to do binary comparison of the key IDs).

 (3) The preparser can set the type of search to be performed.  This means
     that it's not then a one-off setting in the key type.

 (4) The preparser can set an appropriate comparator function.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
---
 crypto/asymmetric_keys/asymmetric_type.c | 31 +++++++++++++++++++-
 include/keys/user-type.h                 |  4 ++-
 include/linux/key-type.h                 | 31 ++++++++++++++++++--
 net/dns_resolver/dns_key.c               |  5 ++--
 security/keys/internal.h                 |  8 ++----
 security/keys/keyring.c                  | 49 +++++++++++++++++++-------------
 security/keys/proc.c                     |  8 +++---
 security/keys/process_keys.c             | 13 +++++----
 security/keys/request_key.c              | 21 ++++++++++----
 security/keys/request_key_auth.c         |  6 ++--
 security/keys/user_defined.c             |  4 +--
 11 files changed, 129 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index eb8cd46961a5..f666b4e8d256 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -59,9 +59,11 @@ EXPORT_SYMBOL_GPL(asymmetric_keyid_match);
  *	"id:<id>"	- request a key matching the ID
  *	"<subtype>:<id>" - request a key of a subtype
  */
-static int asymmetric_key_match(const struct key *key, const void *description)
+static int asymmetric_key_match(const struct key *key,
+				const struct key_match_data *match_data)
 {
 	const struct asymmetric_key_subtype *subtype = asymmetric_key_subtype(key);
+	const char *description = match_data->raw_data;
 	const char *spec = description;
 	const char *id;
 	ptrdiff_t speclen;
@@ -93,6 +95,31 @@ static int asymmetric_key_match(const struct key *key, const void *description)
 	return 0;
 }
 
+/*
+ * Preparse the match criterion.  If we don't set lookup_type and cmp,
+ * the default will be an exact match on the key description.
+ *
+ * There are some specifiers for matching key IDs rather than by the key
+ * description:
+ *
+ *	"id:<id>" - request a key by any available ID
+ *
+ * These have to be searched by iteration rather than by direct lookup because
+ * the key is hashed according to its description.
+ */
+static int asymmetric_key_match_preparse(struct key_match_data *match_data)
+{
+	match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE;
+	return 0;
+}
+
+/*
+ * Free the preparsed the match criterion.
+ */
+static void asymmetric_key_match_free(struct key_match_data *match_data)
+{
+}
+
 /*
  * Describe the asymmetric key
  */
@@ -196,7 +223,9 @@ struct key_type key_type_asymmetric = {
 	.preparse	= asymmetric_key_preparse,
 	.free_preparse	= asymmetric_key_free_preparse,
 	.instantiate	= generic_key_instantiate,
+	.match_preparse	= asymmetric_key_match_preparse,
 	.match		= asymmetric_key_match,
+	.match_free	= asymmetric_key_match_free,
 	.destroy	= asymmetric_key_destroy,
 	.describe	= asymmetric_key_describe,
 	.def_lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE,
diff --git a/include/keys/user-type.h b/include/keys/user-type.h
index 3ab1873a4bfa..66d92af30e7c 100644
--- a/include/keys/user-type.h
+++ b/include/keys/user-type.h
@@ -36,11 +36,13 @@ extern struct key_type key_type_user;
 extern struct key_type key_type_logon;
 
 struct key_preparsed_payload;
+struct key_match_data;
 
 extern int user_preparse(struct key_preparsed_payload *prep);
 extern void user_free_preparse(struct key_preparsed_payload *prep);
 extern int user_update(struct key *key, struct key_preparsed_payload *prep);
-extern int user_match(const struct key *key, const void *criterion);
+extern int user_match(const struct key *key,
+		      const struct key_match_data *match_data);
 extern void user_revoke(struct key *key);
 extern void user_destroy(struct key *key);
 extern void user_describe(const struct key *user, struct seq_file *m);
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 44792ee649de..8aba688a451a 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -52,6 +52,22 @@ struct key_preparsed_payload {
 typedef int (*request_key_actor_t)(struct key_construction *key,
 				   const char *op, void *aux);
 
+/*
+ * Preparsed matching criterion.
+ */
+struct key_match_data {
+	/* Comparison function, defaults to type->match, but can be replaced by
+	 * type->match_preparse(). */
+	int (*cmp)(const struct key *key,
+		   const struct key_match_data *match_data);
+
+	const void	*raw_data;	/* Raw match data */
+	void		*preparsed;	/* For ->match_preparse() to stash stuff */
+	unsigned	lookup_type;	/* Type of lookup for this search. */
+#define KEYRING_SEARCH_LOOKUP_DIRECT	0x0000	/* Direct lookup by description. */
+#define KEYRING_SEARCH_LOOKUP_ITERATE	0x0001	/* Iterative search. */
+};
+
 /*
  * kernel managed key type definition
  */
@@ -67,8 +83,6 @@ struct key_type {
 
 	/* Default key search algorithm. */
 	unsigned def_lookup_type;
-#define KEYRING_SEARCH_LOOKUP_DIRECT	0x0000	/* Direct lookup by description. */
-#define KEYRING_SEARCH_LOOKUP_ITERATE	0x0001	/* Iterative search. */
 
 	/* vet a description */
 	int (*vet_description)(const char *description);
@@ -96,8 +110,19 @@ struct key_type {
 	 */
 	int (*update)(struct key *key, struct key_preparsed_payload *prep);
 
+	/* Preparse the data supplied to ->match() (optional).  The
+	 * data to be preparsed can be found in match_data->raw_data.
+	 * The lookup type can also be set by this function.
+	 */
+	int (*match_preparse)(struct key_match_data *match_data);
+
 	/* match a key against a description */
-	int (*match)(const struct key *key, const void *desc);
+	int (*match)(const struct key *key,
+		     const struct key_match_data *match_data);
+
+	/* Free preparsed match data (optional).  This should be supplied it
+	 * ->match_preparse() is supplied. */
+	void (*match_free)(struct key_match_data *match_data);
 
 	/* clear some of the data from a key on revokation (optional)
 	 * - the key's semaphore will be write-locked by the caller
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index f380b2c58178..92df6e508ae7 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -177,10 +177,11 @@ static void dns_resolver_free_preparse(struct key_preparsed_payload *prep)
  * should end with a period).  The domain name is case-independent.
  */
 static int
-dns_resolver_match(const struct key *key, const void *description)
+dns_resolver_match(const struct key *key,
+		   const struct key_match_data *match_data)
 {
 	int slen, dlen, ret = 0;
-	const char *src = key->description, *dsp = description;
+	const char *src = key->description, *dsp = match_data->raw_data;
 
 	kenter("%s,%s", src, dsp);
 
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 5f20da01fd8d..805e60b0b87e 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -107,13 +107,10 @@ extern int iterate_over_keyring(const struct key *keyring,
 				int (*func)(const struct key *key, void *data),
 				void *data);
 
-typedef int (*key_match_func_t)(const struct key *, const void *);
-
 struct keyring_search_context {
 	struct keyring_index_key index_key;
 	const struct cred	*cred;
-	key_match_func_t	match;
-	const void		*match_data;
+	struct key_match_data	match_data;
 	unsigned		flags;
 #define KEYRING_SEARCH_LOOKUP_TYPE	0x0001	/* [as type->def_lookup_type] */
 #define KEYRING_SEARCH_NO_STATE_CHECK	0x0002	/* Skip state checks */
@@ -152,7 +149,8 @@ extern struct key *request_key_and_link(struct key_type *type,
 					struct key *dest_keyring,
 					unsigned long flags);
 
-extern int lookup_user_key_possessed(const struct key *key, const void *target);
+extern int lookup_user_key_possessed(const struct key *key,
+				     const struct key_match_data *match_data);
 extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags,
 				 key_perm_t perm);
 #define KEY_LOOKUP_CREATE	0x01
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 8314a7d2104d..10f0a5f2d362 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -545,7 +545,7 @@ static int keyring_search_iterator(const void *object, void *iterator_data)
 	}
 
 	/* keys that don't match */
-	if (!ctx->match(key, ctx->match_data)) {
+	if (!ctx->match_data.cmp(key, &ctx->match_data)) {
 		kleave(" = 0 [!match]");
 		return 0;
 	}
@@ -585,8 +585,7 @@ skipped:
  */
 static int search_keyring(struct key *keyring, struct keyring_search_context *ctx)
 {
-	if ((ctx->flags & KEYRING_SEARCH_LOOKUP_TYPE) ==
-	    KEYRING_SEARCH_LOOKUP_DIRECT) {
+	if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_DIRECT) {
 		const void *object;
 
 		object = assoc_array_find(&keyring->keys,
@@ -627,7 +626,7 @@ static bool search_nested_keyrings(struct key *keyring,
 	/* Check to see if this top-level keyring is what we are looking for
 	 * and whether it is valid or not.
 	 */
-	if (ctx->flags & KEYRING_SEARCH_LOOKUP_ITERATE ||
+	if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_ITERATE ||
 	    keyring_compare_object(keyring, &ctx->index_key)) {
 		ctx->skipped_ret = 2;
 		ctx->flags |= KEYRING_SEARCH_DO_STATE_CHECK;
@@ -885,16 +884,28 @@ key_ref_t keyring_search(key_ref_t keyring,
 		.index_key.type		= type,
 		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match			= type->match,
-		.match_data		= description,
-		.flags			= (type->def_lookup_type |
-					   KEYRING_SEARCH_DO_STATE_CHECK),
+		.match_data.cmp		= type->match,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_DO_STATE_CHECK,
 	};
+	key_ref_t key;
+	int ret;
 
-	if (!ctx.match)
+	if (!ctx.match_data.cmp)
 		return ERR_PTR(-ENOKEY);
 
-	return keyring_search_aux(keyring, &ctx);
+	if (type->match_preparse) {
+		ret = type->match_preparse(&ctx.match_data);
+		if (ret < 0)
+			return ERR_PTR(ret);
+	}
+
+	key = keyring_search_aux(keyring, &ctx);
+
+	if (type->match_free)
+		type->match_free(&ctx.match_data);
+	return key;
 }
 EXPORT_SYMBOL(keyring_search);
 
@@ -1014,7 +1025,7 @@ static int keyring_detect_cycle_iterator(const void *object,
 
 	/* We might get a keyring with matching index-key that is nonetheless a
 	 * different keyring. */
-	if (key != ctx->match_data)
+	if (key != ctx->match_data.raw_data)
 		return 0;
 
 	ctx->result = ERR_PTR(-EDEADLK);
@@ -1031,14 +1042,14 @@ static int keyring_detect_cycle_iterator(const void *object,
 static int keyring_detect_cycle(struct key *A, struct key *B)
 {
 	struct keyring_search_context ctx = {
-		.index_key	= A->index_key,
-		.match_data	= A,
-		.iterator	= keyring_detect_cycle_iterator,
-		.flags		= (KEYRING_SEARCH_LOOKUP_DIRECT |
-				   KEYRING_SEARCH_NO_STATE_CHECK |
-				   KEYRING_SEARCH_NO_UPDATE_TIME |
-				   KEYRING_SEARCH_NO_CHECK_PERM |
-				   KEYRING_SEARCH_DETECT_TOO_DEEP),
+		.index_key		= A->index_key,
+		.match_data.raw_data	= A,
+		.match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT,
+		.iterator		= keyring_detect_cycle_iterator,
+		.flags			= (KEYRING_SEARCH_NO_STATE_CHECK |
+					   KEYRING_SEARCH_NO_UPDATE_TIME |
+					   KEYRING_SEARCH_NO_CHECK_PERM |
+					   KEYRING_SEARCH_DETECT_TOO_DEEP),
 	};
 
 	rcu_read_lock();
diff --git a/security/keys/proc.c b/security/keys/proc.c
index d3f6f2fd21db..972eeb336b81 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -194,10 +194,10 @@ static int proc_keys_show(struct seq_file *m, void *v)
 		.index_key.type		= key->type,
 		.index_key.description	= key->description,
 		.cred			= current_cred(),
-		.match			= lookup_user_key_possessed,
-		.match_data		= key,
-		.flags			= (KEYRING_SEARCH_NO_STATE_CHECK |
-					   KEYRING_SEARCH_LOOKUP_DIRECT),
+		.match_data.cmp		= lookup_user_key_possessed,
+		.match_data.raw_data	= key,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_NO_STATE_CHECK,
 	};
 
 	key_ref = make_key_ref(key, 0);
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 0cf8a130a267..08bd533d014f 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -489,9 +489,10 @@ found:
 /*
  * See if the key we're looking at is the target key.
  */
-int lookup_user_key_possessed(const struct key *key, const void *target)
+int lookup_user_key_possessed(const struct key *key,
+			      const struct key_match_data *match_data)
 {
-	return key == target;
+	return key == match_data->raw_data;
 }
 
 /*
@@ -516,9 +517,9 @@ key_ref_t lookup_user_key(key_serial_t id, unsigned long lflags,
 			  key_perm_t perm)
 {
 	struct keyring_search_context ctx = {
-		.match	= lookup_user_key_possessed,
-		.flags	= (KEYRING_SEARCH_NO_STATE_CHECK |
-			   KEYRING_SEARCH_LOOKUP_DIRECT),
+		.match_data.cmp		= lookup_user_key_possessed,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_NO_STATE_CHECK,
 	};
 	struct request_key_auth *rka;
 	struct key *key;
@@ -673,7 +674,7 @@ try_again:
 		ctx.index_key.type		= key->type;
 		ctx.index_key.description	= key->description;
 		ctx.index_key.desc_len		= strlen(key->description);
-		ctx.match_data			= key;
+		ctx.match_data.raw_data		= key;
 		kdebug("check possessed");
 		skey_ref = search_process_keyrings(&ctx);
 		kdebug("possessed=%p", skey_ref);
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 381411941cc1..408523e5e2e2 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -531,9 +531,9 @@ struct key *request_key_and_link(struct key_type *type,
 		.index_key.type		= type,
 		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match			= type->match,
-		.match_data		= description,
-		.flags			= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.match_data.cmp		= type->match,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	};
 	struct key *key;
 	key_ref_t key_ref;
@@ -543,6 +543,14 @@ struct key *request_key_and_link(struct key_type *type,
 	       ctx.index_key.type->name, ctx.index_key.description,
 	       callout_info, callout_len, aux, dest_keyring, flags);
 
+	if (type->match_preparse) {
+		ret = type->match_preparse(&ctx.match_data);
+		if (ret < 0) {
+			key = ERR_PTR(ret);
+			goto error;
+		}
+	}
+
 	/* search all the process keyrings for a key */
 	key_ref = search_process_keyrings(&ctx);
 
@@ -555,7 +563,7 @@ struct key *request_key_and_link(struct key_type *type,
 			if (ret < 0) {
 				key_put(key);
 				key = ERR_PTR(ret);
-				goto error;
+				goto error_free;
 			}
 		}
 	} else if (PTR_ERR(key_ref) != -EAGAIN) {
@@ -565,12 +573,15 @@ struct key *request_key_and_link(struct key_type *type,
 		 * should consult userspace if we can */
 		key = ERR_PTR(-ENOKEY);
 		if (!callout_info)
-			goto error;
+			goto error_free;
 
 		key = construct_key_and_link(&ctx, callout_info, callout_len,
 					     aux, dest_keyring, flags);
 	}
 
+error_free:
+	if (type->match_free)
+		type->match_free(&ctx.match_data);
 error:
 	kleave(" = %p", key);
 	return key;
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 739e7455d388..9ae02819cc06 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -246,9 +246,9 @@ struct key *key_get_instantiation_authkey(key_serial_t target_id)
 		.index_key.type		= &key_type_request_key_auth,
 		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match			= user_match,
-		.match_data		= description,
-		.flags			= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.match_data.cmp		= user_match,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	};
 	struct key *authkey;
 	key_ref_t authkey_ref;
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index eee340011f2b..ec8a56063b02 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -141,9 +141,9 @@ EXPORT_SYMBOL_GPL(user_update);
 /*
  * match users on their name
  */
-int user_match(const struct key *key, const void *description)
+int user_match(const struct key *key, const struct key_match_data *match_data)
 {
-	return strcmp(key->description, description) == 0;
+	return strcmp(key->description, match_data->raw_data) == 0;
 }
 
 EXPORT_SYMBOL_GPL(user_match);
-- 
cgit v1.2.3


From 614d8c39014c185aa0f7254f0a470cc33fc1b284 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 16 Sep 2014 17:36:04 +0100
Subject: KEYS: Remove key_type::def_lookup_type

Remove key_type::def_lookup_type as it's no longer used.  The information now
defaults to KEYRING_SEARCH_LOOKUP_DIRECT but may be overridden by
type->match_preparse().

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
---
 crypto/asymmetric_keys/asymmetric_type.c |  1 -
 crypto/asymmetric_keys/pkcs7_key_type.c  |  1 -
 include/linux/key-type.h                 |  3 ---
 security/keys/big_key.c                  |  1 -
 security/keys/internal.h                 | 11 +++++------
 security/keys/user_defined.c             |  2 --
 6 files changed, 5 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index f666b4e8d256..9d78ad7754d9 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -228,7 +228,6 @@ struct key_type key_type_asymmetric = {
 	.match_free	= asymmetric_key_match_free,
 	.destroy	= asymmetric_key_destroy,
 	.describe	= asymmetric_key_describe,
-	.def_lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE,
 };
 EXPORT_SYMBOL_GPL(key_type_asymmetric);
 
diff --git a/crypto/asymmetric_keys/pkcs7_key_type.c b/crypto/asymmetric_keys/pkcs7_key_type.c
index 3de5fb011de0..d1faa1df1dec 100644
--- a/crypto/asymmetric_keys/pkcs7_key_type.c
+++ b/crypto/asymmetric_keys/pkcs7_key_type.c
@@ -72,7 +72,6 @@ error:
  */
 static struct key_type key_type_pkcs7 = {
 	.name			= "pkcs7_test",
-	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.preparse		= pkcs7_preparse,
 	.free_preparse		= user_free_preparse,
 	.instantiate		= generic_key_instantiate,
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 8aba688a451a..bf93ea609273 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -81,9 +81,6 @@ struct key_type {
 	 */
 	size_t def_datalen;
 
-	/* Default key search algorithm. */
-	unsigned def_lookup_type;
-
 	/* vet a description */
 	int (*vet_description)(const char *description);
 
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index c2f91a0cf889..4045c13a761a 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -33,7 +33,6 @@ MODULE_LICENSE("GPL");
  */
 struct key_type key_type_big_key = {
 	.name			= "big_key",
-	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.preparse		= big_key_preparse,
 	.free_preparse		= big_key_free_preparse,
 	.instantiate		= generic_key_instantiate,
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 805e60b0b87e..b47cc532be1e 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -112,12 +112,11 @@ struct keyring_search_context {
 	const struct cred	*cred;
 	struct key_match_data	match_data;
 	unsigned		flags;
-#define KEYRING_SEARCH_LOOKUP_TYPE	0x0001	/* [as type->def_lookup_type] */
-#define KEYRING_SEARCH_NO_STATE_CHECK	0x0002	/* Skip state checks */
-#define KEYRING_SEARCH_DO_STATE_CHECK	0x0004	/* Override NO_STATE_CHECK */
-#define KEYRING_SEARCH_NO_UPDATE_TIME	0x0008	/* Don't update times */
-#define KEYRING_SEARCH_NO_CHECK_PERM	0x0010	/* Don't check permissions */
-#define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0020	/* Give an error on excessive depth */
+#define KEYRING_SEARCH_NO_STATE_CHECK	0x0001	/* Skip state checks */
+#define KEYRING_SEARCH_DO_STATE_CHECK	0x0002	/* Override NO_STATE_CHECK */
+#define KEYRING_SEARCH_NO_UPDATE_TIME	0x0004	/* Don't update times */
+#define KEYRING_SEARCH_NO_CHECK_PERM	0x0008	/* Don't check permissions */
+#define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0010	/* Give an error on excessive depth */
 
 	int (*iterator)(const void *object, void *iterator_data);
 
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index ec8a56063b02..cd7e726e8646 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -26,7 +26,6 @@ static int logon_vet_description(const char *desc);
  */
 struct key_type key_type_user = {
 	.name			= "user",
-	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.preparse		= user_preparse,
 	.free_preparse		= user_free_preparse,
 	.instantiate		= generic_key_instantiate,
@@ -48,7 +47,6 @@ EXPORT_SYMBOL_GPL(key_type_user);
  */
 struct key_type key_type_logon = {
 	.name			= "logon",
-	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.preparse		= user_preparse,
 	.free_preparse		= user_free_preparse,
 	.instantiate		= generic_key_instantiate,
-- 
cgit v1.2.3


From c06cfb08b88dfbe13be44a69ae2fdc3a7c902d81 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 16 Sep 2014 17:36:06 +0100
Subject: KEYS: Remove key_type::match in favour of overriding default by
 match_preparse

A previous patch added a ->match_preparse() method to the key type.  This is
allowed to override the function called by the iteration algorithm.
Therefore, we can just set a default that simply checks for an exact match of
the key description with the original criterion data and allow match_preparse
to override it as needed.

The key_type::match op is then redundant and can be removed, as can the
user_match() function.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
---
 crypto/asymmetric_keys/asymmetric_type.c |  6 +++---
 crypto/asymmetric_keys/pkcs7_key_type.c  |  1 -
 fs/cifs/cifs_spnego.c                    |  1 -
 fs/cifs/cifsacl.c                        |  1 -
 fs/nfs/idmap.c                           |  2 --
 include/keys/user-type.h                 |  3 ---
 include/linux/key-type.h                 |  4 ----
 net/ceph/crypto.c                        |  1 -
 net/dns_resolver/dns_key.c               | 17 +++++++++++++----
 net/rxrpc/ar-key.c                       |  2 --
 security/keys/big_key.c                  |  1 -
 security/keys/encrypted-keys/encrypted.c |  1 -
 security/keys/internal.h                 |  2 ++
 security/keys/key.c                      |  2 +-
 security/keys/keyring.c                  | 15 ++++++++++-----
 security/keys/request_key.c              |  2 +-
 security/keys/request_key_auth.c         |  2 +-
 security/keys/trusted.c                  |  1 -
 security/keys/user_defined.c             | 12 ------------
 19 files changed, 31 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index 9d78ad7754d9..7c0498968975 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -59,8 +59,8 @@ EXPORT_SYMBOL_GPL(asymmetric_keyid_match);
  *	"id:<id>"	- request a key matching the ID
  *	"<subtype>:<id>" - request a key of a subtype
  */
-static int asymmetric_key_match(const struct key *key,
-				const struct key_match_data *match_data)
+static int asymmetric_key_cmp(const struct key *key,
+			      const struct key_match_data *match_data)
 {
 	const struct asymmetric_key_subtype *subtype = asymmetric_key_subtype(key);
 	const char *description = match_data->raw_data;
@@ -110,6 +110,7 @@ static int asymmetric_key_match(const struct key *key,
 static int asymmetric_key_match_preparse(struct key_match_data *match_data)
 {
 	match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE;
+	match_data->cmp = asymmetric_key_cmp;
 	return 0;
 }
 
@@ -224,7 +225,6 @@ struct key_type key_type_asymmetric = {
 	.free_preparse	= asymmetric_key_free_preparse,
 	.instantiate	= generic_key_instantiate,
 	.match_preparse	= asymmetric_key_match_preparse,
-	.match		= asymmetric_key_match,
 	.match_free	= asymmetric_key_match_free,
 	.destroy	= asymmetric_key_destroy,
 	.describe	= asymmetric_key_describe,
diff --git a/crypto/asymmetric_keys/pkcs7_key_type.c b/crypto/asymmetric_keys/pkcs7_key_type.c
index d1faa1df1dec..751f8fd7335d 100644
--- a/crypto/asymmetric_keys/pkcs7_key_type.c
+++ b/crypto/asymmetric_keys/pkcs7_key_type.c
@@ -75,7 +75,6 @@ static struct key_type key_type_pkcs7 = {
 	.preparse		= pkcs7_preparse,
 	.free_preparse		= user_free_preparse,
 	.instantiate		= generic_key_instantiate,
-	.match			= user_match,
 	.revoke			= user_revoke,
 	.destroy		= user_destroy,
 	.describe		= user_describe,
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index a3e932547617..f4cf200b3c76 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -62,7 +62,6 @@ cifs_spnego_key_destroy(struct key *key)
 struct key_type cifs_spnego_key_type = {
 	.name		= "cifs.spnego",
 	.instantiate	= cifs_spnego_key_instantiate,
-	.match		= user_match,
 	.destroy	= cifs_spnego_key_destroy,
 	.describe	= user_describe,
 };
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 7ff866dbb89e..6d00c419cbae 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -84,7 +84,6 @@ static struct key_type cifs_idmap_key_type = {
 	.instantiate = cifs_idmap_key_instantiate,
 	.destroy     = cifs_idmap_key_destroy,
 	.describe    = user_describe,
-	.match       = user_match,
 };
 
 static char *
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 7dd55b745c4d..2f5db844c172 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -177,7 +177,6 @@ static struct key_type key_type_id_resolver = {
 	.preparse	= user_preparse,
 	.free_preparse	= user_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.revoke		= user_revoke,
 	.destroy	= user_destroy,
 	.describe	= user_describe,
@@ -401,7 +400,6 @@ static struct key_type key_type_id_resolver_legacy = {
 	.preparse	= user_preparse,
 	.free_preparse	= user_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.revoke		= user_revoke,
 	.destroy	= user_destroy,
 	.describe	= user_describe,
diff --git a/include/keys/user-type.h b/include/keys/user-type.h
index 66d92af30e7c..cebefb069c44 100644
--- a/include/keys/user-type.h
+++ b/include/keys/user-type.h
@@ -36,13 +36,10 @@ extern struct key_type key_type_user;
 extern struct key_type key_type_logon;
 
 struct key_preparsed_payload;
-struct key_match_data;
 
 extern int user_preparse(struct key_preparsed_payload *prep);
 extern void user_free_preparse(struct key_preparsed_payload *prep);
 extern int user_update(struct key *key, struct key_preparsed_payload *prep);
-extern int user_match(const struct key *key,
-		      const struct key_match_data *match_data);
 extern void user_revoke(struct key *key);
 extern void user_destroy(struct key *key);
 extern void user_describe(const struct key *user, struct seq_file *m);
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index bf93ea609273..c14816bd3b44 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -113,10 +113,6 @@ struct key_type {
 	 */
 	int (*match_preparse)(struct key_match_data *match_data);
 
-	/* match a key against a description */
-	int (*match)(const struct key *key,
-		     const struct key_match_data *match_data);
-
 	/* Free preparsed match data (optional).  This should be supplied it
 	 * ->match_preparse() is supplied. */
 	void (*match_free)(struct key_match_data *match_data);
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index ffeba8f9dda9..62fc5e7a9acf 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -476,7 +476,6 @@ struct key_type key_type_ceph = {
 	.preparse	= ceph_key_preparse,
 	.free_preparse	= ceph_key_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.destroy	= ceph_key_destroy,
 };
 
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 92df6e508ae7..a07b9ba7e0b7 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -176,9 +176,8 @@ static void dns_resolver_free_preparse(struct key_preparsed_payload *prep)
  * The domain name may be a simple name or an absolute domain name (which
  * should end with a period).  The domain name is case-independent.
  */
-static int
-dns_resolver_match(const struct key *key,
-		   const struct key_match_data *match_data)
+static int dns_resolver_cmp(const struct key *key,
+			    const struct key_match_data *match_data)
 {
 	int slen, dlen, ret = 0;
 	const char *src = key->description, *dsp = match_data->raw_data;
@@ -209,6 +208,16 @@ no_match:
 	return ret;
 }
 
+/*
+ * Preparse the match criterion.
+ */
+static int dns_resolver_match_preparse(struct key_match_data *match_data)
+{
+	match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE;
+	match_data->cmp = dns_resolver_cmp;
+	return 0;
+}
+
 /*
  * Describe a DNS key
  */
@@ -243,7 +252,7 @@ struct key_type key_type_dns_resolver = {
 	.preparse	= dns_resolver_preparse,
 	.free_preparse	= dns_resolver_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= dns_resolver_match,
+	.match_preparse	= dns_resolver_match_preparse,
 	.revoke		= user_revoke,
 	.destroy	= user_destroy,
 	.describe	= dns_resolver_describe,
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index 3907add75932..10c6cb694b43 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -44,7 +44,6 @@ struct key_type key_type_rxrpc = {
 	.preparse	= rxrpc_preparse,
 	.free_preparse	= rxrpc_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.destroy	= rxrpc_destroy,
 	.describe	= rxrpc_describe,
 	.read		= rxrpc_read,
@@ -61,7 +60,6 @@ struct key_type key_type_rxrpc_s = {
 	.preparse	= rxrpc_preparse_s,
 	.free_preparse	= rxrpc_free_preparse_s,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.destroy	= rxrpc_destroy_s,
 	.describe	= rxrpc_describe,
 };
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 4045c13a761a..b6adb94f6d52 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -36,7 +36,6 @@ struct key_type key_type_big_key = {
 	.preparse		= big_key_preparse,
 	.free_preparse		= big_key_free_preparse,
 	.instantiate		= generic_key_instantiate,
-	.match			= user_match,
 	.revoke			= big_key_revoke,
 	.destroy		= big_key_destroy,
 	.describe		= big_key_describe,
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 5fe443d120af..db9675db1026 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -970,7 +970,6 @@ struct key_type key_type_encrypted = {
 	.name = "encrypted",
 	.instantiate = encrypted_instantiate,
 	.update = encrypted_update,
-	.match = user_match,
 	.destroy = encrypted_destroy,
 	.describe = user_describe,
 	.read = encrypted_read,
diff --git a/security/keys/internal.h b/security/keys/internal.h
index b47cc532be1e..e66a16cb63e1 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -127,6 +127,8 @@ struct keyring_search_context {
 	struct timespec		now;
 };
 
+extern int key_default_cmp(const struct key *key,
+			   const struct key_match_data *match_data);
 extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 				    struct keyring_search_context *ctx);
 
diff --git a/security/keys/key.c b/security/keys/key.c
index b90a68c4e2c4..8c0092ca0443 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -799,7 +799,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	}
 
 	key_ref = ERR_PTR(-EINVAL);
-	if (!index_key.type->match || !index_key.type->instantiate ||
+	if (!index_key.type->instantiate ||
 	    (!index_key.description && !index_key.type->preparse))
 		goto error_put_type;
 
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 10f0a5f2d362..253c9a0eb092 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -89,7 +89,6 @@ struct key_type key_type_keyring = {
 	.preparse	= keyring_preparse,
 	.free_preparse	= keyring_free_preparse,
 	.instantiate	= keyring_instantiate,
-	.match		= user_match,
 	.revoke		= keyring_revoke,
 	.destroy	= keyring_destroy,
 	.describe	= keyring_describe,
@@ -511,6 +510,15 @@ struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid,
 }
 EXPORT_SYMBOL(keyring_alloc);
 
+/*
+ * By default, we keys found by getting an exact match on their descriptions.
+ */
+int key_default_cmp(const struct key *key,
+		    const struct key_match_data *match_data)
+{
+	return strcmp(key->description, match_data->raw_data) == 0;
+}
+
 /*
  * Iteration function to consider each key found.
  */
@@ -884,7 +892,7 @@ key_ref_t keyring_search(key_ref_t keyring,
 		.index_key.type		= type,
 		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match_data.cmp		= type->match,
+		.match_data.cmp		= key_default_cmp,
 		.match_data.raw_data	= description,
 		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 		.flags			= KEYRING_SEARCH_DO_STATE_CHECK,
@@ -892,9 +900,6 @@ key_ref_t keyring_search(key_ref_t keyring,
 	key_ref_t key;
 	int ret;
 
-	if (!ctx.match_data.cmp)
-		return ERR_PTR(-ENOKEY);
-
 	if (type->match_preparse) {
 		ret = type->match_preparse(&ctx.match_data);
 		if (ret < 0)
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 408523e5e2e2..dc6ed32b7844 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -531,7 +531,7 @@ struct key *request_key_and_link(struct key_type *type,
 		.index_key.type		= type,
 		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match_data.cmp		= type->match,
+		.match_data.cmp		= key_default_cmp,
 		.match_data.raw_data	= description,
 		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	};
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 9ae02819cc06..6639e2cb8853 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -246,7 +246,7 @@ struct key *key_get_instantiation_authkey(key_serial_t target_id)
 		.index_key.type		= &key_type_request_key_auth,
 		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match_data.cmp		= user_match,
+		.match_data.cmp		= key_default_cmp,
 		.match_data.raw_data	= description,
 		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	};
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index 6b804aa4529a..c0594cb07ada 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1096,7 +1096,6 @@ struct key_type key_type_trusted = {
 	.name = "trusted",
 	.instantiate = trusted_instantiate,
 	.update = trusted_update,
-	.match = user_match,
 	.destroy = trusted_destroy,
 	.describe = user_describe,
 	.read = trusted_read,
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index cd7e726e8646..36b47bbd3d8c 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -30,7 +30,6 @@ struct key_type key_type_user = {
 	.free_preparse		= user_free_preparse,
 	.instantiate		= generic_key_instantiate,
 	.update			= user_update,
-	.match			= user_match,
 	.revoke			= user_revoke,
 	.destroy		= user_destroy,
 	.describe		= user_describe,
@@ -51,7 +50,6 @@ struct key_type key_type_logon = {
 	.free_preparse		= user_free_preparse,
 	.instantiate		= generic_key_instantiate,
 	.update			= user_update,
-	.match			= user_match,
 	.revoke			= user_revoke,
 	.destroy		= user_destroy,
 	.describe		= user_describe,
@@ -136,16 +134,6 @@ error:
 
 EXPORT_SYMBOL_GPL(user_update);
 
-/*
- * match users on their name
- */
-int user_match(const struct key *key, const struct key_match_data *match_data)
-{
-	return strcmp(key->description, match_data->raw_data) == 0;
-}
-
-EXPORT_SYMBOL_GPL(user_match);
-
 /*
  * dispose of the links from a revoked keyring
  * - called with the key sem write-locked
-- 
cgit v1.2.3


From 0c903ab64feb0fe83eac9f67a06e2f5b9508de16 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 16 Sep 2014 17:36:08 +0100
Subject: KEYS: Make the key matching functions return bool

Make the key matching functions pointed to by key_match_data::cmp return bool
rather than int.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
---
 crypto/asymmetric_keys/asymmetric_type.c |  4 ++--
 include/linux/key-type.h                 | 10 ++++++----
 net/dns_resolver/dns_key.c               |  4 ++--
 security/keys/internal.h                 |  8 ++++----
 security/keys/keyring.c                  |  4 ++--
 security/keys/process_keys.c             |  4 ++--
 6 files changed, 18 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index 7c0498968975..7755f918e8d9 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -59,8 +59,8 @@ EXPORT_SYMBOL_GPL(asymmetric_keyid_match);
  *	"id:<id>"	- request a key matching the ID
  *	"<subtype>:<id>" - request a key of a subtype
  */
-static int asymmetric_key_cmp(const struct key *key,
-			      const struct key_match_data *match_data)
+static bool asymmetric_key_cmp(const struct key *key,
+			       const struct key_match_data *match_data)
 {
 	const struct asymmetric_key_subtype *subtype = asymmetric_key_subtype(key);
 	const char *description = match_data->raw_data;
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index c14816bd3b44..ff9f1d394235 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -56,10 +56,12 @@ typedef int (*request_key_actor_t)(struct key_construction *key,
  * Preparsed matching criterion.
  */
 struct key_match_data {
-	/* Comparison function, defaults to type->match, but can be replaced by
-	 * type->match_preparse(). */
-	int (*cmp)(const struct key *key,
-		   const struct key_match_data *match_data);
+	/* Comparison function, defaults to exact description match, but can be
+	 * overridden by type->match_preparse().  Should return true if a match
+	 * is found and false if not.
+	 */
+	bool (*cmp)(const struct key *key,
+		    const struct key_match_data *match_data);
 
 	const void	*raw_data;	/* Raw match data */
 	void		*preparsed;	/* For ->match_preparse() to stash stuff */
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index a07b9ba7e0b7..31cd4fd75486 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -176,8 +176,8 @@ static void dns_resolver_free_preparse(struct key_preparsed_payload *prep)
  * The domain name may be a simple name or an absolute domain name (which
  * should end with a period).  The domain name is case-independent.
  */
-static int dns_resolver_cmp(const struct key *key,
-			    const struct key_match_data *match_data)
+static bool dns_resolver_cmp(const struct key *key,
+			     const struct key_match_data *match_data)
 {
 	int slen, dlen, ret = 0;
 	const char *src = key->description, *dsp = match_data->raw_data;
diff --git a/security/keys/internal.h b/security/keys/internal.h
index e66a16cb63e1..b8960c4959a5 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -127,8 +127,8 @@ struct keyring_search_context {
 	struct timespec		now;
 };
 
-extern int key_default_cmp(const struct key *key,
-			   const struct key_match_data *match_data);
+extern bool key_default_cmp(const struct key *key,
+			    const struct key_match_data *match_data);
 extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 				    struct keyring_search_context *ctx);
 
@@ -150,8 +150,8 @@ extern struct key *request_key_and_link(struct key_type *type,
 					struct key *dest_keyring,
 					unsigned long flags);
 
-extern int lookup_user_key_possessed(const struct key *key,
-				     const struct key_match_data *match_data);
+extern bool lookup_user_key_possessed(const struct key *key,
+				      const struct key_match_data *match_data);
 extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags,
 				 key_perm_t perm);
 #define KEY_LOOKUP_CREATE	0x01
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 253c9a0eb092..8177010174f7 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -513,8 +513,8 @@ EXPORT_SYMBOL(keyring_alloc);
 /*
  * By default, we keys found by getting an exact match on their descriptions.
  */
-int key_default_cmp(const struct key *key,
-		    const struct key_match_data *match_data)
+bool key_default_cmp(const struct key *key,
+		     const struct key_match_data *match_data)
 {
 	return strcmp(key->description, match_data->raw_data) == 0;
 }
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 08bd533d014f..bd536cb221e2 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -489,8 +489,8 @@ found:
 /*
  * See if the key we're looking at is the target key.
  */
-int lookup_user_key_possessed(const struct key *key,
-			      const struct key_match_data *match_data)
+bool lookup_user_key_possessed(const struct key *key,
+			       const struct key_match_data *match_data)
 {
 	return key == match_data->raw_data;
 }
-- 
cgit v1.2.3


From 7901c1a8effbe5f89673bfc09d6e37b8f334f1a7 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 16 Sep 2014 17:36:11 +0100
Subject: KEYS: Implement binary asymmetric key ID handling

Implement the first step in using binary key IDs for asymmetric keys rather
than hex string keys.

The previously added match data preparsing will be able to convert hex
criterion strings into binary which can then be compared more rapidly.

Further, we actually want more then one ID string per public key.  The problem
is that X.509 certs refer to other X.509 certs by matching Issuer + AuthKeyId
to Subject + SubjKeyId, but PKCS#7 messages match against X.509 Issuer +
SerialNumber.

This patch just provides facilities for a later patch to make use of.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
---
 crypto/asymmetric_keys/asymmetric_keys.h |  4 ++
 crypto/asymmetric_keys/asymmetric_type.c | 89 ++++++++++++++++++++++++++++++++
 include/keys/asymmetric-type.h           | 38 ++++++++++++++
 3 files changed, 131 insertions(+)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/asymmetric_keys.h b/crypto/asymmetric_keys/asymmetric_keys.h
index a63c551c6557..917be6b985e7 100644
--- a/crypto/asymmetric_keys/asymmetric_keys.h
+++ b/crypto/asymmetric_keys/asymmetric_keys.h
@@ -10,6 +10,10 @@
  */
 
 int asymmetric_keyid_match(const char *kid, const char *id);
+extern bool asymmetric_match_key_ids(const struct asymmetric_key_ids *kids,
+				     const struct asymmetric_key_id *match_id);
+
+extern struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id);
 
 static inline const char *asymmetric_key_id(const struct key *key)
 {
diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index 7755f918e8d9..92bfc438dd1d 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/ctype.h>
 #include "asymmetric_keys.h"
 
 MODULE_LICENSE("GPL");
@@ -22,6 +23,94 @@ MODULE_LICENSE("GPL");
 static LIST_HEAD(asymmetric_key_parsers);
 static DECLARE_RWSEM(asymmetric_key_parsers_sem);
 
+/**
+ * asymmetric_key_generate_id: Construct an asymmetric key ID
+ * @val_1: First binary blob
+ * @len_1: Length of first binary blob
+ * @val_2: Second binary blob
+ * @len_2: Length of second binary blob
+ *
+ * Construct an asymmetric key ID from a pair of binary blobs.
+ */
+struct asymmetric_key_id *asymmetric_key_generate_id(const void *val_1,
+						     size_t len_1,
+						     const void *val_2,
+						     size_t len_2)
+{
+	struct asymmetric_key_id *kid;
+
+	kid = kmalloc(sizeof(struct asymmetric_key_id) + len_1 + len_2,
+		      GFP_KERNEL);
+	if (!kid)
+		return ERR_PTR(-ENOMEM);
+	kid->len = len_1 + len_2;
+	memcpy(kid->data, val_1, len_1);
+	memcpy(kid->data + len_1, val_2, len_2);
+	return kid;
+}
+EXPORT_SYMBOL_GPL(asymmetric_key_generate_id);
+
+/**
+ * asymmetric_key_id_same - Return true if two asymmetric keys IDs are the same.
+ * @kid_1, @kid_2: The key IDs to compare
+ */
+bool asymmetric_key_id_same(const struct asymmetric_key_id *kid1,
+			    const struct asymmetric_key_id *kid2)
+{
+	if (!kid1 || !kid2)
+		return false;
+	if (kid1->len != kid2->len)
+		return false;
+	return memcmp(kid1->data, kid2->data, kid1->len) == 0;
+}
+EXPORT_SYMBOL_GPL(asymmetric_key_id_same);
+
+/**
+ * asymmetric_match_key_ids - Search asymmetric key IDs
+ * @kids: The list of key IDs to check
+ * @match_id: The key ID we're looking for
+ */
+bool asymmetric_match_key_ids(const struct asymmetric_key_ids *kids,
+			      const struct asymmetric_key_id *match_id)
+{
+	if (!kids || !match_id)
+		return false;
+	if (asymmetric_key_id_same(kids->id[0], match_id))
+		return true;
+	if (asymmetric_key_id_same(kids->id[1], match_id))
+		return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(asymmetric_match_key_ids);
+
+/**
+ * asymmetric_key_hex_to_key_id - Convert a hex string into a key ID.
+ * @id: The ID as a hex string.
+ */
+struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id)
+{
+	struct asymmetric_key_id *match_id;
+	const char *p;
+	ptrdiff_t hexlen;
+
+	if (!*id)
+		return ERR_PTR(-EINVAL);
+	for (p = id; *p; p++)
+		if (!isxdigit(*p))
+			return ERR_PTR(-EINVAL);
+	hexlen = p - id;
+	if (hexlen & 1)
+		return ERR_PTR(-EINVAL);
+
+	match_id = kmalloc(sizeof(struct asymmetric_key_id) + hexlen / 2,
+			   GFP_KERNEL);
+	if (!match_id)
+		return ERR_PTR(-ENOMEM);
+	match_id->len = hexlen / 2;
+	(void)hex2bin(match_id->data, id, hexlen / 2);
+	return match_id;
+}
+
 /*
  * Match asymmetric key id with partial match
  * @id:		key id to match in a form "id:<id>"
diff --git a/include/keys/asymmetric-type.h b/include/keys/asymmetric-type.h
index 7dd473496180..044ab0d3aa45 100644
--- a/include/keys/asymmetric-type.h
+++ b/include/keys/asymmetric-type.h
@@ -18,6 +18,44 @@
 
 extern struct key_type key_type_asymmetric;
 
+/*
+ * Identifiers for an asymmetric key ID.  We have three ways of looking up a
+ * key derived from an X.509 certificate:
+ *
+ * (1) Serial Number & Issuer.  Non-optional.  This is the only valid way to
+ *     map a PKCS#7 signature to an X.509 certificate.
+ *
+ * (2) Issuer & Subject Unique IDs.  Optional.  These were the original way to
+ *     match X.509 certificates, but have fallen into disuse in favour of (3).
+ *
+ * (3) Auth & Subject Key Identifiers.  Optional.  SKIDs are only provided on
+ *     CA keys that are intended to sign other keys, so don't appear in end
+ *     user certificates unless forced.
+ *
+ * We could also support an PGP key identifier, which is just a SHA1 sum of the
+ * public key and certain parameters, but since we don't support PGP keys at
+ * the moment, we shall ignore those.
+ *
+ * What we actually do is provide a place where binary identifiers can be
+ * stashed and then compare against them when checking for an id match.
+ */
+struct asymmetric_key_id {
+	unsigned short	len;
+	unsigned char	data[];
+};
+
+struct asymmetric_key_ids {
+	void		*id[2];
+};
+
+extern bool asymmetric_key_id_same(const struct asymmetric_key_id *kid1,
+				   const struct asymmetric_key_id *kid2);
+
+extern struct asymmetric_key_id *asymmetric_key_generate_id(const void *val_1,
+							    size_t len_1,
+							    const void *val_2,
+							    size_t len_2);
+
 /*
  * The payload is at the discretion of the subtype.
  */
-- 
cgit v1.2.3


From 46963b774d441c833afc1535f6d84b3df2a94204 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 16 Sep 2014 17:36:13 +0100
Subject: KEYS: Overhaul key identification when searching for asymmetric keys

Make use of the new match string preparsing to overhaul key identification
when searching for asymmetric keys.  The following changes are made:

 (1) Use the previously created asymmetric_key_id struct to hold the following
     key IDs derived from the X.509 certificate or PKCS#7 message:

	id: serial number + issuer
	skid: subjKeyId + subject
	authority: authKeyId + issuer

 (2) Replace the hex fingerprint attached to key->type_data[1] with an
     asymmetric_key_ids struct containing the id and the skid (if present).

 (3) Make the asymmetric_type match data preparse select one of two searches:

     (a) An iterative search for the key ID given if prefixed with "id:".  The
     	 prefix is expected to be followed by a hex string giving the ID to
     	 search for.  The criterion key ID is checked against all key IDs
     	 recorded on the key.

     (b) A direct search if the key ID is not prefixed with "id:".  This will
     	 look for an exact match on the key description.

 (4) Make x509_request_asymmetric_key() take a key ID.  This is then converted
     into "id:<hex>" and passed into keyring_search() where match preparsing
     will turn it back into a binary ID.

 (5) X.509 certificate verification then takes the authority key ID and looks
     up a key that matches it to find the public key for the certificate
     signature.

 (6) PKCS#7 certificate verification then takes the id key ID and looks up a
     key that matches it to find the public key for the signed information
     block signature.

Additional changes:

 (1) Multiple subjKeyId and authKeyId values on an X.509 certificate cause the
     cert to be rejected with -EBADMSG.

 (2) The 'fingerprint' ID is gone.  This was primarily intended to convey PGP
     public key fingerprints.  If PGP is supported in future, this should
     generate a key ID that carries the fingerprint.

 (3) Th ca_keyid= kernel command line option is now converted to a key ID and
     used to match the authority key ID.  Possibly this should only match the
     actual authKeyId part and not the issuer as well.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
---
 crypto/asymmetric_keys/asymmetric_keys.h  |   4 +-
 crypto/asymmetric_keys/asymmetric_type.c  | 133 +++++++++++++-----------------
 crypto/asymmetric_keys/pkcs7_parser.c     |  38 ++++++---
 crypto/asymmetric_keys/pkcs7_parser.h     |   5 +-
 crypto/asymmetric_keys/pkcs7_trust.c      |   6 +-
 crypto/asymmetric_keys/pkcs7_verify.c     |  44 +++++-----
 crypto/asymmetric_keys/x509_cert_parser.c |  55 +++++++-----
 crypto/asymmetric_keys/x509_parser.h      |   5 +-
 crypto/asymmetric_keys/x509_public_key.c  |  89 +++++++++++---------
 include/crypto/public_key.h               |   5 +-
 10 files changed, 198 insertions(+), 186 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/asymmetric_keys.h b/crypto/asymmetric_keys/asymmetric_keys.h
index 917be6b985e7..fd21ac28e0a0 100644
--- a/crypto/asymmetric_keys/asymmetric_keys.h
+++ b/crypto/asymmetric_keys/asymmetric_keys.h
@@ -9,13 +9,13 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
-int asymmetric_keyid_match(const char *kid, const char *id);
 extern bool asymmetric_match_key_ids(const struct asymmetric_key_ids *kids,
 				     const struct asymmetric_key_id *match_id);
 
 extern struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id);
 
-static inline const char *asymmetric_key_id(const struct key *key)
+static inline
+const struct asymmetric_key_ids *asymmetric_key_ids(const struct key *key)
 {
 	return key->type_data.p[1];
 }
diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index 92bfc438dd1d..718e779a010e 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -112,76 +112,15 @@ struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id)
 }
 
 /*
- * Match asymmetric key id with partial match
- * @id:		key id to match in a form "id:<id>"
- */
-int asymmetric_keyid_match(const char *kid, const char *id)
-{
-	size_t idlen, kidlen;
-
-	if (!kid || !id)
-		return 0;
-
-	/* make it possible to use id as in the request: "id:<id>" */
-	if (strncmp(id, "id:", 3) == 0)
-		id += 3;
-
-	/* Anything after here requires a partial match on the ID string */
-	idlen = strlen(id);
-	kidlen = strlen(kid);
-	if (idlen > kidlen)
-		return 0;
-
-	kid += kidlen - idlen;
-	if (strcasecmp(id, kid) != 0)
-		return 0;
-
-	return 1;
-}
-EXPORT_SYMBOL_GPL(asymmetric_keyid_match);
-
-/*
- * Match asymmetric keys on (part of) their name
- * We have some shorthand methods for matching keys.  We allow:
- *
- *	"<desc>"	- request a key by description
- *	"id:<id>"	- request a key matching the ID
- *	"<subtype>:<id>" - request a key of a subtype
+ * Match asymmetric keys by ID.
  */
 static bool asymmetric_key_cmp(const struct key *key,
 			       const struct key_match_data *match_data)
 {
-	const struct asymmetric_key_subtype *subtype = asymmetric_key_subtype(key);
-	const char *description = match_data->raw_data;
-	const char *spec = description;
-	const char *id;
-	ptrdiff_t speclen;
-
-	if (!subtype || !spec || !*spec)
-		return 0;
-
-	/* See if the full key description matches as is */
-	if (key->description && strcmp(key->description, description) == 0)
-		return 1;
-
-	/* All tests from here on break the criterion description into a
-	 * specifier, a colon and then an identifier.
-	 */
-	id = strchr(spec, ':');
-	if (!id)
-		return 0;
-
-	speclen = id - spec;
-	id++;
-
-	if (speclen == 2 && memcmp(spec, "id", 2) == 0)
-		return asymmetric_keyid_match(asymmetric_key_id(key), id);
+	const struct asymmetric_key_ids *kids = asymmetric_key_ids(key);
+	const struct asymmetric_key_id *match_id = match_data->preparsed;
 
-	if (speclen == subtype->name_len &&
-	    memcmp(spec, subtype->name, speclen) == 0)
-		return 1;
-
-	return 0;
+	return asymmetric_match_key_ids(kids, match_id);
 }
 
 /*
@@ -198,8 +137,30 @@ static bool asymmetric_key_cmp(const struct key *key,
  */
 static int asymmetric_key_match_preparse(struct key_match_data *match_data)
 {
-	match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE;
+	struct asymmetric_key_id *match_id;
+	const char *spec = match_data->raw_data;
+	const char *id;
+
+	if (!spec || !*spec)
+		return -EINVAL;
+	if (spec[0] == 'i' &&
+	    spec[1] == 'd' &&
+	    spec[2] == ':') {
+		id = spec + 3;
+	} else {
+		goto default_match;
+	}
+
+	match_id = asymmetric_key_hex_to_key_id(id);
+	if (!match_id)
+		return -ENOMEM;
+
+	match_data->preparsed = match_id;
 	match_data->cmp = asymmetric_key_cmp;
+	match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE;
+	return 0;
+
+default_match:
 	return 0;
 }
 
@@ -208,6 +169,7 @@ static int asymmetric_key_match_preparse(struct key_match_data *match_data)
  */
 static void asymmetric_key_match_free(struct key_match_data *match_data)
 {
+	kfree(match_data->preparsed);
 }
 
 /*
@@ -216,8 +178,10 @@ static void asymmetric_key_match_free(struct key_match_data *match_data)
 static void asymmetric_key_describe(const struct key *key, struct seq_file *m)
 {
 	const struct asymmetric_key_subtype *subtype = asymmetric_key_subtype(key);
-	const char *kid = asymmetric_key_id(key);
-	size_t n;
+	const struct asymmetric_key_ids *kids = asymmetric_key_ids(key);
+	const struct asymmetric_key_id *kid;
+	const unsigned char *p;
+	int n;
 
 	seq_puts(m, key->description);
 
@@ -225,13 +189,16 @@ static void asymmetric_key_describe(const struct key *key, struct seq_file *m)
 		seq_puts(m, ": ");
 		subtype->describe(key, m);
 
-		if (kid) {
+		if (kids && kids->id[0]) {
+			kid = kids->id[0];
 			seq_putc(m, ' ');
-			n = strlen(kid);
-			if (n <= 8)
-				seq_puts(m, kid);
-			else
-				seq_puts(m, kid + n - 8);
+			n = kid->len;
+			p = kid->data;
+			if (n > 8) {
+				p += n - 8;
+				n = 8;
+			}
+			seq_printf(m, "%*phN", n, p);
 		}
 
 		seq_puts(m, " [");
@@ -282,6 +249,7 @@ static int asymmetric_key_preparse(struct key_preparsed_payload *prep)
 static void asymmetric_key_free_preparse(struct key_preparsed_payload *prep)
 {
 	struct asymmetric_key_subtype *subtype = prep->type_data[0];
+	struct asymmetric_key_ids *kids = prep->type_data[1];
 
 	pr_devel("==>%s()\n", __func__);
 
@@ -289,7 +257,11 @@ static void asymmetric_key_free_preparse(struct key_preparsed_payload *prep)
 		subtype->destroy(prep->payload[0]);
 		module_put(subtype->owner);
 	}
-	kfree(prep->type_data[1]);
+	if (kids) {
+		kfree(kids->id[0]);
+		kfree(kids->id[1]);
+		kfree(kids);
+	}
 	kfree(prep->description);
 }
 
@@ -299,13 +271,20 @@ static void asymmetric_key_free_preparse(struct key_preparsed_payload *prep)
 static void asymmetric_key_destroy(struct key *key)
 {
 	struct asymmetric_key_subtype *subtype = asymmetric_key_subtype(key);
+	struct asymmetric_key_ids *kids = key->type_data.p[1];
+
 	if (subtype) {
 		subtype->destroy(key->payload.data);
 		module_put(subtype->owner);
 		key->type_data.p[0] = NULL;
 	}
-	kfree(key->type_data.p[1]);
-	key->type_data.p[1] = NULL;
+
+	if (kids) {
+		kfree(kids->id[0]);
+		kfree(kids->id[1]);
+		kfree(kids);
+		key->type_data.p[1] = NULL;
+	}
 }
 
 struct key_type key_type_asymmetric = {
diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c
index 1e9861da7ee4..3bd5a1e4c493 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.c
+++ b/crypto/asymmetric_keys/pkcs7_parser.c
@@ -29,6 +29,10 @@ struct pkcs7_parse_context {
 	enum OID	last_oid;		/* Last OID encountered */
 	unsigned	x509_index;
 	unsigned	sinfo_index;
+	const void	*raw_serial;
+	unsigned	raw_serial_size;
+	unsigned	raw_issuer_size;
+	const void	*raw_issuer;
 };
 
 /*
@@ -39,6 +43,7 @@ static void pkcs7_free_signed_info(struct pkcs7_signed_info *sinfo)
 	if (sinfo) {
 		mpi_free(sinfo->sig.mpi[0]);
 		kfree(sinfo->sig.digest);
+		kfree(sinfo->signing_cert_id);
 		kfree(sinfo);
 	}
 }
@@ -251,10 +256,10 @@ int pkcs7_extract_cert(void *context, size_t hdrlen,
 	if (IS_ERR(x509))
 		return PTR_ERR(x509);
 
-	pr_debug("Got cert for %s\n", x509->subject);
-	pr_debug("- fingerprint %s\n", x509->fingerprint);
-
 	x509->index = ++ctx->x509_index;
+	pr_debug("Got cert %u for %s\n", x509->index, x509->subject);
+	pr_debug("- fingerprint %*phN\n", x509->id->len, x509->id->data);
+
 	*ctx->ppcerts = x509;
 	ctx->ppcerts = &x509->next;
 	return 0;
@@ -343,8 +348,8 @@ int pkcs7_sig_note_serial(void *context, size_t hdrlen,
 			  const void *value, size_t vlen)
 {
 	struct pkcs7_parse_context *ctx = context;
-	ctx->sinfo->raw_serial = value;
-	ctx->sinfo->raw_serial_size = vlen;
+	ctx->raw_serial = value;
+	ctx->raw_serial_size = vlen;
 	return 0;
 }
 
@@ -356,8 +361,8 @@ int pkcs7_sig_note_issuer(void *context, size_t hdrlen,
 			  const void *value, size_t vlen)
 {
 	struct pkcs7_parse_context *ctx = context;
-	ctx->sinfo->raw_issuer = value;
-	ctx->sinfo->raw_issuer_size = vlen;
+	ctx->raw_issuer = value;
+	ctx->raw_issuer_size = vlen;
 	return 0;
 }
 
@@ -390,10 +395,21 @@ int pkcs7_note_signed_info(void *context, size_t hdrlen,
 			   const void *value, size_t vlen)
 {
 	struct pkcs7_parse_context *ctx = context;
-
-	ctx->sinfo->index = ++ctx->sinfo_index;
-	*ctx->ppsinfo = ctx->sinfo;
-	ctx->ppsinfo = &ctx->sinfo->next;
+	struct pkcs7_signed_info *sinfo = ctx->sinfo;
+	struct asymmetric_key_id *kid;
+
+	/* Generate cert issuer + serial number key ID */
+	kid = asymmetric_key_generate_id(ctx->raw_serial,
+					 ctx->raw_serial_size,
+					 ctx->raw_issuer,
+					 ctx->raw_issuer_size);
+	if (IS_ERR(kid))
+		return PTR_ERR(kid);
+
+	sinfo->signing_cert_id = kid;
+	sinfo->index = ++ctx->sinfo_index;
+	*ctx->ppsinfo = sinfo;
+	ctx->ppsinfo = &sinfo->next;
 	ctx->sinfo = kzalloc(sizeof(struct pkcs7_signed_info), GFP_KERNEL);
 	if (!ctx->sinfo)
 		return -ENOMEM;
diff --git a/crypto/asymmetric_keys/pkcs7_parser.h b/crypto/asymmetric_keys/pkcs7_parser.h
index d25f4d15370f..91949f92bc72 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.h
+++ b/crypto/asymmetric_keys/pkcs7_parser.h
@@ -33,10 +33,7 @@ struct pkcs7_signed_info {
 	const void	*authattrs;
 
 	/* Issuing cert serial number and issuer's name */
-	const void	*raw_serial;
-	unsigned	raw_serial_size;
-	unsigned	raw_issuer_size;
-	const void	*raw_issuer;
+	struct asymmetric_key_id *signing_cert_id;
 
 	/* Message signature.
 	 *
diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c
index fad888ea4fad..09197e50fa82 100644
--- a/crypto/asymmetric_keys/pkcs7_trust.c
+++ b/crypto/asymmetric_keys/pkcs7_trust.c
@@ -49,8 +49,7 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 		/* Look to see if this certificate is present in the trusted
 		 * keys.
 		 */
-		key = x509_request_asymmetric_key(trust_keyring, x509->subject,
-						  x509->fingerprint);
+		key = x509_request_asymmetric_key(trust_keyring, x509->id);
 		if (!IS_ERR(key))
 			/* One of the X.509 certificates in the PKCS#7 message
 			 * is apparently the same as one we already trust.
@@ -82,8 +81,7 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 		return -ENOKEY;
 	}
 
-	key = x509_request_asymmetric_key(trust_keyring, last->issuer,
-					  last->authority);
+	key = x509_request_asymmetric_key(trust_keyring, last->authority);
 	if (IS_ERR(key))
 		return PTR_ERR(key) == -ENOMEM ? -ENOMEM : -ENOKEY;
 	x509 = last;
diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c
index c62cf8006e1f..57e90fa17f2b 100644
--- a/crypto/asymmetric_keys/pkcs7_verify.c
+++ b/crypto/asymmetric_keys/pkcs7_verify.c
@@ -131,8 +131,7 @@ static int pkcs7_find_key(struct pkcs7_message *pkcs7,
 	struct x509_certificate *x509;
 	unsigned certix = 1;
 
-	kenter("%u,%u,%u",
-	       sinfo->index, sinfo->raw_serial_size, sinfo->raw_issuer_size);
+	kenter("%u", sinfo->index);
 
 	for (x509 = pkcs7->certs; x509; x509 = x509->next, certix++) {
 		/* I'm _assuming_ that the generator of the PKCS#7 message will
@@ -140,21 +139,11 @@ static int pkcs7_find_key(struct pkcs7_message *pkcs7,
 		 * PKCS#7 message - but I can't be 100% sure of that.  It's
 		 * possible this will need element-by-element comparison.
 		 */
-		if (x509->raw_serial_size != sinfo->raw_serial_size ||
-		    memcmp(x509->raw_serial, sinfo->raw_serial,
-			   sinfo->raw_serial_size) != 0)
+		if (!asymmetric_key_id_same(x509->id, sinfo->signing_cert_id))
 			continue;
 		pr_devel("Sig %u: Found cert serial match X.509[%u]\n",
 			 sinfo->index, certix);
 
-		if (x509->raw_issuer_size != sinfo->raw_issuer_size ||
-		    memcmp(x509->raw_issuer, sinfo->raw_issuer,
-			   sinfo->raw_issuer_size) != 0) {
-			pr_warn("Sig %u: X.509 subject and PKCS#7 issuer don't match\n",
-				sinfo->index);
-			continue;
-		}
-
 		if (x509->pub->pkey_algo != sinfo->sig.pkey_algo) {
 			pr_warn("Sig %u: X.509 algo and PKCS#7 sig algo don't match\n",
 				sinfo->index);
@@ -164,8 +153,10 @@ static int pkcs7_find_key(struct pkcs7_message *pkcs7,
 		sinfo->signer = x509;
 		return 0;
 	}
+
 	pr_warn("Sig %u: Issuing X.509 cert not found (#%*ph)\n",
-		sinfo->index, sinfo->raw_serial_size, sinfo->raw_serial);
+		sinfo->index,
+		sinfo->signing_cert_id->len, sinfo->signing_cert_id->data);
 	return -ENOKEY;
 }
 
@@ -184,7 +175,9 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 		p->seen = false;
 
 	for (;;) {
-		pr_debug("verify %s: %s\n", x509->subject, x509->fingerprint);
+		pr_debug("verify %s: %*phN\n",
+			 x509->subject,
+			 x509->raw_serial_size, x509->raw_serial);
 		x509->seen = true;
 		ret = x509_get_sig_params(x509);
 		if (ret < 0)
@@ -192,7 +185,8 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 
 		pr_debug("- issuer %s\n", x509->issuer);
 		if (x509->authority)
-			pr_debug("- authkeyid %s\n", x509->authority);
+			pr_debug("- authkeyid %*phN\n",
+				 x509->authority->len, x509->authority->data);
 
 		if (!x509->authority ||
 		    strcmp(x509->subject, x509->issuer) == 0) {
@@ -218,13 +212,14 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 		/* Look through the X.509 certificates in the PKCS#7 message's
 		 * list to see if the next one is there.
 		 */
-		pr_debug("- want %s\n", x509->authority);
+		pr_debug("- want %*phN\n",
+			 x509->authority->len, x509->authority->data);
 		for (p = pkcs7->certs; p; p = p->next) {
-			pr_debug("- cmp [%u] %s\n", p->index, p->fingerprint);
-			if (p->raw_subject_size == x509->raw_issuer_size &&
-			    strcmp(p->fingerprint, x509->authority) == 0 &&
-			    memcmp(p->raw_subject, x509->raw_issuer,
-				   x509->raw_issuer_size) == 0)
+			if (!p->skid)
+				continue;
+			pr_debug("- cmp [%u] %*phN\n",
+				 p->index, p->skid->len, p->skid->data);
+			if (asymmetric_key_id_same(p->skid, x509->authority))
 				goto found_issuer;
 		}
 
@@ -233,7 +228,7 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 		return 0;
 
 	found_issuer:
-		pr_debug("- issuer %s\n", p->subject);
+		pr_debug("- subject %s\n", p->subject);
 		if (p->seen) {
 			pr_warn("Sig %u: X.509 chain contains loop\n",
 				sinfo->index);
@@ -304,7 +299,8 @@ int pkcs7_verify(struct pkcs7_message *pkcs7)
 		ret = x509_get_sig_params(x509);
 		if (ret < 0)
 			return ret;
-		pr_debug("X.509[%u] %s\n", n, x509->authority);
+		pr_debug("X.509[%u] %*phN\n",
+			 n, x509->authority->len, x509->authority->data);
 	}
 
 	for (sinfo = pkcs7->signed_infos; sinfo; sinfo = sinfo->next) {
diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index ac72348c186a..96151b2b91a2 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -46,7 +46,8 @@ void x509_free_certificate(struct x509_certificate *cert)
 		public_key_destroy(cert->pub);
 		kfree(cert->issuer);
 		kfree(cert->subject);
-		kfree(cert->fingerprint);
+		kfree(cert->id);
+		kfree(cert->skid);
 		kfree(cert->authority);
 		kfree(cert->sig.digest);
 		mpi_free(cert->sig.rsa.s);
@@ -62,6 +63,7 @@ struct x509_certificate *x509_cert_parse(const void *data, size_t datalen)
 {
 	struct x509_certificate *cert;
 	struct x509_parse_context *ctx;
+	struct asymmetric_key_id *kid;
 	long ret;
 
 	ret = -ENOMEM;
@@ -89,6 +91,17 @@ struct x509_certificate *x509_cert_parse(const void *data, size_t datalen)
 	if (ret < 0)
 		goto error_decode;
 
+	/* Generate cert issuer + serial number key ID */
+	kid = asymmetric_key_generate_id(cert->raw_serial,
+					 cert->raw_serial_size,
+					 cert->raw_issuer,
+					 cert->raw_issuer_size);
+	if (IS_ERR(kid)) {
+		ret = PTR_ERR(kid);
+		goto error_decode;
+	}
+	cert->id = kid;
+
 	kfree(ctx);
 	return cert;
 
@@ -407,36 +420,34 @@ int x509_process_extension(void *context, size_t hdrlen,
 			   const void *value, size_t vlen)
 {
 	struct x509_parse_context *ctx = context;
+	struct asymmetric_key_id *kid;
 	const unsigned char *v = value;
-	char *f;
 	int i;
 
 	pr_debug("Extension: %u\n", ctx->last_oid);
 
 	if (ctx->last_oid == OID_subjectKeyIdentifier) {
 		/* Get hold of the key fingerprint */
-		if (vlen < 3)
+		if (ctx->cert->skid || vlen < 3)
 			return -EBADMSG;
 		if (v[0] != ASN1_OTS || v[1] != vlen - 2)
 			return -EBADMSG;
 		v += 2;
 		vlen -= 2;
 
-		f = kmalloc(vlen * 2 + 1, GFP_KERNEL);
-		if (!f)
-			return -ENOMEM;
-		for (i = 0; i < vlen; i++)
-			sprintf(f + i * 2, "%02x", v[i]);
-		pr_debug("fingerprint %s\n", f);
-		ctx->cert->fingerprint = f;
+		kid = asymmetric_key_generate_id(v, vlen,
+						 ctx->cert->raw_subject,
+						 ctx->cert->raw_subject_size);
+		if (IS_ERR(kid))
+			return PTR_ERR(kid);
+		ctx->cert->skid = kid;
+		pr_debug("subjkeyid %*phN\n", kid->len, kid->data);
 		return 0;
 	}
 
 	if (ctx->last_oid == OID_authorityKeyIdentifier) {
-		size_t key_len;
-
 		/* Get hold of the CA key fingerprint */
-		if (vlen < 5)
+		if (ctx->cert->authority || vlen < 5)
 			return -EBADMSG;
 
 		/* Authority Key Identifier must be a Constructed SEQUENCE */
@@ -454,7 +465,7 @@ int x509_process_extension(void *context, size_t hdrlen,
 			    v[3] > vlen - 4)
 				return -EBADMSG;
 
-			key_len = v[3];
+			vlen = v[3];
 			v += 4;
 		} else {
 			/* Long Form length */
@@ -476,17 +487,17 @@ int x509_process_extension(void *context, size_t hdrlen,
 			    v[sub + 1] > vlen - 4 - sub)
 				return -EBADMSG;
 
-			key_len = v[sub + 1];
+			vlen = v[sub + 1];
 			v += (sub + 2);
 		}
 
-		f = kmalloc(key_len * 2 + 1, GFP_KERNEL);
-		if (!f)
-			return -ENOMEM;
-		for (i = 0; i < key_len; i++)
-			sprintf(f + i * 2, "%02x", v[i]);
-		pr_debug("authority   %s\n", f);
-		ctx->cert->authority = f;
+		kid = asymmetric_key_generate_id(v, vlen,
+						 ctx->cert->raw_issuer,
+						 ctx->cert->raw_issuer_size);
+		if (IS_ERR(kid))
+			return PTR_ERR(kid);
+		pr_debug("authkeyid %*phN\n", kid->len, kid->data);
+		ctx->cert->authority = kid;
 		return 0;
 	}
 
diff --git a/crypto/asymmetric_keys/x509_parser.h b/crypto/asymmetric_keys/x509_parser.h
index 1b76f207c1f3..0e8d59b010fb 100644
--- a/crypto/asymmetric_keys/x509_parser.h
+++ b/crypto/asymmetric_keys/x509_parser.h
@@ -19,8 +19,9 @@ struct x509_certificate {
 	struct public_key_signature sig;	/* Signature parameters */
 	char		*issuer;		/* Name of certificate issuer */
 	char		*subject;		/* Name of certificate subject */
-	char		*fingerprint;		/* Key fingerprint as hex */
-	char		*authority;		/* Authority key fingerprint as hex */
+	struct asymmetric_key_id *id;		/* Issuer + serial number */
+	struct asymmetric_key_id *skid;		/* Subject key identifier */
+	struct asymmetric_key_id *authority;	/* Authority key identifier */
 	struct tm	valid_from;
 	struct tm	valid_to;
 	const void	*tbs;			/* Signed data */
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index f3d62307e6ee..c60905c3f4d2 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -25,7 +25,7 @@
 #include "x509_parser.h"
 
 static bool use_builtin_keys;
-static char *ca_keyid;
+static struct asymmetric_key_id *ca_keyid;
 
 #ifndef MODULE
 static int __init ca_keys_setup(char *str)
@@ -33,10 +33,16 @@ static int __init ca_keys_setup(char *str)
 	if (!str)		/* default system keyring */
 		return 1;
 
-	if (strncmp(str, "id:", 3) == 0)
-		ca_keyid = str;	/* owner key 'id:xxxxxx' */
-	else if (strcmp(str, "builtin") == 0)
+	if (strncmp(str, "id:", 3) == 0) {
+		struct asymmetric_key_id *p;
+		p = asymmetric_key_hex_to_key_id(str);
+		if (p == ERR_PTR(-EINVAL))
+			pr_err("Unparsable hex string in ca_keys\n");
+		else if (!IS_ERR(p))
+			ca_keyid = p;	/* owner key 'id:xxxxxx' */
+	} else if (strcmp(str, "builtin") == 0) {
 		use_builtin_keys = true;
+	}
 
 	return 1;
 }
@@ -46,31 +52,28 @@ __setup("ca_keys=", ca_keys_setup);
 /**
  * x509_request_asymmetric_key - Request a key by X.509 certificate params.
  * @keyring: The keys to search.
- * @subject: The name of the subject to whom the key belongs.
- * @key_id: The subject key ID as a hex string.
+ * @kid: The key ID.
  *
  * Find a key in the given keyring by subject name and key ID.  These might,
  * for instance, be the issuer name and the authority key ID of an X.509
  * certificate that needs to be verified.
  */
 struct key *x509_request_asymmetric_key(struct key *keyring,
-					const char *subject,
-					const char *key_id)
+					const struct asymmetric_key_id *kid)
 {
 	key_ref_t key;
-	size_t subject_len = strlen(subject), key_id_len = strlen(key_id);
-	char *id;
+	char *id, *p;
 
-	/* Construct an identifier "<subjname>:<keyid>". */
-	id = kmalloc(subject_len + 2 + key_id_len + 1, GFP_KERNEL);
+	/* Construct an identifier "id:<keyid>". */
+	p = id = kmalloc(2 + 1 + kid->len * 2 + 1, GFP_KERNEL);
 	if (!id)
 		return ERR_PTR(-ENOMEM);
 
-	memcpy(id, subject, subject_len);
-	id[subject_len + 0] = ':';
-	id[subject_len + 1] = ' ';
-	memcpy(id + subject_len + 2, key_id, key_id_len);
-	id[subject_len + 2 + key_id_len] = 0;
+	*p++ = 'i';
+	*p++ = 'd';
+	*p++ = ':';
+	p = bin2hex(p, kid->data, kid->len);
+	*p = 0;
 
 	pr_debug("Look up: \"%s\"\n", id);
 
@@ -195,11 +198,10 @@ static int x509_validate_trust(struct x509_certificate *cert,
 	if (!trust_keyring)
 		return -EOPNOTSUPP;
 
-	if (ca_keyid && !asymmetric_keyid_match(cert->authority, ca_keyid))
+	if (ca_keyid && !asymmetric_key_id_same(cert->authority, ca_keyid))
 		return -EPERM;
 
-	key = x509_request_asymmetric_key(trust_keyring,
-					  cert->issuer, cert->authority);
+	key = x509_request_asymmetric_key(trust_keyring, cert->authority);
 	if (!IS_ERR(key))  {
 		if (!use_builtin_keys
 		    || test_bit(KEY_FLAG_BUILTIN, &key->flags))
@@ -214,9 +216,11 @@ static int x509_validate_trust(struct x509_certificate *cert,
  */
 static int x509_key_preparse(struct key_preparsed_payload *prep)
 {
+	struct asymmetric_key_ids *kids;
 	struct x509_certificate *cert;
+	const char *q;
 	size_t srlen, sulen;
-	char *desc = NULL;
+	char *desc = NULL, *p;
 	int ret;
 
 	cert = x509_cert_parse(prep->data, prep->datalen);
@@ -249,19 +253,12 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 		 pkey_algo_name[cert->sig.pkey_algo],
 		 hash_algo_name[cert->sig.pkey_hash_algo]);
 
-	if (!cert->fingerprint) {
-		pr_warn("Cert for '%s' must have a SubjKeyId extension\n",
-			cert->subject);
-		ret = -EKEYREJECTED;
-		goto error_free_cert;
-	}
-
 	cert->pub->algo = pkey_algo[cert->pub->pkey_algo];
 	cert->pub->id_type = PKEY_ID_X509;
 
 	/* Check the signature on the key if it appears to be self-signed */
 	if (!cert->authority ||
-	    strcmp(cert->fingerprint, cert->authority) == 0) {
+	    asymmetric_key_id_same(cert->skid, cert->authority)) {
 		ret = x509_check_signature(cert->pub, cert); /* self-signed */
 		if (ret < 0)
 			goto error_free_cert;
@@ -273,31 +270,47 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 
 	/* Propose a description */
 	sulen = strlen(cert->subject);
-	srlen = strlen(cert->fingerprint);
+	srlen = cert->raw_serial_size;
+	q = cert->raw_serial;
+	if (srlen > 1 && *q == 0) {
+		srlen--;
+		q++;
+	}
+
 	ret = -ENOMEM;
-	desc = kmalloc(sulen + 2 + srlen + 1, GFP_KERNEL);
+	desc = kmalloc(sulen + 2 + srlen * 2 + 1, GFP_KERNEL);
 	if (!desc)
 		goto error_free_cert;
-	memcpy(desc, cert->subject, sulen);
-	desc[sulen] = ':';
-	desc[sulen + 1] = ' ';
-	memcpy(desc + sulen + 2, cert->fingerprint, srlen);
-	desc[sulen + 2 + srlen] = 0;
+	p = memcpy(desc, cert->subject, sulen);
+	p += sulen;
+	*p++ = ':';
+	*p++ = ' ';
+	p = bin2hex(p, q, srlen);
+	*p = 0;
+
+	kids = kmalloc(sizeof(struct asymmetric_key_ids), GFP_KERNEL);
+	if (!kids)
+		goto error_free_desc;
+	kids->id[0] = cert->id;
+	kids->id[1] = cert->skid;
 
 	/* We're pinning the module by being linked against it */
 	__module_get(public_key_subtype.owner);
 	prep->type_data[0] = &public_key_subtype;
-	prep->type_data[1] = cert->fingerprint;
+	prep->type_data[1] = kids;
 	prep->payload[0] = cert->pub;
 	prep->description = desc;
 	prep->quotalen = 100;
 
 	/* We've finished with the certificate */
 	cert->pub = NULL;
-	cert->fingerprint = NULL;
+	cert->id = NULL;
+	cert->skid = NULL;
 	desc = NULL;
 	ret = 0;
 
+error_free_desc:
+	kfree(desc);
 error_free_cert:
 	x509_free_certificate(cert);
 	return ret;
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index 0d164c6af539..fa73a6fd536c 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -15,6 +15,7 @@
 #define _LINUX_PUBLIC_KEY_H
 
 #include <linux/mpi.h>
+#include <keys/asymmetric-type.h>
 #include <crypto/hash_info.h>
 
 enum pkey_algo {
@@ -98,8 +99,8 @@ struct key;
 extern int verify_signature(const struct key *key,
 			    const struct public_key_signature *sig);
 
+struct asymmetric_key_id;
 extern struct key *x509_request_asymmetric_key(struct key *keyring,
-					       const char *issuer,
-					       const char *key_id);
+					       const struct asymmetric_key_id *kid);
 
 #endif /* _LINUX_PUBLIC_KEY_H */
-- 
cgit v1.2.3


From f4579fc57cf4244057b713b1f73f4dc9f0b11e97 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 25 Jul 2014 11:21:47 -0700
Subject: rcu: Fix attempt to avoid unsolicited offloading of callbacks

Commit b58cc46c5f6b (rcu: Don't offload callbacks unless specifically
requested) failed to adjust the callback lists of the CPUs that are
known to be no-CBs CPUs only because they are also nohz_full= CPUs.
This failure can result in callbacks that are posted during early boot
getting stranded on nxtlist for CPUs whose no-CBs property becomes
apparent late, and there can also be spurious warnings about offline
CPUs posting callbacks.

This commit fixes these problems by adding an early-boot rcu_init_nohz()
that properly initializes the no-CBs CPUs.

Note that kernels built with CONFIG_RCU_NOCB_CPU_ALL=y or with
CONFIG_RCU_NOCB_CPU=n do not exhibit this bug.  Neither do kernels
booted without the nohz_full= boot parameter.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Pranith Kumar <bobby.prani@gmail.com>
Tested-by: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 include/linux/rcupdate.h |  8 +++++
 init/Kconfig             |  4 +--
 init/main.c              |  1 +
 kernel/rcu/tree_plugin.h | 92 ++++++++++++++++++++++++++++++++----------------
 4 files changed, 72 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d231aa17b1d7..cc7bed1c90dc 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -269,6 +269,14 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 					 struct task_struct *next) { }
 #endif /* CONFIG_RCU_USER_QS */
 
+#ifdef CONFIG_RCU_NOCB_CPU
+void rcu_init_nohz(void);
+#else /* #ifdef CONFIG_RCU_NOCB_CPU */
+static inline void rcu_init_nohz(void)
+{
+}
+#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
+
 /**
  * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers
  * @a: Code that RCU needs to pay attention to.
diff --git a/init/Kconfig b/init/Kconfig
index e84c6423a2e5..64ee4d967786 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -737,7 +737,7 @@ choice
 
 config RCU_NOCB_CPU_NONE
 	bool "No build_forced no-CBs CPUs"
-	depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL
+	depends on RCU_NOCB_CPU
 	help
 	  This option does not force any of the CPUs to be no-CBs CPUs.
 	  Only CPUs designated by the rcu_nocbs= boot parameter will be
@@ -751,7 +751,7 @@ config RCU_NOCB_CPU_NONE
 
 config RCU_NOCB_CPU_ZERO
 	bool "CPU 0 is a build_forced no-CBs CPU"
-	depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL
+	depends on RCU_NOCB_CPU
 	help
 	  This option forces CPU 0 to be a no-CBs CPU, so that its RCU
 	  callbacks are invoked by a per-CPU kthread whose name begins
diff --git a/init/main.c b/init/main.c
index bb1aed928f21..e3c4cdd94d5b 100644
--- a/init/main.c
+++ b/init/main.c
@@ -578,6 +578,7 @@ asmlinkage __visible void __init start_kernel(void)
 	idr_init_cache();
 	rcu_init();
 	tick_nohz_init();
+	rcu_init_nohz();
 	context_tracking_init();
 	radix_tree_init();
 	/* init some links before init_ISA_irqs() */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index a7997e272564..06d077ccf8d5 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -85,33 +85,6 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
-#ifdef CONFIG_RCU_NOCB_CPU
-#ifndef CONFIG_RCU_NOCB_CPU_NONE
-	if (!have_rcu_nocb_mask) {
-		zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL);
-		have_rcu_nocb_mask = true;
-	}
-#ifdef CONFIG_RCU_NOCB_CPU_ZERO
-	pr_info("\tOffload RCU callbacks from CPU 0\n");
-	cpumask_set_cpu(0, rcu_nocb_mask);
-#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
-#ifdef CONFIG_RCU_NOCB_CPU_ALL
-	pr_info("\tOffload RCU callbacks from all CPUs\n");
-	cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
-#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
-	if (have_rcu_nocb_mask) {
-		if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
-			pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
-			cpumask_and(rcu_nocb_mask, cpu_possible_mask,
-				    rcu_nocb_mask);
-		}
-		cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
-		pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
-		if (rcu_nocb_poll)
-			pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
-	}
-#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 }
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
@@ -2451,6 +2424,67 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
 }
 
+void __init rcu_init_nohz(void)
+{
+	int cpu;
+	bool need_rcu_nocb_mask = true;
+	struct rcu_state *rsp;
+
+#ifdef CONFIG_RCU_NOCB_CPU_NONE
+	need_rcu_nocb_mask = false;
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
+
+#if defined(CONFIG_NO_HZ_FULL)
+	if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask))
+		need_rcu_nocb_mask = true;
+#endif /* #if defined(CONFIG_NO_HZ_FULL) */
+
+	if (!have_rcu_nocb_mask && need_rcu_nocb_mask) {
+		zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL);
+		have_rcu_nocb_mask = true;
+	}
+	if (!have_rcu_nocb_mask)
+		return;
+
+#ifdef CONFIG_RCU_NOCB_CPU_ZERO
+	pr_info("\tOffload RCU callbacks from CPU 0\n");
+	cpumask_set_cpu(0, rcu_nocb_mask);
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
+#ifdef CONFIG_RCU_NOCB_CPU_ALL
+	pr_info("\tOffload RCU callbacks from all CPUs\n");
+	cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
+#if defined(CONFIG_NO_HZ_FULL)
+	if (tick_nohz_full_running)
+		cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
+#endif /* #if defined(CONFIG_NO_HZ_FULL) */
+
+	if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
+		pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
+		cpumask_and(rcu_nocb_mask, cpu_possible_mask,
+			    rcu_nocb_mask);
+	}
+	cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
+	pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
+	if (rcu_nocb_poll)
+		pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
+
+	for_each_rcu_flavor(rsp) {
+		for_each_cpu(cpu, rcu_nocb_mask) {
+			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+
+			/*
+			 * If there are early callbacks, they will need
+			 * to be moved to the nocb lists.
+			 */
+			WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] !=
+				     &rdp->nxtlist &&
+				     rdp->nxttail[RCU_NEXT_TAIL] != NULL);
+			init_nocb_callback_list(rdp);
+		}
+	}
+}
+
 /* Initialize per-rcu_data variables for no-CBs CPUs. */
 static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
@@ -2479,10 +2513,6 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 
 	if (rcu_nocb_mask == NULL)
 		return;
-#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL)
-	if (tick_nohz_full_running)
-		cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
-#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */
 	if (ls == -1) {
 		ls = int_sqrt(nr_cpu_ids);
 		rcu_nocb_leader_stride = ls;
-- 
cgit v1.2.3


From d36a7a0d5e8b5bff1671723d733eb61621b0cee4 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Thu, 11 Sep 2014 20:40:21 -0700
Subject: torture: Address race in module cleanup

When performing module cleanups by calling torture_cleanup() the
'torture_type' string in nullified However, callers are not necessarily
done, and might still need to reference the variable. This impacts
both rcutorture and locktorture, causing printing things like:

[   94.226618] (null)-torture: Stopping lock_torture_writer task
[   94.226624] (null)-torture: Stopping lock_torture_stats task

Thus delay this operation until the very end of the cleanup process.
The consequence (which shouldn't matter for this kid of program) is,
of course, that we delay the window between rmmod and modprobing,
for instance in module_torture_begin().

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/torture.h      |  3 ++-
 kernel/locking/locktorture.c |  3 ++-
 kernel/rcu/rcutorture.c      |  3 ++-
 kernel/torture.c             | 16 +++++++++++++---
 4 files changed, 19 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/torture.h b/include/linux/torture.h
index fec46f8c08eb..7759fc3c622d 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -77,7 +77,8 @@ int torture_stutter_init(int s);
 /* Initialization and cleanup. */
 bool torture_init_begin(char *ttype, bool v, int *runnable);
 void torture_init_end(void);
-bool torture_cleanup(void);
+bool torture_cleanup_begin(void);
+void torture_cleanup_end(void);
 bool torture_must_stop(void);
 bool torture_must_stop_irq(void);
 void torture_kthread_stopping(char *title);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index de703a769c1d..988267cc92c1 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -361,7 +361,7 @@ static void lock_torture_cleanup(void)
 {
 	int i;
 
-	if (torture_cleanup())
+	if (torture_cleanup_begin())
 		return;
 
 	if (writer_tasks) {
@@ -384,6 +384,7 @@ static void lock_torture_cleanup(void)
 	else
 		lock_torture_print_module_parms(cur_ops,
 						"End of test: SUCCESS");
+	torture_cleanup_end();
 }
 
 static int __init lock_torture_init(void)
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 6d1509500d2b..04c4b5afb759 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1514,7 +1514,7 @@ rcu_torture_cleanup(void)
 	int i;
 
 	rcutorture_record_test_transition();
-	if (torture_cleanup()) {
+	if (torture_cleanup_begin()) {
 		if (cur_ops->cb_barrier != NULL)
 			cur_ops->cb_barrier();
 		return;
@@ -1566,6 +1566,7 @@ rcu_torture_cleanup(void)
 					       "End of test: RCU_HOTPLUG");
 	else
 		rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
+	torture_cleanup_end();
 }
 
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
diff --git a/kernel/torture.c b/kernel/torture.c
index ede8b25ec1ae..dd70993c266c 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -633,8 +633,13 @@ EXPORT_SYMBOL_GPL(torture_init_end);
  *
  * This must be called before the caller starts shutting down its own
  * kthreads.
+ *
+ * Both torture_cleanup_begin() and torture_cleanup_end() must be paired,
+ * in order to correctly perform the cleanup. They are separated because
+ * threads can still need to reference the torture_type type, thus nullify
+ * only after completing all other relevant calls.
  */
-bool torture_cleanup(void)
+bool torture_cleanup_begin(void)
 {
 	mutex_lock(&fullstop_mutex);
 	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
@@ -649,12 +654,17 @@ bool torture_cleanup(void)
 	torture_shuffle_cleanup();
 	torture_stutter_cleanup();
 	torture_onoff_cleanup();
+	return false;
+}
+EXPORT_SYMBOL_GPL(torture_cleanup_begin);
+
+void torture_cleanup_end(void)
+{
 	mutex_lock(&fullstop_mutex);
 	torture_type = NULL;
 	mutex_unlock(&fullstop_mutex);
-	return false;
 }
-EXPORT_SYMBOL_GPL(torture_cleanup);
+EXPORT_SYMBOL_GPL(torture_cleanup_end);
 
 /*
  * Is it time for the current torture test to stop?
-- 
cgit v1.2.3


From 59da22a02032cf1a069ec431f93d403b321ff6b4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 12 Sep 2014 10:36:15 -0700
Subject: rcutorture: Rename rcutorture_runnable parameter

This commit changes rcutorture_runnable to torture_runnable, which is
consistent with the names of the other parameters and is a bit shorter
as well.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/kernel-parameters.txt                             | 2 +-
 include/linux/rcupdate.h                                        | 3 ---
 kernel/rcu/rcutorture.c                                         | 8 ++++----
 kernel/sysctl.c                                                 | 9 ---------
 tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh | 2 +-
 5 files changed, 6 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e1147bc62633..7aba744afcde 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2938,7 +2938,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set time (s) between CPU-hotplug operations, or
 			zero to disable CPU-hotplug testing.
 
-	rcutorture.rcutorture_runnable= [BOOT]
+	rcutorture.torture_runnable= [BOOT]
 			Start rcutorture running at boot time.
 
 	rcutorture.shuffle_interval= [KNL]
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 5cafd60c1ee4..a4a819ffb2d1 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -47,9 +47,6 @@
 #include <asm/barrier.h>
 
 extern int rcu_expedited; /* for sysctl */
-#ifdef CONFIG_RCU_TORTURE_TEST
-extern int rcutorture_runnable; /* for sysctl */
-#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 enum rcutorture_type {
 	RCU_FLAVOR,
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 04c4b5afb759..240fa9094f83 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -168,9 +168,9 @@ static int rcu_torture_writer_state;
 #else
 #define RCUTORTURE_RUNNABLE_INIT 0
 #endif
-int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
-module_param(rcutorture_runnable, int, 0444);
-MODULE_PARM_DESC(rcutorture_runnable, "Start rcutorture at boot");
+static int torture_runnable = RCUTORTURE_RUNNABLE_INIT;
+module_param(torture_runnable, int, 0444);
+MODULE_PARM_DESC(torture_runnable, "Start rcutorture at boot");
 
 #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
 #define rcu_can_boost() 1
@@ -1636,7 +1636,7 @@ rcu_torture_init(void)
 		RCUTORTURE_TASKS_OPS
 	};
 
-	if (!torture_init_begin(torture_type, verbose, &rcutorture_runnable))
+	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
 		return -EBUSY;
 
 	/* Process args and tell the world that the torturer is on the job. */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 75875a741b5e..ab456664609d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1055,15 +1055,6 @@ static struct ctl_table kern_table[] = {
 		.child		= key_sysctls,
 	},
 #endif
-#ifdef CONFIG_RCU_TORTURE_TEST
-	{
-		.procname       = "rcutorture_runnable",
-		.data           = &rcutorture_runnable,
-		.maxlen         = sizeof(int),
-		.mode           = 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 #ifdef CONFIG_PERF_EVENTS
 	/*
 	 * User-space scripts rely on the existence of this file
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 8977d8d31b19..ffb85ed786fa 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -51,7 +51,7 @@ per_version_boot_params () {
 		`rcutorture_param_n_barrier_cbs "$1"` \
 		rcutorture.stat_interval=15 \
 		rcutorture.shutdown_secs=$3 \
-		rcutorture.rcutorture_runnable=1 \
+		rcutorture.torture_runnable=1 \
 		rcutorture.test_no_idle_hz=1 \
 		rcutorture.verbose=1
 }
-- 
cgit v1.2.3


From ce6eacb07e287c0c3c8b5c316a9a7f9cecf69e95 Mon Sep 17 00:00:00 2001
From: Bruno Prémont <bonbons@linux-vserver.org>
Date: Sun, 24 Aug 2014 23:13:15 +0200
Subject: vgaarb: Drop obsolete #ifndef
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 20cde694027e ("x86, ia64: Move EFI_FB vga_default_device()
initialization to pci_vga_fixup()") moved boot video device detection from
efifb to x86 and ia64 pci/fixup.c.

Remove the left-over #ifndef check that will always match since the
corresponding arch-specific define is gone with above patch.

Signed-off-by: Bruno Prémont <bonbons@linux-vserver.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Matthew Garrett <matthew.garrett@nebula.com>
---
 drivers/gpu/vga/vgaarb.c | 8 --------
 include/linux/vgaarb.h   | 2 --
 2 files changed, 10 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index 24ac52e6cd41..77711623b973 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -113,10 +113,8 @@ both:
 	return 1;
 }
 
-#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE
 /* this is only used a cookie - it should not be dereferenced */
 static struct pci_dev *vga_default;
-#endif
 
 static void vga_arb_device_card_gone(struct pci_dev *pdev);
 
@@ -132,7 +130,6 @@ static struct vga_device *vgadev_find(struct pci_dev *pdev)
 }
 
 /* Returns the default VGA device (vgacon's babe) */
-#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE
 struct pci_dev *vga_default_device(void)
 {
 	return vga_default;
@@ -148,7 +145,6 @@ void vga_set_default_device(struct pci_dev *pdev)
 	pci_dev_put(vga_default);
 	vga_default = pci_dev_get(pdev);
 }
-#endif
 
 static inline void vga_irq_set_state(struct vga_device *vgadev, bool state)
 {
@@ -584,14 +580,12 @@ static bool vga_arbiter_add_pci_device(struct pci_dev *pdev)
 	/* Deal with VGA default device. Use first enabled one
 	 * by default if arch doesn't have it's own hook
 	 */
-#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE
 	if (vga_default == NULL &&
 	    ((vgadev->owns & VGA_RSRC_LEGACY_MASK) == VGA_RSRC_LEGACY_MASK)) {
 		pr_info("vgaarb: setting as boot device: PCI:%s\n",
 			pci_name(pdev));
 		vga_set_default_device(pdev);
 	}
-#endif
 
 	vga_arbiter_check_bridge_sharing(vgadev);
 
@@ -625,10 +619,8 @@ static bool vga_arbiter_del_pci_device(struct pci_dev *pdev)
 		goto bail;
 	}
 
-#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE
 	if (vga_default == pdev)
 		vga_set_default_device(NULL);
-#endif
 
 	if (vgadev->decodes & (VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM))
 		vga_decode_count--;
diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h
index 2c02f3a8d2ba..c37bd4d06739 100644
--- a/include/linux/vgaarb.h
+++ b/include/linux/vgaarb.h
@@ -182,7 +182,6 @@ extern void vga_put(struct pci_dev *pdev, unsigned int rsrc);
  *     vga_get()...
  */
 
-#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE
 #ifdef CONFIG_VGA_ARB
 extern struct pci_dev *vga_default_device(void);
 extern void vga_set_default_device(struct pci_dev *pdev);
@@ -190,7 +189,6 @@ extern void vga_set_default_device(struct pci_dev *pdev);
 static inline struct pci_dev *vga_default_device(void) { return NULL; };
 static inline void vga_set_default_device(struct pci_dev *pdev) { };
 #endif
-#endif
 
 /**
  *     vga_conflicts
-- 
cgit v1.2.3


From eaacabc0d9b637c82788c66955b4ba0efebd5500 Mon Sep 17 00:00:00 2001
From: Felipe Balbi <balbi@ti.com>
Date: Mon, 15 Sep 2014 16:15:01 -0500
Subject: irqchip: add irq-omap-intc.h header

OMAP INTC irqchip driver will be moved under
drivers/irqchip/ soon but we still have a dependency
with mach-omap2 when it comes to idle functions.

In order to make it easy to share those function
prototypes with OMAP PM code, we introduce this new
header.

To avoid modifying several board-files and some of
the PM-related code, we just include the new header
from common.h which was already included by all
users of IRQ-related PM code.

Signed-off-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/common.h          | 10 +---------
 include/linux/irqchip/irq-omap-intc.h | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 9 deletions(-)
 create mode 100644 include/linux/irqchip/irq-omap-intc.h

(limited to 'include')

diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index 180009343adb..377eea849e7b 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -32,6 +32,7 @@
 #include <linux/i2c/twl.h>
 #include <linux/i2c-omap.h>
 #include <linux/reboot.h>
+#include <linux/irqchip/irq-omap-intc.h>
 
 #include <asm/proc-fns.h>
 
@@ -210,15 +211,6 @@ extern struct device *omap2_get_iva_device(void);
 extern struct device *omap2_get_l3_device(void);
 extern struct device *omap4_get_dsp_device(void);
 
-void omap2_init_irq(void);
-void omap3_init_irq(void);
-void ti81xx_init_irq(void);
-extern int omap_irq_pending(void);
-void omap_intc_save_context(void);
-void omap_intc_restore_context(void);
-void omap3_intc_suspend(void);
-void omap3_intc_prepare_idle(void);
-void omap3_intc_resume_idle(void);
 void omap_gic_of_init(void);
 
 #ifdef CONFIG_CACHE_L2X0
diff --git a/include/linux/irqchip/irq-omap-intc.h b/include/linux/irqchip/irq-omap-intc.h
new file mode 100644
index 000000000000..e06b370cfc0d
--- /dev/null
+++ b/include/linux/irqchip/irq-omap-intc.h
@@ -0,0 +1,32 @@
+/**
+ * irq-omap-intc.h - INTC Idle Functions
+ *
+ * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Author: Felipe Balbi <balbi@ti.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2  of
+ * the License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __INCLUDE_LINUX_IRQCHIP_IRQ_OMAP_INTC_H
+#define __INCLUDE_LINUX_IRQCHIP_IRQ_OMAP_INTC_H
+
+void omap2_init_irq(void);
+void omap3_init_irq(void);
+void ti81xx_init_irq(void);
+
+int omap_irq_pending(void);
+void omap_intc_save_context(void);
+void omap_intc_restore_context(void);
+void omap3_intc_suspend(void);
+void omap3_intc_prepare_idle(void);
+void omap3_intc_resume_idle(void);
+
+#endif /* __INCLUDE_LINUX_IRQCHIP_IRQ_OMAP_INTC_H */
-- 
cgit v1.2.3


From ce0529843a505d09f5809a7db6288d2f038f64c4 Mon Sep 17 00:00:00 2001
From: Ethan Zhao <ethan.zhao@oracle.com>
Date: Tue, 9 Sep 2014 10:21:25 +0800
Subject: PCI: Add device flag helper functions

Add helper functions to hide direct device flag operations:

    void pci_set_dev_assigned(struct pci_dev *dev);
    void pci_clear_dev_assigned(struct pci_dev *dev);
    bool pci_is_dev_assigned(struct pci_dev *dev);

Signed-off-by: Ethan Zhao <ethan.zhao@oracle.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 61978a460841..92c131efec1c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1839,4 +1839,17 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
  */
 struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev);
 
+/* helper functions for operation of device flag */
+static inline void pci_set_dev_assigned(struct pci_dev *pdev)
+{
+	pdev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED;
+}
+static inline void pci_clear_dev_assigned(struct pci_dev *pdev)
+{
+	pdev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+}
+static inline bool pci_is_dev_assigned(struct pci_dev *pdev)
+{
+	return (pdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) == PCI_DEV_FLAGS_ASSIGNED;
+}
 #endif /* LINUX_PCI_H */
-- 
cgit v1.2.3


From e0d1b6b77ced59d852d38fcf9a8a0a1c40c84cee Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Tue, 5 Aug 2014 14:08:55 +0200
Subject: PCI/AER: Make <linux/aer.h> standalone includable

The header file references u16 and u32 types, but they are not defined in
the header nor does the header pull in the necessary includes for them.
This causes build breakage when the file is included without any of the
dependencies being satisfied from somewhere else.

Fix this by including linux/types.h (for u16 and u32).

[bhelgaas: removed pci_dev declaration (already added by 5ccb8225abf2)]
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/aer.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/aer.h b/include/linux/aer.h
index c826d1c28f9c..4fef65e57023 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -7,6 +7,8 @@
 #ifndef _AER_H_
 #define _AER_H_
 
+#include <linux/types.h>
+
 #define AER_NONFATAL			0
 #define AER_FATAL			1
 #define AER_CORRECTABLE			2
-- 
cgit v1.2.3


From 63ddc0b8fe5ebbac88e2ac84b489470bf3a22965 Mon Sep 17 00:00:00 2001
From: Megan Kamiya <megan.a.kamiya@intel.com>
Date: Fri, 5 Sep 2014 20:19:10 -0700
Subject: PCI: Parenthesize PCI_DEVID and PCI_VPD_LRDT_ID parameters

Add parentheses around parameters in PCI_DEVID and PCI_VPD_LRDT_ID macros
to prevent possible expansion errors as described by the CERT Secure Coding
Standard: PRE01-C: Use parentheses within macros around parameter names

Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Megan Kamiya <megan.a.kamiya@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 61978a460841..cb744f3925a4 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -45,7 +45,7 @@
  * In the interest of not exposing interfaces to user-space unnecessarily,
  * the following kernel-only defines are being added here.
  */
-#define PCI_DEVID(bus, devfn)  ((((u16)bus) << 8) | devfn)
+#define PCI_DEVID(bus, devfn)  ((((u16)(bus)) << 8) | (devfn))
 /* return bus from PCI devid = ((u16)bus_number) << 8) | devfn */
 #define PCI_BUS_NUM(x) (((x) >> 8) & 0xff)
 
@@ -1701,7 +1701,7 @@ bool pci_acs_path_enabled(struct pci_dev *start,
 			  struct pci_dev *end, u16 acs_flags);
 
 #define PCI_VPD_LRDT			0x80	/* Large Resource Data Type */
-#define PCI_VPD_LRDT_ID(x)		(x | PCI_VPD_LRDT)
+#define PCI_VPD_LRDT_ID(x)		((x) | PCI_VPD_LRDT)
 
 /* Large Resource Data Type Tag Item Names */
 #define PCI_VPD_LTIN_ID_STRING		0x02	/* Identifier String */
-- 
cgit v1.2.3


From 0097db06f5ab2df1756bc4cbf4395593024d87a1 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 16 Sep 2014 21:36:09 +0200
Subject: Bluetooth: Remove exported hci_recv_fragment function

The hci_recv_fragment function is no longer used by any driver and thus
do not export it. In fact it is not even needed by the core and it can
be removed altogether.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/hci_core.c         | 20 --------------------
 2 files changed, 21 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 206b92bfeebb..37ff1aef0845 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -926,7 +926,6 @@ int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr);
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
 
 int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb);
-int hci_recv_fragment(struct hci_dev *hdev, int type, void *data, int count);
 int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count);
 
 void hci_init_sysfs(struct hci_dev *hdev);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 41948678f514..cb05d7f16a34 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -4374,26 +4374,6 @@ static int hci_reassembly(struct hci_dev *hdev, int type, void *data,
 	return remain;
 }
 
-int hci_recv_fragment(struct hci_dev *hdev, int type, void *data, int count)
-{
-	int rem = 0;
-
-	if (type < HCI_ACLDATA_PKT || type > HCI_EVENT_PKT)
-		return -EILSEQ;
-
-	while (count) {
-		rem = hci_reassembly(hdev, type, data, count, type - 1);
-		if (rem < 0)
-			return rem;
-
-		data += (count - rem);
-		count = rem;
-	}
-
-	return rem;
-}
-EXPORT_SYMBOL(hci_recv_fragment);
-
 #define STREAM_REASSEMBLY 0
 
 int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count)
-- 
cgit v1.2.3


From fef775caa705255358cdf7bbaf9bbc2fd1111761 Mon Sep 17 00:00:00 2001
From: Ezequiel García <ezequiel@vanguardiasur.com.ar>
Date: Thu, 11 Sep 2014 12:02:08 -0300
Subject: nand: omap2: Add support for flash-based bad block table

This commit adds a new platform-data boolean property that enables use
of a flash-based bad block table. This can also be enabled by setting
the 'nand-on-flash-bbt' devicetree property.

If the flash BBT is not enabled, the driver falls back to use OOB
bad block markers only, as before. If the flash BBT is enabled the
kernel will keep track of bad blocks using a BBT, in addition to
the OOB markers.

As explained by Brian Norris the reasons for using a BBT are:

""
The primary reason would be that NAND datasheets specify it these days.
A better argument is that nobody guarantees that you can write a
bad block marker to a worn out block; you may just get program failures.

This has been acknowledged by several developers over the last several
years.

Additionally, you get a boot-time performance improvement if you only
have to read a few pages, instead of a page or two from every block on
the flash.
""

Signed-off-by: Ezequiel Garcia <ezequiel@vanguardiasur.com.ar>
Acked-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 arch/arm/mach-omap2/gpmc.c                   | 2 ++
 drivers/mtd/nand/omap2.c                     | 6 +++++-
 include/linux/platform_data/mtd-nand-omap2.h | 1 +
 3 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index 2f97228f188a..b55a225387cd 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -1440,6 +1440,8 @@ static int gpmc_probe_nand_child(struct platform_device *pdev,
 				break;
 			}
 
+	gpmc_nand_data->flash_bbt = of_get_nand_on_flash_bbt(child);
+
 	val = of_get_nand_bus_width(child);
 	if (val == 16)
 		gpmc_nand_data->devsize = NAND_BUSWIDTH_16;
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 5967b385141b..e1a9b310c159 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1663,7 +1663,6 @@ static int omap_nand_probe(struct platform_device *pdev)
 	mtd->owner		= THIS_MODULE;
 	nand_chip		= &info->nand;
 	nand_chip->ecc.priv	= NULL;
-	nand_chip->options	|= NAND_SKIP_BBTSCAN;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
@@ -1692,6 +1691,11 @@ static int omap_nand_probe(struct platform_device *pdev)
 		nand_chip->chip_delay = 50;
 	}
 
+	if (pdata->flash_bbt)
+		nand_chip->bbt_options |= NAND_BBT_USE_FLASH | NAND_BBT_NO_OOB;
+	else
+		nand_chip->options |= NAND_SKIP_BBTSCAN;
+
 	/* scan NAND device connected to chip controller */
 	nand_chip->options |= pdata->devsize & NAND_BUSWIDTH_16;
 	if (nand_scan_ident(mtd, 1, NULL)) {
diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h
index 16ec262dfcc8..090bbab0130a 100644
--- a/include/linux/platform_data/mtd-nand-omap2.h
+++ b/include/linux/platform_data/mtd-nand-omap2.h
@@ -71,6 +71,7 @@ struct omap_nand_platform_data {
 	struct mtd_partition	*parts;
 	int			nr_parts;
 	bool			dev_ready;
+	bool			flash_bbt;
 	enum nand_io		xfer_type;
 	int			devsize;
 	enum omap_ecc           ecc_opt;
-- 
cgit v1.2.3


From d60eacb07053142bfb9b41582074a89a790a9d46 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 2 Sep 2014 10:27:33 +0100
Subject: KVM: device: add simple registration mechanism for kvm_device_ops

kvm_ioctl_create_device currently has knowledge of all the device types
and their associated ops. This is fairly inflexible when adding support
for new in-kernel device emulations, so move what we currently have out
into a table, which can support dynamic registration of ops by new
drivers for virtual hardware.

Cc: Alex Williamson <Alex.Williamson@redhat.com>
Cc: Alex Graf <agraf@suse.de>
Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  1 +
 include/uapi/linux/kvm.h | 22 +++++++++++-----
 virt/kvm/kvm_main.c      | 65 ++++++++++++++++++++++++++++--------------------
 3 files changed, 55 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e098dce179df..b6e954742951 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1064,6 +1064,7 @@ struct kvm_device_ops {
 void kvm_device_get(struct kvm_device *dev);
 void kvm_device_put(struct kvm_device *dev);
 struct kvm_device *kvm_device_from_filp(struct file *filp);
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 0695a1e3e332..60768822b140 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -943,15 +943,25 @@ struct kvm_device_attr {
 	__u64	addr;		/* userspace address of attr data */
 };
 
-#define KVM_DEV_TYPE_FSL_MPIC_20	1
-#define KVM_DEV_TYPE_FSL_MPIC_42	2
-#define KVM_DEV_TYPE_XICS		3
-#define KVM_DEV_TYPE_VFIO		4
 #define  KVM_DEV_VFIO_GROUP			1
 #define   KVM_DEV_VFIO_GROUP_ADD			1
 #define   KVM_DEV_VFIO_GROUP_DEL			2
-#define KVM_DEV_TYPE_ARM_VGIC_V2	5
-#define KVM_DEV_TYPE_FLIC		6
+
+enum kvm_device_type {
+	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
+#define KVM_DEV_TYPE_FSL_MPIC_20	KVM_DEV_TYPE_FSL_MPIC_20
+	KVM_DEV_TYPE_FSL_MPIC_42,
+#define KVM_DEV_TYPE_FSL_MPIC_42	KVM_DEV_TYPE_FSL_MPIC_42
+	KVM_DEV_TYPE_XICS,
+#define KVM_DEV_TYPE_XICS		KVM_DEV_TYPE_XICS
+	KVM_DEV_TYPE_VFIO,
+#define KVM_DEV_TYPE_VFIO		KVM_DEV_TYPE_VFIO
+	KVM_DEV_TYPE_ARM_VGIC_V2,
+#define KVM_DEV_TYPE_ARM_VGIC_V2	KVM_DEV_TYPE_ARM_VGIC_V2
+	KVM_DEV_TYPE_FLIC,
+#define KVM_DEV_TYPE_FLIC		KVM_DEV_TYPE_FLIC
+	KVM_DEV_TYPE_MAX,
+};
 
 /*
  * ioctls for VM fds
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c338599804e0..686d783387a0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2272,44 +2272,55 @@ struct kvm_device *kvm_device_from_filp(struct file *filp)
 	return filp->private_data;
 }
 
-static int kvm_ioctl_create_device(struct kvm *kvm,
-				   struct kvm_create_device *cd)
-{
-	struct kvm_device_ops *ops = NULL;
-	struct kvm_device *dev;
-	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
-	int ret;
-
-	switch (cd->type) {
+static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 #ifdef CONFIG_KVM_MPIC
-	case KVM_DEV_TYPE_FSL_MPIC_20:
-	case KVM_DEV_TYPE_FSL_MPIC_42:
-		ops = &kvm_mpic_ops;
-		break;
+	[KVM_DEV_TYPE_FSL_MPIC_20]	= &kvm_mpic_ops,
+	[KVM_DEV_TYPE_FSL_MPIC_42]	= &kvm_mpic_ops,
 #endif
+
 #ifdef CONFIG_KVM_XICS
-	case KVM_DEV_TYPE_XICS:
-		ops = &kvm_xics_ops;
-		break;
+	[KVM_DEV_TYPE_XICS]		= &kvm_xics_ops,
 #endif
+
 #ifdef CONFIG_KVM_VFIO
-	case KVM_DEV_TYPE_VFIO:
-		ops = &kvm_vfio_ops;
-		break;
+	[KVM_DEV_TYPE_VFIO]		= &kvm_vfio_ops,
 #endif
+
 #ifdef CONFIG_KVM_ARM_VGIC
-	case KVM_DEV_TYPE_ARM_VGIC_V2:
-		ops = &kvm_arm_vgic_v2_ops;
-		break;
+	[KVM_DEV_TYPE_ARM_VGIC_V2]	= &kvm_arm_vgic_v2_ops,
 #endif
+
 #ifdef CONFIG_S390
-	case KVM_DEV_TYPE_FLIC:
-		ops = &kvm_flic_ops;
-		break;
+	[KVM_DEV_TYPE_FLIC]		= &kvm_flic_ops,
 #endif
-	default:
+};
+
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
+{
+	if (type >= ARRAY_SIZE(kvm_device_ops_table))
+		return -ENOSPC;
+
+	if (kvm_device_ops_table[type] != NULL)
+		return -EEXIST;
+
+	kvm_device_ops_table[type] = ops;
+	return 0;
+}
+
+static int kvm_ioctl_create_device(struct kvm *kvm,
+				   struct kvm_create_device *cd)
+{
+	struct kvm_device_ops *ops = NULL;
+	struct kvm_device *dev;
+	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+	int ret;
+
+	if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
+		return -ENODEV;
+
+	ops = kvm_device_ops_table[cd->type];
+	if (ops == NULL)
 		return -ENODEV;
-	}
 
 	if (test)
 		return 0;
-- 
cgit v1.2.3


From c06a841bf36340e9e917ce60d11a6425ac85d0bd Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 2 Sep 2014 10:27:34 +0100
Subject: KVM: ARM: vgic: register kvm_device_ops dynamically

Now that we have a dynamic means to register kvm_device_ops, use that
for the ARM VGIC, instead of relying on the static table.

Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |   1 -
 virt/kvm/arm/vgic.c      | 157 ++++++++++++++++++++++++-----------------------
 virt/kvm/kvm_main.c      |   4 --
 3 files changed, 79 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b6e954742951..601d321f96e7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1069,7 +1069,6 @@ int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
 extern struct kvm_device_ops kvm_vfio_ops;
-extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
 extern struct kvm_device_ops kvm_flic_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 73eba793b17f..3ee3ce06bbec 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1522,83 +1522,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static void vgic_init_maintenance_interrupt(void *info)
-{
-	enable_percpu_irq(vgic->maint_irq, 0);
-}
-
-static int vgic_cpu_notify(struct notifier_block *self,
-			   unsigned long action, void *cpu)
-{
-	switch (action) {
-	case CPU_STARTING:
-	case CPU_STARTING_FROZEN:
-		vgic_init_maintenance_interrupt(NULL);
-		break;
-	case CPU_DYING:
-	case CPU_DYING_FROZEN:
-		disable_percpu_irq(vgic->maint_irq);
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block vgic_cpu_nb = {
-	.notifier_call = vgic_cpu_notify,
-};
-
-static const struct of_device_id vgic_ids[] = {
-	{ .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
-	{ .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
-	{},
-};
-
-int kvm_vgic_hyp_init(void)
-{
-	const struct of_device_id *matched_id;
-	int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
-			  const struct vgic_params **);
-	struct device_node *vgic_node;
-	int ret;
-
-	vgic_node = of_find_matching_node_and_match(NULL,
-						    vgic_ids, &matched_id);
-	if (!vgic_node) {
-		kvm_err("error: no compatible GIC node found\n");
-		return -ENODEV;
-	}
-
-	vgic_probe = matched_id->data;
-	ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
-	if (ret)
-		return ret;
-
-	ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
-				 "vgic", kvm_get_running_vcpus());
-	if (ret) {
-		kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
-		return ret;
-	}
-
-	ret = __register_cpu_notifier(&vgic_cpu_nb);
-	if (ret) {
-		kvm_err("Cannot register vgic CPU notifier\n");
-		goto out_free_irq;
-	}
-
-	/* Callback into for arch code for setup */
-	vgic_arch_setup(vgic);
-
-	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
-
-	return 0;
-
-out_free_irq:
-	free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
-	return ret;
-}
-
 /**
  * kvm_vgic_init - Initialize global VGIC state before running any VCPUs
  * @kvm: pointer to the kvm struct
@@ -2062,7 +1985,7 @@ static int vgic_create(struct kvm_device *dev, u32 type)
 	return kvm_vgic_create(dev->kvm);
 }
 
-struct kvm_device_ops kvm_arm_vgic_v2_ops = {
+static struct kvm_device_ops kvm_arm_vgic_v2_ops = {
 	.name = "kvm-arm-vgic",
 	.create = vgic_create,
 	.destroy = vgic_destroy,
@@ -2070,3 +1993,81 @@ struct kvm_device_ops kvm_arm_vgic_v2_ops = {
 	.get_attr = vgic_get_attr,
 	.has_attr = vgic_has_attr,
 };
+
+static void vgic_init_maintenance_interrupt(void *info)
+{
+	enable_percpu_irq(vgic->maint_irq, 0);
+}
+
+static int vgic_cpu_notify(struct notifier_block *self,
+			   unsigned long action, void *cpu)
+{
+	switch (action) {
+	case CPU_STARTING:
+	case CPU_STARTING_FROZEN:
+		vgic_init_maintenance_interrupt(NULL);
+		break;
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		disable_percpu_irq(vgic->maint_irq);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block vgic_cpu_nb = {
+	.notifier_call = vgic_cpu_notify,
+};
+
+static const struct of_device_id vgic_ids[] = {
+	{ .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
+	{ .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
+	{},
+};
+
+int kvm_vgic_hyp_init(void)
+{
+	const struct of_device_id *matched_id;
+	int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
+			  const struct vgic_params **);
+	struct device_node *vgic_node;
+	int ret;
+
+	vgic_node = of_find_matching_node_and_match(NULL,
+						    vgic_ids, &matched_id);
+	if (!vgic_node) {
+		kvm_err("error: no compatible GIC node found\n");
+		return -ENODEV;
+	}
+
+	vgic_probe = matched_id->data;
+	ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
+	if (ret)
+		return ret;
+
+	ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
+				 "vgic", kvm_get_running_vcpus());
+	if (ret) {
+		kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
+		return ret;
+	}
+
+	ret = __register_cpu_notifier(&vgic_cpu_nb);
+	if (ret) {
+		kvm_err("Cannot register vgic CPU notifier\n");
+		goto out_free_irq;
+	}
+
+	/* Callback into for arch code for setup */
+	vgic_arch_setup(vgic);
+
+	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+
+	return kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
+				       KVM_DEV_TYPE_ARM_VGIC_V2);
+
+out_free_irq:
+	free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
+	return ret;
+}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 686d783387a0..68d96f5dbfe2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2286,10 +2286,6 @@ static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 	[KVM_DEV_TYPE_VFIO]		= &kvm_vfio_ops,
 #endif
 
-#ifdef CONFIG_KVM_ARM_VGIC
-	[KVM_DEV_TYPE_ARM_VGIC_V2]	= &kvm_arm_vgic_v2_ops,
-#endif
-
 #ifdef CONFIG_S390
 	[KVM_DEV_TYPE_FLIC]		= &kvm_flic_ops,
 #endif
-- 
cgit v1.2.3


From 84877d93336de21a6251db00b841468a83c65906 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Tue, 2 Sep 2014 10:27:35 +0100
Subject: KVM: s390: register flic ops dynamically

Using the new kvm_register_device_ops() interface makes us get rid of
an #ifdef in common code.

Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 3 ++-
 arch/s390/kvm/kvm-s390.h | 1 +
 include/linux/kvm_host.h | 1 -
 virt/kvm/kvm_main.c      | 4 ----
 4 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b95d4a481b0c..56a411c0245a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -122,7 +122,8 @@ void kvm_arch_hardware_unsetup(void)
 
 int kvm_arch_init(void *opaque)
 {
-	return 0;
+	/* Register floating interrupt controller interface. */
+	return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
 }
 
 /* Section: device related */
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index b1a77669137b..244d02303182 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -227,6 +227,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int psw_extint_disabled(struct kvm_vcpu *vcpu);
 void kvm_s390_destroy_adapters(struct kvm *kvm);
 int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu);
+extern struct kvm_device_ops kvm_flic_ops;
 
 /* implemented in guestdbg.c */
 void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 601d321f96e7..7ef088bec715 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1069,7 +1069,6 @@ int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
 extern struct kvm_device_ops kvm_vfio_ops;
-extern struct kvm_device_ops kvm_flic_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 68d96f5dbfe2..f4e792fedb4f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2285,10 +2285,6 @@ static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 #ifdef CONFIG_KVM_VFIO
 	[KVM_DEV_TYPE_VFIO]		= &kvm_vfio_ops,
 #endif
-
-#ifdef CONFIG_S390
-	[KVM_DEV_TYPE_FLIC]		= &kvm_flic_ops,
-#endif
 };
 
 int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
-- 
cgit v1.2.3


From 80ce1639727e9d38729c34f162378508c307ca25 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 2 Sep 2014 10:27:36 +0100
Subject: KVM: VFIO: register kvm_device_ops dynamically

Now that we have a dynamic means to register kvm_device_ops, use that
for the VFIO kvm device, instead of relying on the static table.

This is achieved by a module_init call to register the ops with KVM.

Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Alex Williamson <Alex.Williamson@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  1 -
 virt/kvm/kvm_main.c      |  4 ----
 virt/kvm/vfio.c          | 22 +++++++++++++++-------
 3 files changed, 15 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7ef088bec715..d44a2d640551 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1068,7 +1068,6 @@ int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
-extern struct kvm_device_ops kvm_vfio_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f4e792fedb4f..db57363cc287 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2281,10 +2281,6 @@ static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 #ifdef CONFIG_KVM_XICS
 	[KVM_DEV_TYPE_XICS]		= &kvm_xics_ops,
 #endif
-
-#ifdef CONFIG_KVM_VFIO
-	[KVM_DEV_TYPE_VFIO]		= &kvm_vfio_ops,
-#endif
 };
 
 int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index ba1a93f935c7..bb11b36ee8a2 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -246,6 +246,16 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 	kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
 }
 
+static int kvm_vfio_create(struct kvm_device *dev, u32 type);
+
+static struct kvm_device_ops kvm_vfio_ops = {
+	.name = "kvm-vfio",
+	.create = kvm_vfio_create,
+	.destroy = kvm_vfio_destroy,
+	.set_attr = kvm_vfio_set_attr,
+	.has_attr = kvm_vfio_has_attr,
+};
+
 static int kvm_vfio_create(struct kvm_device *dev, u32 type)
 {
 	struct kvm_device *tmp;
@@ -268,10 +278,8 @@ static int kvm_vfio_create(struct kvm_device *dev, u32 type)
 	return 0;
 }
 
-struct kvm_device_ops kvm_vfio_ops = {
-	.name = "kvm-vfio",
-	.create = kvm_vfio_create,
-	.destroy = kvm_vfio_destroy,
-	.set_attr = kvm_vfio_set_attr,
-	.has_attr = kvm_vfio_has_attr,
-};
+static int __init kvm_vfio_ops_init(void)
+{
+	return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO);
+}
+module_init(kvm_vfio_ops_init);
-- 
cgit v1.2.3


From f7790029655f79cdcee4fa7c7884e0c2795ebebe Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 12 Sep 2014 16:40:20 -0400
Subject: lockd: move lockd's grace period handling into its own module

Currently, all of the grace period handling is part of lockd. Eventually
though we'd like to be able to build v4-only servers, at which point
we'll need to put all of this elsewhere.

Move the code itself into fs/nfs_common and have it build a grace.ko
module. Then, rejigger the Kconfig options so that both nfsd and lockd
enable it automatically.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
 fs/Kconfig              |   6 ++-
 fs/lockd/Makefile       |   2 +-
 fs/lockd/grace.c        |  65 ----------------------------
 fs/lockd/netns.h        |   1 -
 fs/lockd/svc.c          |   2 +-
 fs/nfs_common/Makefile  |   3 +-
 fs/nfs_common/grace.c   | 113 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfsd/Kconfig         |   1 +
 include/linux/proc_fs.h |   2 +
 9 files changed, 125 insertions(+), 70 deletions(-)
 delete mode 100644 fs/lockd/grace.c
 create mode 100644 fs/nfs_common/grace.c

(limited to 'include')

diff --git a/fs/Kconfig b/fs/Kconfig
index 312393f32948..db5dc1598716 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -233,9 +233,13 @@ if NETWORK_FILESYSTEMS
 source "fs/nfs/Kconfig"
 source "fs/nfsd/Kconfig"
 
+config GRACE_PERIOD
+	tristate
+
 config LOCKD
 	tristate
 	depends on FILE_LOCKING
+	select GRACE_PERIOD
 
 config LOCKD_V4
 	bool
@@ -249,7 +253,7 @@ config NFS_ACL_SUPPORT
 
 config NFS_COMMON
 	bool
-	depends on NFSD || NFS_FS
+	depends on NFSD || NFS_FS || LOCKD
 	default y
 
 source "net/sunrpc/Kconfig"
diff --git a/fs/lockd/Makefile b/fs/lockd/Makefile
index ca58d64374ca..6a0b351ce30e 100644
--- a/fs/lockd/Makefile
+++ b/fs/lockd/Makefile
@@ -5,6 +5,6 @@
 obj-$(CONFIG_LOCKD) += lockd.o
 
 lockd-objs-y := clntlock.o clntproc.o clntxdr.o host.o svc.o svclock.o \
-	        svcshare.o svcproc.o svcsubs.o mon.o xdr.o grace.o
+	        svcshare.o svcproc.o svcsubs.o mon.o xdr.o
 lockd-objs-$(CONFIG_LOCKD_V4) += clnt4xdr.o xdr4.o svc4proc.o
 lockd-objs		      := $(lockd-objs-y)
diff --git a/fs/lockd/grace.c b/fs/lockd/grace.c
deleted file mode 100644
index 6d1ee7204c88..000000000000
--- a/fs/lockd/grace.c
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- * Common code for control of lockd and nfsv4 grace periods.
- */
-
-#include <linux/module.h>
-#include <linux/lockd/bind.h>
-#include <net/net_namespace.h>
-
-#include "netns.h"
-
-static DEFINE_SPINLOCK(grace_lock);
-
-/**
- * locks_start_grace
- * @lm: who this grace period is for
- *
- * A grace period is a period during which locks should not be given
- * out.  Currently grace periods are only enforced by the two lock
- * managers (lockd and nfsd), using the locks_in_grace() function to
- * check when they are in a grace period.
- *
- * This function is called to start a grace period.
- */
-void locks_start_grace(struct net *net, struct lock_manager *lm)
-{
-	struct lockd_net *ln = net_generic(net, lockd_net_id);
-
-	spin_lock(&grace_lock);
-	list_add(&lm->list, &ln->grace_list);
-	spin_unlock(&grace_lock);
-}
-EXPORT_SYMBOL_GPL(locks_start_grace);
-
-/**
- * locks_end_grace
- * @lm: who this grace period is for
- *
- * Call this function to state that the given lock manager is ready to
- * resume regular locking.  The grace period will not end until all lock
- * managers that called locks_start_grace() also call locks_end_grace().
- * Note that callers count on it being safe to call this more than once,
- * and the second call should be a no-op.
- */
-void locks_end_grace(struct lock_manager *lm)
-{
-	spin_lock(&grace_lock);
-	list_del_init(&lm->list);
-	spin_unlock(&grace_lock);
-}
-EXPORT_SYMBOL_GPL(locks_end_grace);
-
-/**
- * locks_in_grace
- *
- * Lock managers call this function to determine when it is OK for them
- * to answer ordinary lock requests, and when they should accept only
- * lock reclaims.
- */
-int locks_in_grace(struct net *net)
-{
-	struct lockd_net *ln = net_generic(net, lockd_net_id);
-
-	return !list_empty(&ln->grace_list);
-}
-EXPORT_SYMBOL_GPL(locks_in_grace);
diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h
index 5010b55628b4..097bfa3adb1c 100644
--- a/fs/lockd/netns.h
+++ b/fs/lockd/netns.h
@@ -11,7 +11,6 @@ struct lockd_net {
 
 	struct delayed_work grace_period_end;
 	struct lock_manager lockd_manager;
-	struct list_head grace_list;
 
 	spinlock_t nsm_clnt_lock;
 	unsigned int nsm_users;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 09857b48d0c3..266b67972305 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -586,7 +586,7 @@ static int lockd_init_net(struct net *net)
 	struct lockd_net *ln = net_generic(net, lockd_net_id);
 
 	INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender);
-	INIT_LIST_HEAD(&ln->grace_list);
+	INIT_LIST_HEAD(&ln->lockd_manager.list);
 	spin_lock_init(&ln->nsm_clnt_lock);
 	return 0;
 }
diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile
index f689ed82af3a..d153ca3ea577 100644
--- a/fs/nfs_common/Makefile
+++ b/fs/nfs_common/Makefile
@@ -3,5 +3,6 @@
 #
 
 obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o
-
 nfs_acl-objs := nfsacl.o
+
+obj-$(CONFIG_GRACE_PERIOD) += grace.o
diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c
new file mode 100644
index 000000000000..ae6e58ea4de5
--- /dev/null
+++ b/fs/nfs_common/grace.c
@@ -0,0 +1,113 @@
+/*
+ * Common code for control of lockd and nfsv4 grace periods.
+ *
+ * Transplanted from lockd code
+ */
+
+#include <linux/module.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <linux/fs.h>
+
+static int grace_net_id;
+static DEFINE_SPINLOCK(grace_lock);
+
+/**
+ * locks_start_grace
+ * @net: net namespace that this lock manager belongs to
+ * @lm: who this grace period is for
+ *
+ * A grace period is a period during which locks should not be given
+ * out.  Currently grace periods are only enforced by the two lock
+ * managers (lockd and nfsd), using the locks_in_grace() function to
+ * check when they are in a grace period.
+ *
+ * This function is called to start a grace period.
+ */
+void
+locks_start_grace(struct net *net, struct lock_manager *lm)
+{
+	struct list_head *grace_list = net_generic(net, grace_net_id);
+
+	spin_lock(&grace_lock);
+	list_add(&lm->list, grace_list);
+	spin_unlock(&grace_lock);
+}
+EXPORT_SYMBOL_GPL(locks_start_grace);
+
+/**
+ * locks_end_grace
+ * @net: net namespace that this lock manager belongs to
+ * @lm: who this grace period is for
+ *
+ * Call this function to state that the given lock manager is ready to
+ * resume regular locking.  The grace period will not end until all lock
+ * managers that called locks_start_grace() also call locks_end_grace().
+ * Note that callers count on it being safe to call this more than once,
+ * and the second call should be a no-op.
+ */
+void
+locks_end_grace(struct lock_manager *lm)
+{
+	spin_lock(&grace_lock);
+	list_del_init(&lm->list);
+	spin_unlock(&grace_lock);
+}
+EXPORT_SYMBOL_GPL(locks_end_grace);
+
+/**
+ * locks_in_grace
+ *
+ * Lock managers call this function to determine when it is OK for them
+ * to answer ordinary lock requests, and when they should accept only
+ * lock reclaims.
+ */
+int
+locks_in_grace(struct net *net)
+{
+	struct list_head *grace_list = net_generic(net, grace_net_id);
+
+	return !list_empty(grace_list);
+}
+EXPORT_SYMBOL_GPL(locks_in_grace);
+
+static int __net_init
+grace_init_net(struct net *net)
+{
+	struct list_head *grace_list = net_generic(net, grace_net_id);
+
+	INIT_LIST_HEAD(grace_list);
+	return 0;
+}
+
+static void __net_exit
+grace_exit_net(struct net *net)
+{
+	struct list_head *grace_list = net_generic(net, grace_net_id);
+
+	BUG_ON(!list_empty(grace_list));
+}
+
+static struct pernet_operations grace_net_ops = {
+	.init = grace_init_net,
+	.exit = grace_exit_net,
+	.id   = &grace_net_id,
+	.size = sizeof(struct list_head),
+};
+
+static int __init
+init_grace(void)
+{
+	return register_pernet_subsys(&grace_net_ops);
+}
+
+static void __exit
+exit_grace(void)
+{
+	unregister_pernet_subsys(&grace_net_ops);
+}
+
+MODULE_AUTHOR("Jeff Layton <jlayton@primarydata.com>");
+MODULE_LICENSE("GPL");
+module_init(init_grace)
+module_exit(exit_grace)
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index f3586b645d7d..73395156bdb4 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -71,6 +71,7 @@ config NFSD_V4
 	select FS_POSIX_ACL
 	select SUNRPC_GSS
 	select CRYPTO
+	select GRACE_PERIOD
 	help
 	  This option enables support in your system's NFS server for
 	  version 4 of the NFS protocol (RFC 3530).
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 9d117f61d976..b97bf2ef996e 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -74,6 +74,8 @@ static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *p
 
 #endif /* CONFIG_PROC_FS */
 
+struct net;
+
 static inline struct proc_dir_entry *proc_net_mkdir(
 	struct net *net, const char *name, struct proc_dir_entry *parent)
 {
-- 
cgit v1.2.3


From d3982100baeb9bed8cf931545fb0522268f526e5 Mon Sep 17 00:00:00 2001
From: Mark Fasheh <mfasheh@suse.de>
Date: Thu, 17 Jul 2014 12:39:00 -0700
Subject: btrfs: add trace for qgroup accounting

We want this to debug qgroup changes on live systems.

Signed-off-by: Mark Fasheh <mfasheh@suse.de>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>
---
 fs/btrfs/qgroup.c            |  4 ++++
 fs/btrfs/super.c             |  1 +
 include/trace/events/btrfs.h | 56 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 61 insertions(+)

(limited to 'include')

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 2ce4ce7b47d8..1e4c6e95ab55 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1335,6 +1335,8 @@ int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans,
 	INIT_LIST_HEAD(&oper->elem.list);
 	oper->elem.seq = 0;
 
+	trace_btrfs_qgroup_record_ref(oper);
+
 	if (type == BTRFS_QGROUP_OPER_SUB_SUBTREE) {
 		/*
 		 * If any operation for this bytenr/ref_root combo
@@ -2077,6 +2079,8 @@ static int btrfs_qgroup_account(struct btrfs_trans_handle *trans,
 
 	ASSERT(is_fstree(oper->ref_root));
 
+	trace_btrfs_qgroup_account(oper);
+
 	switch (oper->type) {
 	case BTRFS_QGROUP_OPER_ADD_EXCL:
 	case BTRFS_QGROUP_OPER_SUB_EXCL:
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d66fbd57f1b5..3f1f4e2dc78f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -60,6 +60,7 @@
 #include "backref.h"
 #include "tests/btrfs-tests.h"
 
+#include "qgroup.h"
 #define CREATE_TRACE_POINTS
 #include <trace/events/btrfs.h>
 
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 4ee4e30d26d9..b8774b3f88d7 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -23,6 +23,7 @@ struct map_lookup;
 struct extent_buffer;
 struct btrfs_work;
 struct __btrfs_workqueue;
+struct btrfs_qgroup_operation;
 
 #define show_ref_type(type)						\
 	__print_symbolic(type,						\
@@ -1119,6 +1120,61 @@ DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy,
 	TP_ARGS(wq)
 );
 
+#define show_oper_type(type)						\
+	__print_symbolic(type,						\
+		{ BTRFS_QGROUP_OPER_ADD_EXCL, 	"OPER_ADD_EXCL" },	\
+		{ BTRFS_QGROUP_OPER_ADD_SHARED, "OPER_ADD_SHARED" },	\
+		{ BTRFS_QGROUP_OPER_SUB_EXCL, 	"OPER_SUB_EXCL" },	\
+		{ BTRFS_QGROUP_OPER_SUB_SHARED,	"OPER_SUB_SHARED" })
+
+DECLARE_EVENT_CLASS(btrfs_qgroup_oper,
+
+	TP_PROTO(struct btrfs_qgroup_operation *oper),
+
+	TP_ARGS(oper),
+
+	TP_STRUCT__entry(
+		__field(	u64,  ref_root		)
+		__field(	u64,  bytenr		)
+		__field(	u64,  num_bytes		)
+		__field(	u64,  seq		)
+		__field(	int,  type		)
+		__field(	u64,  elem_seq		)
+	),
+
+	TP_fast_assign(
+		__entry->ref_root	= oper->ref_root;
+		__entry->bytenr		= oper->bytenr,
+		__entry->num_bytes	= oper->num_bytes;
+		__entry->seq 		= oper->seq;
+		__entry->type		= oper->type;
+		__entry->elem_seq	= oper->elem.seq;
+	),
+
+	TP_printk("ref_root = %llu, bytenr = %llu, num_bytes = %llu, "
+		  "seq = %llu, elem.seq = %llu, type = %s",
+		  (unsigned long long)__entry->ref_root,
+		  (unsigned long long)__entry->bytenr,
+		  (unsigned long long)__entry->num_bytes,
+		  (unsigned long long)__entry->seq,
+		  (unsigned long long)__entry->elem_seq,
+		  show_oper_type(__entry->type))
+);
+
+DEFINE_EVENT(btrfs_qgroup_oper, btrfs_qgroup_account,
+
+	TP_PROTO(struct btrfs_qgroup_operation *oper),
+
+	TP_ARGS(oper)
+);
+
+DEFINE_EVENT(btrfs_qgroup_oper, btrfs_qgroup_record_ref,
+
+	TP_PROTO(struct btrfs_qgroup_operation *oper),
+
+	TP_ARGS(oper)
+);
+
 #endif /* _TRACE_BTRFS_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From b38a62586fed4ce058dc8d40deaa1b85cafc7fb3 Mon Sep 17 00:00:00 2001
From: Liu Bo <bo.li.liu@oracle.com>
Date: Tue, 12 Aug 2014 16:33:17 +0800
Subject: Btrfs: add work_struct information for workqueue tracepoint

Kernel workqueue's tracepoints print the address of work_struct, while btrfs
workqueue's tracepoints print the address of btrfs_work.

We need a connection between this two, for example when debuging, we usually
grep an address in the trace output.  So it'd be better to also print
work_struct in btrfs workqueue's tracepoint.

Please note that we can only add this into those tracepoints whose work is still
available in memory because we need to reference the work.

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
---
 include/trace/events/btrfs.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index b8774b3f88d7..e3f3d10c6647 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -997,6 +997,7 @@ DECLARE_EVENT_CLASS(btrfs__work,
 		__field(	void *,	func			)
 		__field(	void *,	ordered_func		)
 		__field(	void *,	ordered_free		)
+		__field(	void *,	normal_work		)
 	),
 
 	TP_fast_assign(
@@ -1005,11 +1006,13 @@ DECLARE_EVENT_CLASS(btrfs__work,
 		__entry->func		= work->func;
 		__entry->ordered_func	= work->ordered_func;
 		__entry->ordered_free	= work->ordered_free;
+		__entry->normal_work	= &work->normal_work;
 	),
 
-	TP_printk("work=%p, wq=%p, func=%p, ordered_func=%p, ordered_free=%p",
-		  __entry->work, __entry->wq, __entry->func,
-		  __entry->ordered_func, __entry->ordered_free)
+	TP_printk("work=%p (normal_work=%p), wq=%p, func=%p, ordered_func=%p,"
+		  " ordered_free=%p",
+		  __entry->work, __entry->normal_work, __entry->wq,
+		   __entry->func, __entry->ordered_func, __entry->ordered_free)
 );
 
 /* For situiations that the work is freed */
-- 
cgit v1.2.3


From 1a76e4ba5b18775e532faa4f8eb858c4553d196c Mon Sep 17 00:00:00 2001
From: Liu Bo <bo.li.liu@oracle.com>
Date: Tue, 12 Aug 2014 16:33:18 +0800
Subject: Btrfs: cleanup for btrfs workqueue tracepoints

Tracepoint trace_btrfs_normal_work_done never has an user, just cleanup it.

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
---
 include/trace/events/btrfs.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index e3f3d10c6647..64a90d78e6bb 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1047,13 +1047,6 @@ DEFINE_EVENT(btrfs__work, btrfs_work_sched,
 	TP_ARGS(work)
 );
 
-DEFINE_EVENT(btrfs__work, btrfs_normal_work_done,
-
-	TP_PROTO(struct btrfs_work *work),
-
-	TP_ARGS(work)
-);
-
 DEFINE_EVENT(btrfs__work__done, btrfs_all_work_done,
 
 	TP_PROTO(struct btrfs_work *work),
-- 
cgit v1.2.3


From b7831b20f32019b741eb8fe3435c2516e13e0c4a Mon Sep 17 00:00:00 2001
From: Liu Bo <bo.li.liu@oracle.com>
Date: Fri, 15 Aug 2014 23:38:06 +0800
Subject: Btrfs: show real function name in btrfs workqueue tracepoint

Use %pf instead of %p, just same as kernel workqueue tracepoints.

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Chris Mason <clm@fb.com>
---
 include/trace/events/btrfs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 64a90d78e6bb..e022a60699df 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1009,7 +1009,7 @@ DECLARE_EVENT_CLASS(btrfs__work,
 		__entry->normal_work	= &work->normal_work;
 	),
 
-	TP_printk("work=%p (normal_work=%p), wq=%p, func=%p, ordered_func=%p,"
+	TP_printk("work=%p (normal_work=%p), wq=%p, func=%pf, ordered_func=%p,"
 		  " ordered_free=%p",
 		  __entry->work, __entry->normal_work, __entry->wq,
 		   __entry->func, __entry->ordered_func, __entry->ordered_free)
-- 
cgit v1.2.3


From 6213daab2547fdc0d02a86abf3ac209ac6881ae3 Mon Sep 17 00:00:00 2001
From: Li Zefan <lizefan@huawei.com>
Date: Wed, 17 Sep 2014 18:18:09 +0800
Subject: cgroup: remove some useless forward declarations

Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h | 1 -
 kernel/cgroup.c        | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b5223c570eba..f7898e0bce1e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -27,7 +27,6 @@
 
 struct cgroup_root;
 struct cgroup_subsys;
-struct inode;
 struct cgroup;
 
 extern int cgroup_init_early(void);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ebd4476c57de..619aae399a3a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -185,7 +185,6 @@ static int need_forkexit_callback __read_mostly;
 static struct cftype cgroup_dfl_base_files[];
 static struct cftype cgroup_legacy_base_files[];
 
-static void cgroup_put(struct cgroup *cgrp);
 static int rebind_subsystems(struct cgroup_root *dst_root,
 			     unsigned int ss_mask);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
@@ -195,7 +194,6 @@ static void css_release(struct percpu_ref *ref);
 static void kill_css(struct cgroup_subsys_state *css);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 			      bool is_add);
-static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
 
 /* IDR wrappers which synchronize using cgroup_idr_lock */
 static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
-- 
cgit v1.2.3


From b729bf34535ed413667b397a2f59cfa81266facf Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Tue, 19 Aug 2014 20:29:19 +0300
Subject: spi/pxa2xx: Don't use slave_id of dma_slave_config

That field has been deprecated in favour of getting the necessary
information from ACPI/DT.

However, we still need to deal systems that are PCI only (no ACPI to back
up). In order to support such systems, we allow the DMA filter function and
its corresponding parameter via pxa2xx_spi_master platform data. Then when
the pxa2xx_spi_dma_setup() doesn't find the channel via ACPI, it falls back
to use the given filter function.

Suggested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/spi/spi-pxa2xx-dma.c   | 15 ++--------
 drivers/spi/spi-pxa2xx-pci.c   | 64 +++++++++++++++++++++++++++++++-----------
 drivers/spi/spi-pxa2xx.c       |  2 --
 include/linux/spi/pxa2xx_spi.h |  9 +++---
 4 files changed, 54 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index c41ff148a2b4..62a9297e96ac 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -157,7 +157,6 @@ static struct dma_async_tx_descriptor *
 pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 			   enum dma_transfer_direction dir)
 {
-	struct pxa2xx_spi_master *pdata = drv_data->master_info;
 	struct chip_data *chip = drv_data->cur_chip;
 	enum dma_slave_buswidth width;
 	struct dma_slave_config cfg;
@@ -184,7 +183,6 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 		cfg.dst_addr = drv_data->ssdr_physical;
 		cfg.dst_addr_width = width;
 		cfg.dst_maxburst = chip->dma_burst_size;
-		cfg.slave_id = pdata->tx_slave_id;
 
 		sgt = &drv_data->tx_sgt;
 		nents = drv_data->tx_nents;
@@ -193,7 +191,6 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 		cfg.src_addr = drv_data->ssdr_physical;
 		cfg.src_addr_width = width;
 		cfg.src_maxburst = chip->dma_burst_size;
-		cfg.slave_id = pdata->rx_slave_id;
 
 		sgt = &drv_data->rx_sgt;
 		nents = drv_data->rx_nents;
@@ -210,14 +207,6 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 }
 
-static bool pxa2xx_spi_dma_filter(struct dma_chan *chan, void *param)
-{
-	const struct pxa2xx_spi_master *pdata = param;
-
-	return chan->chan_id == pdata->tx_chan_id ||
-	       chan->chan_id == pdata->rx_chan_id;
-}
-
 bool pxa2xx_spi_dma_is_possible(size_t len)
 {
 	return len <= MAX_DMA_LEN;
@@ -321,12 +310,12 @@ int pxa2xx_spi_dma_setup(struct driver_data *drv_data)
 		return -ENOMEM;
 
 	drv_data->tx_chan = dma_request_slave_channel_compat(mask,
-				pxa2xx_spi_dma_filter, pdata, dev, "tx");
+				pdata->dma_filter, pdata->tx_param, dev, "tx");
 	if (!drv_data->tx_chan)
 		return -ENODEV;
 
 	drv_data->rx_chan = dma_request_slave_channel_compat(mask,
-				pxa2xx_spi_dma_filter, pdata, dev, "rx");
+				pdata->dma_filter, pdata->rx_param, dev, "rx");
 	if (!drv_data->rx_chan) {
 		dma_release_channel(drv_data->tx_chan);
 		drv_data->tx_chan = NULL;
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index 20ebbc764693..0424b67c983e 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -10,6 +10,9 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 
+#include <linux/dmaengine.h>
+#include <linux/platform_data/dma-dw.h>
+
 enum {
 	PORT_CE4100,
 	PORT_BYT,
@@ -19,33 +22,41 @@ struct pxa_spi_info {
 	enum pxa_ssp_type type;
 	int port_id;
 	int num_chipselect;
-	int tx_slave_id;
-	int tx_chan_id;
-	int rx_slave_id;
-	int rx_chan_id;
 	unsigned long max_clk_rate;
+
+	/* DMA channel request parameters */
+	void *tx_param;
+	void *rx_param;
 };
 
+static struct dw_dma_slave byt_tx_param = { .dst_id = 0 };
+static struct dw_dma_slave byt_rx_param = { .src_id = 1 };
+
+static bool lpss_dma_filter(struct dma_chan *chan, void *param)
+{
+	struct dw_dma_slave *dws = param;
+
+	if (dws->dma_dev != chan->device->dev)
+		return false;
+
+	chan->private = dws;
+	return true;
+}
+
 static struct pxa_spi_info spi_info_configs[] = {
 	[PORT_CE4100] = {
 		.type = PXA25x_SSP,
 		.port_id =  -1,
 		.num_chipselect = -1,
-		.tx_slave_id = -1,
-		.tx_chan_id = -1,
-		.rx_slave_id = -1,
-		.rx_chan_id = -1,
 		.max_clk_rate = 3686400,
 	},
 	[PORT_BYT] = {
 		.type = LPSS_SSP,
 		.port_id = 0,
 		.num_chipselect = 1,
-		.tx_slave_id = 0,
-		.tx_chan_id = 0,
-		.rx_slave_id = 1,
-		.rx_chan_id = 1,
 		.max_clk_rate = 50000000,
+		.tx_param = &byt_tx_param,
+		.rx_param = &byt_rx_param,
 	},
 };
 
@@ -59,6 +70,7 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
 	struct ssp_device *ssp;
 	struct pxa_spi_info *c;
 	char buf[40];
+	struct pci_dev *dma_dev;
 
 	ret = pcim_enable_device(dev);
 	if (ret)
@@ -73,11 +85,29 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
 	memset(&spi_pdata, 0, sizeof(spi_pdata));
 	spi_pdata.num_chipselect = (c->num_chipselect > 0) ?
 					c->num_chipselect : dev->devfn;
-	spi_pdata.tx_slave_id = c->tx_slave_id;
-	spi_pdata.tx_chan_id = c->tx_chan_id;
-	spi_pdata.rx_slave_id = c->rx_slave_id;
-	spi_pdata.rx_chan_id = c->rx_chan_id;
-	spi_pdata.enable_dma = c->rx_slave_id >= 0 && c->tx_slave_id >= 0;
+
+	dma_dev = pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+
+	if (c->tx_param) {
+		struct dw_dma_slave *slave = c->tx_param;
+
+		slave->dma_dev = &dma_dev->dev;
+		slave->src_master = 1;
+		slave->dst_master = 0;
+	}
+
+	if (c->rx_param) {
+		struct dw_dma_slave *slave = c->rx_param;
+
+		slave->dma_dev = &dma_dev->dev;
+		slave->src_master = 1;
+		slave->dst_master = 0;
+	}
+
+	spi_pdata.dma_filter = lpss_dma_filter;
+	spi_pdata.tx_param = c->tx_param;
+	spi_pdata.rx_param = c->rx_param;
+	spi_pdata.enable_dma = c->rx_param && c->tx_param;
 
 	ssp = &spi_pdata.ssp;
 	ssp->phys_base = pci_resource_start(dev, 0);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index fe792106bdc5..256c0abbddd2 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1062,8 +1062,6 @@ pxa2xx_spi_acpi_get_pdata(struct platform_device *pdev)
 
 	pdata->num_chipselect = 1;
 	pdata->enable_dma = true;
-	pdata->tx_chan_id = -1;
-	pdata->rx_chan_id = -1;
 
 	return pdata;
 }
diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h
index 82d5111cd0c2..d5a316550177 100644
--- a/include/linux/spi/pxa2xx_spi.h
+++ b/include/linux/spi/pxa2xx_spi.h
@@ -23,6 +23,8 @@
 #define PXA2XX_CS_ASSERT (0x01)
 #define PXA2XX_CS_DEASSERT (0x02)
 
+struct dma_chan;
+
 /* device.platform_data for SSP controller devices */
 struct pxa2xx_spi_master {
 	u32 clock_enable;
@@ -30,10 +32,9 @@ struct pxa2xx_spi_master {
 	u8 enable_dma;
 
 	/* DMA engine specific config */
-	int rx_chan_id;
-	int tx_chan_id;
-	int rx_slave_id;
-	int tx_slave_id;
+	bool (*dma_filter)(struct dma_chan *chan, void *param);
+	void *tx_param;
+	void *rx_param;
 
 	/* For non-PXA arches */
 	struct ssp_device ssp;
-- 
cgit v1.2.3


From 689f1c9de2abbd76fda224d12cea5f43568a4335 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 18 Sep 2014 16:38:18 +0800
Subject: ipsec: Remove obsolete MAX_AH_AUTH_LEN

While tracking down the MAX_AH_AUTH_LEN crash in an old kernel
I thought that this limit was rather arbitrary and we should
just get rid of it.

In fact it seems that we've already done all the work needed
to remove it apart from actually removing it.  This limit was
there in order to limit stack usage.  Since we've already
switched over to allocating scratch space using kmalloc, there
is no longer any need to limit the authentication length.

This patch kills all references to it, including the BUG_ONs
that led me here.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/ah.h     | 3 ---
 net/ipv4/ah4.c       | 2 --
 net/ipv6/ah6.c       | 2 --
 net/xfrm/xfrm_user.c | 3 +--
 4 files changed, 1 insertion(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/ah.h b/include/net/ah.h
index ca95b98969dd..4e2dfa474a7e 100644
--- a/include/net/ah.h
+++ b/include/net/ah.h
@@ -3,9 +3,6 @@
 
 #include <linux/skbuff.h>
 
-/* This is the maximum truncated ICV length that we know of. */
-#define MAX_AH_AUTH_LEN	64
-
 struct crypto_ahash;
 
 struct ah_data {
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a2afa89513a0..ac9a32ec3ee4 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -505,8 +505,6 @@ static int ah_init_state(struct xfrm_state *x)
 	ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8;
 	ahp->icv_trunc_len = x->aalg->alg_trunc_len/8;
 
-	BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN);
-
 	if (x->props.flags & XFRM_STATE_ALIGN4)
 		x->props.header_len = XFRM_ALIGN4(sizeof(struct ip_auth_hdr) +
 						  ahp->icv_trunc_len);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index fcffd4e522c8..6d16eb0e0c7f 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -713,8 +713,6 @@ static int ah6_init_state(struct xfrm_state *x)
 	ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8;
 	ahp->icv_trunc_len = x->aalg->alg_trunc_len/8;
 
-	BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN);
-
 	x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) +
 					  ahp->icv_trunc_len);
 	switch (x->props.mode) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index eaf8a8f1cbe8..e812e988c111 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -333,8 +333,7 @@ static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props,
 	algo = xfrm_aalg_get_byname(ualg->alg_name, 1);
 	if (!algo)
 		return -ENOSYS;
-	if ((ualg->alg_trunc_len / 8) > MAX_AH_AUTH_LEN ||
-	    ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits)
+	if (ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits)
 		return -EINVAL;
 	*props = algo->desc.sadb_alg_id;
 
-- 
cgit v1.2.3


From d364a77d02071355edbd5ee26c248b1ea75c653c Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Fri, 11 Jul 2014 17:18:28 +0300
Subject: ARM: tegra: Add PLL_M_UD and PLL_C_UD to tegra124-car binding header

Add these clocks to the binding header so that EMC timings that have
them as parent can refer to the clocks.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
---
 include/dt-bindings/clock/tegra124-car.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h
index 8a4c5892890f..6bac637fd635 100644
--- a/include/dt-bindings/clock/tegra124-car.h
+++ b/include/dt-bindings/clock/tegra124-car.h
@@ -337,6 +337,10 @@
 #define TEGRA124_CLK_DSIB_MUX 310
 #define TEGRA124_CLK_SOR0_LVDS 311
 #define TEGRA124_CLK_XUSB_SS_DIV2 312
-#define TEGRA124_CLK_CLK_MAX 313
+
+#define TEGRA124_CLK_PLL_M_UD 313
+#define TEGRA124_CLK_PLL_C_UD 314
+
+#define TEGRA124_CLK_CLK_MAX 315
 
 #endif	/* _DT_BINDINGS_CLOCK_TEGRA124_CAR_H */
-- 
cgit v1.2.3


From 254a2d14fa77ac8a1b64f6171ec5f717f0753b53 Mon Sep 17 00:00:00 2001
From: Liu Bo <bo.li.liu@oracle.com>
Date: Wed, 17 Sep 2014 21:36:41 +0800
Subject: Btrfs: fix wrong parse of extent map's tracepoint

The tracepoint of extent map doesn't parse @flag correctly, we set @flag via
set_bit(), so we need to parse it on a bit bias.

Also add the missing flag, EXTENT_FLAG_FS_MAPPING.

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
---
 include/trace/events/btrfs.h | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index e022a60699df..1faecea101f3 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -158,12 +158,13 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 
 #define show_map_flags(flag)						\
 	__print_flags(flag, "|",					\
-		{ EXTENT_FLAG_PINNED, 		"PINNED" 	},	\
-		{ EXTENT_FLAG_COMPRESSED, 	"COMPRESSED" 	},	\
-		{ EXTENT_FLAG_VACANCY, 		"VACANCY" 	},	\
-		{ EXTENT_FLAG_PREALLOC, 	"PREALLOC" 	},	\
-		{ EXTENT_FLAG_LOGGING,	 	"LOGGING" 	},	\
-		{ EXTENT_FLAG_FILLING,	 	"FILLING" 	})
+		{ (1 << EXTENT_FLAG_PINNED), 		"PINNED" 	},\
+		{ (1 << EXTENT_FLAG_COMPRESSED), 	"COMPRESSED" 	},\
+		{ (1 << EXTENT_FLAG_VACANCY), 		"VACANCY" 	},\
+		{ (1 << EXTENT_FLAG_PREALLOC), 		"PREALLOC" 	},\
+		{ (1 << EXTENT_FLAG_LOGGING),	 	"LOGGING" 	},\
+		{ (1 << EXTENT_FLAG_FILLING),	 	"FILLING" 	},\
+		{ (1 << EXTENT_FLAG_FS_MAPPING),	"FS_MAPPING"	})
 
 TRACE_EVENT_CONDITION(btrfs_get_extent,
 
-- 
cgit v1.2.3


From 175655bd79b815f2b2035f3b44117c60be90e1d4 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 16 Sep 2014 17:36:28 -0700
Subject: ARM: OMAP: Remove unused pieces of legacy DMA API

We're moving to the dmaengine API, so let's remove the unused
pieces of the omap legacy DMA code to make sure we don't get
any new users for these:

omap_set_dma_color_mode
omap_set_dma_src_index
omap_set_dma_dest_index
omap_dma_unlink_lch
omap_clear_dma
omap_dma_running
omap_dma_set_prio_lch
omap_set_dma_dst_endian_type
omap_set_dma_src_endian_type
omap_get_dma_index
omap_dma_disable_irq
omap_request_dma_chain
omap_free_dma_chain
omap_dma_chain_a_transfer
omap_start_dma_chain_transfers
omap_stop_dma_chain_transfers
omap_get_dma_chain_index
omap_get_dma_chain_dst_pos
omap_get_dma_chain_src_pos
omap_modify_dma_chain_params
omap_dma_chain_status

Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/plat-omap/dma.c | 737 +----------------------------------------------
 include/linux/omap-dma.h |  37 ---
 2 files changed, 6 insertions(+), 768 deletions(-)

(limited to 'include')

diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index c2baa8ede543..24770e5a5081 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -64,7 +64,9 @@ enum { DMA_CHAIN_STARTED, DMA_CHAIN_NOTSTARTED };
 
 static struct omap_system_dma_plat_info *p;
 static struct omap_dma_dev_attr *d;
-
+static void omap_clear_dma(int lch);
+static int omap_dma_set_prio_lch(int lch, unsigned char read_prio,
+				 unsigned char write_prio);
 static int enable_1510_mode;
 static u32 errata;
 
@@ -284,66 +286,6 @@ void omap_set_dma_transfer_params(int lch, int data_type, int elem_count,
 }
 EXPORT_SYMBOL(omap_set_dma_transfer_params);
 
-void omap_set_dma_color_mode(int lch, enum omap_dma_color_mode mode, u32 color)
-{
-	BUG_ON(omap_dma_in_1510_mode());
-
-	if (dma_omap1()) {
-		u16 w;
-
-		w = p->dma_read(CCR2, lch);
-		w &= ~0x03;
-
-		switch (mode) {
-		case OMAP_DMA_CONSTANT_FILL:
-			w |= 0x01;
-			break;
-		case OMAP_DMA_TRANSPARENT_COPY:
-			w |= 0x02;
-			break;
-		case OMAP_DMA_COLOR_DIS:
-			break;
-		default:
-			BUG();
-		}
-		p->dma_write(w, CCR2, lch);
-
-		w = p->dma_read(LCH_CTRL, lch);
-		w &= ~0x0f;
-		/* Default is channel type 2D */
-		if (mode) {
-			p->dma_write(color, COLOR, lch);
-			w |= 1;		/* Channel type G */
-		}
-		p->dma_write(w, LCH_CTRL, lch);
-	}
-
-	if (dma_omap2plus()) {
-		u32 val;
-
-		val = p->dma_read(CCR, lch);
-		val &= ~((1 << 17) | (1 << 16));
-
-		switch (mode) {
-		case OMAP_DMA_CONSTANT_FILL:
-			val |= 1 << 16;
-			break;
-		case OMAP_DMA_TRANSPARENT_COPY:
-			val |= 1 << 17;
-			break;
-		case OMAP_DMA_COLOR_DIS:
-			break;
-		default:
-			BUG();
-		}
-		p->dma_write(val, CCR, lch);
-
-		color &= 0xffffff;
-		p->dma_write(color, COLOR, lch);
-	}
-}
-EXPORT_SYMBOL(omap_set_dma_color_mode);
-
 void omap_set_dma_write_mode(int lch, enum omap_dma_write_mode mode)
 {
 	if (dma_omap2plus()) {
@@ -417,16 +359,6 @@ void omap_set_dma_params(int lch, struct omap_dma_channel_params *params)
 }
 EXPORT_SYMBOL(omap_set_dma_params);
 
-void omap_set_dma_src_index(int lch, int eidx, int fidx)
-{
-	if (dma_omap2plus())
-		return;
-
-	p->dma_write(eidx, CSEI, lch);
-	p->dma_write(fidx, CSFI, lch);
-}
-EXPORT_SYMBOL(omap_set_dma_src_index);
-
 void omap_set_dma_src_data_pack(int lch, int enable)
 {
 	u32 l;
@@ -510,16 +442,6 @@ void omap_set_dma_dest_params(int lch, int dest_port, int dest_amode,
 }
 EXPORT_SYMBOL(omap_set_dma_dest_params);
 
-void omap_set_dma_dest_index(int lch, int eidx, int fidx)
-{
-	if (dma_omap2plus())
-		return;
-
-	p->dma_write(eidx, CDEI, lch);
-	p->dma_write(fidx, CDFI, lch);
-}
-EXPORT_SYMBOL(omap_set_dma_dest_index);
-
 void omap_set_dma_dest_data_pack(int lch, int enable)
 {
 	u32 l;
@@ -843,7 +765,7 @@ EXPORT_SYMBOL(omap_dma_set_global_params);
  * Both of the above can be set with one of the following values :
  * 	DMA_CH_PRIO_HIGH/DMA_CH_PRIO_LOW
  */
-int
+static int
 omap_dma_set_prio_lch(int lch, unsigned char read_prio,
 		      unsigned char write_prio)
 {
@@ -864,13 +786,13 @@ omap_dma_set_prio_lch(int lch, unsigned char read_prio,
 
 	return 0;
 }
-EXPORT_SYMBOL(omap_dma_set_prio_lch);
+
 
 /*
  * Clears any DMA state so the DMA engine is ready to restart with new buffers
  * through omap_start_dma(). Any buffers in flight are discarded.
  */
-void omap_clear_dma(int lch)
+static void omap_clear_dma(int lch)
 {
 	unsigned long flags;
 
@@ -878,7 +800,6 @@ void omap_clear_dma(int lch)
 	p->clear_dma(lch);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL(omap_clear_dma);
 
 void omap_start_dma(int lch)
 {
@@ -1167,652 +1088,6 @@ void omap_dma_link_lch(int lch_head, int lch_queue)
 }
 EXPORT_SYMBOL(omap_dma_link_lch);
 
-/*
- * Once the DMA queue is stopped, we can destroy it.
- */
-void omap_dma_unlink_lch(int lch_head, int lch_queue)
-{
-	if (omap_dma_in_1510_mode()) {
-		if (lch_head == lch_queue) {
-			p->dma_write(p->dma_read(CCR, lch_head) & ~(3 << 8),
-								CCR, lch_head);
-			return;
-		}
-		printk(KERN_ERR "DMA linking is not supported in 1510 mode\n");
-		BUG();
-		return;
-	}
-
-	if (dma_chan[lch_head].next_lch != lch_queue ||
-	    dma_chan[lch_head].next_lch == -1) {
-		pr_err("omap_dma: trying to unlink non linked channels\n");
-		dump_stack();
-	}
-
-	if ((dma_chan[lch_head].flags & OMAP_DMA_ACTIVE) ||
-	    (dma_chan[lch_queue].flags & OMAP_DMA_ACTIVE)) {
-		pr_err("omap_dma: You need to stop the DMA channels before unlinking\n");
-		dump_stack();
-	}
-
-	dma_chan[lch_head].next_lch = -1;
-}
-EXPORT_SYMBOL(omap_dma_unlink_lch);
-
-#ifndef CONFIG_ARCH_OMAP1
-/* Create chain of DMA channesls */
-static void create_dma_lch_chain(int lch_head, int lch_queue)
-{
-	u32 l;
-
-	/* Check if this is the first link in chain */
-	if (dma_chan[lch_head].next_linked_ch == -1) {
-		dma_chan[lch_head].next_linked_ch = lch_queue;
-		dma_chan[lch_head].prev_linked_ch = lch_queue;
-		dma_chan[lch_queue].next_linked_ch = lch_head;
-		dma_chan[lch_queue].prev_linked_ch = lch_head;
-	}
-
-	/* a link exists, link the new channel in circular chain */
-	else {
-		dma_chan[lch_queue].next_linked_ch =
-					dma_chan[lch_head].next_linked_ch;
-		dma_chan[lch_queue].prev_linked_ch = lch_head;
-		dma_chan[lch_head].next_linked_ch = lch_queue;
-		dma_chan[dma_chan[lch_queue].next_linked_ch].prev_linked_ch =
-					lch_queue;
-	}
-
-	l = p->dma_read(CLNK_CTRL, lch_head);
-	l &= ~(0x1f);
-	l |= lch_queue;
-	p->dma_write(l, CLNK_CTRL, lch_head);
-
-	l = p->dma_read(CLNK_CTRL, lch_queue);
-	l &= ~(0x1f);
-	l |= (dma_chan[lch_queue].next_linked_ch);
-	p->dma_write(l, CLNK_CTRL, lch_queue);
-}
-
-/**
- * @brief omap_request_dma_chain : Request a chain of DMA channels
- *
- * @param dev_id - Device id using the dma channel
- * @param dev_name - Device name
- * @param callback - Call back function
- * @chain_id -
- * @no_of_chans - Number of channels requested
- * @chain_mode - Dynamic or static chaining : OMAP_DMA_STATIC_CHAIN
- * 					      OMAP_DMA_DYNAMIC_CHAIN
- * @params - Channel parameters
- *
- * @return - Success : 0
- * 	     Failure: -EINVAL/-ENOMEM
- */
-int omap_request_dma_chain(int dev_id, const char *dev_name,
-			   void (*callback) (int lch, u16 ch_status,
-					     void *data),
-			   int *chain_id, int no_of_chans, int chain_mode,
-			   struct omap_dma_channel_params params)
-{
-	int *channels;
-	int i, err;
-
-	/* Is the chain mode valid ? */
-	if (chain_mode != OMAP_DMA_STATIC_CHAIN
-			&& chain_mode != OMAP_DMA_DYNAMIC_CHAIN) {
-		printk(KERN_ERR "Invalid chain mode requested\n");
-		return -EINVAL;
-	}
-
-	if (unlikely((no_of_chans < 1
-			|| no_of_chans > dma_lch_count))) {
-		printk(KERN_ERR "Invalid Number of channels requested\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * Allocate a queue to maintain the status of the channels
-	 * in the chain
-	 */
-	channels = kmalloc(sizeof(*channels) * no_of_chans, GFP_KERNEL);
-	if (channels == NULL) {
-		printk(KERN_ERR "omap_dma: No memory for channel queue\n");
-		return -ENOMEM;
-	}
-
-	/* request and reserve DMA channels for the chain */
-	for (i = 0; i < no_of_chans; i++) {
-		err = omap_request_dma(dev_id, dev_name,
-					callback, NULL, &channels[i]);
-		if (err < 0) {
-			int j;
-			for (j = 0; j < i; j++)
-				omap_free_dma(channels[j]);
-			kfree(channels);
-			printk(KERN_ERR "omap_dma: Request failed %d\n", err);
-			return err;
-		}
-		dma_chan[channels[i]].prev_linked_ch = -1;
-		dma_chan[channels[i]].state = DMA_CH_NOTSTARTED;
-
-		/*
-		 * Allowing client drivers to set common parameters now,
-		 * so that later only relevant (src_start, dest_start
-		 * and element count) can be set
-		 */
-		omap_set_dma_params(channels[i], &params);
-	}
-
-	*chain_id = channels[0];
-	dma_linked_lch[*chain_id].linked_dmach_q = channels;
-	dma_linked_lch[*chain_id].chain_mode = chain_mode;
-	dma_linked_lch[*chain_id].chain_state = DMA_CHAIN_NOTSTARTED;
-	dma_linked_lch[*chain_id].no_of_lchs_linked = no_of_chans;
-
-	for (i = 0; i < no_of_chans; i++)
-		dma_chan[channels[i]].chain_id = *chain_id;
-
-	/* Reset the Queue pointers */
-	OMAP_DMA_CHAIN_QINIT(*chain_id);
-
-	/* Set up the chain */
-	if (no_of_chans == 1)
-		create_dma_lch_chain(channels[0], channels[0]);
-	else {
-		for (i = 0; i < (no_of_chans - 1); i++)
-			create_dma_lch_chain(channels[i], channels[i + 1]);
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(omap_request_dma_chain);
-
-/**
- * @brief omap_modify_dma_chain_param : Modify the chain's params - Modify the
- * params after setting it. Dont do this while dma is running!!
- *
- * @param chain_id - Chained logical channel id.
- * @param params
- *
- * @return - Success : 0
- * 	     Failure : -EINVAL
- */
-int omap_modify_dma_chain_params(int chain_id,
-				struct omap_dma_channel_params params)
-{
-	int *channels;
-	u32 i;
-
-	/* Check for input params */
-	if (unlikely((chain_id < 0
-			|| chain_id >= dma_lch_count))) {
-		printk(KERN_ERR "Invalid chain id\n");
-		return -EINVAL;
-	}
-
-	/* Check if the chain exists */
-	if (dma_linked_lch[chain_id].linked_dmach_q == NULL) {
-		printk(KERN_ERR "Chain doesn't exists\n");
-		return -EINVAL;
-	}
-	channels = dma_linked_lch[chain_id].linked_dmach_q;
-
-	for (i = 0; i < dma_linked_lch[chain_id].no_of_lchs_linked; i++) {
-		/*
-		 * Allowing client drivers to set common parameters now,
-		 * so that later only relevant (src_start, dest_start
-		 * and element count) can be set
-		 */
-		omap_set_dma_params(channels[i], &params);
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(omap_modify_dma_chain_params);
-
-/**
- * @brief omap_free_dma_chain - Free all the logical channels in a chain.
- *
- * @param chain_id
- *
- * @return - Success : 0
- * 	     Failure : -EINVAL
- */
-int omap_free_dma_chain(int chain_id)
-{
-	int *channels;
-	u32 i;
-
-	/* Check for input params */
-	if (unlikely((chain_id < 0 || chain_id >= dma_lch_count))) {
-		printk(KERN_ERR "Invalid chain id\n");
-		return -EINVAL;
-	}
-
-	/* Check if the chain exists */
-	if (dma_linked_lch[chain_id].linked_dmach_q == NULL) {
-		printk(KERN_ERR "Chain doesn't exists\n");
-		return -EINVAL;
-	}
-
-	channels = dma_linked_lch[chain_id].linked_dmach_q;
-	for (i = 0; i < dma_linked_lch[chain_id].no_of_lchs_linked; i++) {
-		dma_chan[channels[i]].next_linked_ch = -1;
-		dma_chan[channels[i]].prev_linked_ch = -1;
-		dma_chan[channels[i]].chain_id = -1;
-		dma_chan[channels[i]].state = DMA_CH_NOTSTARTED;
-		omap_free_dma(channels[i]);
-	}
-
-	kfree(channels);
-
-	dma_linked_lch[chain_id].linked_dmach_q = NULL;
-	dma_linked_lch[chain_id].chain_mode = -1;
-	dma_linked_lch[chain_id].chain_state = -1;
-
-	return (0);
-}
-EXPORT_SYMBOL(omap_free_dma_chain);
-
-/**
- * @brief omap_dma_chain_status - Check if the chain is in
- * active / inactive state.
- * @param chain_id
- *
- * @return - Success : OMAP_DMA_CHAIN_ACTIVE/OMAP_DMA_CHAIN_INACTIVE
- * 	     Failure : -EINVAL
- */
-int omap_dma_chain_status(int chain_id)
-{
-	/* Check for input params */
-	if (unlikely((chain_id < 0 || chain_id >= dma_lch_count))) {
-		printk(KERN_ERR "Invalid chain id\n");
-		return -EINVAL;
-	}
-
-	/* Check if the chain exists */
-	if (dma_linked_lch[chain_id].linked_dmach_q == NULL) {
-		printk(KERN_ERR "Chain doesn't exists\n");
-		return -EINVAL;
-	}
-	pr_debug("CHAINID=%d, qcnt=%d\n", chain_id,
-			dma_linked_lch[chain_id].q_count);
-
-	if (OMAP_DMA_CHAIN_QEMPTY(chain_id))
-		return OMAP_DMA_CHAIN_INACTIVE;
-
-	return OMAP_DMA_CHAIN_ACTIVE;
-}
-EXPORT_SYMBOL(omap_dma_chain_status);
-
-/**
- * @brief omap_dma_chain_a_transfer - Get a free channel from a chain,
- * set the params and start the transfer.
- *
- * @param chain_id
- * @param src_start - buffer start address
- * @param dest_start - Dest address
- * @param elem_count
- * @param frame_count
- * @param callbk_data - channel callback parameter data.
- *
- * @return  - Success : 0
- * 	      Failure: -EINVAL/-EBUSY
- */
-int omap_dma_chain_a_transfer(int chain_id, int src_start, int dest_start,
-			int elem_count, int frame_count, void *callbk_data)
-{
-	int *channels;
-	u32 l, lch;
-	int start_dma = 0;
-
-	/*
-	 * if buffer size is less than 1 then there is
-	 * no use of starting the chain
-	 */
-	if (elem_count < 1) {
-		printk(KERN_ERR "Invalid buffer size\n");
-		return -EINVAL;
-	}
-
-	/* Check for input params */
-	if (unlikely((chain_id < 0
-			|| chain_id >= dma_lch_count))) {
-		printk(KERN_ERR "Invalid chain id\n");
-		return -EINVAL;
-	}
-
-	/* Check if the chain exists */
-	if (dma_linked_lch[chain_id].linked_dmach_q == NULL) {
-		printk(KERN_ERR "Chain doesn't exist\n");
-		return -EINVAL;
-	}
-
-	/* Check if all the channels in chain are in use */
-	if (OMAP_DMA_CHAIN_QFULL(chain_id))
-		return -EBUSY;
-
-	/* Frame count may be negative in case of indexed transfers */
-	channels = dma_linked_lch[chain_id].linked_dmach_q;
-
-	/* Get a free channel */
-	lch = channels[dma_linked_lch[chain_id].q_tail];
-
-	/* Store the callback data */
-	dma_chan[lch].data = callbk_data;
-
-	/* Increment the q_tail */
-	OMAP_DMA_CHAIN_INCQTAIL(chain_id);
-
-	/* Set the params to the free channel */
-	if (src_start != 0)
-		p->dma_write(src_start, CSSA, lch);
-	if (dest_start != 0)
-		p->dma_write(dest_start, CDSA, lch);
-
-	/* Write the buffer size */
-	p->dma_write(elem_count, CEN, lch);
-	p->dma_write(frame_count, CFN, lch);
-
-	/*
-	 * If the chain is dynamically linked,
-	 * then we may have to start the chain if its not active
-	 */
-	if (dma_linked_lch[chain_id].chain_mode == OMAP_DMA_DYNAMIC_CHAIN) {
-
-		/*
-		 * In Dynamic chain, if the chain is not started,
-		 * queue the channel
-		 */
-		if (dma_linked_lch[chain_id].chain_state ==
-						DMA_CHAIN_NOTSTARTED) {
-			/* Enable the link in previous channel */
-			if (dma_chan[dma_chan[lch].prev_linked_ch].state ==
-								DMA_CH_QUEUED)
-				enable_lnk(dma_chan[lch].prev_linked_ch);
-			dma_chan[lch].state = DMA_CH_QUEUED;
-		}
-
-		/*
-		 * Chain is already started, make sure its active,
-		 * if not then start the chain
-		 */
-		else {
-			start_dma = 1;
-
-			if (dma_chan[dma_chan[lch].prev_linked_ch].state ==
-							DMA_CH_STARTED) {
-				enable_lnk(dma_chan[lch].prev_linked_ch);
-				dma_chan[lch].state = DMA_CH_QUEUED;
-				start_dma = 0;
-				if (0 == ((1 << 7) & p->dma_read(
-					CCR, dma_chan[lch].prev_linked_ch))) {
-					disable_lnk(dma_chan[lch].
-						    prev_linked_ch);
-					pr_debug("\n prev ch is stopped\n");
-					start_dma = 1;
-				}
-			}
-
-			else if (dma_chan[dma_chan[lch].prev_linked_ch].state
-							== DMA_CH_QUEUED) {
-				enable_lnk(dma_chan[lch].prev_linked_ch);
-				dma_chan[lch].state = DMA_CH_QUEUED;
-				start_dma = 0;
-			}
-			omap_enable_channel_irq(lch);
-
-			l = p->dma_read(CCR, lch);
-
-			if ((0 == (l & (1 << 24))))
-				l &= ~(1 << 25);
-			else
-				l |= (1 << 25);
-			if (start_dma == 1) {
-				if (0 == (l & (1 << 7))) {
-					l |= (1 << 7);
-					dma_chan[lch].state = DMA_CH_STARTED;
-					pr_debug("starting %d\n", lch);
-					p->dma_write(l, CCR, lch);
-				} else
-					start_dma = 0;
-			} else {
-				if (0 == (l & (1 << 7)))
-					p->dma_write(l, CCR, lch);
-			}
-			dma_chan[lch].flags |= OMAP_DMA_ACTIVE;
-		}
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(omap_dma_chain_a_transfer);
-
-/**
- * @brief omap_start_dma_chain_transfers - Start the chain
- *
- * @param chain_id
- *
- * @return - Success : 0
- * 	     Failure : -EINVAL/-EBUSY
- */
-int omap_start_dma_chain_transfers(int chain_id)
-{
-	int *channels;
-	u32 l, i;
-
-	if (unlikely((chain_id < 0 || chain_id >= dma_lch_count))) {
-		printk(KERN_ERR "Invalid chain id\n");
-		return -EINVAL;
-	}
-
-	channels = dma_linked_lch[chain_id].linked_dmach_q;
-
-	if (dma_linked_lch[channels[0]].chain_state == DMA_CHAIN_STARTED) {
-		printk(KERN_ERR "Chain is already started\n");
-		return -EBUSY;
-	}
-
-	if (dma_linked_lch[chain_id].chain_mode == OMAP_DMA_STATIC_CHAIN) {
-		for (i = 0; i < dma_linked_lch[chain_id].no_of_lchs_linked;
-									i++) {
-			enable_lnk(channels[i]);
-			omap_enable_channel_irq(channels[i]);
-		}
-	} else {
-		omap_enable_channel_irq(channels[0]);
-	}
-
-	l = p->dma_read(CCR, channels[0]);
-	l |= (1 << 7);
-	dma_linked_lch[chain_id].chain_state = DMA_CHAIN_STARTED;
-	dma_chan[channels[0]].state = DMA_CH_STARTED;
-
-	if ((0 == (l & (1 << 24))))
-		l &= ~(1 << 25);
-	else
-		l |= (1 << 25);
-	p->dma_write(l, CCR, channels[0]);
-
-	dma_chan[channels[0]].flags |= OMAP_DMA_ACTIVE;
-
-	return 0;
-}
-EXPORT_SYMBOL(omap_start_dma_chain_transfers);
-
-/**
- * @brief omap_stop_dma_chain_transfers - Stop the dma transfer of a chain.
- *
- * @param chain_id
- *
- * @return - Success : 0
- * 	     Failure : EINVAL
- */
-int omap_stop_dma_chain_transfers(int chain_id)
-{
-	int *channels;
-	u32 l, i;
-	u32 sys_cf = 0;
-
-	/* Check for input params */
-	if (unlikely((chain_id < 0 || chain_id >= dma_lch_count))) {
-		printk(KERN_ERR "Invalid chain id\n");
-		return -EINVAL;
-	}
-
-	/* Check if the chain exists */
-	if (dma_linked_lch[chain_id].linked_dmach_q == NULL) {
-		printk(KERN_ERR "Chain doesn't exists\n");
-		return -EINVAL;
-	}
-	channels = dma_linked_lch[chain_id].linked_dmach_q;
-
-	if (IS_DMA_ERRATA(DMA_ERRATA_i88)) {
-		sys_cf = p->dma_read(OCP_SYSCONFIG, 0);
-		l = sys_cf;
-		/* Middle mode reg set no Standby */
-		l &= ~((1 << 12)|(1 << 13));
-		p->dma_write(l, OCP_SYSCONFIG, 0);
-	}
-
-	for (i = 0; i < dma_linked_lch[chain_id].no_of_lchs_linked; i++) {
-
-		/* Stop the Channel transmission */
-		l = p->dma_read(CCR, channels[i]);
-		l &= ~(1 << 7);
-		p->dma_write(l, CCR, channels[i]);
-
-		/* Disable the link in all the channels */
-		disable_lnk(channels[i]);
-		dma_chan[channels[i]].state = DMA_CH_NOTSTARTED;
-
-	}
-	dma_linked_lch[chain_id].chain_state = DMA_CHAIN_NOTSTARTED;
-
-	/* Reset the Queue pointers */
-	OMAP_DMA_CHAIN_QINIT(chain_id);
-
-	if (IS_DMA_ERRATA(DMA_ERRATA_i88))
-		p->dma_write(sys_cf, OCP_SYSCONFIG, 0);
-
-	return 0;
-}
-EXPORT_SYMBOL(omap_stop_dma_chain_transfers);
-
-/* Get the index of the ongoing DMA in chain */
-/**
- * @brief omap_get_dma_chain_index - Get the element and frame index
- * of the ongoing DMA in chain
- *
- * @param chain_id
- * @param ei - Element index
- * @param fi - Frame index
- *
- * @return - Success : 0
- * 	     Failure : -EINVAL
- */
-int omap_get_dma_chain_index(int chain_id, int *ei, int *fi)
-{
-	int lch;
-	int *channels;
-
-	/* Check for input params */
-	if (unlikely((chain_id < 0 || chain_id >= dma_lch_count))) {
-		printk(KERN_ERR "Invalid chain id\n");
-		return -EINVAL;
-	}
-
-	/* Check if the chain exists */
-	if (dma_linked_lch[chain_id].linked_dmach_q == NULL) {
-		printk(KERN_ERR "Chain doesn't exists\n");
-		return -EINVAL;
-	}
-	if ((!ei) || (!fi))
-		return -EINVAL;
-
-	channels = dma_linked_lch[chain_id].linked_dmach_q;
-
-	/* Get the current channel */
-	lch = channels[dma_linked_lch[chain_id].q_head];
-
-	*ei = p->dma_read(CCEN, lch);
-	*fi = p->dma_read(CCFN, lch);
-
-	return 0;
-}
-EXPORT_SYMBOL(omap_get_dma_chain_index);
-
-/**
- * @brief omap_get_dma_chain_dst_pos - Get the destination position of the
- * ongoing DMA in chain
- *
- * @param chain_id
- *
- * @return - Success : Destination position
- * 	     Failure : -EINVAL
- */
-int omap_get_dma_chain_dst_pos(int chain_id)
-{
-	int lch;
-	int *channels;
-
-	/* Check for input params */
-	if (unlikely((chain_id < 0 || chain_id >= dma_lch_count))) {
-		printk(KERN_ERR "Invalid chain id\n");
-		return -EINVAL;
-	}
-
-	/* Check if the chain exists */
-	if (dma_linked_lch[chain_id].linked_dmach_q == NULL) {
-		printk(KERN_ERR "Chain doesn't exists\n");
-		return -EINVAL;
-	}
-
-	channels = dma_linked_lch[chain_id].linked_dmach_q;
-
-	/* Get the current channel */
-	lch = channels[dma_linked_lch[chain_id].q_head];
-
-	return p->dma_read(CDAC, lch);
-}
-EXPORT_SYMBOL(omap_get_dma_chain_dst_pos);
-
-/**
- * @brief omap_get_dma_chain_src_pos - Get the source position
- * of the ongoing DMA in chain
- * @param chain_id
- *
- * @return - Success : Destination position
- * 	     Failure : -EINVAL
- */
-int omap_get_dma_chain_src_pos(int chain_id)
-{
-	int lch;
-	int *channels;
-
-	/* Check for input params */
-	if (unlikely((chain_id < 0 || chain_id >= dma_lch_count))) {
-		printk(KERN_ERR "Invalid chain id\n");
-		return -EINVAL;
-	}
-
-	/* Check if the chain exists */
-	if (dma_linked_lch[chain_id].linked_dmach_q == NULL) {
-		printk(KERN_ERR "Chain doesn't exists\n");
-		return -EINVAL;
-	}
-
-	channels = dma_linked_lch[chain_id].linked_dmach_q;
-
-	/* Get the current channel */
-	lch = channels[dma_linked_lch[chain_id].q_head];
-
-	return p->dma_read(CSAC, lch);
-}
-EXPORT_SYMBOL(omap_get_dma_chain_src_pos);
-#endif	/* ifndef CONFIG_ARCH_OMAP1 */
-
 /*----------------------------------------------------------------------------*/
 
 #ifdef CONFIG_ARCH_OMAP1
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 6f06f8bc612c..e5a70132a240 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -306,15 +306,12 @@ extern void omap_set_dma_transfer_params(int lch, int data_type,
 					 int elem_count, int frame_count,
 					 int sync_mode,
 					 int dma_trigger, int src_or_dst_synch);
-extern void omap_set_dma_color_mode(int lch, enum omap_dma_color_mode mode,
-				    u32 color);
 extern void omap_set_dma_write_mode(int lch, enum omap_dma_write_mode mode);
 extern void omap_set_dma_channel_mode(int lch, enum omap_dma_channel_mode mode);
 
 extern void omap_set_dma_src_params(int lch, int src_port, int src_amode,
 				    unsigned long src_start,
 				    int src_ei, int src_fi);
-extern void omap_set_dma_src_index(int lch, int eidx, int fidx);
 extern void omap_set_dma_src_data_pack(int lch, int enable);
 extern void omap_set_dma_src_burst_mode(int lch,
 					enum omap_dma_burst_mode burst_mode);
@@ -322,7 +319,6 @@ extern void omap_set_dma_src_burst_mode(int lch,
 extern void omap_set_dma_dest_params(int lch, int dest_port, int dest_amode,
 				     unsigned long dest_start,
 				     int dst_ei, int dst_fi);
-extern void omap_set_dma_dest_index(int lch, int eidx, int fidx);
 extern void omap_set_dma_dest_data_pack(int lch, int enable);
 extern void omap_set_dma_dest_burst_mode(int lch,
 					 enum omap_dma_burst_mode burst_mode);
@@ -331,52 +327,19 @@ extern void omap_set_dma_params(int lch,
 				struct omap_dma_channel_params *params);
 
 extern void omap_dma_link_lch(int lch_head, int lch_queue);
-extern void omap_dma_unlink_lch(int lch_head, int lch_queue);
 
 extern int omap_set_dma_callback(int lch,
 			void (*callback)(int lch, u16 ch_status, void *data),
 			void *data);
 extern dma_addr_t omap_get_dma_src_pos(int lch);
 extern dma_addr_t omap_get_dma_dst_pos(int lch);
-extern void omap_clear_dma(int lch);
 extern int omap_get_dma_active_status(int lch);
 extern int omap_dma_running(void);
 extern void omap_dma_set_global_params(int arb_rate, int max_fifo_depth,
 				       int tparams);
-extern int omap_dma_set_prio_lch(int lch, unsigned char read_prio,
-				 unsigned char write_prio);
-extern void omap_set_dma_dst_endian_type(int lch, enum end_type etype);
-extern void omap_set_dma_src_endian_type(int lch, enum end_type etype);
-extern int omap_get_dma_index(int lch, int *ei, int *fi);
-
 void omap_dma_global_context_save(void);
 void omap_dma_global_context_restore(void);
 
-extern void omap_dma_disable_irq(int lch);
-
-/* Chaining APIs */
-#ifndef CONFIG_ARCH_OMAP1
-extern int omap_request_dma_chain(int dev_id, const char *dev_name,
-				  void (*callback) (int lch, u16 ch_status,
-						    void *data),
-				  int *chain_id, int no_of_chans,
-				  int chain_mode,
-				  struct omap_dma_channel_params params);
-extern int omap_free_dma_chain(int chain_id);
-extern int omap_dma_chain_a_transfer(int chain_id, int src_start,
-				     int dest_start, int elem_count,
-				     int frame_count, void *callbk_data);
-extern int omap_start_dma_chain_transfers(int chain_id);
-extern int omap_stop_dma_chain_transfers(int chain_id);
-extern int omap_get_dma_chain_index(int chain_id, int *ei, int *fi);
-extern int omap_get_dma_chain_dst_pos(int chain_id);
-extern int omap_get_dma_chain_src_pos(int chain_id);
-
-extern int omap_modify_dma_chain_params(int chain_id,
-					struct omap_dma_channel_params params);
-extern int omap_dma_chain_status(int chain_id);
-#endif
-
 #if defined(CONFIG_ARCH_OMAP1) && IS_ENABLED(CONFIG_FB_OMAP)
 #include <mach/lcd_dma.h>
 #else
-- 
cgit v1.2.3


From 971ff49355387fef41d1327434d8939721a4eb35 Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Thu, 18 Sep 2014 16:06:19 +0800
Subject: cgroup: use a per-cgroup work for release agent

Instead of using a global work to schedule release agent on removable
cgroups, we change to use a per-cgroup work to do this, which makes
the code much simpler.

v2: use a dedicated work instead of reusing css->destroy_work. (Tejun)

Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h |  10 ++---
 kernel/cgroup.c        | 108 +++++++++++++++----------------------------------
 2 files changed, 36 insertions(+), 82 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f7898e0bce1e..51958d0fb88f 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -233,13 +233,6 @@ struct cgroup {
 	 */
 	struct list_head e_csets[CGROUP_SUBSYS_COUNT];
 
-	/*
-	 * Linked list running through all cgroups that can
-	 * potentially be reaped by the release agent. Protected by
-	 * release_list_lock
-	 */
-	struct list_head release_list;
-
 	/*
 	 * list of pidlists, up to two for each namespace (one for procs, one
 	 * for tasks); created on demand.
@@ -249,6 +242,9 @@ struct cgroup {
 
 	/* used to wait for offlining of csses */
 	wait_queue_head_t offline_waitq;
+
+	/* used to schedule release agent */
+	struct work_struct release_agent_work;
 };
 
 #define MAX_CGROUP_ROOT_NAMELEN 64
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 4ddc75588983..db19a4884a7f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -392,12 +392,7 @@ static int notify_on_release(const struct cgroup *cgrp)
 			;						\
 		else
 
-/* the list of cgroups eligible for automatic release. Protected by
- * release_list_lock */
-static LIST_HEAD(release_list);
-static DEFINE_RAW_SPINLOCK(release_list_lock);
 static void cgroup_release_agent(struct work_struct *work);
-static DECLARE_WORK(release_agent_work, cgroup_release_agent);
 static void check_for_release(struct cgroup *cgrp);
 
 /*
@@ -1577,7 +1572,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->self.sibling);
 	INIT_LIST_HEAD(&cgrp->self.children);
 	INIT_LIST_HEAD(&cgrp->cset_links);
-	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
 	cgrp->self.cgroup = cgrp;
@@ -1587,6 +1581,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 		INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
 
 	init_waitqueue_head(&cgrp->offline_waitq);
+	INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent);
 }
 
 static void init_cgroup_root(struct cgroup_root *root,
@@ -4342,6 +4337,7 @@ static void css_free_work_fn(struct work_struct *work)
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
 		cgroup_pidlist_destroy_all(cgrp);
+		cancel_work_sync(&cgrp->release_agent_work);
 
 		if (cgroup_parent(cgrp)) {
 			/*
@@ -4804,12 +4800,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	for_each_css(css, ssid, cgrp)
 		kill_css(css);
 
-	/* CSS_ONLINE is clear, remove from ->release_list for the last time */
-	raw_spin_lock(&release_list_lock);
-	if (!list_empty(&cgrp->release_list))
-		list_del_init(&cgrp->release_list);
-	raw_spin_unlock(&release_list_lock);
-
 	/*
 	 * Remove @cgrp directory along with the base files.  @cgrp has an
 	 * extra ref on its kn.
@@ -5271,25 +5261,9 @@ void cgroup_exit(struct task_struct *tsk)
 
 static void check_for_release(struct cgroup *cgrp)
 {
-	if (cgroup_is_releasable(cgrp) && list_empty(&cgrp->cset_links) &&
-	    !css_has_online_children(&cgrp->self)) {
-		/*
-		 * Control Group is currently removeable. If it's not
-		 * already queued for a userspace notification, queue
-		 * it now
-		 */
-		int need_schedule_work = 0;
-
-		raw_spin_lock(&release_list_lock);
-		if (!cgroup_is_dead(cgrp) &&
-		    list_empty(&cgrp->release_list)) {
-			list_add(&cgrp->release_list, &release_list);
-			need_schedule_work = 1;
-		}
-		raw_spin_unlock(&release_list_lock);
-		if (need_schedule_work)
-			schedule_work(&release_agent_work);
-	}
+	if (cgroup_is_releasable(cgrp) && !cgroup_has_tasks(cgrp) &&
+	    !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp))
+		schedule_work(&cgrp->release_agent_work);
 }
 
 /*
@@ -5317,52 +5291,36 @@ static void check_for_release(struct cgroup *cgrp)
  */
 static void cgroup_release_agent(struct work_struct *work)
 {
-	BUG_ON(work != &release_agent_work);
+	struct cgroup *cgrp =
+		container_of(work, struct cgroup, release_agent_work);
+	char *pathbuf = NULL, *agentbuf = NULL, *path;
+	char *argv[3], *envp[3];
+
 	mutex_lock(&cgroup_mutex);
-	raw_spin_lock(&release_list_lock);
-	while (!list_empty(&release_list)) {
-		char *argv[3], *envp[3];
-		int i;
-		char *pathbuf = NULL, *agentbuf = NULL, *path;
-		struct cgroup *cgrp = list_entry(release_list.next,
-						    struct cgroup,
-						    release_list);
-		list_del_init(&cgrp->release_list);
-		raw_spin_unlock(&release_list_lock);
-		pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
-		if (!pathbuf)
-			goto continue_free;
-		path = cgroup_path(cgrp, pathbuf, PATH_MAX);
-		if (!path)
-			goto continue_free;
-		agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-		if (!agentbuf)
-			goto continue_free;
-
-		i = 0;
-		argv[i++] = agentbuf;
-		argv[i++] = path;
-		argv[i] = NULL;
-
-		i = 0;
-		/* minimal command environment */
-		envp[i++] = "HOME=/";
-		envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
-		envp[i] = NULL;
-
-		/* Drop the lock while we invoke the usermode helper,
-		 * since the exec could involve hitting disk and hence
-		 * be a slow process */
-		mutex_unlock(&cgroup_mutex);
-		call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
-		mutex_lock(&cgroup_mutex);
- continue_free:
-		kfree(pathbuf);
-		kfree(agentbuf);
-		raw_spin_lock(&release_list_lock);
-	}
-	raw_spin_unlock(&release_list_lock);
+
+	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
+	if (!pathbuf || !agentbuf)
+		goto out;
+
+	path = cgroup_path(cgrp, pathbuf, PATH_MAX);
+	if (!path)
+		goto out;
+
+	argv[0] = agentbuf;
+	argv[1] = path;
+	argv[2] = NULL;
+
+	/* minimal command environment */
+	envp[0] = "HOME=/";
+	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+	envp[2] = NULL;
+
 	mutex_unlock(&cgroup_mutex);
+	call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+out:
+	kfree(agentbuf);
+	kfree(pathbuf);
 }
 
 static int __init cgroup_disable(char *str)
-- 
cgit v1.2.3


From 006f4ac49742b5f70ef7e39176fd42a500144ccc Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Thu, 18 Sep 2014 16:03:15 +0800
Subject: cgroup: simplify proc_cgroup_show()

Use the ONE macro instead of REG, and we can simplify proc_cgroup_show().

Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 fs/proc/base.c         | 19 ++-----------------
 include/linux/cgroup.h |  3 ++-
 kernel/cgroup.c        | 18 +++---------------
 3 files changed, 7 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index baf852b648ad..6b96892015ec 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -376,21 +376,6 @@ static const struct file_operations proc_lstats_operations = {
 
 #endif
 
-#ifdef CONFIG_CGROUPS
-static int cgroup_open(struct inode *inode, struct file *file)
-{
-	struct pid *pid = PROC_I(inode)->pid;
-	return single_open(file, proc_cgroup_show, pid);
-}
-
-static const struct file_operations proc_cgroup_operations = {
-	.open		= cgroup_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
 #ifdef CONFIG_PROC_PID_CPUSET
 
 static int cpuset_open(struct inode *inode, struct file *file)
@@ -2576,7 +2561,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("cpuset",     S_IRUGO, proc_cpuset_operations),
 #endif
 #ifdef CONFIG_CGROUPS
-	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
+	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
 #endif
 	ONE("oom_score",  S_IRUGO, proc_oom_score),
 	REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adj_operations),
@@ -2922,7 +2907,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("cpuset",    S_IRUGO, proc_cpuset_operations),
 #endif
 #ifdef CONFIG_CGROUPS
-	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
+	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
 #endif
 	ONE("oom_score", S_IRUGO, proc_oom_score),
 	REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adj_operations),
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 51958d0fb88f..77a1d37b742b 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -37,7 +37,8 @@ extern void cgroup_exit(struct task_struct *p);
 extern int cgroupstats_build(struct cgroupstats *stats,
 				struct dentry *dentry);
 
-extern int proc_cgroup_show(struct seq_file *, void *);
+extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *tsk);
 
 /* define the enumeration of all cgroup subsystems */
 #define SUBSYS(_x) _x ## _cgrp_id,
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index db19a4884a7f..df7733b48d2e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -5030,12 +5030,9 @@ core_initcall(cgroup_wq_init);
  *  - Print task's cgroup paths into seq_file, one line for each hierarchy
  *  - Used for /proc/<pid>/cgroup.
  */
-
-/* TODO: Use a proper seq_file iterator */
-int proc_cgroup_show(struct seq_file *m, void *v)
+int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk)
 {
-	struct pid *pid;
-	struct task_struct *tsk;
 	char *buf, *path;
 	int retval;
 	struct cgroup_root *root;
@@ -5045,14 +5042,6 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 	if (!buf)
 		goto out;
 
-	retval = -ESRCH;
-	pid = m->private;
-	tsk = get_pid_task(pid, PIDTYPE_PID);
-	if (!tsk)
-		goto out_free;
-
-	retval = 0;
-
 	mutex_lock(&cgroup_mutex);
 	down_read(&css_set_rwsem);
 
@@ -5082,11 +5071,10 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 		seq_putc(m, '\n');
 	}
 
+	retval = 0;
 out_unlock:
 	up_read(&css_set_rwsem);
 	mutex_unlock(&cgroup_mutex);
-	put_task_struct(tsk);
-out_free:
 	kfree(buf);
 out:
 	return retval;
-- 
cgit v1.2.3


From 52de4779f201758ddcf37360f09a16895756e708 Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Thu, 18 Sep 2014 16:03:36 +0800
Subject: cpuset: simplify proc_cpuset_show()

Use the ONE macro instead of REG, and we can simplify proc_cpuset_show().

Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 fs/proc/base.c         | 20 ++------------------
 include/linux/cpuset.h |  3 ++-
 kernel/cpuset.c        | 15 +++------------
 3 files changed, 7 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 6b96892015ec..4e8aa35fc3eb 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -376,22 +376,6 @@ static const struct file_operations proc_lstats_operations = {
 
 #endif
 
-#ifdef CONFIG_PROC_PID_CPUSET
-
-static int cpuset_open(struct inode *inode, struct file *file)
-{
-	struct pid *pid = PROC_I(inode)->pid;
-	return single_open(file, proc_cpuset_show, pid);
-}
-
-static const struct file_operations proc_cpuset_operations = {
-	.open		= cpuset_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
 static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
 			  struct pid *pid, struct task_struct *task)
 {
@@ -2558,7 +2542,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("latency",  S_IRUGO, proc_lstats_operations),
 #endif
 #ifdef CONFIG_PROC_PID_CPUSET
-	REG("cpuset",     S_IRUGO, proc_cpuset_operations),
+	ONE("cpuset",     S_IRUGO, proc_cpuset_show),
 #endif
 #ifdef CONFIG_CGROUPS
 	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
@@ -2904,7 +2888,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("latency",  S_IRUGO, proc_lstats_operations),
 #endif
 #ifdef CONFIG_PROC_PID_CPUSET
-	REG("cpuset",    S_IRUGO, proc_cpuset_operations),
+	ONE("cpuset",    S_IRUGO, proc_cpuset_show),
 #endif
 #ifdef CONFIG_CGROUPS
 	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index ade2390ffe92..0d4e0675b318 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -86,7 +86,8 @@ extern void __cpuset_memory_pressure_bump(void);
 
 extern void cpuset_task_status_allowed(struct seq_file *m,
 					struct task_struct *task);
-extern int proc_cpuset_show(struct seq_file *, void *);
+extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *tsk);
 
 extern int cpuset_mem_spread_node(void);
 extern int cpuset_slab_spread_node(void);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 22874d7cf2c0..a37f4ed24867 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2729,10 +2729,9 @@ void __cpuset_memory_pressure_bump(void)
  *    and we take cpuset_mutex, keeping cpuset_attach() from changing it
  *    anyway.
  */
-int proc_cpuset_show(struct seq_file *m, void *unused_v)
+int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk)
 {
-	struct pid *pid;
-	struct task_struct *tsk;
 	char *buf, *p;
 	struct cgroup_subsys_state *css;
 	int retval;
@@ -2742,24 +2741,16 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v)
 	if (!buf)
 		goto out;
 
-	retval = -ESRCH;
-	pid = m->private;
-	tsk = get_pid_task(pid, PIDTYPE_PID);
-	if (!tsk)
-		goto out_free;
-
 	retval = -ENAMETOOLONG;
 	rcu_read_lock();
 	css = task_css(tsk, cpuset_cgrp_id);
 	p = cgroup_path(css->cgroup, buf, PATH_MAX);
 	rcu_read_unlock();
 	if (!p)
-		goto out_put_task;
+		goto out_free;
 	seq_puts(m, p);
 	seq_putc(m, '\n');
 	retval = 0;
-out_put_task:
-	put_task_struct(tsk);
 out_free:
 	kfree(buf);
 out:
-- 
cgit v1.2.3


From 69803d4f487fc60ce740f1fe1f0d2092d97277b6 Mon Sep 17 00:00:00 2001
From: Grégory Soutadé <gsoutade@neotion.com>
Date: Mon, 15 Sep 2014 17:47:09 +0200
Subject: mmc: Replace "enhanced_area_en" attribute by
 "partition_setting_completed"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace ext_csd "enhanced_area_en" attribute by
 "partition_setting_completed". It was used whether or
 not enhanced user area is defined and without checks of
 EXT_CSD_PARTITION_SETTING_COMPLETED bit.

Signed-off-by: Grégory Soutadé <gsoutade@neotion.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc.c   | 13 ++++++++-----
 include/linux/mmc/card.h |  2 +-
 include/linux/mmc/mmc.h  |  2 ++
 3 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 5b4b969c18bf..eb78fcd01e52 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -315,7 +315,6 @@ static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd)
 		hc_wp_grp_sz =
 			ext_csd[EXT_CSD_HC_WP_GRP_SIZE];
 
-		card->ext_csd.enhanced_area_en = 1;
 		/*
 		 * calculate the enhanced data area offset, in bytes
 		 */
@@ -356,13 +355,11 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd)
 	 */
 	if (ext_csd[EXT_CSD_PARTITION_SUPPORT] &
 	    EXT_CSD_PART_SUPPORT_PART_EN) {
-		if (card->ext_csd.enhanced_area_en != 1) {
+		if (card->ext_csd.partition_setting_completed) {
 			hc_erase_grp_sz =
 				ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE];
 			hc_wp_grp_sz =
 				ext_csd[EXT_CSD_HC_WP_GRP_SIZE];
-
-			card->ext_csd.enhanced_area_en = 1;
 		}
 
 		for (idx = 0; idx < MMC_NUM_GP_PARTITION; idx++) {
@@ -489,6 +486,12 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		ext_csd[EXT_CSD_TRIM_MULT];
 	card->ext_csd.raw_partition_support = ext_csd[EXT_CSD_PARTITION_SUPPORT];
 	if (card->ext_csd.rev >= 4) {
+		if (ext_csd[EXT_CSD_PARTITION_SETTING_COMPLETED] &
+		    EXT_CSD_PART_SETTING_COMPLETED)
+			card->ext_csd.partition_setting_completed = 1;
+		else
+			card->ext_csd.partition_setting_completed = 0;
+
 		mmc_manage_enhanced_area(card, ext_csd);
 
 		mmc_manage_gp_partitions(card, ext_csd);
@@ -1348,7 +1351,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	 * If enhanced_area_en is TRUE, host needs to enable ERASE_GRP_DEF
 	 * bit.  This bit will be lost every time after a reset or power off.
 	 */
-	if (card->ext_csd.enhanced_area_en ||
+	if (card->ext_csd.partition_setting_completed ||
 	    (card->ext_csd.rev >= 3 && (host->caps2 & MMC_CAP2_HC_ERASE_SZ))) {
 		err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 				 EXT_CSD_ERASE_GROUP_DEF, 1,
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 0ea795f5feb9..b0692d28f8e6 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -75,7 +75,7 @@ struct mmc_ext_csd {
 	unsigned int		sec_trim_mult;	/* Secure trim multiplier  */
 	unsigned int		sec_erase_mult;	/* Secure erase multiplier */
 	unsigned int		trim_timeout;		/* In milliseconds */
-	bool			enhanced_area_en;	/* enable bit */
+	bool			partition_setting_completed;	/* enable bit */
 	unsigned long long	enhanced_area_offset;	/* Units: Byte */
 	unsigned int		enhanced_area_size;	/* Units: KB */
 	unsigned int		cache_size;		/* Units: KB */
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 64ec963ed347..78753bc90a87 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -281,6 +281,7 @@ struct _mmc_csd {
 #define EXT_CSD_EXP_EVENTS_CTRL		56	/* R/W, 2 bytes */
 #define EXT_CSD_DATA_SECTOR_SIZE	61	/* R */
 #define EXT_CSD_GP_SIZE_MULT		143	/* R/W */
+#define EXT_CSD_PARTITION_SETTING_COMPLETED 155	/* R/W */
 #define EXT_CSD_PARTITION_ATTRIBUTE	156	/* R/W */
 #define EXT_CSD_PARTITION_SUPPORT	160	/* RO */
 #define EXT_CSD_HPI_MGMT		161	/* R/W */
@@ -349,6 +350,7 @@ struct _mmc_csd {
 #define EXT_CSD_PART_CONFIG_ACC_RPMB	(0x3)
 #define EXT_CSD_PART_CONFIG_ACC_GP0	(0x4)
 
+#define EXT_CSD_PART_SETTING_COMPLETED	(0x1)
 #define EXT_CSD_PART_SUPPORT_PART_EN	(0x1)
 
 #define EXT_CSD_CMD_SET_NORMAL		(1<<0)
-- 
cgit v1.2.3


From 766a53d059d1500c9755c8af017bd411bd8f1b20 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 12 Sep 2014 17:51:29 -0400
Subject: vgaswitcheroo: add vga_switcheroo_fini_domain_pm_ops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drivers should call this on unload to unregister pmops.

Bug:
https://bugzilla.kernel.org/show_bug.cgi?id=84431

Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Pali Rohár <pali.rohar@gmail.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/vga/vga_switcheroo.c | 6 ++++++
 include/linux/vga_switcheroo.h   | 2 ++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index 6866448083b2..37ac7b5dbd06 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -660,6 +660,12 @@ int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *
 }
 EXPORT_SYMBOL(vga_switcheroo_init_domain_pm_ops);
 
+void vga_switcheroo_fini_domain_pm_ops(struct device *dev)
+{
+	dev->pm_domain = NULL;
+}
+EXPORT_SYMBOL(vga_switcheroo_fini_domain_pm_ops);
+
 static int vga_switcheroo_runtime_resume_hdmi_audio(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h
index 502073a53dd3..b483abd34493 100644
--- a/include/linux/vga_switcheroo.h
+++ b/include/linux/vga_switcheroo.h
@@ -64,6 +64,7 @@ int vga_switcheroo_get_client_state(struct pci_dev *dev);
 void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic);
 
 int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain);
+void vga_switcheroo_fini_domain_pm_ops(struct device *dev);
 int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain);
 #else
 
@@ -82,6 +83,7 @@ static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return
 static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {}
 
 static inline int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; }
+static inline void vga_switcheroo_fini_domain_pm_ops(struct device *dev) {}
 static inline int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; }
 
 #endif
-- 
cgit v1.2.3


From dd56af42bd829c6e770ed69812bd65a04eaeb1e4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 25 Aug 2014 20:25:06 -0700
Subject: rcu: Eliminate deadlock between CPU hotplug and expedited grace
 periods

Currently, the expedited grace-period primitives do get_online_cpus().
This greatly simplifies their implementation, but means that calls
to them holding locks that are acquired by CPU-hotplug notifiers (to
say nothing of calls to these primitives from CPU-hotplug notifiers)
can deadlock.  But this is starting to become inconvenient, as can be
seen here: https://lkml.org/lkml/2014/8/5/754.  The problem in this
case is that some developers need to acquire a mutex from a CPU-hotplug
notifier, but also need to hold it across a synchronize_rcu_expedited().
As noted above, this currently results in deadlock.

This commit avoids the deadlock and retains the simplicity by creating
a try_get_online_cpus(), which returns false if the get_online_cpus()
reference count could not immediately be incremented.  If a call to
try_get_online_cpus() returns true, the expedited primitives operate as
before.  If a call returns false, the expedited primitives fall back to
normal grace-period operations.  This falling back of course results in
increased grace-period latency, but only during times when CPU hotplug
operations are actually in flight.  The effect should therefore be
negligible during normal operation.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Tested-by: Lan Tianyu <tianyu.lan@intel.com>
---
 include/linux/cpu.h      |  2 ++
 include/linux/lockdep.h  |  1 +
 kernel/cpu.c             | 16 +++++++++++++++-
 kernel/rcu/tree.c        | 19 ++++++++++++-------
 kernel/rcu/tree_plugin.h | 11 +++++------
 5 files changed, 35 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 95978ad7fcdd..b2d9a43012b2 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -213,6 +213,7 @@ extern struct bus_type cpu_subsys;
 extern void cpu_hotplug_begin(void);
 extern void cpu_hotplug_done(void);
 extern void get_online_cpus(void);
+extern bool try_get_online_cpus(void);
 extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
@@ -230,6 +231,7 @@ int cpu_down(unsigned int cpu);
 static inline void cpu_hotplug_begin(void) {}
 static inline void cpu_hotplug_done(void) {}
 #define get_online_cpus()	do { } while (0)
+#define try_get_online_cpus()	true
 #define put_online_cpus()	do { } while (0)
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 008388f920d7..4f86465cc317 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -505,6 +505,7 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 
 #define lock_map_acquire(l)			lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_)
 #define lock_map_acquire_read(l)		lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_)
+#define lock_map_acquire_tryread(l)		lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_)
 #define lock_map_release(l)			lock_release(l, 1, _THIS_IP_)
 
 #ifdef CONFIG_PROVE_LOCKING
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 81e2a388a0f6..356450f09c1f 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -79,6 +79,8 @@ static struct {
 
 /* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
 #define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
+#define cpuhp_lock_acquire_tryread() \
+				  lock_map_acquire_tryread(&cpu_hotplug.dep_map)
 #define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
 #define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
 
@@ -91,10 +93,22 @@ void get_online_cpus(void)
 	mutex_lock(&cpu_hotplug.lock);
 	cpu_hotplug.refcount++;
 	mutex_unlock(&cpu_hotplug.lock);
-
 }
 EXPORT_SYMBOL_GPL(get_online_cpus);
 
+bool try_get_online_cpus(void)
+{
+	if (cpu_hotplug.active_writer == current)
+		return true;
+	if (!mutex_trylock(&cpu_hotplug.lock))
+		return false;
+	cpuhp_lock_acquire_tryread();
+	cpu_hotplug.refcount++;
+	mutex_unlock(&cpu_hotplug.lock);
+	return true;
+}
+EXPORT_SYMBOL_GPL(try_get_online_cpus);
+
 void put_online_cpus(void)
 {
 	if (cpu_hotplug.active_writer == current)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d7a3b13bc94c..133e47223095 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2940,11 +2940,6 @@ static int synchronize_sched_expedited_cpu_stop(void *data)
  * restructure your code to batch your updates, and then use a single
  * synchronize_sched() instead.
  *
- * Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
- * to call this function from a CPU-hotplug notifier.  Failing to observe
- * these restriction will result in deadlock.
- *
  * This implementation can be thought of as an application of ticket
  * locking to RCU, with sync_sched_expedited_started and
  * sync_sched_expedited_done taking on the roles of the halves
@@ -2994,7 +2989,12 @@ void synchronize_sched_expedited(void)
 	 */
 	snap = atomic_long_inc_return(&rsp->expedited_start);
 	firstsnap = snap;
-	get_online_cpus();
+	if (!try_get_online_cpus()) {
+		/* CPU hotplug operation in flight, fall back to normal GP. */
+		wait_rcu_gp(call_rcu_sched);
+		atomic_long_inc(&rsp->expedited_normal);
+		return;
+	}
 	WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
 
 	/*
@@ -3041,7 +3041,12 @@ void synchronize_sched_expedited(void)
 		 * and they started after our first try, so their grace
 		 * period works for us.
 		 */
-		get_online_cpus();
+		if (!try_get_online_cpus()) {
+			/* CPU hotplug operation in flight, use normal GP. */
+			wait_rcu_gp(call_rcu_sched);
+			atomic_long_inc(&rsp->expedited_normal);
+			return;
+		}
 		snap = atomic_long_read(&rsp->expedited_start);
 		smp_mb(); /* ensure read is before try_stop_cpus(). */
 	}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index e2c5910546f6..387dd4599344 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -793,11 +793,6 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
  * In fact, if you are using synchronize_rcu_expedited() in a loop,
  * please restructure your code to batch your updates, and then Use a
  * single synchronize_rcu() instead.
- *
- * Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
- * to call this function from a CPU-hotplug notifier.  Failing to observe
- * these restriction will result in deadlock.
  */
 void synchronize_rcu_expedited(void)
 {
@@ -819,7 +814,11 @@ void synchronize_rcu_expedited(void)
 	 * being boosted.  This simplifies the process of moving tasks
 	 * from leaf to root rcu_node structures.
 	 */
-	get_online_cpus();
+	if (!try_get_online_cpus()) {
+		/* CPU-hotplug operation in flight, fall back to normal GP. */
+		wait_rcu_gp(call_rcu);
+		return;
+	}
 
 	/*
 	 * Acquire lock, falling back to synchronize_rcu() if too many
-- 
cgit v1.2.3


From 227844f53864077ccaefe01d0960fcccc03445ce Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Mon, 9 Jun 2014 12:27:18 +0200
Subject: arm/arm64: KVM: Rename irq_state to irq_pending

The irq_state field on the distributor struct is ambiguous in its
meaning; the comment says it's the level of the input put, but that
doesn't make much sense for edge-triggered interrupts.  The code
actually uses this state variable to check if the interrupt is in the
pending state on the distributor so clarify the comment and rename the
actual variable and accessor methods.

Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 include/kvm/arm_vgic.h |  4 ++--
 virt/kvm/arm/vgic.c    | 52 +++++++++++++++++++++++++-------------------------
 2 files changed, 28 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 35b0c121bb65..388d442eecb5 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -140,8 +140,8 @@ struct vgic_dist {
 	/* Interrupt enabled (one bit per IRQ) */
 	struct vgic_bitmap	irq_enabled;
 
-	/* Interrupt 'pin' level */
-	struct vgic_bitmap	irq_state;
+	/* Interrupt state is pending on the distributor */
+	struct vgic_bitmap	irq_pending;
 
 	/* Level-triggered interrupt in progress */
 	struct vgic_bitmap	irq_active;
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index eeb23b37f87c..7e86a36f3fc5 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -37,7 +37,7 @@
  *
  * - At any time, the dist->irq_pending_on_cpu is the oracle that knows if
  *   something is pending
- * - VGIC pending interrupts are stored on the vgic.irq_state vgic
+ * - VGIC pending interrupts are stored on the vgic.irq_pending vgic
  *   bitmap (this bitmap is updated by both user land ioctls and guest
  *   mmio ops, and other in-kernel peripherals such as the
  *   arch. timers) and indicate the 'wire' state.
@@ -45,8 +45,8 @@
  *   recalculated
  * - To calculate the oracle, we need info for each cpu from
  *   compute_pending_for_cpu, which considers:
- *   - PPI: dist->irq_state & dist->irq_enable
- *   - SPI: dist->irq_state & dist->irq_enable & dist->irq_spi_target
+ *   - PPI: dist->irq_pending & dist->irq_enable
+ *   - SPI: dist->irq_pending & dist->irq_enable & dist->irq_spi_target
  *   - irq_spi_target is a 'formatted' version of the GICD_ICFGR
  *     registers, stored on each vcpu. We only keep one bit of
  *     information per interrupt, making sure that only one vcpu can
@@ -221,21 +221,21 @@ static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	return vgic_bitmap_get_irq_val(&dist->irq_state, vcpu->vcpu_id, irq);
+	return vgic_bitmap_get_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq);
 }
 
-static void vgic_dist_irq_set(struct kvm_vcpu *vcpu, int irq)
+static void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 1);
+	vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 1);
 }
 
-static void vgic_dist_irq_clear(struct kvm_vcpu *vcpu, int irq)
+static void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 0);
+	vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 0);
 }
 
 static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq)
@@ -409,7 +409,7 @@ static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
 					struct kvm_exit_mmio *mmio,
 					phys_addr_t offset)
 {
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
+	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_pending,
 				       vcpu->vcpu_id, offset);
 	vgic_reg_access(mmio, reg, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
@@ -425,7 +425,7 @@ static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
 					  struct kvm_exit_mmio *mmio,
 					  phys_addr_t offset)
 {
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
+	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_pending,
 				       vcpu->vcpu_id, offset);
 	vgic_reg_access(mmio, reg, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
@@ -651,7 +651,7 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 		 * is fine, then we are only setting a few bits that were
 		 * already set.
 		 */
-		vgic_dist_irq_set(vcpu, lr.irq);
+		vgic_dist_irq_set_pending(vcpu, lr.irq);
 		if (lr.irq < VGIC_NR_SGIS)
 			dist->irq_sgi_sources[vcpu_id][lr.irq] |= 1 << lr.source;
 		lr.state &= ~LR_STATE_PENDING;
@@ -932,7 +932,7 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		if (target_cpus & 1) {
 			/* Flag the SGI as pending */
-			vgic_dist_irq_set(vcpu, sgi);
+			vgic_dist_irq_set_pending(vcpu, sgi);
 			dist->irq_sgi_sources[c][sgi] |= 1 << vcpu_id;
 			kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c);
 		}
@@ -952,11 +952,11 @@ static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
 	pend_percpu = vcpu->arch.vgic_cpu.pending_percpu;
 	pend_shared = vcpu->arch.vgic_cpu.pending_shared;
 
-	pending = vgic_bitmap_get_cpu_map(&dist->irq_state, vcpu_id);
+	pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id);
 	enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
 	bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS);
 
-	pending = vgic_bitmap_get_shared_map(&dist->irq_state);
+	pending = vgic_bitmap_get_shared_map(&dist->irq_pending);
 	enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
 	bitmap_and(pend_shared, pending, enabled, VGIC_NR_SHARED_IRQS);
 	bitmap_and(pend_shared, pend_shared,
@@ -1160,7 +1160,7 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
 	 * our emulated gic and can get rid of them.
 	 */
 	if (!sources) {
-		vgic_dist_irq_clear(vcpu, irq);
+		vgic_dist_irq_clear_pending(vcpu, irq);
 		vgic_cpu_irq_clear(vcpu, irq);
 		return true;
 	}
@@ -1175,7 +1175,7 @@ static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
 
 	if (vgic_queue_irq(vcpu, 0, irq)) {
 		if (vgic_irq_is_edge(vcpu, irq)) {
-			vgic_dist_irq_clear(vcpu, irq);
+			vgic_dist_irq_clear_pending(vcpu, irq);
 			vgic_cpu_irq_clear(vcpu, irq);
 		} else {
 			vgic_irq_set_active(vcpu, irq);
@@ -1376,7 +1376,7 @@ static void vgic_kick_vcpus(struct kvm *kvm)
 
 static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
 {
-	int is_edge = vgic_irq_is_edge(vcpu, irq);
+	int edge_triggered = vgic_irq_is_edge(vcpu, irq);
 	int state = vgic_dist_irq_is_pending(vcpu, irq);
 
 	/*
@@ -1384,26 +1384,26 @@ static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
 	 * - edge triggered and we have a rising edge
 	 * - level triggered and we change level
 	 */
-	if (is_edge)
+	if (edge_triggered)
 		return level > state;
 	else
 		return level != state;
 }
 
-static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
+static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 				  unsigned int irq_num, bool level)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct kvm_vcpu *vcpu;
-	int is_edge, is_level;
+	int edge_triggered, level_triggered;
 	int enabled;
 	bool ret = true;
 
 	spin_lock(&dist->lock);
 
 	vcpu = kvm_get_vcpu(kvm, cpuid);
-	is_edge = vgic_irq_is_edge(vcpu, irq_num);
-	is_level = !is_edge;
+	edge_triggered = vgic_irq_is_edge(vcpu, irq_num);
+	level_triggered = !edge_triggered;
 
 	if (!vgic_validate_injection(vcpu, irq_num, level)) {
 		ret = false;
@@ -1418,9 +1418,9 @@ static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
 	kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid);
 
 	if (level)
-		vgic_dist_irq_set(vcpu, irq_num);
+		vgic_dist_irq_set_pending(vcpu, irq_num);
 	else
-		vgic_dist_irq_clear(vcpu, irq_num);
+		vgic_dist_irq_clear_pending(vcpu, irq_num);
 
 	enabled = vgic_irq_is_enabled(vcpu, irq_num);
 
@@ -1429,7 +1429,7 @@ static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
 		goto out;
 	}
 
-	if (is_level && vgic_irq_is_active(vcpu, irq_num)) {
+	if (level_triggered && vgic_irq_is_active(vcpu, irq_num)) {
 		/*
 		 * Level interrupt in progress, will be picked up
 		 * when EOId.
@@ -1466,7 +1466,7 @@ out:
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
 			bool level)
 {
-	if (vgic_update_irq_state(kvm, cpuid, irq_num, level))
+	if (vgic_update_irq_pending(kvm, cpuid, irq_num, level))
 		vgic_kick_vcpus(kvm);
 
 	return 0;
-- 
cgit v1.2.3


From dbf20f9d8105cca531614c8bff9a74351e8e67e7 Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Mon, 9 Jun 2014 12:55:13 +0200
Subject: arm/arm64: KVM: Rename irq_active to irq_queued

We have a special bitmap on the distributor struct to keep track of when
level-triggered interrupts are queued on the list registers.  This was
named irq_active, which is confusing, because the active state of an
interrupt as per the GIC spec is a different thing, not specifically
related to edge-triggered/level-triggered configurations but rather
indicates an interrupt which has been ack'ed but not yet eoi'ed.

Rename the bitmap and the corresponding accessor functions to irq_queued
to clarify what this is actually used for.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 include/kvm/arm_vgic.h |  4 ++--
 virt/kvm/arm/vgic.c    | 33 +++++++++++++++++++--------------
 2 files changed, 21 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 388d442eecb5..7d8e61fa9928 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -143,8 +143,8 @@ struct vgic_dist {
 	/* Interrupt state is pending on the distributor */
 	struct vgic_bitmap	irq_pending;
 
-	/* Level-triggered interrupt in progress */
-	struct vgic_bitmap	irq_active;
+	/* Level-triggered interrupt queued on VCPU interface */
+	struct vgic_bitmap	irq_queued;
 
 	/* Interrupt priority. Not used yet. */
 	struct vgic_bytemap	irq_priority;
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 7e86a36f3fc5..ce1a2d17ee81 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -60,12 +60,12 @@
  * the 'line' again. This is achieved as such:
  *
  * - When a level interrupt is moved onto a vcpu, the corresponding
- *   bit in irq_active is set. As long as this bit is set, the line
+ *   bit in irq_queued is set. As long as this bit is set, the line
  *   will be ignored for further interrupts. The interrupt is injected
  *   into the vcpu with the GICH_LR_EOI bit set (generate a
  *   maintenance interrupt on EOI).
  * - When the interrupt is EOIed, the maintenance interrupt fires,
- *   and clears the corresponding bit in irq_active. This allow the
+ *   and clears the corresponding bit in irq_queued. This allows the
  *   interrupt line to be sampled again.
  */
 
@@ -196,25 +196,25 @@ static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq)
 	return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq);
 }
 
-static int vgic_irq_is_active(struct kvm_vcpu *vcpu, int irq)
+static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq);
+	return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq);
 }
 
-static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq)
+static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1);
+	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 1);
 }
 
-static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq)
+static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 0);
+	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0);
 }
 
 static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
@@ -256,6 +256,11 @@ static void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
 			  vcpu->arch.vgic_cpu.pending_shared);
 }
 
+static bool vgic_can_sample_irq(struct kvm_vcpu *vcpu, int irq)
+{
+	return vgic_irq_is_edge(vcpu, irq) || !vgic_irq_is_queued(vcpu, irq);
+}
+
 static u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
 {
 	return le32_to_cpu(*((u32 *)mmio->data)) & mask;
@@ -1079,8 +1084,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
 
 		if (!vgic_irq_is_enabled(vcpu, vlr.irq)) {
 			vgic_retire_lr(lr, vlr.irq, vcpu);
-			if (vgic_irq_is_active(vcpu, vlr.irq))
-				vgic_irq_clear_active(vcpu, vlr.irq);
+			if (vgic_irq_is_queued(vcpu, vlr.irq))
+				vgic_irq_clear_queued(vcpu, vlr.irq);
 		}
 	}
 }
@@ -1170,7 +1175,7 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
 
 static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
 {
-	if (vgic_irq_is_active(vcpu, irq))
+	if (!vgic_can_sample_irq(vcpu, irq))
 		return true; /* level interrupt, already queued */
 
 	if (vgic_queue_irq(vcpu, 0, irq)) {
@@ -1178,7 +1183,7 @@ static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
 			vgic_dist_irq_clear_pending(vcpu, irq);
 			vgic_cpu_irq_clear(vcpu, irq);
 		} else {
-			vgic_irq_set_active(vcpu, irq);
+			vgic_irq_set_queued(vcpu, irq);
 		}
 
 		return true;
@@ -1262,7 +1267,7 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 		for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
 			struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
 
-			vgic_irq_clear_active(vcpu, vlr.irq);
+			vgic_irq_clear_queued(vcpu, vlr.irq);
 			WARN_ON(vlr.state & LR_STATE_MASK);
 			vlr.state = 0;
 			vgic_set_lr(vcpu, lr, vlr);
@@ -1429,7 +1434,7 @@ static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 		goto out;
 	}
 
-	if (level_triggered && vgic_irq_is_active(vcpu, irq_num)) {
+	if (!vgic_can_sample_irq(vcpu, irq_num)) {
 		/*
 		 * Level interrupt in progress, will be picked up
 		 * when EOId.
-- 
cgit v1.2.3


From faa1b46c3e9f4d40359aee04ff275eea5f4cae3a Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Sat, 14 Jun 2014 21:54:51 +0200
Subject: arm/arm64: KVM: vgic: Improve handling of GICD_I{CS}PENDRn

Writes to GICD_ISPENDRn and GICD_ICPENDRn are currently not handled
correctly for level-triggered interrupts.  The spec states that for
level-triggered interrupts, writes to the GICD_ISPENDRn activate the
output of a flip-flop which is in turn or'ed with the actual input
interrupt signal.  Correspondingly, writes to GICD_ICPENDRn simply
deactivates the output of that flip-flop, but does not (of course) affect
the external input signal.  Reads from GICC_IAR will also deactivate the
flip-flop output.

This requires us to track the state of the level-input separately from
the state in the flip-flop.  We therefore introduce two new variables on
the distributor struct to track these two states.  Astute readers may
notice that this is introducing more state than required (because an OR
of the two states gives you the pending state), but the remaining vgic
code uses the pending bitmap for optimized operations to figure out, at
the end of the day, if an interrupt is pending or not on the distributor
side.  Refactoring the code to consider the two state variables all the
places where we currently access the precomputed pending value, did not
look pretty.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 include/kvm/arm_vgic.h |  16 ++++++-
 virt/kvm/arm/vgic.c    | 119 ++++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 123 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 7d8e61fa9928..f074539c6ac5 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -140,9 +140,23 @@ struct vgic_dist {
 	/* Interrupt enabled (one bit per IRQ) */
 	struct vgic_bitmap	irq_enabled;
 
-	/* Interrupt state is pending on the distributor */
+	/* Level-triggered interrupt external input is asserted */
+	struct vgic_bitmap	irq_level;
+
+	/*
+	 * Interrupt state is pending on the distributor
+	 */
 	struct vgic_bitmap	irq_pending;
 
+	/*
+	 * Tracks writes to GICD_ISPENDRn and GICD_ICPENDRn for level-triggered
+	 * interrupts.  Essentially holds the state of the flip-flop in
+	 * Figure 4-10 on page 4-101 in ARM IHI 0048B.b.
+	 * Once set, it is only cleared for level-triggered interrupts on
+	 * guest ACKs (when we queue it) or writes to GICD_ICPENDRn.
+	 */
+	struct vgic_bitmap	irq_soft_pend;
+
 	/* Level-triggered interrupt queued on VCPU interface */
 	struct vgic_bitmap	irq_queued;
 
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 2026b6147805..435d8e7ad137 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -67,6 +67,11 @@
  * - When the interrupt is EOIed, the maintenance interrupt fires,
  *   and clears the corresponding bit in irq_queued. This allows the
  *   interrupt line to be sampled again.
+ * - Note that level-triggered interrupts can also be set to pending from
+ *   writes to GICD_ISPENDRn and lowering the external input line does not
+ *   cause the interrupt to become inactive in such a situation.
+ *   Conversely, writes to GICD_ICPENDRn do not cause the interrupt to become
+ *   inactive as long as the external input line is held high.
  */
 
 #define VGIC_ADDR_UNDEF		(-1)
@@ -217,6 +222,41 @@ static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq)
 	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0);
 }
 
+static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	return vgic_bitmap_get_irq_val(&dist->irq_level, vcpu->vcpu_id, irq);
+}
+
+static void vgic_dist_irq_set_level(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 1);
+}
+
+static void vgic_dist_irq_clear_level(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 0);
+}
+
+static int vgic_dist_irq_soft_pend(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	return vgic_bitmap_get_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq);
+}
+
+static void vgic_dist_irq_clear_soft_pend(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0);
+}
+
 static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
@@ -414,11 +454,26 @@ static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
 					struct kvm_exit_mmio *mmio,
 					phys_addr_t offset)
 {
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_pending,
-				       vcpu->vcpu_id, offset);
+	u32 *reg;
+	u32 level_mask;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu->vcpu_id, offset);
+	level_mask = (~(*reg));
+
+	/* Mark both level and edge triggered irqs as pending */
+	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
 	vgic_reg_access(mmio, reg, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+
 	if (mmio->is_write) {
+		/* Set the soft-pending flag only for level-triggered irqs */
+		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
+					  vcpu->vcpu_id, offset);
+		vgic_reg_access(mmio, reg, offset,
+				ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+		*reg &= level_mask;
+
 		vgic_update_state(vcpu->kvm);
 		return true;
 	}
@@ -430,11 +485,27 @@ static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
 					  struct kvm_exit_mmio *mmio,
 					  phys_addr_t offset)
 {
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_pending,
-				       vcpu->vcpu_id, offset);
+	u32 *level_active;
+	u32 *reg;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
 	vgic_reg_access(mmio, reg, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
 	if (mmio->is_write) {
+		/* Re-set level triggered level-active interrupts */
+		level_active = vgic_bitmap_get_reg(&dist->irq_level,
+					  vcpu->vcpu_id, offset);
+		reg = vgic_bitmap_get_reg(&dist->irq_pending,
+					  vcpu->vcpu_id, offset);
+		*reg |= *level_active;
+
+		/* Clear soft-pending flags */
+		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
+					  vcpu->vcpu_id, offset);
+		vgic_reg_access(mmio, reg, offset,
+				ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
+
 		vgic_update_state(vcpu->kvm);
 		return true;
 	}
@@ -1268,17 +1339,32 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 
 		for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
 			struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
+			WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq));
 
 			vgic_irq_clear_queued(vcpu, vlr.irq);
 			WARN_ON(vlr.state & LR_STATE_MASK);
 			vlr.state = 0;
 			vgic_set_lr(vcpu, lr, vlr);
 
+			/*
+			 * If the IRQ was EOIed it was also ACKed and we we
+			 * therefore assume we can clear the soft pending
+			 * state (should it had been set) for this interrupt.
+			 *
+			 * Note: if the IRQ soft pending state was set after
+			 * the IRQ was acked, it actually shouldn't be
+			 * cleared, but we have no way of knowing that unless
+			 * we start trapping ACKs when the soft-pending state
+			 * is set.
+			 */
+			vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);
+
 			/* Any additional pending interrupt? */
-			if (vgic_dist_irq_is_pending(vcpu, vlr.irq)) {
+			if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
 				vgic_cpu_irq_set(vcpu, vlr.irq);
 				level_pending = true;
 			} else {
+				vgic_dist_irq_clear_pending(vcpu, vlr.irq);
 				vgic_cpu_irq_clear(vcpu, vlr.irq);
 			}
 
@@ -1384,17 +1470,19 @@ static void vgic_kick_vcpus(struct kvm *kvm)
 static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
 {
 	int edge_triggered = vgic_irq_is_edge(vcpu, irq);
-	int state = vgic_dist_irq_is_pending(vcpu, irq);
 
 	/*
 	 * Only inject an interrupt if:
 	 * - edge triggered and we have a rising edge
 	 * - level triggered and we change level
 	 */
-	if (edge_triggered)
+	if (edge_triggered) {
+		int state = vgic_dist_irq_is_pending(vcpu, irq);
 		return level > state;
-	else
+	} else {
+		int state = vgic_dist_irq_get_level(vcpu, irq);
 		return level != state;
+	}
 }
 
 static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
@@ -1424,10 +1512,19 @@ static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 
 	kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid);
 
-	if (level)
+	if (level) {
+		if (level_triggered)
+			vgic_dist_irq_set_level(vcpu, irq_num);
 		vgic_dist_irq_set_pending(vcpu, irq_num);
-	else
-		vgic_dist_irq_clear_pending(vcpu, irq_num);
+	} else {
+		if (level_triggered) {
+			vgic_dist_irq_clear_level(vcpu, irq_num);
+			if (!vgic_dist_irq_soft_pend(vcpu, irq_num))
+				vgic_dist_irq_clear_pending(vcpu, irq_num);
+		} else {
+			vgic_dist_irq_clear_pending(vcpu, irq_num);
+		}
+	}
 
 	enabled = vgic_irq_is_enabled(vcpu, irq_num);
 
-- 
cgit v1.2.3


From c1bfb577addd4867a82c4f235824a315d5afb94a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 8 Jul 2014 12:09:01 +0100
Subject: arm/arm64: KVM: vgic: switch to dynamic allocation

So far, all the VGIC data structures are statically defined by the
*maximum* number of vcpus and interrupts it supports. It means that
we always have to oversize it to cater for the worse case.

Start by changing the data structures to be dynamically sizeable,
and allocate them at runtime.

The sizes are still very static though.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/kvm/arm.c     |   3 +
 include/kvm/arm_vgic.h |  76 ++++++++++++----
 virt/kvm/arm/vgic.c    | 243 ++++++++++++++++++++++++++++++++++++++++++-------
 3 files changed, 269 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 88c901cfc75e..c1a11496817b 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -161,6 +161,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 			kvm->vcpus[i] = NULL;
 		}
 	}
+
+	kvm_vgic_destroy(kvm);
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -243,6 +245,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
+	kvm_vgic_vcpu_destroy(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index f074539c6ac5..fd1b8f252da1 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -54,19 +54,33 @@
  * - a bunch of shared interrupts (SPI)
  */
 struct vgic_bitmap {
-	union {
-		u32 reg[VGIC_NR_PRIVATE_IRQS / 32];
-		DECLARE_BITMAP(reg_ul, VGIC_NR_PRIVATE_IRQS);
-	} percpu[VGIC_MAX_CPUS];
-	union {
-		u32 reg[VGIC_NR_SHARED_IRQS / 32];
-		DECLARE_BITMAP(reg_ul, VGIC_NR_SHARED_IRQS);
-	} shared;
+	/*
+	 * - One UL per VCPU for private interrupts (assumes UL is at
+	 *   least 32 bits)
+	 * - As many UL as necessary for shared interrupts.
+	 *
+	 * The private interrupts are accessed via the "private"
+	 * field, one UL per vcpu (the state for vcpu n is in
+	 * private[n]). The shared interrupts are accessed via the
+	 * "shared" pointer (IRQn state is at bit n-32 in the bitmap).
+	 */
+	unsigned long *private;
+	unsigned long *shared;
 };
 
 struct vgic_bytemap {
-	u32 percpu[VGIC_MAX_CPUS][VGIC_NR_PRIVATE_IRQS / 4];
-	u32 shared[VGIC_NR_SHARED_IRQS  / 4];
+	/*
+	 * - 8 u32 per VCPU for private interrupts
+	 * - As many u32 as necessary for shared interrupts.
+	 *
+	 * The private interrupts are accessed via the "private"
+	 * field, (the state for vcpu n is in private[n*8] to
+	 * private[n*8 + 7]). The shared interrupts are accessed via
+	 * the "shared" pointer (IRQn state is at byte (n-32)%4 of the
+	 * shared[(n-32)/4] word).
+	 */
+	u32 *private;
+	u32 *shared;
 };
 
 struct kvm_vcpu;
@@ -127,6 +141,9 @@ struct vgic_dist {
 	bool			in_kernel;
 	bool			ready;
 
+	int			nr_cpus;
+	int			nr_irqs;
+
 	/* Virtual control interface mapping */
 	void __iomem		*vctrl_base;
 
@@ -166,15 +183,36 @@ struct vgic_dist {
 	/* Level/edge triggered */
 	struct vgic_bitmap	irq_cfg;
 
-	/* Source CPU per SGI and target CPU */
-	u8			irq_sgi_sources[VGIC_MAX_CPUS][VGIC_NR_SGIS];
+	/*
+	 * Source CPU per SGI and target CPU:
+	 *
+	 * Each byte represent a SGI observable on a VCPU, each bit of
+	 * this byte indicating if the corresponding VCPU has
+	 * generated this interrupt. This is a GICv2 feature only.
+	 *
+	 * For VCPUn (n < 8), irq_sgi_sources[n*16] to [n*16 + 15] are
+	 * the SGIs observable on VCPUn.
+	 */
+	u8			*irq_sgi_sources;
 
-	/* Target CPU for each IRQ */
-	u8			irq_spi_cpu[VGIC_NR_SHARED_IRQS];
-	struct vgic_bitmap	irq_spi_target[VGIC_MAX_CPUS];
+	/*
+	 * Target CPU for each SPI:
+	 *
+	 * Array of available SPI, each byte indicating the target
+	 * VCPU for SPI. IRQn (n >=32) is at irq_spi_cpu[n-32].
+	 */
+	u8			*irq_spi_cpu;
+
+	/*
+	 * Reverse lookup of irq_spi_cpu for faster compute pending:
+	 *
+	 * Array of bitmaps, one per VCPU, describing if IRQn is
+	 * routed to a particular VCPU.
+	 */
+	struct vgic_bitmap	*irq_spi_target;
 
 	/* Bitmap indicating which CPU has something pending */
-	unsigned long		irq_pending_on_cpu;
+	unsigned long		*irq_pending_on_cpu;
 #endif
 };
 
@@ -204,11 +242,11 @@ struct vgic_v3_cpu_if {
 struct vgic_cpu {
 #ifdef CONFIG_KVM_ARM_VGIC
 	/* per IRQ to LR mapping */
-	u8		vgic_irq_lr_map[VGIC_NR_IRQS];
+	u8		*vgic_irq_lr_map;
 
 	/* Pending interrupts on this VCPU */
 	DECLARE_BITMAP(	pending_percpu, VGIC_NR_PRIVATE_IRQS);
-	DECLARE_BITMAP(	pending_shared, VGIC_NR_SHARED_IRQS);
+	unsigned long	*pending_shared;
 
 	/* Bitmap of used/free list registers */
 	DECLARE_BITMAP(	lr_used, VGIC_V2_MAX_LRS);
@@ -239,7 +277,9 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
 int kvm_vgic_hyp_init(void);
 int kvm_vgic_init(struct kvm *kvm);
 int kvm_vgic_create(struct kvm *kvm);
+void kvm_vgic_destroy(struct kvm *kvm);
 int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 9bdf181a00e2..08db8764496a 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -95,6 +95,7 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
 static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
 static void vgic_update_state(struct kvm *kvm);
 static void vgic_kick_vcpus(struct kvm *kvm);
+static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi);
 static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
 static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
 static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);
@@ -105,10 +106,8 @@ static const struct vgic_ops *vgic_ops;
 static const struct vgic_params *vgic;
 
 /*
- * struct vgic_bitmap contains unions that provide two views of
- * the same data. In one case it is an array of registers of
- * u32's, and in the other case it is a bitmap of unsigned
- * longs.
+ * struct vgic_bitmap contains a bitmap made of unsigned longs, but
+ * extracts u32s out of them.
  *
  * This does not work on 64-bit BE systems, because the bitmap access
  * will store two consecutive 32-bit words with the higher-addressed
@@ -124,23 +123,45 @@ static const struct vgic_params *vgic;
 #define REG_OFFSET_SWIZZLE	0
 #endif
 
+static int vgic_init_bitmap(struct vgic_bitmap *b, int nr_cpus, int nr_irqs)
+{
+	int nr_longs;
+
+	nr_longs = nr_cpus + BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
+
+	b->private = kzalloc(sizeof(unsigned long) * nr_longs, GFP_KERNEL);
+	if (!b->private)
+		return -ENOMEM;
+
+	b->shared = b->private + nr_cpus;
+
+	return 0;
+}
+
+static void vgic_free_bitmap(struct vgic_bitmap *b)
+{
+	kfree(b->private);
+	b->private = NULL;
+	b->shared = NULL;
+}
+
 static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
 				int cpuid, u32 offset)
 {
 	offset >>= 2;
 	if (!offset)
-		return x->percpu[cpuid].reg + (offset ^ REG_OFFSET_SWIZZLE);
+		return (u32 *)(x->private + cpuid) + REG_OFFSET_SWIZZLE;
 	else
-		return x->shared.reg + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
+		return (u32 *)(x->shared) + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
 }
 
 static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
 				   int cpuid, int irq)
 {
 	if (irq < VGIC_NR_PRIVATE_IRQS)
-		return test_bit(irq, x->percpu[cpuid].reg_ul);
+		return test_bit(irq, x->private + cpuid);
 
-	return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared.reg_ul);
+	return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared);
 }
 
 static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
@@ -149,9 +170,9 @@ static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
 	unsigned long *reg;
 
 	if (irq < VGIC_NR_PRIVATE_IRQS) {
-		reg = x->percpu[cpuid].reg_ul;
+		reg = x->private + cpuid;
 	} else {
-		reg =  x->shared.reg_ul;
+		reg = x->shared;
 		irq -= VGIC_NR_PRIVATE_IRQS;
 	}
 
@@ -163,24 +184,49 @@ static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
 
 static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid)
 {
-	if (unlikely(cpuid >= VGIC_MAX_CPUS))
-		return NULL;
-	return x->percpu[cpuid].reg_ul;
+	return x->private + cpuid;
 }
 
 static unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
 {
-	return x->shared.reg_ul;
+	return x->shared;
+}
+
+static int vgic_init_bytemap(struct vgic_bytemap *x, int nr_cpus, int nr_irqs)
+{
+	int size;
+
+	size  = nr_cpus * VGIC_NR_PRIVATE_IRQS;
+	size += nr_irqs - VGIC_NR_PRIVATE_IRQS;
+
+	x->private = kzalloc(size, GFP_KERNEL);
+	if (!x->private)
+		return -ENOMEM;
+
+	x->shared = x->private + nr_cpus * VGIC_NR_PRIVATE_IRQS / sizeof(u32);
+	return 0;
+}
+
+static void vgic_free_bytemap(struct vgic_bytemap *b)
+{
+	kfree(b->private);
+	b->private = NULL;
+	b->shared = NULL;
 }
 
 static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
 {
-	offset >>= 2;
-	BUG_ON(offset > (VGIC_NR_IRQS / 4));
-	if (offset < 8)
-		return x->percpu[cpuid] + offset;
-	else
-		return x->shared + offset - 8;
+	u32 *reg;
+
+	if (offset < VGIC_NR_PRIVATE_IRQS) {
+		reg = x->private;
+		offset += cpuid * VGIC_NR_PRIVATE_IRQS;
+	} else {
+		reg = x->shared;
+		offset -= VGIC_NR_PRIVATE_IRQS;
+	}
+
+	return reg + (offset / sizeof(u32));
 }
 
 #define VGIC_CFG_LEVEL	0
@@ -744,7 +790,7 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 		 */
 		vgic_dist_irq_set_pending(vcpu, lr.irq);
 		if (lr.irq < VGIC_NR_SGIS)
-			dist->irq_sgi_sources[vcpu_id][lr.irq] |= 1 << lr.source;
+			*vgic_get_sgi_sources(dist, vcpu_id, lr.irq) |= 1 << lr.source;
 		lr.state &= ~LR_STATE_PENDING;
 		vgic_set_lr(vcpu, i, lr);
 
@@ -778,7 +824,7 @@ static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
 	/* Copy source SGIs from distributor side */
 	for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
 		int shift = 8 * (sgi - min_sgi);
-		reg |= (u32)dist->irq_sgi_sources[vcpu_id][sgi] << shift;
+		reg |= ((u32)*vgic_get_sgi_sources(dist, vcpu_id, sgi)) << shift;
 	}
 
 	mmio_data_write(mmio, ~0, reg);
@@ -802,14 +848,15 @@ static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
 	/* Clear pending SGIs on the distributor */
 	for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
 		u8 mask = reg >> (8 * (sgi - min_sgi));
+		u8 *src = vgic_get_sgi_sources(dist, vcpu_id, sgi);
 		if (set) {
-			if ((dist->irq_sgi_sources[vcpu_id][sgi] & mask) != mask)
+			if ((*src & mask) != mask)
 				updated = true;
-			dist->irq_sgi_sources[vcpu_id][sgi] |= mask;
+			*src |= mask;
 		} else {
-			if (dist->irq_sgi_sources[vcpu_id][sgi] & mask)
+			if (*src & mask)
 				updated = true;
-			dist->irq_sgi_sources[vcpu_id][sgi] &= ~mask;
+			*src &= ~mask;
 		}
 	}
 
@@ -993,6 +1040,11 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	return true;
 }
 
+static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi)
+{
+	return dist->irq_sgi_sources + vcpu_id * VGIC_NR_SGIS + sgi;
+}
+
 static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -1026,7 +1078,7 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 		if (target_cpus & 1) {
 			/* Flag the SGI as pending */
 			vgic_dist_irq_set_pending(vcpu, sgi);
-			dist->irq_sgi_sources[c][sgi] |= 1 << vcpu_id;
+			*vgic_get_sgi_sources(dist, c, sgi) |= 1 << vcpu_id;
 			kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c);
 		}
 
@@ -1073,14 +1125,14 @@ static void vgic_update_state(struct kvm *kvm)
 	int c;
 
 	if (!dist->enabled) {
-		set_bit(0, &dist->irq_pending_on_cpu);
+		set_bit(0, dist->irq_pending_on_cpu);
 		return;
 	}
 
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		if (compute_pending_for_cpu(vcpu)) {
 			pr_debug("CPU%d has pending interrupts\n", c);
-			set_bit(c, &dist->irq_pending_on_cpu);
+			set_bit(c, dist->irq_pending_on_cpu);
 		}
 	}
 }
@@ -1237,14 +1289,14 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
 	int vcpu_id = vcpu->vcpu_id;
 	int c;
 
-	sources = dist->irq_sgi_sources[vcpu_id][irq];
+	sources = *vgic_get_sgi_sources(dist, vcpu_id, irq);
 
 	for_each_set_bit(c, &sources, VGIC_MAX_CPUS) {
 		if (vgic_queue_irq(vcpu, c, irq))
 			clear_bit(c, &sources);
 	}
 
-	dist->irq_sgi_sources[vcpu_id][irq] = sources;
+	*vgic_get_sgi_sources(dist, vcpu_id, irq) = sources;
 
 	/*
 	 * If the sources bitmap has been cleared it means that we
@@ -1332,7 +1384,7 @@ epilog:
 		 * us. Claim we don't have anything pending. We'll
 		 * adjust that if needed while exiting.
 		 */
-		clear_bit(vcpu_id, &dist->irq_pending_on_cpu);
+		clear_bit(vcpu_id, dist->irq_pending_on_cpu);
 	}
 }
 
@@ -1430,7 +1482,7 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 	/* Check if we still have something up our sleeve... */
 	pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr);
 	if (level_pending || pending < vgic->nr_lr)
-		set_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
+		set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
 }
 
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
@@ -1464,7 +1516,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
 	if (!irqchip_in_kernel(vcpu->kvm))
 		return 0;
 
-	return test_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
+	return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
 }
 
 static void vgic_kick_vcpus(struct kvm *kvm)
@@ -1559,7 +1611,7 @@ static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 
 	if (level) {
 		vgic_cpu_irq_set(vcpu, irq_num);
-		set_bit(cpuid, &dist->irq_pending_on_cpu);
+		set_bit(cpuid, dist->irq_pending_on_cpu);
 	}
 
 out:
@@ -1603,6 +1655,32 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	kfree(vgic_cpu->pending_shared);
+	kfree(vgic_cpu->vgic_irq_lr_map);
+	vgic_cpu->pending_shared = NULL;
+	vgic_cpu->vgic_irq_lr_map = NULL;
+}
+
+static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
+	vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
+	vgic_cpu->vgic_irq_lr_map = kzalloc(nr_irqs, GFP_KERNEL);
+
+	if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) {
+		kvm_vgic_vcpu_destroy(vcpu);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 /**
  * kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state
  * @vcpu: pointer to the vcpu struct
@@ -1642,6 +1720,97 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+void kvm_vgic_destroy(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vgic_vcpu_destroy(vcpu);
+
+	vgic_free_bitmap(&dist->irq_enabled);
+	vgic_free_bitmap(&dist->irq_level);
+	vgic_free_bitmap(&dist->irq_pending);
+	vgic_free_bitmap(&dist->irq_soft_pend);
+	vgic_free_bitmap(&dist->irq_queued);
+	vgic_free_bitmap(&dist->irq_cfg);
+	vgic_free_bytemap(&dist->irq_priority);
+	if (dist->irq_spi_target) {
+		for (i = 0; i < dist->nr_cpus; i++)
+			vgic_free_bitmap(&dist->irq_spi_target[i]);
+	}
+	kfree(dist->irq_sgi_sources);
+	kfree(dist->irq_spi_cpu);
+	kfree(dist->irq_spi_target);
+	kfree(dist->irq_pending_on_cpu);
+	dist->irq_sgi_sources = NULL;
+	dist->irq_spi_cpu = NULL;
+	dist->irq_spi_target = NULL;
+	dist->irq_pending_on_cpu = NULL;
+}
+
+/*
+ * Allocate and initialize the various data structures. Must be called
+ * with kvm->lock held!
+ */
+static int vgic_init_maps(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct kvm_vcpu *vcpu;
+	int nr_cpus, nr_irqs;
+	int ret, i;
+
+	nr_cpus = dist->nr_cpus = VGIC_MAX_CPUS;
+	nr_irqs = dist->nr_irqs = VGIC_NR_IRQS;
+
+	ret  = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_level, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs);
+	ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs);
+
+	if (ret)
+		goto out;
+
+	dist->irq_sgi_sources = kzalloc(nr_cpus * VGIC_NR_SGIS, GFP_KERNEL);
+	dist->irq_spi_cpu = kzalloc(nr_irqs - VGIC_NR_PRIVATE_IRQS, GFP_KERNEL);
+	dist->irq_spi_target = kzalloc(sizeof(*dist->irq_spi_target) * nr_cpus,
+				       GFP_KERNEL);
+	dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
+					   GFP_KERNEL);
+	if (!dist->irq_sgi_sources ||
+	    !dist->irq_spi_cpu ||
+	    !dist->irq_spi_target ||
+	    !dist->irq_pending_on_cpu) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < nr_cpus; i++)
+		ret |= vgic_init_bitmap(&dist->irq_spi_target[i],
+					nr_cpus, nr_irqs);
+
+	if (ret)
+		goto out;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
+		if (ret) {
+			kvm_err("VGIC: Failed to allocate vcpu memory\n");
+			break;
+		}
+	}
+
+out:
+	if (ret)
+		kvm_vgic_destroy(kvm);
+
+	return ret;
+}
+
 /**
  * kvm_vgic_init - Initialize global VGIC state before running any VCPUs
  * @kvm: pointer to the kvm struct
@@ -1722,6 +1891,10 @@ int kvm_vgic_create(struct kvm *kvm)
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
 
+	ret = vgic_init_maps(kvm);
+	if (ret)
+		kvm_err("Unable to allocate maps\n");
+
 out_unlock:
 	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
 		vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
-- 
cgit v1.2.3


From fb65ab63b8cae510ea1e43e68b5da2f9980aa6d5 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 8 Jul 2014 12:09:02 +0100
Subject: arm/arm64: KVM: vgic: Parametrize VGIC_NR_SHARED_IRQS

Having a dynamic number of supported interrupts means that we
cannot relly on VGIC_NR_SHARED_IRQS being fixed anymore.

Instead, make it take the distributor structure as a parameter,
so it can return the right value.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 include/kvm/arm_vgic.h |  1 -
 virt/kvm/arm/vgic.c    | 16 +++++++++++-----
 2 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index fd1b8f252da1..b2f9936df319 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -29,7 +29,6 @@
 #define VGIC_NR_SGIS		16
 #define VGIC_NR_PPIS		16
 #define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
-#define VGIC_NR_SHARED_IRQS	(VGIC_NR_IRQS - VGIC_NR_PRIVATE_IRQS)
 #define VGIC_MAX_CPUS		KVM_MAX_VCPUS
 
 #define VGIC_V2_MAX_LRS		(1 << 6)
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 08db8764496a..7d64dc242afc 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1086,11 +1086,17 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 	}
 }
 
+static int vgic_nr_shared_irqs(struct vgic_dist *dist)
+{
+	return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
+}
+
 static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	unsigned long *pending, *enabled, *pend_percpu, *pend_shared;
 	unsigned long pending_private, pending_shared;
+	int nr_shared = vgic_nr_shared_irqs(dist);
 	int vcpu_id;
 
 	vcpu_id = vcpu->vcpu_id;
@@ -1103,15 +1109,15 @@ static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
 
 	pending = vgic_bitmap_get_shared_map(&dist->irq_pending);
 	enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
-	bitmap_and(pend_shared, pending, enabled, VGIC_NR_SHARED_IRQS);
+	bitmap_and(pend_shared, pending, enabled, nr_shared);
 	bitmap_and(pend_shared, pend_shared,
 		   vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
-		   VGIC_NR_SHARED_IRQS);
+		   nr_shared);
 
 	pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS);
-	pending_shared = find_first_bit(pend_shared, VGIC_NR_SHARED_IRQS);
+	pending_shared = find_first_bit(pend_shared, nr_shared);
 	return (pending_private < VGIC_NR_PRIVATE_IRQS ||
-		pending_shared < VGIC_NR_SHARED_IRQS);
+		pending_shared < vgic_nr_shared_irqs(dist));
 }
 
 /*
@@ -1368,7 +1374,7 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 	}
 
 	/* SPIs */
-	for_each_set_bit(i, vgic_cpu->pending_shared, VGIC_NR_SHARED_IRQS) {
+	for_each_set_bit(i, vgic_cpu->pending_shared, vgic_nr_shared_irqs(dist)) {
 		if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
 			overflow = 1;
 	}
-- 
cgit v1.2.3


From fc675e355e705a046df7b635d3f3330c0ad94569 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 8 Jul 2014 12:09:03 +0100
Subject: arm/arm64: KVM: vgic: kill VGIC_MAX_CPUS

We now have the information about the number of CPU interfaces in
the distributor itself. Let's get rid of VGIC_MAX_CPUS, and just
rely on KVM_MAX_VCPUS where we don't have the choice. Yet.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 include/kvm/arm_vgic.h | 3 +--
 virt/kvm/arm/vgic.c    | 6 +++---
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index b2f9936df319..3b73d7845124 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -29,13 +29,12 @@
 #define VGIC_NR_SGIS		16
 #define VGIC_NR_PPIS		16
 #define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
-#define VGIC_MAX_CPUS		KVM_MAX_VCPUS
 
 #define VGIC_V2_MAX_LRS		(1 << 6)
 #define VGIC_V3_MAX_LRS		16
 
 /* Sanity checks... */
-#if (VGIC_MAX_CPUS > 8)
+#if (KVM_MAX_VCPUS > 8)
 #error	Invalid number of CPU interfaces
 #endif
 
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 7d64dc242afc..599ad17e5436 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1297,7 +1297,7 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
 
 	sources = *vgic_get_sgi_sources(dist, vcpu_id, irq);
 
-	for_each_set_bit(c, &sources, VGIC_MAX_CPUS) {
+	for_each_set_bit(c, &sources, dist->nr_cpus) {
 		if (vgic_queue_irq(vcpu, c, irq))
 			clear_bit(c, &sources);
 	}
@@ -1700,7 +1700,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	int i;
 
-	if (vcpu->vcpu_id >= VGIC_MAX_CPUS)
+	if (vcpu->vcpu_id >= dist->nr_cpus)
 		return -EBUSY;
 
 	for (i = 0; i < VGIC_NR_IRQS; i++) {
@@ -1767,7 +1767,7 @@ static int vgic_init_maps(struct kvm *kvm)
 	int nr_cpus, nr_irqs;
 	int ret, i;
 
-	nr_cpus = dist->nr_cpus = VGIC_MAX_CPUS;
+	nr_cpus = dist->nr_cpus = KVM_MAX_VCPUS;
 	nr_irqs = dist->nr_irqs = VGIC_NR_IRQS;
 
 	ret  = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs);
-- 
cgit v1.2.3


From c3c918361adcceb816c92b21dd95d2b46fb96a8f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 8 Jul 2014 12:09:04 +0100
Subject: arm/arm64: KVM: vgic: handle out-of-range MMIO accesses

Now that we can (almost) dynamically size the number of interrupts,
we're facing an interesting issue:

We have to evaluate at runtime whether or not an access hits a valid
register, based on the sizing of this particular instance of the
distributor. Furthermore, the GIC spec says that accessing a reserved
register is RAZ/WI.

For this, add a new field to our range structure, indicating the number
of bits a single interrupts uses. That allows us to find out whether or
not the access is in range.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 include/kvm/arm_vgic.h |  3 ++-
 virt/kvm/arm/vgic.c    | 56 ++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 47 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 3b73d7845124..2767f939f47c 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -32,6 +32,7 @@
 
 #define VGIC_V2_MAX_LRS		(1 << 6)
 #define VGIC_V3_MAX_LRS		16
+#define VGIC_MAX_IRQS		1024
 
 /* Sanity checks... */
 #if (KVM_MAX_VCPUS > 8)
@@ -42,7 +43,7 @@
 #error "VGIC_NR_IRQS must be a multiple of 32"
 #endif
 
-#if (VGIC_NR_IRQS > 1024)
+#if (VGIC_NR_IRQS > VGIC_MAX_IRQS)
 #error "VGIC_NR_IRQS must be <= 1024"
 #endif
 
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 599ad17e5436..973eaf7ebe98 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -895,6 +895,7 @@ static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
 struct mmio_range {
 	phys_addr_t base;
 	unsigned long len;
+	int bits_per_irq;
 	bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
 			    phys_addr_t offset);
 };
@@ -903,56 +904,67 @@ static const struct mmio_range vgic_dist_ranges[] = {
 	{
 		.base		= GIC_DIST_CTRL,
 		.len		= 12,
+		.bits_per_irq	= 0,
 		.handle_mmio	= handle_mmio_misc,
 	},
 	{
 		.base		= GIC_DIST_IGROUP,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{
 		.base		= GIC_DIST_ENABLE_SET,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_set_enable_reg,
 	},
 	{
 		.base		= GIC_DIST_ENABLE_CLEAR,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_clear_enable_reg,
 	},
 	{
 		.base		= GIC_DIST_PENDING_SET,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_set_pending_reg,
 	},
 	{
 		.base		= GIC_DIST_PENDING_CLEAR,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_clear_pending_reg,
 	},
 	{
 		.base		= GIC_DIST_ACTIVE_SET,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{
 		.base		= GIC_DIST_ACTIVE_CLEAR,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{
 		.base		= GIC_DIST_PRI,
-		.len		= VGIC_NR_IRQS,
+		.len		= VGIC_MAX_IRQS,
+		.bits_per_irq	= 8,
 		.handle_mmio	= handle_mmio_priority_reg,
 	},
 	{
 		.base		= GIC_DIST_TARGET,
-		.len		= VGIC_NR_IRQS,
+		.len		= VGIC_MAX_IRQS,
+		.bits_per_irq	= 8,
 		.handle_mmio	= handle_mmio_target_reg,
 	},
 	{
 		.base		= GIC_DIST_CONFIG,
-		.len		= VGIC_NR_IRQS / 4,
+		.len		= VGIC_MAX_IRQS / 4,
+		.bits_per_irq	= 2,
 		.handle_mmio	= handle_mmio_cfg_reg,
 	},
 	{
@@ -990,6 +1002,22 @@ struct mmio_range *find_matching_range(const struct mmio_range *ranges,
 	return NULL;
 }
 
+static bool vgic_validate_access(const struct vgic_dist *dist,
+				 const struct mmio_range *range,
+				 unsigned long offset)
+{
+	int irq;
+
+	if (!range->bits_per_irq)
+		return true;	/* Not an irq-based access */
+
+	irq = offset * 8 / range->bits_per_irq;
+	if (irq >= dist->nr_irqs)
+		return false;
+
+	return true;
+}
+
 /**
  * vgic_handle_mmio - handle an in-kernel MMIO access
  * @vcpu:	pointer to the vcpu performing the access
@@ -1029,7 +1057,13 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 	spin_lock(&vcpu->kvm->arch.vgic.lock);
 	offset = mmio->phys_addr - range->base - base;
-	updated_state = range->handle_mmio(vcpu, mmio, offset);
+	if (vgic_validate_access(dist, range, offset)) {
+		updated_state = range->handle_mmio(vcpu, mmio, offset);
+	} else {
+		vgic_reg_access(mmio, NULL, offset,
+				ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
+		updated_state = false;
+	}
 	spin_unlock(&vcpu->kvm->arch.vgic.lock);
 	kvm_prepare_mmio(run, mmio);
 	kvm_handle_mmio_return(vcpu, run);
-- 
cgit v1.2.3


From 5fb66da64064d0cb8dcce4cc8bf4cb1b921b13a0 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 8 Jul 2014 12:09:05 +0100
Subject: arm/arm64: KVM: vgic: kill VGIC_NR_IRQS

Nuke VGIC_NR_IRQS entierly, now that the distributor instance
contains the number of IRQ allocated to this GIC.

Also add VGIC_NR_IRQS_LEGACY to preserve the current API.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 include/kvm/arm_vgic.h |  6 +++---
 virt/kvm/arm/vgic.c    | 17 +++++++++++------
 2 files changed, 14 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 2767f939f47c..aa20d4a7242f 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -25,7 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
-#define VGIC_NR_IRQS		256
+#define VGIC_NR_IRQS_LEGACY	256
 #define VGIC_NR_SGIS		16
 #define VGIC_NR_PPIS		16
 #define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
@@ -39,11 +39,11 @@
 #error	Invalid number of CPU interfaces
 #endif
 
-#if (VGIC_NR_IRQS & 31)
+#if (VGIC_NR_IRQS_LEGACY & 31)
 #error "VGIC_NR_IRQS must be a multiple of 32"
 #endif
 
-#if (VGIC_NR_IRQS > VGIC_MAX_IRQS)
+#if (VGIC_NR_IRQS_LEGACY > VGIC_MAX_IRQS)
 #error "VGIC_NR_IRQS must be <= 1024"
 #endif
 
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 973eaf7ebe98..725d829ad1d9 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -439,7 +439,7 @@ static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
 
 	case 4:			/* GICD_TYPER */
 		reg  = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
-		reg |= (VGIC_NR_IRQS >> 5) - 1;
+		reg |= (vcpu->kvm->arch.vgic.nr_irqs >> 5) - 1;
 		vgic_reg_access(mmio, &reg, word_offset,
 				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
 		break;
@@ -1277,13 +1277,14 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
 static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	struct vgic_lr vlr;
 	int lr;
 
 	/* Sanitize the input... */
 	BUG_ON(sgi_source_id & ~7);
 	BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS);
-	BUG_ON(irq >= VGIC_NR_IRQS);
+	BUG_ON(irq >= dist->nr_irqs);
 
 	kvm_debug("Queue IRQ%d\n", irq);
 
@@ -1515,7 +1516,7 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 
 		vlr = vgic_get_lr(vcpu, lr);
 
-		BUG_ON(vlr.irq >= VGIC_NR_IRQS);
+		BUG_ON(vlr.irq >= dist->nr_irqs);
 		vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY;
 	}
 
@@ -1737,7 +1738,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	if (vcpu->vcpu_id >= dist->nr_cpus)
 		return -EBUSY;
 
-	for (i = 0; i < VGIC_NR_IRQS; i++) {
+	for (i = 0; i < dist->nr_irqs; i++) {
 		if (i < VGIC_NR_PPIS)
 			vgic_bitmap_set_irq_val(&dist->irq_enabled,
 						vcpu->vcpu_id, i, 1);
@@ -1802,7 +1803,11 @@ static int vgic_init_maps(struct kvm *kvm)
 	int ret, i;
 
 	nr_cpus = dist->nr_cpus = KVM_MAX_VCPUS;
-	nr_irqs = dist->nr_irqs = VGIC_NR_IRQS;
+
+	if (!dist->nr_irqs)
+		dist->nr_irqs = VGIC_NR_IRQS_LEGACY;
+
+	nr_irqs = dist->nr_irqs;
 
 	ret  = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs);
 	ret |= vgic_init_bitmap(&dist->irq_level, nr_cpus, nr_irqs);
@@ -1886,7 +1891,7 @@ int kvm_vgic_init(struct kvm *kvm)
 		goto out;
 	}
 
-	for (i = VGIC_NR_PRIVATE_IRQS; i < VGIC_NR_IRQS; i += 4)
+	for (i = VGIC_NR_PRIVATE_IRQS; i < kvm->arch.vgic.nr_irqs; i += 4)
 		vgic_set_target_reg(kvm, 0, i);
 
 	kvm->arch.vgic.ready = true;
-- 
cgit v1.2.3


From 4956f2bc1fdee4bc336532f3f34635a8534cedfd Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 8 Jul 2014 12:09:06 +0100
Subject: arm/arm64: KVM: vgic: delay vgic allocation until init time

It is now quite easy to delay the allocation of the vgic tables
until we actually require it to be up and running (when the first
vcpu is kicking around, or someones tries to access the GIC registers).

This allow us to allocate memory for the exact number of CPUs we
have. As nobody configures the number of interrupts just yet,
use a fallback to VGIC_NR_IRQS_LEGACY.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 arch/arm/kvm/arm.c     |  7 -------
 include/kvm/arm_vgic.h |  1 -
 virt/kvm/arm/vgic.c    | 42 +++++++++++++++++++++++++++++-------------
 3 files changed, 29 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index c1a11496817b..40bc3df6d87b 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -261,16 +261,9 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
-	int ret;
-
 	/* Force users to call KVM_ARM_VCPU_INIT */
 	vcpu->arch.target = -1;
 
-	/* Set up VGIC */
-	ret = kvm_vgic_vcpu_init(vcpu);
-	if (ret)
-		return ret;
-
 	/* Set up the timer */
 	kvm_timer_vcpu_init(vcpu);
 
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index aa20d4a7242f..2f2aac8448a4 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -277,7 +277,6 @@ int kvm_vgic_hyp_init(void);
 int kvm_vgic_init(struct kvm *kvm);
 int kvm_vgic_create(struct kvm *kvm);
 void kvm_vgic_destroy(struct kvm *kvm);
-int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 725d829ad1d9..ac2b44d58e60 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1729,15 +1729,12 @@ static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
  * Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to
  * this vcpu and enable the VGIC for this VCPU
  */
-int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	int i;
 
-	if (vcpu->vcpu_id >= dist->nr_cpus)
-		return -EBUSY;
-
 	for (i = 0; i < dist->nr_irqs; i++) {
 		if (i < VGIC_NR_PPIS)
 			vgic_bitmap_set_irq_val(&dist->irq_enabled,
@@ -1757,8 +1754,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	vgic_cpu->nr_lr = vgic->nr_lr;
 
 	vgic_enable(vcpu);
-
-	return 0;
 }
 
 void kvm_vgic_destroy(struct kvm *kvm)
@@ -1802,8 +1797,17 @@ static int vgic_init_maps(struct kvm *kvm)
 	int nr_cpus, nr_irqs;
 	int ret, i;
 
-	nr_cpus = dist->nr_cpus = KVM_MAX_VCPUS;
+	if (dist->nr_cpus)	/* Already allocated */
+		return 0;
+
+	nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
+	if (!nr_cpus)		/* No vcpus? Can't be good... */
+		return -EINVAL;
 
+	/*
+	 * If nobody configured the number of interrupts, use the
+	 * legacy one.
+	 */
 	if (!dist->nr_irqs)
 		dist->nr_irqs = VGIC_NR_IRQS_LEGACY;
 
@@ -1849,6 +1853,9 @@ static int vgic_init_maps(struct kvm *kvm)
 		}
 	}
 
+	for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
+		vgic_set_target_reg(kvm, 0, i);
+
 out:
 	if (ret)
 		kvm_vgic_destroy(kvm);
@@ -1867,6 +1874,7 @@ out:
  */
 int kvm_vgic_init(struct kvm *kvm)
 {
+	struct kvm_vcpu *vcpu;
 	int ret = 0, i;
 
 	if (!irqchip_in_kernel(kvm))
@@ -1884,6 +1892,12 @@ int kvm_vgic_init(struct kvm *kvm)
 		goto out;
 	}
 
+	ret = vgic_init_maps(kvm);
+	if (ret) {
+		kvm_err("Unable to allocate maps\n");
+		goto out;
+	}
+
 	ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base,
 				    vgic->vcpu_base, KVM_VGIC_V2_CPU_SIZE);
 	if (ret) {
@@ -1891,11 +1905,13 @@ int kvm_vgic_init(struct kvm *kvm)
 		goto out;
 	}
 
-	for (i = VGIC_NR_PRIVATE_IRQS; i < kvm->arch.vgic.nr_irqs; i += 4)
-		vgic_set_target_reg(kvm, 0, i);
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vgic_vcpu_init(vcpu);
 
 	kvm->arch.vgic.ready = true;
 out:
+	if (ret)
+		kvm_vgic_destroy(kvm);
 	mutex_unlock(&kvm->lock);
 	return ret;
 }
@@ -1936,10 +1952,6 @@ int kvm_vgic_create(struct kvm *kvm)
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
 
-	ret = vgic_init_maps(kvm);
-	if (ret)
-		kvm_err("Unable to allocate maps\n");
-
 out_unlock:
 	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
 		vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
@@ -2140,6 +2152,10 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->lock);
 
+	ret = vgic_init_maps(dev->kvm);
+	if (ret)
+		goto out;
+
 	if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) {
 		ret = -EINVAL;
 		goto out;
-- 
cgit v1.2.3


From 84d7fce693884897c6196cc98228a2ad56ae2a9a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 4 Sep 2014 14:30:22 +0200
Subject: netfilter: nf_tables: export rule-set generation ID

This patch exposes the ruleset generation ID in three ways:

1) The new command NFT_MSG_GETGEN that exposes the 32-bits ruleset
   generation ID. This ID is incremented in every commit and it
   should be large enough to avoid wraparound problems.

2) The less significant 16-bits of the generation ID are exposed through
   the nfgenmsg->res_id header field. This allows us to quickly catch
   if the ruleset has change between two consecutive list dumps from
   different object lists (in this specific case I think the risk of
   wraparound is unlikely).

3) Userspace subscribers may receive notifications of new rule-set
   generation after every commit. This also provides an alternative
   way to monitor the generation ID. If the events are lost, the
   userspace process hits a overrun error, so it knows that it is
   working with a stale ruleset anyway.

Patrick spotted that rule-set transformations in userspace may take
quite some time. In that case, it annotates the 32-bits generation ID
before fetching the rule-set, then:

1) it compares it to what we obtain after the transformation to
   make sure it is not working with a stale rule-set and no wraparound
   has ocurred.

2) it subscribes to ruleset notifications, so it can watch for new
   generation ID.

This is complementary to the NLM_F_DUMP_INTR approach, which allows
us to detect an interference in the middle one single list dumping.
There is no way to explicitly check that an interference has occurred
between two list dumps from the kernel, since it doesn't know how
many lists the userspace client is actually going to dump.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  16 ++++
 net/netfilter/nf_tables_api.c            | 140 +++++++++++++++++++++++++------
 2 files changed, 130 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 66d66dd3ff79..b72ccfeaf865 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -51,6 +51,8 @@ enum nft_verdicts {
  * @NFT_MSG_NEWSETELEM: create a new set element (enum nft_set_elem_attributes)
  * @NFT_MSG_GETSETELEM: get a set element (enum nft_set_elem_attributes)
  * @NFT_MSG_DELSETELEM: delete a set element (enum nft_set_elem_attributes)
+ * @NFT_MSG_NEWGEN: announce a new generation, only for events (enum nft_gen_attributes)
+ * @NFT_MSG_GETGEN: get the rule-set generation (enum nft_gen_attributes)
  */
 enum nf_tables_msg_types {
 	NFT_MSG_NEWTABLE,
@@ -68,6 +70,8 @@ enum nf_tables_msg_types {
 	NFT_MSG_NEWSETELEM,
 	NFT_MSG_GETSETELEM,
 	NFT_MSG_DELSETELEM,
+	NFT_MSG_NEWGEN,
+	NFT_MSG_GETGEN,
 	NFT_MSG_MAX,
 };
 
@@ -812,4 +816,16 @@ enum nft_masq_attributes {
 };
 #define NFTA_MASQ_MAX		(__NFTA_MASQ_MAX - 1)
 
+/**
+ * enum nft_gen_attributes - nf_tables ruleset generation attributes
+ *
+ * @NFTA_GEN_ID: Ruleset generation ID (NLA_U32)
+ */
+enum nft_gen_attributes {
+	NFTA_GEN_UNSPEC,
+	NFTA_GEN_ID,
+	__NFTA_GEN_MAX
+};
+#define NFTA_GEN_MAX		(__NFTA_GEN_MAX - 1)
+
 #endif /* _LINUX_NF_TABLES_H */
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 82374601577e..a476b9962155 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -405,9 +405,9 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
 	[NFTA_TABLE_FLAGS]	= { .type = NLA_U32 },
 };
 
-static int nf_tables_fill_table_info(struct sk_buff *skb, u32 portid, u32 seq,
-				     int event, u32 flags, int family,
-				     const struct nft_table *table)
+static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
+				     u32 portid, u32 seq, int event, u32 flags,
+				     int family, const struct nft_table *table)
 {
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
@@ -420,7 +420,7 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, u32 portid, u32 seq,
 	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family	= family;
 	nfmsg->version		= NFNETLINK_V0;
-	nfmsg->res_id		= 0;
+	nfmsg->res_id		= htons(net->nft.base_seq & 0xffff);
 
 	if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) ||
 	    nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) ||
@@ -448,8 +448,8 @@ static int nf_tables_table_notify(const struct nft_ctx *ctx, int event)
 	if (skb == NULL)
 		goto err;
 
-	err = nf_tables_fill_table_info(skb, ctx->portid, ctx->seq, event, 0,
-					ctx->afi->family, ctx->table);
+	err = nf_tables_fill_table_info(skb, ctx->net, ctx->portid, ctx->seq,
+					event, 0, ctx->afi->family, ctx->table);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto err;
@@ -488,7 +488,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 			if (idx > s_idx)
 				memset(&cb->args[1], 0,
 				       sizeof(cb->args) - sizeof(cb->args[0]));
-			if (nf_tables_fill_table_info(skb,
+			if (nf_tables_fill_table_info(skb, net,
 						      NETLINK_CB(cb->skb).portid,
 						      cb->nlh->nlmsg_seq,
 						      NFT_MSG_NEWTABLE,
@@ -540,7 +540,7 @@ static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
 	if (!skb2)
 		return -ENOMEM;
 
-	err = nf_tables_fill_table_info(skb2, NETLINK_CB(skb).portid,
+	err = nf_tables_fill_table_info(skb2, net, NETLINK_CB(skb).portid,
 					nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0,
 					family, table);
 	if (err < 0)
@@ -914,9 +914,9 @@ nla_put_failure:
 	return -ENOSPC;
 }
 
-static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
-				     int event, u32 flags, int family,
-				     const struct nft_table *table,
+static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
+				     u32 portid, u32 seq, int event, u32 flags,
+				     int family, const struct nft_table *table,
 				     const struct nft_chain *chain)
 {
 	struct nlmsghdr *nlh;
@@ -930,7 +930,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
 	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family	= family;
 	nfmsg->version		= NFNETLINK_V0;
-	nfmsg->res_id		= 0;
+	nfmsg->res_id		= htons(net->nft.base_seq & 0xffff);
 
 	if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name))
 		goto nla_put_failure;
@@ -988,8 +988,8 @@ static int nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
 	if (skb == NULL)
 		goto err;
 
-	err = nf_tables_fill_chain_info(skb, ctx->portid, ctx->seq, event, 0,
-					ctx->afi->family, ctx->table,
+	err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq,
+					event, 0, ctx->afi->family, ctx->table,
 					ctx->chain);
 	if (err < 0) {
 		kfree_skb(skb);
@@ -1031,7 +1031,8 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 				if (idx > s_idx)
 					memset(&cb->args[1], 0,
 					       sizeof(cb->args) - sizeof(cb->args[0]));
-				if (nf_tables_fill_chain_info(skb, NETLINK_CB(cb->skb).portid,
+				if (nf_tables_fill_chain_info(skb, net,
+							      NETLINK_CB(cb->skb).portid,
 							      cb->nlh->nlmsg_seq,
 							      NFT_MSG_NEWCHAIN,
 							      NLM_F_MULTI,
@@ -1090,7 +1091,7 @@ static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
 	if (!skb2)
 		return -ENOMEM;
 
-	err = nf_tables_fill_chain_info(skb2, NETLINK_CB(skb).portid,
+	err = nf_tables_fill_chain_info(skb2, net, NETLINK_CB(skb).portid,
 					nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0,
 					family, table, chain);
 	if (err < 0)
@@ -1647,8 +1648,9 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
 				    .len = NFT_USERDATA_MAXLEN },
 };
 
-static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
-				    int event, u32 flags, int family,
+static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
+				    u32 portid, u32 seq, int event,
+				    u32 flags, int family,
 				    const struct nft_table *table,
 				    const struct nft_chain *chain,
 				    const struct nft_rule *rule)
@@ -1668,7 +1670,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
 	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family	= family;
 	nfmsg->version		= NFNETLINK_V0;
-	nfmsg->res_id		= 0;
+	nfmsg->res_id		= htons(net->nft.base_seq & 0xffff);
 
 	if (nla_put_string(skb, NFTA_RULE_TABLE, table->name))
 		goto nla_put_failure;
@@ -1724,8 +1726,8 @@ static int nf_tables_rule_notify(const struct nft_ctx *ctx,
 	if (skb == NULL)
 		goto err;
 
-	err = nf_tables_fill_rule_info(skb, ctx->portid, ctx->seq, event, 0,
-				       ctx->afi->family, ctx->table,
+	err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq,
+				       event, 0, ctx->afi->family, ctx->table,
 				       ctx->chain, rule);
 	if (err < 0) {
 		kfree_skb(skb);
@@ -1771,7 +1773,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 					if (idx > s_idx)
 						memset(&cb->args[1], 0,
 						       sizeof(cb->args) - sizeof(cb->args[0]));
-					if (nf_tables_fill_rule_info(skb, NETLINK_CB(cb->skb).portid,
+					if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid,
 								      cb->nlh->nlmsg_seq,
 								      NFT_MSG_NEWRULE,
 								      NLM_F_MULTI | NLM_F_APPEND,
@@ -1837,7 +1839,7 @@ static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb,
 	if (!skb2)
 		return -ENOMEM;
 
-	err = nf_tables_fill_rule_info(skb2, NETLINK_CB(skb).portid,
+	err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid,
 				       nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0,
 				       family, table, chain, rule);
 	if (err < 0)
@@ -2321,7 +2323,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family	= ctx->afi->family;
 	nfmsg->version		= NFNETLINK_V0;
-	nfmsg->res_id		= 0;
+	nfmsg->res_id		= htons(ctx->net->nft.base_seq & 0xffff);
 
 	if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name))
 		goto nla_put_failure;
@@ -2925,7 +2927,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family = ctx.afi->family;
 	nfmsg->version      = NFNETLINK_V0;
-	nfmsg->res_id       = 0;
+	nfmsg->res_id	    = htons(ctx.net->nft.base_seq & 0xffff);
 
 	if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, ctx.table->name))
 		goto nla_put_failure;
@@ -3006,7 +3008,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
 	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family	= ctx->afi->family;
 	nfmsg->version		= NFNETLINK_V0;
-	nfmsg->res_id		= 0;
+	nfmsg->res_id		= htons(ctx->net->nft.base_seq & 0xffff);
 
 	if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name))
 		goto nla_put_failure;
@@ -3293,6 +3295,87 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
 	return err;
 }
 
+static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
+				   u32 portid, u32 seq)
+{
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfmsg;
+	int event = (NFNL_SUBSYS_NFTABLES << 8) | NFT_MSG_NEWGEN;
+
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), 0);
+	if (nlh == NULL)
+		goto nla_put_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family	= AF_UNSPEC;
+	nfmsg->version		= NFNETLINK_V0;
+	nfmsg->res_id		= htons(net->nft.base_seq & 0xffff);
+
+	if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)))
+		goto nla_put_failure;
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_trim(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int nf_tables_gen_notify(struct net *net, struct sk_buff *skb, int event)
+{
+	struct nlmsghdr *nlh = nlmsg_hdr(skb);
+	struct sk_buff *skb2;
+	int err;
+
+	if (nlmsg_report(nlh) &&
+	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+		return 0;
+
+	err = -ENOBUFS;
+	skb2 = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (skb2 == NULL)
+		goto err;
+
+	err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid,
+				      nlh->nlmsg_seq);
+	if (err < 0) {
+		kfree_skb(skb2);
+		goto err;
+	}
+
+	err = nfnetlink_send(skb2, net, NETLINK_CB(skb).portid,
+			     NFNLGRP_NFTABLES, nlmsg_report(nlh), GFP_KERNEL);
+err:
+	if (err < 0) {
+		nfnetlink_set_err(net, NETLINK_CB(skb).portid, NFNLGRP_NFTABLES,
+				  err);
+	}
+	return err;
+}
+
+static int nf_tables_getgen(struct sock *nlsk, struct sk_buff *skb,
+			    const struct nlmsghdr *nlh,
+			    const struct nlattr * const nla[])
+{
+	struct net *net = sock_net(skb->sk);
+	struct sk_buff *skb2;
+	int err;
+
+	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (skb2 == NULL)
+		return -ENOMEM;
+
+	err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid,
+				      nlh->nlmsg_seq);
+	if (err < 0)
+		goto err;
+
+	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+err:
+	kfree_skb(skb2);
+	return err;
+}
+
 static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 	[NFT_MSG_NEWTABLE] = {
 		.call_batch	= nf_tables_newtable,
@@ -3369,6 +3452,9 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.attr_count	= NFTA_SET_ELEM_LIST_MAX,
 		.policy		= nft_set_elem_list_policy,
 	},
+	[NFT_MSG_GETGEN] = {
+		.call		= nf_tables_getgen,
+	},
 };
 
 static void nft_chain_commit_update(struct nft_trans *trans)
@@ -3526,6 +3612,8 @@ static int nf_tables_commit(struct sk_buff *skb)
 		call_rcu(&trans->rcu_head, nf_tables_commit_release_rcu);
 	}
 
+	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From f6be8af1c95de4a46e325e728900a70ceadb52cf Mon Sep 17 00:00:00 2001
From: Chuansheng Liu <chuansheng.liu@intel.com>
Date: Thu, 4 Sep 2014 15:17:53 +0800
Subject: sched: Add new API wake_up_if_idle() to wake up the idle cpu

Implementing one new API wake_up_if_idle(), which is used to
wake up the idle CPU.

Suggested-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Chuansheng Liu <chuansheng.liu@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: daniel.lezcano@linaro.org
Cc: rjw@rjwysocki.net
Cc: linux-pm@vger.kernel.org
Cc: changcheng.liu@intel.com
Cc: xiaoming.wang@intel.com
Cc: souvik.k.chakravarty@intel.com
Cc: chuansheng.liu@intel.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1409815075-4180-1-git-send-email-chuansheng.liu@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  1 +
 kernel/sched/core.c   | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index dd9eb4807389..82ff3d6efb19 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1024,6 +1024,7 @@ struct sched_domain_topology_level {
 extern struct sched_domain_topology_level *sched_domain_topology;
 
 extern void set_sched_topology(struct sched_domain_topology_level *tl);
+extern void wake_up_if_idle(int cpu);
 
 #ifdef CONFIG_SCHED_DEBUG
 # define SD_INIT_NAME(type)		.name = #type
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78e5c839df13..f7c6ed2fd69d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1634,6 +1634,25 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu)
 	}
 }
 
+void wake_up_if_idle(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	if (!is_idle_task(rq->curr))
+		return;
+
+	if (set_nr_if_polling(rq->idle)) {
+		trace_sched_wake_idle_without_ipi(cpu);
+	} else {
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		if (is_idle_task(rq->curr))
+			smp_send_reschedule(cpu);
+		/* Else cpu is not in idle, do nothing here */
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	}
+}
+
 bool cpus_share_cache(int this_cpu, int that_cpu)
 {
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
-- 
cgit v1.2.3


From c6f4459fc3ba532e896cb678e29b45cb985f82bf Mon Sep 17 00:00:00 2001
From: Chuansheng Liu <chuansheng.liu@intel.com>
Date: Thu, 4 Sep 2014 15:17:54 +0800
Subject: smp: Add new wake_up_all_idle_cpus() function

Currently kick_all_cpus_sync() can break non-polling idle cpus
thru IPI interrupts.

But sometimes we need to break the polling idle cpus immediately
to reselect the suitable c-state, also for non-idle cpus, we need
to do nothing if we try to wake up them.

Here adding one new function wake_up_all_idle_cpus() to let all cpus
out of idle based on function wake_up_if_idle().

Signed-off-by: Chuansheng Liu <chuansheng.liu@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: daniel.lezcano@linaro.org
Cc: rjw@rjwysocki.net
Cc: linux-pm@vger.kernel.org
Cc: changcheng.liu@intel.com
Cc: xiaoming.wang@intel.com
Cc: souvik.k.chakravarty@intel.com
Cc: luto@amacapital.net
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@fb.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1409815075-4180-2-git-send-email-chuansheng.liu@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/smp.h |  2 ++
 kernel/smp.c        | 22 ++++++++++++++++++++++
 2 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/linux/smp.h b/include/linux/smp.h
index 34347f26be9b..93dff5fff524 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -100,6 +100,7 @@ int smp_call_function_any(const struct cpumask *mask,
 			  smp_call_func_t func, void *info, int wait);
 
 void kick_all_cpus_sync(void);
+void wake_up_all_idle_cpus(void);
 
 /*
  * Generic and arch helpers
@@ -148,6 +149,7 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
 }
 
 static inline void kick_all_cpus_sync(void) {  }
+static inline void wake_up_all_idle_cpus(void) {  }
 
 #endif /* !SMP */
 
diff --git a/kernel/smp.c b/kernel/smp.c
index aff8aa14f547..9e0d0b289118 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -13,6 +13,7 @@
 #include <linux/gfp.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
+#include <linux/sched.h>
 
 #include "smpboot.h"
 
@@ -699,3 +700,24 @@ void kick_all_cpus_sync(void)
 	smp_call_function(do_nothing, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(kick_all_cpus_sync);
+
+/**
+ * wake_up_all_idle_cpus - break all cpus out of idle
+ * wake_up_all_idle_cpus try to break all cpus which is in idle state even
+ * including idle polling cpus, for non-idle cpus, we will do nothing
+ * for them.
+ */
+void wake_up_all_idle_cpus(void)
+{
+	int cpu;
+
+	preempt_disable();
+	for_each_online_cpu(cpu) {
+		if (cpu == smp_processor_id())
+			continue;
+
+		wake_up_if_idle(cpu);
+	}
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus);
-- 
cgit v1.2.3


From ef8ac06359ddf95431cf6bb04ad2b36fff562328 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Fri, 12 Sep 2014 09:12:14 -0400
Subject: seqlock: Add irqsave variant of read_seqbegin_or_lock()

There are cases where read_seqbegin_or_lock() needs to block irqs,
because the seqlock in question nests inside a lock that is also
be taken from irq context.

Add read_seqbegin_or_lock_irqsave() and done_seqretry_irqrestore(), which
are almost identical to read_seqbegin_or_lock() and done_seqretry().

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: prarit@redhat.com
Cc: oleg@redhat.com
Cc: sgruszka@redhat.com
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Stephen Boyd <sboyd@codeaurora.org>
Cc: Trond Myklebust <trond.myklebust@primarydata.com>
Link: http://lkml.kernel.org/r/1410527535-9814-2-git-send-email-riel@redhat.com
[ Improved the readability of the code a bit. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/seqlock.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index cc359636cfa3..f5df8f687b4d 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -456,4 +456,23 @@ read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags)
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
+static inline unsigned long
+read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq)
+{
+	unsigned long flags = 0;
+
+	if (!(*seq & 1))	/* Even */
+		*seq = read_seqbegin(lock);
+	else			/* Odd */
+		read_seqlock_excl_irqsave(lock, flags);
+
+	return flags;
+}
+
+static inline void
+done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags)
+{
+	if (seq & 1)
+		read_sequnlock_excl_irqrestore(lock, flags);
+}
 #endif /* __LINUX_SEQLOCK_H */
-- 
cgit v1.2.3


From d4311ff1a8da48d609db9500f121c15580dfeeb7 Mon Sep 17 00:00:00 2001
From: Aaron Tomlin <atomlin@redhat.com>
Date: Fri, 12 Sep 2014 14:16:17 +0100
Subject: init/main.c: Give init_task a canary

Tasks get their end of stack set to STACK_END_MAGIC with the
aim to catch stack overruns. Currently this feature does not
apply to init_task. This patch removes this restriction.

Note that a similar patch was posted by Prarit Bhargava
some time ago but was never merged:

  http://marc.info/?l=linux-kernel&m=127144305403241&w=2

Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: aneesh.kumar@linux.vnet.ibm.com
Cc: dzickus@redhat.com
Cc: bmr@redhat.com
Cc: jcastillo@redhat.com
Cc: jgh@redhat.com
Cc: minchan@kernel.org
Cc: tglx@linutronix.de
Cc: hannes@cmpxchg.org
Cc: Alex Thorlton <athorlton@sgi.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Daeseok Youn <daeseok.youn@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Fabian Frederick <fabf@skynet.be>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Seiji Aguchi <seiji.aguchi@hds.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/1410527779-8133-2-git-send-email-atomlin@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/mm/fault.c    |  3 +--
 arch/x86/mm/fault.c        |  3 +--
 include/linux/sched.h      |  2 ++
 init/main.c                |  1 +
 kernel/fork.c              | 12 +++++++++---
 kernel/trace/trace_stack.c |  4 +---
 6 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 51ab9e7e6c39..35d0760c3fa4 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -30,7 +30,6 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/perf_event.h>
-#include <linux/magic.h>
 #include <linux/ratelimit.h>
 #include <linux/context_tracking.h>
 
@@ -538,7 +537,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 		regs->nip);
 
 	stackend = end_of_stack(current);
-	if (current != &init_task && *stackend != STACK_END_MAGIC)
+	if (*stackend != STACK_END_MAGIC)
 		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
 
 	die("Kernel access of bad area", regs, sig);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a24194681513..bc23a7043c65 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -3,7 +3,6 @@
  *  Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
  *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
  */
-#include <linux/magic.h>		/* STACK_END_MAGIC		*/
 #include <linux/sched.h>		/* test_thread_flag(), ...	*/
 #include <linux/kdebug.h>		/* oops_begin/end, ...		*/
 #include <linux/module.h>		/* search_exception_table	*/
@@ -710,7 +709,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	show_fault_oops(regs, error_code, address);
 
 	stackend = end_of_stack(tsk);
-	if (tsk != &init_task && *stackend != STACK_END_MAGIC)
+	if (*stackend != STACK_END_MAGIC)
 		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
 	tsk->thread.cr2		= address;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 82ff3d6efb19..118dca7d5a28 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -57,6 +57,7 @@ struct sched_param {
 #include <linux/llist.h>
 #include <linux/uidgid.h>
 #include <linux/gfp.h>
+#include <linux/magic.h>
 
 #include <asm/processor.h>
 
@@ -2638,6 +2639,7 @@ static inline unsigned long stack_not_used(struct task_struct *p)
 	return (unsigned long)n - (unsigned long)end_of_stack(p);
 }
 #endif
+extern void set_task_stack_end_magic(struct task_struct *tsk);
 
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
diff --git a/init/main.c b/init/main.c
index bb1aed928f21..5fc3fc7bd475 100644
--- a/init/main.c
+++ b/init/main.c
@@ -508,6 +508,7 @@ asmlinkage __visible void __init start_kernel(void)
 	 * lockdep hash:
 	 */
 	lockdep_init();
+	set_task_stack_end_magic(&init_task);
 	smp_setup_processor_id();
 	debug_objects_early_init();
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 9387ae8ab048..ad64248c4b18 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -294,11 +294,18 @@ int __weak arch_dup_task_struct(struct task_struct *dst,
 	return 0;
 }
 
+void set_task_stack_end_magic(struct task_struct *tsk)
+{
+	unsigned long *stackend;
+
+	stackend = end_of_stack(tsk);
+	*stackend = STACK_END_MAGIC;	/* for overflow detection */
+}
+
 static struct task_struct *dup_task_struct(struct task_struct *orig)
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
-	unsigned long *stackend;
 	int node = tsk_fork_get_node(orig);
 	int err;
 
@@ -328,8 +335,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	setup_thread_stack(tsk, orig);
 	clear_user_return_notifier(tsk);
 	clear_tsk_need_resched(tsk);
-	stackend = end_of_stack(tsk);
-	*stackend = STACK_END_MAGIC;	/* for overflow detection */
+	set_task_stack_end_magic(tsk);
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 	tsk->stack_canary = get_random_int();
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 8a4e5cb66a4c..1636e41828c2 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -13,7 +13,6 @@
 #include <linux/sysctl.h>
 #include <linux/init.h>
 #include <linux/fs.h>
-#include <linux/magic.h>
 
 #include <asm/setup.h>
 
@@ -171,8 +170,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
-	if ((current != &init_task &&
-		*(end_of_stack(current)) != STACK_END_MAGIC)) {
+	if (*end_of_stack(current) != STACK_END_MAGIC) {
 		print_max_stack();
 		BUG();
 	}
-- 
cgit v1.2.3


From a70857e46dd13e87ae06bf0e64cb6a2d4f436265 Mon Sep 17 00:00:00 2001
From: Aaron Tomlin <atomlin@redhat.com>
Date: Fri, 12 Sep 2014 14:16:18 +0100
Subject: sched: Add helper for task stack page overrun checking

This facility is used in a few places so let's introduce
a helper function to improve code readability.

Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: aneesh.kumar@linux.vnet.ibm.com
Cc: dzickus@redhat.com
Cc: bmr@redhat.com
Cc: jcastillo@redhat.com
Cc: oleg@redhat.com
Cc: riel@redhat.com
Cc: prarit@redhat.com
Cc: jgh@redhat.com
Cc: minchan@kernel.org
Cc: mpe@ellerman.id.au
Cc: tglx@linutronix.de
Cc: hannes@cmpxchg.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Seiji Aguchi <seiji.aguchi@hds.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/1410527779-8133-3-git-send-email-atomlin@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/mm/fault.c    | 4 +---
 arch/x86/mm/fault.c        | 4 +---
 include/linux/sched.h      | 2 ++
 kernel/trace/trace_stack.c | 2 +-
 4 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 35d0760c3fa4..99b2f2775658 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -507,7 +507,6 @@ bail:
 void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 {
 	const struct exception_table_entry *entry;
-	unsigned long *stackend;
 
 	/* Are we prepared to handle this fault?  */
 	if ((entry = search_exception_tables(regs->nip)) != NULL) {
@@ -536,8 +535,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 	printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n",
 		regs->nip);
 
-	stackend = end_of_stack(current);
-	if (*stackend != STACK_END_MAGIC)
+	if (task_stack_end_corrupted(current))
 		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
 
 	die("Kernel access of bad area", regs, sig);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index bc23a7043c65..6240bc7ae741 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -648,7 +648,6 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	   unsigned long address, int signal, int si_code)
 {
 	struct task_struct *tsk = current;
-	unsigned long *stackend;
 	unsigned long flags;
 	int sig;
 
@@ -708,8 +707,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	show_fault_oops(regs, error_code, address);
 
-	stackend = end_of_stack(tsk);
-	if (*stackend != STACK_END_MAGIC)
+	if (task_stack_end_corrupted(tsk))
 		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
 	tsk->thread.cr2		= address;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 118dca7d5a28..18f52624eaa6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2617,6 +2617,8 @@ static inline unsigned long *end_of_stack(struct task_struct *p)
 }
 
 #endif
+#define task_stack_end_corrupted(task) \
+		(*(end_of_stack(task)) != STACK_END_MAGIC)
 
 static inline int object_is_on_stack(void *obj)
 {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 1636e41828c2..16eddb308c33 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -170,7 +170,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
-	if (*end_of_stack(current) != STACK_END_MAGIC) {
+	if (task_stack_end_corrupted(current)) {
 		print_max_stack();
 		BUG();
 	}
-- 
cgit v1.2.3


From e8be1cf58d5b4ddbf8089700df8458f432ed5934 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Fri, 12 Sep 2014 16:00:32 -0700
Subject: [SCSI] fix regression that accidentally disabled block-based tcq

The scsi blk-mq support accidentally flipped a conditional, which lead to
never enabling block based tcq when using the legacy request path.

Fixes: d285203cf647d7c9 scsi: add support for a blk-mq based I/O path.
Reported-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
---
 include/scsi/scsi_tcq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index cdcc90b07ecb..e64583560701 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -68,7 +68,7 @@ static inline void scsi_activate_tcq(struct scsi_device *sdev, int depth)
 		return;
 
 	if (!shost_use_blk_mq(sdev->host) &&
-	    blk_queue_tagged(sdev->request_queue))
+	    !blk_queue_tagged(sdev->request_queue))
 		blk_queue_init_tags(sdev->request_queue, depth,
 				    sdev->host->bqt);
 
-- 
cgit v1.2.3


From f29374b146dd02f5f99742aedaddd6ef3512fc9c Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Fri, 19 Sep 2014 16:29:31 +0800
Subject: cgroup: remove redundant check in cgroup_ino()

After we implemented default unified hierarchy, cgrp->kn can never
be NULL.

Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h | 7 ++-----
 mm/memory-failure.c    | 2 +-
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 77a1d37b742b..818a81fe7ccc 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -532,13 +532,10 @@ static inline bool cgroup_has_tasks(struct cgroup *cgrp)
 	return !list_empty(&cgrp->cset_links);
 }
 
-/* returns ino associated with a cgroup, 0 indicates unmounted root */
+/* returns ino associated with a cgroup */
 static inline ino_t cgroup_ino(struct cgroup *cgrp)
 {
-	if (cgrp->kn)
-		return cgrp->kn->ino;
-	else
-		return 0;
+	return cgrp->kn->ino;
 }
 
 /* cft/css accessors for cftype->write() operation */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 44c6bd201d3a..8639f6b28746 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -148,7 +148,7 @@ static int hwpoison_filter_task(struct page *p)
 	ino = cgroup_ino(css->cgroup);
 	css_put(css);
 
-	if (!ino || ino != hwpoison_filter_memcg)
+	if (ino != hwpoison_filter_memcg)
 		return -EINVAL;
 
 	return 0;
-- 
cgit v1.2.3


From a25eb52e81a40e986179a790fbb5a1f02f482b7a Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Fri, 19 Sep 2014 16:51:00 +0800
Subject: cgroup: remove CGRP_RELEASABLE flag

We call put_css_set() after setting CGRP_RELEASABLE flag in
cgroup_task_migrate(), but in other places we call it without setting
the flag. I don't see the necessity of this flag.

Moreover once the flag is set, it will never be cleared, unless writing
to the notify_on_release control file, so it can be quite confusing
if we look at the output of debug.releasable.

  # mount -t cgroup -o debug xxx /cgroup
  # mkdir /cgroup/child
  # cat /cgroup/child/debug.releasable
  0   <-- shows 0 though the cgroup is empty
  # echo $$ > /cgroup/child/tasks
  # cat /cgroup/child/debug.releasable
  0
  # echo $$ > /cgroup/tasks && echo $$ > /cgroup/child/tasks
  # cat /proc/child/debug.releasable
  1   <-- shows 1 though the cgroup is not empty

This patch removes the flag, and now debug.releasable shows if the
cgroup is empty or not.

Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h |  5 -----
 kernel/cgroup.c        | 40 +++++++++++++---------------------------
 2 files changed, 13 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 818a81fe7ccc..1d5196889048 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -161,11 +161,6 @@ static inline void css_put(struct cgroup_subsys_state *css)
 
 /* bits in struct cgroup flags field */
 enum {
-	/*
-	 * Control Group has previously had a child cgroup or a task,
-	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
-	 */
-	CGRP_RELEASABLE,
 	/* Control Group requires release notifications to userspace */
 	CGRP_NOTIFY_ON_RELEASE,
 	/*
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index df7733b48d2e..16e3a4f5c9dc 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -329,14 +329,6 @@ bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
 	return false;
 }
 
-static int cgroup_is_releasable(const struct cgroup *cgrp)
-{
-	const int bits =
-		(1 << CGRP_RELEASABLE) |
-		(1 << CGRP_NOTIFY_ON_RELEASE);
-	return (cgrp->flags & bits) == bits;
-}
-
 static int notify_on_release(const struct cgroup *cgrp)
 {
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -491,7 +483,7 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
 	return key;
 }
 
-static void put_css_set_locked(struct css_set *cset, bool taskexit)
+static void put_css_set_locked(struct css_set *cset)
 {
 	struct cgrp_cset_link *link, *tmp_link;
 	struct cgroup_subsys *ss;
@@ -517,11 +509,7 @@ static void put_css_set_locked(struct css_set *cset, bool taskexit)
 		/* @cgrp can't go away while we're holding css_set_rwsem */
 		if (list_empty(&cgrp->cset_links)) {
 			cgroup_update_populated(cgrp, false);
-			if (notify_on_release(cgrp)) {
-				if (taskexit)
-					set_bit(CGRP_RELEASABLE, &cgrp->flags);
-				check_for_release(cgrp);
-			}
+			check_for_release(cgrp);
 		}
 
 		kfree(link);
@@ -530,7 +518,7 @@ static void put_css_set_locked(struct css_set *cset, bool taskexit)
 	kfree_rcu(cset, rcu_head);
 }
 
-static void put_css_set(struct css_set *cset, bool taskexit)
+static void put_css_set(struct css_set *cset)
 {
 	/*
 	 * Ensure that the refcount doesn't hit zero while any readers
@@ -541,7 +529,7 @@ static void put_css_set(struct css_set *cset, bool taskexit)
 		return;
 
 	down_write(&css_set_rwsem);
-	put_css_set_locked(cset, taskexit);
+	put_css_set_locked(cset);
 	up_write(&css_set_rwsem);
 }
 
@@ -2037,8 +2025,7 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 	 * task. As trading it for new_cset is protected by cgroup_mutex,
 	 * we're safe to drop it here; it will be freed under RCU.
 	 */
-	set_bit(CGRP_RELEASABLE, &old_cgrp->flags);
-	put_css_set_locked(old_cset, false);
+	put_css_set_locked(old_cset);
 }
 
 /**
@@ -2059,7 +2046,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
 		cset->mg_src_cgrp = NULL;
 		cset->mg_dst_cset = NULL;
 		list_del_init(&cset->mg_preload_node);
-		put_css_set_locked(cset, false);
+		put_css_set_locked(cset);
 	}
 	up_write(&css_set_rwsem);
 }
@@ -2153,8 +2140,8 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
 		if (src_cset == dst_cset) {
 			src_cset->mg_src_cgrp = NULL;
 			list_del_init(&src_cset->mg_preload_node);
-			put_css_set(src_cset, false);
-			put_css_set(dst_cset, false);
+			put_css_set(src_cset);
+			put_css_set(dst_cset);
 			continue;
 		}
 
@@ -2163,7 +2150,7 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
 		if (list_empty(&dst_cset->mg_preload_node))
 			list_add(&dst_cset->mg_preload_node, &csets);
 		else
-			put_css_set(dst_cset, false);
+			put_css_set(dst_cset);
 	}
 
 	list_splice_tail(&csets, preloaded_csets);
@@ -4159,7 +4146,6 @@ static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
 static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
 					  struct cftype *cft, u64 val)
 {
-	clear_bit(CGRP_RELEASABLE, &css->cgroup->flags);
 	if (val)
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
 	else
@@ -4806,7 +4792,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	 */
 	kernfs_remove(cgrp->kn);
 
-	set_bit(CGRP_RELEASABLE, &cgroup_parent(cgrp)->flags);
 	check_for_release(cgroup_parent(cgrp));
 
 	/* put the base reference */
@@ -5244,12 +5229,12 @@ void cgroup_exit(struct task_struct *tsk)
 	}
 
 	if (put_cset)
-		put_css_set(cset, true);
+		put_css_set(cset);
 }
 
 static void check_for_release(struct cgroup *cgrp)
 {
-	if (cgroup_is_releasable(cgrp) && !cgroup_has_tasks(cgrp) &&
+	if (notify_on_release(cgrp) && !cgroup_has_tasks(cgrp) &&
 	    !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp))
 		schedule_work(&cgrp->release_agent_work);
 }
@@ -5496,7 +5481,8 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 
 static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
 {
-	return test_bit(CGRP_RELEASABLE, &css->cgroup->flags);
+	return (!cgroup_has_tasks(css->cgroup) &&
+		!css_has_online_children(&css->cgroup->self));
 }
 
 static struct cftype debug_files[] =  {
-- 
cgit v1.2.3


From d87f09abb31d2d52dda261b5128c39d3944afbab Mon Sep 17 00:00:00 2001
From: Inki Dae <inki.dae@samsung.com>
Date: Wed, 13 Aug 2014 16:38:23 +0900
Subject: drm/mipi-dsi: consider low power transmission

This patch adds a new flag, MIPI_DSI-MODE_LPM, to transmit data
in low power. With this flag, msg.flags has MIPI_DSI_MSG_USE_LPM
so that host driver of each SoC can clear or set relevant register
bit for low power transmission.

All host drivers shall support continuous clock behavior on the
Clock Lane, and optionally may support non-continuous clock behavior.
Both of them can transmit data in high speed of low power.

With each clock behavior, non-continuous or continuous clock mode,
host controller will transmit data in high speed by default so if
peripheral wants to receive data in low power, the peripheral driver
should set MIPI_DSI_MODE_LPM flag.

Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/drm_mipi_dsi.c | 6 ++++++
 include/drm/drm_mipi_dsi.h     | 2 ++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index 6aa6a9e95570..eb6dfe52cab2 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -231,6 +231,9 @@ ssize_t mipi_dsi_dcs_write(struct mipi_dsi_device *dsi, const void *data,
 		break;
 	}
 
+	if (dsi->mode_flags & MIPI_DSI_MODE_LPM)
+		msg.flags = MIPI_DSI_MSG_USE_LPM;
+
 	return ops->transfer(dsi->host, &msg);
 }
 EXPORT_SYMBOL(mipi_dsi_dcs_write);
@@ -260,6 +263,9 @@ ssize_t mipi_dsi_dcs_read(struct mipi_dsi_device *dsi, u8 cmd, void *data,
 	if (!ops || !ops->transfer)
 		return -ENOSYS;
 
+	if (dsi->mode_flags & MIPI_DSI_MODE_LPM)
+		msg.flags = MIPI_DSI_MSG_USE_LPM;
+
 	return ops->transfer(dsi->host, &msg);
 }
 EXPORT_SYMBOL(mipi_dsi_dcs_read);
diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h
index 2bb55b8b9031..8569dc5a1026 100644
--- a/include/drm/drm_mipi_dsi.h
+++ b/include/drm/drm_mipi_dsi.h
@@ -96,6 +96,8 @@ void mipi_dsi_host_unregister(struct mipi_dsi_host *host);
 #define MIPI_DSI_MODE_EOT_PACKET	BIT(9)
 /* device supports non-continuous clock behavior (DSI spec 5.6.1) */
 #define MIPI_DSI_CLOCK_NON_CONTINUOUS	BIT(10)
+/* transmit data in low power */
+#define MIPI_DSI_MODE_LPM		BIT(11)
 
 enum mipi_dsi_pixel_format {
 	MIPI_DSI_FMT_RGB888,
-- 
cgit v1.2.3


From d931589c01a20595d67192f075f9c84093c43c45 Mon Sep 17 00:00:00 2001
From: Inki Dae <inki.dae@samsung.com>
Date: Wed, 17 Sep 2014 22:48:45 +0900
Subject: drm/exynos: remove DRM_EXYNOS_GEM_MAP_OFFSET ioctl

This interface and relevant codes aren't used anymore.

Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_drv.c |  3 ---
 drivers/gpu/drm/exynos/exynos_drm_gem.c | 17 -----------------
 drivers/gpu/drm/exynos/exynos_drm_gem.h |  4 ----
 include/uapi/drm/exynos_drm.h           | 18 ------------------
 4 files changed, 42 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 2103d970d6ea..d69bd9723805 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -299,9 +299,6 @@ static const struct vm_operations_struct exynos_drm_gem_vm_ops = {
 static const struct drm_ioctl_desc exynos_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_CREATE, exynos_drm_gem_create_ioctl,
 			DRM_UNLOCKED | DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_MAP_OFFSET,
-			exynos_drm_gem_map_offset_ioctl, DRM_UNLOCKED |
-			DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_MMAP,
 			exynos_drm_gem_mmap_ioctl, DRM_UNLOCKED | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_GET,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 15db80138382..2f3665de2d60 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -318,23 +318,6 @@ void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
 	drm_gem_object_unreference_unlocked(obj);
 }
 
-int exynos_drm_gem_map_offset_ioctl(struct drm_device *dev, void *data,
-				    struct drm_file *file_priv)
-{
-	struct drm_exynos_gem_map_off *args = data;
-
-	DRM_DEBUG_KMS("handle = 0x%x, offset = 0x%lx\n",
-			args->handle, (unsigned long)args->offset);
-
-	if (!(dev->driver->driver_features & DRIVER_GEM)) {
-		DRM_ERROR("does not support GEM.\n");
-		return -ENODEV;
-	}
-
-	return exynos_drm_gem_dumb_map_offset(file_priv, dev, args->handle,
-			&args->offset);
-}
-
 int exynos_drm_gem_mmap_buffer(struct file *filp,
 				      struct vm_area_struct *vma)
 {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 1592c0ba7de8..8e460940d118 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -111,10 +111,6 @@ void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
 					unsigned int gem_handle,
 					struct drm_file *filp);
 
-/* get buffer offset to map to user space. */
-int exynos_drm_gem_map_offset_ioctl(struct drm_device *dev, void *data,
-				    struct drm_file *file_priv);
-
 /*
  * mmap the physically continuous memory that a gem object contains
  * to user space.
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index d5844122ff32..67a751c74a77 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -32,20 +32,6 @@ struct drm_exynos_gem_create {
 	unsigned int handle;
 };
 
-/**
- * A structure for getting buffer offset.
- *
- * @handle: a pointer to gem object created.
- * @pad: just padding to be 64-bit aligned.
- * @offset: relatived offset value of the memory region allocated.
- *	- this value should be set by user.
- */
-struct drm_exynos_gem_map_off {
-	unsigned int handle;
-	unsigned int pad;
-	uint64_t offset;
-};
-
 /**
  * A structure for mapping buffer.
  *
@@ -316,7 +302,6 @@ struct drm_exynos_ipp_cmd_ctrl {
 };
 
 #define DRM_EXYNOS_GEM_CREATE		0x00
-#define DRM_EXYNOS_GEM_MAP_OFFSET	0x01
 #define DRM_EXYNOS_GEM_MMAP		0x02
 /* Reserved 0x03 ~ 0x05 for exynos specific gem ioctl */
 #define DRM_EXYNOS_GEM_GET		0x04
@@ -336,9 +321,6 @@ struct drm_exynos_ipp_cmd_ctrl {
 #define DRM_IOCTL_EXYNOS_GEM_CREATE		DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_GEM_CREATE, struct drm_exynos_gem_create)
 
-#define DRM_IOCTL_EXYNOS_GEM_MAP_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + \
-		DRM_EXYNOS_GEM_MAP_OFFSET, struct drm_exynos_gem_map_off)
-
 #define DRM_IOCTL_EXYNOS_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_GEM_MMAP, struct drm_exynos_gem_mmap)
 
-- 
cgit v1.2.3


From 832316c704fe3d15ae6ca9a552ae80411d1bbbcd Mon Sep 17 00:00:00 2001
From: Inki Dae <inki.dae@samsung.com>
Date: Thu, 18 Sep 2014 14:19:01 +0900
Subject: drm/exynos: use drm generic mmap interface

This patch removes DRM_EXYNOS_GEM_MMAP ictrl feature specific
to Exynos drm and instead uses drm generic mmap.

We had used the interface specific to Exynos drm to do mmap directly,
not to use demand paging which maps each page with physical memory
at page fault handler. We don't need the specific mmap interface
because the drm generic mmap which uses vm offset manager stuff can
also do mmap directly.

This patch makes a userspace region to be mapped with whole physical
memory region allocated by userspace request when mmap system call is
requested.

Changelog v2:
- do not set VM_IO, VM_DONTEXPEND and VM_DONTDUMP. These flags were already
  set by drm_gem_mmap
- do not include <linux/anon_inodes.h>, which isn't needed anymore.

Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_drv.c | 26 ----------
 drivers/gpu/drm/exynos/exynos_drm_drv.h |  1 -
 drivers/gpu/drm/exynos/exynos_drm_gem.c | 89 ++++++---------------------------
 drivers/gpu/drm/exynos/exynos_drm_gem.h | 10 ----
 include/uapi/drm/exynos_drm.h           | 22 --------
 5 files changed, 16 insertions(+), 132 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index d69bd9723805..513ba940bae0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -15,7 +15,6 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 
-#include <linux/anon_inodes.h>
 #include <linux/component.h>
 
 #include <drm/exynos_drm.h>
@@ -166,10 +165,6 @@ static int exynos_drm_unload(struct drm_device *dev)
 	return 0;
 }
 
-static const struct file_operations exynos_drm_gem_fops = {
-	.mmap = exynos_drm_gem_mmap_buffer,
-};
-
 static int exynos_drm_suspend(struct drm_device *dev, pm_message_t state)
 {
 	struct drm_connector *connector;
@@ -208,7 +203,6 @@ static int exynos_drm_resume(struct drm_device *dev)
 static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv;
-	struct file *anon_filp;
 	int ret;
 
 	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
@@ -221,21 +215,8 @@ static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
 	if (ret)
 		goto err_file_priv_free;
 
-	anon_filp = anon_inode_getfile("exynos_gem", &exynos_drm_gem_fops,
-					NULL, 0);
-	if (IS_ERR(anon_filp)) {
-		ret = PTR_ERR(anon_filp);
-		goto err_subdrv_close;
-	}
-
-	anon_filp->f_mode = FMODE_READ | FMODE_WRITE;
-	file_priv->anon_filp = anon_filp;
-
 	return ret;
 
-err_subdrv_close:
-	exynos_drm_subdrv_close(dev, file);
-
 err_file_priv_free:
 	kfree(file_priv);
 	file->driver_priv = NULL;
@@ -251,7 +232,6 @@ static void exynos_drm_preclose(struct drm_device *dev,
 static void exynos_drm_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct exynos_drm_private *private = dev->dev_private;
-	struct drm_exynos_file_private *file_priv;
 	struct drm_pending_vblank_event *v, *vt;
 	struct drm_pending_event *e, *et;
 	unsigned long flags;
@@ -277,10 +257,6 @@ static void exynos_drm_postclose(struct drm_device *dev, struct drm_file *file)
 	}
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
-	file_priv = file->driver_priv;
-	if (file_priv->anon_filp)
-		fput(file_priv->anon_filp);
-
 	kfree(file->driver_priv);
 	file->driver_priv = NULL;
 }
@@ -299,8 +275,6 @@ static const struct vm_operations_struct exynos_drm_gem_vm_ops = {
 static const struct drm_ioctl_desc exynos_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_CREATE, exynos_drm_gem_create_ioctl,
 			DRM_UNLOCKED | DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_MMAP,
-			exynos_drm_gem_mmap_ioctl, DRM_UNLOCKED | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_GET,
 			exynos_drm_gem_get_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(EXYNOS_VIDI_CONNECTION,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index 69a6fa397d75..d22e640f59a0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -240,7 +240,6 @@ struct exynos_drm_g2d_private {
 struct drm_exynos_file_private {
 	struct exynos_drm_g2d_private	*g2d_priv;
 	struct device			*ipp_dev;
-	struct file			*anon_filp;
 };
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 2f3665de2d60..0d5b9698d384 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -318,23 +318,16 @@ void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
 	drm_gem_object_unreference_unlocked(obj);
 }
 
-int exynos_drm_gem_mmap_buffer(struct file *filp,
+int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj,
 				      struct vm_area_struct *vma)
 {
-	struct drm_gem_object *obj = filp->private_data;
-	struct exynos_drm_gem_obj *exynos_gem_obj = to_exynos_gem_obj(obj);
-	struct drm_device *drm_dev = obj->dev;
+	struct drm_device *drm_dev = exynos_gem_obj->base.dev;
 	struct exynos_drm_gem_buf *buffer;
 	unsigned long vm_size;
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
-
-	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
-	vma->vm_private_data = obj;
-	vma->vm_ops = drm_dev->driver->gem_vm_ops;
-
-	update_vm_cache_attr(exynos_gem_obj, vma);
+	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_pgoff = 0;
 
 	vm_size = vma->vm_end - vma->vm_start;
 
@@ -356,60 +349,6 @@ int exynos_drm_gem_mmap_buffer(struct file *filp,
 		return ret;
 	}
 
-	/*
-	 * take a reference to this mapping of the object. And this reference
-	 * is unreferenced by the corresponding vm_close call.
-	 */
-	drm_gem_object_reference(obj);
-
-	drm_vm_open_locked(drm_dev, vma);
-
-	return 0;
-}
-
-int exynos_drm_gem_mmap_ioctl(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv)
-{
-	struct drm_exynos_file_private *exynos_file_priv;
-	struct drm_exynos_gem_mmap *args = data;
-	struct drm_gem_object *obj;
-	struct file *anon_filp;
-	unsigned long addr;
-
-	if (!(dev->driver->driver_features & DRIVER_GEM)) {
-		DRM_ERROR("does not support GEM.\n");
-		return -ENODEV;
-	}
-
-	mutex_lock(&dev->struct_mutex);
-
-	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		mutex_unlock(&dev->struct_mutex);
-		return -EINVAL;
-	}
-
-	exynos_file_priv = file_priv->driver_priv;
-	anon_filp = exynos_file_priv->anon_filp;
-	anon_filp->private_data = obj;
-
-	addr = vm_mmap(anon_filp, 0, args->size, PROT_READ | PROT_WRITE,
-			MAP_SHARED, 0);
-
-	drm_gem_object_unreference(obj);
-
-	if (IS_ERR_VALUE(addr)) {
-		mutex_unlock(&dev->struct_mutex);
-		return (int)addr;
-	}
-
-	mutex_unlock(&dev->struct_mutex);
-
-	args->mapped = addr;
-
-	DRM_DEBUG_KMS("mapped = 0x%lx\n", (unsigned long)args->mapped);
-
 	return 0;
 }
 
@@ -693,16 +632,20 @@ int exynos_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	exynos_gem_obj = to_exynos_gem_obj(obj);
 
 	ret = check_gem_flags(exynos_gem_obj->flags);
-	if (ret) {
-		drm_gem_vm_close(vma);
-		drm_gem_free_mmap_offset(obj);
-		return ret;
-	}
-
-	vma->vm_flags &= ~VM_PFNMAP;
-	vma->vm_flags |= VM_MIXEDMAP;
+	if (ret)
+		goto err_close_vm;
 
 	update_vm_cache_attr(exynos_gem_obj, vma);
 
+	ret = exynos_drm_gem_mmap_buffer(exynos_gem_obj, vma);
+	if (ret)
+		goto err_close_vm;
+
+	return ret;
+
+err_close_vm:
+	drm_gem_vm_close(vma);
+	drm_gem_free_mmap_offset(obj);
+
 	return ret;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 8e460940d118..09d021bbccf5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -111,16 +111,6 @@ void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
 					unsigned int gem_handle,
 					struct drm_file *filp);
 
-/*
- * mmap the physically continuous memory that a gem object contains
- * to user space.
- */
-int exynos_drm_gem_mmap_ioctl(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv);
-
-int exynos_drm_gem_mmap_buffer(struct file *filp,
-				      struct vm_area_struct *vma);
-
 /* map user space allocated by malloc to pages. */
 int exynos_drm_gem_userptr_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv);
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index 67a751c74a77..5575ed1598bd 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -32,24 +32,6 @@ struct drm_exynos_gem_create {
 	unsigned int handle;
 };
 
-/**
- * A structure for mapping buffer.
- *
- * @handle: a handle to gem object created.
- * @pad: just padding to be 64-bit aligned.
- * @size: memory size to be mapped.
- * @mapped: having user virtual address mmaped.
- *	- this variable would be filled by exynos gem module
- *	of kernel side with user virtual address which is allocated
- *	by do_mmap().
- */
-struct drm_exynos_gem_mmap {
-	unsigned int handle;
-	unsigned int pad;
-	uint64_t size;
-	uint64_t mapped;
-};
-
 /**
  * A structure to gem information.
  *
@@ -302,7 +284,6 @@ struct drm_exynos_ipp_cmd_ctrl {
 };
 
 #define DRM_EXYNOS_GEM_CREATE		0x00
-#define DRM_EXYNOS_GEM_MMAP		0x02
 /* Reserved 0x03 ~ 0x05 for exynos specific gem ioctl */
 #define DRM_EXYNOS_GEM_GET		0x04
 #define DRM_EXYNOS_VIDI_CONNECTION	0x07
@@ -321,9 +302,6 @@ struct drm_exynos_ipp_cmd_ctrl {
 #define DRM_IOCTL_EXYNOS_GEM_CREATE		DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_GEM_CREATE, struct drm_exynos_gem_create)
 
-#define DRM_IOCTL_EXYNOS_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + \
-		DRM_EXYNOS_GEM_MMAP, struct drm_exynos_gem_mmap)
-
 #define DRM_IOCTL_EXYNOS_GEM_GET	DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_GEM_GET,	struct drm_exynos_gem_info)
 
-- 
cgit v1.2.3


From 87773dd56d5405ac28119fcfadacefd35877c18f Mon Sep 17 00:00:00 2001
From: Shawn Bohrer <sbohrer@rgmadvisors.com>
Date: Wed, 3 Sep 2014 12:13:57 -0500
Subject: IB: ib_umem_release() should decrement mm->pinned_vm from ib_umem_get

In debugging an application that receives -ENOMEM from ib_reg_mr(), I
found that ib_umem_get() can fail because the pinned_vm count has
wrapped causing it to always be larger than the lock limit even with
RLIMIT_MEMLOCK set to RLIM_INFINITY.

The wrapping of pinned_vm occurs because the process that calls
ib_reg_mr() will have its mm->pinned_vm count incremented.  Later a
different process with a different mm_struct than the one that
allocated the ib_umem struct ends up releasing it which results in
decrementing the new processes mm->pinned_vm count past zero and
wrapping.

I'm not entirely sure what circumstances cause a different process to
release the ib_umem than the one that allocated it but the kernel
stack trace of the freeing process from my situation looks like the
following:

    Call Trace:
     [<ffffffff814d64b1>] dump_stack+0x19/0x1b
     [<ffffffffa0b522a5>] ib_umem_release+0x1f5/0x200 [ib_core]
     [<ffffffffa0b90681>] mlx4_ib_destroy_qp+0x241/0x440 [mlx4_ib]
     [<ffffffffa0b4d93c>] ib_destroy_qp+0x12c/0x170 [ib_core]
     [<ffffffffa0cc7129>] ib_uverbs_close+0x259/0x4e0 [ib_uverbs]
     [<ffffffff81141cba>] __fput+0xba/0x240
     [<ffffffff81141e4e>] ____fput+0xe/0x10
     [<ffffffff81060894>] task_work_run+0xc4/0xe0
     [<ffffffff810029e5>] do_notify_resume+0x95/0xa0
     [<ffffffff814e3dd0>] int_signal+0x12/0x17

The following patch fixes the issue by storing the pid struct of the
process that calls ib_umem_get() so that ib_umem_release and/or
ib_umem_account() can properly decrement the pinned_vm count of the
correct mm_struct.

Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Reviewed-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/umem.c | 19 +++++++++++++------
 include/rdma/ib_umem.h         |  1 +
 2 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index a3a2e9c1639b..df0c4f605a21 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -105,6 +105,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 	umem->length    = size;
 	umem->offset    = addr & ~PAGE_MASK;
 	umem->page_size = PAGE_SIZE;
+	umem->pid       = get_task_pid(current, PIDTYPE_PID);
 	/*
 	 * We ask for writable memory if any access flags other than
 	 * "remote read" are set.  "Local write" and "remote write"
@@ -198,6 +199,7 @@ out:
 	if (ret < 0) {
 		if (need_release)
 			__ib_umem_release(context->device, umem, 0);
+		put_pid(umem->pid);
 		kfree(umem);
 	} else
 		current->mm->pinned_vm = locked;
@@ -230,15 +232,19 @@ void ib_umem_release(struct ib_umem *umem)
 {
 	struct ib_ucontext *context = umem->context;
 	struct mm_struct *mm;
+	struct task_struct *task;
 	unsigned long diff;
 
 	__ib_umem_release(umem->context->device, umem, 1);
 
-	mm = get_task_mm(current);
-	if (!mm) {
-		kfree(umem);
-		return;
-	}
+	task = get_pid_task(umem->pid, PIDTYPE_PID);
+	put_pid(umem->pid);
+	if (!task)
+		goto out;
+	mm = get_task_mm(task);
+	put_task_struct(task);
+	if (!mm)
+		goto out;
 
 	diff = PAGE_ALIGN(umem->length + umem->offset) >> PAGE_SHIFT;
 
@@ -262,9 +268,10 @@ void ib_umem_release(struct ib_umem *umem)
 	} else
 		down_write(&mm->mmap_sem);
 
-	current->mm->pinned_vm -= diff;
+	mm->pinned_vm -= diff;
 	up_write(&mm->mmap_sem);
 	mmput(mm);
+out:
 	kfree(umem);
 }
 EXPORT_SYMBOL(ib_umem_release);
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 1ea0b65c4cfb..a2bf41e0bde9 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -47,6 +47,7 @@ struct ib_umem {
 	int                     writable;
 	int                     hugetlb;
 	struct work_struct	work;
+	struct pid             *pid;
 	struct mm_struct       *mm;
 	unsigned long		diff;
 	struct sg_table sg_head;
-- 
cgit v1.2.3


From fd384412e199b62c3ddaabd18dce86d0e164c5b9 Mon Sep 17 00:00:00 2001
From: Andy Zhou <azhou@nicira.com>
Date: Tue, 16 Sep 2014 17:31:16 -0700
Subject: udp_tunnel: Seperate ipv6 functions into its own file.

Add ip6_udp_tunnel.c for ipv6 UDP tunnel functions to avoid ifdefs
in udp_tunnel.c

Signed-off-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp_tunnel.h  | 28 ++++++++++++++--
 net/ipv4/udp_tunnel.c     | 85 ++++++++++++-----------------------------------
 net/ipv6/Makefile         |  1 +
 net/ipv6/ip6_udp_tunnel.c | 63 +++++++++++++++++++++++++++++++++++
 4 files changed, 111 insertions(+), 66 deletions(-)
 create mode 100644 net/ipv6/ip6_udp_tunnel.c

(limited to 'include')

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index ffd69cbded35..0b9e017c9038 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -26,7 +26,31 @@ struct udp_port_cfg {
 				use_udp6_rx_checksums:1;
 };
 
-int udp_sock_create(struct net *net, struct udp_port_cfg *cfg,
-		    struct socket **sockp);
+int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
+		     struct socket **sockp);
+
+#if IS_ENABLED(CONFIG_IPV6)
+int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
+		     struct socket **sockp);
+#else
+static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
+				   struct socket **sockp)
+{
+	return 0;
+}
+#endif
+
+static inline int udp_sock_create(struct net *net,
+				  struct udp_port_cfg *cfg,
+				  struct socket **sockp)
+{
+	if (cfg->family == AF_INET)
+		return udp_sock_create4(net, cfg, sockp);
+
+	if (cfg->family == AF_INET6)
+		return udp_sock_create6(net, cfg, sockp);
+
+	return -EPFNOSUPPORT;
+}
 
 #endif
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 61ec1a65207e..7fccf6c3417a 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -8,83 +8,40 @@
 #include <net/udp_tunnel.h>
 #include <net/net_namespace.h>
 
-int udp_sock_create(struct net *net, struct udp_port_cfg *cfg,
-		    struct socket **sockp)
+int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
+		     struct socket **sockp)
 {
 	int err = -EINVAL;
 	struct socket *sock = NULL;
+	struct sockaddr_in udp_addr;
 
-#if IS_ENABLED(CONFIG_IPV6)
-	if (cfg->family == AF_INET6) {
-		struct sockaddr_in6 udp6_addr;
+	err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock);
+	if (err < 0)
+		goto error;
 
-		err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock);
-		if (err < 0)
-			goto error;
-
-		sk_change_net(sock->sk, net);
-
-		udp6_addr.sin6_family = AF_INET6;
-		memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
-		       sizeof(udp6_addr.sin6_addr));
-		udp6_addr.sin6_port = cfg->local_udp_port;
-		err = kernel_bind(sock, (struct sockaddr *)&udp6_addr,
-				  sizeof(udp6_addr));
-		if (err < 0)
-			goto error;
-
-		if (cfg->peer_udp_port) {
-			udp6_addr.sin6_family = AF_INET6;
-			memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6,
-			       sizeof(udp6_addr.sin6_addr));
-			udp6_addr.sin6_port = cfg->peer_udp_port;
-			err = kernel_connect(sock,
-					     (struct sockaddr *)&udp6_addr,
-					     sizeof(udp6_addr), 0);
-		}
-		if (err < 0)
-			goto error;
-
-		udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums);
-		udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums);
-	} else
-#endif
-	if (cfg->family == AF_INET) {
-		struct sockaddr_in udp_addr;
-
-		err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock);
-		if (err < 0)
-			goto error;
+	sk_change_net(sock->sk, net);
 
-		sk_change_net(sock->sk, net);
+	udp_addr.sin_family = AF_INET;
+	udp_addr.sin_addr = cfg->local_ip;
+	udp_addr.sin_port = cfg->local_udp_port;
+	err = kernel_bind(sock, (struct sockaddr *)&udp_addr,
+			  sizeof(udp_addr));
+	if (err < 0)
+		goto error;
 
+	if (cfg->peer_udp_port) {
 		udp_addr.sin_family = AF_INET;
-		udp_addr.sin_addr = cfg->local_ip;
-		udp_addr.sin_port = cfg->local_udp_port;
-		err = kernel_bind(sock, (struct sockaddr *)&udp_addr,
-				  sizeof(udp_addr));
+		udp_addr.sin_addr = cfg->peer_ip;
+		udp_addr.sin_port = cfg->peer_udp_port;
+		err = kernel_connect(sock, (struct sockaddr *)&udp_addr,
+				     sizeof(udp_addr), 0);
 		if (err < 0)
 			goto error;
-
-		if (cfg->peer_udp_port) {
-			udp_addr.sin_family = AF_INET;
-			udp_addr.sin_addr = cfg->peer_ip;
-			udp_addr.sin_port = cfg->peer_udp_port;
-			err = kernel_connect(sock,
-					     (struct sockaddr *)&udp_addr,
-					     sizeof(udp_addr), 0);
-			if (err < 0)
-				goto error;
-		}
-
-		sock->sk->sk_no_check_tx = !cfg->use_udp_checksums;
-	} else {
-		return -EPFNOSUPPORT;
 	}
 
+	sock->sk->sk_no_check_tx = !cfg->use_udp_checksums;
 
 	*sockp = sock;
-
 	return 0;
 
 error:
@@ -95,6 +52,6 @@ error:
 	*sockp = NULL;
 	return err;
 }
-EXPORT_SYMBOL(udp_sock_create);
+EXPORT_SYMBOL(udp_sock_create4);
 
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 2fe68364bb20..45f830e5f820 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -35,6 +35,7 @@ obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o
 obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o
 obj-$(CONFIG_IPV6_MIP6) += mip6.o
 obj-$(CONFIG_NETFILTER)	+= netfilter/
+obj-$(CONFIG_NET_UDP_TUNNEL) += ip6_udp_tunnel.o
 
 obj-$(CONFIG_IPV6_VTI) += ip6_vti.o
 obj-$(CONFIG_IPV6_SIT) += sit.o
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
new file mode 100644
index 000000000000..bcfbb4b496fc
--- /dev/null
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -0,0 +1,63 @@
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/socket.h>
+#include <linux/udp.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/in6.h>
+#include <net/udp.h>
+#include <net/udp_tunnel.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/ip6_tunnel.h>
+#include <net/ip6_checksum.h>
+
+int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
+		     struct socket **sockp)
+{
+	struct sockaddr_in6 udp6_addr;
+	int err;
+	struct socket *sock = NULL;
+
+	err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock);
+	if (err < 0)
+		goto error;
+
+	sk_change_net(sock->sk, net);
+
+	udp6_addr.sin6_family = AF_INET6;
+	memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6,
+	       sizeof(udp6_addr.sin6_addr));
+	udp6_addr.sin6_port = cfg->local_udp_port;
+	err = kernel_bind(sock, (struct sockaddr *)&udp6_addr,
+			  sizeof(udp6_addr));
+	if (err < 0)
+		goto error;
+
+	if (cfg->peer_udp_port) {
+		udp6_addr.sin6_family = AF_INET6;
+		memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6,
+		       sizeof(udp6_addr.sin6_addr));
+		udp6_addr.sin6_port = cfg->peer_udp_port;
+		err = kernel_connect(sock,
+				     (struct sockaddr *)&udp6_addr,
+				     sizeof(udp6_addr), 0);
+	}
+	if (err < 0)
+		goto error;
+
+	udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums);
+	udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums);
+
+	*sockp = sock;
+	return 0;
+
+error:
+	if (sock) {
+		kernel_sock_shutdown(sock, SHUT_RDWR);
+		sk_release_kernel(sock->sk);
+	}
+	*sockp = NULL;
+	return err;
+}
+EXPORT_SYMBOL_GPL(udp_sock_create6);
-- 
cgit v1.2.3


From 6a93cc9052748c6355ec9d5b6c38b77f85f1cb0d Mon Sep 17 00:00:00 2001
From: Andy Zhou <azhou@nicira.com>
Date: Tue, 16 Sep 2014 17:31:17 -0700
Subject: udp-tunnel: Add a few more UDP tunnel APIs

Added a few more UDP tunnel APIs that can be shared by UDP based
tunnel protocol implementation. The main ones are highlighted below.

setup_udp_tunnel_sock() configures UDP listener socket for
receiving UDP encapsulated packets.

udp_tunnel_xmit_skb() and upd_tunnel6_xmit_skb() transmit skb
using UDP encapsulation.

udp_tunnel_sock_release() closes the UDP tunnel listener socket.

Signed-off-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp_tunnel.h  | 57 +++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/udp_tunnel.c     | 53 ++++++++++++++++++++++++++++++++++++++++++-
 net/ipv6/ip6_udp_tunnel.c | 42 ++++++++++++++++++++++++++++++++++
 3 files changed, 151 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 0b9e017c9038..a47790bcaa38 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -1,6 +1,14 @@
 #ifndef __NET_UDP_TUNNEL_H
 #define __NET_UDP_TUNNEL_H
 
+#include <net/ip_tunnels.h>
+#include <net/udp.h>
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+#endif
+
 struct udp_port_cfg {
 	u8			family;
 
@@ -53,4 +61,53 @@ static inline int udp_sock_create(struct net *net,
 	return -EPFNOSUPPORT;
 }
 
+typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
+typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
+
+struct udp_tunnel_sock_cfg {
+	void *sk_user_data;     /* user data used by encap_rcv call back */
+	/* Used for setting up udp_sock fields, see udp.h for details */
+	__u8  encap_type;
+	udp_tunnel_encap_rcv_t encap_rcv;
+	udp_tunnel_encap_destroy_t encap_destroy;
+};
+
+/* Setup the given (UDP) sock to receive UDP encapsulated packets */
+void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
+			   struct udp_tunnel_sock_cfg *sock_cfg);
+
+/* Transmit the skb using UDP encapsulation. */
+int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
+			struct sk_buff *skb, __be32 src, __be32 dst,
+			__u8 tos, __u8 ttl, __be16 df, __be16 src_port,
+			__be16 dst_port, bool xnet);
+
+#if IS_ENABLED(CONFIG_IPV6)
+int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
+			 struct sk_buff *skb, struct net_device *dev,
+			 struct in6_addr *saddr, struct in6_addr *daddr,
+			 __u8 prio, __u8 ttl, __be16 src_port,
+			 __be16 dst_port);
+#endif
+
+void udp_tunnel_sock_release(struct socket *sock);
+
+static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb,
+							 bool udp_csum)
+{
+	int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+
+	return iptunnel_handle_offloads(skb, udp_csum, type);
+}
+
+static inline void udp_tunnel_encap_enable(struct socket *sock)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sock->sk->sk_family == PF_INET6)
+		ipv6_stub->udpv6_encap_enable();
+	else
+#endif
+		udp_encap_enable();
+}
+
 #endif
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 7fccf6c3417a..1671263e5fa0 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -11,7 +11,7 @@
 int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
 		     struct socket **sockp)
 {
-	int err = -EINVAL;
+	int err;
 	struct socket *sock = NULL;
 	struct sockaddr_in udp_addr;
 
@@ -54,4 +54,55 @@ error:
 }
 EXPORT_SYMBOL(udp_sock_create4);
 
+void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
+			   struct udp_tunnel_sock_cfg *cfg)
+{
+	struct sock *sk = sock->sk;
+
+	/* Disable multicast loopback */
+	inet_sk(sk)->mc_loop = 0;
+
+	/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
+	udp_set_convert_csum(sk, true);
+
+	rcu_assign_sk_user_data(sk, cfg->sk_user_data);
+
+	udp_sk(sk)->encap_type = cfg->encap_type;
+	udp_sk(sk)->encap_rcv = cfg->encap_rcv;
+	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
+
+	udp_tunnel_encap_enable(sock);
+}
+EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
+
+int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
+			struct sk_buff *skb, __be32 src, __be32 dst,
+			__u8 tos, __u8 ttl, __be16 df, __be16 src_port,
+			__be16 dst_port, bool xnet)
+{
+	struct udphdr *uh;
+
+	__skb_push(skb, sizeof(*uh));
+	skb_reset_transport_header(skb);
+	uh = udp_hdr(skb);
+
+	uh->dest = dst_port;
+	uh->source = src_port;
+	uh->len = htons(skb->len);
+
+	udp_set_csum(sock->sk->sk_no_check_tx, skb, src, dst, skb->len);
+
+	return iptunnel_xmit(sock->sk, rt, skb, src, dst, IPPROTO_UDP,
+			     tos, ttl, df, xnet);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
+
+void udp_tunnel_sock_release(struct socket *sock)
+{
+	rcu_assign_sk_user_data(sock->sk, NULL);
+	kernel_sock_shutdown(sock, SHUT_RDWR);
+	sk_release_kernel(sock->sk);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_sock_release);
+
 MODULE_LICENSE("GPL");
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index bcfbb4b496fc..cbc990712cc1 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -61,3 +61,45 @@ error:
 	return err;
 }
 EXPORT_SYMBOL_GPL(udp_sock_create6);
+
+int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
+			 struct sk_buff *skb, struct net_device *dev,
+			 struct in6_addr *saddr, struct in6_addr *daddr,
+			 __u8 prio, __u8 ttl, __be16 src_port, __be16 dst_port)
+{
+	struct udphdr *uh;
+	struct ipv6hdr *ip6h;
+	struct sock *sk = sock->sk;
+
+	__skb_push(skb, sizeof(*uh));
+	skb_reset_transport_header(skb);
+	uh = udp_hdr(skb);
+
+	uh->dest = dst_port;
+	uh->source = src_port;
+
+	uh->len = htons(skb->len);
+	uh->check = 0;
+
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
+			    | IPSKB_REROUTED);
+	skb_dst_set(skb, dst);
+
+	udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr,
+		      &sk->sk_v6_daddr, skb->len);
+
+	__skb_push(skb, sizeof(*ip6h));
+	skb_reset_network_header(skb);
+	ip6h		  = ipv6_hdr(skb);
+	ip6_flow_hdr(ip6h, prio, htonl(0));
+	ip6h->payload_len = htons(skb->len);
+	ip6h->nexthdr     = IPPROTO_UDP;
+	ip6h->hop_limit   = ttl;
+	ip6h->daddr	  = *daddr;
+	ip6h->saddr	  = *saddr;
+
+	ip6tunnel_xmit(skb, dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb);
-- 
cgit v1.2.3


From 2e4e44107176d552f8bb1bb76053e850e3809841 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 17 Sep 2014 04:49:49 -0700
Subject: net: add alloc_skb_with_frags() helper

Extract from sock_alloc_send_pskb() code building skb with frags,
so that we can reuse this in other contexts.

Intent is to use it from tcp_send_rcvq(), tcp_collapse(), ...

We also want to replace some skb_linearize() calls to a more reliable
strategy in pathological cases where we need to reduce number of frags.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  6 ++++
 net/core/skbuff.c      | 78 ++++++++++++++++++++++++++++++++++++++++++++++++++
 net/core/sock.c        | 78 ++++++++++----------------------------------------
 3 files changed, 99 insertions(+), 63 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 756e3d057e84..f1bfa3781c75 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -769,6 +769,12 @@ static inline struct sk_buff *alloc_skb(unsigned int size,
 	return __alloc_skb(size, priority, 0, NUMA_NO_NODE);
 }
 
+struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
+				     unsigned long data_len,
+				     int max_page_order,
+				     int *errcode,
+				     gfp_t gfp_mask);
+
 static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 					       gfp_t priority)
 {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 29f7f0121491..06a8feb10099 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4102,3 +4102,81 @@ err_free:
 	return NULL;
 }
 EXPORT_SYMBOL(skb_vlan_untag);
+
+/**
+ * alloc_skb_with_frags - allocate skb with page frags
+ *
+ * header_len: size of linear part
+ * data_len: needed length in frags
+ * max_page_order: max page order desired.
+ * errcode: pointer to error code if any
+ * gfp_mask: allocation mask
+ *
+ * This can be used to allocate a paged skb, given a maximal order for frags.
+ */
+struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
+				     unsigned long data_len,
+				     int max_page_order,
+				     int *errcode,
+				     gfp_t gfp_mask)
+{
+	int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
+	unsigned long chunk;
+	struct sk_buff *skb;
+	struct page *page;
+	gfp_t gfp_head;
+	int i;
+
+	*errcode = -EMSGSIZE;
+	/* Note this test could be relaxed, if we succeed to allocate
+	 * high order pages...
+	 */
+	if (npages > MAX_SKB_FRAGS)
+		return NULL;
+
+	gfp_head = gfp_mask;
+	if (gfp_head & __GFP_WAIT)
+		gfp_head |= __GFP_REPEAT;
+
+	*errcode = -ENOBUFS;
+	skb = alloc_skb(header_len, gfp_head);
+	if (!skb)
+		return NULL;
+
+	skb->truesize += npages << PAGE_SHIFT;
+
+	for (i = 0; npages > 0; i++) {
+		int order = max_page_order;
+
+		while (order) {
+			if (npages >= 1 << order) {
+				page = alloc_pages(gfp_mask |
+						   __GFP_COMP |
+						   __GFP_NOWARN |
+						   __GFP_NORETRY,
+						   order);
+				if (page)
+					goto fill_page;
+				/* Do not retry other high order allocations */
+				order = 1;
+				max_page_order = 0;
+			}
+			order--;
+		}
+		page = alloc_page(gfp_mask);
+		if (!page)
+			goto failure;
+fill_page:
+		chunk = min_t(unsigned long, data_len,
+			      PAGE_SIZE << order);
+		skb_fill_page_desc(skb, i, page, 0, chunk);
+		data_len -= chunk;
+		npages -= 1 << order;
+	}
+	return skb;
+
+failure:
+	kfree_skb(skb);
+	return NULL;
+}
+EXPORT_SYMBOL(alloc_skb_with_frags);
diff --git a/net/core/sock.c b/net/core/sock.c
index 6f436b5e4961..de887c45c63b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1762,21 +1762,12 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 				     unsigned long data_len, int noblock,
 				     int *errcode, int max_page_order)
 {
-	struct sk_buff *skb = NULL;
-	unsigned long chunk;
-	gfp_t gfp_mask;
+	struct sk_buff *skb;
 	long timeo;
 	int err;
-	int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-	struct page *page;
-	int i;
-
-	err = -EMSGSIZE;
-	if (npages > MAX_SKB_FRAGS)
-		goto failure;
 
 	timeo = sock_sndtimeo(sk, noblock);
-	while (!skb) {
+	for (;;) {
 		err = sock_error(sk);
 		if (err != 0)
 			goto failure;
@@ -1785,66 +1776,27 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 		if (sk->sk_shutdown & SEND_SHUTDOWN)
 			goto failure;
 
-		if (atomic_read(&sk->sk_wmem_alloc) >= sk->sk_sndbuf) {
-			set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
-			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-			err = -EAGAIN;
-			if (!timeo)
-				goto failure;
-			if (signal_pending(current))
-				goto interrupted;
-			timeo = sock_wait_for_wmem(sk, timeo);
-			continue;
-		}
-
-		err = -ENOBUFS;
-		gfp_mask = sk->sk_allocation;
-		if (gfp_mask & __GFP_WAIT)
-			gfp_mask |= __GFP_REPEAT;
+		if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
+			break;
 
-		skb = alloc_skb(header_len, gfp_mask);
-		if (!skb)
+		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+		err = -EAGAIN;
+		if (!timeo)
 			goto failure;
-
-		skb->truesize += data_len;
-
-		for (i = 0; npages > 0; i++) {
-			int order = max_page_order;
-
-			while (order) {
-				if (npages >= 1 << order) {
-					page = alloc_pages(sk->sk_allocation |
-							   __GFP_COMP |
-							   __GFP_NOWARN |
-							   __GFP_NORETRY,
-							   order);
-					if (page)
-						goto fill_page;
-					/* Do not retry other high order allocations */
-					order = 1;
-					max_page_order = 0;
-				}
-				order--;
-			}
-			page = alloc_page(sk->sk_allocation);
-			if (!page)
-				goto failure;
-fill_page:
-			chunk = min_t(unsigned long, data_len,
-				      PAGE_SIZE << order);
-			skb_fill_page_desc(skb, i, page, 0, chunk);
-			data_len -= chunk;
-			npages -= 1 << order;
-		}
+		if (signal_pending(current))
+			goto interrupted;
+		timeo = sock_wait_for_wmem(sk, timeo);
 	}
-
-	skb_set_owner_w(skb, sk);
+	skb = alloc_skb_with_frags(header_len, data_len, max_page_order,
+				   errcode, sk->sk_allocation);
+	if (skb)
+		skb_set_owner_w(skb, sk);
 	return skb;
 
 interrupted:
 	err = sock_intr_errno(timeo);
 failure:
-	kfree_skb(skb);
 	*errcode = err;
 	return NULL;
 }
-- 
cgit v1.2.3


From bb7d93496f7ac203f7c3e9678000d1c83eb4e0ba Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 19 Sep 2014 13:07:50 -0700
Subject: net: phy: broadcom: add helper for PHY revision and patch level

The Broadcom BCM7xxx internal PHYs do not contain any useful revision
information in the low 4-bits of their MII_PHYSID2 (MII register 3)
which could allow us to properly identify them.

As a result, we need the actual hardware block integrating these PHYs:
GENET or the SF2 switch to tell us what revision they are built with. To
assist with that, add two helper macros for fetching the the PHY
revision and patch level from the struct phy_device::dev_flags.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/brcmphy.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 5bd35cc0d471..e4ee9c6679e8 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -41,6 +41,8 @@
 #define PHY_BRCM_DIS_TXCRXC_NOENRGY	0x00008000
 /* Broadcom BCM7xxx specific workarounds */
 #define PHY_BRCM_100MBPS_WAR		0x00010000
+#define PHY_BRCM_7XXX_REV(x)		(((x) >> 8) & 0xff)
+#define PHY_BRCM_7XXX_PATCH(x)		((x) & 0xff)
 #define PHY_BCM_FLAGS_VALID		0x80000000
 
 /* Broadcom BCM54XX register definitions, common to most Broadcom PHYs */
-- 
cgit v1.2.3


From 80780a54ecded1647e661ababde13554a149f7f3 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 19 Sep 2014 13:07:52 -0700
Subject: net: bcmgenet: remove PHY_BRCM_100MBPS_WAR

Now that we have removed the need for the PHY_BRCM_100MBPS_WAR flag, we
can remove it from the GENET driver and the broadcom shared header file.
The PHY driver checks the PHY supported bitmask instead.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 10 ----------
 include/linux/brcmphy.h                      |  1 -
 2 files changed, 11 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index c88f7ae99636..71f2ef7d33a9 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -296,7 +296,6 @@ static int bcmgenet_mii_probe(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device_node *dn = priv->pdev->dev.of_node;
 	struct phy_device *phydev;
-	unsigned int phy_flags;
 	int ret;
 
 	if (priv->phydev) {
@@ -338,15 +337,6 @@ static int bcmgenet_mii_probe(struct net_device *dev)
 		return ret;
 	}
 
-	phy_flags = PHY_BRCM_100MBPS_WAR;
-
-	/* workarounds are only needed for 100Mpbs PHYs, and
-	 * never on GENET V1 hardware
-	 */
-	if ((phydev->supported & PHY_GBIT_FEATURES) || GENET_IS_V1(priv))
-		phy_flags = 0;
-
-	phydev->dev_flags |= phy_flags;
 	phydev->advertising = phydev->supported;
 
 	/* The internal PHY has its link interrupts routed to the
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index e4ee9c6679e8..3f626fe48c9a 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -40,7 +40,6 @@
 #define PHY_BRCM_CLEAR_RGMII_MODE	0x00004000
 #define PHY_BRCM_DIS_TXCRXC_NOENRGY	0x00008000
 /* Broadcom BCM7xxx specific workarounds */
-#define PHY_BRCM_100MBPS_WAR		0x00010000
 #define PHY_BRCM_7XXX_REV(x)		(((x) >> 8) & 0xff)
 #define PHY_BRCM_7XXX_PATCH(x)		((x) & 0xff)
 #define PHY_BCM_FLAGS_VALID		0x80000000
-- 
cgit v1.2.3


From 6819563e646a7f3692836daefd12cd86c697759f Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 19 Sep 2014 13:07:54 -0700
Subject: net: dsa: allow switch drivers to specify phy_device::dev_flags

Some switch drivers (e.g: bcm_sf2) may have to communicate specific
workarounds or flags towards the PHY device driver. Allow switches
driver to be delegated that task by introducing a get_phy_flags()
callback which will do just that.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 1 +
 net/dsa/slave.c   | 9 ++++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index c779e9bba1b3..e020b8a12b7d 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -181,6 +181,7 @@ struct dsa_switch_driver {
 	char	*(*probe)(struct device *host_dev, int sw_addr);
 	int	(*setup)(struct dsa_switch *ds);
 	int	(*set_addr)(struct dsa_switch *ds, u8 *addr);
+	u32	(*get_phy_flags)(struct dsa_switch *ds, int port);
 
 	/*
 	 * Access to the switch's PHY registers.
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 90c9689ed362..a7997265019a 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -371,6 +371,7 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 	struct dsa_chip_data *cd = ds->pd;
 	struct device_node *phy_dn, *port_dn;
 	bool phy_is_fixed = false;
+	u32 phy_flags = 0;
 	int ret;
 
 	port_dn = cd->port_dn[p->port];
@@ -390,9 +391,12 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 		phy_dn = port_dn;
 	}
 
+	if (ds->drv->get_phy_flags)
+		phy_flags = ds->drv->get_phy_flags(ds, p->port);
+
 	if (phy_dn)
 		p->phy = of_phy_connect(slave_dev, phy_dn,
-					dsa_slave_adjust_link, 0,
+					dsa_slave_adjust_link, phy_flags,
 					p->phy_interface);
 
 	if (p->phy && phy_is_fixed)
@@ -480,6 +484,9 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	netif_carrier_off(slave_dev);
 
 	if (p->phy != NULL) {
+		if (ds->drv->get_phy_flags(ds, port))
+			p->phy->dev_flags |= ds->drv->get_phy_flags(ds, port);
+
 		phy_attach(slave_dev, dev_name(&p->phy->dev),
 			   PHY_INTERFACE_MODE_GMII);
 
-- 
cgit v1.2.3


From 23461551c00628c3f3fe9cf837bf53cf8f212b63 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Wed, 17 Sep 2014 12:25:56 -0700
Subject: fou: Support for foo-over-udp RX path

This patch provides a receive path for foo-over-udp. This allows
direct encapsulation of IP protocols over UDP. The bound destination
port is used to map to an IP protocol, and the XFRM framework
(udp_encap_rcv) is used to receive encapsulated packets. Upon
reception, the encapsulation header is logically removed (pointer
to transport header is advanced) and the packet is reinjected into
the receive path with the IP protocol indicated by the mapping.

Netlink is used to configure FOU ports. The configuration information
includes the port number to bind to and the IP protocol corresponding
to that port.

This should support GRE/UDP
(http://tools.ietf.org/html/draft-yong-tsvwg-gre-in-udp-encap-02),
as will as the other IP tunneling protocols (IPIP, SIT).

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/fou.h |  32 ++++++
 net/ipv4/Kconfig         |  10 ++
 net/ipv4/Makefile        |   1 +
 net/ipv4/fou.c           | 279 +++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 322 insertions(+)
 create mode 100644 include/uapi/linux/fou.h
 create mode 100644 net/ipv4/fou.c

(limited to 'include')

diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h
new file mode 100644
index 000000000000..e03376de453d
--- /dev/null
+++ b/include/uapi/linux/fou.h
@@ -0,0 +1,32 @@
+/* fou.h - FOU Interface */
+
+#ifndef _UAPI_LINUX_FOU_H
+#define _UAPI_LINUX_FOU_H
+
+/* NETLINK_GENERIC related info
+ */
+#define FOU_GENL_NAME		"fou"
+#define FOU_GENL_VERSION	0x1
+
+enum {
+	FOU_ATTR_UNSPEC,
+	FOU_ATTR_PORT,				/* u16 */
+	FOU_ATTR_AF,				/* u8 */
+	FOU_ATTR_IPPROTO,			/* u8 */
+
+	__FOU_ATTR_MAX,
+};
+
+#define FOU_ATTR_MAX		(__FOU_ATTR_MAX - 1)
+
+enum {
+	FOU_CMD_UNSPEC,
+	FOU_CMD_ADD,
+	FOU_CMD_DEL,
+
+	__FOU_CMD_MAX,
+};
+
+#define FOU_CMD_MAX	(__FOU_CMD_MAX - 1)
+
+#endif /* _UAPI_LINUX_FOU_H */
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index dbc10d84161f..84f710b7472a 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -311,6 +311,16 @@ config NET_UDP_TUNNEL
 	tristate
 	default n
 
+config NET_FOU
+	tristate "IP: Foo (IP protocols) over UDP"
+	select XFRM
+	select NET_UDP_TUNNEL
+	---help---
+	  Foo over UDP allows any IP protocol to be directly encapsulated
+	  over UDP include tunnels (IPIP, GRE, SIT). By encapsulating in UDP
+	  network mechanisms and optimizations for UDP (such as ECMP
+	  and RSS) can be leveraged to provide better service.
+
 config INET_AH
 	tristate "IP: AH transformation"
 	select XFRM_ALGO
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 8ee1cd4053ee..d78d404c596f 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
 obj-$(CONFIG_IP_MROUTE) += ipmr.o
 obj-$(CONFIG_NET_IPIP) += ipip.o
 gre-y := gre_demux.o
+obj-$(CONFIG_NET_FOU) += fou.o
 obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o
 obj-$(CONFIG_NET_IPGRE) += ip_gre.o
 obj-$(CONFIG_NET_UDP_TUNNEL) += udp_tunnel.o
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
new file mode 100644
index 000000000000..d44f97b79418
--- /dev/null
+++ b/net/ipv4/fou.c
@@ -0,0 +1,279 @@
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/socket.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <net/genetlink.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/udp_tunnel.h>
+#include <net/xfrm.h>
+#include <uapi/linux/fou.h>
+#include <uapi/linux/genetlink.h>
+
+static DEFINE_SPINLOCK(fou_lock);
+static LIST_HEAD(fou_list);
+
+struct fou {
+	struct socket *sock;
+	u8 protocol;
+	u16 port;
+	struct list_head list;
+};
+
+struct fou_cfg {
+	u8 protocol;
+	struct udp_port_cfg udp_config;
+};
+
+static inline struct fou *fou_from_sock(struct sock *sk)
+{
+	return sk->sk_user_data;
+}
+
+static int fou_udp_encap_recv_deliver(struct sk_buff *skb,
+				      u8 protocol, size_t len)
+{
+	struct iphdr *iph = ip_hdr(skb);
+
+	/* Remove 'len' bytes from the packet (UDP header and
+	 * FOU header if present), modify the protocol to the one
+	 * we found, and then call rcv_encap.
+	 */
+	iph->tot_len = htons(ntohs(iph->tot_len) - len);
+	__skb_pull(skb, len);
+	skb_postpull_rcsum(skb, udp_hdr(skb), len);
+	skb_reset_transport_header(skb);
+
+	return -protocol;
+}
+
+static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct fou *fou = fou_from_sock(sk);
+
+	if (!fou)
+		return 1;
+
+	return fou_udp_encap_recv_deliver(skb, fou->protocol,
+					  sizeof(struct udphdr));
+}
+
+static int fou_add_to_port_list(struct fou *fou)
+{
+	struct fou *fout;
+
+	spin_lock(&fou_lock);
+	list_for_each_entry(fout, &fou_list, list) {
+		if (fou->port == fout->port) {
+			spin_unlock(&fou_lock);
+			return -EALREADY;
+		}
+	}
+
+	list_add(&fou->list, &fou_list);
+	spin_unlock(&fou_lock);
+
+	return 0;
+}
+
+static void fou_release(struct fou *fou)
+{
+	struct socket *sock = fou->sock;
+	struct sock *sk = sock->sk;
+
+	udp_del_offload(&fou->udp_offloads);
+
+	list_del(&fou->list);
+
+	/* Remove hooks into tunnel socket */
+	sk->sk_user_data = NULL;
+
+	sock_release(sock);
+
+	kfree(fou);
+}
+
+static int fou_create(struct net *net, struct fou_cfg *cfg,
+		      struct socket **sockp)
+{
+	struct fou *fou = NULL;
+	int err;
+	struct socket *sock = NULL;
+	struct sock *sk;
+
+	/* Open UDP socket */
+	err = udp_sock_create(net, &cfg->udp_config, &sock);
+	if (err < 0)
+		goto error;
+
+	/* Allocate FOU port structure */
+	fou = kzalloc(sizeof(*fou), GFP_KERNEL);
+	if (!fou) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	sk = sock->sk;
+
+	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
+	fou->protocol = cfg->protocol;
+	fou->port =  cfg->udp_config.local_udp_port;
+	udp_sk(sk)->encap_rcv = fou_udp_recv;
+
+	udp_sk(sk)->encap_type = 1;
+	udp_encap_enable();
+
+	sk->sk_user_data = fou;
+	fou->sock = sock;
+
+	udp_set_convert_csum(sk, true);
+
+	sk->sk_allocation = GFP_ATOMIC;
+
+	err = fou_add_to_port_list(fou);
+	if (err)
+		goto error;
+
+	if (sockp)
+		*sockp = sock;
+
+	return 0;
+
+error:
+	kfree(fou);
+	if (sock)
+		sock_release(sock);
+
+	return err;
+}
+
+static int fou_destroy(struct net *net, struct fou_cfg *cfg)
+{
+	struct fou *fou;
+	u16 port = cfg->udp_config.local_udp_port;
+	int err = -EINVAL;
+
+	spin_lock(&fou_lock);
+	list_for_each_entry(fou, &fou_list, list) {
+		if (fou->port == port) {
+			fou_release(fou);
+			err = 0;
+			break;
+		}
+	}
+	spin_unlock(&fou_lock);
+
+	return err;
+}
+
+static struct genl_family fou_nl_family = {
+	.id		= GENL_ID_GENERATE,
+	.hdrsize	= 0,
+	.name		= FOU_GENL_NAME,
+	.version	= FOU_GENL_VERSION,
+	.maxattr	= FOU_ATTR_MAX,
+	.netnsok	= true,
+};
+
+static struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
+	[FOU_ATTR_PORT] = { .type = NLA_U16, },
+	[FOU_ATTR_AF] = { .type = NLA_U8, },
+	[FOU_ATTR_IPPROTO] = { .type = NLA_U8, },
+};
+
+static int parse_nl_config(struct genl_info *info,
+			   struct fou_cfg *cfg)
+{
+	memset(cfg, 0, sizeof(*cfg));
+
+	cfg->udp_config.family = AF_INET;
+
+	if (info->attrs[FOU_ATTR_AF]) {
+		u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]);
+
+		if (family != AF_INET && family != AF_INET6)
+			return -EINVAL;
+
+		cfg->udp_config.family = family;
+	}
+
+	if (info->attrs[FOU_ATTR_PORT]) {
+		u16 port = nla_get_u16(info->attrs[FOU_ATTR_PORT]);
+
+		cfg->udp_config.local_udp_port = port;
+	}
+
+	if (info->attrs[FOU_ATTR_IPPROTO])
+		cfg->protocol = nla_get_u8(info->attrs[FOU_ATTR_IPPROTO]);
+
+	return 0;
+}
+
+static int fou_nl_cmd_add_port(struct sk_buff *skb, struct genl_info *info)
+{
+	struct fou_cfg cfg;
+	int err;
+
+	err = parse_nl_config(info, &cfg);
+	if (err)
+		return err;
+
+	return fou_create(&init_net, &cfg, NULL);
+}
+
+static int fou_nl_cmd_rm_port(struct sk_buff *skb, struct genl_info *info)
+{
+	struct fou_cfg cfg;
+
+	parse_nl_config(info, &cfg);
+
+	return fou_destroy(&init_net, &cfg);
+}
+
+static const struct genl_ops fou_nl_ops[] = {
+	{
+		.cmd = FOU_CMD_ADD,
+		.doit = fou_nl_cmd_add_port,
+		.policy = fou_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = FOU_CMD_DEL,
+		.doit = fou_nl_cmd_rm_port,
+		.policy = fou_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+};
+
+static int __init fou_init(void)
+{
+	int ret;
+
+	ret = genl_register_family_with_ops(&fou_nl_family,
+					    fou_nl_ops);
+
+	return ret;
+}
+
+static void __exit fou_fini(void)
+{
+	struct fou *fou, *next;
+
+	genl_unregister_family(&fou_nl_family);
+
+	/* Close all the FOU sockets */
+
+	spin_lock(&fou_lock);
+	list_for_each_entry_safe(fou, next, &fou_list, list)
+		fou_release(fou);
+	spin_unlock(&fou_lock);
+}
+
+module_init(fou_init);
+module_exit(fou_fini);
+MODULE_AUTHOR("Tom Herbert <therbert@google.com>");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From afe93325bc02a5b2dea0cd7d78225de692265e6e Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Wed, 17 Sep 2014 12:25:57 -0700
Subject: fou: Add GRO support

Implement fou_gro_receive and fou_gro_complete, and populate these
in the correponsing udp_offloads for the socket. Added ipproto to
udp_offloads and pass this from UDP to the fou GRO routine in proto
field of napi_gro_cb structure.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  3 +-
 net/ipv4/fou.c            | 89 +++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv4/udp_offload.c    |  5 ++-
 3 files changed, 95 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 28d4378615e5..4354b4307e37 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1874,7 +1874,7 @@ struct napi_gro_cb {
 	/* jiffies when first packet was created/queued */
 	unsigned long age;
 
-	/* Used in ipv6_gro_receive() */
+	/* Used in ipv6_gro_receive() and foo-over-udp */
 	u16	proto;
 
 	/* Used in udp_gro_receive */
@@ -1925,6 +1925,7 @@ struct packet_offload {
 
 struct udp_offload {
 	__be16			 port;
+	u8			 ipproto;
 	struct offload_callbacks callbacks;
 };
 
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index d44f97b79418..dced89fbe480 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <net/genetlink.h>
 #include <net/ip.h>
+#include <net/protocol.h>
 #include <net/udp.h>
 #include <net/udp_tunnel.h>
 #include <net/xfrm.h>
@@ -21,6 +22,7 @@ struct fou {
 	struct socket *sock;
 	u8 protocol;
 	u16 port;
+	struct udp_offload udp_offloads;
 	struct list_head list;
 };
 
@@ -62,6 +64,69 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 					  sizeof(struct udphdr));
 }
 
+static struct sk_buff **fou_gro_receive(struct sk_buff **head,
+					struct sk_buff *skb,
+					const struct net_offload **offloads)
+{
+	const struct net_offload *ops;
+	struct sk_buff **pp = NULL;
+	u8 proto = NAPI_GRO_CB(skb)->proto;
+
+	rcu_read_lock();
+	ops = rcu_dereference(offloads[proto]);
+	if (!ops || !ops->callbacks.gro_receive)
+		goto out_unlock;
+
+	pp = ops->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+
+	return pp;
+}
+
+static int fou_gro_complete(struct sk_buff *skb, int nhoff,
+			    const struct net_offload **offloads)
+{
+	const struct net_offload *ops;
+	u8 proto = NAPI_GRO_CB(skb)->proto;
+	int err = -ENOSYS;
+
+	rcu_read_lock();
+	ops = rcu_dereference(offloads[proto]);
+	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
+		goto out_unlock;
+
+	err = ops->callbacks.gro_complete(skb, nhoff);
+
+out_unlock:
+	rcu_read_unlock();
+
+	return err;
+}
+
+static struct sk_buff **fou4_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	return fou_gro_receive(head, skb, inet_offloads);
+}
+
+static int fou4_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	return fou_gro_complete(skb, nhoff, inet_offloads);
+}
+
+static struct sk_buff **fou6_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	return fou_gro_receive(head, skb, inet6_offloads);
+}
+
+static int fou6_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	return fou_gro_complete(skb, nhoff, inet6_offloads);
+}
+
 static int fou_add_to_port_list(struct fou *fou)
 {
 	struct fou *fout;
@@ -134,6 +199,29 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 
 	sk->sk_allocation = GFP_ATOMIC;
 
+	switch (cfg->udp_config.family) {
+	case AF_INET:
+		fou->udp_offloads.callbacks.gro_receive = fou4_gro_receive;
+		fou->udp_offloads.callbacks.gro_complete = fou4_gro_complete;
+		break;
+	case AF_INET6:
+		fou->udp_offloads.callbacks.gro_receive = fou6_gro_receive;
+		fou->udp_offloads.callbacks.gro_complete = fou6_gro_complete;
+		break;
+	default:
+		err = -EPFNOSUPPORT;
+		goto error;
+	}
+
+	fou->udp_offloads.port = cfg->udp_config.local_udp_port;
+	fou->udp_offloads.ipproto = cfg->protocol;
+
+	if (cfg->udp_config.family == AF_INET) {
+		err = udp_add_offload(&fou->udp_offloads);
+		if (err)
+			goto error;
+	}
+
 	err = fou_add_to_port_list(fou);
 	if (err)
 		goto error;
@@ -160,6 +248,7 @@ static int fou_destroy(struct net *net, struct fou_cfg *cfg)
 	spin_lock(&fou_lock);
 	list_for_each_entry(fou, &fou_list, list) {
 		if (fou->port == port) {
+			udp_del_offload(&fou->udp_offloads);
 			fou_release(fou);
 			err = 0;
 			break;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index adab393b2fe5..d7c43f764c71 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -276,6 +276,7 @@ unflush:
 
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
+	NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
 	pp = uo_priv->offload->callbacks.gro_receive(head, skb);
 
 out_unlock:
@@ -329,8 +330,10 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff)
 			break;
 	}
 
-	if (uo_priv != NULL)
+	if (uo_priv != NULL) {
+		NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
 		err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr));
+	}
 
 	rcu_read_unlock();
 	return err;
-- 
cgit v1.2.3


From 56328486539ddd07cbaafec7a542a2c8a3043623 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Wed, 17 Sep 2014 12:25:58 -0700
Subject: net: Changes to ip_tunnel to support foo-over-udp encapsulation

This patch changes IP tunnel to support (secondary) encapsulation,
Foo-over-UDP. Changes include:

1) Adding tun_hlen as the tunnel header length, encap_hlen as the
   encapsulation header length, and hlen becomes the grand total
   of these.
2) Added common netlink define to support FOU encapsulation.
3) Routines to perform FOU encapsulation.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_tunnels.h       | 19 ++++++++-
 include/uapi/linux/if_tunnel.h | 12 ++++++
 net/ipv4/ip_tunnel.c           | 91 +++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 120 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 8dd8cab88b87..7f538ba6e267 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -10,6 +10,7 @@
 #include <net/gro_cells.h>
 #include <net/inet_ecn.h>
 #include <net/ip.h>
+#include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -31,6 +32,13 @@ struct ip_tunnel_6rd_parm {
 };
 #endif
 
+struct ip_tunnel_encap {
+	__u16			type;
+	__u16			flags;
+	__be16			sport;
+	__be16			dport;
+};
+
 struct ip_tunnel_prl_entry {
 	struct ip_tunnel_prl_entry __rcu *next;
 	__be32				addr;
@@ -56,13 +64,18 @@ struct ip_tunnel {
 	/* These four fields used only by GRE */
 	__u32		i_seqno;	/* The last seen seqno	*/
 	__u32		o_seqno;	/* The last output seqno */
-	int		hlen;		/* Precalculated header length */
+	int		tun_hlen;	/* Precalculated header length */
 	int		mlink;
 
 	struct ip_tunnel_dst __percpu *dst_cache;
 
 	struct ip_tunnel_parm parms;
 
+	int		encap_hlen;	/* Encap header length (FOU,GUE) */
+	struct ip_tunnel_encap encap;
+
+	int		hlen;		/* tun_hlen + encap_hlen */
+
 	/* for SIT */
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel_6rd_parm ip6rd;
@@ -114,6 +127,8 @@ void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops);
 void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		    const struct iphdr *tnl_params, const u8 protocol);
 int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
+int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
+		    u8 *protocol, struct flowi4 *fl4);
 int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
 
 struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
@@ -131,6 +146,8 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 		      struct ip_tunnel_parm *p);
 void ip_tunnel_setup(struct net_device *dev, int net_id);
 void ip_tunnel_dst_reset_all(struct ip_tunnel *t);
+int ip_tunnel_encap_setup(struct ip_tunnel *t,
+			  struct ip_tunnel_encap *ipencap);
 
 /* Extract dsfield from inner protocol */
 static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 3bce9e9d9f7c..9fedca7d8dae 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -53,10 +53,22 @@ enum {
 	IFLA_IPTUN_6RD_RELAY_PREFIX,
 	IFLA_IPTUN_6RD_PREFIXLEN,
 	IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
+	IFLA_IPTUN_ENCAP_TYPE,
+	IFLA_IPTUN_ENCAP_FLAGS,
+	IFLA_IPTUN_ENCAP_SPORT,
+	IFLA_IPTUN_ENCAP_DPORT,
 	__IFLA_IPTUN_MAX,
 };
 #define IFLA_IPTUN_MAX	(__IFLA_IPTUN_MAX - 1)
 
+enum tunnel_encap_types {
+	TUNNEL_ENCAP_NONE,
+	TUNNEL_ENCAP_FOU,
+};
+
+#define TUNNEL_ENCAP_FLAG_CSUM		(1<<0)
+#define TUNNEL_ENCAP_FLAG_CSUM6		(1<<1)
+
 /* SIT-mode i_flags */
 #define	SIT_ISATAP	0x0001
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index afed1aac2638..e3a3dc91e49c 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -55,6 +55,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
+#include <net/udp.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -487,6 +488,91 @@ drop:
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
 
+static int ip_encap_hlen(struct ip_tunnel_encap *e)
+{
+	switch (e->type) {
+	case TUNNEL_ENCAP_NONE:
+		return 0;
+	case TUNNEL_ENCAP_FOU:
+		return sizeof(struct udphdr);
+	default:
+		return -EINVAL;
+	}
+}
+
+int ip_tunnel_encap_setup(struct ip_tunnel *t,
+			  struct ip_tunnel_encap *ipencap)
+{
+	int hlen;
+
+	memset(&t->encap, 0, sizeof(t->encap));
+
+	hlen = ip_encap_hlen(ipencap);
+	if (hlen < 0)
+		return hlen;
+
+	t->encap.type = ipencap->type;
+	t->encap.sport = ipencap->sport;
+	t->encap.dport = ipencap->dport;
+	t->encap.flags = ipencap->flags;
+
+	t->encap_hlen = hlen;
+	t->hlen = t->encap_hlen + t->tun_hlen;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup);
+
+static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+			    size_t hdr_len, u8 *protocol, struct flowi4 *fl4)
+{
+	struct udphdr *uh;
+	__be16 sport;
+	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
+	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+
+	skb = iptunnel_handle_offloads(skb, csum, type);
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	/* Get length and hash before making space in skb */
+
+	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+					       skb, 0, 0, false);
+
+	skb_push(skb, hdr_len);
+
+	skb_reset_transport_header(skb);
+	uh = udp_hdr(skb);
+
+	uh->dest = e->dport;
+	uh->source = sport;
+	uh->len = htons(skb->len);
+	uh->check = 0;
+	udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb,
+		     fl4->saddr, fl4->daddr, skb->len);
+
+	*protocol = IPPROTO_UDP;
+
+	return 0;
+}
+
+int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
+		    u8 *protocol, struct flowi4 *fl4)
+{
+	switch (t->encap.type) {
+	case TUNNEL_ENCAP_NONE:
+		return 0;
+	case TUNNEL_ENCAP_FOU:
+		return fou_build_header(skb, &t->encap, t->encap_hlen,
+					protocol, fl4);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL(ip_tunnel_encap);
+
 static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 			    struct rtable *rt, __be16 df)
 {
@@ -536,7 +622,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 }
 
 void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
-		    const struct iphdr *tnl_params, const u8 protocol)
+		    const struct iphdr *tnl_params, u8 protocol)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr *inner_iph;
@@ -617,6 +703,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
 			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
 
+	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
+		goto tx_error;
+
 	rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL;
 
 	if (!rt) {
-- 
cgit v1.2.3


From 4565e9919cda747815547e2e5d7b78f15efbffdf Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Wed, 17 Sep 2014 12:26:01 -0700
Subject: gre: Setup and TX path for gre/UDP foo-over-udp encapsulation

Added netlink attrs to configure FOU encapsulation for GRE, netlink
handling of these flags, and properly adjust MTU for encapsulation.
ip_tunnel_encap is called from ip_tunnel_xmit to actually perform FOU
encapsulation.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tunnel.h |  4 ++
 net/ipv4/ip_gre.c              | 90 +++++++++++++++++++++++++++++++++++++++---
 2 files changed, 89 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 9fedca7d8dae..7c832afdfa94 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -106,6 +106,10 @@ enum {
 	IFLA_GRE_ENCAP_LIMIT,
 	IFLA_GRE_FLOWINFO,
 	IFLA_GRE_FLAGS,
+	IFLA_GRE_ENCAP_TYPE,
+	IFLA_GRE_ENCAP_FLAGS,
+	IFLA_GRE_ENCAP_SPORT,
+	IFLA_GRE_ENCAP_DPORT,
 	__IFLA_GRE_MAX,
 };
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 9b842544aea3..829aff8bf723 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -239,7 +239,7 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
 	tpi.seq = htonl(tunnel->o_seqno);
 
 	/* Push GRE header. */
-	gre_build_header(skb, &tpi, tunnel->hlen);
+	gre_build_header(skb, &tpi, tunnel->tun_hlen);
 
 	ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol);
 }
@@ -310,7 +310,7 @@ out:
 static int ipgre_tunnel_ioctl(struct net_device *dev,
 			      struct ifreq *ifr, int cmd)
 {
-	int err = 0;
+	int err;
 	struct ip_tunnel_parm p;
 
 	if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
@@ -470,13 +470,18 @@ static void ipgre_tunnel_setup(struct net_device *dev)
 static void __gre_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel;
+	int t_hlen;
 
 	tunnel = netdev_priv(dev);
-	tunnel->hlen = ip_gre_calc_hlen(tunnel->parms.o_flags);
+	tunnel->tun_hlen = ip_gre_calc_hlen(tunnel->parms.o_flags);
 	tunnel->parms.iph.protocol = IPPROTO_GRE;
 
-	dev->needed_headroom	= LL_MAX_HEADER + sizeof(struct iphdr) + 4;
-	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr) - 4;
+	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
+
+	t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
+	dev->needed_headroom	= LL_MAX_HEADER + t_hlen + 4;
+	dev->mtu		= ETH_DATA_LEN - t_hlen - 4;
 
 	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
@@ -628,6 +633,40 @@ static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[],
 		parms->iph.frag_off = htons(IP_DF);
 }
 
+/* This function returns true when ENCAP attributes are present in the nl msg */
+static bool ipgre_netlink_encap_parms(struct nlattr *data[],
+				      struct ip_tunnel_encap *ipencap)
+{
+	bool ret = false;
+
+	memset(ipencap, 0, sizeof(*ipencap));
+
+	if (!data)
+		return ret;
+
+	if (data[IFLA_GRE_ENCAP_TYPE]) {
+		ret = true;
+		ipencap->type = nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]);
+	}
+
+	if (data[IFLA_GRE_ENCAP_FLAGS]) {
+		ret = true;
+		ipencap->flags = nla_get_u16(data[IFLA_GRE_ENCAP_FLAGS]);
+	}
+
+	if (data[IFLA_GRE_ENCAP_SPORT]) {
+		ret = true;
+		ipencap->sport = nla_get_u16(data[IFLA_GRE_ENCAP_SPORT]);
+	}
+
+	if (data[IFLA_GRE_ENCAP_DPORT]) {
+		ret = true;
+		ipencap->dport = nla_get_u16(data[IFLA_GRE_ENCAP_DPORT]);
+	}
+
+	return ret;
+}
+
 static int gre_tap_init(struct net_device *dev)
 {
 	__gre_tunnel_init(dev);
@@ -657,6 +696,15 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
 	struct ip_tunnel_parm p;
+	struct ip_tunnel_encap ipencap;
+
+	if (ipgre_netlink_encap_parms(data, &ipencap)) {
+		struct ip_tunnel *t = netdev_priv(dev);
+		int err = ip_tunnel_encap_setup(t, &ipencap);
+
+		if (err < 0)
+			return err;
+	}
 
 	ipgre_netlink_parms(data, tb, &p);
 	return ip_tunnel_newlink(dev, tb, &p);
@@ -666,6 +714,15 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct nlattr *data[])
 {
 	struct ip_tunnel_parm p;
+	struct ip_tunnel_encap ipencap;
+
+	if (ipgre_netlink_encap_parms(data, &ipencap)) {
+		struct ip_tunnel *t = netdev_priv(dev);
+		int err = ip_tunnel_encap_setup(t, &ipencap);
+
+		if (err < 0)
+			return err;
+	}
 
 	ipgre_netlink_parms(data, tb, &p);
 	return ip_tunnel_changelink(dev, tb, &p);
@@ -694,6 +751,14 @@ static size_t ipgre_get_size(const struct net_device *dev)
 		nla_total_size(1) +
 		/* IFLA_GRE_PMTUDISC */
 		nla_total_size(1) +
+		/* IFLA_GRE_ENCAP_TYPE */
+		nla_total_size(2) +
+		/* IFLA_GRE_ENCAP_FLAGS */
+		nla_total_size(2) +
+		/* IFLA_GRE_ENCAP_SPORT */
+		nla_total_size(2) +
+		/* IFLA_GRE_ENCAP_DPORT */
+		nla_total_size(2) +
 		0;
 }
 
@@ -714,6 +779,17 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_GRE_PMTUDISC,
 		       !!(p->iph.frag_off & htons(IP_DF))))
 		goto nla_put_failure;
+
+	if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
+			t->encap.type) ||
+	    nla_put_u16(skb, IFLA_GRE_ENCAP_SPORT,
+			t->encap.sport) ||
+	    nla_put_u16(skb, IFLA_GRE_ENCAP_DPORT,
+			t->encap.dport) ||
+	    nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS,
+			t->encap.dport))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -731,6 +807,10 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
 	[IFLA_GRE_TTL]		= { .type = NLA_U8 },
 	[IFLA_GRE_TOS]		= { .type = NLA_U8 },
 	[IFLA_GRE_PMTUDISC]	= { .type = NLA_U8 },
+	[IFLA_GRE_ENCAP_TYPE]	= { .type = NLA_U16 },
+	[IFLA_GRE_ENCAP_FLAGS]	= { .type = NLA_U16 },
+	[IFLA_GRE_ENCAP_SPORT]	= { .type = NLA_U16 },
+	[IFLA_GRE_ENCAP_DPORT]	= { .type = NLA_U16 },
 };
 
 static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
-- 
cgit v1.2.3


From 54003f119c26573d3bb86a5efc64f3e5fd43b8c6 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 17 Sep 2014 23:23:12 +0200
Subject: net: fix sparse warnings in SNMP_UPD_PO_STATS(_BH)

ptr used to be a non __percpu pointer (result of a this_cpu_ptr
assignment, 7d720c3e4f0c4 ("percpu: add __percpu sparse annotations to
net")). Since d25398df59b56 ("net: avoid reloads in SNMP_UPD_PO_STATS"),
that's no longer the case, SNMP_UPD_PO_STATS uses this_cpu_add and ptr
is now __percpu.

Silence sparse warnings by preserving the original type and
annotation, and remove the out-of-date comment.

warning: incorrect type in initializer (different address spaces)
   expected unsigned long long *ptr
   got unsigned long long [noderef] <asn:3>*<noident>
warning: incorrect type in initializer (different address spaces)
   expected void const [noderef] <asn:3>*__vpp_verify
   got unsigned long long *<noident>
warning: incorrect type in initializer (different address spaces)
   expected void const [noderef] <asn:3>*__vpp_verify
   got unsigned long long *<noident>

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/snmp.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/snmp.h b/include/net/snmp.h
index f1f27fdbb0d5..8fd2f498782e 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -146,19 +146,15 @@ struct linux_xfrm_mib {
 
 #define SNMP_ADD_STATS(mib, field, addend)	\
 			this_cpu_add(mib->mibs[field], addend)
-/*
- * Use "__typeof__(*mib) *ptr" instead of "__typeof__(mib) ptr"
- * to make @ptr a non-percpu pointer.
- */
 #define SNMP_UPD_PO_STATS(mib, basefield, addend)	\
 	do { \
-		__typeof__(*mib->mibs) *ptr = mib->mibs;	\
+		__typeof__((mib->mibs) + 0) ptr = mib->mibs;	\
 		this_cpu_inc(ptr[basefield##PKTS]);		\
 		this_cpu_add(ptr[basefield##OCTETS], addend);	\
 	} while (0)
 #define SNMP_UPD_PO_STATS_BH(mib, basefield, addend)	\
 	do { \
-		__typeof__(*mib->mibs) *ptr = mib->mibs;	\
+		__typeof__((mib->mibs) + 0) ptr = mib->mibs;	\
 		__this_cpu_inc(ptr[basefield##PKTS]);		\
 		__this_cpu_add(ptr[basefield##OCTETS], addend);	\
 	} while (0)
-- 
cgit v1.2.3


From 0d566379c5e15a2922dc6bb2ee6a4b7f7a3a0786 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 18 Sep 2014 10:31:03 +0200
Subject: genetlink: add function genl_has_listeners()

This function is the counterpart of the function netlink_has_listeners().

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 93695f0e22a5..af10c2cf8a1d 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -394,4 +394,12 @@ static inline int genl_set_err(struct genl_family *family, struct net *net,
 	return netlink_set_err(net->genl_sock, portid, group, code);
 }
 
+static inline int genl_has_listeners(struct genl_family *family,
+				     struct sock *sk, unsigned int group)
+{
+	if (WARN_ON_ONCE(group >= family->n_mcgrps))
+		return -EINVAL;
+	group = family->mcgrp_offset + group;
+	return netlink_has_listeners(sk, group);
+}
 #endif	/* __NET_GENERIC_NETLINK_H */
-- 
cgit v1.2.3


From 77507aa249aecd06fa25ad058b64481e46887a01 Mon Sep 17 00:00:00 2001
From: Ido Shamay <idos@mellanox.com>
Date: Thu, 18 Sep 2014 11:50:59 +0300
Subject: net/mlx4_core: Enable CQE/EQE stride support

This feature is intended for archs having cache line larger then 64B.

Since our CQE/EQEs are generally 64B in those systems, HW will write
twice to the same cache line consecutively, causing pipe locks due to
he hazard prevention mechanism. For elements in a cyclic buffer, writes
are consecutive, so entries smaller than a cache line should be
avoided, especially if they are written at a high rate.

Reduce consecutive writes to same cache line in CQs/EQs, by allowing the
driver to increase the distance between entries so that each will reside
in a different cache line. Until the introduction of this feature, there
were two types of CQE/EQE:

1. 32B stride and context in the [0-31] segment
2. 64B stride and context in the [32-63] segment

This feature introduces two additional types:

3. 128B stride and context in the [0-31] segment (128B cache line)
4. 256B stride and context in the [0-31] segment (256B cache line)

Modify the mlx4_core driver to query the device for the CQE/EQE cache
line stride capability and to enable that capability when the host
cache line size is larger than 64 bytes (supported cache lines are
128B and 256B).

The mlx4 IB driver and libmlx4 need not be aware of this change. The PF
context behaviour is changed to require this change in VF drivers
running on such archs.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/fw.c   | 38 ++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/fw.h   |  2 +
 drivers/net/ethernet/mellanox/mlx4/main.c | 61 ++++++++++++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h |  3 ++
 include/linux/mlx4/device.h               | 11 ++++--
 5 files changed, 108 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 494753e44ae3..13b2e4a51ef4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -137,7 +137,9 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[8] = "Dynamic QP updates support",
 		[9] = "Device managed flow steering IPoIB support",
 		[10] = "TCP/IP offloads/flow-steering for VXLAN support",
-		[11] = "MAD DEMUX (Secure-Host) support"
+		[11] = "MAD DEMUX (Secure-Host) support",
+		[12] = "Large cache line (>64B) CQE stride support",
+		[13] = "Large cache line (>64B) EQE stride support"
 	};
 	int i;
 
@@ -557,6 +559,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET	0x74
 #define QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET	0x76
 #define QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET	0x77
+#define QUERY_DEV_CAP_CQ_EQ_CACHE_LINE_STRIDE	0x7a
 #define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET	0x80
 #define QUERY_DEV_CAP_QPC_ENTRY_SZ_OFFSET	0x82
 #define QUERY_DEV_CAP_AUX_ENTRY_SZ_OFFSET	0x84
@@ -733,6 +736,11 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev_cap->max_rq_sg = field;
 	MLX4_GET(size, outbox, QUERY_DEV_CAP_MAX_DESC_SZ_RQ_OFFSET);
 	dev_cap->max_rq_desc_sz = size;
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_CQ_EQ_CACHE_LINE_STRIDE);
+	if (field & (1 << 6))
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_CQE_STRIDE;
+	if (field & (1 << 7))
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
 
 	MLX4_GET(dev_cap->bmme_flags, outbox,
 		 QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
@@ -1376,6 +1384,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 #define	 INIT_HCA_CQC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x30)
 #define	 INIT_HCA_LOG_CQ_OFFSET		 (INIT_HCA_QPC_OFFSET + 0x37)
 #define	 INIT_HCA_EQE_CQE_OFFSETS	 (INIT_HCA_QPC_OFFSET + 0x38)
+#define	 INIT_HCA_EQE_CQE_STRIDE_OFFSET  (INIT_HCA_QPC_OFFSET + 0x3b)
 #define	 INIT_HCA_ALTC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x40)
 #define	 INIT_HCA_AUXC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x50)
 #define	 INIT_HCA_EQC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x60)
@@ -1452,11 +1461,25 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_64B_CQE) {
 		*(inbox + INIT_HCA_EQE_CQE_OFFSETS / 4) |= cpu_to_be32(1 << 30);
 		dev->caps.cqe_size   = 64;
-		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_64B_CQE;
+		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_LARGE_CQE;
 	} else {
 		dev->caps.cqe_size   = 32;
 	}
 
+	/* CX3 is capable of extending CQEs\EQEs to strides larger than 64B */
+	if ((dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_EQE_STRIDE) &&
+	    (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_CQE_STRIDE)) {
+		dev->caps.eqe_size = cache_line_size();
+		dev->caps.cqe_size = cache_line_size();
+		dev->caps.eqe_factor = 0;
+		MLX4_PUT(inbox, (u8)((ilog2(dev->caps.eqe_size) - 5) << 4 |
+				      (ilog2(dev->caps.eqe_size) - 5)),
+			 INIT_HCA_EQE_CQE_STRIDE_OFFSET);
+
+		/* User still need to know to support CQE > 32B */
+		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_LARGE_CQE;
+	}
+
 	/* QPC/EEC/CQC/EQC/RDMARC attributes */
 
 	MLX4_PUT(inbox, param->qpc_base,      INIT_HCA_QPC_BASE_OFFSET);
@@ -1616,6 +1639,17 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	if (byte_field & 0x40) /* 64-bytes cqe enabled */
 		param->dev_cap_enabled |= MLX4_DEV_CAP_64B_CQE_ENABLED;
 
+	/* CX3 is capable of extending CQEs\EQEs to strides larger than 64B */
+	MLX4_GET(byte_field, outbox, INIT_HCA_EQE_CQE_STRIDE_OFFSET);
+	if (byte_field) {
+		param->dev_cap_enabled |= MLX4_DEV_CAP_64B_EQE_ENABLED;
+		param->dev_cap_enabled |= MLX4_DEV_CAP_64B_CQE_ENABLED;
+		param->cqe_size = 1 << ((byte_field &
+					 MLX4_CQE_SIZE_MASK_STRIDE) + 5);
+		param->eqe_size = 1 << (((byte_field &
+					  MLX4_EQE_SIZE_MASK_STRIDE) >> 4) + 5);
+	}
+
 	/* TPT attributes */
 
 	MLX4_GET(param->dmpt_base,  outbox, INIT_HCA_DMPT_BASE_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 1fce03ebe5c4..9b835aecac96 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -178,6 +178,8 @@ struct mlx4_init_hca_param {
 	u8  uar_page_sz; /* log pg sz in 4k chunks */
 	u8  steering_mode; /* for QUERY_HCA */
 	u64 dev_cap_enabled;
+	u16 cqe_size; /* For use only when CQE stride feature enabled */
+	u16 eqe_size; /* For use only when EQE stride feature enabled */
 };
 
 struct mlx4_init_ib_param {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7e2d5d57c598..1f10023af1db 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -104,7 +104,8 @@ module_param(enable_64b_cqe_eqe, bool, 0444);
 MODULE_PARM_DESC(enable_64b_cqe_eqe,
 		 "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");
 
-#define PF_CONTEXT_BEHAVIOUR_MASK	MLX4_FUNC_CAP_64B_EQE_CQE
+#define PF_CONTEXT_BEHAVIOUR_MASK	(MLX4_FUNC_CAP_64B_EQE_CQE | \
+					 MLX4_FUNC_CAP_EQE_CQE_STRIDE)
 
 static char mlx4_version[] =
 	DRV_NAME ": Mellanox ConnectX core driver v"
@@ -196,6 +197,40 @@ static void mlx4_set_port_mask(struct mlx4_dev *dev)
 		dev->caps.port_mask[i] = dev->caps.port_type[i];
 }
 
+static void mlx4_enable_cqe_eqe_stride(struct mlx4_dev *dev)
+{
+	struct mlx4_caps *dev_cap = &dev->caps;
+
+	/* FW not supporting or cancelled by user */
+	if (!(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_EQE_STRIDE) ||
+	    !(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_CQE_STRIDE))
+		return;
+
+	/* Must have 64B CQE_EQE enabled by FW to use bigger stride
+	 * When FW has NCSI it may decide not to report 64B CQE/EQEs
+	 */
+	if (!(dev_cap->flags & MLX4_DEV_CAP_FLAG_64B_EQE) ||
+	    !(dev_cap->flags & MLX4_DEV_CAP_FLAG_64B_CQE)) {
+		dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_CQE_STRIDE;
+		dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
+		return;
+	}
+
+	if (cache_line_size() == 128 || cache_line_size() == 256) {
+		mlx4_dbg(dev, "Enabling CQE stride cacheLine supported\n");
+		/* Changing the real data inside CQE size to 32B */
+		dev_cap->flags &= ~MLX4_DEV_CAP_FLAG_64B_CQE;
+		dev_cap->flags &= ~MLX4_DEV_CAP_FLAG_64B_EQE;
+
+		if (mlx4_is_master(dev))
+			dev_cap->function_caps |= MLX4_FUNC_CAP_EQE_CQE_STRIDE;
+	} else {
+		mlx4_dbg(dev, "Disabling CQE stride cacheLine unsupported\n");
+		dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_CQE_STRIDE;
+		dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
+	}
+}
+
 static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 {
 	int err;
@@ -390,6 +425,14 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 			dev->caps.flags &= ~MLX4_DEV_CAP_FLAG_64B_CQE;
 			dev->caps.flags &= ~MLX4_DEV_CAP_FLAG_64B_EQE;
 		}
+
+		if (dev_cap->flags2 &
+		    (MLX4_DEV_CAP_FLAG2_CQE_STRIDE |
+		     MLX4_DEV_CAP_FLAG2_EQE_STRIDE)) {
+			mlx4_warn(dev, "Disabling EQE/CQE stride per user request\n");
+			dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_CQE_STRIDE;
+			dev_cap->flags2 &= ~MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
+		}
 	}
 
 	if ((dev->caps.flags &
@@ -397,6 +440,9 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	    mlx4_is_master(dev))
 		dev->caps.function_caps |= MLX4_FUNC_CAP_64B_EQE_CQE;
 
+	if (!mlx4_is_slave(dev))
+		mlx4_enable_cqe_eqe_stride(dev);
+
 	return 0;
 }
 
@@ -724,11 +770,22 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 
 	if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_64B_CQE_ENABLED) {
 		dev->caps.cqe_size   = 64;
-		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_64B_CQE;
+		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_LARGE_CQE;
 	} else {
 		dev->caps.cqe_size   = 32;
 	}
 
+	if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_EQE_STRIDE_ENABLED) {
+		dev->caps.eqe_size = hca_param.eqe_size;
+		dev->caps.eqe_factor = 0;
+	}
+
+	if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_CQE_STRIDE_ENABLED) {
+		dev->caps.cqe_size = hca_param.cqe_size;
+		/* User still need to know when CQE > 32B */
+		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_LARGE_CQE;
+	}
+
 	dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS;
 	mlx4_warn(dev, "Timestamping is not supported in slave mode\n");
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index b508c7887ef8..de10dbb2e6ed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -285,6 +285,9 @@ struct mlx4_icm_table {
 #define MLX4_MPT_STATUS_SW		0xF0
 #define MLX4_MPT_STATUS_HW		0x00
 
+#define MLX4_CQE_SIZE_MASK_STRIDE	0x3
+#define MLX4_EQE_SIZE_MASK_STRIDE	0x30
+
 /*
  * Must be packed because mtt_seg is 64 bits but only aligned to 32 bits.
  */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 1befd8df9cfc..7bcefe749a39 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -185,19 +185,24 @@ enum {
 	MLX4_DEV_CAP_FLAG2_DMFS_IPOIB		= 1LL <<  9,
 	MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS	= 1LL <<  10,
 	MLX4_DEV_CAP_FLAG2_MAD_DEMUX		= 1LL <<  11,
+	MLX4_DEV_CAP_FLAG2_CQE_STRIDE		= 1LL <<  12,
+	MLX4_DEV_CAP_FLAG2_EQE_STRIDE		= 1LL <<  13
 };
 
 enum {
 	MLX4_DEV_CAP_64B_EQE_ENABLED	= 1LL << 0,
-	MLX4_DEV_CAP_64B_CQE_ENABLED	= 1LL << 1
+	MLX4_DEV_CAP_64B_CQE_ENABLED	= 1LL << 1,
+	MLX4_DEV_CAP_CQE_STRIDE_ENABLED	= 1LL << 2,
+	MLX4_DEV_CAP_EQE_STRIDE_ENABLED	= 1LL << 3
 };
 
 enum {
-	MLX4_USER_DEV_CAP_64B_CQE	= 1L << 0
+	MLX4_USER_DEV_CAP_LARGE_CQE	= 1L << 0
 };
 
 enum {
-	MLX4_FUNC_CAP_64B_EQE_CQE	= 1L << 0
+	MLX4_FUNC_CAP_64B_EQE_CQE	= 1L << 0,
+	MLX4_FUNC_CAP_EQE_CQE_STRIDE	= 1L << 1
 };
 
 
-- 
cgit v1.2.3


From e625305b390790717cf2cccf61efb81299647028 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 20 Sep 2014 01:27:25 -0400
Subject: percpu-refcount: make percpu_ref based on longs instead of ints

percpu_ref is currently based on ints and the number of refs it can
cover is (1 << 31).  This makes it impossible to use a percpu_ref to
count memory objects or pages on 64bit machines as it may overflow.
This forces those users to somehow aggregate the references before
contributing to the percpu_ref which is often cumbersome and sometimes
challenging to get the same level of performance as using the
percpu_ref directly.

While using ints for the percpu counters makes them pack tighter on
64bit machines, the possible gain from using ints instead of longs is
extremely small compared to the overall gain from per-cpu operation.
This patch makes percpu_ref based on longs so that it can be used to
directly count memory objects or pages.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
---
 include/linux/percpu-refcount.h | 24 ++++++++++++------------
 lib/percpu-refcount.c           | 37 +++++++++++++++++++------------------
 2 files changed, 31 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index ee8325122dbd..5df6784bd9d2 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -55,7 +55,7 @@ struct percpu_ref;
 typedef void (percpu_ref_func_t)(struct percpu_ref *);
 
 struct percpu_ref {
-	atomic_t		count;
+	atomic_long_t		count;
 	/*
 	 * The low bit of the pointer indicates whether the ref is in percpu
 	 * mode; if set, then get/put will manipulate the atomic_t.
@@ -97,7 +97,7 @@ static inline void percpu_ref_kill(struct percpu_ref *ref)
  * branches as it can't assume that @ref->pcpu_count is not NULL.
  */
 static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
-				    unsigned __percpu **pcpu_countp)
+				    unsigned long __percpu **pcpu_countp)
 {
 	unsigned long pcpu_ptr = ACCESS_ONCE(ref->pcpu_count_ptr);
 
@@ -107,7 +107,7 @@ static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
 	if (unlikely(pcpu_ptr & PCPU_REF_DEAD))
 		return false;
 
-	*pcpu_countp = (unsigned __percpu *)pcpu_ptr;
+	*pcpu_countp = (unsigned long __percpu *)pcpu_ptr;
 	return true;
 }
 
@@ -119,14 +119,14 @@ static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
   */
 static inline void percpu_ref_get(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__pcpu_ref_alive(ref, &pcpu_count))
 		this_cpu_inc(*pcpu_count);
 	else
-		atomic_inc(&ref->count);
+		atomic_long_inc(&ref->count);
 
 	rcu_read_unlock_sched();
 }
@@ -142,7 +142,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 	int ret = false;
 
 	rcu_read_lock_sched();
@@ -151,7 +151,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 		this_cpu_inc(*pcpu_count);
 		ret = true;
 	} else {
-		ret = atomic_inc_not_zero(&ref->count);
+		ret = atomic_long_inc_not_zero(&ref->count);
 	}
 
 	rcu_read_unlock_sched();
@@ -175,7 +175,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 	int ret = false;
 
 	rcu_read_lock_sched();
@@ -199,13 +199,13 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
  */
 static inline void percpu_ref_put(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__pcpu_ref_alive(ref, &pcpu_count))
 		this_cpu_dec(*pcpu_count);
-	else if (unlikely(atomic_dec_and_test(&ref->count)))
+	else if (unlikely(atomic_long_dec_and_test(&ref->count)))
 		ref->release(ref);
 
 	rcu_read_unlock_sched();
@@ -219,11 +219,11 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *pcpu_count;
 
 	if (__pcpu_ref_alive(ref, &pcpu_count))
 		return false;
-	return !atomic_read(&ref->count);
+	return !atomic_long_read(&ref->count);
 }
 
 #endif
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 70d28c91f35a..559ee0b20318 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -25,15 +25,15 @@
  * works.
  *
  * Converting to non percpu mode is done with some RCUish stuff in
- * percpu_ref_kill. Additionally, we need a bias value so that the atomic_t
- * can't hit 0 before we've added up all the percpu refs.
+ * percpu_ref_kill. Additionally, we need a bias value so that the
+ * atomic_long_t can't hit 0 before we've added up all the percpu refs.
  */
 
-#define PCPU_COUNT_BIAS		(1U << 31)
+#define PCPU_COUNT_BIAS		(1LU << (BITS_PER_LONG - 1))
 
-static unsigned __percpu *pcpu_count_ptr(struct percpu_ref *ref)
+static unsigned long __percpu *pcpu_count_ptr(struct percpu_ref *ref)
 {
-	return (unsigned __percpu *)(ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
+	return (unsigned long __percpu *)(ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
 }
 
 /**
@@ -43,7 +43,7 @@ static unsigned __percpu *pcpu_count_ptr(struct percpu_ref *ref)
  * @gfp: allocation mask to use
  *
  * Initializes the refcount in single atomic counter mode with a refcount of 1;
- * analagous to atomic_set(ref, 1).
+ * analagous to atomic_long_set(ref, 1).
  *
  * Note that @release must not sleep - it may potentially be called from RCU
  * callback context by percpu_ref_kill().
@@ -51,9 +51,9 @@ static unsigned __percpu *pcpu_count_ptr(struct percpu_ref *ref)
 int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 		    gfp_t gfp)
 {
-	atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+	atomic_long_set(&ref->count, 1 + PCPU_COUNT_BIAS);
 
-	ref->pcpu_count_ptr = (unsigned long)alloc_percpu_gfp(unsigned, gfp);
+	ref->pcpu_count_ptr = (unsigned long)alloc_percpu_gfp(unsigned long, gfp);
 	if (!ref->pcpu_count_ptr)
 		return -ENOMEM;
 
@@ -75,13 +75,13 @@ EXPORT_SYMBOL_GPL(percpu_ref_init);
  */
 void percpu_ref_reinit(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count = pcpu_count_ptr(ref);
+	unsigned long __percpu *pcpu_count = pcpu_count_ptr(ref);
 	int cpu;
 
 	BUG_ON(!pcpu_count);
 	WARN_ON(!percpu_ref_is_zero(ref));
 
-	atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+	atomic_long_set(&ref->count, 1 + PCPU_COUNT_BIAS);
 
 	/*
 	 * Restore per-cpu operation.  smp_store_release() is paired with
@@ -109,7 +109,7 @@ EXPORT_SYMBOL_GPL(percpu_ref_reinit);
  */
 void percpu_ref_exit(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count = pcpu_count_ptr(ref);
+	unsigned long __percpu *pcpu_count = pcpu_count_ptr(ref);
 
 	if (pcpu_count) {
 		free_percpu(pcpu_count);
@@ -121,14 +121,15 @@ EXPORT_SYMBOL_GPL(percpu_ref_exit);
 static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 {
 	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
-	unsigned __percpu *pcpu_count = pcpu_count_ptr(ref);
-	unsigned count = 0;
+	unsigned long __percpu *pcpu_count = pcpu_count_ptr(ref);
+	unsigned long count = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu)
 		count += *per_cpu_ptr(pcpu_count, cpu);
 
-	pr_debug("global %i pcpu %i", atomic_read(&ref->count), (int) count);
+	pr_debug("global %ld pcpu %ld",
+		 atomic_long_read(&ref->count), (long)count);
 
 	/*
 	 * It's crucial that we sum the percpu counters _before_ adding the sum
@@ -143,11 +144,11 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 	 * time is equivalent and saves us atomic operations:
 	 */
 
-	atomic_add((int) count - PCPU_COUNT_BIAS, &ref->count);
+	atomic_long_add((long)count - PCPU_COUNT_BIAS, &ref->count);
 
-	WARN_ONCE(atomic_read(&ref->count) <= 0,
-		  "percpu ref (%pf) <= 0 (%i) after killed",
-		  ref->release, atomic_read(&ref->count));
+	WARN_ONCE(atomic_long_read(&ref->count) <= 0,
+		  "percpu ref (%pf) <= 0 (%ld) after killed",
+		  ref->release, atomic_long_read(&ref->count));
 
 	/* @ref is viewed as dead on all CPUs, send out kill confirmation */
 	if (ref->confirm_kill)
-- 
cgit v1.2.3


From 6a40281ab5c1ed8ba2253857118a5d400a2d084b Mon Sep 17 00:00:00 2001
From: Chuck Ebbert <cebbert.lkml@gmail.com>
Date: Sat, 20 Sep 2014 10:17:51 -0500
Subject: sched: Fix end_of_stack() and location of stack canary for
 architectures using CONFIG_STACK_GROWSUP

Aaron Tomlin recently posted patches [1] to enable checking the
stack canary on every task switch. Looking at the canary code, I
realized that every arch (except ia64, which adds some space for
register spill above the stack) shares a definition of
end_of_stack() that makes it the first long after the
threadinfo.

For stacks that grow down, this low address is correct because
the stack starts at the end of the thread area and grows toward
lower addresses. However, for stacks that grow up, toward higher
addresses, this is wrong. (The stack actually grows away from
the canary.) On these archs end_of_stack() should return the
address of the last long, at the highest possible address for the stack.

[1] http://lkml.org/lkml/2014/9/12/293

Signed-off-by: Chuck Ebbert <cebbert.lkml@gmail.com>
Link: http://lkml.kernel.org/r/20140920101751.6c5166b6@as
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: James Hogan <james.hogan@imgtec.com> [metag]
Acked-by: James Hogan <james.hogan@imgtec.com>
Acked-by: Aaron Tomlin <atomlin@redhat.com>
---
 include/linux/sched.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c2c885ee52b..1f07040d28e3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2608,9 +2608,22 @@ static inline void setup_thread_stack(struct task_struct *p, struct task_struct
 	task_thread_info(p)->task = p;
 }
 
+/*
+ * Return the address of the last usable long on the stack.
+ *
+ * When the stack grows down, this is just above the thread
+ * info struct. Going any lower will corrupt the threadinfo.
+ *
+ * When the stack grows up, this is the highest address.
+ * Beyond that position, we corrupt data on the next page.
+ */
 static inline unsigned long *end_of_stack(struct task_struct *p)
 {
+#ifdef CONFIG_STACK_GROWSUP
+	return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1;
+#else
 	return (unsigned long *)(task_thread_info(p) + 1);
+#endif
 }
 
 #endif
-- 
cgit v1.2.3


From 8ab17fc92e49bc2b8fff9d220c19bf50ec9c1158 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Sun, 21 Sep 2014 02:58:18 +0200
Subject: ACPI / hotplug: Generate online uevents for ACPI containers

Commit 46394fd01 (ACPI / hotplug: Move container-specific code out of
the core) removed the generation of "online" uevents for containers,
because "add" uevents are now generated for them automatically when
container system devices are registered.  However, there are user
space tools that need to be notified when the container and all of
its children have been enumerated, which doesn't happen any more.

For this reason, add a mechanism allowing "online" uevents to be
generated for ACPI containers after enumerating the container along
with all of its children.

Fixes: 46394fd01 (ACPI / hotplug: Move container-specific code out of the core)
Reported-and-tested-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: 3.14+ <stable@vger.kernel.org> # 3.14+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/container.c | 8 ++++++++
 drivers/acpi/scan.c      | 3 +++
 include/acpi/acpi_bus.h  | 1 +
 3 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
index 76f7cff64594..c8ead9f97375 100644
--- a/drivers/acpi/container.c
+++ b/drivers/acpi/container.c
@@ -99,6 +99,13 @@ static void container_device_detach(struct acpi_device *adev)
 		device_unregister(dev);
 }
 
+static void container_device_online(struct acpi_device *adev)
+{
+	struct device *dev = acpi_driver_data(adev);
+
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
 static struct acpi_scan_handler container_handler = {
 	.ids = container_device_ids,
 	.attach = container_device_attach,
@@ -106,6 +113,7 @@ static struct acpi_scan_handler container_handler = {
 	.hotplug = {
 		.enabled = true,
 		.demand_offline = true,
+		.notify_online = container_device_online,
 	},
 };
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 3bf7764659a4..1c9a664c1705 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2189,6 +2189,9 @@ static void acpi_bus_attach(struct acpi_device *device)
  ok:
 	list_for_each_entry(child, &device->children, node)
 		acpi_bus_attach(child);
+
+	if (device->handler && device->handler->hotplug.notify_online)
+		device->handler->hotplug.notify_online(device);
 }
 
 /**
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index c1c9de19edbe..2f98cf84368f 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -118,6 +118,7 @@ struct acpi_device;
 struct acpi_hotplug_profile {
 	struct kobject kobj;
 	int (*scan_dependent)(struct acpi_device *adev);
+	void (*notify_online)(struct acpi_device *adev);
 	bool enabled:1;
 	bool demand_offline:1;
 };
-- 
cgit v1.2.3


From ead130335f35fb732921ee0ffde6639be35aa108 Mon Sep 17 00:00:00 2001
From: Prabhakar Lad <prabhakar.csengg@gmail.com>
Date: Sat, 6 Sep 2014 12:26:49 -0300
Subject: [media] media: videobuf2-core.h: add a helper to get status of
 start_streaming()

this patch adds a helper to get the status if start_streaming()
was called successfully.

Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Cc: Pawel Osciak <pawel@osciak.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/videobuf2-core.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 5a10d8d695b4..b3c9973463ed 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -590,6 +590,15 @@ vb2_plane_size(struct vb2_buffer *vb, unsigned int plane_no)
 	return 0;
 }
 
+/**
+ * vb2_start_streaming_called() - return streaming status of driver
+ * @q:		videobuf queue
+ */
+static inline bool vb2_start_streaming_called(struct vb2_queue *q)
+{
+	return q->start_streaming_called;
+}
+
 /*
  * The following functions are not part of the vb2 core API, but are simple
  * helper functions that you can use in your struct v4l2_file_operations,
-- 
cgit v1.2.3


From e3d6eb1c16ef174a8fbbdd40770f5cbace0710e4 Mon Sep 17 00:00:00 2001
From: Vincent Palatin <vpalatin@chromium.org>
Date: Wed, 3 Sep 2014 16:38:39 -0300
Subject: [media] v4l: Add camera pan/tilt speed controls

The V4L2_CID_PAN_SPEED and V4L2_CID_TILT_SPEED controls allow to move the
camera by setting its rotation speed around its axis.

Signed-off-by: Vincent Palatin <vpalatin@chromium.org>
Reviewed-by: Pawel Osciak <posciak@chromium.org>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 Documentation/DocBook/media/v4l/compat.xml   | 10 ++++++++++
 Documentation/DocBook/media/v4l/controls.xml | 21 +++++++++++++++++++++
 drivers/media/v4l2-core/v4l2-ctrls.c         |  2 ++
 include/uapi/linux/v4l2-controls.h           |  2 ++
 4 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/Documentation/DocBook/media/v4l/compat.xml b/Documentation/DocBook/media/v4l/compat.xml
index eee6f0f4aa43..7aa7c5d41e3b 100644
--- a/Documentation/DocBook/media/v4l/compat.xml
+++ b/Documentation/DocBook/media/v4l/compat.xml
@@ -2545,6 +2545,16 @@ fields changed from _s32 to _u32.
       </orderedlist>
     </section>
 
+    <section>
+      <title>V4L2 in Linux 3.18</title>
+      <orderedlist>
+	<listitem>
+	  <para>Added <constant>V4L2_CID_PAN_SPEED</constant> and
+ <constant>V4L2_CID_TILT_SPEED</constant> camera controls.</para>
+	</listitem>
+      </orderedlist>
+    </section>
+
     <section id="other">
       <title>Relation of V4L2 to other Linux multimedia APIs</title>
 
diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml
index a7eb1bde8b92..e013e4bf244c 100644
--- a/Documentation/DocBook/media/v4l/controls.xml
+++ b/Documentation/DocBook/media/v4l/controls.xml
@@ -3965,6 +3965,27 @@ by exposure, white balance or focus controls.</entry>
 	  </row>
 	  <row><entry></entry></row>
 
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_PAN_SPEED</constant>&nbsp;</entry>
+	    <entry>integer</entry>
+	  </row><row><entry spanname="descr">This control turns the
+camera horizontally at the specific speed. The unit is undefined. A
+positive value moves the camera to the right (clockwise when viewed
+from above), a negative value to the left. A value of zero stops the motion
+if one is in progress and has no effect otherwise.</entry>
+	  </row>
+	  <row><entry></entry></row>
+
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TILT_SPEED</constant>&nbsp;</entry>
+	    <entry>integer</entry>
+	  </row><row><entry spanname="descr">This control turns the
+camera vertically at the specified speed. The unit is undefined. A
+positive value moves the camera up, a negative value down. A value of zero
+stops the motion if one is in progress and has no effect otherwise.</entry>
+	  </row>
+	  <row><entry></entry></row>
+
 	</tbody>
       </tgroup>
     </table>
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 35d1f3d5045b..86012140923f 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -796,6 +796,8 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_AUTO_FOCUS_STOP:		return "Auto Focus, Stop";
 	case V4L2_CID_AUTO_FOCUS_STATUS:	return "Auto Focus, Status";
 	case V4L2_CID_AUTO_FOCUS_RANGE:		return "Auto Focus, Range";
+	case V4L2_CID_PAN_SPEED:		return "Pan, Speed";
+	case V4L2_CID_TILT_SPEED:		return "Tilt, Speed";
 
 	/* FM Radio Modulator controls */
 	/* Keep the order of the 'case's the same as in v4l2-controls.h! */
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 8b930210a4b9..661f119a51b8 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -746,6 +746,8 @@ enum v4l2_auto_focus_range {
 	V4L2_AUTO_FOCUS_RANGE_INFINITY		= 3,
 };
 
+#define V4L2_CID_PAN_SPEED			(V4L2_CID_CAMERA_CLASS_BASE+32)
+#define V4L2_CID_TILT_SPEED			(V4L2_CID_CAMERA_CLASS_BASE+33)
 
 /* FM Modulator class control IDs */
 
-- 
cgit v1.2.3


From fcc0d3db28922f9ba21ea6c7b23ea10ffb5d3521 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 21 Jul 2014 17:06:33 -0300
Subject: [media] v4l: Add ARGB555X and XRGB555X pixel formats

The existing RGB555X pixel format is ill-defined in respect to its alpha
bit and its meaning is driver dependent. Create new standard ARGB555X
and XRGB555X variants with clearly defined meanings and make the
existing variant deprecated.

The new pixel formats 4CC values have been selected to match the DRM
4CCs for the same in-memory formats.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 .../DocBook/media/v4l/pixfmt-packed-rgb.xml        | 50 ++++++++++++++++++++--
 include/uapi/linux/videodev2.h                     |  3 ++
 2 files changed, 50 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/DocBook/media/v4l/pixfmt-packed-rgb.xml b/Documentation/DocBook/media/v4l/pixfmt-packed-rgb.xml
index 2aae8e9452a4..65a11867e0ae 100644
--- a/Documentation/DocBook/media/v4l/pixfmt-packed-rgb.xml
+++ b/Documentation/DocBook/media/v4l/pixfmt-packed-rgb.xml
@@ -237,9 +237,9 @@ for a pixel lie next to each other in memory.</para>
 	    <entry>g<subscript>4</subscript></entry>
 	    <entry>g<subscript>3</subscript></entry>
 	  </row>
-	  <row id="V4L2-PIX-FMT-RGB555X">
-	    <entry><constant>V4L2_PIX_FMT_RGB555X</constant></entry>
-	    <entry>'RGBQ'</entry>
+	  <row id="V4L2-PIX-FMT-ARGB555X">
+	    <entry><constant>V4L2_PIX_FMT_ARGB555X</constant></entry>
+	    <entry>'AR15' | (1 &lt;&lt; 31)</entry>
 	    <entry></entry>
 	    <entry>a</entry>
 	    <entry>r<subscript>4</subscript></entry>
@@ -259,6 +259,28 @@ for a pixel lie next to each other in memory.</para>
 	    <entry>b<subscript>1</subscript></entry>
 	    <entry>b<subscript>0</subscript></entry>
 	  </row>
+	  <row id="V4L2-PIX-FMT-XRGB555X">
+	    <entry><constant>V4L2_PIX_FMT_XRGB555X</constant></entry>
+	    <entry>'XR15' | (1 &lt;&lt; 31)</entry>
+	    <entry></entry>
+	    <entry>-</entry>
+	    <entry>r<subscript>4</subscript></entry>
+	    <entry>r<subscript>3</subscript></entry>
+	    <entry>r<subscript>2</subscript></entry>
+	    <entry>r<subscript>1</subscript></entry>
+	    <entry>r<subscript>0</subscript></entry>
+	    <entry>g<subscript>4</subscript></entry>
+	    <entry>g<subscript>3</subscript></entry>
+	    <entry></entry>
+	    <entry>g<subscript>2</subscript></entry>
+	    <entry>g<subscript>1</subscript></entry>
+	    <entry>g<subscript>0</subscript></entry>
+	    <entry>b<subscript>4</subscript></entry>
+	    <entry>b<subscript>3</subscript></entry>
+	    <entry>b<subscript>2</subscript></entry>
+	    <entry>b<subscript>1</subscript></entry>
+	    <entry>b<subscript>0</subscript></entry>
+	  </row>
 	  <row id="V4L2-PIX-FMT-RGB565X">
 	    <entry><constant>V4L2_PIX_FMT_RGB565X</constant></entry>
 	    <entry>'RGBR'</entry>
@@ -800,6 +822,28 @@ image</title>
 	    <entry>g<subscript>4</subscript></entry>
 	    <entry>g<subscript>3</subscript></entry>
 	  </row>
+	  <row id="V4L2-PIX-FMT-RGB555X">
+	    <entry><constant>V4L2_PIX_FMT_RGB555X</constant></entry>
+	    <entry>'RGBQ'</entry>
+	    <entry></entry>
+	    <entry>a</entry>
+	    <entry>r<subscript>4</subscript></entry>
+	    <entry>r<subscript>3</subscript></entry>
+	    <entry>r<subscript>2</subscript></entry>
+	    <entry>r<subscript>1</subscript></entry>
+	    <entry>r<subscript>0</subscript></entry>
+	    <entry>g<subscript>4</subscript></entry>
+	    <entry>g<subscript>3</subscript></entry>
+	    <entry></entry>
+	    <entry>g<subscript>2</subscript></entry>
+	    <entry>g<subscript>1</subscript></entry>
+	    <entry>g<subscript>0</subscript></entry>
+	    <entry>b<subscript>4</subscript></entry>
+	    <entry>b<subscript>3</subscript></entry>
+	    <entry>b<subscript>2</subscript></entry>
+	    <entry>b<subscript>1</subscript></entry>
+	    <entry>b<subscript>0</subscript></entry>
+	  </row>
 	  <row id="V4L2-PIX-FMT-BGR32">
 	    <entry><constant>V4L2_PIX_FMT_BGR32</constant></entry>
 	    <entry>'BGR4'</entry>
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 0b1ba5c6a8d2..1c2f84fd4d99 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -79,6 +79,7 @@
 /*  Four-character-code (FOURCC) */
 #define v4l2_fourcc(a, b, c, d)\
 	((__u32)(a) | ((__u32)(b) << 8) | ((__u32)(c) << 16) | ((__u32)(d) << 24))
+#define v4l2_fourcc_be(a, b, c, d)	(v4l2_fourcc(a, b, c, d) | (1 << 31))
 
 /*
  *	E N U M S
@@ -307,6 +308,8 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_XRGB555 v4l2_fourcc('X', 'R', '1', '5') /* 16  XRGB-1-5-5-5  */
 #define V4L2_PIX_FMT_RGB565  v4l2_fourcc('R', 'G', 'B', 'P') /* 16  RGB-5-6-5     */
 #define V4L2_PIX_FMT_RGB555X v4l2_fourcc('R', 'G', 'B', 'Q') /* 16  RGB-5-5-5 BE  */
+#define V4L2_PIX_FMT_ARGB555X v4l2_fourcc_be('A', 'R', '1', '5') /* 16  ARGB-5-5-5 BE */
+#define V4L2_PIX_FMT_XRGB555X v4l2_fourcc_be('X', 'R', '1', '5') /* 16  XRGB-5-5-5 BE */
 #define V4L2_PIX_FMT_RGB565X v4l2_fourcc('R', 'G', 'B', 'R') /* 16  RGB-5-6-5 BE  */
 #define V4L2_PIX_FMT_BGR666  v4l2_fourcc('B', 'G', 'R', 'H') /* 18  BGR-6-6-6	  */
 #define V4L2_PIX_FMT_BGR24   v4l2_fourcc('B', 'G', 'R', '3') /* 24  BGR-8-8-8     */
-- 
cgit v1.2.3


From 44e8e69d46db9928cd3b81cbea4ca24257412286 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 4 Aug 2014 07:12:32 -0300
Subject: [media] videobuf2-core.h: fix comment

The comment for start_streaming that tells the developer with which vb2 state
buffers should be returned to vb2 gave the wrong state. Very confusing.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/videobuf2-core.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index fc910a622451..80fa7253e483 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -295,7 +295,7 @@ struct vb2_buffer {
  *			can return an error if hardware fails, in that case all
  *			buffers that have been already given by the @buf_queue
  *			callback are to be returned by the driver by calling
- *			@vb2_buffer_done(VB2_BUF_STATE_DEQUEUED).
+ *			@vb2_buffer_done(VB2_BUF_STATE_QUEUED).
  *			If you need a minimum number of buffers before you can
  *			start streaming, then set @min_buffers_needed in the
  *			vb2_queue structure. If that is non-zero then
-- 
cgit v1.2.3


From 58d75f4b1ce26324b4d809b18f94819843a98731 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Sat, 20 Sep 2014 16:16:35 -0300
Subject: [media] vb2: fix VBI/poll regression

The recent conversion of saa7134 to vb2 unconvered a poll() bug that
broke the teletext applications alevt and mtt. These applications
expect that calling poll() without having called VIDIOC_STREAMON will
cause poll() to return POLLERR. That did not happen in vb2.

This patch fixes that behavior. It also fixes what should happen when
poll() is called when STREAMON is called but no buffers have been
queued. In that case poll() will also return POLLERR, but only for
capture queues since output queues will always return POLLOUT
anyway in that situation.

This brings the vb2 behavior in line with the old videobuf behavior.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/v4l2-core/videobuf2-core.c | 17 ++++++++++++++---
 include/media/videobuf2-core.h           |  4 ++++
 2 files changed, 18 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index c2126d874549..25d3ae2188cb 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -971,6 +971,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 	 * to the userspace.
 	 */
 	req->count = allocated_buffers;
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	return 0;
 }
@@ -1018,6 +1019,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create
 		memset(q->plane_sizes, 0, sizeof(q->plane_sizes));
 		memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
 		q->memory = create->memory;
+		q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 	}
 
 	num_buffers = min(create->count, VIDEO_MAX_FRAME - q->num_buffers);
@@ -1821,6 +1823,7 @@ static int vb2_internal_qbuf(struct vb2_queue *q, struct v4l2_buffer *b)
 	 */
 	list_add_tail(&vb->queued_entry, &q->queued_list);
 	q->queued_count++;
+	q->waiting_for_buffers = false;
 	vb->state = VB2_BUF_STATE_QUEUED;
 	if (V4L2_TYPE_IS_OUTPUT(q->type)) {
 		/*
@@ -2287,6 +2290,7 @@ static int vb2_internal_streamoff(struct vb2_queue *q, enum v4l2_buf_type type)
 	 * their normal dequeued state.
 	 */
 	__vb2_queue_cancel(q);
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	dprintk(3, "successful\n");
 	return 0;
@@ -2605,10 +2609,17 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait)
 	}
 
 	/*
-	 * There is nothing to wait for if no buffer has been queued and the
-	 * queue isn't streaming, or if the error flag is set.
+	 * There is nothing to wait for if the queue isn't streaming, or if the
+	 * error flag is set.
 	 */
-	if ((list_empty(&q->queued_list) && !vb2_is_streaming(q)) || q->error)
+	if (!vb2_is_streaming(q) || q->error)
+		return res | POLLERR;
+	/*
+	 * For compatibility with vb1: if QBUF hasn't been called yet, then
+	 * return POLLERR as well. This only affects capture queues, output
+	 * queues will always initialize waiting_for_buffers to false.
+	 */
+	if (q->waiting_for_buffers)
 		return res | POLLERR;
 
 	/*
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 80fa7253e483..2fefcf491aa8 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -380,6 +380,9 @@ struct v4l2_fh;
  * @start_streaming_called: start_streaming() was called successfully and we
  *		started streaming.
  * @error:	a fatal error occurred on the queue
+ * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for
+ *		buffers. Only set for capture queues if qbuf has not yet been
+ *		called since poll() needs to return POLLERR in that situation.
  * @fileio:	file io emulator internal data, used only if emulator is active
  * @threadio:	thread io internal data, used only if thread is active
  */
@@ -417,6 +420,7 @@ struct vb2_queue {
 	unsigned int			streaming:1;
 	unsigned int			start_streaming_called:1;
 	unsigned int			error:1;
+	unsigned int			waiting_for_buffers:1;
 
 	struct vb2_fileio_data		*fileio;
 	struct vb2_threadio_data	*threadio;
-- 
cgit v1.2.3


From ca2a07e45d1d3d31a0a85d2f63d81a897c610040 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Thu, 31 Jul 2014 16:32:46 +0900
Subject: extcon: sm5502: Move sm5502.h header file to extcon directory

This patch move sm5502.h header file from 'include/linux/extcon' to
'driver/extcon' because sm5502.h is used for driver/extcon/extcon-sm5502.c.
and remove duplicate license description.

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/extcon/extcon-sm5502.c |   8 +-
 drivers/extcon/extcon-sm5502.h | 282 ++++++++++++++++++++++++++++++++++++++++
 include/linux/extcon/sm5502.h  | 287 -----------------------------------------
 3 files changed, 284 insertions(+), 293 deletions(-)
 create mode 100644 drivers/extcon/extcon-sm5502.h
 delete mode 100644 include/linux/extcon/sm5502.h

(limited to 'include')

diff --git a/drivers/extcon/extcon-sm5502.c b/drivers/extcon/extcon-sm5502.c
index a1ba9242e9cb..f94d66aae9e3 100644
--- a/drivers/extcon/extcon-sm5502.c
+++ b/drivers/extcon/extcon-sm5502.c
@@ -8,11 +8,6 @@
  * under  the terms of  the GNU General  Public License as published by the
  * Free Software Foundation;  either version 2 of the  License, or (at your
  * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/err.h>
@@ -26,7 +21,8 @@
 #include <linux/regmap.h>
 #include <linux/slab.h>
 #include <linux/extcon.h>
-#include <linux/extcon/sm5502.h>
+
+#include "extcon-sm5502.h"
 
 #define	DELAY_MS_DEFAULT		17000	/* unit: millisecond */
 
diff --git a/drivers/extcon/extcon-sm5502.h b/drivers/extcon/extcon-sm5502.h
new file mode 100644
index 000000000000..974b53222f56
--- /dev/null
+++ b/drivers/extcon/extcon-sm5502.h
@@ -0,0 +1,282 @@
+/*
+ * sm5502.h
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __LINUX_EXTCON_SM5502_H
+#define __LINUX_EXTCON_SM5502_H
+
+enum sm5502_types {
+	TYPE_SM5502,
+};
+
+/* SM5502 registers */
+enum sm5502_reg {
+	SM5502_REG_DEVICE_ID = 0x01,
+	SM5502_REG_CONTROL,
+	SM5502_REG_INT1,
+	SM5502_REG_INT2,
+	SM5502_REG_INTMASK1,
+	SM5502_REG_INTMASK2,
+	SM5502_REG_ADC,
+	SM5502_REG_TIMING_SET1,
+	SM5502_REG_TIMING_SET2,
+	SM5502_REG_DEV_TYPE1,
+	SM5502_REG_DEV_TYPE2,
+	SM5502_REG_BUTTON1,
+	SM5502_REG_BUTTON2,
+	SM5502_REG_CAR_KIT_STATUS,
+	SM5502_REG_RSVD1,
+	SM5502_REG_RSVD2,
+	SM5502_REG_RSVD3,
+	SM5502_REG_RSVD4,
+	SM5502_REG_MANUAL_SW1,
+	SM5502_REG_MANUAL_SW2,
+	SM5502_REG_DEV_TYPE3,
+	SM5502_REG_RSVD5,
+	SM5502_REG_RSVD6,
+	SM5502_REG_RSVD7,
+	SM5502_REG_RSVD8,
+	SM5502_REG_RSVD9,
+	SM5502_REG_RESET,
+	SM5502_REG_RSVD10,
+	SM5502_REG_RESERVED_ID1,
+	SM5502_REG_RSVD11,
+	SM5502_REG_RSVD12,
+	SM5502_REG_RESERVED_ID2,
+	SM5502_REG_RSVD13,
+	SM5502_REG_OCP,
+	SM5502_REG_RSVD14,
+	SM5502_REG_RSVD15,
+	SM5502_REG_RSVD16,
+	SM5502_REG_RSVD17,
+	SM5502_REG_RSVD18,
+	SM5502_REG_RSVD19,
+	SM5502_REG_RSVD20,
+	SM5502_REG_RSVD21,
+	SM5502_REG_RSVD22,
+	SM5502_REG_RSVD23,
+	SM5502_REG_RSVD24,
+	SM5502_REG_RSVD25,
+	SM5502_REG_RSVD26,
+	SM5502_REG_RSVD27,
+	SM5502_REG_RSVD28,
+	SM5502_REG_RSVD29,
+	SM5502_REG_RSVD30,
+	SM5502_REG_RSVD31,
+	SM5502_REG_RSVD32,
+	SM5502_REG_RSVD33,
+	SM5502_REG_RSVD34,
+	SM5502_REG_RSVD35,
+	SM5502_REG_RSVD36,
+	SM5502_REG_RESERVED_ID3,
+
+	SM5502_REG_END,
+};
+
+/* Define SM5502 MASK/SHIFT constant */
+#define SM5502_REG_DEVICE_ID_VENDOR_SHIFT	0
+#define SM5502_REG_DEVICE_ID_VERSION_SHIFT	3
+#define SM5502_REG_DEVICE_ID_VENDOR_MASK	(0x3 << SM5502_REG_DEVICE_ID_VENDOR_SHIFT)
+#define SM5502_REG_DEVICE_ID_VERSION_MASK	(0x1f << SM5502_REG_DEVICE_ID_VERSION_SHIFT)
+
+#define SM5502_REG_CONTROL_MASK_INT_SHIFT	0
+#define SM5502_REG_CONTROL_WAIT_SHIFT		1
+#define SM5502_REG_CONTROL_MANUAL_SW_SHIFT	2
+#define SM5502_REG_CONTROL_RAW_DATA_SHIFT	3
+#define SM5502_REG_CONTROL_SW_OPEN_SHIFT	4
+#define SM5502_REG_CONTROL_MASK_INT_MASK	(0x1 << SM5502_REG_CONTROL_MASK_INT_SHIFT)
+#define SM5502_REG_CONTROL_WAIT_MASK		(0x1 << SM5502_REG_CONTROL_WAIT_SHIFT)
+#define SM5502_REG_CONTROL_MANUAL_SW_MASK	(0x1 << SM5502_REG_CONTROL_MANUAL_SW_SHIFT)
+#define SM5502_REG_CONTROL_RAW_DATA_MASK	(0x1 << SM5502_REG_CONTROL_RAW_DATA_SHIFT)
+#define SM5502_REG_CONTROL_SW_OPEN_MASK		(0x1 << SM5502_REG_CONTROL_SW_OPEN_SHIFT)
+
+#define SM5502_REG_INTM1_ATTACH_SHIFT		0
+#define SM5502_REG_INTM1_DETACH_SHIFT		1
+#define SM5502_REG_INTM1_KP_SHIFT		2
+#define SM5502_REG_INTM1_LKP_SHIFT		3
+#define SM5502_REG_INTM1_LKR_SHIFT		4
+#define SM5502_REG_INTM1_OVP_EVENT_SHIFT	5
+#define SM5502_REG_INTM1_OCP_EVENT_SHIFT	6
+#define SM5502_REG_INTM1_OVP_OCP_DIS_SHIFT	7
+#define SM5502_REG_INTM1_ATTACH_MASK		(0x1 << SM5502_REG_INTM1_ATTACH_SHIFT)
+#define SM5502_REG_INTM1_DETACH_MASK		(0x1 << SM5502_REG_INTM1_DETACH_SHIFT)
+#define SM5502_REG_INTM1_KP_MASK		(0x1 << SM5502_REG_INTM1_KP_SHIFT)
+#define SM5502_REG_INTM1_LKP_MASK		(0x1 << SM5502_REG_INTM1_LKP_SHIFT)
+#define SM5502_REG_INTM1_LKR_MASK		(0x1 << SM5502_REG_INTM1_LKR_SHIFT)
+#define SM5502_REG_INTM1_OVP_EVENT_MASK		(0x1 << SM5502_REG_INTM1_OVP_EVENT_SHIFT)
+#define SM5502_REG_INTM1_OCP_EVENT_MASK		(0x1 << SM5502_REG_INTM1_OCP_EVENT_SHIFT)
+#define SM5502_REG_INTM1_OVP_OCP_DIS_MASK	(0x1 << SM5502_REG_INTM1_OVP_OCP_DIS_SHIFT)
+
+#define SM5502_REG_INTM2_VBUS_DET_SHIFT		0
+#define SM5502_REG_INTM2_REV_ACCE_SHIFT		1
+#define SM5502_REG_INTM2_ADC_CHG_SHIFT		2
+#define SM5502_REG_INTM2_STUCK_KEY_SHIFT	3
+#define SM5502_REG_INTM2_STUCK_KEY_RCV_SHIFT	4
+#define SM5502_REG_INTM2_MHL_SHIFT		5
+#define SM5502_REG_INTM2_VBUS_DET_MASK		(0x1 << SM5502_REG_INTM2_VBUS_DET_SHIFT)
+#define SM5502_REG_INTM2_REV_ACCE_MASK		(0x1 << SM5502_REG_INTM2_REV_ACCE_SHIFT)
+#define SM5502_REG_INTM2_ADC_CHG_MASK		(0x1 << SM5502_REG_INTM2_ADC_CHG_SHIFT)
+#define SM5502_REG_INTM2_STUCK_KEY_MASK		(0x1 << SM5502_REG_INTM2_STUCK_KEY_SHIFT)
+#define SM5502_REG_INTM2_STUCK_KEY_RCV_MASK	(0x1 << SM5502_REG_INTM2_STUCK_KEY_RCV_SHIFT)
+#define SM5502_REG_INTM2_MHL_MASK		(0x1 << SM5502_REG_INTM2_MHL_SHIFT)
+
+#define SM5502_REG_ADC_SHIFT			0
+#define SM5502_REG_ADC_MASK			(0x1f << SM5502_REG_ADC_SHIFT)
+
+#define SM5502_REG_TIMING_SET1_KEY_PRESS_SHIFT	4
+#define SM5502_REG_TIMING_SET1_KEY_PRESS_MASK	(0xf << SM5502_REG_TIMING_SET1_KEY_PRESS_SHIFT)
+#define TIMING_KEY_PRESS_100MS			0x0
+#define TIMING_KEY_PRESS_200MS			0x1
+#define TIMING_KEY_PRESS_300MS			0x2
+#define TIMING_KEY_PRESS_400MS			0x3
+#define TIMING_KEY_PRESS_500MS			0x4
+#define TIMING_KEY_PRESS_600MS			0x5
+#define TIMING_KEY_PRESS_700MS			0x6
+#define TIMING_KEY_PRESS_800MS			0x7
+#define TIMING_KEY_PRESS_900MS			0x8
+#define TIMING_KEY_PRESS_1000MS			0x9
+#define SM5502_REG_TIMING_SET1_ADC_DET_SHIFT	0
+#define SM5502_REG_TIMING_SET1_ADC_DET_MASK	(0xf << SM5502_REG_TIMING_SET1_ADC_DET_SHIFT)
+#define TIMING_ADC_DET_50MS			0x0
+#define TIMING_ADC_DET_100MS			0x1
+#define TIMING_ADC_DET_150MS			0x2
+#define TIMING_ADC_DET_200MS			0x3
+#define TIMING_ADC_DET_300MS			0x4
+#define TIMING_ADC_DET_400MS			0x5
+#define TIMING_ADC_DET_500MS			0x6
+#define TIMING_ADC_DET_600MS			0x7
+#define TIMING_ADC_DET_700MS			0x8
+#define TIMING_ADC_DET_800MS			0x9
+#define TIMING_ADC_DET_900MS			0xA
+#define TIMING_ADC_DET_1000MS			0xB
+
+#define SM5502_REG_TIMING_SET2_SW_WAIT_SHIFT	4
+#define SM5502_REG_TIMING_SET2_SW_WAIT_MASK	(0xf << SM5502_REG_TIMING_SET2_SW_WAIT_SHIFT)
+#define TIMING_SW_WAIT_10MS			0x0
+#define TIMING_SW_WAIT_30MS			0x1
+#define TIMING_SW_WAIT_50MS			0x2
+#define TIMING_SW_WAIT_70MS			0x3
+#define TIMING_SW_WAIT_90MS			0x4
+#define TIMING_SW_WAIT_110MS			0x5
+#define TIMING_SW_WAIT_130MS			0x6
+#define TIMING_SW_WAIT_150MS			0x7
+#define TIMING_SW_WAIT_170MS			0x8
+#define TIMING_SW_WAIT_190MS			0x9
+#define TIMING_SW_WAIT_210MS			0xA
+#define SM5502_REG_TIMING_SET2_LONG_KEY_SHIFT	0
+#define SM5502_REG_TIMING_SET2_LONG_KEY_MASK	(0xf << SM5502_REG_TIMING_SET2_LONG_KEY_SHIFT)
+#define TIMING_LONG_KEY_300MS			0x0
+#define TIMING_LONG_KEY_400MS			0x1
+#define TIMING_LONG_KEY_500MS			0x2
+#define TIMING_LONG_KEY_600MS			0x3
+#define TIMING_LONG_KEY_700MS			0x4
+#define TIMING_LONG_KEY_800MS			0x5
+#define TIMING_LONG_KEY_900MS			0x6
+#define TIMING_LONG_KEY_1000MS			0x7
+#define TIMING_LONG_KEY_1100MS			0x8
+#define TIMING_LONG_KEY_1200MS			0x9
+#define TIMING_LONG_KEY_1300MS			0xA
+#define TIMING_LONG_KEY_1400MS			0xB
+#define TIMING_LONG_KEY_1500MS			0xC
+
+#define SM5502_REG_DEV_TYPE1_AUDIO_TYPE1_SHIFT		0
+#define SM5502_REG_DEV_TYPE1_AUDIO_TYPE2_SHIFT		1
+#define SM5502_REG_DEV_TYPE1_USB_SDP_SHIFT		2
+#define SM5502_REG_DEV_TYPE1_UART_SHIFT			3
+#define SM5502_REG_DEV_TYPE1_CAR_KIT_CHARGER_SHIFT	4
+#define SM5502_REG_DEV_TYPE1_USB_CHG_SHIFT		5
+#define SM5502_REG_DEV_TYPE1_DEDICATED_CHG_SHIFT	6
+#define SM5502_REG_DEV_TYPE1_USB_OTG_SHIFT		7
+#define SM5502_REG_DEV_TYPE1_AUDIO_TYPE1_MASK		(0x1 << SM5502_REG_DEV_TYPE1_AUDIO_TYPE1_SHIFT)
+#define SM5502_REG_DEV_TYPE1_AUDIO_TYPE1__MASK		(0x1 << SM5502_REG_DEV_TYPE1_AUDIO_TYPE2_SHIFT)
+#define SM5502_REG_DEV_TYPE1_USB_SDP_MASK		(0x1 << SM5502_REG_DEV_TYPE1_USB_SDP_SHIFT)
+#define SM5502_REG_DEV_TYPE1_UART_MASK			(0x1 << SM5502_REG_DEV_TYPE1_UART_SHIFT)
+#define SM5502_REG_DEV_TYPE1_CAR_KIT_CHARGER_MASK	(0x1 << SM5502_REG_DEV_TYPE1_CAR_KIT_CHARGER_SHIFT)
+#define SM5502_REG_DEV_TYPE1_USB_CHG_MASK		(0x1 << SM5502_REG_DEV_TYPE1_USB_CHG_SHIFT)
+#define SM5502_REG_DEV_TYPE1_DEDICATED_CHG_MASK		(0x1 << SM5502_REG_DEV_TYPE1_DEDICATED_CHG_SHIFT)
+#define SM5502_REG_DEV_TYPE1_USB_OTG_MASK		(0x1 << SM5502_REG_DEV_TYPE1_USB_OTG_SHIFT)
+
+#define SM5502_REG_DEV_TYPE2_JIG_USB_ON_SHIFT		0
+#define SM5502_REG_DEV_TYPE2_JIG_USB_OFF_SHIFT		1
+#define SM5502_REG_DEV_TYPE2_JIG_UART_ON_SHIFT		2
+#define SM5502_REG_DEV_TYPE2_JIG_UART_OFF_SHIFT		3
+#define SM5502_REG_DEV_TYPE2_PPD_SHIFT			4
+#define SM5502_REG_DEV_TYPE2_TTY_SHIFT			5
+#define SM5502_REG_DEV_TYPE2_AV_CABLE_SHIFT		6
+#define SM5502_REG_DEV_TYPE2_JIG_USB_ON_MASK		(0x1 << SM5502_REG_DEV_TYPE2_JIG_USB_ON_SHIFT)
+#define SM5502_REG_DEV_TYPE2_JIG_USB_OFF_MASK		(0x1 << SM5502_REG_DEV_TYPE2_JIG_USB_OFF_SHIFT)
+#define SM5502_REG_DEV_TYPE2_JIG_UART_ON_MASK		(0x1 << SM5502_REG_DEV_TYPE2_JIG_UART_ON_SHIFT)
+#define SM5502_REG_DEV_TYPE2_JIG_UART_OFF_MASK		(0x1 << SM5502_REG_DEV_TYPE2_JIG_UART_OFF_SHIFT)
+#define SM5502_REG_DEV_TYPE2_PPD_MASK			(0x1 << SM5502_REG_DEV_TYPE2_PPD_SHIFT)
+#define SM5502_REG_DEV_TYPE2_TTY_MASK			(0x1 << SM5502_REG_DEV_TYPE2_TTY_SHIFT)
+#define SM5502_REG_DEV_TYPE2_AV_CABLE_MASK		(0x1 << SM5502_REG_DEV_TYPE2_AV_CABLE_SHIFT)
+
+#define SM5502_REG_MANUAL_SW1_VBUSIN_SHIFT	0
+#define SM5502_REG_MANUAL_SW1_DP_SHIFT		2
+#define SM5502_REG_MANUAL_SW1_DM_SHIFT		5
+#define SM5502_REG_MANUAL_SW1_VBUSIN_MASK	(0x3 << SM5502_REG_MANUAL_SW1_VBUSIN_SHIFT)
+#define SM5502_REG_MANUAL_SW1_DP_MASK		(0x7 << SM5502_REG_MANUAL_SW1_DP_SHIFT)
+#define SM5502_REG_MANUAL_SW1_DM_MASK		(0x7 << SM5502_REG_MANUAL_SW1_DM_SHIFT)
+#define VBUSIN_SWITCH_OPEN			0x0
+#define VBUSIN_SWITCH_VBUSOUT			0x1
+#define VBUSIN_SWITCH_MIC			0x2
+#define VBUSIN_SWITCH_VBUSOUT_WITH_USB		0x3
+#define DM_DP_CON_SWITCH_OPEN			0x0
+#define DM_DP_CON_SWITCH_USB			0x1
+#define DM_DP_CON_SWITCH_AUDIO			0x2
+#define DM_DP_CON_SWITCH_UART			0x3
+#define DM_DP_SWITCH_OPEN			((DM_DP_CON_SWITCH_OPEN <<SM5502_REG_MANUAL_SW1_DP_SHIFT) \
+						| (DM_DP_CON_SWITCH_OPEN <<SM5502_REG_MANUAL_SW1_DM_SHIFT))
+#define DM_DP_SWITCH_USB			((DM_DP_CON_SWITCH_USB <<SM5502_REG_MANUAL_SW1_DP_SHIFT) \
+						| (DM_DP_CON_SWITCH_USB <<SM5502_REG_MANUAL_SW1_DM_SHIFT))
+#define DM_DP_SWITCH_AUDIO			((DM_DP_CON_SWITCH_AUDIO <<SM5502_REG_MANUAL_SW1_DP_SHIFT) \
+						| (DM_DP_CON_SWITCH_AUDIO <<SM5502_REG_MANUAL_SW1_DM_SHIFT))
+#define DM_DP_SWITCH_UART			((DM_DP_CON_SWITCH_UART <<SM5502_REG_MANUAL_SW1_DP_SHIFT) \
+						| (DM_DP_CON_SWITCH_UART <<SM5502_REG_MANUAL_SW1_DM_SHIFT))
+
+/* SM5502 Interrupts */
+enum sm5502_irq {
+	/* INT1 */
+	SM5502_IRQ_INT1_ATTACH,
+	SM5502_IRQ_INT1_DETACH,
+	SM5502_IRQ_INT1_KP,
+	SM5502_IRQ_INT1_LKP,
+	SM5502_IRQ_INT1_LKR,
+	SM5502_IRQ_INT1_OVP_EVENT,
+	SM5502_IRQ_INT1_OCP_EVENT,
+	SM5502_IRQ_INT1_OVP_OCP_DIS,
+
+	/* INT2 */
+	SM5502_IRQ_INT2_VBUS_DET,
+	SM5502_IRQ_INT2_REV_ACCE,
+	SM5502_IRQ_INT2_ADC_CHG,
+	SM5502_IRQ_INT2_STUCK_KEY,
+	SM5502_IRQ_INT2_STUCK_KEY_RCV,
+	SM5502_IRQ_INT2_MHL,
+
+	SM5502_IRQ_NUM,
+};
+
+#define SM5502_IRQ_INT1_ATTACH_MASK		BIT(0)
+#define SM5502_IRQ_INT1_DETACH_MASK		BIT(1)
+#define SM5502_IRQ_INT1_KP_MASK			BIT(2)
+#define SM5502_IRQ_INT1_LKP_MASK		BIT(3)
+#define SM5502_IRQ_INT1_LKR_MASK		BIT(4)
+#define SM5502_IRQ_INT1_OVP_EVENT_MASK		BIT(5)
+#define SM5502_IRQ_INT1_OCP_EVENT_MASK		BIT(6)
+#define SM5502_IRQ_INT1_OVP_OCP_DIS_MASK	BIT(7)
+#define SM5502_IRQ_INT2_VBUS_DET_MASK		BIT(0)
+#define SM5502_IRQ_INT2_REV_ACCE_MASK		BIT(1)
+#define SM5502_IRQ_INT2_ADC_CHG_MASK		BIT(2)
+#define SM5502_IRQ_INT2_STUCK_KEY_MASK		BIT(3)
+#define SM5502_IRQ_INT2_STUCK_KEY_RCV_MASK	BIT(4)
+#define SM5502_IRQ_INT2_MHL_MASK		BIT(5)
+
+#endif /*  __LINUX_EXTCON_SM5502_H */
diff --git a/include/linux/extcon/sm5502.h b/include/linux/extcon/sm5502.h
deleted file mode 100644
index 030526bf8d79..000000000000
--- a/include/linux/extcon/sm5502.h
+++ /dev/null
@@ -1,287 +0,0 @@
-/*
- * sm5502.h
- *
- * Copyright (c) 2014 Samsung Electronics Co., Ltd
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef __LINUX_EXTCON_SM5502_H
-#define __LINUX_EXTCON_SM5502_H
-
-enum sm5502_types {
-	TYPE_SM5502,
-};
-
-/* SM5502 registers */
-enum sm5502_reg {
-	SM5502_REG_DEVICE_ID = 0x01,
-	SM5502_REG_CONTROL,
-	SM5502_REG_INT1,
-	SM5502_REG_INT2,
-	SM5502_REG_INTMASK1,
-	SM5502_REG_INTMASK2,
-	SM5502_REG_ADC,
-	SM5502_REG_TIMING_SET1,
-	SM5502_REG_TIMING_SET2,
-	SM5502_REG_DEV_TYPE1,
-	SM5502_REG_DEV_TYPE2,
-	SM5502_REG_BUTTON1,
-	SM5502_REG_BUTTON2,
-	SM5502_REG_CAR_KIT_STATUS,
-	SM5502_REG_RSVD1,
-	SM5502_REG_RSVD2,
-	SM5502_REG_RSVD3,
-	SM5502_REG_RSVD4,
-	SM5502_REG_MANUAL_SW1,
-	SM5502_REG_MANUAL_SW2,
-	SM5502_REG_DEV_TYPE3,
-	SM5502_REG_RSVD5,
-	SM5502_REG_RSVD6,
-	SM5502_REG_RSVD7,
-	SM5502_REG_RSVD8,
-	SM5502_REG_RSVD9,
-	SM5502_REG_RESET,
-	SM5502_REG_RSVD10,
-	SM5502_REG_RESERVED_ID1,
-	SM5502_REG_RSVD11,
-	SM5502_REG_RSVD12,
-	SM5502_REG_RESERVED_ID2,
-	SM5502_REG_RSVD13,
-	SM5502_REG_OCP,
-	SM5502_REG_RSVD14,
-	SM5502_REG_RSVD15,
-	SM5502_REG_RSVD16,
-	SM5502_REG_RSVD17,
-	SM5502_REG_RSVD18,
-	SM5502_REG_RSVD19,
-	SM5502_REG_RSVD20,
-	SM5502_REG_RSVD21,
-	SM5502_REG_RSVD22,
-	SM5502_REG_RSVD23,
-	SM5502_REG_RSVD24,
-	SM5502_REG_RSVD25,
-	SM5502_REG_RSVD26,
-	SM5502_REG_RSVD27,
-	SM5502_REG_RSVD28,
-	SM5502_REG_RSVD29,
-	SM5502_REG_RSVD30,
-	SM5502_REG_RSVD31,
-	SM5502_REG_RSVD32,
-	SM5502_REG_RSVD33,
-	SM5502_REG_RSVD34,
-	SM5502_REG_RSVD35,
-	SM5502_REG_RSVD36,
-	SM5502_REG_RESERVED_ID3,
-
-	SM5502_REG_END,
-};
-
-/* Define SM5502 MASK/SHIFT constant */
-#define SM5502_REG_DEVICE_ID_VENDOR_SHIFT	0
-#define SM5502_REG_DEVICE_ID_VERSION_SHIFT	3
-#define SM5502_REG_DEVICE_ID_VENDOR_MASK	(0x3 << SM5502_REG_DEVICE_ID_VENDOR_SHIFT)
-#define SM5502_REG_DEVICE_ID_VERSION_MASK	(0x1f << SM5502_REG_DEVICE_ID_VERSION_SHIFT)
-
-#define SM5502_REG_CONTROL_MASK_INT_SHIFT	0
-#define SM5502_REG_CONTROL_WAIT_SHIFT		1
-#define SM5502_REG_CONTROL_MANUAL_SW_SHIFT	2
-#define SM5502_REG_CONTROL_RAW_DATA_SHIFT	3
-#define SM5502_REG_CONTROL_SW_OPEN_SHIFT	4
-#define SM5502_REG_CONTROL_MASK_INT_MASK	(0x1 << SM5502_REG_CONTROL_MASK_INT_SHIFT)
-#define SM5502_REG_CONTROL_WAIT_MASK		(0x1 << SM5502_REG_CONTROL_WAIT_SHIFT)
-#define SM5502_REG_CONTROL_MANUAL_SW_MASK	(0x1 << SM5502_REG_CONTROL_MANUAL_SW_SHIFT)
-#define SM5502_REG_CONTROL_RAW_DATA_MASK	(0x1 << SM5502_REG_CONTROL_RAW_DATA_SHIFT)
-#define SM5502_REG_CONTROL_SW_OPEN_MASK		(0x1 << SM5502_REG_CONTROL_SW_OPEN_SHIFT)
-
-#define SM5502_REG_INTM1_ATTACH_SHIFT		0
-#define SM5502_REG_INTM1_DETACH_SHIFT		1
-#define SM5502_REG_INTM1_KP_SHIFT		2
-#define SM5502_REG_INTM1_LKP_SHIFT		3
-#define SM5502_REG_INTM1_LKR_SHIFT		4
-#define SM5502_REG_INTM1_OVP_EVENT_SHIFT	5
-#define SM5502_REG_INTM1_OCP_EVENT_SHIFT	6
-#define SM5502_REG_INTM1_OVP_OCP_DIS_SHIFT	7
-#define SM5502_REG_INTM1_ATTACH_MASK		(0x1 << SM5502_REG_INTM1_ATTACH_SHIFT)
-#define SM5502_REG_INTM1_DETACH_MASK		(0x1 << SM5502_REG_INTM1_DETACH_SHIFT)
-#define SM5502_REG_INTM1_KP_MASK		(0x1 << SM5502_REG_INTM1_KP_SHIFT)
-#define SM5502_REG_INTM1_LKP_MASK		(0x1 << SM5502_REG_INTM1_LKP_SHIFT)
-#define SM5502_REG_INTM1_LKR_MASK		(0x1 << SM5502_REG_INTM1_LKR_SHIFT)
-#define SM5502_REG_INTM1_OVP_EVENT_MASK		(0x1 << SM5502_REG_INTM1_OVP_EVENT_SHIFT)
-#define SM5502_REG_INTM1_OCP_EVENT_MASK		(0x1 << SM5502_REG_INTM1_OCP_EVENT_SHIFT)
-#define SM5502_REG_INTM1_OVP_OCP_DIS_MASK	(0x1 << SM5502_REG_INTM1_OVP_OCP_DIS_SHIFT)
-
-#define SM5502_REG_INTM2_VBUS_DET_SHIFT		0
-#define SM5502_REG_INTM2_REV_ACCE_SHIFT		1
-#define SM5502_REG_INTM2_ADC_CHG_SHIFT		2
-#define SM5502_REG_INTM2_STUCK_KEY_SHIFT	3
-#define SM5502_REG_INTM2_STUCK_KEY_RCV_SHIFT	4
-#define SM5502_REG_INTM2_MHL_SHIFT		5
-#define SM5502_REG_INTM2_VBUS_DET_MASK		(0x1 << SM5502_REG_INTM2_VBUS_DET_SHIFT)
-#define SM5502_REG_INTM2_REV_ACCE_MASK		(0x1 << SM5502_REG_INTM2_REV_ACCE_SHIFT)
-#define SM5502_REG_INTM2_ADC_CHG_MASK		(0x1 << SM5502_REG_INTM2_ADC_CHG_SHIFT)
-#define SM5502_REG_INTM2_STUCK_KEY_MASK		(0x1 << SM5502_REG_INTM2_STUCK_KEY_SHIFT)
-#define SM5502_REG_INTM2_STUCK_KEY_RCV_MASK	(0x1 << SM5502_REG_INTM2_STUCK_KEY_RCV_SHIFT)
-#define SM5502_REG_INTM2_MHL_MASK		(0x1 << SM5502_REG_INTM2_MHL_SHIFT)
-
-#define SM5502_REG_ADC_SHIFT			0
-#define SM5502_REG_ADC_MASK			(0x1f << SM5502_REG_ADC_SHIFT)
-
-#define SM5502_REG_TIMING_SET1_KEY_PRESS_SHIFT	4
-#define SM5502_REG_TIMING_SET1_KEY_PRESS_MASK	(0xf << SM5502_REG_TIMING_SET1_KEY_PRESS_SHIFT)
-#define TIMING_KEY_PRESS_100MS			0x0
-#define TIMING_KEY_PRESS_200MS			0x1
-#define TIMING_KEY_PRESS_300MS			0x2
-#define TIMING_KEY_PRESS_400MS			0x3
-#define TIMING_KEY_PRESS_500MS			0x4
-#define TIMING_KEY_PRESS_600MS			0x5
-#define TIMING_KEY_PRESS_700MS			0x6
-#define TIMING_KEY_PRESS_800MS			0x7
-#define TIMING_KEY_PRESS_900MS			0x8
-#define TIMING_KEY_PRESS_1000MS			0x9
-#define SM5502_REG_TIMING_SET1_ADC_DET_SHIFT	0
-#define SM5502_REG_TIMING_SET1_ADC_DET_MASK	(0xf << SM5502_REG_TIMING_SET1_ADC_DET_SHIFT)
-#define TIMING_ADC_DET_50MS			0x0
-#define TIMING_ADC_DET_100MS			0x1
-#define TIMING_ADC_DET_150MS			0x2
-#define TIMING_ADC_DET_200MS			0x3
-#define TIMING_ADC_DET_300MS			0x4
-#define TIMING_ADC_DET_400MS			0x5
-#define TIMING_ADC_DET_500MS			0x6
-#define TIMING_ADC_DET_600MS			0x7
-#define TIMING_ADC_DET_700MS			0x8
-#define TIMING_ADC_DET_800MS			0x9
-#define TIMING_ADC_DET_900MS			0xA
-#define TIMING_ADC_DET_1000MS			0xB
-
-#define SM5502_REG_TIMING_SET2_SW_WAIT_SHIFT	4
-#define SM5502_REG_TIMING_SET2_SW_WAIT_MASK	(0xf << SM5502_REG_TIMING_SET2_SW_WAIT_SHIFT)
-#define TIMING_SW_WAIT_10MS			0x0
-#define TIMING_SW_WAIT_30MS			0x1
-#define TIMING_SW_WAIT_50MS			0x2
-#define TIMING_SW_WAIT_70MS			0x3
-#define TIMING_SW_WAIT_90MS			0x4
-#define TIMING_SW_WAIT_110MS			0x5
-#define TIMING_SW_WAIT_130MS			0x6
-#define TIMING_SW_WAIT_150MS			0x7
-#define TIMING_SW_WAIT_170MS			0x8
-#define TIMING_SW_WAIT_190MS			0x9
-#define TIMING_SW_WAIT_210MS			0xA
-#define SM5502_REG_TIMING_SET2_LONG_KEY_SHIFT	0
-#define SM5502_REG_TIMING_SET2_LONG_KEY_MASK	(0xf << SM5502_REG_TIMING_SET2_LONG_KEY_SHIFT)
-#define TIMING_LONG_KEY_300MS			0x0
-#define TIMING_LONG_KEY_400MS			0x1
-#define TIMING_LONG_KEY_500MS			0x2
-#define TIMING_LONG_KEY_600MS			0x3
-#define TIMING_LONG_KEY_700MS			0x4
-#define TIMING_LONG_KEY_800MS			0x5
-#define TIMING_LONG_KEY_900MS			0x6
-#define TIMING_LONG_KEY_1000MS			0x7
-#define TIMING_LONG_KEY_1100MS			0x8
-#define TIMING_LONG_KEY_1200MS			0x9
-#define TIMING_LONG_KEY_1300MS			0xA
-#define TIMING_LONG_KEY_1400MS			0xB
-#define TIMING_LONG_KEY_1500MS			0xC
-
-#define SM5502_REG_DEV_TYPE1_AUDIO_TYPE1_SHIFT		0
-#define SM5502_REG_DEV_TYPE1_AUDIO_TYPE2_SHIFT		1
-#define SM5502_REG_DEV_TYPE1_USB_SDP_SHIFT		2
-#define SM5502_REG_DEV_TYPE1_UART_SHIFT			3
-#define SM5502_REG_DEV_TYPE1_CAR_KIT_CHARGER_SHIFT	4
-#define SM5502_REG_DEV_TYPE1_USB_CHG_SHIFT		5
-#define SM5502_REG_DEV_TYPE1_DEDICATED_CHG_SHIFT	6
-#define SM5502_REG_DEV_TYPE1_USB_OTG_SHIFT		7
-#define SM5502_REG_DEV_TYPE1_AUDIO_TYPE1_MASK		(0x1 << SM5502_REG_DEV_TYPE1_AUDIO_TYPE1_SHIFT)
-#define SM5502_REG_DEV_TYPE1_AUDIO_TYPE1__MASK		(0x1 << SM5502_REG_DEV_TYPE1_AUDIO_TYPE2_SHIFT)
-#define SM5502_REG_DEV_TYPE1_USB_SDP_MASK		(0x1 << SM5502_REG_DEV_TYPE1_USB_SDP_SHIFT)
-#define SM5502_REG_DEV_TYPE1_UART_MASK			(0x1 << SM5502_REG_DEV_TYPE1_UART_SHIFT)
-#define SM5502_REG_DEV_TYPE1_CAR_KIT_CHARGER_MASK	(0x1 << SM5502_REG_DEV_TYPE1_CAR_KIT_CHARGER_SHIFT)
-#define SM5502_REG_DEV_TYPE1_USB_CHG_MASK		(0x1 << SM5502_REG_DEV_TYPE1_USB_CHG_SHIFT)
-#define SM5502_REG_DEV_TYPE1_DEDICATED_CHG_MASK		(0x1 << SM5502_REG_DEV_TYPE1_DEDICATED_CHG_SHIFT)
-#define SM5502_REG_DEV_TYPE1_USB_OTG_MASK		(0x1 << SM5502_REG_DEV_TYPE1_USB_OTG_SHIFT)
-
-#define SM5502_REG_DEV_TYPE2_JIG_USB_ON_SHIFT		0
-#define SM5502_REG_DEV_TYPE2_JIG_USB_OFF_SHIFT		1
-#define SM5502_REG_DEV_TYPE2_JIG_UART_ON_SHIFT		2
-#define SM5502_REG_DEV_TYPE2_JIG_UART_OFF_SHIFT		3
-#define SM5502_REG_DEV_TYPE2_PPD_SHIFT			4
-#define SM5502_REG_DEV_TYPE2_TTY_SHIFT			5
-#define SM5502_REG_DEV_TYPE2_AV_CABLE_SHIFT		6
-#define SM5502_REG_DEV_TYPE2_JIG_USB_ON_MASK		(0x1 << SM5502_REG_DEV_TYPE2_JIG_USB_ON_SHIFT)
-#define SM5502_REG_DEV_TYPE2_JIG_USB_OFF_MASK		(0x1 << SM5502_REG_DEV_TYPE2_JIG_USB_OFF_SHIFT)
-#define SM5502_REG_DEV_TYPE2_JIG_UART_ON_MASK		(0x1 << SM5502_REG_DEV_TYPE2_JIG_UART_ON_SHIFT)
-#define SM5502_REG_DEV_TYPE2_JIG_UART_OFF_MASK		(0x1 << SM5502_REG_DEV_TYPE2_JIG_UART_OFF_SHIFT)
-#define SM5502_REG_DEV_TYPE2_PPD_MASK			(0x1 << SM5502_REG_DEV_TYPE2_PPD_SHIFT)
-#define SM5502_REG_DEV_TYPE2_TTY_MASK			(0x1 << SM5502_REG_DEV_TYPE2_TTY_SHIFT)
-#define SM5502_REG_DEV_TYPE2_AV_CABLE_MASK		(0x1 << SM5502_REG_DEV_TYPE2_AV_CABLE_SHIFT)
-
-#define SM5502_REG_MANUAL_SW1_VBUSIN_SHIFT	0
-#define SM5502_REG_MANUAL_SW1_DP_SHIFT		2
-#define SM5502_REG_MANUAL_SW1_DM_SHIFT		5
-#define SM5502_REG_MANUAL_SW1_VBUSIN_MASK	(0x3 << SM5502_REG_MANUAL_SW1_VBUSIN_SHIFT)
-#define SM5502_REG_MANUAL_SW1_DP_MASK		(0x7 << SM5502_REG_MANUAL_SW1_DP_SHIFT)
-#define SM5502_REG_MANUAL_SW1_DM_MASK		(0x7 << SM5502_REG_MANUAL_SW1_DM_SHIFT)
-#define VBUSIN_SWITCH_OPEN			0x0
-#define VBUSIN_SWITCH_VBUSOUT			0x1
-#define VBUSIN_SWITCH_MIC			0x2
-#define VBUSIN_SWITCH_VBUSOUT_WITH_USB		0x3
-#define DM_DP_CON_SWITCH_OPEN			0x0
-#define DM_DP_CON_SWITCH_USB			0x1
-#define DM_DP_CON_SWITCH_AUDIO			0x2
-#define DM_DP_CON_SWITCH_UART			0x3
-#define DM_DP_SWITCH_OPEN			((DM_DP_CON_SWITCH_OPEN <<SM5502_REG_MANUAL_SW1_DP_SHIFT) \
-						| (DM_DP_CON_SWITCH_OPEN <<SM5502_REG_MANUAL_SW1_DM_SHIFT))
-#define DM_DP_SWITCH_USB			((DM_DP_CON_SWITCH_USB <<SM5502_REG_MANUAL_SW1_DP_SHIFT) \
-						| (DM_DP_CON_SWITCH_USB <<SM5502_REG_MANUAL_SW1_DM_SHIFT))
-#define DM_DP_SWITCH_AUDIO			((DM_DP_CON_SWITCH_AUDIO <<SM5502_REG_MANUAL_SW1_DP_SHIFT) \
-						| (DM_DP_CON_SWITCH_AUDIO <<SM5502_REG_MANUAL_SW1_DM_SHIFT))
-#define DM_DP_SWITCH_UART			((DM_DP_CON_SWITCH_UART <<SM5502_REG_MANUAL_SW1_DP_SHIFT) \
-						| (DM_DP_CON_SWITCH_UART <<SM5502_REG_MANUAL_SW1_DM_SHIFT))
-
-/* SM5502 Interrupts */
-enum sm5502_irq {
-	/* INT1 */
-	SM5502_IRQ_INT1_ATTACH,
-	SM5502_IRQ_INT1_DETACH,
-	SM5502_IRQ_INT1_KP,
-	SM5502_IRQ_INT1_LKP,
-	SM5502_IRQ_INT1_LKR,
-	SM5502_IRQ_INT1_OVP_EVENT,
-	SM5502_IRQ_INT1_OCP_EVENT,
-	SM5502_IRQ_INT1_OVP_OCP_DIS,
-
-	/* INT2 */
-	SM5502_IRQ_INT2_VBUS_DET,
-	SM5502_IRQ_INT2_REV_ACCE,
-	SM5502_IRQ_INT2_ADC_CHG,
-	SM5502_IRQ_INT2_STUCK_KEY,
-	SM5502_IRQ_INT2_STUCK_KEY_RCV,
-	SM5502_IRQ_INT2_MHL,
-
-	SM5502_IRQ_NUM,
-};
-
-#define SM5502_IRQ_INT1_ATTACH_MASK		BIT(0)
-#define SM5502_IRQ_INT1_DETACH_MASK		BIT(1)
-#define SM5502_IRQ_INT1_KP_MASK			BIT(2)
-#define SM5502_IRQ_INT1_LKP_MASK		BIT(3)
-#define SM5502_IRQ_INT1_LKR_MASK		BIT(4)
-#define SM5502_IRQ_INT1_OVP_EVENT_MASK		BIT(5)
-#define SM5502_IRQ_INT1_OCP_EVENT_MASK		BIT(6)
-#define SM5502_IRQ_INT1_OVP_OCP_DIS_MASK	BIT(7)
-#define SM5502_IRQ_INT2_VBUS_DET_MASK		BIT(0)
-#define SM5502_IRQ_INT2_REV_ACCE_MASK		BIT(1)
-#define SM5502_IRQ_INT2_ADC_CHG_MASK		BIT(2)
-#define SM5502_IRQ_INT2_STUCK_KEY_MASK		BIT(3)
-#define SM5502_IRQ_INT2_STUCK_KEY_RCV_MASK	BIT(4)
-#define SM5502_IRQ_INT2_MHL_MASK		BIT(5)
-
-#endif /*  __LINUX_EXTCON_SM5502_H */
-- 
cgit v1.2.3


From 62364357c184db52d556f868e493963fac2aea78 Mon Sep 17 00:00:00 2001
From: George Cherian <george.cherian@ti.com>
Date: Tue, 9 Sep 2014 09:44:34 +0530
Subject: extcon: gpio: Fix code cleanup

This patch fixes following minor cleanup:
 - Order the include files in alphabetical order.
 - Fix description of state_off in extcon_gpio.h
 - Add a descrition for check_on_resume in extcon_gpio.h

Signed-off-by: George Cherian <george.cherian@ti.com>
[Modify the name/description of patch to keep standary codiyg style by Chanwoo Choi]
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/extcon/extcon-gpio.c       | 10 +++++-----
 include/linux/extcon/extcon-gpio.h |  4 +++-
 2 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/extcon/extcon-gpio.c b/drivers/extcon/extcon-gpio.c
index 5b7ec274cb63..72f19a37fd01 100644
--- a/drivers/extcon/extcon-gpio.c
+++ b/drivers/extcon/extcon-gpio.c
@@ -20,16 +20,16 @@
  *
 */
 
-#include <linux/module.h>
-#include <linux/kernel.h>
+#include <linux/extcon.h>
+#include <linux/extcon/extcon-gpio.h>
+#include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
-#include <linux/gpio.h>
-#include <linux/extcon.h>
-#include <linux/extcon/extcon-gpio.h>
 
 struct gpio_extcon_data {
 	struct extcon_dev *edev;
diff --git a/include/linux/extcon/extcon-gpio.h b/include/linux/extcon/extcon-gpio.h
index 8900fdf511c6..0b17ad43fbfc 100644
--- a/include/linux/extcon/extcon-gpio.h
+++ b/include/linux/extcon/extcon-gpio.h
@@ -34,8 +34,10 @@
  * @irq_flags:		IRQ Flags (e.g., IRQF_TRIGGER_LOW).
  * @state_on:		print_state is overriden with state_on if attached.
  *			If NULL, default method of extcon class is used.
- * @state_off:		print_state is overriden with state_on if detached.
+ * @state_off:		print_state is overriden with state_off if detached.
  *			If NUll, default method of extcon class is used.
+ * @check_on_resume:	Boolean describing whether to check the state of gpio
+ *			while resuming from sleep.
  *
  * Note that in order for state_on or state_off to be valid, both state_on
  * and state_off should be not NULL. If at least one of them is NULL,
-- 
cgit v1.2.3


From bcc5fd49a0fda5abc22057f65b318788ccb5d2ad Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Mon, 15 Sep 2014 18:15:53 +0200
Subject: clk: at91: add a driver for the h32mx clock

Newer SoCs have two different AHB interconnect. The AHB 32 bits Matrix
interconnect (h32mx) has a clock that can be setup at the half of the h64mx
clock (which is mck). The h32mx clock can not exceed 90 MHz.

Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Acked-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
 .../devicetree/bindings/clock/at91-clock.txt       |  14 +++
 arch/arm/mach-at91/Kconfig                         |   3 +
 drivers/clk/at91/Makefile                          |   1 +
 drivers/clk/at91/clk-h32mx.c                       | 123 +++++++++++++++++++++
 drivers/clk/at91/pmc.c                             |   6 +
 drivers/clk/at91/pmc.h                             |   5 +
 include/linux/clk/at91_pmc.h                       |   1 +
 7 files changed, 153 insertions(+)
 create mode 100644 drivers/clk/at91/clk-h32mx.c

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/at91-clock.txt b/Documentation/devicetree/bindings/clock/at91-clock.txt
index b3d544ca522a..7a4d4926f44e 100644
--- a/Documentation/devicetree/bindings/clock/at91-clock.txt
+++ b/Documentation/devicetree/bindings/clock/at91-clock.txt
@@ -74,6 +74,9 @@ Required properties:
 	"atmel,at91sam9x5-clk-utmi":
 		at91 utmi clock
 
+	"atmel,sama5d4-clk-h32mx":
+		at91 h32mx clock
+
 Required properties for SCKC node:
 - reg : defines the IO memory reserved for the SCKC.
 - #size-cells : shall be 0 (reg is used to encode clk id).
@@ -447,3 +450,14 @@ For example:
 		#clock-cells = <0>;
 		clocks = <&main>;
 	};
+
+Required properties for 32 bits bus Matrix clock (h32mx clock):
+- #clock-cells : from common clock binding; shall be set to 0.
+- clocks : shall be the master clock source phandle.
+
+For example:
+	h32ck: h32mxck {
+		#clock-cells = <0>;
+		compatible = "atmel,sama5d4-clk-h32mx";
+		clocks = <&mck>;
+	};
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 6cc6f7aebdae..321210cc3be7 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -42,6 +42,9 @@ config AT91_SAM9_TIME
 config HAVE_AT91_SMD
 	bool
 
+config HAVE_AT91_H32MX
+	bool
+
 config SOC_AT91SAM9
 	bool
 	select AT91_SAM9_TIME
diff --git a/drivers/clk/at91/Makefile b/drivers/clk/at91/Makefile
index 4998aee59267..89a48a7bd5df 100644
--- a/drivers/clk/at91/Makefile
+++ b/drivers/clk/at91/Makefile
@@ -9,3 +9,4 @@ obj-y += clk-system.o clk-peripheral.o clk-programmable.o
 obj-$(CONFIG_HAVE_AT91_UTMI)		+= clk-utmi.o
 obj-$(CONFIG_HAVE_AT91_USB_CLK)		+= clk-usb.o
 obj-$(CONFIG_HAVE_AT91_SMD)		+= clk-smd.o
+obj-$(CONFIG_HAVE_AT91_H32MX)		+= clk-h32mx.o
diff --git a/drivers/clk/at91/clk-h32mx.c b/drivers/clk/at91/clk-h32mx.c
new file mode 100644
index 000000000000..152dcb3f7b5f
--- /dev/null
+++ b/drivers/clk/at91/clk-h32mx.c
@@ -0,0 +1,123 @@
+/*
+ * clk-h32mx.c
+ *
+ *  Copyright (C) 2014 Atmel
+ *
+ * Alexandre Belloni <alexandre.belloni@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/clk/at91_pmc.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+
+#include "pmc.h"
+
+#define H32MX_MAX_FREQ	90000000
+
+struct clk_sama5d4_h32mx {
+	struct clk_hw hw;
+	struct at91_pmc *pmc;
+};
+
+#define to_clk_sama5d4_h32mx(hw) container_of(hw, struct clk_sama5d4_h32mx, hw)
+
+static unsigned long clk_sama5d4_h32mx_recalc_rate(struct clk_hw *hw,
+						 unsigned long parent_rate)
+{
+	struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw);
+
+	if (pmc_read(h32mxclk->pmc, AT91_PMC_MCKR) & AT91_PMC_H32MXDIV)
+		return parent_rate / 2;
+
+	if (parent_rate > H32MX_MAX_FREQ)
+		pr_warn("H32MX clock is too fast\n");
+	return parent_rate;
+}
+
+static long clk_sama5d4_h32mx_round_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long *parent_rate)
+{
+	unsigned long div;
+
+	if (rate > *parent_rate)
+		return *parent_rate;
+	div = *parent_rate / 2;
+	if (rate < div)
+		return div;
+
+	if (rate - div < *parent_rate - rate)
+		return div;
+
+	return *parent_rate;
+}
+
+static int clk_sama5d4_h32mx_set_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate)
+{
+	struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw);
+	struct at91_pmc *pmc = h32mxclk->pmc;
+	u32 tmp;
+
+	if (parent_rate != rate && (parent_rate / 2) != rate)
+		return -EINVAL;
+
+	pmc_lock(pmc);
+	tmp = pmc_read(pmc, AT91_PMC_MCKR) & ~AT91_PMC_H32MXDIV;
+	if ((parent_rate / 2) == rate)
+		tmp |= AT91_PMC_H32MXDIV;
+	pmc_write(pmc, AT91_PMC_MCKR, tmp);
+	pmc_unlock(pmc);
+
+	return 0;
+}
+
+static const struct clk_ops h32mx_ops = {
+	.recalc_rate = clk_sama5d4_h32mx_recalc_rate,
+	.round_rate = clk_sama5d4_h32mx_round_rate,
+	.set_rate = clk_sama5d4_h32mx_set_rate,
+};
+
+void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
+				     struct at91_pmc *pmc)
+{
+	struct clk_sama5d4_h32mx *h32mxclk;
+	struct clk_init_data init;
+	const char *parent_name;
+	struct clk *clk;
+
+	h32mxclk = kzalloc(sizeof(*h32mxclk), GFP_KERNEL);
+	if (!h32mxclk)
+		return;
+
+	parent_name = of_clk_get_parent_name(np, 0);
+
+	init.name = np->name;
+	init.ops = &h32mx_ops;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+	init.flags = CLK_SET_RATE_GATE;
+
+	h32mxclk->hw.init = &init;
+	h32mxclk->pmc = pmc;
+
+	clk = clk_register(NULL, &h32mxclk->hw);
+	if (!clk)
+		return;
+
+	of_clk_add_provider(np, of_clk_src_simple_get, clk);
+}
diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c
index 524196bb35a5..386999b4f8eb 100644
--- a/drivers/clk/at91/pmc.c
+++ b/drivers/clk/at91/pmc.c
@@ -336,6 +336,12 @@ static const struct of_device_id pmc_clk_ids[] __initconst = {
 		.compatible = "atmel,at91sam9x5-clk-smd",
 		.data = of_at91sam9x5_clk_smd_setup,
 	},
+#endif
+#if defined(CONFIG_HAVE_AT91_H32MX)
+	{
+		.compatible = "atmel,sama5d4-clk-h32mx",
+		.data = of_sama5d4_clk_h32mx_setup,
+	},
 #endif
 	{ /*sentinel*/ }
 };
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 6c7625976113..52d2041fa3f6 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -120,4 +120,9 @@ extern void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
 					       struct at91_pmc *pmc);
 #endif
 
+#if defined(CONFIG_HAVE_AT91_SMD)
+extern void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
+					      struct at91_pmc *pmc);
+#endif
+
 #endif /* __PMC_H_ */
diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
index de4268d4987a..c8e3b3d1eded 100644
--- a/include/linux/clk/at91_pmc.h
+++ b/include/linux/clk/at91_pmc.h
@@ -125,6 +125,7 @@ extern void __iomem *at91_pmc_base;
 #define		AT91_PMC_PLLADIV2	(1 << 12)		/* PLLA divisor by 2 [some SAM9 only] */
 #define			AT91_PMC_PLLADIV2_OFF		(0 << 12)
 #define			AT91_PMC_PLLADIV2_ON		(1 << 12)
+#define		AT91_PMC_H32MXDIV	BIT(24)
 
 #define	AT91_PMC_USB		0x38			/* USB Clock Register [some SAM9 only] */
 #define		AT91_PMC_USBS		(0x1 <<  0)		/* USB OHCI Input clock selection */
-- 
cgit v1.2.3


From 02d31c7de1e799c1fc171d86cfac92240885ce7e Mon Sep 17 00:00:00 2001
From: Zubair Lutfullah Kakakhel <Zubair.Kakakhel@imgtec.com>
Date: Wed, 16 Jul 2014 16:51:29 +0100
Subject: asm-generic: Add dma-contiguous.h

This header is used by arm64 and x86 individually.

Adding to asm-generic to avoid further code repetition while adding cma
to mips.

Signed-off-by: Zubair Lutfullah Kakakhel <Zubair.Kakakhel@imgtec.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: catalin.marinas@arm.com
Cc: will.deacon@arm.com
Cc: tglx@linutronix.de
Cc: mingo@redhat.com
Cc: hpa@zytor.com
Cc: arnd@arndb.de
Cc: gregkh@linuxfoundation.org
Cc: m.szyprowski@samsung.com
Cc: x86@kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-arch@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/7357/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 include/asm-generic/dma-contiguous.h | 9 +++++++++
 1 file changed, 9 insertions(+)
 create mode 100644 include/asm-generic/dma-contiguous.h

(limited to 'include')

diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
new file mode 100644
index 000000000000..292c571750f0
--- /dev/null
+++ b/include/asm-generic/dma-contiguous.h
@@ -0,0 +1,9 @@
+#ifndef _ASM_GENERIC_DMA_CONTIGUOUS_H
+#define _ASM_GENERIC_DMA_CONTIGUOUS_H
+
+#include <linux/types.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
-- 
cgit v1.2.3


From e3c3f19bc6185e0a24454e7b439e11635e6db960 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Tue, 2 Sep 2014 15:21:15 +0200
Subject: clk: samsung: exynos3250: Register DMC clk provider

Add clock provider for clocks in DMC domain including EPLL and BPLL. The
DMC clocks are necessary for Exynos3 devfreq driver.

The DMC clock domain uses different address space (0x105C0000) than
standard clock domain (0x10030000 - 0x10050000). The difference is huge
enough to add new DT node for the clock provider, rather than extending
existing address space.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Tomasz Figa <tomasz.figa@gmail.com>
---
 drivers/clk/samsung/clk-exynos3250.c   | 195 +++++++++++++++++++++++++++++++++
 include/dt-bindings/clock/exynos3250.h |  27 +++++
 2 files changed, 222 insertions(+)

(limited to 'include')

diff --git a/drivers/clk/samsung/clk-exynos3250.c b/drivers/clk/samsung/clk-exynos3250.c
index 5e2d86e2cede..6e6cca392082 100644
--- a/drivers/clk/samsung/clk-exynos3250.c
+++ b/drivers/clk/samsung/clk-exynos3250.c
@@ -110,7 +110,14 @@ enum exynos3250_plls {
 	nr_plls
 };
 
+/* list of PLLs in DMC block to be registered */
+enum exynos3250_dmc_plls {
+	bpll, epll,
+	nr_dmc_plls
+};
+
 static void __iomem *reg_base;
+static void __iomem *dmc_reg_base;
 
 /*
  * Support for CMU save/restore across system suspends
@@ -725,6 +732,25 @@ static struct samsung_pll_rate_table exynos3250_pll_rates[] = {
 	{ /* sentinel */ }
 };
 
+/* EPLL */
+static struct samsung_pll_rate_table exynos3250_epll_rates[] = {
+	PLL_36XX_RATE(800000000, 200, 3, 1,     0),
+	PLL_36XX_RATE(288000000,  96, 2, 2,     0),
+	PLL_36XX_RATE(192000000, 128, 2, 3,     0),
+	PLL_36XX_RATE(144000000,  96, 2, 3,     0),
+	PLL_36XX_RATE( 96000000, 128, 2, 4,     0),
+	PLL_36XX_RATE( 84000000, 112, 2, 4,     0),
+	PLL_36XX_RATE( 80000004, 106, 2, 4, 43691),
+	PLL_36XX_RATE( 73728000,  98, 2, 4, 19923),
+	PLL_36XX_RATE( 67737598, 270, 3, 5, 62285),
+	PLL_36XX_RATE( 65535999, 174, 2, 5, 49982),
+	PLL_36XX_RATE( 50000000, 200, 3, 5,     0),
+	PLL_36XX_RATE( 49152002, 131, 2, 5,  4719),
+	PLL_36XX_RATE( 48000000, 128, 2, 5,     0),
+	PLL_36XX_RATE( 45158401, 180, 3, 5, 41524),
+	{ /* sentinel */ }
+};
+
 /* VPLL */
 static struct samsung_pll_rate_table exynos3250_vpll_rates[] = {
 	PLL_36XX_RATE(600000000, 100, 2, 1,     0),
@@ -822,3 +848,172 @@ static void __init exynos3250_cmu_init(struct device_node *np)
 	samsung_clk_of_add_provider(np, ctx);
 }
 CLK_OF_DECLARE(exynos3250_cmu, "samsung,exynos3250-cmu", exynos3250_cmu_init);
+
+/*
+ * CMU DMC
+ */
+
+#define BPLL_LOCK		0x0118
+#define BPLL_CON0		0x0218
+#define BPLL_CON1		0x021c
+#define BPLL_CON2		0x0220
+#define SRC_DMC			0x0300
+#define DIV_DMC1		0x0504
+#define GATE_BUS_DMC0		0x0700
+#define GATE_BUS_DMC1		0x0704
+#define GATE_BUS_DMC2		0x0708
+#define GATE_BUS_DMC3		0x070c
+#define GATE_SCLK_DMC		0x0800
+#define GATE_IP_DMC0		0x0900
+#define GATE_IP_DMC1		0x0904
+#define EPLL_LOCK		0x1110
+#define EPLL_CON0		0x1114
+#define EPLL_CON1		0x1118
+#define EPLL_CON2		0x111c
+#define SRC_EPLL		0x1120
+
+/*
+ * Support for CMU save/restore across system suspends
+ */
+#ifdef CONFIG_PM_SLEEP
+static struct samsung_clk_reg_dump *exynos3250_dmc_clk_regs;
+
+static unsigned long exynos3250_cmu_dmc_clk_regs[] __initdata = {
+	BPLL_LOCK,
+	BPLL_CON0,
+	BPLL_CON1,
+	BPLL_CON2,
+	SRC_DMC,
+	DIV_DMC1,
+	GATE_BUS_DMC0,
+	GATE_BUS_DMC1,
+	GATE_BUS_DMC2,
+	GATE_BUS_DMC3,
+	GATE_SCLK_DMC,
+	GATE_IP_DMC0,
+	GATE_IP_DMC1,
+	EPLL_LOCK,
+	EPLL_CON0,
+	EPLL_CON1,
+	EPLL_CON2,
+	SRC_EPLL,
+};
+
+static int exynos3250_dmc_clk_suspend(void)
+{
+	samsung_clk_save(dmc_reg_base, exynos3250_dmc_clk_regs,
+				ARRAY_SIZE(exynos3250_cmu_dmc_clk_regs));
+	return 0;
+}
+
+static void exynos3250_dmc_clk_resume(void)
+{
+	samsung_clk_restore(dmc_reg_base, exynos3250_dmc_clk_regs,
+				ARRAY_SIZE(exynos3250_cmu_dmc_clk_regs));
+}
+
+static struct syscore_ops exynos3250_dmc_clk_syscore_ops = {
+	.suspend = exynos3250_dmc_clk_suspend,
+	.resume = exynos3250_dmc_clk_resume,
+};
+
+static void exynos3250_dmc_clk_sleep_init(void)
+{
+	exynos3250_dmc_clk_regs =
+		samsung_clk_alloc_reg_dump(exynos3250_cmu_dmc_clk_regs,
+				   ARRAY_SIZE(exynos3250_cmu_dmc_clk_regs));
+	if (!exynos3250_dmc_clk_regs) {
+		pr_warn("%s: Failed to allocate sleep save data\n", __func__);
+		goto err;
+	}
+
+	register_syscore_ops(&exynos3250_dmc_clk_syscore_ops);
+	return;
+err:
+	kfree(exynos3250_dmc_clk_regs);
+}
+#else
+static inline void exynos3250_dmc_clk_sleep_init(void) { }
+#endif
+
+PNAME(mout_epll_p)	= { "fin_pll", "fout_epll", };
+PNAME(mout_bpll_p)	= { "fin_pll", "fout_bpll", };
+PNAME(mout_mpll_mif_p)	= { "fin_pll", "sclk_mpll_mif", };
+PNAME(mout_dphy_p)	= { "mout_mpll_mif", "mout_bpll", };
+
+static struct samsung_mux_clock dmc_mux_clks[] __initdata = {
+	/*
+	 * NOTE: Following table is sorted by register address in ascending
+	 * order and then bitfield shift in descending order, as it is done
+	 * in the User's Manual. When adding new entries, please make sure
+	 * that the order is preserved, to avoid merge conflicts and make
+	 * further work with defined data easier.
+	 */
+
+	/* SRC_DMC */
+	MUX(CLK_MOUT_MPLL_MIF, "mout_mpll_mif", mout_mpll_mif_p, SRC_DMC, 12, 1),
+	MUX(CLK_MOUT_BPLL, "mout_bpll", mout_bpll_p, SRC_DMC, 10, 1),
+	MUX(CLK_MOUT_DPHY, "mout_dphy", mout_dphy_p, SRC_DMC, 8, 1),
+	MUX(CLK_MOUT_DMC_BUS, "mout_dmc_bus", mout_dphy_p, SRC_DMC,  4, 1),
+
+	/* SRC_EPLL */
+	MUX(CLK_MOUT_EPLL, "mout_epll", mout_epll_p, SRC_EPLL, 4, 1),
+};
+
+static struct samsung_div_clock dmc_div_clks[] __initdata = {
+	/*
+	 * NOTE: Following table is sorted by register address in ascending
+	 * order and then bitfield shift in descending order, as it is done
+	 * in the User's Manual. When adding new entries, please make sure
+	 * that the order is preserved, to avoid merge conflicts and make
+	 * further work with defined data easier.
+	 */
+
+	/* DIV_DMC1 */
+	DIV(CLK_DIV_DMC, "div_dmc", "div_dmc_pre", DIV_DMC1, 27, 3),
+	DIV(CLK_DIV_DPHY, "div_dphy", "mout_dphy", DIV_DMC1, 23, 3),
+	DIV(CLK_DIV_DMC_PRE, "div_dmc_pre", "mout_dmc_bus", DIV_DMC1, 19, 2),
+	DIV(CLK_DIV_DMCP, "div_dmcp", "div_dmcd", DIV_DMC1, 15, 3),
+	DIV(CLK_DIV_DMCD, "div_dmcd", "div_dmc", DIV_DMC1, 11, 3),
+};
+
+static struct samsung_pll_clock exynos3250_dmc_plls[nr_dmc_plls] __initdata = {
+	[bpll] = PLL(pll_35xx, CLK_FOUT_BPLL, "fout_bpll", "fin_pll",
+			BPLL_LOCK, BPLL_CON0, NULL),
+	[epll] = PLL(pll_36xx, CLK_FOUT_EPLL, "fout_epll", "fin_pll",
+			EPLL_LOCK, EPLL_CON0, NULL),
+};
+
+static void __init exynos3250_cmu_dmc_init(struct device_node *np)
+{
+	struct samsung_clk_provider *ctx;
+
+	dmc_reg_base = of_iomap(np, 0);
+	if (!dmc_reg_base)
+		panic("%s: failed to map registers\n", __func__);
+
+	ctx = samsung_clk_init(np, dmc_reg_base, NR_CLKS_DMC);
+	if (!ctx)
+		panic("%s: unable to allocate context.\n", __func__);
+
+	exynos3250_dmc_plls[bpll].rate_table = exynos3250_pll_rates;
+	exynos3250_dmc_plls[epll].rate_table = exynos3250_epll_rates;
+
+	pr_err("CLK registering epll bpll: %d, %d, %d, %d\n",
+			exynos3250_dmc_plls[bpll].rate_table[0].rate,
+			exynos3250_dmc_plls[bpll].rate_table[0].mdiv,
+			exynos3250_dmc_plls[bpll].rate_table[0].pdiv,
+			exynos3250_dmc_plls[bpll].rate_table[0].sdiv
+	      );
+	samsung_clk_register_pll(ctx, exynos3250_dmc_plls,
+				ARRAY_SIZE(exynos3250_dmc_plls), dmc_reg_base);
+
+	samsung_clk_register_mux(ctx, dmc_mux_clks, ARRAY_SIZE(dmc_mux_clks));
+	samsung_clk_register_div(ctx, dmc_div_clks, ARRAY_SIZE(dmc_div_clks));
+
+	exynos3250_dmc_clk_sleep_init();
+
+	samsung_clk_of_add_provider(np, ctx);
+}
+CLK_OF_DECLARE(exynos3250_cmu_dmc, "samsung,exynos3250-cmu-dmc",
+		exynos3250_cmu_dmc_init);
diff --git a/include/dt-bindings/clock/exynos3250.h b/include/dt-bindings/clock/exynos3250.h
index b535e9da7de6..961b9c130ea9 100644
--- a/include/dt-bindings/clock/exynos3250.h
+++ b/include/dt-bindings/clock/exynos3250.h
@@ -255,4 +255,31 @@
  */
 #define CLK_NR_CLKS			248
 
+/*
+ * CMU DMC
+ */
+
+#define CLK_FOUT_BPLL			1
+#define CLK_FOUT_EPLL			2
+
+/* Muxes */
+#define CLK_MOUT_MPLL_MIF		8
+#define CLK_MOUT_BPLL			9
+#define CLK_MOUT_DPHY			10
+#define CLK_MOUT_DMC_BUS		11
+#define CLK_MOUT_EPLL			12
+
+/* Dividers */
+#define CLK_DIV_DMC			16
+#define CLK_DIV_DPHY			17
+#define CLK_DIV_DMC_PRE			18
+#define CLK_DIV_DMCP			19
+#define CLK_DIV_DMCD			20
+
+/*
+ * Total number of clocks of main CMU.
+ * NOTE: Must be equal to last clock ID increased by one.
+ */
+#define NR_CLKS_DMC			21
+
 #endif /* _DT_BINDINGS_CLOCK_SAMSUNG_EXYNOS3250_CLOCK_H */
-- 
cgit v1.2.3


From c14254300131f5dcb3fe18a1ff6eee163c2bc9b4 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Tue, 16 Sep 2014 13:54:31 +0200
Subject: clk: samsung: exynos4: add missing smmu_g2d clock and update comments

This patch adds missing smmu_g2d clock implementation and updates
comment about Exynos4 clocks from 278-282 range. Those clocks are
available on all Exynos4 SoC series, so the misleading comment has been
removed.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Tomasz Figa <tomasz.figa@gmail.com>
---
 drivers/clk/samsung/clk-exynos4.c   |  1 +
 include/dt-bindings/clock/exynos4.h | 10 +++++-----
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index ac163d7f5bc3..12a7cc3b5953 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -1183,6 +1183,7 @@ static struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 	GATE(CLK_SPI1_ISP, "spi1_isp", "aclk200", E4X12_GATE_ISP1, 13,
 			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(CLK_G2D, "g2d", "aclk200", GATE_IP_DMC, 23, 0, 0),
+	GATE(CLK_SMMU_G2D, "smmu_g2d", "aclk200", GATE_IP_DMC, 24, 0, 0),
 	GATE(CLK_TMU_APBIF, "tmu_apbif", "aclk100", E4X12_GATE_IP_PERIR, 17, 0,
 		0),
 };
diff --git a/include/dt-bindings/clock/exynos4.h b/include/dt-bindings/clock/exynos4.h
index 459bd2bd411f..fb9816354079 100644
--- a/include/dt-bindings/clock/exynos4.h
+++ b/include/dt-bindings/clock/exynos4.h
@@ -115,11 +115,11 @@
 #define CLK_SMMU_MFCR		275
 #define CLK_G3D			276
 #define CLK_G2D			277
-#define CLK_ROTATOR		278 /* Exynos4210 only */
-#define CLK_MDMA		279 /* Exynos4210 only */
-#define CLK_SMMU_G2D		280 /* Exynos4210 only */
-#define CLK_SMMU_ROTATOR	281 /* Exynos4210 only */
-#define CLK_SMMU_MDMA		282 /* Exynos4210 only */
+#define CLK_ROTATOR		278
+#define CLK_MDMA		279
+#define CLK_SMMU_G2D		280
+#define CLK_SMMU_ROTATOR	281
+#define CLK_SMMU_MDMA		282
 #define CLK_FIMD0		283
 #define CLK_MIE0		284
 #define CLK_MDNIE0		285 /* Exynos4412 only */
-- 
cgit v1.2.3


From 4676f0aab9dc4f9aa729d5a5b75d20f824d77742 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Tue, 1 Jul 2014 10:10:05 +0200
Subject: clk: samsung: exynos4: add support for MOUT_HDMI and MOUT_MIXER
 clocks

This patch adds support for exporting mout_hdmi and mout_mixer to device
tree. Access to those clocks is required to correctly setup HDMI module
on Exynos 4210 and 4x12 SoCs.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
CC: Mike Turquette <mturquette@linaro.org>
CC: Tomasz Figa <t.figa@samsung.com>
Signed-off-by: Tomasz Figa <tomasz.figa@gmail.com>
---
 drivers/clk/samsung/clk-exynos4.c   | 4 ++--
 include/dt-bindings/clock/exynos4.h | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 12a7cc3b5953..1b0dd73636c0 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -535,7 +535,7 @@ static struct samsung_fixed_factor_clock exynos4x12_fixed_factor_clks[] __initda
 static struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
 	MUX_FA(CLK_MOUT_APLL, "mout_apll", mout_apll_p, SRC_CPU, 0, 1,
 			CLK_SET_RATE_PARENT, 0, "mout_apll"),
-	MUX(0, "mout_hdmi", mout_hdmi_p, SRC_TV, 0, 1),
+	MUX(CLK_MOUT_HDMI, "mout_hdmi", mout_hdmi_p, SRC_TV, 0, 1),
 	MUX(0, "mout_mfc1", sclk_evpll_p, SRC_MFC, 4, 1),
 	MUX(0, "mout_mfc", mout_mfc_p, SRC_MFC, 8, 1),
 	MUX_F(CLK_MOUT_G3D1, "mout_g3d1", sclk_evpll_p, SRC_G3D, 4, 1,
@@ -569,7 +569,7 @@ static struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
 	MUX(0, "mout_aclk100", sclk_ampll_p4210, SRC_TOP0, 16, 1),
 	MUX(0, "mout_aclk160", sclk_ampll_p4210, SRC_TOP0, 20, 1),
 	MUX(0, "mout_aclk133", sclk_ampll_p4210, SRC_TOP0, 24, 1),
-	MUX(0, "mout_mixer", mout_mixer_p4210, SRC_TV, 4, 1),
+	MUX(CLK_MOUT_MIXER, "mout_mixer", mout_mixer_p4210, SRC_TV, 4, 1),
 	MUX(0, "mout_dac", mout_dac_p4210, SRC_TV, 8, 1),
 	MUX(0, "mout_g2d0", sclk_ampll_p4210, E4210_SRC_IMAGE, 0, 1),
 	MUX(0, "mout_g2d1", sclk_evpll_p, E4210_SRC_IMAGE, 4, 1),
diff --git a/include/dt-bindings/clock/exynos4.h b/include/dt-bindings/clock/exynos4.h
index fb9816354079..34fe28c622d0 100644
--- a/include/dt-bindings/clock/exynos4.h
+++ b/include/dt-bindings/clock/exynos4.h
@@ -234,6 +234,8 @@
 #define CLK_MOUT_G3D1		393
 #define CLK_MOUT_G3D		394
 #define CLK_ACLK400_MCUISP	395 /* Exynos4x12 only */
+#define CLK_MOUT_HDMI		396
+#define CLK_MOUT_MIXER		397
 
 /* gate clocks - ppmu */
 #define CLK_PPMULEFT		400
-- 
cgit v1.2.3


From c3099a5294f2c7266234e8ea35cbffc20a41aa9a Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 19 Sep 2014 20:27:34 +0200
Subject: PM / Domains: Add a detach callback to the struct dev_pm_domain

The intent of this callback is to simplify detachment of devices from
their PM domains. Further patches will show the benefit.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index 72c0fe098a27..1022ba1eb4de 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -619,6 +619,7 @@ extern int dev_pm_put_subsys_data(struct device *dev);
  */
 struct dev_pm_domain {
 	struct dev_pm_ops	ops;
+	void (*detach)(struct device *dev, bool power_off);
 };
 
 /*
-- 
cgit v1.2.3


From aa42240ab2544a8bcb2efb400193826f57f3175e Mon Sep 17 00:00:00 2001
From: Tomasz Figa <tomasz.figa@gmail.com>
Date: Fri, 19 Sep 2014 20:27:36 +0200
Subject: PM / Domains: Add generic OF-based PM domain look-up

This patch introduces generic code to perform PM domain look-up using
device tree and automatically bind devices to their PM domains.

Generic device tree bindings are introduced to specify PM domains of
devices in their device tree nodes.

Backwards compatibility with legacy Samsung-specific PM domain bindings
is provided, but for now the new code is not compiled when
CONFIG_ARCH_EXYNOS is selected to avoid collision with legacy code.
This will change as soon as the Exynos PM domain code gets converted to
use the generic framework in further patch.

This patch was originally submitted by Tomasz Figa when he was employed
by Samsung.

Link: http://marc.info/?l=linux-pm&m=139955349702152&w=2
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
Tested-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 .../devicetree/bindings/power/power_domain.txt     |  49 ++++
 drivers/base/power/domain.c                        | 289 +++++++++++++++++++++
 include/linux/pm_domain.h                          |  52 ++++
 kernel/power/Kconfig                               |   4 +
 4 files changed, 394 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/power/power_domain.txt

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
new file mode 100644
index 000000000000..98c16672ab5f
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -0,0 +1,49 @@
+* Generic PM domains
+
+System on chip designs are often divided into multiple PM domains that can be
+used for power gating of selected IP blocks for power saving by reduced leakage
+current.
+
+This device tree binding can be used to bind PM domain consumer devices with
+their PM domains provided by PM domain providers. A PM domain provider can be
+represented by any node in the device tree and can provide one or more PM
+domains. A consumer node can refer to the provider by a phandle and a set of
+phandle arguments (so called PM domain specifiers) of length specified by the
+#power-domain-cells property in the PM domain provider node.
+
+==PM domain providers==
+
+Required properties:
+ - #power-domain-cells : Number of cells in a PM domain specifier;
+   Typically 0 for nodes representing a single PM domain and 1 for nodes
+   providing multiple PM domains (e.g. power controllers), but can be any value
+   as specified by device tree binding documentation of particular provider.
+
+Example:
+
+	power: power-controller@12340000 {
+		compatible = "foo,power-controller";
+		reg = <0x12340000 0x1000>;
+		#power-domain-cells = <1>;
+	};
+
+The node above defines a power controller that is a PM domain provider and
+expects one cell as its phandle argument.
+
+==PM domain consumers==
+
+Required properties:
+ - power-domains : A phandle and PM domain specifier as defined by bindings of
+                   the power controller specified by phandle.
+
+Example:
+
+	leaky-device@12350000 {
+		compatible = "foo,i-leak-current";
+		reg = <0x12350000 0x1000>;
+		power-domains = <&power 0>;
+	};
+
+The node above defines a typical PM domain consumer device, which is located
+inside a PM domain with index 0 of a power controller represented by a node
+with the label "power".
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e6a11ca3ce26..a3d41a883d83 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -8,6 +8,7 @@
 
 #include <linux/kernel.h>
 #include <linux/io.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
@@ -1933,3 +1934,291 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
 }
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+/*
+ * Device Tree based PM domain providers.
+ *
+ * The code below implements generic device tree based PM domain providers that
+ * bind device tree nodes with generic PM domains registered in the system.
+ *
+ * Any driver that registers generic PM domains and needs to support binding of
+ * devices to these domains is supposed to register a PM domain provider, which
+ * maps a PM domain specifier retrieved from the device tree to a PM domain.
+ *
+ * Two simple mapping functions have been provided for convenience:
+ *  - __of_genpd_xlate_simple() for 1:1 device tree node to PM domain mapping.
+ *  - __of_genpd_xlate_onecell() for mapping of multiple PM domains per node by
+ *    index.
+ */
+
+/**
+ * struct of_genpd_provider - PM domain provider registration structure
+ * @link: Entry in global list of PM domain providers
+ * @node: Pointer to device tree node of PM domain provider
+ * @xlate: Provider-specific xlate callback mapping a set of specifier cells
+ *         into a PM domain.
+ * @data: context pointer to be passed into @xlate callback
+ */
+struct of_genpd_provider {
+	struct list_head link;
+	struct device_node *node;
+	genpd_xlate_t xlate;
+	void *data;
+};
+
+/* List of registered PM domain providers. */
+static LIST_HEAD(of_genpd_providers);
+/* Mutex to protect the list above. */
+static DEFINE_MUTEX(of_genpd_mutex);
+
+/**
+ * __of_genpd_xlate_simple() - Xlate function for direct node-domain mapping
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct generic_pm_domain
+ *
+ * This is a generic xlate function that can be used to model PM domains that
+ * have their own device tree nodes. The private data of xlate function needs
+ * to be a valid pointer to struct generic_pm_domain.
+ */
+struct generic_pm_domain *__of_genpd_xlate_simple(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	if (genpdspec->args_count != 0)
+		return ERR_PTR(-EINVAL);
+	return data;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_simple);
+
+/**
+ * __of_genpd_xlate_onecell() - Xlate function using a single index.
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct genpd_onecell_data
+ *
+ * This is a generic xlate function that can be used to model simple PM domain
+ * controllers that have one device tree node and provide multiple PM domains.
+ * A single cell is used as an index into an array of PM domains specified in
+ * the genpd_onecell_data struct when registering the provider.
+ */
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	struct genpd_onecell_data *genpd_data = data;
+	unsigned int idx = genpdspec->args[0];
+
+	if (genpdspec->args_count != 1)
+		return ERR_PTR(-EINVAL);
+
+	if (idx >= genpd_data->num_domains) {
+		pr_err("%s: invalid domain index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!genpd_data->domains[idx])
+		return ERR_PTR(-ENOENT);
+
+	return genpd_data->domains[idx];
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_onecell);
+
+/**
+ * __of_genpd_add_provider() - Register a PM domain provider for a node
+ * @np: Device node pointer associated with the PM domain provider.
+ * @xlate: Callback for decoding PM domain from phandle arguments.
+ * @data: Context pointer for @xlate callback.
+ */
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+			void *data)
+{
+	struct of_genpd_provider *cp;
+
+	cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+	if (!cp)
+		return -ENOMEM;
+
+	cp->node = of_node_get(np);
+	cp->data = data;
+	cp->xlate = xlate;
+
+	mutex_lock(&of_genpd_mutex);
+	list_add(&cp->link, &of_genpd_providers);
+	mutex_unlock(&of_genpd_mutex);
+	pr_debug("Added domain provider from %s\n", np->full_name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_add_provider);
+
+/**
+ * of_genpd_del_provider() - Remove a previously registered PM domain provider
+ * @np: Device node pointer associated with the PM domain provider
+ */
+void of_genpd_del_provider(struct device_node *np)
+{
+	struct of_genpd_provider *cp;
+
+	mutex_lock(&of_genpd_mutex);
+	list_for_each_entry(cp, &of_genpd_providers, link) {
+		if (cp->node == np) {
+			list_del(&cp->link);
+			of_node_put(cp->node);
+			kfree(cp);
+			break;
+		}
+	}
+	mutex_unlock(&of_genpd_mutex);
+}
+EXPORT_SYMBOL_GPL(of_genpd_del_provider);
+
+/**
+ * of_genpd_get_from_provider() - Look-up PM domain
+ * @genpdspec: OF phandle args to use for look-up
+ *
+ * Looks for a PM domain provider under the node specified by @genpdspec and if
+ * found, uses xlate function of the provider to map phandle args to a PM
+ * domain.
+ *
+ * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR()
+ * on failure.
+ */
+static struct generic_pm_domain *of_genpd_get_from_provider(
+					struct of_phandle_args *genpdspec)
+{
+	struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
+	struct of_genpd_provider *provider;
+
+	mutex_lock(&of_genpd_mutex);
+
+	/* Check if we have such a provider in our array */
+	list_for_each_entry(provider, &of_genpd_providers, link) {
+		if (provider->node == genpdspec->np)
+			genpd = provider->xlate(genpdspec, provider->data);
+		if (!IS_ERR(genpd))
+			break;
+	}
+
+	mutex_unlock(&of_genpd_mutex);
+
+	return genpd;
+}
+
+/**
+ * genpd_dev_pm_detach - Detach a device from its PM domain.
+ * @dev: Device to attach.
+ * @power_off: Currently not used
+ *
+ * Try to locate a corresponding generic PM domain, which the device was
+ * attached to previously. If such is found, the device is detached from it.
+ */
+static void genpd_dev_pm_detach(struct device *dev, bool power_off)
+{
+	struct generic_pm_domain *pd = NULL, *gpd;
+	int ret = 0;
+
+	if (!dev->pm_domain)
+		return;
+
+	mutex_lock(&gpd_list_lock);
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+		if (&gpd->domain == dev->pm_domain) {
+			pd = gpd;
+			break;
+		}
+	}
+	mutex_unlock(&gpd_list_lock);
+
+	if (!pd)
+		return;
+
+	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_remove_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to remove from PM domain %s: %d",
+			pd->name, ret);
+		return;
+	}
+
+	/* Check if PM domain can be powered off after removing this device. */
+	genpd_queue_power_off_work(pd);
+}
+
+/**
+ * genpd_dev_pm_attach - Attach a device to its PM domain using DT.
+ * @dev: Device to attach.
+ *
+ * Parse device's OF node to find a PM domain specifier. If such is found,
+ * attaches the device to retrieved pm_domain ops.
+ *
+ * Both generic and legacy Samsung-specific DT bindings are supported to keep
+ * backwards compatibility with existing DTBs.
+ *
+ * Returns 0 on successfully attached PM domain or negative error code.
+ */
+int genpd_dev_pm_attach(struct device *dev)
+{
+	struct of_phandle_args pd_args;
+	struct generic_pm_domain *pd;
+	int ret;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	if (dev->pm_domain)
+		return -EEXIST;
+
+	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
+					"#power-domain-cells", 0, &pd_args);
+	if (ret < 0) {
+		if (ret != -ENOENT)
+			return ret;
+
+		/*
+		 * Try legacy Samsung-specific bindings
+		 * (for backwards compatibility of DT ABI)
+		 */
+		pd_args.args_count = 0;
+		pd_args.np = of_parse_phandle(dev->of_node,
+						"samsung,power-domain", 0);
+		if (!pd_args.np)
+			return -ENOENT;
+	}
+
+	pd = of_genpd_get_from_provider(&pd_args);
+	if (IS_ERR(pd)) {
+		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
+			__func__, PTR_ERR(pd));
+		of_node_put(dev->of_node);
+		return PTR_ERR(pd);
+	}
+
+	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_add_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to add to PM domain %s: %d",
+			pd->name, ret);
+		of_node_put(dev->of_node);
+		return ret;
+	}
+
+	dev->pm_domain->detach = genpd_dev_pm_detach;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
+#endif
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index aa03586c94a2..292079d8da6b 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -264,4 +264,56 @@ static inline void pm_genpd_syscore_poweroff(struct device *dev) {}
 static inline void pm_genpd_syscore_poweron(struct device *dev) {}
 #endif
 
+/* OF PM domain providers */
+struct of_device_id;
+
+struct genpd_onecell_data {
+	struct generic_pm_domain **domains;
+	unsigned int num_domains;
+};
+
+typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args,
+						void *data);
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+			void *data);
+void of_genpd_del_provider(struct device_node *np);
+
+struct generic_pm_domain *__of_genpd_xlate_simple(
+					struct of_phandle_args *genpdspec,
+					void *data);
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+					struct of_phandle_args *genpdspec,
+					void *data);
+
+int genpd_dev_pm_attach(struct device *dev);
+#else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
+static inline int __of_genpd_add_provider(struct device_node *np,
+					genpd_xlate_t xlate, void *data)
+{
+	return 0;
+}
+static inline void of_genpd_del_provider(struct device_node *np) {}
+
+#define __of_genpd_xlate_simple		NULL
+#define __of_genpd_xlate_onecell	NULL
+
+static inline int genpd_dev_pm_attach(struct device *dev)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
+
+static inline int of_genpd_add_provider_simple(struct device_node *np,
+					struct generic_pm_domain *genpd)
+{
+	return __of_genpd_add_provider(np, __of_genpd_xlate_simple, genpd);
+}
+static inline int of_genpd_add_provider_onecell(struct device_node *np,
+					struct genpd_onecell_data *data)
+{
+	return __of_genpd_add_provider(np, __of_genpd_xlate_onecell, data);
+}
+
 #endif /* _LINUX_PM_DOMAIN_H */
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index e4e4121fa327..897619b11fb2 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -302,6 +302,10 @@ config PM_GENERIC_DOMAINS_RUNTIME
 	def_bool y
 	depends on PM_RUNTIME && PM_GENERIC_DOMAINS
 
+config PM_GENERIC_DOMAINS_OF
+	def_bool y
+	depends on PM_GENERIC_DOMAINS && OF && !ARCH_EXYNOS
+
 config CPU_PM
 	bool
 	depends on SUSPEND || CPU_IDLE
-- 
cgit v1.2.3


From 46420dd73b800f87a19af13af5883855cf38cb08 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 19 Sep 2014 20:27:37 +0200
Subject: PM / Domains: Add APIs to attach/detach a PM domain for a device

To maintain scalability let's add common methods to attach and detach
a PM domain for a device, dev_pm_domain_attach|detach().

Typically dev_pm_domain_attach() shall be invoked from subsystem level
code at the probe phase to try to attach a device to its PM domain.
The reversed actions may be done a the remove phase and then by
invoking dev_pm_domain_detach().

When attachment succeeds, the attach function should assign its
corresponding detach function to a new ->detach() callback added in the
struct dev_pm_domain.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/common.c | 52 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pm.h          | 11 ++++++++++
 2 files changed, 63 insertions(+)

(limited to 'include')

diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index df2e5eeaeb05..b0f138806bbc 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -11,6 +11,8 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/pm_clock.h>
+#include <linux/acpi.h>
+#include <linux/pm_domain.h>
 
 /**
  * dev_pm_get_subsys_data - Create or refcount power.subsys_data for device.
@@ -82,3 +84,53 @@ int dev_pm_put_subsys_data(struct device *dev)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
+
+/**
+ * dev_pm_domain_attach - Attach a device to its PM domain.
+ * @dev: Device to attach.
+ * @power_on: Used to indicate whether we should power on the device.
+ *
+ * The @dev may only be attached to a single PM domain. By iterating through
+ * the available alternatives we try to find a valid PM domain for the device.
+ * As attachment succeeds, the ->detach() callback in the struct dev_pm_domain
+ * should be assigned by the corresponding attach function.
+ *
+ * This function should typically be invoked from subsystem level code during
+ * the probe phase. Especially for those that holds devices which requires
+ * power management through PM domains.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ *
+ * Returns 0 on successfully attached PM domain or negative error code.
+ */
+int dev_pm_domain_attach(struct device *dev, bool power_on)
+{
+	int ret;
+
+	ret = acpi_dev_pm_attach(dev, power_on);
+	if (ret)
+		ret = genpd_dev_pm_attach(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach);
+
+/**
+ * dev_pm_domain_detach - Detach a device from its PM domain.
+ * @dev: Device to attach.
+ * @power_off: Used to indicate whether we should power off the device.
+ *
+ * This functions will reverse the actions from dev_pm_domain_attach() and thus
+ * try to detach the @dev from its PM domain. Typically it should be invoked
+ * from subsystem level code during the remove phase.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ */
+void dev_pm_domain_detach(struct device *dev, bool power_off)
+{
+	if (dev->pm_domain && dev->pm_domain->detach)
+		dev->pm_domain->detach(dev, power_off);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_detach);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 1022ba1eb4de..c4cbf485a5d6 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -622,6 +622,17 @@ struct dev_pm_domain {
 	void (*detach)(struct device *dev, bool power_off);
 };
 
+#ifdef CONFIG_PM
+extern int dev_pm_domain_attach(struct device *dev, bool power_on);
+extern void dev_pm_domain_detach(struct device *dev, bool power_off);
+#else
+static inline int dev_pm_domain_attach(struct device *dev, bool power_on)
+{
+	return -ENODEV;
+}
+static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
+#endif
+
 /*
  * The PM_EVENT_ messages are also used by drivers implementing the legacy
  * suspend framework, based on the ->suspend() and ->resume() callbacks common
-- 
cgit v1.2.3


From 91d66cd27f5fd8a3bca4621a3505c9067925478d Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 19 Sep 2014 20:27:44 +0200
Subject: ACPI / PM: Convert acpi_dev_pm_detach() into a static function

The ->detach() callback for the PM domain has now been fully adopted,
thus there no users left of the acpi_dev_pm_detach() API. This allow us
to convert it into a static function.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/device_pm.c | 69 ++++++++++++++++++++++++------------------------
 include/linux/acpi.h     |  2 --
 2 files changed, 34 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index eec5ed5be949..bea6896be122 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -1040,6 +1040,40 @@ static struct dev_pm_domain acpi_general_pm_domain = {
 	},
 };
 
+/**
+ * acpi_dev_pm_detach - Remove ACPI power management from the device.
+ * @dev: Device to take care of.
+ * @power_off: Whether or not to try to remove power from the device.
+ *
+ * Remove the device from the general ACPI PM domain and remove its wakeup
+ * notifier.  If @power_off is set, additionally remove power from the device if
+ * possible.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ */
+static void acpi_dev_pm_detach(struct device *dev, bool power_off)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+
+	if (adev && dev->pm_domain == &acpi_general_pm_domain) {
+		dev->pm_domain = NULL;
+		acpi_remove_pm_notifier(adev);
+		if (power_off) {
+			/*
+			 * If the device's PM QoS resume latency limit or flags
+			 * have been exposed to user space, they have to be
+			 * hidden at this point, so that they don't affect the
+			 * choice of the low-power state to put the device into.
+			 */
+			dev_pm_qos_hide_latency_limit(dev);
+			dev_pm_qos_hide_flags(dev);
+			acpi_device_wakeup(adev, ACPI_STATE_S0, false);
+			acpi_dev_pm_low_power(dev, adev, ACPI_STATE_S0);
+		}
+	}
+}
+
 /**
  * acpi_dev_pm_attach - Prepare device for ACPI power management.
  * @dev: Device to prepare.
@@ -1077,39 +1111,4 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
-
-/**
- * acpi_dev_pm_detach - Remove ACPI power management from the device.
- * @dev: Device to take care of.
- * @power_off: Whether or not to try to remove power from the device.
- *
- * Remove the device from the general ACPI PM domain and remove its wakeup
- * notifier.  If @power_off is set, additionally remove power from the device if
- * possible.
- *
- * Callers must ensure proper synchronization of this function with power
- * management callbacks.
- */
-void acpi_dev_pm_detach(struct device *dev, bool power_off)
-{
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-
-	if (adev && dev->pm_domain == &acpi_general_pm_domain) {
-		dev->pm_domain = NULL;
-		acpi_remove_pm_notifier(adev);
-		if (power_off) {
-			/*
-			 * If the device's PM QoS resume latency limit or flags
-			 * have been exposed to user space, they have to be
-			 * hidden at this point, so that they don't affect the
-			 * choice of the low-power state to put the device into.
-			 */
-			dev_pm_qos_hide_latency_limit(dev);
-			dev_pm_qos_hide_flags(dev);
-			acpi_device_wakeup(adev, ACPI_STATE_S0, false);
-			acpi_dev_pm_low_power(dev, adev, ACPI_STATE_S0);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(acpi_dev_pm_detach);
 #endif /* CONFIG_PM */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 807cbc46d73e..b7926bb9b444 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -587,7 +587,6 @@ static inline int acpi_subsys_freeze(struct device *dev) { return 0; }
 #if defined(CONFIG_ACPI) && defined(CONFIG_PM)
 struct acpi_device *acpi_dev_pm_get_node(struct device *dev);
 int acpi_dev_pm_attach(struct device *dev, bool power_on);
-void acpi_dev_pm_detach(struct device *dev, bool power_off);
 #else
 static inline struct acpi_device *acpi_dev_pm_get_node(struct device *dev)
 {
@@ -597,7 +596,6 @@ static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
 {
 	return -ENODEV;
 }
-static inline void acpi_dev_pm_detach(struct device *dev, bool power_off) {}
 #endif
 
 #ifdef CONFIG_ACPI
-- 
cgit v1.2.3


From bf57229745f849e500ba69ff91e35bc8160a7373 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 13 Sep 2014 16:40:08 -0700
Subject: blk-mq: remove REQ_END

Pass an explicit parameter for the last request in a batch to ->queue_rq
instead of using a request flag.  Besides being a cleaner and non-stateful
interface this is also required for the next patch, which fixes the blk-mq
I/O submission code to not start a time too early.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c                    | 22 +++++-----------------
 drivers/block/mtip32xx/mtip32xx.c |  3 ++-
 drivers/block/null_blk.c          |  3 ++-
 drivers/block/virtio_blk.c        |  4 ++--
 drivers/scsi/scsi_lib.c           |  3 ++-
 include/linux/blk-mq.h            |  2 +-
 include/linux/blk_types.h         |  2 --
 7 files changed, 14 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index e743d28620b2..32b4797f4186 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -384,7 +384,7 @@ void blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
-static void blk_mq_start_request(struct request *rq, bool last)
+static void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
@@ -421,16 +421,6 @@ static void blk_mq_start_request(struct request *rq, bool last)
 		 */
 		rq->nr_phys_segments++;
 	}
-
-	/*
-	 * Flag the last request in the series so that drivers know when IO
-	 * should be kicked off, if they don't do it on a per-request basis.
-	 *
-	 * Note: the flag isn't the only condition drivers should do kick off.
-	 * If drive is busy, the last request might not have the bit set.
-	 */
-	if (last)
-		rq->cmd_flags |= REQ_END;
 }
 
 static void __blk_mq_requeue_request(struct request *rq)
@@ -440,8 +430,6 @@ static void __blk_mq_requeue_request(struct request *rq)
 	trace_block_rq_requeue(q, rq);
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
 
-	rq->cmd_flags &= ~REQ_END;
-
 	if (q->dma_drain_size && blk_rq_bytes(rq))
 		rq->nr_phys_segments--;
 }
@@ -755,9 +743,9 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 
-		blk_mq_start_request(rq, list_empty(&rq_list));
+		blk_mq_start_request(rq);
 
-		ret = q->mq_ops->queue_rq(hctx, rq);
+		ret = q->mq_ops->queue_rq(hctx, rq, list_empty(&rq_list));
 		switch (ret) {
 		case BLK_MQ_RQ_QUEUE_OK:
 			queued++;
@@ -1198,14 +1186,14 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		int ret;
 
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_start_request(rq, true);
+		blk_mq_start_request(rq);
 
 		/*
 		 * For OK queue, we are done. For error, kill it. Any other
 		 * error (busy), just add it to our list as we previously
 		 * would have done
 		 */
-		ret = q->mq_ops->queue_rq(data.hctx, rq);
+		ret = q->mq_ops->queue_rq(data.hctx, rq, true);
 		if (ret == BLK_MQ_RQ_QUEUE_OK)
 			goto done;
 		else {
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 5c8e7fe07745..0e2084f37c67 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3775,7 +3775,8 @@ static bool mtip_check_unal_depth(struct blk_mq_hw_ctx *hctx,
 	return false;
 }
 
-static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
+		bool last)
 {
 	int ret;
 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 00d469c7f9f7..c5b7315c2c13 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -313,7 +313,8 @@ static void null_request_fn(struct request_queue *q)
 	}
 }
 
-static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
+		bool last)
 {
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 0a581400de0f..13756e016797 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -164,14 +164,14 @@ static void virtblk_done(struct virtqueue *vq)
 	spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
 }
 
-static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
+static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
+		bool last)
 {
 	struct virtio_blk *vblk = hctx->queue->queuedata;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	unsigned long flags;
 	unsigned int num;
 	int qid = hctx->queue_num;
-	const bool last = (req->cmd_flags & REQ_END) != 0;
 	int err;
 	bool notify = false;
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 1f2bae475cb7..f1df41168391 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1855,7 +1855,8 @@ static void scsi_mq_done(struct scsi_cmnd *cmd)
 	blk_mq_complete_request(cmd->request);
 }
 
-static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
+static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
+		bool last)
 {
 	struct request_queue *q = req->q;
 	struct scsi_device *sdev = q->queuedata;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a1e31f274fcd..9c4e306a9217 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -77,7 +77,7 @@ struct blk_mq_tag_set {
 	struct list_head	tag_list;
 };
 
-typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, struct request *);
+typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, struct request *, bool);
 typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
 typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
 typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 66c2167f04a9..bb7d66460e7a 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -188,7 +188,6 @@ enum rq_flag_bits {
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_PM,		/* runtime pm request */
-	__REQ_END,		/* last of chain of requests */
 	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_MQ_INFLIGHT,	/* track inflight for MQ */
 	__REQ_NR_BITS,		/* stops here */
@@ -242,7 +241,6 @@ enum rq_flag_bits {
 #define REQ_SECURE		(1ULL << __REQ_SECURE)
 #define REQ_KERNEL		(1ULL << __REQ_KERNEL)
 #define REQ_PM			(1ULL << __REQ_PM)
-#define REQ_END			(1ULL << __REQ_END)
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
 
-- 
cgit v1.2.3


From e2490073cd7c3d6f6ef6e029a208edd4d38efac4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 13 Sep 2014 16:40:09 -0700
Subject: blk-mq: call blk_mq_start_request from ->queue_rq

When we call blk_mq_start_request from the core blk-mq code before calling into
->queue_rq there is a racy window where the timeout handler can hit before we've
fully set up the driver specific part of the command.

Move the call to blk_mq_start_request into the driver so the driver can start
the request only once it is fully set up.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c                    | 13 ++++++-------
 drivers/block/mtip32xx/mtip32xx.c |  2 ++
 drivers/block/null_blk.c          |  2 ++
 drivers/block/virtio_blk.c        |  2 ++
 drivers/scsi/scsi_lib.c           |  1 +
 include/linux/blk-mq.h            |  1 +
 6 files changed, 14 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 32b4797f4186..141f2e06803a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -384,7 +384,7 @@ void blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
-static void blk_mq_start_request(struct request *rq)
+void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
@@ -422,16 +422,18 @@ static void blk_mq_start_request(struct request *rq)
 		rq->nr_phys_segments++;
 	}
 }
+EXPORT_SYMBOL(blk_mq_start_request);
 
 static void __blk_mq_requeue_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
 	trace_block_rq_requeue(q, rq);
-	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
 
-	if (q->dma_drain_size && blk_rq_bytes(rq))
-		rq->nr_phys_segments--;
+	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
+		if (q->dma_drain_size && blk_rq_bytes(rq))
+			rq->nr_phys_segments--;
+	}
 }
 
 void blk_mq_requeue_request(struct request *rq)
@@ -743,8 +745,6 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 
-		blk_mq_start_request(rq);
-
 		ret = q->mq_ops->queue_rq(hctx, rq, list_empty(&rq_list));
 		switch (ret) {
 		case BLK_MQ_RQ_QUEUE_OK:
@@ -1186,7 +1186,6 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		int ret;
 
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_start_request(rq);
 
 		/*
 		 * For OK queue, we are done. For error, kill it. Any other
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 0e2084f37c67..4042440a0470 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3783,6 +3783,8 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	if (unlikely(mtip_check_unal_depth(hctx, rq)))
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
+	blk_mq_start_request(rq);
+
 	ret = mtip_submit_request(hctx, rq);
 	if (likely(!ret))
 		return BLK_MQ_RQ_QUEUE_OK;
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index c5b7315c2c13..332ce20d45da 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -321,6 +321,8 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	cmd->rq = rq;
 	cmd->nq = hctx->driver_data;
 
+	blk_mq_start_request(rq);
+
 	null_handle_cmd(cmd);
 	return BLK_MQ_RQ_QUEUE_OK;
 }
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 13756e016797..83816bf6882f 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -205,6 +205,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 		}
 	}
 
+	blk_mq_start_request(req);
+
 	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
 	if (num) {
 		if (rq_data_dir(vbr->req) == WRITE)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index f1df41168391..2dcd9078de48 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1890,6 +1890,7 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
 	scsi_init_cmd_errh(cmd);
 	cmd->scsi_done = scsi_mq_done;
 
+	blk_mq_start_request(req);
 	reason = scsi_dispatch_cmd(cmd);
 	if (reason) {
 		scsi_set_blocked(cmd, reason);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 9c4e306a9217..878b6f71da48 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -159,6 +159,7 @@ struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
 struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
 
+void blk_mq_start_request(struct request *rq);
 void blk_mq_end_io(struct request *rq, int error);
 void __blk_mq_end_io(struct request *rq, int error);
 
-- 
cgit v1.2.3


From c8a446ad695ada43a885ec12b38411dbd190a11b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 13 Sep 2014 16:40:10 -0700
Subject: blk-mq: rename blk_mq_end_io to blk_mq_end_request

Now that we've changed the driver API on the submission side use the
opportunity to fix up the name on the completion side to fit into the
general scheme.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-flush.c                 |  4 ++--
 block/blk-mq.c                    | 16 ++++++++--------
 drivers/block/mtip32xx/mtip32xx.c |  4 ++--
 drivers/block/null_blk.c          |  2 +-
 drivers/block/virtio_blk.c        |  2 +-
 drivers/scsi/scsi_lib.c           |  4 ++--
 include/linux/blk-mq.h            |  4 ++--
 7 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/block/blk-flush.c b/block/blk-flush.c
index 3cb5e9e7108a..698e6926388c 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -202,7 +202,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 		list_del_init(&rq->flush.list);
 		blk_flush_restore_request(rq);
 		if (q->mq_ops)
-			blk_mq_end_io(rq, error);
+			blk_mq_end_request(rq, error);
 		else
 			__blk_end_request_all(rq, error);
 		break;
@@ -378,7 +378,7 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if (!policy) {
 		if (q->mq_ops)
-			blk_mq_end_io(rq, 0);
+			blk_mq_end_request(rq, 0);
 		else
 			__blk_end_bidi_request(rq, 0, 0, 0);
 		return;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 141f2e06803a..1713686f5c2f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -300,7 +300,7 @@ void blk_mq_clone_flush_request(struct request *flush_rq,
 		hctx->cmd_size);
 }
 
-inline void __blk_mq_end_io(struct request *rq, int error)
+inline void __blk_mq_end_request(struct request *rq, int error)
 {
 	blk_account_io_done(rq);
 
@@ -312,15 +312,15 @@ inline void __blk_mq_end_io(struct request *rq, int error)
 		blk_mq_free_request(rq);
 	}
 }
-EXPORT_SYMBOL(__blk_mq_end_io);
+EXPORT_SYMBOL(__blk_mq_end_request);
 
-void blk_mq_end_io(struct request *rq, int error)
+void blk_mq_end_request(struct request *rq, int error)
 {
 	if (blk_update_request(rq, error, blk_rq_bytes(rq)))
 		BUG();
-	__blk_mq_end_io(rq, error);
+	__blk_mq_end_request(rq, error);
 }
-EXPORT_SYMBOL(blk_mq_end_io);
+EXPORT_SYMBOL(blk_mq_end_request);
 
 static void __blk_mq_complete_request_remote(void *data)
 {
@@ -360,7 +360,7 @@ void __blk_mq_complete_request(struct request *rq)
 	struct request_queue *q = rq->q;
 
 	if (!q->softirq_done_fn)
-		blk_mq_end_io(rq, rq->errors);
+		blk_mq_end_request(rq, rq->errors);
 	else
 		blk_mq_ipi_complete_request(rq);
 }
@@ -758,7 +758,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 			pr_err("blk-mq: bad return on queue: %d\n", ret);
 		case BLK_MQ_RQ_QUEUE_ERROR:
 			rq->errors = -EIO;
-			blk_mq_end_io(rq, rq->errors);
+			blk_mq_end_request(rq, rq->errors);
 			break;
 		}
 
@@ -1200,7 +1200,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 			if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
 				rq->errors = -EIO;
-				blk_mq_end_io(rq, rq->errors);
+				blk_mq_end_request(rq, rq->errors);
 				goto done;
 			}
 		}
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 4042440a0470..6b7e8d0fba99 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -247,7 +247,7 @@ static void mtip_async_complete(struct mtip_port *port,
 	if (unlikely(cmd->unaligned))
 		up(&port->cmd_slot_unal);
 
-	blk_mq_end_io(rq, status ? -EIO : 0);
+	blk_mq_end_request(rq, status ? -EIO : 0);
 }
 
 /*
@@ -3739,7 +3739,7 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
 		int err;
 
 		err = mtip_send_trim(dd, blk_rq_pos(rq), blk_rq_sectors(rq));
-		blk_mq_end_io(rq, err);
+		blk_mq_end_request(rq, err);
 		return 0;
 	}
 
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 332ce20d45da..ac50a2931044 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -177,7 +177,7 @@ static void end_cmd(struct nullb_cmd *cmd)
 {
 	switch (queue_mode)  {
 	case NULL_Q_MQ:
-		blk_mq_end_io(cmd->rq, 0);
+		blk_mq_end_request(cmd->rq, 0);
 		return;
 	case NULL_Q_RQ:
 		INIT_LIST_HEAD(&cmd->rq->queuelist);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 83816bf6882f..f751fc392ba9 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -135,7 +135,7 @@ static inline void virtblk_request_done(struct request *req)
 		req->errors = (error != 0);
 	}
 
-	blk_mq_end_io(req, error);
+	blk_mq_end_request(req, error);
 }
 
 static void virtblk_done(struct virtqueue *vq)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 2dcd9078de48..73ce7d27f5c8 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -713,7 +713,7 @@ static bool scsi_end_request(struct request *req, int error,
 
 	if (req->mq_ctx) {
 		/*
-		 * In the MQ case the command gets freed by __blk_mq_end_io,
+		 * In the MQ case the command gets freed by __blk_mq_end_request,
 		 * so we have to do all cleanup that depends on it earlier.
 		 *
 		 * We also can't kick the queues from irq context, so we
@@ -721,7 +721,7 @@ static bool scsi_end_request(struct request *req, int error,
 		 */
 		scsi_mq_uninit_cmd(cmd);
 
-		__blk_mq_end_io(req, error);
+		__blk_mq_end_request(req, error);
 
 		if (scsi_target(sdev)->single_lun ||
 		    !list_empty(&sdev->host->starved_list))
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 878b6f71da48..cb217c16990d 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -160,8 +160,8 @@ struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_ind
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
 
 void blk_mq_start_request(struct request *rq);
-void blk_mq_end_io(struct request *rq, int error);
-void __blk_mq_end_io(struct request *rq, int error);
+void blk_mq_end_request(struct request *rq, int error);
+void __blk_mq_end_request(struct request *rq, int error);
 
 void blk_mq_requeue_request(struct request *rq);
 void blk_mq_add_to_requeue_list(struct request *rq, bool at_head);
-- 
cgit v1.2.3


From 81481eb423c295c5480a3fab9bb961cf286c91e7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 13 Sep 2014 16:40:11 -0700
Subject: blk-mq: fix and simplify tag iteration for the timeout handler

Don't do a kmalloc from timer to handle timeouts, chances are we could be
under heavy load or similar and thus just miss out on the timeouts.
Fortunately it is very easy to just iterate over all in use tags, and doing
this properly actually cleans up the blk_mq_busy_iter API as well, and
prepares us for the next patch by passing a reserved argument to the
iterator.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq-tag.c      | 44 +++++++++++--------------
 block/blk-mq.c          | 85 +++++++++++++++----------------------------------
 include/linux/blk-mq.h  |  6 +++-
 include/scsi/scsi_tcq.h |  2 +-
 4 files changed, 49 insertions(+), 88 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c1b92426c95e..b08788086414 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -392,45 +392,37 @@ void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag,
 		__blk_mq_put_reserved_tag(tags, tag);
 }
 
-static void bt_for_each_free(struct blk_mq_bitmap_tags *bt,
-			     unsigned long *free_map, unsigned int off)
+static void bt_for_each(struct blk_mq_hw_ctx *hctx,
+		struct blk_mq_bitmap_tags *bt, unsigned int off,
+		busy_iter_fn *fn, void *data, bool reserved)
 {
-	int i;
+	struct request *rq;
+	int bit, i;
 
 	for (i = 0; i < bt->map_nr; i++) {
 		struct blk_align_bitmap *bm = &bt->map[i];
-		int bit = 0;
-
-		do {
-			bit = find_next_zero_bit(&bm->word, bm->depth, bit);
-			if (bit >= bm->depth)
-				break;
 
-			__set_bit(bit + off, free_map);
-			bit++;
-		} while (1);
+		for (bit = find_first_bit(&bm->word, bm->depth);
+		     bit < bm->depth;
+		     bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
+		     	rq = blk_mq_tag_to_rq(hctx->tags, off + bit);
+			if (rq->q == hctx->queue)
+				fn(hctx, rq, data, reserved);
+		}
 
 		off += (1 << bt->bits_per_word);
 	}
 }
 
-void blk_mq_tag_busy_iter(struct blk_mq_tags *tags,
-			  void (*fn)(void *, unsigned long *), void *data)
+void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
+		void *priv)
 {
-	unsigned long *tag_map;
-	size_t map_size;
-
-	map_size = ALIGN(tags->nr_tags, BITS_PER_LONG) / BITS_PER_LONG;
-	tag_map = kzalloc(map_size * sizeof(unsigned long), GFP_ATOMIC);
-	if (!tag_map)
-		return;
+	struct blk_mq_tags *tags = hctx->tags;
 
-	bt_for_each_free(&tags->bitmap_tags, tag_map, tags->nr_reserved_tags);
 	if (tags->nr_reserved_tags)
-		bt_for_each_free(&tags->breserved_tags, tag_map, 0);
-
-	fn(data, tag_map);
-	kfree(tag_map);
+		bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true);
+	bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
+			false);
 }
 EXPORT_SYMBOL(blk_mq_tag_busy_iter);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1713686f5c2f..3baebcaf36db 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -525,58 +525,6 @@ struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
 }
 EXPORT_SYMBOL(blk_mq_tag_to_rq);
 
-struct blk_mq_timeout_data {
-	struct blk_mq_hw_ctx *hctx;
-	unsigned long *next;
-	unsigned int *next_set;
-};
-
-static void blk_mq_timeout_check(void *__data, unsigned long *free_tags)
-{
-	struct blk_mq_timeout_data *data = __data;
-	struct blk_mq_hw_ctx *hctx = data->hctx;
-	unsigned int tag;
-
-	 /* It may not be in flight yet (this is where
-	 * the REQ_ATOMIC_STARTED flag comes in). The requests are
-	 * statically allocated, so we know it's always safe to access the
-	 * memory associated with a bit offset into ->rqs[].
-	 */
-	tag = 0;
-	do {
-		struct request *rq;
-
-		tag = find_next_zero_bit(free_tags, hctx->tags->nr_tags, tag);
-		if (tag >= hctx->tags->nr_tags)
-			break;
-
-		rq = blk_mq_tag_to_rq(hctx->tags, tag++);
-		if (rq->q != hctx->queue)
-			continue;
-		if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
-			continue;
-
-		blk_rq_check_expired(rq, data->next, data->next_set);
-	} while (1);
-}
-
-static void blk_mq_hw_ctx_check_timeout(struct blk_mq_hw_ctx *hctx,
-					unsigned long *next,
-					unsigned int *next_set)
-{
-	struct blk_mq_timeout_data data = {
-		.hctx		= hctx,
-		.next		= next,
-		.next_set	= next_set,
-	};
-
-	/*
-	 * Ask the tagging code to iterate busy requests, so we can
-	 * check them for timeout.
-	 */
-	blk_mq_tag_busy_iter(hctx->tags, blk_mq_timeout_check, &data);
-}
-
 static enum blk_eh_timer_return blk_mq_rq_timed_out(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -598,13 +546,30 @@ static enum blk_eh_timer_return blk_mq_rq_timed_out(struct request *rq)
 
 	return q->mq_ops->timeout(rq);
 }
+		
+struct blk_mq_timeout_data {
+	unsigned long next;
+	unsigned int next_set;
+};
+
+static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
+		struct request *rq, void *priv, bool reserved)
+{
+	struct blk_mq_timeout_data *data = priv;
+
+	if (test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+		blk_rq_check_expired(rq, &data->next, &data->next_set);
+}
 
-static void blk_mq_rq_timer(unsigned long data)
+static void blk_mq_rq_timer(unsigned long priv)
 {
-	struct request_queue *q = (struct request_queue *) data;
+	struct request_queue *q = (struct request_queue *)priv;
+	struct blk_mq_timeout_data data = {
+		.next		= 0,
+		.next_set	= 0,
+	};
 	struct blk_mq_hw_ctx *hctx;
-	unsigned long next = 0;
-	int i, next_set = 0;
+	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		/*
@@ -614,12 +579,12 @@ static void blk_mq_rq_timer(unsigned long data)
 		if (!hctx->nr_ctx || !hctx->tags)
 			continue;
 
-		blk_mq_hw_ctx_check_timeout(hctx, &next, &next_set);
+		blk_mq_tag_busy_iter(hctx, blk_mq_check_expired, &data);
 	}
 
-	if (next_set) {
-		next = blk_rq_timeout(round_jiffies_up(next));
-		mod_timer(&q->timeout, next);
+	if (data.next_set) {
+		data.next = blk_rq_timeout(round_jiffies_up(data.next));
+		mod_timer(&q->timeout, data.next);
 	} else {
 		queue_for_each_hw_ctx(q, hctx, i)
 			blk_mq_tag_idle(hctx);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index cb217c16990d..0eb0f642be4b 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -86,6 +86,9 @@ typedef int (init_request_fn)(void *, struct request *, unsigned int,
 typedef void (exit_request_fn)(void *, struct request *, unsigned int,
 		unsigned int);
 
+typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
+		bool);
+
 struct blk_mq_ops {
 	/*
 	 * Queue request
@@ -174,7 +177,8 @@ void blk_mq_stop_hw_queues(struct request_queue *q);
 void blk_mq_start_hw_queues(struct request_queue *q);
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
-void blk_mq_tag_busy_iter(struct blk_mq_tags *tags, void (*fn)(void *data, unsigned long *), void *data);
+void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
+		void *priv);
 
 /*
  * Driver command data is immediately after the request. So subtract request
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index cdcc90b07ecb..e64583560701 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -68,7 +68,7 @@ static inline void scsi_activate_tcq(struct scsi_device *sdev, int depth)
 		return;
 
 	if (!shost_use_blk_mq(sdev->host) &&
-	    blk_queue_tagged(sdev->request_queue))
+	    !blk_queue_tagged(sdev->request_queue))
 		blk_queue_init_tags(sdev->request_queue, depth,
 				    sdev->host->bqt);
 
-- 
cgit v1.2.3


From 0152fb6b57c4fae769ee75ea2ae670f4ff39fba9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 13 Sep 2014 16:40:13 -0700
Subject: blk-mq: pass a reserved argument to the timeout handler

Allow blk-mq to pass an argument to the timeout handler to indicate
if we're timing out a reserved or regular command.  For many drivers
those need to be handled different.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c          |  6 +++---
 drivers/scsi/scsi_lib.c | 10 +++++++++-
 include/linux/blk-mq.h  |  3 ++-
 3 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 298d6e360661..d12f1983d493 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -530,7 +530,7 @@ struct blk_mq_timeout_data {
 	unsigned int next_set;
 };
 
-static void blk_mq_rq_timed_out(struct request *req)
+static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 {
 	struct blk_mq_ops *ops = req->q->mq_ops;
 	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
@@ -548,7 +548,7 @@ static void blk_mq_rq_timed_out(struct request *req)
 		return;
 
 	if (ops->timeout)
-		ret = ops->timeout(req);
+		ret = ops->timeout(req, reserved);
 
 	switch (ret) {
 	case BLK_EH_HANDLED:
@@ -576,7 +576,7 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 
 	if (time_after_eq(jiffies, rq->deadline)) {
 		if (!blk_mark_rq_complete(rq))
-			blk_mq_rq_timed_out(rq);
+			blk_mq_rq_timed_out(rq, reserved);
 	} else if (!data->next_set || time_after(data->next, rq->deadline)) {
 		data->next = rq->deadline;
 		data->next_set = 1;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 73ce7d27f5c8..86b1156edb82 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1932,6 +1932,14 @@ out:
 	return ret;
 }
 
+static enum blk_eh_timer_return scsi_timeout(struct request *req,
+		bool reserved)
+{
+	if (reserved)
+		return BLK_EH_RESET_TIMER;
+	return scsi_times_out(req);
+}
+
 static int scsi_init_request(void *data, struct request *rq,
 		unsigned int hctx_idx, unsigned int request_idx,
 		unsigned int numa_node)
@@ -2043,7 +2051,7 @@ static struct blk_mq_ops scsi_mq_ops = {
 	.map_queue	= blk_mq_map_queue,
 	.queue_rq	= scsi_queue_rq,
 	.complete	= scsi_softirq_done,
-	.timeout	= scsi_times_out,
+	.timeout	= scsi_timeout,
 	.init_request	= scsi_init_request,
 	.exit_request	= scsi_exit_request,
 };
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 0eb0f642be4b..325349559fb0 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -79,6 +79,7 @@ struct blk_mq_tag_set {
 
 typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, struct request *, bool);
 typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
+typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
 typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
 typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
 typedef int (init_request_fn)(void *, struct request *, unsigned int,
@@ -103,7 +104,7 @@ struct blk_mq_ops {
 	/*
 	 * Called on request timeout
 	 */
-	rq_timed_out_fn		*timeout;
+	timeout_fn		*timeout;
 
 	softirq_done_fn		*complete;
 
-- 
cgit v1.2.3


From 257117862634d89de33fec74858b1a0ba5ab444b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 18 Sep 2014 08:02:05 -0700
Subject: net: sched: shrink struct qdisc_skb_cb to 28 bytes

We cannot make struct qdisc_skb_cb bigger without impacting IPoIB,
or increasing skb->cb[] size.

Commit e0f31d849867 ("flow_keys: Record IP layer protocol in
skb_flow_dissect()") broke IPoIB.

Only current offender is sch_choke, and this one do not need an
absolutely precise flow key.

If we store 17 bytes of flow key, its more than enough. (Its the actual
size of flow_keys if it was a packed structure, but we might add new
fields at the end of it later)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: e0f31d849867 ("flow_keys: Record IP layer protocol in skb_flow_dissect()")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  3 ++-
 net/sched/sch_choke.c     | 18 ++++++++++++++----
 2 files changed, 16 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index a3cfb8ebeb53..620e086c0cbe 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -231,7 +231,8 @@ struct qdisc_skb_cb {
 	unsigned int		pkt_len;
 	u16			slave_dev_queue_mapping;
 	u16			_pad;
-	unsigned char		data[24];
+#define QDISC_CB_PRIV_LEN 20
+	unsigned char		data[QDISC_CB_PRIV_LEN];
 };
 
 static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index ed30e436128b..fb666d1e4de3 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -133,10 +133,16 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 	--sch->q.qlen;
 }
 
+/* private part of skb->cb[] that a qdisc is allowed to use
+ * is limited to QDISC_CB_PRIV_LEN bytes.
+ * As a flow key might be too large, we store a part of it only.
+ */
+#define CHOKE_K_LEN min_t(u32, sizeof(struct flow_keys), QDISC_CB_PRIV_LEN - 3)
+
 struct choke_skb_cb {
 	u16			classid;
 	u8			keys_valid;
-	struct flow_keys	keys;
+	u8			keys[QDISC_CB_PRIV_LEN - 3];
 };
 
 static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb)
@@ -163,22 +169,26 @@ static u16 choke_get_classid(const struct sk_buff *skb)
 static bool choke_match_flow(struct sk_buff *skb1,
 			     struct sk_buff *skb2)
 {
+	struct flow_keys temp;
+
 	if (skb1->protocol != skb2->protocol)
 		return false;
 
 	if (!choke_skb_cb(skb1)->keys_valid) {
 		choke_skb_cb(skb1)->keys_valid = 1;
-		skb_flow_dissect(skb1, &choke_skb_cb(skb1)->keys);
+		skb_flow_dissect(skb1, &temp);
+		memcpy(&choke_skb_cb(skb1)->keys, &temp, CHOKE_K_LEN);
 	}
 
 	if (!choke_skb_cb(skb2)->keys_valid) {
 		choke_skb_cb(skb2)->keys_valid = 1;
-		skb_flow_dissect(skb2, &choke_skb_cb(skb2)->keys);
+		skb_flow_dissect(skb2, &temp);
+		memcpy(&choke_skb_cb(skb2)->keys, &temp, CHOKE_K_LEN);
 	}
 
 	return !memcmp(&choke_skb_cb(skb1)->keys,
 		       &choke_skb_cb(skb2)->keys,
-		       sizeof(struct flow_keys));
+		       CHOKE_K_LEN);
 }
 
 /*
-- 
cgit v1.2.3


From 57a94e24bc927f642f7f48ca1bf5476aa5be269d Mon Sep 17 00:00:00 2001
From: Boris BREZILLON <boris.brezillon@free-electrons.com>
Date: Mon, 22 Sep 2014 20:11:50 +0200
Subject: mtd: nand: support ONFI timing mode retrieval for non-ONFI NANDs

Add an onfi_timing_mode_default field to nand_chip and nand_flash_dev in
order to support NAND timings definition for non-ONFI NAND.

NAND that support better timings mode than the default one have to define
a new entry in the nand_ids table.

The default timing mode should be deduced from timings description from
the datasheet and the ONFI specification
(www.onfi.org/~/media/ONFI/specs/onfi_3_1_spec.pdf, chapter 4.15
"Timing Parameters").
You should choose the closest mode that fit the timings requirements of
your NAND chip.

Signed-off-by: Boris BREZILLON <boris.brezillon@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/nand/nand_base.c |  2 ++
 include/linux/mtd/nand.h     | 11 +++++++++++
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 801cad1de9eb..5b5c62712814 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3594,6 +3594,8 @@ static bool find_full_id_nand(struct mtd_info *mtd, struct nand_chip *chip,
 		chip->options |= type->options;
 		chip->ecc_strength_ds = NAND_ECC_STRENGTH(type);
 		chip->ecc_step_ds = NAND_ECC_STEP(type);
+		chip->onfi_timing_mode_default =
+					type->onfi_timing_mode_default;
 
 		*busw = type->options & NAND_BUSWIDTH_16;
 
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 8acb307b6fde..e4d451e4600b 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -587,6 +587,11 @@ struct nand_buffers {
  * @ecc_step_ds:	[INTERN] ECC step required by the @ecc_strength_ds,
  *                      also from the datasheet. It is the recommended ECC step
  *			size, if known; if unknown, set to zero.
+ * @onfi_timing_mode_default: [INTERN] default ONFI timing mode. This field is
+ *			      either deduced from the datasheet if the NAND
+ *			      chip is not ONFI compliant or set to 0 if it is
+ *			      (an ONFI chip is always configured in mode 0
+ *			      after a NAND reset)
  * @numchips:		[INTERN] number of physical chips
  * @chipsize:		[INTERN] the size of one chip for multichip arrays
  * @pagemask:		[INTERN] page number mask = number of (pages / chip) - 1
@@ -671,6 +676,7 @@ struct nand_chip {
 	uint8_t bits_per_cell;
 	uint16_t ecc_strength_ds;
 	uint16_t ecc_step_ds;
+	int onfi_timing_mode_default;
 	int badblockpos;
 	int badblockbits;
 
@@ -773,6 +779,10 @@ struct nand_chip {
  *               @ecc_step_ds in nand_chip{}, also from the datasheet.
  *               For example, the "4bit ECC for each 512Byte" can be set with
  *               NAND_ECC_INFO(4, 512).
+ * @onfi_timing_mode_default: the default ONFI timing mode entered after a NAND
+ *			      reset. Should be deduced from timings described
+ *			      in the datasheet.
+ *
  */
 struct nand_flash_dev {
 	char *name;
@@ -793,6 +803,7 @@ struct nand_flash_dev {
 		uint16_t strength_ds;
 		uint16_t step_ds;
 	} ecc;
+	int onfi_timing_mode_default;
 };
 
 /**
-- 
cgit v1.2.3


From 93af53b8633c4cb474585158512182b21219d743 Mon Sep 17 00:00:00 2001
From: Ezequiel García <ezequiel@vanguardiasur.com.ar>
Date: Sat, 20 Sep 2014 17:53:12 +0100
Subject: nand: omap2: Remove horrible ifdefs to fix module probe

The current code abuses ifdefs to determine if the selected ECC scheme
is supported by the running kernel. As a result the code is hard to read,
and it also fails to load as a module.

This commit removes all the ifdefs and instead introduces a function
omap2_nand_ecc_check() to check if the ECC is supported by using
IS_ENABLED(CONFIG_xxx).

Since IS_ENABLED() is true when a config is =y or =m, this change fixes the
module so it can be loaded with no issues.

Acked-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Ezequiel Garcia <ezequiel@vanguardiasur.com.ar>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/nand/omap2.c          | 130 +++++++++++++++++++++-----------------
 include/linux/platform_data/elm.h |  16 +++++
 2 files changed, 87 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index e1a9b310c159..f97a4ffd489d 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -136,7 +136,6 @@
 
 #define BADBLOCK_MARKER_LENGTH		2
 
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 static u_char bch16_vector[] = {0xf5, 0x24, 0x1c, 0xd0, 0x61, 0xb3, 0xf1, 0x55,
 				0x2e, 0x2c, 0x86, 0xa3, 0xed, 0x36, 0x1b, 0x78,
 				0x48, 0x76, 0xa9, 0x3b, 0x97, 0xd1, 0x7a, 0x93,
@@ -144,7 +143,6 @@ static u_char bch16_vector[] = {0xf5, 0x24, 0x1c, 0xd0, 0x61, 0xb3, 0xf1, 0x55,
 static u_char bch8_vector[] = {0xf3, 0xdb, 0x14, 0x16, 0x8b, 0xd2, 0xbe, 0xcc,
 	0xac, 0x6b, 0xff, 0x99, 0x7b};
 static u_char bch4_vector[] = {0x00, 0x6b, 0x31, 0xdd, 0x41, 0xbc, 0x10};
-#endif
 
 /* oob info generated runtime depending on ecc algorithm and layout selected */
 static struct nand_ecclayout omap_oobinfo;
@@ -1292,7 +1290,6 @@ static int __maybe_unused omap_calculate_ecc_bch(struct mtd_info *mtd,
 	return 0;
 }
 
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 /**
  * erased_sector_bitflips - count bit flips
  * @data:	data sector buffer
@@ -1593,33 +1590,71 @@ static int omap_read_page_bch(struct mtd_info *mtd, struct nand_chip *chip,
 /**
  * is_elm_present - checks for presence of ELM module by scanning DT nodes
  * @omap_nand_info: NAND device structure containing platform data
- * @bch_type: 0x0=BCH4, 0x1=BCH8, 0x2=BCH16
  */
-static int is_elm_present(struct omap_nand_info *info,
-			struct device_node *elm_node, enum bch_ecc bch_type)
+static bool is_elm_present(struct omap_nand_info *info,
+			   struct device_node *elm_node)
 {
 	struct platform_device *pdev;
-	struct nand_ecc_ctrl *ecc = &info->nand.ecc;
-	int err;
+
 	/* check whether elm-id is passed via DT */
 	if (!elm_node) {
 		pr_err("nand: error: ELM DT node not found\n");
-		return -ENODEV;
+		return false;
 	}
 	pdev = of_find_device_by_node(elm_node);
 	/* check whether ELM device is registered */
 	if (!pdev) {
 		pr_err("nand: error: ELM device not found\n");
-		return -ENODEV;
+		return false;
 	}
 	/* ELM module available, now configure it */
 	info->elm_dev = &pdev->dev;
-	err = elm_config(info->elm_dev, bch_type,
-		(info->mtd.writesize / ecc->size), ecc->size, ecc->bytes);
+	return true;
+}
 
-	return err;
+static bool omap2_nand_ecc_check(struct omap_nand_info *info,
+				 struct omap_nand_platform_data	*pdata)
+{
+	bool ecc_needs_bch, ecc_needs_omap_bch, ecc_needs_elm;
+
+	switch (info->ecc_opt) {
+	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
+	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
+		ecc_needs_omap_bch = false;
+		ecc_needs_bch = true;
+		ecc_needs_elm = false;
+		break;
+	case OMAP_ECC_BCH4_CODE_HW:
+	case OMAP_ECC_BCH8_CODE_HW:
+	case OMAP_ECC_BCH16_CODE_HW:
+		ecc_needs_omap_bch = true;
+		ecc_needs_bch = false;
+		ecc_needs_elm = true;
+		break;
+	default:
+		ecc_needs_omap_bch = false;
+		ecc_needs_bch = false;
+		ecc_needs_elm = false;
+		break;
+	}
+
+	if (ecc_needs_bch && !IS_ENABLED(CONFIG_MTD_NAND_ECC_BCH)) {
+		dev_err(&info->pdev->dev,
+			"CONFIG_MTD_NAND_ECC_BCH not enabled\n");
+		return false;
+	}
+	if (ecc_needs_omap_bch && !IS_ENABLED(CONFIG_MTD_NAND_OMAP_BCH)) {
+		dev_err(&info->pdev->dev,
+			"CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
+		return false;
+	}
+	if (ecc_needs_elm && !is_elm_present(info, pdata->elm_of_node)) {
+		dev_err(&info->pdev->dev, "ELM not available\n");
+		return false;
+	}
+
+	return true;
 }
-#endif /* CONFIG_MTD_NAND_ECC_BCH */
 
 static int omap_nand_probe(struct platform_device *pdev)
 {
@@ -1797,6 +1832,11 @@ static int omap_nand_probe(struct platform_device *pdev)
 		goto return_error;
 	}
 
+	if (!omap2_nand_ecc_check(info, pdata)) {
+		err = -EINVAL;
+		goto return_error;
+	}
+
 	/* populate MTD interface based on ECC scheme */
 	ecclayout		= &omap_oobinfo;
 	switch (info->ecc_opt) {
@@ -1829,7 +1869,6 @@ static int omap_nand_probe(struct platform_device *pdev)
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
-#ifdef CONFIG_MTD_NAND_ECC_BCH
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW_DETECTION_SW\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1861,14 +1900,8 @@ static int omap_nand_probe(struct platform_device *pdev)
 			err = -EINVAL;
 		}
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_ECC_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 
 	case OMAP_ECC_BCH4_CODE_HW:
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW ECC scheme\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1890,21 +1923,15 @@ static int omap_nand_probe(struct platform_device *pdev)
 		/* reserved marker already included in ecclayout->eccbytes */
 		ecclayout->oobfree->offset	=
 				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
-		/* This ECC scheme requires ELM H/W block */
-		if (is_elm_present(info, pdata->elm_of_node, BCH4_ECC) < 0) {
-			pr_err("nand: error: could not initialize ELM\n");
-			err = -ENODEV;
+
+		err = elm_config(info->elm_dev, BCH4_ECC,
+				 info->mtd.writesize / nand_chip->ecc.size,
+				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+		if (err < 0)
 			goto return_error;
-		}
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 
 	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
-#ifdef CONFIG_MTD_NAND_ECC_BCH
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW_DETECTION_SW\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1937,14 +1964,8 @@ static int omap_nand_probe(struct platform_device *pdev)
 			goto return_error;
 		}
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_ECC_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 
 	case OMAP_ECC_BCH8_CODE_HW:
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW ECC scheme\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1956,12 +1977,13 @@ static int omap_nand_probe(struct platform_device *pdev)
 		nand_chip->ecc.calculate	= omap_calculate_ecc_bch;
 		nand_chip->ecc.read_page	= omap_read_page_bch;
 		nand_chip->ecc.write_page	= omap_write_page_bch;
-		/* This ECC scheme requires ELM H/W block */
-		err = is_elm_present(info, pdata->elm_of_node, BCH8_ECC);
-		if (err < 0) {
-			pr_err("nand: error: could not initialize ELM\n");
+
+		err = elm_config(info->elm_dev, BCH8_ECC,
+				 info->mtd.writesize / nand_chip->ecc.size,
+				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+		if (err < 0)
 			goto return_error;
-		}
+
 		/* define ECC layout */
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
@@ -1973,14 +1995,8 @@ static int omap_nand_probe(struct platform_device *pdev)
 		ecclayout->oobfree->offset	=
 				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 
 	case OMAP_ECC_BCH16_CODE_HW:
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 		pr_info("using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1991,12 +2007,13 @@ static int omap_nand_probe(struct platform_device *pdev)
 		nand_chip->ecc.calculate	= omap_calculate_ecc_bch;
 		nand_chip->ecc.read_page	= omap_read_page_bch;
 		nand_chip->ecc.write_page	= omap_write_page_bch;
-		/* This ECC scheme requires ELM H/W block */
-		err = is_elm_present(info, pdata->elm_of_node, BCH16_ECC);
-		if (err < 0) {
-			pr_err("ELM is required for this ECC scheme\n");
+
+		err = elm_config(info->elm_dev, BCH16_ECC,
+				 info->mtd.writesize / nand_chip->ecc.size,
+				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+		if (err < 0)
 			goto return_error;
-		}
+
 		/* define ECC layout */
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
@@ -2008,11 +2025,6 @@ static int omap_nand_probe(struct platform_device *pdev)
 		ecclayout->oobfree->offset	=
 				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 	default:
 		pr_err("nand: error: invalid or unsupported ECC scheme\n");
 		err = -EINVAL;
diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h
index 780d1e97f620..b8686c00f15f 100644
--- a/include/linux/platform_data/elm.h
+++ b/include/linux/platform_data/elm.h
@@ -42,8 +42,24 @@ struct elm_errorvec {
 	int error_loc[16];
 };
 
+#if IS_ENABLED(CONFIG_MTD_NAND_OMAP_BCH)
 void elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc,
 		struct elm_errorvec *err_vec);
 int elm_config(struct device *dev, enum bch_ecc bch_type,
 	int ecc_steps, int ecc_step_size, int ecc_syndrome_size);
+#else
+static inline void
+elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc,
+			  struct elm_errorvec *err_vec)
+{
+}
+
+static inline int elm_config(struct device *dev, enum bch_ecc bch_type,
+			     int ecc_steps, int ecc_step_size,
+			     int ecc_syndrome_size)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_MTD_NAND_ECC_BCH */
+
 #endif /* __ELM_H */
-- 
cgit v1.2.3


From 2446254915a7d6f08bba9a755a34cc0402880472 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 18 Sep 2014 17:31:22 -0700
Subject: net: dsa: allow switch drivers to implement suspend/resume hooks

Add an abstraction layer to suspend/resume switch devices, doing the
following split:

- suspend/resume the slave network devices and their corresponding PHY
  devices
- suspend/resume the switch hardware using switch driver callbacks

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h  |  6 ++++
 net/dsa/dsa.c      | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 net/dsa/dsa_priv.h |  2 ++
 net/dsa/slave.c    | 31 +++++++++++++++++++++
 4 files changed, 119 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index e020b8a12b7d..846dce4abaa5 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -210,6 +210,12 @@ struct dsa_switch_driver {
 	void	(*get_ethtool_stats)(struct dsa_switch *ds,
 				     int port, uint64_t *data);
 	int	(*get_sset_count)(struct dsa_switch *ds);
+
+	/*
+	 * Suspend and resume
+	 */
+	int	(*suspend)(struct dsa_switch *ds);
+	int	(*resume)(struct dsa_switch *ds);
 };
 
 void register_switch_driver(struct dsa_switch_driver *type);
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 6e40928ec0e7..6905f2d84c44 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -238,6 +238,49 @@ static void dsa_switch_destroy(struct dsa_switch *ds)
 {
 }
 
+static int dsa_switch_suspend(struct dsa_switch *ds)
+{
+	int i, ret = 0;
+
+	/* Suspend slave network devices */
+	for (i = 0; i < DSA_MAX_PORTS; i++) {
+		if (!(ds->phys_port_mask & (1 << i)))
+			continue;
+
+		ret = dsa_slave_suspend(ds->ports[i]);
+		if (ret)
+			return ret;
+	}
+
+	if (ds->drv->suspend)
+		ret = ds->drv->suspend(ds);
+
+	return ret;
+}
+
+static int dsa_switch_resume(struct dsa_switch *ds)
+{
+	int i, ret = 0;
+
+	if (ds->drv->resume)
+		ret = ds->drv->resume(ds);
+
+	if (ret)
+		return ret;
+
+	/* Resume slave network devices */
+	for (i = 0; i < DSA_MAX_PORTS; i++) {
+		if (!(ds->phys_port_mask & (1 << i)))
+			continue;
+
+		ret = dsa_slave_resume(ds->ports[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 
 /* link polling *************************************************************/
 static void dsa_link_poll_work(struct work_struct *ugly)
@@ -650,6 +693,42 @@ static struct packet_type dsa_pack_type __read_mostly = {
 	.func	= dsa_switch_rcv,
 };
 
+#ifdef CONFIG_PM_SLEEP
+static int dsa_suspend(struct device *d)
+{
+	struct platform_device *pdev = to_platform_device(d);
+	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
+	int i, ret = 0;
+
+	for (i = 0; i < dst->pd->nr_chips; i++) {
+		struct dsa_switch *ds = dst->ds[i];
+
+		if (ds != NULL)
+			ret = dsa_switch_suspend(ds);
+	}
+
+	return ret;
+}
+
+static int dsa_resume(struct device *d)
+{
+	struct platform_device *pdev = to_platform_device(d);
+	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
+	int i, ret = 0;
+
+	for (i = 0; i < dst->pd->nr_chips; i++) {
+		struct dsa_switch *ds = dst->ds[i];
+
+		if (ds != NULL)
+			ret = dsa_switch_resume(ds);
+	}
+
+	return ret;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(dsa_pm_ops, dsa_suspend, dsa_resume);
+
 static const struct of_device_id dsa_of_match_table[] = {
 	{ .compatible = "brcm,bcm7445-switch-v4.0" },
 	{ .compatible = "marvell,dsa", },
@@ -665,6 +744,7 @@ static struct platform_driver dsa_driver = {
 		.name	= "dsa",
 		.owner	= THIS_MODULE,
 		.of_match_table = dsa_of_match_table,
+		.pm	= &dsa_pm_ops,
 	},
 };
 
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index f90899e8ab5a..dc9756d3154c 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -56,6 +56,8 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds);
 struct net_device *dsa_slave_create(struct dsa_switch *ds,
 				    struct device *parent,
 				    int port, char *name);
+int dsa_slave_suspend(struct net_device *slave_dev);
+int dsa_slave_resume(struct net_device *slave_dev);
 
 /* tag_dsa.c */
 extern const struct dsa_device_ops dsa_netdev_ops;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index a7997265019a..143811ef57ae 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -412,6 +412,37 @@ static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
 			p->phy->addr, p->phy->drv->name);
 }
 
+int dsa_slave_suspend(struct net_device *slave_dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(slave_dev);
+
+	netif_device_detach(slave_dev);
+
+	if (p->phy) {
+		phy_stop(p->phy);
+		p->old_pause = -1;
+		p->old_link = -1;
+		p->old_duplex = -1;
+		phy_suspend(p->phy);
+	}
+
+	return 0;
+}
+
+int dsa_slave_resume(struct net_device *slave_dev)
+{
+	struct dsa_slave_priv *p = netdev_priv(slave_dev);
+
+	netif_device_attach(slave_dev);
+
+	if (p->phy) {
+		phy_resume(p->phy);
+		phy_start(p->phy);
+	}
+
+	return 0;
+}
+
 struct net_device *
 dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 		 int port, char *name)
-- 
cgit v1.2.3


From 19e57c4e6dc6b82a3204b801f4c5f27c7d007559 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 18 Sep 2014 17:31:24 -0700
Subject: net: dsa: add {get, set}_wol callbacks to slave devices

Allow switch drivers to implement per-port Wake-on-LAN getter and
setters.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  8 ++++++++
 net/dsa/slave.c   | 23 +++++++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 846dce4abaa5..d8054fb4a4df 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -211,6 +211,14 @@ struct dsa_switch_driver {
 				     int port, uint64_t *data);
 	int	(*get_sset_count)(struct dsa_switch *ds);
 
+	/*
+	 * ethtool Wake-on-LAN
+	 */
+	void	(*get_wol)(struct dsa_switch *ds, int port,
+			   struct ethtool_wolinfo *w);
+	int	(*set_wol)(struct dsa_switch *ds, int port,
+			   struct ethtool_wolinfo *w);
+
 	/*
 	 * Suspend and resume
 	 */
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 143811ef57ae..43c1e4ade689 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -301,6 +301,27 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset)
 	return -EOPNOTSUPP;
 }
 
+static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+
+	if (ds->drv->get_wol)
+		ds->drv->get_wol(ds, p->port, w);
+}
+
+static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret = -EOPNOTSUPP;
+
+	if (ds->drv->set_wol)
+		ret = ds->drv->set_wol(ds, p->port, w);
+
+	return ret;
+}
+
 static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_settings		= dsa_slave_get_settings,
 	.set_settings		= dsa_slave_set_settings,
@@ -310,6 +331,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_strings		= dsa_slave_get_strings,
 	.get_ethtool_stats	= dsa_slave_get_ethtool_stats,
 	.get_sset_count		= dsa_slave_get_sset_count,
+	.set_wol		= dsa_slave_set_wol,
+	.get_wol		= dsa_slave_get_wol,
 };
 
 static const struct net_device_ops dsa_slave_netdev_ops = {
-- 
cgit v1.2.3


From 35f7aa5309c048bb70e58571942795fa9411ce6a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Sat, 20 Sep 2014 14:03:55 +0200
Subject: ipv6: mld: answer mldv2 queries with mldv1 reports in mldv1 fallback

RFC2710 (MLDv1), section 3.7. says:

  The length of a received MLD message is computed by taking the
  IPv6 Payload Length value and subtracting the length of any IPv6
  extension headers present between the IPv6 header and the MLD
  message. If that length is greater than 24 octets, that indicates
  that there are other fields present *beyond* the fields described
  above, perhaps belonging to a *future backwards-compatible* version
  of MLD. An implementation of the version of MLD specified in this
  document *MUST NOT* send an MLD message longer than 24 octets and
  MUST ignore anything past the first 24 octets of a received MLD
  message.

RFC3810 (MLDv2), section 8.2.1. states for *listeners* regarding
presence of MLDv1 routers:

  In order to be compatible with MLDv1 routers, MLDv2 hosts MUST
  operate in version 1 compatibility mode. [...] When Host
  Compatibility Mode is MLDv2, a host acts using the MLDv2 protocol
  on that interface. When Host Compatibility Mode is MLDv1, a host
  acts in MLDv1 compatibility mode, using *only* the MLDv1 protocol,
  on that interface. [...]

While section 8.3.1. specifies *router* behaviour regarding presence
of MLDv1 routers:

  MLDv2 routers may be placed on a network where there is at least
  one MLDv1 router. The following requirements apply:

  If an MLDv1 router is present on the link, the Querier MUST use
  the *lowest* version of MLD present on the network. This must be
  administratively assured. Routers that desire to be compatible
  with MLDv1 MUST have a configuration option to act in MLDv1 mode;
  if an MLDv1 router is present on the link, the system administrator
  must explicitly configure all MLDv2 routers to act in MLDv1 mode.
  When in MLDv1 mode, the Querier MUST send periodic General Queries
  truncated at the Multicast Address field (i.e., 24 bytes long),
  and SHOULD also warn about receiving an MLDv2 Query (such warnings
  must be rate-limited). The Querier MUST also fill in the Maximum
  Response Delay in the Maximum Response Code field, i.e., the
  exponential algorithm described in section 5.1.3. is not used. [...]

That means that we should not get queries from different versions of
MLD. When there's a MLDv1 router present, MLDv2 enforces truncation
and MRC == MRD (both fields are overlapping within the 24 octet range).

Section 8.3.2. specifies behaviour in the presence of MLDv1 multicast
address *listeners*:

  MLDv2 routers may be placed on a network where there are hosts
  that have not yet been upgraded to MLDv2. In order to be compatible
  with MLDv1 hosts, MLDv2 routers MUST operate in version 1 compatibility
  mode. MLDv2 routers keep a compatibility mode per multicast address
  record. The compatibility mode of a multicast address is determined
  from the Multicast Address Compatibility Mode variable, which can be
  in one of the two following states: MLDv1 or MLDv2.

  The Multicast Address Compatibility Mode of a multicast address
  record is set to MLDv1 whenever an MLDv1 Multicast Listener Report is
  *received* for that multicast address. At the same time, the Older
  Version Host Present timer for the multicast address is set to Older
  Version Host Present Timeout seconds. The timer is re-set whenever a
  new MLDv1 Report is received for that multicast address. If the Older
  Version Host Present timer expires, the router switches back to
  Multicast Address Compatibility Mode of MLDv2 for that multicast
  address. [...]

That means, what can happen is the following scenario, that hosts can
act in MLDv1 compatibility mode when they previously have received an
MLDv1 query (or, simply operate in MLDv1 mode-only); and at the same
time, an MLDv2 router could start up and transmits MLDv2 startup query
messages while being unaware of the current operational mode.

Given RFC2710, section 3.7 we would need to answer to that with an MLDv1
listener report, so that the router according to RFC3810, section 8.3.2.
would receive that and internally switch to MLDv1 compatibility as well.

Right now, I believe since the initial implementation of MLDv2, Linux
hosts would just silently drop such MLDv2 queries instead of replying
with an MLDv1 listener report, which would prevent a MLDv2 router going
into fallback mode (until it receives other MLDv1 queries).

Since the mapping of MRC to MRD in exactly such cases can make use of
the exponential algorithm from 5.1.3, we cannot [strictly speaking] be
aware in MLDv1 of the encoding in MRC, it seems also not mentioned by
the RFC. Since encodings are the same up to 32767, assume in such a
situation this value as a hard upper limit we would clamp. We have asked
one of the RFC authors on that regard, and he mentioned that there seem
not to be any implementations that make use of that exponential algorithm
on startup messages. In any case, this patch fixes this MLD
interoperability issue.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/mld.h |  5 ++++-
 net/ipv6/mcast.c  | 41 +++++++++++++++++++++++++++++++----------
 2 files changed, 35 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/mld.h b/include/net/mld.h
index faa1d161bf24..01d751303498 100644
--- a/include/net/mld.h
+++ b/include/net/mld.h
@@ -88,12 +88,15 @@ struct mld2_query {
 #define MLDV2_QQIC_EXP(value)	(((value) >> 4) & 0x07)
 #define MLDV2_QQIC_MAN(value)	((value) & 0x0f)
 
+#define MLD_EXP_MIN_LIMIT	32768UL
+#define MLDV1_MRD_MAX_COMPAT	(MLD_EXP_MIN_LIMIT - 1)
+
 static inline unsigned long mldv2_mrc(const struct mld2_query *mlh2)
 {
 	/* RFC3810, 5.1.3. Maximum Response Code */
 	unsigned long ret, mc_mrc = ntohs(mlh2->mld2q_mrc);
 
-	if (mc_mrc < 32768) {
+	if (mc_mrc < MLD_EXP_MIN_LIMIT) {
 		ret = mc_mrc;
 	} else {
 		unsigned long mc_man, mc_exp;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 592eba61e78a..9648de2b6745 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1237,7 +1237,7 @@ static void mld_update_qri(struct inet6_dev *idev,
 }
 
 static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld,
-			  unsigned long *max_delay)
+			  unsigned long *max_delay, bool v1_query)
 {
 	unsigned long mldv1_md;
 
@@ -1245,11 +1245,32 @@ static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld,
 	if (mld_in_v2_mode_only(idev))
 		return -EINVAL;
 
-	/* MLDv1 router present */
 	mldv1_md = ntohs(mld->mld_maxdelay);
+
+	/* When in MLDv1 fallback and a MLDv2 router start-up being
+	 * unaware of current MLDv1 operation, the MRC == MRD mapping
+	 * only works when the exponential algorithm is not being
+	 * used (as MLDv1 is unaware of such things).
+	 *
+	 * According to the RFC author, the MLDv2 implementations
+	 * he's aware of all use a MRC < 32768 on start up queries.
+	 *
+	 * Thus, should we *ever* encounter something else larger
+	 * than that, just assume the maximum possible within our
+	 * reach.
+	 */
+	if (!v1_query)
+		mldv1_md = min(mldv1_md, MLDV1_MRD_MAX_COMPAT);
+
 	*max_delay = max(msecs_to_jiffies(mldv1_md), 1UL);
 
-	mld_set_v1_mode(idev);
+	/* MLDv1 router present: we need to go into v1 mode *only*
+	 * when an MLDv1 query is received as per section 9.12. of
+	 * RFC3810! And we know from RFC2710 section 3.7 that MLDv1
+	 * queries MUST be of exactly 24 octets.
+	 */
+	if (v1_query)
+		mld_set_v1_mode(idev);
 
 	/* cancel MLDv2 report timer */
 	mld_gq_stop_timer(idev);
@@ -1264,10 +1285,6 @@ static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld,
 static int mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld,
 			  unsigned long *max_delay)
 {
-	/* hosts need to stay in MLDv1 mode, discard MLDv2 queries */
-	if (mld_in_v1_mode(idev))
-		return -EINVAL;
-
 	*max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL);
 
 	mld_update_qrv(idev, mld);
@@ -1324,8 +1341,11 @@ int igmp6_event_query(struct sk_buff *skb)
 	    !(group_type&IPV6_ADDR_MULTICAST))
 		return -EINVAL;
 
-	if (len == MLD_V1_QUERY_LEN) {
-		err = mld_process_v1(idev, mld, &max_delay);
+	if (len < MLD_V1_QUERY_LEN) {
+		return -EINVAL;
+	} else if (len == MLD_V1_QUERY_LEN || mld_in_v1_mode(idev)) {
+		err = mld_process_v1(idev, mld, &max_delay,
+				     len == MLD_V1_QUERY_LEN);
 		if (err < 0)
 			return err;
 	} else if (len >= MLD_V2_QUERY_LEN_MIN) {
@@ -1357,8 +1377,9 @@ int igmp6_event_query(struct sk_buff *skb)
 			mlh2 = (struct mld2_query *)skb_transport_header(skb);
 			mark = 1;
 		}
-	} else
+	} else {
 		return -EINVAL;
+	}
 
 	read_lock_bh(&idev->lock);
 	if (group_type == IPV6_ADDR_ANY) {
-- 
cgit v1.2.3


From fcdd1cf4dd63aecf86c987d7f4ec7187be5c2fbc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 22 Sep 2014 13:19:44 -0700
Subject: tcp: avoid possible arithmetic overflows

icsk_rto is a 32bit field, and icsk_backoff can reach 15 by default,
or more if some sysctl (eg tcp_retries2) are changed.

Better use 64bit to perform icsk_rto << icsk_backoff operations

As Joe Perches suggested, add a helper for this.

Yuchung spotted the tcp_v4_err() case.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h |  9 +++++++++
 net/ipv4/tcp_input.c               |  5 +++--
 net/ipv4/tcp_ipv4.c                |  6 +++---
 net/ipv4/tcp_output.c              | 13 ++++++-------
 net/ipv4/tcp_timer.c               |  4 ++--
 5 files changed, 23 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 5fbe6568c3cf..848e85cb5c61 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -242,6 +242,15 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
 #endif
 }
 
+static inline unsigned long
+inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
+		     unsigned long max_when)
+{
+        u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff;
+
+        return (unsigned long)min_t(u64, when, max_when);
+}
+
 struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
 
 struct request_sock *inet_csk_search_req(const struct sock *sk,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 02fb66d4a018..13f3da4762e3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3208,9 +3208,10 @@ static void tcp_ack_probe(struct sock *sk)
 		 * This function is not for random using!
 		 */
 	} else {
+		unsigned long when = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
+
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-					  min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX),
-					  TCP_RTO_MAX);
+					  when, TCP_RTO_MAX);
 	}
 }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 006b045716d8..3b2e49cb2b61 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -430,9 +430,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 			break;
 
 		icsk->icsk_backoff--;
-		inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) :
-			TCP_TIMEOUT_INIT) << icsk->icsk_backoff;
-		tcp_bound_rto(sk);
+		icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) :
+					       TCP_TIMEOUT_INIT;
+		icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
 
 		skb = tcp_write_queue_head(sk);
 		BUG_ON(!skb);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7f1280dcad57..8c61a7c0c889 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3279,6 +3279,7 @@ void tcp_send_probe0(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	unsigned long probe_max;
 	int err;
 
 	err = tcp_write_wakeup(sk);
@@ -3294,9 +3295,7 @@ void tcp_send_probe0(struct sock *sk)
 		if (icsk->icsk_backoff < sysctl_tcp_retries2)
 			icsk->icsk_backoff++;
 		icsk->icsk_probes_out++;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-					  min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX),
-					  TCP_RTO_MAX);
+		probe_max = TCP_RTO_MAX;
 	} else {
 		/* If packet was not sent due to local congestion,
 		 * do not backoff and do not remember icsk_probes_out.
@@ -3306,11 +3305,11 @@ void tcp_send_probe0(struct sock *sk)
 		 */
 		if (!icsk->icsk_probes_out)
 			icsk->icsk_probes_out = 1;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-					  min(icsk->icsk_rto << icsk->icsk_backoff,
-					      TCP_RESOURCE_PROBE_INTERVAL),
-					  TCP_RTO_MAX);
+		probe_max = TCP_RESOURCE_PROBE_INTERVAL;
 	}
+	inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+				  inet_csk_rto_backoff(icsk, probe_max),
+				  TCP_RTO_MAX);
 }
 
 int tcp_rtx_synack(struct sock *sk, struct request_sock *req)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index a339e7ba05a4..b24360f6e293 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -180,7 +180,7 @@ static int tcp_write_timeout(struct sock *sk)
 
 		retry_until = sysctl_tcp_retries2;
 		if (sock_flag(sk, SOCK_DEAD)) {
-			const int alive = (icsk->icsk_rto < TCP_RTO_MAX);
+			const int alive = icsk->icsk_rto < TCP_RTO_MAX;
 
 			retry_until = tcp_orphan_retries(sk, alive);
 			do_reset = alive ||
@@ -294,7 +294,7 @@ static void tcp_probe_timer(struct sock *sk)
 	max_probes = sysctl_tcp_retries2;
 
 	if (sock_flag(sk, SOCK_DEAD)) {
-		const int alive = ((icsk->icsk_rto << icsk->icsk_backoff) < TCP_RTO_MAX);
+		const int alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
 
 		max_probes = tcp_orphan_retries(sk, alive);
 
-- 
cgit v1.2.3


From bee3f304435a9c8c70b135083e23516872a17c98 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 22 Sep 2014 14:46:13 -0600
Subject: PCI: Remove unused pci_find_upstream_pcie_bridge()

pci_find_upstream_pcie_bridge() is unused, so remove it.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/search.c | 34 ----------------------------------
 include/linux/pci.h  | 11 -----------
 2 files changed, 45 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index 827ad831f1dd..a81f413083e4 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -103,40 +103,6 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
 	return ret;
 }
 
-/*
- * find the upstream PCIe-to-PCI bridge of a PCI device
- * if the device is PCIE, return NULL
- * if the device isn't connected to a PCIe bridge (that is its parent is a
- * legacy PCI bridge and the bridge is directly connected to bus 0), return its
- * parent
- */
-struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev)
-{
-	struct pci_dev *tmp = NULL;
-
-	if (pci_is_pcie(pdev))
-		return NULL;
-	while (1) {
-		if (pci_is_root_bus(pdev->bus))
-			break;
-		pdev = pdev->bus->self;
-		/* a p2p bridge */
-		if (!pci_is_pcie(pdev)) {
-			tmp = pdev;
-			continue;
-		}
-		/* PCI device should connect to a PCIe bridge */
-		if (pci_pcie_type(pdev) != PCI_EXP_TYPE_PCI_BRIDGE) {
-			/* Busted hardware? */
-			WARN_ON_ONCE(1);
-			return NULL;
-		}
-		return pdev;
-	}
-
-	return tmp;
-}
-
 static struct pci_bus *pci_do_find_bus(struct pci_bus *bus, unsigned char busnr)
 {
 	struct pci_bus *child;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 92c131efec1c..bf5a47c0cb42 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1828,17 +1828,6 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
 			   int (*fn)(struct pci_dev *pdev,
 				     u16 alias, void *data), void *data);
 
-/**
- * pci_find_upstream_pcie_bridge - find upstream PCIe-to-PCI bridge of a device
- * @pdev: the PCI device
- *
- * if the device is PCIE, return NULL
- * if the device isn't connected to a PCIe bridge (that is its parent is a
- * legacy PCI bridge and the bridge is directly connected to bus 0), return its
- * parent
- */
-struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev);
-
 /* helper functions for operation of device flag */
 static inline void pci_set_dev_assigned(struct pci_dev *pdev)
 {
-- 
cgit v1.2.3


From 5d8f4c9fdd67404c9f94683836e49ec8bded2287 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Wed, 17 Sep 2014 10:41:13 -0600
Subject: PCI: Remove unused pci_get_dma_source()

pci_get_dma_source() is unused, so remove it.  We now have
dma_alias_devfn() to describe this.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/quirks.c | 51 ---------------------------------------------------
 include/linux/pci.h  |  5 -----
 2 files changed, 56 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index da062d8ae36f..01c935cc38dc 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3514,57 +3514,6 @@ DECLARE_PCI_FIXUP_HEADER(0x1283, 0x8892, quirk_use_pcie_bridge_dma_alias);
 /* Intel 82801, https://bugzilla.kernel.org/show_bug.cgi?id=44881#c49 */
 DECLARE_PCI_FIXUP_HEADER(0x8086, 0x244e, quirk_use_pcie_bridge_dma_alias);
 
-static struct pci_dev *pci_func_0_dma_source(struct pci_dev *dev)
-{
-	if (!PCI_FUNC(dev->devfn))
-		return pci_dev_get(dev);
-
-	return pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
-}
-
-static const struct pci_dev_dma_source {
-	u16 vendor;
-	u16 device;
-	struct pci_dev *(*dma_source)(struct pci_dev *dev);
-} pci_dev_dma_source[] = {
-	/*
-	 * https://bugzilla.redhat.com/show_bug.cgi?id=605888
-	 *
-	 * Some Ricoh devices use the function 0 source ID for DMA on
-	 * other functions of a multifunction device.  The DMA devices
-	 * is therefore function 0, which will have implications of the
-	 * iommu grouping of these devices.
-	 */
-	{ PCI_VENDOR_ID_RICOH, 0xe822, pci_func_0_dma_source },
-	{ PCI_VENDOR_ID_RICOH, 0xe230, pci_func_0_dma_source },
-	{ PCI_VENDOR_ID_RICOH, 0xe832, pci_func_0_dma_source },
-	{ PCI_VENDOR_ID_RICOH, 0xe476, pci_func_0_dma_source },
-	{ 0 }
-};
-
-/*
- * IOMMUs with isolation capabilities need to be programmed with the
- * correct source ID of a device.  In most cases, the source ID matches
- * the device doing the DMA, but sometimes hardware is broken and will
- * tag the DMA as being sourced from a different device.  This function
- * allows that translation.  Note that the reference count of the
- * returned device is incremented on all paths.
- */
-struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
-{
-	const struct pci_dev_dma_source *i;
-
-	for (i = pci_dev_dma_source; i->dma_source; i++) {
-		if ((i->vendor == dev->vendor ||
-		     i->vendor == (u16)PCI_ANY_ID) &&
-		    (i->device == dev->device ||
-		     i->device == (u16)PCI_ANY_ID))
-			return i->dma_source(dev);
-	}
-
-	return pci_dev_get(dev);
-}
-
 /*
  * AMD has indicated that the devices below do not support peer-to-peer
  * in any system where they are found in the southbridge with an AMD
diff --git a/include/linux/pci.h b/include/linux/pci.h
index bf5a47c0cb42..d68d8e33c196 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1557,16 +1557,11 @@ enum pci_fixup_pass {
 
 #ifdef CONFIG_PCI_QUIRKS
 void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
-struct pci_dev *pci_get_dma_source(struct pci_dev *dev);
 int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
 void pci_dev_specific_enable_acs(struct pci_dev *dev);
 #else
 static inline void pci_fixup_device(enum pci_fixup_pass pass,
 				    struct pci_dev *dev) { }
-static inline struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
-{
-	return pci_dev_get(dev);
-}
 static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
 					       u16 acs_flags)
 {
-- 
cgit v1.2.3


From 48d11e067fc90ec9fc9c8f7ab982e5a83bf1887b Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Mon, 22 Sep 2014 12:26:10 -0700
Subject: mmc: Consolidate emmc tuning blocks

The same tuning block exists in the dw_mmc h.c and sdhci-msm.c
files. Move these into mmc.c so that they can be shared across
drivers.

Reported-by: Jaehoon Chung <jh80.chung@samsung.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc.c       | 32 ++++++++++++++++++++++++++++++++
 drivers/mmc/host/dw_mmc.c    | 30 ------------------------------
 drivers/mmc/host/sdhci-msm.c | 38 ++++----------------------------------
 include/linux/mmc/mmc.h      |  5 +++++
 4 files changed, 41 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index ce11d89aa305..6390787fb32a 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1177,6 +1177,38 @@ bus_speed:
 	return err;
 }
 
+const u8 tuning_blk_pattern_4bit[MMC_TUNING_BLK_PATTERN_4BIT_SIZE] = {
+	0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc,
+	0xc3, 0x3c, 0xcc, 0xff, 0xfe, 0xff, 0xfe, 0xef,
+	0xff, 0xdf, 0xff, 0xdd, 0xff, 0xfb, 0xff, 0xfb,
+	0xbf, 0xff, 0x7f, 0xff, 0x77, 0xf7, 0xbd, 0xef,
+	0xff, 0xf0, 0xff, 0xf0, 0x0f, 0xfc, 0xcc, 0x3c,
+	0xcc, 0x33, 0xcc, 0xcf, 0xff, 0xef, 0xff, 0xee,
+	0xff, 0xfd, 0xff, 0xfd, 0xdf, 0xff, 0xbf, 0xff,
+	0xbb, 0xff, 0xf7, 0xff, 0xf7, 0x7f, 0x7b, 0xde,
+};
+EXPORT_SYMBOL(tuning_blk_pattern_4bit);
+
+const u8 tuning_blk_pattern_8bit[MMC_TUNING_BLK_PATTERN_8BIT_SIZE] = {
+	0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, 0x00,
+	0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, 0xcc,
+	0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, 0xff,
+	0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, 0xff,
+	0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, 0xdd,
+	0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, 0xbb,
+	0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, 0xff,
+	0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, 0xff,
+	0xff, 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00,
+	0x00, 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc,
+	0xcc, 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff,
+	0xff, 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee,
+	0xff, 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd,
+	0xdd, 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff,
+	0xbb, 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff,
+	0xff, 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee,
+};
+EXPORT_SYMBOL(tuning_blk_pattern_8bit);
+
 /*
  * Execute tuning sequence to seek the proper bus operating
  * conditions for HS200 and HS400, which sends CMD21 to the device.
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 109fefeb9597..69f0cc68d5b2 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -82,36 +82,6 @@ struct idmac_desc {
 };
 #endif /* CONFIG_MMC_DW_IDMAC */
 
-static const u8 tuning_blk_pattern_4bit[] = {
-	0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc,
-	0xc3, 0x3c, 0xcc, 0xff, 0xfe, 0xff, 0xfe, 0xef,
-	0xff, 0xdf, 0xff, 0xdd, 0xff, 0xfb, 0xff, 0xfb,
-	0xbf, 0xff, 0x7f, 0xff, 0x77, 0xf7, 0xbd, 0xef,
-	0xff, 0xf0, 0xff, 0xf0, 0x0f, 0xfc, 0xcc, 0x3c,
-	0xcc, 0x33, 0xcc, 0xcf, 0xff, 0xef, 0xff, 0xee,
-	0xff, 0xfd, 0xff, 0xfd, 0xdf, 0xff, 0xbf, 0xff,
-	0xbb, 0xff, 0xf7, 0xff, 0xf7, 0x7f, 0x7b, 0xde,
-};
-
-static const u8 tuning_blk_pattern_8bit[] = {
-	0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, 0x00,
-	0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, 0xcc,
-	0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, 0xff,
-	0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, 0xff,
-	0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, 0xdd,
-	0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, 0xbb,
-	0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, 0xff,
-	0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, 0xff,
-	0xff, 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00,
-	0x00, 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc,
-	0xcc, 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff,
-	0xff, 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee,
-	0xff, 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd,
-	0xdd, 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff,
-	0xbb, 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff,
-	0xff, 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee,
-};
-
 static bool dw_mci_reset(struct dw_mci *host);
 
 #if defined(CONFIG_DEBUG_FS)
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 19539c61353c..30804385af6d 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -46,36 +46,6 @@
 #define CMUX_SHIFT_PHASE_SHIFT	24
 #define CMUX_SHIFT_PHASE_MASK	(7 << CMUX_SHIFT_PHASE_SHIFT)
 
-static const u8 tuning_block_64[] = {
-	0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc,
-	0xc3, 0x3c, 0xcc, 0xff, 0xfe, 0xff, 0xfe, 0xef,
-	0xff, 0xdf, 0xff, 0xdd, 0xff, 0xfb, 0xff, 0xfb,
-	0xbf, 0xff, 0x7f, 0xff, 0x77, 0xf7, 0xbd, 0xef,
-	0xff, 0xf0, 0xff, 0xf0, 0x0f, 0xfc, 0xcc, 0x3c,
-	0xcc, 0x33, 0xcc, 0xcf, 0xff, 0xef, 0xff, 0xee,
-	0xff, 0xfd, 0xff, 0xfd, 0xdf, 0xff, 0xbf, 0xff,
-	0xbb, 0xff, 0xf7, 0xff, 0xf7, 0x7f, 0x7b, 0xde,
-};
-
-static const u8 tuning_block_128[] = {
-	0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, 0x00,
-	0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, 0xcc,
-	0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, 0xff,
-	0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, 0xff,
-	0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, 0xdd,
-	0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, 0xbb,
-	0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, 0xff,
-	0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, 0xff,
-	0xff, 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00,
-	0x00, 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc,
-	0xcc, 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff,
-	0xff, 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee,
-	0xff, 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd,
-	0xdd, 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff,
-	0xbb, 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff,
-	0xff, 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee,
-};
-
 struct sdhci_msm_host {
 	struct platform_device *pdev;
 	void __iomem *core_mem;	/* MSM SDCC mapped address */
@@ -370,8 +340,8 @@ static int sdhci_msm_execute_tuning(struct sdhci_host *host, u32 opcode)
 {
 	int tuning_seq_cnt = 3;
 	u8 phase, *data_buf, tuned_phases[16], tuned_phase_cnt = 0;
-	const u8 *tuning_block_pattern = tuning_block_64;
-	int size = sizeof(tuning_block_64);	/* Pattern size in bytes */
+	const u8 *tuning_block_pattern = tuning_blk_pattern_4bit;
+	int size = sizeof(tuning_blk_pattern_4bit);
 	int rc;
 	struct mmc_host *mmc = host->mmc;
 	struct mmc_ios ios = host->mmc->ios;
@@ -387,8 +357,8 @@ static int sdhci_msm_execute_tuning(struct sdhci_host *host, u32 opcode)
 
 	if ((opcode == MMC_SEND_TUNING_BLOCK_HS200) &&
 	    (mmc->ios.bus_width == MMC_BUS_WIDTH_8)) {
-		tuning_block_pattern = tuning_block_128;
-		size = sizeof(tuning_block_128);
+		tuning_block_pattern = tuning_blk_pattern_8bit;
+		size = sizeof(tuning_blk_pattern_8bit);
 	}
 
 	data_buf = kmalloc(size, GFP_KERNEL);
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 78753bc90a87..1cd00b3a75b9 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -53,6 +53,11 @@
 #define MMC_SEND_TUNING_BLOCK    19   /* adtc                    R1  */
 #define MMC_SEND_TUNING_BLOCK_HS200	21	/* adtc R1  */
 
+#define MMC_TUNING_BLK_PATTERN_4BIT_SIZE	 64
+#define MMC_TUNING_BLK_PATTERN_8BIT_SIZE	128
+extern const u8 tuning_blk_pattern_4bit[MMC_TUNING_BLK_PATTERN_4BIT_SIZE];
+extern const u8 tuning_blk_pattern_8bit[MMC_TUNING_BLK_PATTERN_8BIT_SIZE];
+
   /* class 3 */
 #define MMC_WRITE_DAT_UNTIL_STOP 20   /* adtc [31:0] data addr   R1  */
 
-- 
cgit v1.2.3


From 854072dd0f73b8e4238c88bdf0dd2a8db0239c1c Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Thu, 28 Aug 2014 06:44:09 +0200
Subject: xen/events: support threaded irqs for interdomain event channels

Export bind_interdomain_evtchn_to_irq() so drivers can use threaded
interrupt handlers with:

 irq = bind_interdomain_evtchn_to_irq(remote_dom, remote_port);
 if (irq < 0)
     /* error */
 ret = request_threaded_irq(...);

Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 drivers/xen/events/events_base.c | 5 +++--
 include/xen/events.h             | 2 ++
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 5b5c5ff273fd..b4bca2d4a7e5 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -900,8 +900,8 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 	return irq;
 }
 
-static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
-					  unsigned int remote_port)
+int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+				   unsigned int remote_port)
 {
 	struct evtchn_bind_interdomain bind_interdomain;
 	int err;
@@ -914,6 +914,7 @@ static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
 
 	return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
 }
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq);
 
 static int find_virq(unsigned int virq, unsigned int cpu)
 {
diff --git a/include/xen/events.h b/include/xen/events.h
index 8bee7a75e850..5321cd9636e6 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -28,6 +28,8 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 			   unsigned long irqflags,
 			   const char *devname,
 			   void *dev_id);
+int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+				   unsigned int remote_port);
 int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
 					  unsigned int remote_port,
 					  irq_handler_t handler,
-- 
cgit v1.2.3


From e124c9a2c3c4c51555fe6f0bc214fe1b5cce3666 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Thu, 28 Aug 2014 06:44:10 +0200
Subject: xen: Add Xen pvSCSI protocol description

Add the definition of pvSCSI protocol used between the pvSCSI frontend
in a XEN domU and the pvSCSI backend in a XEN driver domain (usually
Dom0).

This header was originally provided by Fujitsu for Xen based on Linux
2.6.18.  Changes are:
- Added comments.
- Adapt to Linux style guide.
- Add support for larger SG-lists by putting them in an own granted
  page.
- Remove stale definitions.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 include/xen/interface/io/vscsiif.h | 229 +++++++++++++++++++++++++++++++++++++
 1 file changed, 229 insertions(+)
 create mode 100644 include/xen/interface/io/vscsiif.h

(limited to 'include')

diff --git a/include/xen/interface/io/vscsiif.h b/include/xen/interface/io/vscsiif.h
new file mode 100644
index 000000000000..d07d7aca8d1c
--- /dev/null
+++ b/include/xen/interface/io/vscsiif.h
@@ -0,0 +1,229 @@
+/******************************************************************************
+ * vscsiif.h
+ *
+ * Based on the blkif.h code.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright(c) FUJITSU Limited 2008.
+ */
+
+#ifndef __XEN__PUBLIC_IO_SCSI_H__
+#define __XEN__PUBLIC_IO_SCSI_H__
+
+#include "ring.h"
+#include "../grant_table.h"
+
+/*
+ * Feature and Parameter Negotiation
+ * =================================
+ * The two halves of a Xen pvSCSI driver utilize nodes within the XenStore to
+ * communicate capabilities and to negotiate operating parameters.  This
+ * section enumerates these nodes which reside in the respective front and
+ * backend portions of the XenStore, following the XenBus convention.
+ *
+ * Any specified default value is in effect if the corresponding XenBus node
+ * is not present in the XenStore.
+ *
+ * XenStore nodes in sections marked "PRIVATE" are solely for use by the
+ * driver side whose XenBus tree contains them.
+ *
+ *****************************************************************************
+ *                            Backend XenBus Nodes
+ *****************************************************************************
+ *
+ *------------------ Backend Device Identification (PRIVATE) ------------------
+ *
+ * p-devname
+ *      Values:         string
+ *
+ *      A free string used to identify the physical device (e.g. a disk name).
+ *
+ * p-dev
+ *      Values:         string
+ *
+ *      A string specifying the backend device: either a 4-tuple "h:c:t:l"
+ *      (host, controller, target, lun, all integers), or a WWN (e.g.
+ *      "naa.60014054ac780582").
+ *
+ * v-dev
+ *      Values:         string
+ *
+ *      A string specifying the frontend device in form of a 4-tuple "h:c:t:l"
+ *      (host, controller, target, lun, all integers).
+ *
+ *--------------------------------- Features ---------------------------------
+ *
+ * feature-sg-grant
+ *      Values:         unsigned [VSCSIIF_SG_TABLESIZE...65535]
+ *      Default Value:  0
+ *
+ *      Specifies the maximum number of scatter/gather elements in grant pages
+ *      supported. If not set, the backend supports up to VSCSIIF_SG_TABLESIZE
+ *      SG elements specified directly in the request.
+ *
+ *****************************************************************************
+ *                            Frontend XenBus Nodes
+ *****************************************************************************
+ *
+ *----------------------- Request Transport Parameters -----------------------
+ *
+ * event-channel
+ *      Values:         unsigned
+ *
+ *      The identifier of the Xen event channel used to signal activity
+ *      in the ring buffer.
+ *
+ * ring-ref
+ *      Values:         unsigned
+ *
+ *      The Xen grant reference granting permission for the backend to map
+ *      the sole page in a single page sized ring buffer.
+ *
+ * protocol
+ *      Values:         string (XEN_IO_PROTO_ABI_*)
+ *      Default Value:  XEN_IO_PROTO_ABI_NATIVE
+ *
+ *      The machine ABI rules governing the format of all ring request and
+ *      response structures.
+ */
+
+/* Requests from the frontend to the backend */
+
+/*
+ * Request a SCSI operation specified via a CDB in vscsiif_request.cmnd.
+ * The target is specified via channel, id and lun.
+ *
+ * The operation to be performed is specified via a CDB in cmnd[], the length
+ * of the CDB is in cmd_len. sc_data_direction specifies the direction of data
+ * (to the device, from the device, or none at all).
+ *
+ * If data is to be transferred to or from the device the buffer(s) in the
+ * guest memory is/are specified via one or multiple scsiif_request_segment
+ * descriptors each specifying a memory page via a grant_ref_t, a offset into
+ * the page and the length of the area in that page. All scsiif_request_segment
+ * areas concatenated form the resulting data buffer used by the operation.
+ * If the number of scsiif_request_segment areas is not too large (less than
+ * or equal VSCSIIF_SG_TABLESIZE) the areas can be specified directly in the
+ * seg[] array and the number of valid scsiif_request_segment elements is to be
+ * set in nr_segments.
+ *
+ * If "feature-sg-grant" in the Xenstore is set it is possible to specify more
+ * than VSCSIIF_SG_TABLESIZE scsiif_request_segment elements via indirection.
+ * The maximum number of allowed scsiif_request_segment elements is the value
+ * of the "feature-sg-grant" entry from Xenstore. When using indirection the
+ * seg[] array doesn't contain specifications of the data buffers, but
+ * references to scsiif_request_segment arrays, which in turn reference the
+ * data buffers. While nr_segments holds the number of populated seg[] entries
+ * (plus the set VSCSIIF_SG_GRANT bit), the number of scsiif_request_segment
+ * elements referencing the target data buffers is calculated from the lengths
+ * of the seg[] elements (the sum of all valid seg[].length divided by the
+ * size of one scsiif_request_segment structure).
+ */
+#define VSCSIIF_ACT_SCSI_CDB		1
+
+/*
+ * Request abort of a running operation for the specified target given by
+ * channel, id, lun and the operation's rqid in ref_rqid.
+ */
+#define VSCSIIF_ACT_SCSI_ABORT		2
+
+/*
+ * Request a device reset of the specified target (channel and id).
+ */
+#define VSCSIIF_ACT_SCSI_RESET		3
+
+/*
+ * Preset scatter/gather elements for a following request. Deprecated.
+ * Keeping the define only to avoid usage of the value "4" for other actions.
+ */
+#define VSCSIIF_ACT_SCSI_SG_PRESET	4
+
+/*
+ * Maximum scatter/gather segments per request.
+ *
+ * Considering balance between allocating at least 16 "vscsiif_request"
+ * structures on one page (4096 bytes) and the number of scatter/gather
+ * elements needed, we decided to use 26 as a magic number.
+ *
+ * If "feature-sg-grant" is set, more scatter/gather elements can be specified
+ * by placing them in one or more (up to VSCSIIF_SG_TABLESIZE) granted pages.
+ * In this case the vscsiif_request seg elements don't contain references to
+ * the user data, but to the SG elements referencing the user data.
+ */
+#define VSCSIIF_SG_TABLESIZE		26
+
+/*
+ * based on Linux kernel 2.6.18, still valid
+ * Changing these values requires support of multiple protocols via the rings
+ * as "old clients" will blindly use these values and the resulting structure
+ * sizes.
+ */
+#define VSCSIIF_MAX_COMMAND_SIZE	16
+#define VSCSIIF_SENSE_BUFFERSIZE	96
+
+struct scsiif_request_segment {
+	grant_ref_t gref;
+	uint16_t offset;
+	uint16_t length;
+};
+
+#define VSCSIIF_SG_PER_PAGE (PAGE_SIZE / sizeof(struct scsiif_request_segment))
+
+/* Size of one request is 252 bytes */
+struct vscsiif_request {
+	uint16_t rqid;		/* private guest value, echoed in resp  */
+	uint8_t act;		/* command between backend and frontend */
+	uint8_t cmd_len;	/* valid CDB bytes */
+
+	uint8_t cmnd[VSCSIIF_MAX_COMMAND_SIZE];	/* the CDB */
+	uint16_t timeout_per_command;	/* deprecated */
+	uint16_t channel, id, lun;	/* (virtual) device specification */
+	uint16_t ref_rqid;		/* command abort reference */
+	uint8_t sc_data_direction;	/* for DMA_TO_DEVICE(1)
+					   DMA_FROM_DEVICE(2)
+					   DMA_NONE(3) requests */
+	uint8_t nr_segments;		/* Number of pieces of scatter-gather */
+/*
+ * flag in nr_segments: SG elements via grant page
+ *
+ * If VSCSIIF_SG_GRANT is set, the low 7 bits of nr_segments specify the number
+ * of grant pages containing SG elements. Usable if "feature-sg-grant" set.
+ */
+#define VSCSIIF_SG_GRANT	0x80
+
+	struct scsiif_request_segment seg[VSCSIIF_SG_TABLESIZE];
+	uint32_t reserved[3];
+};
+
+/* Size of one response is 252 bytes */
+struct vscsiif_response {
+	uint16_t rqid;		/* identifies request */
+	uint8_t padding;
+	uint8_t sense_len;
+	uint8_t sense_buffer[VSCSIIF_SENSE_BUFFERSIZE];
+	int32_t rslt;
+	uint32_t residual_len;	/* request bufflen -
+				   return the value from physical device */
+	uint32_t reserved[36];
+};
+
+DEFINE_RING_TYPES(vscsiif, struct vscsiif_request, struct vscsiif_response);
+
+#endif /*__XEN__PUBLIC_IO_SCSI_H__*/
-- 
cgit v1.2.3


From d7bead1b8890c3e47a24db270fdb840ea728d8f0 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 22 Sep 2014 09:52:18 -0700
Subject: libata: change ata_<foo>_printk routines to return void

The return value is not used by callers of these functions nor
by uses of all macros so change the functions to return void.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/libata-core.c | 35 +++++++++++++----------------------
 include/linux/libata.h    | 12 ++++++------
 2 files changed, 19 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 782d126cf191..f785ae50a0ea 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -6772,32 +6772,28 @@ const struct ata_port_info ata_dummy_port_info = {
 /*
  * Utility print functions
  */
-int ata_port_printk(const struct ata_port *ap, const char *level,
-		    const char *fmt, ...)
+void ata_port_printk(const struct ata_port *ap, const char *level,
+		     const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, fmt);
 
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	r = printk("%sata%u: %pV", level, ap->print_id, &vaf);
+	printk("%sata%u: %pV", level, ap->print_id, &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(ata_port_printk);
 
-int ata_link_printk(const struct ata_link *link, const char *level,
-		    const char *fmt, ...)
+void ata_link_printk(const struct ata_link *link, const char *level,
+		     const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, fmt);
 
@@ -6805,37 +6801,32 @@ int ata_link_printk(const struct ata_link *link, const char *level,
 	vaf.va = &args;
 
 	if (sata_pmp_attached(link->ap) || link->ap->slave_link)
-		r = printk("%sata%u.%02u: %pV",
-			   level, link->ap->print_id, link->pmp, &vaf);
+		printk("%sata%u.%02u: %pV",
+		       level, link->ap->print_id, link->pmp, &vaf);
 	else
-		r = printk("%sata%u: %pV",
-			   level, link->ap->print_id, &vaf);
+		printk("%sata%u: %pV",
+		       level, link->ap->print_id, &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(ata_link_printk);
 
-int ata_dev_printk(const struct ata_device *dev, const char *level,
+void ata_dev_printk(const struct ata_device *dev, const char *level,
 		    const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, fmt);
 
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	r = printk("%sata%u.%02u: %pV",
-		   level, dev->link->ap->print_id, dev->link->pmp + dev->devno,
-		   &vaf);
+	printk("%sata%u.%02u: %pV",
+	       level, dev->link->ap->print_id, dev->link->pmp + dev->devno,
+	       &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(ata_dev_printk);
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 92abb497ab14..bd5fefeaf548 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1404,14 +1404,14 @@ static inline int sata_srst_pmp(struct ata_link *link)
  * printk helpers
  */
 __printf(3, 4)
-int ata_port_printk(const struct ata_port *ap, const char *level,
-		    const char *fmt, ...);
+void ata_port_printk(const struct ata_port *ap, const char *level,
+		     const char *fmt, ...);
 __printf(3, 4)
-int ata_link_printk(const struct ata_link *link, const char *level,
-		    const char *fmt, ...);
+void ata_link_printk(const struct ata_link *link, const char *level,
+		     const char *fmt, ...);
 __printf(3, 4)
-int ata_dev_printk(const struct ata_device *dev, const char *level,
-		   const char *fmt, ...);
+void ata_dev_printk(const struct ata_device *dev, const char *level,
+		    const char *fmt, ...);
 
 #define ata_port_err(ap, fmt, ...)				\
 	ata_port_printk(ap, KERN_ERR, fmt, ##__VA_ARGS__)
-- 
cgit v1.2.3


From d9ff958bb34aabdce08d11b0db24123c093d87cd Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Wed, 20 Aug 2014 19:20:53 +0200
Subject: dmaengine: Mark the struct dma_slave_config direction field
 deprecated

The direction passed to the device_prep_slave_sg, device_prep_dma_cyclic
or device_prep_interleaved_dma (through struct dma_interleaved_template)
should be used instead.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 include/linux/dmaengine.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 1f9e642c66ad..3d291f59acd8 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -307,7 +307,9 @@ enum dma_slave_buswidth {
  * struct dma_slave_config - dma slave channel runtime config
  * @direction: whether the data shall go in or out on this slave
  * channel, right now. DMA_MEM_TO_DEV and DMA_DEV_TO_MEM are
- * legal values.
+ * legal values. DEPRECATED, drivers should use the direction argument
+ * to the device_prep_slave_sg and device_prep_dma_cyclic functions or
+ * the dir field in the dma_interleaved_template structure.
  * @src_addr: this is the physical address where DMA slave data
  * should be read (RX), if the source is memory this argument is
  * ignored.
-- 
cgit v1.2.3


From e1db1706c86ee455f25eeaeadeda827e1e02310f Mon Sep 17 00:00:00 2001
From: abdoulaye berthe <berthe.ab@gmail.com>
Date: Sat, 5 Jul 2014 18:28:50 +0200
Subject: gpio: gpiolib: set gpiochip_remove retval to void

This avoids handling gpiochip remove error in device
remove handler.

Signed-off-by: Abdoulaye Berthe <berthe.ab@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c      | 24 +++++++-----------------
 include/linux/gpio/driver.h |  2 +-
 2 files changed, 8 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index a5831d6a9b91..bf1bb795f100 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -308,10 +308,9 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
  *
  * A gpio_chip with any GPIOs still requested may not be removed.
  */
-int gpiochip_remove(struct gpio_chip *chip)
+void gpiochip_remove(struct gpio_chip *chip)
 {
 	unsigned long	flags;
-	int		status = 0;
 	unsigned	id;
 
 	acpi_gpiochip_remove(chip);
@@ -323,24 +322,15 @@ int gpiochip_remove(struct gpio_chip *chip)
 	of_gpiochip_remove(chip);
 
 	for (id = 0; id < chip->ngpio; id++) {
-		if (test_bit(FLAG_REQUESTED, &chip->desc[id].flags)) {
-			status = -EBUSY;
-			break;
-		}
-	}
-	if (status == 0) {
-		for (id = 0; id < chip->ngpio; id++)
-			chip->desc[id].chip = NULL;
-
-		list_del(&chip->list);
+		if (test_bit(FLAG_REQUESTED, &chip->desc[id].flags))
+			dev_crit(chip->dev, "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
 	}
+	for (id = 0; id < chip->ngpio; id++)
+		chip->desc[id].chip = NULL;
 
+	list_del(&chip->list);
 	spin_unlock_irqrestore(&gpio_lock, flags);
-
-	if (status == 0)
-		gpiochip_unexport(chip);
-
-	return status;
+	gpiochip_unexport(chip);
 }
 EXPORT_SYMBOL_GPL(gpiochip_remove);
 
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index a2de58fffd19..560bf7fa614f 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -141,7 +141,7 @@ extern const char *gpiochip_is_requested(struct gpio_chip *chip,
 
 /* add/remove chips */
 extern int gpiochip_add(struct gpio_chip *chip);
-extern int gpiochip_remove(struct gpio_chip *chip);
+extern void gpiochip_remove(struct gpio_chip *chip);
 extern struct gpio_chip *gpiochip_find(void *data,
 			      int (*match)(struct gpio_chip *chip, void *data));
 
-- 
cgit v1.2.3


From 3d2613c4289ff22de3aa24d2d0a29e33937f023a Mon Sep 17 00:00:00 2001
From: Weike Chen <alvin.chen@intel.com>
Date: Wed, 17 Sep 2014 09:18:39 -0700
Subject: GPIO: gpio-dwapb: Enable platform driver binding to MFD driver

The Synopsys DesignWare APB GPIO driver only supports open firmware devices.
But, like Intel Quark X1000 SOC, which has a single PCI function exporting
a GPIO and an I2C controller, it is a Multifunction device. This patch is
to enable the current Synopsys DesignWare APB GPIO driver to support the
Multifunction device which exports the designware GPIO controller.

Reviewed-by: Hock Leong Kweh <hock.leong.kweh@intel.com>
Signed-off-by: Weike Chen <alvin.chen@intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/Kconfig                     |   1 -
 drivers/gpio/gpio-dwapb.c                | 224 +++++++++++++++++++++++--------
 include/linux/platform_data/gpio-dwapb.h |  32 +++++
 3 files changed, 199 insertions(+), 58 deletions(-)
 create mode 100644 include/linux/platform_data/gpio-dwapb.h

(limited to 'include')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index ec398bee7c60..d9ffb6dfa54b 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -136,7 +136,6 @@ config GPIO_DWAPB
 	tristate "Synopsys DesignWare APB GPIO driver"
 	select GPIO_GENERIC
 	select GENERIC_IRQ_CHIP
-	depends on OF_GPIO
 	help
 	  Say Y or M here to build support for the Synopsys DesignWare APB
 	  GPIO block.
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index d6618a6e2399..27466b5af5e8 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -21,6 +21,8 @@
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/spinlock.h>
+#include <linux/platform_data/gpio-dwapb.h>
+#include <linux/slab.h>
 
 #define GPIO_SWPORTA_DR		0x00
 #define GPIO_SWPORTA_DDR	0x04
@@ -84,11 +86,10 @@ static void dwapb_toggle_trigger(struct dwapb_gpio *gpio, unsigned int offs)
 	writel(v, gpio->regs + GPIO_INT_POLARITY);
 }
 
-static void dwapb_irq_handler(u32 irq, struct irq_desc *desc)
+static u32 dwapb_do_irq(struct dwapb_gpio *gpio)
 {
-	struct dwapb_gpio *gpio = irq_get_handler_data(irq);
-	struct irq_chip *chip = irq_desc_get_chip(desc);
 	u32 irq_status = readl_relaxed(gpio->regs + GPIO_INTSTATUS);
+	u32 ret = irq_status;
 
 	while (irq_status) {
 		int hwirq = fls(irq_status) - 1;
@@ -102,6 +103,16 @@ static void dwapb_irq_handler(u32 irq, struct irq_desc *desc)
 			dwapb_toggle_trigger(gpio, hwirq);
 	}
 
+	return ret;
+}
+
+static void dwapb_irq_handler(u32 irq, struct irq_desc *desc)
+{
+	struct dwapb_gpio *gpio = irq_get_handler_data(irq);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	dwapb_do_irq(gpio);
+
 	if (chip->irq_eoi)
 		chip->irq_eoi(irq_desc_get_irq_data(desc));
 }
@@ -207,22 +218,26 @@ static int dwapb_irq_set_type(struct irq_data *d, u32 type)
 	return 0;
 }
 
+static irqreturn_t dwapb_irq_handler_mfd(int irq, void *dev_id)
+{
+	u32 worked;
+	struct dwapb_gpio *gpio = dev_id;
+
+	worked = dwapb_do_irq(gpio);
+
+	return worked ? IRQ_HANDLED : IRQ_NONE;
+}
+
 static void dwapb_configure_irqs(struct dwapb_gpio *gpio,
-				 struct dwapb_gpio_port *port)
+				 struct dwapb_gpio_port *port,
+				 struct dwapb_port_property *pp)
 {
 	struct gpio_chip *gc = &port->bgc.gc;
-	struct device_node *node =  gc->of_node;
-	struct irq_chip_generic	*irq_gc;
+	struct device_node *node = pp->node;
+	struct irq_chip_generic	*irq_gc = NULL;
 	unsigned int hwirq, ngpio = gc->ngpio;
 	struct irq_chip_type *ct;
-	int err, irq, i;
-
-	irq = irq_of_parse_and_map(node, 0);
-	if (!irq) {
-		dev_warn(gpio->dev, "no irq for bank %s\n",
-			port->bgc.gc.of_node->full_name);
-		return;
-	}
+	int err, i;
 
 	gpio->domain = irq_domain_add_linear(node, ngpio,
 					     &irq_generic_chip_ops, gpio);
@@ -269,8 +284,24 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio,
 	irq_gc->chip_types[1].type = IRQ_TYPE_EDGE_BOTH;
 	irq_gc->chip_types[1].handler = handle_edge_irq;
 
-	irq_set_chained_handler(irq, dwapb_irq_handler);
-	irq_set_handler_data(irq, gpio);
+	if (!pp->irq_shared) {
+		irq_set_chained_handler(pp->irq, dwapb_irq_handler);
+		irq_set_handler_data(pp->irq, gpio);
+	} else {
+		/*
+		 * Request a shared IRQ since where MFD would have devices
+		 * using the same irq pin
+		 */
+		err = devm_request_irq(gpio->dev, pp->irq,
+				       dwapb_irq_handler_mfd,
+				       IRQF_SHARED, "gpio-dwapb-mfd", gpio);
+		if (err) {
+			dev_err(gpio->dev, "error requesting IRQ\n");
+			irq_domain_remove(gpio->domain);
+			gpio->domain = NULL;
+			return;
+		}
+	}
 
 	for (hwirq = 0 ; hwirq < ngpio ; hwirq++)
 		irq_create_mapping(gpio->domain, hwirq);
@@ -296,57 +327,42 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio)
 }
 
 static int dwapb_gpio_add_port(struct dwapb_gpio *gpio,
-			       struct device_node *port_np,
+			       struct dwapb_port_property *pp,
 			       unsigned int offs)
 {
 	struct dwapb_gpio_port *port;
-	u32 port_idx, ngpio;
 	void __iomem *dat, *set, *dirout;
 	int err;
 
-	if (of_property_read_u32(port_np, "reg", &port_idx) ||
-		port_idx >= DWAPB_MAX_PORTS) {
-		dev_err(gpio->dev, "missing/invalid port index for %s\n",
-			port_np->full_name);
-		return -EINVAL;
-	}
-
 	port = &gpio->ports[offs];
 	port->gpio = gpio;
 
-	if (of_property_read_u32(port_np, "snps,nr-gpios", &ngpio)) {
-		dev_info(gpio->dev, "failed to get number of gpios for %s\n",
-			 port_np->full_name);
-		ngpio = 32;
-	}
-
-	dat = gpio->regs + GPIO_EXT_PORTA + (port_idx * GPIO_EXT_PORT_SIZE);
-	set = gpio->regs + GPIO_SWPORTA_DR + (port_idx * GPIO_SWPORT_DR_SIZE);
+	dat = gpio->regs + GPIO_EXT_PORTA + (pp->idx * GPIO_EXT_PORT_SIZE);
+	set = gpio->regs + GPIO_SWPORTA_DR + (pp->idx * GPIO_SWPORT_DR_SIZE);
 	dirout = gpio->regs + GPIO_SWPORTA_DDR +
-		(port_idx * GPIO_SWPORT_DDR_SIZE);
+		(pp->idx * GPIO_SWPORT_DDR_SIZE);
 
 	err = bgpio_init(&port->bgc, gpio->dev, 4, dat, set, NULL, dirout,
 			 NULL, false);
 	if (err) {
 		dev_err(gpio->dev, "failed to init gpio chip for %s\n",
-			port_np->full_name);
+			pp->name);
 		return err;
 	}
 
-	port->bgc.gc.ngpio = ngpio;
-	port->bgc.gc.of_node = port_np;
+#ifdef CONFIG_OF_GPIO
+	port->bgc.gc.of_node = pp->node;
+#endif
+	port->bgc.gc.ngpio = pp->ngpio;
+	port->bgc.gc.base = pp->gpio_base;
 
-	/*
-	 * Only port A can provide interrupts in all configurations of the IP.
-	 */
-	if (port_idx == 0 &&
-	    of_property_read_bool(port_np, "interrupt-controller"))
-		dwapb_configure_irqs(gpio, port);
+	if (pp->irq)
+		dwapb_configure_irqs(gpio, port, pp);
 
 	err = gpiochip_add(&port->bgc.gc);
 	if (err)
 		dev_err(gpio->dev, "failed to register gpiochip for %s\n",
-			port_np->full_name);
+			pp->name);
 	else
 		port->is_registered = true;
 
@@ -362,25 +378,116 @@ static void dwapb_gpio_unregister(struct dwapb_gpio *gpio)
 			gpiochip_remove(&gpio->ports[m].bgc.gc);
 }
 
+static struct dwapb_platform_data *
+dwapb_gpio_get_pdata_of(struct device *dev)
+{
+	struct device_node *node, *port_np;
+	struct dwapb_platform_data *pdata;
+	struct dwapb_port_property *pp;
+	int nports;
+	int i;
+
+	node = dev->of_node;
+	if (!IS_ENABLED(CONFIG_OF_GPIO) || !node)
+		return ERR_PTR(-ENODEV);
+
+	nports = of_get_child_count(node);
+	if (nports == 0)
+		return ERR_PTR(-ENODEV);
+
+	pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	pdata->properties = kcalloc(nports, sizeof(*pp), GFP_KERNEL);
+	if (!pdata->properties) {
+		kfree(pdata);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	pdata->nports = nports;
+
+	i = 0;
+	for_each_child_of_node(node, port_np) {
+		pp = &pdata->properties[i++];
+		pp->node = port_np;
+
+		if (of_property_read_u32(port_np, "reg", &pp->idx) ||
+		    pp->idx >= DWAPB_MAX_PORTS) {
+			dev_err(dev, "missing/invalid port index for %s\n",
+				port_np->full_name);
+			kfree(pdata->properties);
+			kfree(pdata);
+			return ERR_PTR(-EINVAL);
+		}
+
+		if (of_property_read_u32(port_np, "snps,nr-gpios",
+					 &pp->ngpio)) {
+			dev_info(dev, "failed to get number of gpios for %s\n",
+				 port_np->full_name);
+			pp->ngpio = 32;
+		}
+
+		/*
+		 * Only port A can provide interrupts in all configurations of
+		 * the IP.
+		 */
+		if (pp->idx == 0 &&
+		    of_property_read_bool(port_np, "interrupt-controller")) {
+			pp->irq = irq_of_parse_and_map(port_np, 0);
+			if (!pp->irq) {
+				dev_warn(dev, "no irq for bank %s\n",
+					 port_np->full_name);
+			}
+		}
+
+		pp->irq_shared	= false;
+		pp->gpio_base	= -1;
+		pp->name	= port_np->full_name;
+	}
+
+	return pdata;
+}
+
+static inline void dwapb_free_pdata_of(struct dwapb_platform_data *pdata)
+{
+	if (!IS_ENABLED(CONFIG_OF_GPIO) || !pdata)
+		return;
+
+	kfree(pdata->properties);
+	kfree(pdata);
+}
+
 static int dwapb_gpio_probe(struct platform_device *pdev)
 {
+	unsigned int i;
 	struct resource *res;
 	struct dwapb_gpio *gpio;
-	struct device_node *np;
 	int err;
-	unsigned int offs = 0;
+	struct device *dev = &pdev->dev;
+	struct dwapb_platform_data *pdata = dev_get_platdata(dev);
+	bool is_pdata_alloc = !pdata;
+
+	if (is_pdata_alloc) {
+		pdata = dwapb_gpio_get_pdata_of(dev);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+	}
 
-	gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
-	if (!gpio)
-		return -ENOMEM;
-	gpio->dev = &pdev->dev;
+	if (!pdata->nports) {
+		err = -ENODEV;
+		goto out_err;
+	}
 
-	gpio->nr_ports = of_get_child_count(pdev->dev.of_node);
-	if (!gpio->nr_ports) {
-		err = -EINVAL;
+	gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
+	if (!gpio) {
+		err = -ENOMEM;
 		goto out_err;
 	}
-	gpio->ports = devm_kzalloc(&pdev->dev, gpio->nr_ports *
+	gpio->dev = &pdev->dev;
+	gpio->nr_ports = pdata->nports;
+
+	gpio->ports = devm_kcalloc(&pdev->dev, gpio->nr_ports,
 				   sizeof(*gpio->ports), GFP_KERNEL);
 	if (!gpio->ports) {
 		err = -ENOMEM;
@@ -394,20 +501,23 @@ static int dwapb_gpio_probe(struct platform_device *pdev)
 		goto out_err;
 	}
 
-	for_each_child_of_node(pdev->dev.of_node, np) {
-		err = dwapb_gpio_add_port(gpio, np, offs++);
+	for (i = 0; i < gpio->nr_ports; i++) {
+		err = dwapb_gpio_add_port(gpio, &pdata->properties[i], i);
 		if (err)
 			goto out_unregister;
 	}
 	platform_set_drvdata(pdev, gpio);
 
-	return 0;
+	goto out_err;
 
 out_unregister:
 	dwapb_gpio_unregister(gpio);
 	dwapb_irq_teardown(gpio);
 
 out_err:
+	if (is_pdata_alloc)
+		dwapb_free_pdata_of(pdata);
+
 	return err;
 }
 
diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h
new file mode 100644
index 000000000000..28702c849af1
--- /dev/null
+++ b/include/linux/platform_data/gpio-dwapb.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef GPIO_DW_APB_H
+#define GPIO_DW_APB_H
+
+struct dwapb_port_property {
+	struct device_node *node;
+	const char	*name;
+	unsigned int	idx;
+	unsigned int	ngpio;
+	unsigned int	gpio_base;
+	unsigned int	irq;
+	bool		irq_shared;
+};
+
+struct dwapb_platform_data {
+	struct dwapb_port_property *properties;
+	unsigned int nports;
+};
+
+#endif
-- 
cgit v1.2.3


From 7ca267faba8ad097f57cb71c32ae1865de83241a Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Mon, 15 Sep 2014 17:09:44 +0300
Subject: gpio: Increase ARCH_NR_GPIOs to 512

Some newer Intel SoCs, like Braswell already have more than 256 GPIOs
available so the default limit is exceeded. Instead of adding more
architecture specific gpio.h files with custom ARCH_NR_GPIOs we increase
the gpiolib default limit to be twice the current.

Current generic ARCH_NR_GPIOS limit is 256 which starts to be too small
for newer Intel SoCs like Braswell. In order to support GPIO controllers
on these SoCs we increase ARCH_NR_GPIOS to be 512 which should be
sufficient for now.

The kernel size increases a bit with this change. Below is an example of
x86_64 kernel image.

ARCH_NR_GPIOS=256
 text     data    bss     dec      hex    filename
 11476173 1971328 1265664 14713165 e0814d vmlinux

ARCH_NR_GPIOS=512
 text     data    bss     dec      hex    filename
 11476173 1971328 1269760 14717261 e0914d vmlinux

So the BSS size and this the kernel image size increases by 4k.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/asm-generic/gpio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index c1d4105e1c1d..383ade1a211b 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -27,7 +27,7 @@
  */
 
 #ifndef ARCH_NR_GPIOS
-#define ARCH_NR_GPIOS		256
+#define ARCH_NR_GPIOS		512
 #endif
 
 /*
-- 
cgit v1.2.3


From 4cdf507d54525842dfd9f6313fdafba039084046 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 19 Sep 2014 07:38:40 -0700
Subject: icmp: add a global rate limitation

Current ICMP rate limiting uses inetpeer cache, which is an RBL tree
protected by a lock, meaning that hosts can be stuck hard if all cpus
want to check ICMP limits.

When say a DNS or NTP server process is restarted, inetpeer tree grows
quick and machine comes to its knees.

iptables can not help because the bottleneck happens before ICMP
messages are even cooked and sent.

This patch adds a new global limitation, using a token bucket filter,
controlled by two new sysctl :

icmp_msgs_per_sec - INTEGER
    Limit maximal number of ICMP packets sent per second from this host.
    Only messages whose type matches icmp_ratemask are
    controlled by this limit.
    Default: 1000

icmp_msgs_burst - INTEGER
    icmp_msgs_per_sec controls number of ICMP packets sent per second,
    while icmp_msgs_burst controls the burst size of these packets.
    Default: 50

Note that if we really want to send millions of ICMP messages per
second, we might extend idea and infra added in commit 04ca6973f7c1a
("ip: make IP identifiers less predictable") :
add a token bucket in the ip_idents hash and no longer rely on inetpeer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 13 +++++++
 include/net/ip.h                       |  4 +++
 net/ipv4/icmp.c                        | 64 +++++++++++++++++++++++++++++++---
 net/ipv4/sysctl_net_ipv4.c             | 16 +++++++++
 net/ipv6/icmp.c                        | 20 ++++++-----
 5 files changed, 105 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 1b5581a30d77..c7a81ace35d0 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -769,8 +769,21 @@ icmp_ratelimit - INTEGER
 	icmp_ratemask (see below) to specific targets.
 	0 to disable any limiting,
 	otherwise the minimal space between responses in milliseconds.
+	Note that another sysctl, icmp_msgs_per_sec limits the number
+	of ICMP packets	sent on all targets.
 	Default: 1000
 
+icmp_msgs_per_sec - INTEGER
+	Limit maximal number of ICMP packets sent per second from this host.
+	Only messages whose type matches icmp_ratemask (see below) are
+	controlled by this limit.
+	Default: 1000
+
+icmp_msgs_burst - INTEGER
+	icmp_msgs_per_sec controls number of ICMP packets sent per second,
+	while icmp_msgs_burst controls the burst size of these packets.
+	Default: 50
+
 icmp_ratemask - INTEGER
 	Mask made of ICMP types for which rates are being limited.
 	Significant bits: IHGFEDCBA9876543210
diff --git a/include/net/ip.h b/include/net/ip.h
index 14bfc8e1bcf9..fcd9068fb8c3 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -548,6 +548,10 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
 void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
 		    u32 info);
 
+bool icmp_global_allow(void);
+extern int sysctl_icmp_msgs_per_sec;
+extern int sysctl_icmp_msgs_burst;
+
 #ifdef CONFIG_PROC_FS
 int ip_misc_proc_init(void);
 #endif
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index ea7d4afe8205..5882f584910e 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -231,12 +231,62 @@ static inline void icmp_xmit_unlock(struct sock *sk)
 	spin_unlock_bh(&sk->sk_lock.slock);
 }
 
+int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
+int sysctl_icmp_msgs_burst __read_mostly = 50;
+
+static struct {
+	spinlock_t	lock;
+	u32		credit;
+	u32		stamp;
+} icmp_global = {
+	.lock		= __SPIN_LOCK_UNLOCKED(icmp_global.lock),
+};
+
+/**
+ * icmp_global_allow - Are we allowed to send one more ICMP message ?
+ *
+ * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec.
+ * Returns false if we reached the limit and can not send another packet.
+ * Note: called with BH disabled
+ */
+bool icmp_global_allow(void)
+{
+	u32 credit, delta, incr = 0, now = (u32)jiffies;
+	bool rc = false;
+
+	/* Check if token bucket is empty and cannot be refilled
+	 * without taking the spinlock.
+	 */
+	if (!icmp_global.credit) {
+		delta = min_t(u32, now - icmp_global.stamp, HZ);
+		if (delta < HZ / 50)
+			return false;
+	}
+
+	spin_lock(&icmp_global.lock);
+	delta = min_t(u32, now - icmp_global.stamp, HZ);
+	if (delta >= HZ / 50) {
+		incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
+		if (incr)
+			icmp_global.stamp = now;
+	}
+	credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
+	if (credit) {
+		credit--;
+		rc = true;
+	}
+	icmp_global.credit = credit;
+	spin_unlock(&icmp_global.lock);
+	return rc;
+}
+EXPORT_SYMBOL(icmp_global_allow);
+
 /*
  *	Send an ICMP frame.
  */
 
-static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
-				      struct flowi4 *fl4, int type, int code)
+static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
+			       struct flowi4 *fl4, int type, int code)
 {
 	struct dst_entry *dst = &rt->dst;
 	bool rc = true;
@@ -253,8 +303,14 @@ static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 		goto out;
 
 	/* Limit if icmp type is enabled in ratemask. */
-	if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) {
-		struct inet_peer *peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1);
+	if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+		goto out;
+
+	rc = false;
+	if (icmp_global_allow()) {
+		struct inet_peer *peer;
+
+		peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1);
 		rc = inet_peer_xrlim_allow(peer,
 					   net->ipv4.sysctl_icmp_ratelimit);
 		if (peer)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1599966f4639..8a25509c35b3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -730,6 +730,22 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+	{
+		.procname	= "icmp_msgs_per_sec",
+		.data		= &sysctl_icmp_msgs_per_sec,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+	},
+	{
+		.procname	= "icmp_msgs_burst",
+		.data		= &sysctl_icmp_msgs_burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+	},
 	{
 		.procname	= "udp_mem",
 		.data		= &sysctl_udp_mem,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 394bb824fe4b..141e1f3ab74e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -170,11 +170,11 @@ static bool is_ineligible(const struct sk_buff *skb)
 /*
  * Check the ICMP output rate limit
  */
-static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
-				      struct flowi6 *fl6)
+static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
+			       struct flowi6 *fl6)
 {
-	struct dst_entry *dst;
 	struct net *net = sock_net(sk);
+	struct dst_entry *dst;
 	bool res = false;
 
 	/* Informational messages are not limited. */
@@ -199,16 +199,20 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	} else {
 		struct rt6_info *rt = (struct rt6_info *)dst;
 		int tmo = net->ipv6.sysctl.icmpv6_time;
-		struct inet_peer *peer;
 
 		/* Give more bandwidth to wider prefixes. */
 		if (rt->rt6i_dst.plen < 128)
 			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
 
-		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
-		res = inet_peer_xrlim_allow(peer, tmo);
-		if (peer)
-			inet_putpeer(peer);
+		if (icmp_global_allow()) {
+			struct inet_peer *peer;
+
+			peer = inet_getpeer_v6(net->ipv6.peers,
+					       &rt->rt6i_dst.addr, 1);
+			res = inet_peer_xrlim_allow(peer, tmo);
+			if (peer)
+				inet_putpeer(peer);
+		}
 	}
 	dst_release(dst);
 	return res;
-- 
cgit v1.2.3


From 55cf9cb63f0e5439f208d78ed944de9a8df65011 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Mon, 15 Sep 2014 18:01:10 +0800
Subject: f2fs: support large sector size

Block size in f2fs is 4096 bytes, so theoretically, f2fs can support 4096 bytes
sector device at maximum. But now f2fs only support 512 bytes size sector, so
block device such as zRAM which uses page cache as its block storage space will
not be mounted successfully as mismatch between sector size of zRAM and sector
size of f2fs supported.

In this patch we support large sector size in f2fs, so block device with sector
size of 512/1024/2048/4096 bytes can be supported in f2fs.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c          |  2 +-
 fs/f2fs/segment.c       |  4 ++--
 fs/f2fs/segment.h       | 10 +++++-----
 fs/f2fs/super.c         | 20 ++++++++++++++------
 include/linux/f2fs_fs.h |  5 +++--
 5 files changed, 25 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index aaf22a912044..13ab72084913 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -85,7 +85,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 	bio = bio_alloc(GFP_NOIO, npages);
 
 	bio->bi_bdev = sbi->sb->s_bdev;
-	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
+	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
 	bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
 	bio->bi_private = sbi;
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 4ea53aab786d..24b768ae39c4 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -370,8 +370,8 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 				block_t blkstart, block_t blklen)
 {
-	sector_t start = SECTOR_FROM_BLOCK(sbi, blkstart);
-	sector_t len = SECTOR_FROM_BLOCK(sbi, blklen);
+	sector_t start = SECTOR_FROM_BLOCK(blkstart);
+	sector_t len = SECTOR_FROM_BLOCK(blklen);
 	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
 	return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
 }
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 848ac519958f..032c0905a12b 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -89,10 +89,10 @@
 #define TOTAL_SECS(sbi)	(sbi->total_sections)
 #define TOTAL_BLKS(sbi)	(SM_I(sbi)->segment_count << sbi->log_blocks_per_seg)
 
-#define SECTOR_FROM_BLOCK(sbi, blk_addr)				\
-	(((sector_t)blk_addr) << (sbi)->log_sectors_per_block)
-#define SECTOR_TO_BLOCK(sbi, sectors)					\
-	(sectors >> (sbi)->log_sectors_per_block)
+#define SECTOR_FROM_BLOCK(blk_addr)					\
+	(((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
+#define SECTOR_TO_BLOCK(sectors)					\
+	(sectors >> F2FS_LOG_SECTORS_PER_BLOCK)
 #define MAX_BIO_BLOCKS(sbi)						\
 	((int)min((int)max_hw_blocks(sbi), BIO_MAX_PAGES))
 
@@ -711,7 +711,7 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
 {
 	struct block_device *bdev = sbi->sb->s_bdev;
 	struct request_queue *q = bdev_get_queue(bdev);
-	return SECTOR_TO_BLOCK(sbi, queue_max_sectors(q));
+	return SECTOR_TO_BLOCK(queue_max_sectors(q));
 }
 
 /*
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index ed4095e5e8a7..3dfa1b5eae2f 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -788,14 +788,22 @@ static int sanity_check_raw_super(struct super_block *sb,
 		return 1;
 	}
 
-	if (le32_to_cpu(raw_super->log_sectorsize) !=
-					F2FS_LOG_SECTOR_SIZE) {
-		f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
+	/* Currently, support 512/1024/2048/4096 bytes sector size */
+	if (le32_to_cpu(raw_super->log_sectorsize) >
+				F2FS_MAX_LOG_SECTOR_SIZE ||
+		le32_to_cpu(raw_super->log_sectorsize) <
+				F2FS_MIN_LOG_SECTOR_SIZE) {
+		f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize (%u)",
+			le32_to_cpu(raw_super->log_sectorsize));
 		return 1;
 	}
-	if (le32_to_cpu(raw_super->log_sectors_per_block) !=
-					F2FS_LOG_SECTORS_PER_BLOCK) {
-		f2fs_msg(sb, KERN_INFO, "Invalid log sectors per block");
+	if (le32_to_cpu(raw_super->log_sectors_per_block) +
+		le32_to_cpu(raw_super->log_sectorsize) !=
+			F2FS_MAX_LOG_SECTOR_SIZE) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid log sectors per block(%u) log sectorsize(%u)",
+			le32_to_cpu(raw_super->log_sectors_per_block),
+			le32_to_cpu(raw_super->log_sectorsize));
 		return 1;
 	}
 	return 0;
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 9ca1ff3d4662..860313a33a43 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -15,8 +15,9 @@
 #include <linux/types.h>
 
 #define F2FS_SUPER_OFFSET		1024	/* byte-size offset */
-#define F2FS_LOG_SECTOR_SIZE		9	/* 9 bits for 512 byte */
-#define F2FS_LOG_SECTORS_PER_BLOCK	3	/* 4KB: F2FS_BLKSIZE */
+#define F2FS_MIN_LOG_SECTOR_SIZE	9	/* 9 bits for 512 bytes */
+#define F2FS_MAX_LOG_SECTOR_SIZE	12	/* 12 bits for 4096 bytes */
+#define F2FS_LOG_SECTORS_PER_BLOCK	3	/* log number for sector/blk */
 #define F2FS_BLKSIZE			4096	/* support only 4KB block */
 #define F2FS_MAX_EXTENSION		64	/* # of extension entries */
 #define F2FS_BLK_ALIGN(x)	(((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE)
-- 
cgit v1.2.3


From 072f1a489efa348223db07730c4b946a4b1ca0cc Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Thu, 11 Sep 2014 19:43:46 -0300
Subject: [media] v4l: videobuf2: Fix typos in comments

The buffer flags are incorrectly referred to as V4L2_BUF_FLAGS_* instead
of V4L2_BUF_FLAG_* in comments. Fix it.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/videobuf2-core.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index b3c9973463ed..a8608ce37a75 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -356,8 +356,8 @@ struct v4l2_fh;
  * @buf_struct_size: size of the driver-specific buffer structure;
  *		"0" indicates the driver doesn't want to use a custom buffer
  *		structure type, so sizeof(struct vb2_buffer) will is used
- * @timestamp_flags: Timestamp flags; V4L2_BUF_FLAGS_TIMESTAMP_* and
- *		V4L2_BUF_FLAGS_TSTAMP_SRC_*
+ * @timestamp_flags: Timestamp flags; V4L2_BUF_FLAG_TIMESTAMP_* and
+ *		V4L2_BUF_FLAG_TSTAMP_SRC_*
  * @gfp_flags:	additional gfp flags used when allocating the buffers.
  *		Typically this is 0, but it may be e.g. GFP_DMA or __GFP_DMA32
  *		to force the buffer allocation to a specific memory zone.
-- 
cgit v1.2.3


From 8db3e5df4b5aa5ab8ce1edb8ee59ca9f2c2e7cd9 Mon Sep 17 00:00:00 2001
From: "nibble.max" <nibble.max@gmail.com>
Date: Wed, 6 Aug 2014 01:40:01 -0300
Subject: [media] rc: add dvbsky rc keymap macro

This RC will be used by DVBSky driver, added on the next patch.

Signed-off-by: Nibble Max <nibble.max@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/rc-map.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/media/rc-map.h b/include/media/rc-map.h
index 80f951890b4c..e7a1514075ec 100644
--- a/include/media/rc-map.h
+++ b/include/media/rc-map.h
@@ -135,6 +135,7 @@ void rc_map_init(void);
 #define RC_MAP_DM1105_NEC                "rc-dm1105-nec"
 #define RC_MAP_DNTV_LIVE_DVBT_PRO        "rc-dntv-live-dvbt-pro"
 #define RC_MAP_DNTV_LIVE_DVB_T           "rc-dntv-live-dvb-t"
+#define RC_MAP_DVBSKY                    "rc-dvbsky"
 #define RC_MAP_EMPTY                     "rc-empty"
 #define RC_MAP_EM_TERRATEC               "rc-em-terratec"
 #define RC_MAP_ENCORE_ENLTV2             "rc-encore-enltv2"
-- 
cgit v1.2.3


From 7e51aa4486bcf72daeb5d30227c4c01563f37044 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Wed, 2 Apr 2014 16:00:58 -0400
Subject: audit: drop unused struct audit_rule definition

The kernel only uses struct audit_rule_data.  We dropped support for
struct audit_rule a long time ago.  Drop the definition in the header
file.

Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/uapi/linux/audit.h | 13 -------------
 1 file changed, 13 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index cf6714752b69..df71b1d2cbb8 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -444,17 +444,4 @@ struct audit_rule_data {
 	char		buf[0];	/* string fields buffer */
 };
 
-/* audit_rule is supported to maintain backward compatibility with
- * userspace.  It supports integer fields only and corresponds to
- * AUDIT_ADD, AUDIT_DEL and AUDIT_LIST requests.
- */
-struct audit_rule {		/* for AUDIT_LIST, AUDIT_ADD, and AUDIT_DEL */
-	__u32		flags;	/* AUDIT_PER_{TASK,CALL}, AUDIT_PREPEND */
-	__u32		action;	/* AUDIT_NEVER, AUDIT_POSSIBLE, AUDIT_ALWAYS */
-	__u32		field_count;
-	__u32		mask[AUDIT_BITMASK_SIZE];
-	__u32		fields[AUDIT_MAX_FIELDS];
-	__u32		values[AUDIT_MAX_FIELDS];
-};
-
 #endif /* _UAPI_LINUX_AUDIT_H_ */
-- 
cgit v1.2.3


From 1002d94d30765b1faf0840adef9ed7e6b7aa5783 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Fri, 28 Feb 2014 15:34:19 -0500
Subject: syscall.h: fix doc text for syscall_get_arch()

syscall_get_arch() used to take a task as a argument.  It now uses
current.  Fix the doc text.

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/asm-generic/syscall.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index d401e5463fb0..0c938a4354f6 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -147,7 +147,7 @@ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
  *
  * Returns the AUDIT_ARCH_* based on the system call convention in use.
  *
- * It's only valid to call this when @task is stopped on entry to a system
+ * It's only valid to call this when current is stopped on entry to a system
  * call, due to %TIF_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or %TIF_SECCOMP.
  *
  * Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
-- 
cgit v1.2.3


From ce5d112827e5c2e9864323d0efd7ec2a62c6dce0 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Tue, 11 Mar 2014 13:50:46 -0400
Subject: ARCH: AUDIT: implement syscall_get_arch for all arches

For all arches which support audit implement syscall_get_arch()
They are all pretty easy and straight forward, stolen from how the call
to audit_syscall_entry() determines the arch.

Based-on-patch-by: Richard Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Cc: linux-ia64@vger.kernel.org
Cc: microblaze-uclinux@itee.uq.edu.au
Cc: linux-mips@linux-mips.org
Cc: linux@lists.openrisc.net
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: sparclinux@vger.kernel.org
---
 arch/ia64/include/asm/syscall.h       |  6 ++++++
 arch/microblaze/include/asm/syscall.h |  5 +++++
 arch/mips/include/asm/syscall.h       |  2 +-
 arch/openrisc/include/asm/syscall.h   |  5 +++++
 arch/parisc/include/asm/syscall.h     | 11 +++++++++++
 arch/powerpc/include/asm/syscall.h    | 12 ++++++++++++
 arch/sparc/include/asm/syscall.h      |  8 ++++++++
 include/uapi/linux/audit.h            |  1 +
 8 files changed, 49 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h
index a7ff1c6ab068..1d0b875fec44 100644
--- a/arch/ia64/include/asm/syscall.h
+++ b/arch/ia64/include/asm/syscall.h
@@ -13,6 +13,7 @@
 #ifndef _ASM_SYSCALL_H
 #define _ASM_SYSCALL_H	1
 
+#include <uapi/linux/audit.h>
 #include <linux/sched.h>
 #include <linux/err.h>
 
@@ -79,4 +80,9 @@ static inline void syscall_set_arguments(struct task_struct *task,
 
 	ia64_syscall_get_set_arguments(task, regs, i, n, args, 1);
 }
+
+static inline int syscall_get_arch(void)
+{
+	return AUDIT_ARCH_IA64;
+}
 #endif	/* _ASM_SYSCALL_H */
diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h
index 9bc431783105..53cfaf34c343 100644
--- a/arch/microblaze/include/asm/syscall.h
+++ b/arch/microblaze/include/asm/syscall.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_MICROBLAZE_SYSCALL_H
 #define __ASM_MICROBLAZE_SYSCALL_H
 
+#include <uapi/linux/audit.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <asm/ptrace.h>
@@ -99,4 +100,8 @@ static inline void syscall_set_arguments(struct task_struct *task,
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
 asmlinkage void do_syscall_trace_leave(struct pt_regs *regs);
 
+static inline int syscall_get_arch(void)
+{
+	return AUDIT_ARCH_MICROBLAZE;
+}
 #endif /* __ASM_MICROBLAZE_SYSCALL_H */
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 17960fe7a8ce..93b3b86c293c 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -129,7 +129,7 @@ extern const unsigned long sysn32_call_table[];
 
 static inline int syscall_get_arch(void)
 {
-	int arch = EM_MIPS;
+	int arch = AUDIT_ARCH_MIPS;
 #ifdef CONFIG_64BIT
 	if (!test_thread_flag(TIF_32BIT_REGS))
 		arch |= __AUDIT_ARCH_64BIT;
diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h
index b752bb67891d..2db9f1cf0694 100644
--- a/arch/openrisc/include/asm/syscall.h
+++ b/arch/openrisc/include/asm/syscall.h
@@ -19,6 +19,7 @@
 #ifndef __ASM_OPENRISC_SYSCALL_H__
 #define __ASM_OPENRISC_SYSCALL_H__
 
+#include <uapi/linux/audit.h>
 #include <linux/err.h>
 #include <linux/sched.h>
 
@@ -71,4 +72,8 @@ syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
 	memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
 }
 
+static inline int syscall_get_arch(void)
+{
+	return AUDIT_ARCH_OPENRISC;
+}
 #endif
diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h
index 8bdfd2c8c39f..a5eba95d87fe 100644
--- a/arch/parisc/include/asm/syscall.h
+++ b/arch/parisc/include/asm/syscall.h
@@ -3,6 +3,8 @@
 #ifndef _ASM_PARISC_SYSCALL_H_
 #define _ASM_PARISC_SYSCALL_H_
 
+#include <uapi/linux/audit.h>
+#include <linux/compat.h>
 #include <linux/err.h>
 #include <asm/ptrace.h>
 
@@ -37,4 +39,13 @@ static inline void syscall_get_arguments(struct task_struct *tsk,
 	}
 }
 
+static inline int syscall_get_arch(void)
+{
+	int arch = AUDIT_ARCH_PARISC;
+#ifdef CONFIG_64BIT
+	if (!is_compat_task())
+		arch = AUDIT_ARCH_PARISC64;
+#endif
+	return arch;
+}
 #endif /*_ASM_PARISC_SYSCALL_H_*/
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index b54b2add07be..427154444f6d 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -13,6 +13,8 @@
 #ifndef _ASM_SYSCALL_H
 #define _ASM_SYSCALL_H	1
 
+#include <uapi/linux/audit.h>
+#include <linux/compat.h>
 #include <linux/sched.h>
 
 /* ftrace syscalls requires exporting the sys_call_table */
@@ -86,4 +88,14 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
 }
 
+static inline int syscall_get_arch(void)
+{
+	int arch = AUDIT_ARCH_PPC;
+
+#ifdef CONFIG_PPC64
+	if (!is_32bit_task())
+		arch = AUDIT_ARCH_PPC64;
+#endif
+	return arch;
+}
 #endif	/* _ASM_SYSCALL_H */
diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h
index 025a02ad2e31..fed3d511b108 100644
--- a/arch/sparc/include/asm/syscall.h
+++ b/arch/sparc/include/asm/syscall.h
@@ -1,9 +1,11 @@
 #ifndef __ASM_SPARC_SYSCALL_H
 #define __ASM_SPARC_SYSCALL_H
 
+#include <uapi/linux/audit.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <asm/ptrace.h>
+#include <asm/thread_info.h>
 
 /*
  * The syscall table always contains 32 bit pointers since we know that the
@@ -124,4 +126,10 @@ static inline void syscall_set_arguments(struct task_struct *task,
 		regs->u_regs[UREG_I0 + i + j] = args[j];
 }
 
+static inline int syscall_get_arch(void)
+{
+	return test_thread_flag(TIF_32BIT) ? AUDIT_ARCH_SPARC
+					   : AUDIT_ARCH_SPARC64;
+}
+
 #endif /* __ASM_SPARC_SYSCALL_H */
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index df71b1d2cbb8..4d100c841c80 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -351,6 +351,7 @@ enum {
 #define AUDIT_ARCH_IA64		(EM_IA_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_M32R		(EM_M32R)
 #define AUDIT_ARCH_M68K		(EM_68K)
+#define AUDIT_ARCH_MICROBLAZE	(EM_MICROBLAZE)
 #define AUDIT_ARCH_MIPS		(EM_MIPS)
 #define AUDIT_ARCH_MIPSEL	(EM_MIPS|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_MIPS64	(EM_MIPS|__AUDIT_ARCH_64BIT)
-- 
cgit v1.2.3


From 91397401bb5072f71e8ce8744ad0bdec3e875a91 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Tue, 11 Mar 2014 13:29:28 -0400
Subject: ARCH: AUDIT: audit_syscall_entry() should not require the arch

We have a function where the arch can be queried, syscall_get_arch().
So rather than have every single piece of arch specific code use and/or
duplicate syscall_get_arch(), just have the audit code use the
syscall_get_arch() code.

Based-on-patch-by: Richard Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Cc: linux-alpha@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-ia64@vger.kernel.org
Cc: microblaze-uclinux@itee.uq.edu.au
Cc: linux-mips@linux-mips.org
Cc: linux@lists.openrisc.net
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: user-mode-linux-devel@lists.sourceforge.net
Cc: linux-xtensa@linux-xtensa.org
Cc: x86@kernel.org
---
 arch/alpha/kernel/ptrace.c      |  2 +-
 arch/arm/kernel/ptrace.c        |  4 ++--
 arch/ia64/kernel/ptrace.c       |  2 +-
 arch/microblaze/kernel/ptrace.c |  3 +--
 arch/mips/kernel/ptrace.c       |  4 +---
 arch/openrisc/kernel/ptrace.c   |  3 +--
 arch/parisc/kernel/ptrace.c     |  9 +++------
 arch/powerpc/kernel/ptrace.c    |  7 ++-----
 arch/s390/kernel/ptrace.c       |  4 +---
 arch/sh/kernel/ptrace_32.c      | 14 +-------------
 arch/sh/kernel/ptrace_64.c      | 17 +----------------
 arch/sparc/kernel/ptrace_64.c   |  9 ++-------
 arch/um/kernel/ptrace.c         |  3 +--
 arch/x86/kernel/ptrace.c        |  8 ++------
 arch/x86/um/asm/ptrace.h        |  4 ----
 arch/xtensa/kernel/ptrace.c     |  2 +-
 include/linux/audit.h           |  7 ++++---
 17 files changed, 25 insertions(+), 77 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/ptrace.c b/arch/alpha/kernel/ptrace.c
index 86d835157b54..d9ee81769899 100644
--- a/arch/alpha/kernel/ptrace.c
+++ b/arch/alpha/kernel/ptrace.c
@@ -321,7 +321,7 @@ asmlinkage unsigned long syscall_trace_enter(void)
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
 	    tracehook_report_syscall_entry(current_pt_regs()))
 		ret = -1UL;
-	audit_syscall_entry(AUDIT_ARCH_ALPHA, regs->r0, regs->r16, regs->r17, regs->r18, regs->r19);
+	audit_syscall_entry(regs->r0, regs->r16, regs->r17, regs->r18, regs->r19);
 	return ret ?: current_pt_regs()->r0;
 }
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 0c27ed6f3f23..6af95986fbf7 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -944,8 +944,8 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, scno);
 
-	audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0, regs->ARM_r1,
-			    regs->ARM_r2, regs->ARM_r3);
+	audit_syscall_entry(scno, regs->ARM_r0, regs->ARM_r1, regs->ARM_r2,
+			    regs->ARM_r3);
 
 	return scno;
 }
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index b7a5fffe0924..6f54d511cc50 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -1219,7 +1219,7 @@ syscall_trace_enter (long arg0, long arg1, long arg2, long arg3,
 		ia64_sync_krbs();
 
 
-	audit_syscall_entry(AUDIT_ARCH_IA64, regs.r15, arg0, arg1, arg2, arg3);
+	audit_syscall_entry(regs.r15, arg0, arg1, arg2, arg3);
 
 	return 0;
 }
diff --git a/arch/microblaze/kernel/ptrace.c b/arch/microblaze/kernel/ptrace.c
index 39cf50841f6d..bb10637ce688 100644
--- a/arch/microblaze/kernel/ptrace.c
+++ b/arch/microblaze/kernel/ptrace.c
@@ -147,8 +147,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 		 */
 		ret = -1L;
 
-	audit_syscall_entry(EM_MICROBLAZE, regs->r12, regs->r5, regs->r6,
-			    regs->r7, regs->r8);
+	audit_syscall_entry(regs->r12, regs->r5, regs->r6, regs->r7, regs->r8);
 
 	return ret ?: regs->r12;
 }
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index f639ccd5060c..d8a76f97a053 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -649,9 +649,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[2]);
 
-	audit_syscall_entry(syscall_get_arch(),
-			    syscall,
-			    regs->regs[4], regs->regs[5],
+	audit_syscall_entry(syscall, regs->regs[4], regs->regs[5],
 			    regs->regs[6], regs->regs[7]);
 	return syscall;
 }
diff --git a/arch/openrisc/kernel/ptrace.c b/arch/openrisc/kernel/ptrace.c
index 71a2a0c34c65..4f59fa4e34e5 100644
--- a/arch/openrisc/kernel/ptrace.c
+++ b/arch/openrisc/kernel/ptrace.c
@@ -187,8 +187,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 		 */
 		ret = -1L;
 
-	audit_syscall_entry(AUDIT_ARCH_OPENRISC, regs->gpr[11],
-			    regs->gpr[3], regs->gpr[4],
+	audit_syscall_entry(regs->gpr[11], regs->gpr[3], regs->gpr[4],
 			    regs->gpr[5], regs->gpr[6]);
 
 	return ret ? : regs->gpr[11];
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index e842ee233db4..74814577e4b8 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -276,14 +276,11 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 
 #ifdef CONFIG_64BIT
 	if (!is_compat_task())
-		audit_syscall_entry(AUDIT_ARCH_PARISC64,
-			regs->gr[20],
-			regs->gr[26], regs->gr[25],
-			regs->gr[24], regs->gr[23]);
+		audit_syscall_entry(regs->gr[20], regs->gr[26], regs->gr[25],
+				    regs->gr[24], regs->gr[23]);
 	else
 #endif
-		audit_syscall_entry(AUDIT_ARCH_PARISC,
-			regs->gr[20] & 0xffffffff,
+		audit_syscall_entry(regs->gr[20] & 0xffffffff,
 			regs->gr[26] & 0xffffffff,
 			regs->gr[25] & 0xffffffff,
 			regs->gr[24] & 0xffffffff,
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 2e3d2bf536c5..524a943a33bb 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1788,14 +1788,11 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 
 #ifdef CONFIG_PPC64
 	if (!is_32bit_task())
-		audit_syscall_entry(AUDIT_ARCH_PPC64,
-				    regs->gpr[0],
-				    regs->gpr[3], regs->gpr[4],
+		audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
 				    regs->gpr[5], regs->gpr[6]);
 	else
 #endif
-		audit_syscall_entry(AUDIT_ARCH_PPC,
-				    regs->gpr[0],
+		audit_syscall_entry(regs->gpr[0],
 				    regs->gpr[3] & 0xffffffff,
 				    regs->gpr[4] & 0xffffffff,
 				    regs->gpr[5] & 0xffffffff,
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 5dc7ad9e2fbf..910f253b22bc 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -828,9 +828,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->gprs[2]);
 
-	audit_syscall_entry(is_compat_task() ?
-				AUDIT_ARCH_S390 : AUDIT_ARCH_S390X,
-			    regs->gprs[2], regs->orig_gpr2,
+	audit_syscall_entry(regs->gprs[2], regs->orig_gpr2,
 			    regs->gprs[3], regs->gprs[4],
 			    regs->gprs[5]);
 out:
diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c
index 668c81631c08..c1a6b89bfe70 100644
--- a/arch/sh/kernel/ptrace_32.c
+++ b/arch/sh/kernel/ptrace_32.c
@@ -484,17 +484,6 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ret;
 }
 
-static inline int audit_arch(void)
-{
-	int arch = EM_SH;
-
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-	arch |= __AUDIT_ARCH_LE;
-#endif
-
-	return arch;
-}
-
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
@@ -513,8 +502,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[0]);
 
-	audit_syscall_entry(audit_arch(), regs->regs[3],
-			    regs->regs[4], regs->regs[5],
+	audit_syscall_entry(regs->regs[3], regs->regs[4], regs->regs[5],
 			    regs->regs[6], regs->regs[7]);
 
 	return ret ?: regs->regs[0];
diff --git a/arch/sh/kernel/ptrace_64.c b/arch/sh/kernel/ptrace_64.c
index af90339dadcd..5cea973a65b2 100644
--- a/arch/sh/kernel/ptrace_64.c
+++ b/arch/sh/kernel/ptrace_64.c
@@ -504,20 +504,6 @@ asmlinkage int sh64_ptrace(long request, long pid,
 	return sys_ptrace(request, pid, addr, data);
 }
 
-static inline int audit_arch(void)
-{
-	int arch = EM_SH;
-
-#ifdef CONFIG_64BIT
-	arch |= __AUDIT_ARCH_64BIT;
-#endif
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-	arch |= __AUDIT_ARCH_LE;
-#endif
-
-	return arch;
-}
-
 asmlinkage long long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	long long ret = 0;
@@ -536,8 +522,7 @@ asmlinkage long long do_syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[9]);
 
-	audit_syscall_entry(audit_arch(), regs->regs[1],
-			    regs->regs[2], regs->regs[3],
+	audit_syscall_entry(regs->regs[1], regs->regs[2], regs->regs[3],
 			    regs->regs[4], regs->regs[5]);
 
 	return ret ?: regs->regs[9];
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index c13c9f25d83a..9ddc4928a089 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -1076,13 +1076,8 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->u_regs[UREG_G1]);
 
-	audit_syscall_entry((test_thread_flag(TIF_32BIT) ?
-			     AUDIT_ARCH_SPARC :
-			     AUDIT_ARCH_SPARC64),
-			    regs->u_regs[UREG_G1],
-			    regs->u_regs[UREG_I0],
-			    regs->u_regs[UREG_I1],
-			    regs->u_regs[UREG_I2],
+	audit_syscall_entry(regs->u_regs[UREG_G1], regs->u_regs[UREG_I0],
+			    regs->u_regs[UREG_I1], regs->u_regs[UREG_I2],
 			    regs->u_regs[UREG_I3]);
 
 	return ret;
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index 694d551c8899..62435ef003d9 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -165,8 +165,7 @@ static void send_sigtrap(struct task_struct *tsk, struct uml_pt_regs *regs,
  */
 void syscall_trace_enter(struct pt_regs *regs)
 {
-	audit_syscall_entry(HOST_AUDIT_ARCH,
-			    UPT_SYSCALL_NR(&regs->regs),
+	audit_syscall_entry(UPT_SYSCALL_NR(&regs->regs),
 			    UPT_SYSCALL_ARG1(&regs->regs),
 			    UPT_SYSCALL_ARG2(&regs->regs),
 			    UPT_SYSCALL_ARG3(&regs->regs),
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 678c0ada3b3c..eb1c87f0b03b 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1488,15 +1488,11 @@ long syscall_trace_enter(struct pt_regs *regs)
 		trace_sys_enter(regs, regs->orig_ax);
 
 	if (IS_IA32)
-		audit_syscall_entry(AUDIT_ARCH_I386,
-				    regs->orig_ax,
-				    regs->bx, regs->cx,
+		audit_syscall_entry(regs->orig_ax, regs->bx, regs->cx,
 				    regs->dx, regs->si);
 #ifdef CONFIG_X86_64
 	else
-		audit_syscall_entry(AUDIT_ARCH_X86_64,
-				    regs->orig_ax,
-				    regs->di, regs->si,
+		audit_syscall_entry(regs->orig_ax, regs->di, regs->si,
 				    regs->dx, regs->r10);
 #endif
 
diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h
index 54f8102ccde5..e59eef20647b 100644
--- a/arch/x86/um/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace.h
@@ -47,8 +47,6 @@ struct user_desc;
 
 #ifdef CONFIG_X86_32
 
-#define HOST_AUDIT_ARCH AUDIT_ARCH_I386
-
 extern int ptrace_get_thread_area(struct task_struct *child, int idx,
                                   struct user_desc __user *user_desc);
 
@@ -57,8 +55,6 @@ extern int ptrace_set_thread_area(struct task_struct *child, int idx,
 
 #else
 
-#define HOST_AUDIT_ARCH AUDIT_ARCH_X86_64
-
 #define PT_REGS_R8(r) UPT_R8(&(r)->regs)
 #define PT_REGS_R9(r) UPT_R9(&(r)->regs)
 #define PT_REGS_R10(r) UPT_R10(&(r)->regs)
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index 562fac664751..4d54b481123b 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -342,7 +342,7 @@ void do_syscall_trace_enter(struct pt_regs *regs)
 		do_syscall_trace();
 
 #if 0
-	audit_syscall_entry(current, AUDIT_ARCH_XTENSA..);
+	audit_syscall_entry(...);
 #endif
 }
 
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 22cfddb75566..bb1c3ab611bf 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <linux/ptrace.h>
 #include <uapi/linux/audit.h>
+#include <asm/syscall.h>
 
 struct audit_sig_info {
 	uid_t		uid;
@@ -141,12 +142,12 @@ static inline void audit_free(struct task_struct *task)
 	if (unlikely(task->audit_context))
 		__audit_free(task);
 }
-static inline void audit_syscall_entry(int arch, int major, unsigned long a0,
+static inline void audit_syscall_entry(int major, unsigned long a0,
 				       unsigned long a1, unsigned long a2,
 				       unsigned long a3)
 {
 	if (unlikely(current->audit_context))
-		__audit_syscall_entry(arch, major, a0, a1, a2, a3);
+		__audit_syscall_entry(syscall_get_arch(), major, a0, a1, a2, a3);
 }
 static inline void audit_syscall_exit(void *pt_regs)
 {
@@ -322,7 +323,7 @@ static inline int audit_alloc(struct task_struct *task)
 }
 static inline void audit_free(struct task_struct *task)
 { }
-static inline void audit_syscall_entry(int arch, int major, unsigned long a0,
+static inline void audit_syscall_entry(int major, unsigned long a0,
 				       unsigned long a1, unsigned long a2,
 				       unsigned long a3)
 { }
-- 
cgit v1.2.3


From a9ebe0b98896b276a3a1664da5f40d3b7c92f316 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Tue, 22 Apr 2014 11:46:16 -0400
Subject: audit: fix build error when asm/syscall.h does not exist

avr32 does not have an asm/syscall.h file.  We need the
syscall_get_arch() definition from that file for all arch's which
support CONFIG_AUDITSYSCALL.  Obviously avr32 is not one of those
arch's.  Move the include inside the CONFIG_AUDITSYSCALL such that we
only do the include if we need the results.

When the syscall_get_arch() call is moved inside __audit_syscall_entry()
this include can be dropped entirely.  But that is going to require some
assembly changes on x86* in a patch that is not ready for the tree...

Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/audit.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index bb1c3ab611bf..783157b289e8 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -26,7 +26,6 @@
 #include <linux/sched.h>
 #include <linux/ptrace.h>
 #include <uapi/linux/audit.h>
-#include <asm/syscall.h>
 
 struct audit_sig_info {
 	uid_t		uid;
@@ -110,6 +109,8 @@ extern void audit_log_session_info(struct audit_buffer *ab);
 #endif
 
 #ifdef CONFIG_AUDITSYSCALL
+#include <asm/syscall.h> /* for syscall_get_arch() */
+
 /* These are defined in auditsc.c */
 				/* Public API */
 extern int  audit_alloc(struct task_struct *task);
-- 
cgit v1.2.3


From b4f0d3755c5e9cc86292d5fd78261903b4f23d4a Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Tue, 4 Mar 2014 10:38:06 -0500
Subject: audit: x86: drop arch from __audit_syscall_entry() interface

Since the arch is found locally in __audit_syscall_entry(), there is no need to
pass it in as a parameter.  Delete it from the parameter list.

x86* was the only arch to call __audit_syscall_entry() directly and did so from
assembly code.

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-audit@redhat.com
Signed-off-by: Eric Paris <eparis@redhat.com>

---

As this patch relies on changes in the audit tree, I think it
appropriate to send it through my tree rather than the x86 tree.
---
 arch/x86/ia32/ia32entry.S  | 12 ++++++------
 arch/x86/kernel/entry_32.S | 11 +++++------
 arch/x86/kernel/entry_64.S | 11 +++++------
 include/linux/audit.h      |  5 ++---
 kernel/auditsc.c           |  6 ++----
 5 files changed, 20 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 4299eb05023c..f5bdd2881815 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -186,12 +186,12 @@ sysexit_from_sys_call:
 
 #ifdef CONFIG_AUDITSYSCALL
 	.macro auditsys_entry_common
-	movl %esi,%r9d			/* 6th arg: 4th syscall arg */
-	movl %edx,%r8d			/* 5th arg: 3rd syscall arg */
-	/* (already in %ecx)		   4th arg: 2nd syscall arg */
-	movl %ebx,%edx			/* 3rd arg: 1st syscall arg */
-	movl %eax,%esi			/* 2nd arg: syscall number */
-	movl $AUDIT_ARCH_I386,%edi	/* 1st arg: audit arch */
+	movl %esi,%r8d			/* 5th arg: 4th syscall arg */
+	movl %ecx,%r9d			/*swap with edx*/
+	movl %edx,%ecx			/* 4th arg: 3rd syscall arg */
+	movl %r9d,%edx			/* 3rd arg: 2nd syscall arg */
+	movl %ebx,%esi			/* 2nd arg: 1st syscall arg */
+	movl %eax,%edi			/* 1st arg: syscall number */
 	call __audit_syscall_entry
 	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall number */
 	cmpq $(IA32_NR_syscalls-1),%rax
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 0d0c9d4ab6d5..f9e3fabc8716 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -449,12 +449,11 @@ sysenter_audit:
 	jnz syscall_trace_entry
 	addl $4,%esp
 	CFI_ADJUST_CFA_OFFSET -4
-	/* %esi already in 8(%esp)	   6th arg: 4th syscall arg */
-	/* %edx already in 4(%esp)	   5th arg: 3rd syscall arg */
-	/* %ecx already in 0(%esp)	   4th arg: 2nd syscall arg */
-	movl %ebx,%ecx			/* 3rd arg: 1st syscall arg */
-	movl %eax,%edx			/* 2nd arg: syscall number */
-	movl $AUDIT_ARCH_I386,%eax	/* 1st arg: audit arch */
+	movl %esi,4(%esp)		/* 5th arg: 4th syscall arg */
+	movl %edx,(%esp)		/* 4th arg: 3rd syscall arg */
+	/* %ecx already in %ecx		   3rd arg: 2nd syscall arg */
+	movl %ebx,%edx			/* 2nd arg: 1st syscall arg */
+	/* %eax already in %eax		   1st arg: syscall number */
 	call __audit_syscall_entry
 	pushl_cfi %ebx
 	movl PT_EAX(%esp),%eax		/* reload syscall number */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index c844f0816ab8..5e8cb2ad9fb3 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -488,12 +488,11 @@ badsys:
 	 * jump back to the normal fast path.
 	 */
 auditsys:
-	movq %r10,%r9			/* 6th arg: 4th syscall arg */
-	movq %rdx,%r8			/* 5th arg: 3rd syscall arg */
-	movq %rsi,%rcx			/* 4th arg: 2nd syscall arg */
-	movq %rdi,%rdx			/* 3rd arg: 1st syscall arg */
-	movq %rax,%rsi			/* 2nd arg: syscall number */
-	movl $AUDIT_ARCH_X86_64,%edi	/* 1st arg: audit arch */
+	movq %r10,%r8			/* 5th arg: 4th syscall arg */
+	movq %rdx,%rcx			/* 4th arg: 3rd syscall arg */
+	movq %rsi,%rdx			/* 3rd arg: 2nd syscall arg */
+	movq %rdi,%rsi			/* 2nd arg: 1st syscall arg */
+	movq %rax,%rdi			/* 1st arg: syscall number */
 	call __audit_syscall_entry
 	LOAD_ARGS 0		/* reload call-clobbered registers */
 	jmp system_call_fastpath
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 783157b289e8..1ae00891aff9 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -115,8 +115,7 @@ extern void audit_log_session_info(struct audit_buffer *ab);
 				/* Public API */
 extern int  audit_alloc(struct task_struct *task);
 extern void __audit_free(struct task_struct *task);
-extern void __audit_syscall_entry(int arch,
-				  int major, unsigned long a0, unsigned long a1,
+extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1,
 				  unsigned long a2, unsigned long a3);
 extern void __audit_syscall_exit(int ret_success, long ret_value);
 extern struct filename *__audit_reusename(const __user char *uptr);
@@ -148,7 +147,7 @@ static inline void audit_syscall_entry(int major, unsigned long a0,
 				       unsigned long a3)
 {
 	if (unlikely(current->audit_context))
-		__audit_syscall_entry(syscall_get_arch(), major, a0, a1, a2, a3);
+		__audit_syscall_entry(major, a0, a1, a2, a3);
 }
 static inline void audit_syscall_exit(void *pt_regs)
 {
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 9f03ac205e1f..4e17443fd1ef 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1506,7 +1506,6 @@ void __audit_free(struct task_struct *tsk)
 
 /**
  * audit_syscall_entry - fill in an audit record at syscall entry
- * @arch: architecture type
  * @major: major syscall type (function)
  * @a1: additional syscall register 1
  * @a2: additional syscall register 2
@@ -1521,9 +1520,8 @@ void __audit_free(struct task_struct *tsk)
  * will only be written if another part of the kernel requests that it
  * be written).
  */
-void __audit_syscall_entry(int arch, int major,
-			 unsigned long a1, unsigned long a2,
-			 unsigned long a3, unsigned long a4)
+void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
+			   unsigned long a3, unsigned long a4)
 {
 	struct task_struct *tsk = current;
 	struct audit_context *context = tsk->audit_context;
-- 
cgit v1.2.3


From 219ca39427bf6c46c4e1473493e33bc00635e99b Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Wed, 26 Mar 2014 07:26:47 -0400
Subject: audit: use union for audit_field values since they are mutually
 exclusive

Since only one of val, uid, gid and lsm* are used at any given time, combine
them to reduce the size of the struct audit_field.

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
---
 include/linux/audit.h | 14 +++++++++-----
 kernel/auditfilter.c  | 29 ++++++++++++++++++++---------
 2 files changed, 29 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 1ae00891aff9..36dffeccebdb 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -66,12 +66,16 @@ struct audit_krule {
 
 struct audit_field {
 	u32				type;
-	u32				val;
-	kuid_t				uid;
-	kgid_t				gid;
+	union {
+		u32			val;
+		kuid_t			uid;
+		kgid_t			gid;
+		struct {
+			char		*lsm_str;
+			void		*lsm_rule;
+		};
+	};
 	u32				op;
-	char				*lsm_str;
-	void				*lsm_rule;
 };
 
 extern int is_audit_feature_set(int which);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index b65a138250b8..40ed9813d4b2 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -71,6 +71,24 @@ static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = {
 
 DEFINE_MUTEX(audit_filter_mutex);
 
+static void audit_free_lsm_field(struct audit_field *f)
+{
+	switch (f->type) {
+	case AUDIT_SUBJ_USER:
+	case AUDIT_SUBJ_ROLE:
+	case AUDIT_SUBJ_TYPE:
+	case AUDIT_SUBJ_SEN:
+	case AUDIT_SUBJ_CLR:
+	case AUDIT_OBJ_USER:
+	case AUDIT_OBJ_ROLE:
+	case AUDIT_OBJ_TYPE:
+	case AUDIT_OBJ_LEV_LOW:
+	case AUDIT_OBJ_LEV_HIGH:
+		kfree(f->lsm_str);
+		security_audit_rule_free(f->lsm_rule);
+	}
+}
+
 static inline void audit_free_rule(struct audit_entry *e)
 {
 	int i;
@@ -80,11 +98,8 @@ static inline void audit_free_rule(struct audit_entry *e)
 	if (erule->watch)
 		audit_put_watch(erule->watch);
 	if (erule->fields)
-		for (i = 0; i < erule->field_count; i++) {
-			struct audit_field *f = &erule->fields[i];
-			kfree(f->lsm_str);
-			security_audit_rule_free(f->lsm_rule);
-		}
+		for (i = 0; i < erule->field_count; i++)
+			audit_free_lsm_field(&erule->fields[i]);
 	kfree(erule->fields);
 	kfree(erule->filterkey);
 	kfree(e);
@@ -422,10 +437,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 
 		f->type = data->fields[i];
 		f->val = data->values[i];
-		f->uid = INVALID_UID;
-		f->gid = INVALID_GID;
-		f->lsm_str = NULL;
-		f->lsm_rule = NULL;
 
 		/* Support legacy tests for a valid loginuid */
 		if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
-- 
cgit v1.2.3


From 9e87f9a9c4c4754508b2c2638fbde9e10c7a103b Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sat, 13 Sep 2014 10:28:49 +0200
Subject: NFC: nci: Add support for proprietary RF Protocols

In NFC Forum NCI specification, some RF Protocol values are
reserved for proprietary use (from 0x80 to 0xfe).
Some CLF vendor may need to use one value within this range
for specific technology.
Furthermore, some CLF may not becompliant with NFC Froum NCI
specification 2.0 and therefore will not support RF Protocol
value 0x06 for PROTOCOL_T5T as mention in a draft specification
and in a recent push.

Adding get_rf_protocol handle to the nci_ops structure will
help to set the correct technology to target.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/st21nfcb/st21nfcb.c | 10 ++++++++++
 include/net/nfc/nci_core.h      |  9 +++++----
 net/nfc/nci/ntf.c               |  9 ++++++++-
 3 files changed, 23 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/nfc/st21nfcb/st21nfcb.c b/drivers/nfc/st21nfcb/st21nfcb.c
index 90d37156169e..e72dae816e72 100644
--- a/drivers/nfc/st21nfcb/st21nfcb.c
+++ b/drivers/nfc/st21nfcb/st21nfcb.c
@@ -25,6 +25,8 @@
 
 #define DRIVER_DESC "NCI NFC driver for ST21NFCB"
 
+#define ST21NFCB_NCI1_X_PROPRIETARY_ISO15693 0x83
+
 static int st21nfcb_nci_open(struct nci_dev *ndev)
 {
 	struct st21nfcb_nci_info *info = nci_get_drvdata(ndev);
@@ -64,10 +66,18 @@ static int st21nfcb_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
 	return ndlc_send(info->ndlc, skb);
 }
 
+static __u32 st21nfcb_nci_get_rfprotocol(struct nci_dev *ndev,
+					 __u8 rf_protocol)
+{
+	return rf_protocol == ST21NFCB_NCI1_X_PROPRIETARY_ISO15693 ?
+		NFC_PROTO_ISO15693_MASK : 0;
+}
+
 static struct nci_ops st21nfcb_nci_ops = {
 	.open = st21nfcb_nci_open,
 	.close = st21nfcb_nci_close,
 	.send = st21nfcb_nci_send,
+	.get_rfprotocol = st21nfcb_nci_get_rfprotocol,
 };
 
 int st21nfcb_nci_probe(struct llt_ndlc *ndlc, int phy_headroom,
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 1f9a0f5272fe..75d10e625c49 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -64,10 +64,11 @@ enum nci_state {
 struct nci_dev;
 
 struct nci_ops {
-	int (*open)(struct nci_dev *ndev);
-	int (*close)(struct nci_dev *ndev);
-	int (*send)(struct nci_dev *ndev, struct sk_buff *skb);
-	int (*setup)(struct nci_dev *ndev);
+	int   (*open)(struct nci_dev *ndev);
+	int   (*close)(struct nci_dev *ndev);
+	int   (*send)(struct nci_dev *ndev, struct sk_buff *skb);
+	int   (*setup)(struct nci_dev *ndev);
+	__u32 (*get_rfprotocol)(struct nci_dev *ndev, __u8 rf_protocol);
 };
 
 #define NCI_MAX_SUPPORTED_RF_INTERFACES		4
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 25e44cebd60a..205b35f666db 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -167,6 +167,13 @@ static __u8 *nci_extract_rf_params_nfcv_passive_poll(struct nci_dev *ndev,
 	return data;
 }
 
+__u32 nci_get_prop_rf_protocol(struct nci_dev *ndev, __u8 rf_protocol)
+{
+	if (ndev->ops->get_rfprotocol)
+		return ndev->ops->get_rfprotocol(ndev, rf_protocol);
+	return 0;
+}
+
 static int nci_add_new_protocol(struct nci_dev *ndev,
 				struct nfc_target *target,
 				__u8 rf_protocol,
@@ -195,7 +202,7 @@ static int nci_add_new_protocol(struct nci_dev *ndev,
 	else if (rf_protocol == NCI_RF_PROTOCOL_T5T)
 		protocol = NFC_PROTO_ISO15693_MASK;
 	else
-		protocol = 0;
+		protocol = nci_get_prop_rf_protocol(ndev, rf_protocol);
 
 	if (!(protocol & ndev->poll_prots)) {
 		pr_err("the target found does not have the desired protocol\n");
-- 
cgit v1.2.3


From 9908fb654088e50d7d528f74898c5e5ebbd0fb68 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 22 Sep 2014 09:30:11 -0700
Subject: drm: change drm_err return type to void

The return value is not used by callers of this function
nor by uses of the DRM_ERROR macro so change the function
to return void.

Signed-off-by: Joe Perches <joe@perches.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_drv.c | 7 ++-----
 include/drm/drmP.h        | 2 +-
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 6a119026a76b..8889f8ec50ab 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -56,22 +56,19 @@ static struct idr drm_minors_idr;
 struct class *drm_class;
 static struct dentry *drm_debugfs_root;
 
-int drm_err(const char *func, const char *format, ...)
+void drm_err(const char *func, const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, format);
 
 	vaf.fmt = format;
 	vaf.va = &args;
 
-	r = printk(KERN_ERR "[" DRM_NAME ":%s] *ERROR* %pV", func, &vaf);
+	printk(KERN_ERR "[" DRM_NAME ":%s] *ERROR* %pV", func, &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(drm_err);
 
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 5c60d384b37b..2163ccbee50f 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -124,7 +124,7 @@ extern __printf(2, 3)
 void drm_ut_debug_printk(const char *function_name,
 			 const char *format, ...);
 extern __printf(2, 3)
-int drm_err(const char *func, const char *format, ...);
+void drm_err(const char *func, const char *format, ...);
 
 /***********************************************************************/
 /** \name DRM template customization defaults */
-- 
cgit v1.2.3


From bfbf3c851ce53b914fe98d60ea3fe3fc1ab75b96 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 23 Sep 2014 15:46:49 +0200
Subject: drm: move drm_mmap to <drm/drm_legacy.h>

Now that we've removed the copypasted users in gem/ttm we can
relegate the legacy buffer mapping support to where it belongs.
Also give it the proper drm_legacy_ prefix.

While at it statify drm_mmap_locked, somehow I've missed that in my
previous header rework.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_internal.h      | 1 -
 drivers/gpu/drm/drm_vm.c            | 6 +++---
 drivers/gpu/drm/i810/i810_drv.c     | 2 +-
 drivers/gpu/drm/mga/mga_drv.c       | 2 +-
 drivers/gpu/drm/r128/r128_drv.c     | 2 +-
 drivers/gpu/drm/radeon/radeon_drv.c | 2 +-
 drivers/gpu/drm/savage/savage_drv.c | 2 +-
 drivers/gpu/drm/sis/sis_drv.c       | 2 +-
 drivers/gpu/drm/tdfx/tdfx_drv.c     | 3 ++-
 drivers/gpu/drm/via/via_drv.c       | 2 +-
 include/drm/drmP.h                  | 1 -
 include/drm/drm_legacy.h            | 1 +
 12 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 7e459bf38c26..d27faae45f1b 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -37,7 +37,6 @@ int drm_irq_by_busid(struct drm_device *dev, void *data,
 
 /* drm_vm.c */
 int drm_vma_info(struct seq_file *m, void *data);
-int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma);
 void drm_vm_close_locked(struct drm_device *dev, struct vm_area_struct *vma);
 
 /* drm_prime.c */
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index b2b231cda139..28739d401596 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -537,7 +537,7 @@ static resource_size_t drm_core_get_reg_ofs(struct drm_device *dev)
  * according to the mapping type and remaps the pages. Finally sets the file
  * pointer and calls vm_open().
  */
-int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma)
+static int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma)
 {
 	struct drm_file *priv = filp->private_data;
 	struct drm_device *dev = priv->minor->dev;
@@ -651,7 +651,7 @@ int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma)
 	return 0;
 }
 
-int drm_mmap(struct file *filp, struct vm_area_struct *vma)
+int drm_legacy_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct drm_file *priv = filp->private_data;
 	struct drm_device *dev = priv->minor->dev;
@@ -666,7 +666,7 @@ int drm_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_mmap);
+EXPORT_SYMBOL(drm_legacy_mmap);
 
 void drm_legacy_vma_flush(struct drm_device *dev)
 {
diff --git a/drivers/gpu/drm/i810/i810_drv.c b/drivers/gpu/drm/i810/i810_drv.c
index 6cb08a1c6b62..44f4a131c8dd 100644
--- a/drivers/gpu/drm/i810/i810_drv.c
+++ b/drivers/gpu/drm/i810/i810_drv.c
@@ -47,7 +47,7 @@ static const struct file_operations i810_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
diff --git a/drivers/gpu/drm/mga/mga_drv.c b/drivers/gpu/drm/mga/mga_drv.c
index cb5c71f4b28e..5e2f131a6a72 100644
--- a/drivers/gpu/drm/mga/mga_drv.c
+++ b/drivers/gpu/drm/mga/mga_drv.c
@@ -48,7 +48,7 @@ static const struct file_operations mga_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = mga_compat_ioctl,
diff --git a/drivers/gpu/drm/r128/r128_drv.c b/drivers/gpu/drm/r128/r128_drv.c
index 4a59370eb580..c57b4de63caf 100644
--- a/drivers/gpu/drm/r128/r128_drv.c
+++ b/drivers/gpu/drm/r128/r128_drv.c
@@ -46,7 +46,7 @@ static const struct file_operations r128_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = r128_compat_ioctl,
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index ec7e963d9bf7..dd082049fd5b 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -308,7 +308,7 @@ static const struct file_operations radeon_driver_old_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
 #ifdef CONFIG_COMPAT
diff --git a/drivers/gpu/drm/savage/savage_drv.c b/drivers/gpu/drm/savage/savage_drv.c
index 1b09d2182037..21aed1febeb4 100644
--- a/drivers/gpu/drm/savage/savage_drv.c
+++ b/drivers/gpu/drm/savage/savage_drv.c
@@ -40,7 +40,7 @@ static const struct file_operations savage_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
diff --git a/drivers/gpu/drm/sis/sis_drv.c b/drivers/gpu/drm/sis/sis_drv.c
index 54858e6fedaf..79bce76cb8f7 100644
--- a/drivers/gpu/drm/sis/sis_drv.c
+++ b/drivers/gpu/drm/sis/sis_drv.c
@@ -70,7 +70,7 @@ static const struct file_operations sis_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
diff --git a/drivers/gpu/drm/tdfx/tdfx_drv.c b/drivers/gpu/drm/tdfx/tdfx_drv.c
index df533ff999a4..fab5ebcb0fef 100644
--- a/drivers/gpu/drm/tdfx/tdfx_drv.c
+++ b/drivers/gpu/drm/tdfx/tdfx_drv.c
@@ -36,6 +36,7 @@
 #include "tdfx_drv.h"
 
 #include <drm/drm_pciids.h>
+#include <drm/drm_legacy.h>
 
 static struct pci_device_id pciidlist[] = {
 	tdfx_PCI_IDS
@@ -46,7 +47,7 @@ static const struct file_operations tdfx_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
diff --git a/drivers/gpu/drm/via/via_drv.c b/drivers/gpu/drm/via/via_drv.c
index c16ffa63ded6..ed8aa8ff861a 100644
--- a/drivers/gpu/drm/via/via_drv.c
+++ b/drivers/gpu/drm/via/via_drv.c
@@ -62,7 +62,7 @@ static const struct file_operations via_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 2163ccbee50f..40c999019d9e 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -961,7 +961,6 @@ extern ssize_t drm_read(struct file *filp, char __user *buffer,
 extern int drm_release(struct inode *inode, struct file *filp);
 
 				/* Mapping support (drm_vm.h) */
-extern int drm_mmap(struct file *filp, struct vm_area_struct *vma);
 extern void drm_vm_open_locked(struct drm_device *dev, struct vm_area_struct *vma);
 extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
 
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
index 6486306beb0d..3e698038dc7b 100644
--- a/include/drm/drm_legacy.h
+++ b/include/drm/drm_legacy.h
@@ -157,6 +157,7 @@ int drm_legacy_addmap(struct drm_device *d, resource_size_t offset,
 int drm_legacy_rmmap(struct drm_device *d, struct drm_local_map *map);
 int drm_legacy_rmmap_locked(struct drm_device *d, struct drm_local_map *map);
 struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev);
+int drm_legacy_mmap(struct file *filp, struct vm_area_struct *vma);
 
 int drm_legacy_addbufs_agp(struct drm_device *d, struct drm_buf_desc *req);
 int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
-- 
cgit v1.2.3


From 884d9f05eb6c765d62da0ec8c36a669d8c813340 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 23 Sep 2014 15:46:50 +0200
Subject: drm: Move drm_vm_open_locked into drm_internal.h

Leftover from my previous header cleanup.

This depends upon the patch to rework exynos mmap support, otherwise
it'll break exynos.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_internal.h | 1 +
 drivers/gpu/drm/drm_vm.c       | 1 -
 include/drm/drmP.h             | 1 -
 3 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index d27faae45f1b..05624561118a 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -37,6 +37,7 @@ int drm_irq_by_busid(struct drm_device *dev, void *data,
 
 /* drm_vm.c */
 int drm_vma_info(struct seq_file *m, void *data);
+void drm_vm_open_locked(struct drm_device *dev, struct vm_area_struct *vma);
 void drm_vm_close_locked(struct drm_device *dev, struct vm_area_struct *vma);
 
 /* drm_prime.c */
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 28739d401596..4a2c328959e5 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -417,7 +417,6 @@ void drm_vm_open_locked(struct drm_device *dev,
 		list_add(&vma_entry->head, &dev->vmalist);
 	}
 }
-EXPORT_SYMBOL_GPL(drm_vm_open_locked);
 
 static void drm_vm_open(struct vm_area_struct *vma)
 {
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 40c999019d9e..7b545975afd9 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -961,7 +961,6 @@ extern ssize_t drm_read(struct file *filp, char __user *buffer,
 extern int drm_release(struct inode *inode, struct file *filp);
 
 				/* Mapping support (drm_vm.h) */
-extern void drm_vm_open_locked(struct drm_device *dev, struct vm_area_struct *vma);
 extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
 
 /* Misc. IOCTL support (drm_ioctl.c) */
-- 
cgit v1.2.3


From e7f0a889841e14315062c268abea6d2e657d60d3 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 23 Sep 2014 15:46:51 +0200
Subject: drm: Move leftover ioctl declarations to drm_internal.h

Somehow I've missed these three, fix this up asap. Plus move
drm_master_create since while at it.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_internal.h | 9 +++++++++
 include/drm/drmP.h             | 7 -------
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 05624561118a..bc71be6f29e0 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -62,6 +62,8 @@ int drm_gem_name_info(struct seq_file *m, void *data);
 /* drm_irq.c */
 int drm_control(struct drm_device *dev, void *data,
 		struct drm_file *file_priv);
+int drm_modeset_ctl(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv);
 
 /* drm_auth.c */
 int drm_getmagic(struct drm_device *dev, void *data,
@@ -93,3 +95,10 @@ int drm_gem_open_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
 void drm_gem_open(struct drm_device *dev, struct drm_file *file_private);
 void drm_gem_release(struct drm_device *dev, struct drm_file *file_private);
+
+/* drm_drv.c */
+int drm_setmaster_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv);
+struct drm_master *drm_master_create(struct drm_minor *minor);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 7b545975afd9..1ec2ca1d997b 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1026,15 +1026,8 @@ static inline wait_queue_head_t *drm_crtc_vblank_waitqueue(struct drm_crtc *crtc
 /* Modesetting support */
 extern void drm_vblank_pre_modeset(struct drm_device *dev, int crtc);
 extern void drm_vblank_post_modeset(struct drm_device *dev, int crtc);
-extern int drm_modeset_ctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv);
 
 				/* Stub support (drm_stub.h) */
-extern int drm_setmaster_ioctl(struct drm_device *dev, void *data,
-			       struct drm_file *file_priv);
-extern int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
-				struct drm_file *file_priv);
-struct drm_master *drm_master_create(struct drm_minor *minor);
 extern struct drm_master *drm_master_get(struct drm_master *master);
 extern void drm_master_put(struct drm_master **master);
 
-- 
cgit v1.2.3


From c2611031b49e9ccd571a3737845af3fca2a2090f Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 23 Sep 2014 15:46:52 +0200
Subject: drm: Move internal debugfs functions to drm_internal.h

In my header cleanup I've missed the debugfs functions completely.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_internal.h | 28 ++++++++++++++++++++++++++++
 include/drm/drmP.h             | 25 -------------------------
 2 files changed, 28 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index bc71be6f29e0..7cc0a3516871 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -102,3 +102,31 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data,
 int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 struct drm_master *drm_master_create(struct drm_minor *minor);
+
+/* drm_debugfs.c */
+#if defined(CONFIG_DEBUG_FS)
+int drm_debugfs_init(struct drm_minor *minor, int minor_id,
+		     struct dentry *root);
+int drm_debugfs_cleanup(struct drm_minor *minor);
+int drm_debugfs_connector_add(struct drm_connector *connector);
+void drm_debugfs_connector_remove(struct drm_connector *connector);
+#else
+static inline int drm_debugfs_init(struct drm_minor *minor, int minor_id,
+				   struct dentry *root)
+{
+	return 0;
+}
+
+static inline int drm_debugfs_cleanup(struct drm_minor *minor)
+{
+	return 0;
+}
+
+static inline int drm_debugfs_connector_add(struct drm_connector *connector)
+{
+	return 0;
+}
+static inline void drm_debugfs_connector_remove(struct drm_connector *connector)
+{
+}
+#endif
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 1ec2ca1d997b..6656fd7d64d4 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1037,23 +1037,12 @@ extern unsigned int drm_debug;
 
 				/* Debugfs support */
 #if defined(CONFIG_DEBUG_FS)
-extern int drm_debugfs_init(struct drm_minor *minor, int minor_id,
-			    struct dentry *root);
 extern int drm_debugfs_create_files(const struct drm_info_list *files,
 				    int count, struct dentry *root,
 				    struct drm_minor *minor);
 extern int drm_debugfs_remove_files(const struct drm_info_list *files,
 				    int count, struct drm_minor *minor);
-extern int drm_debugfs_cleanup(struct drm_minor *minor);
-extern int drm_debugfs_connector_add(struct drm_connector *connector);
-extern void drm_debugfs_connector_remove(struct drm_connector *connector);
 #else
-static inline int drm_debugfs_init(struct drm_minor *minor, int minor_id,
-				   struct dentry *root)
-{
-	return 0;
-}
-
 static inline int drm_debugfs_create_files(const struct drm_info_list *files,
 					   int count, struct dentry *root,
 					   struct drm_minor *minor)
@@ -1066,20 +1055,6 @@ static inline int drm_debugfs_remove_files(const struct drm_info_list *files,
 {
 	return 0;
 }
-
-static inline int drm_debugfs_cleanup(struct drm_minor *minor)
-{
-	return 0;
-}
-
-static inline int drm_debugfs_connector_add(struct drm_connector *connector)
-{
-	return 0;
-}
-static inline void drm_debugfs_connector_remove(struct drm_connector *connector)
-{
-}
-
 #endif
 
 extern struct dma_buf *drm_gem_prime_export(struct drm_device *dev,
-- 
cgit v1.2.3


From d9fc9413f97f5c615256a5657ec667c064c07a70 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 23 Sep 2014 15:46:53 +0200
Subject: drm: Extract <drm/drm_gem.h>

v2: Don't forget git add, noticed by David.

Cc: David Herrmann <dh.herrmann@gmail.com>

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Acked-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/armada/armada_gem.h     |   2 +
 drivers/gpu/drm/ast/ast_drv.h           |   2 +
 drivers/gpu/drm/bochs/bochs.h           |   2 +
 drivers/gpu/drm/cirrus/cirrus_drv.h     |   2 +
 drivers/gpu/drm/drm_gem.c               |   1 +
 drivers/gpu/drm/drm_info.c              |   2 +
 drivers/gpu/drm/drm_prime.c             |   2 +
 drivers/gpu/drm/exynos/exynos_drm_gem.h |   2 +
 drivers/gpu/drm/gma500/gtt.h            |   1 +
 drivers/gpu/drm/i915/i915_drv.h         |   1 +
 drivers/gpu/drm/mgag200/mgag200_drv.h   |   2 +
 drivers/gpu/drm/msm/msm_drv.h           |   1 +
 drivers/gpu/drm/nouveau/nouveau_bo.h    |   2 +
 drivers/gpu/drm/omapdrm/omap_drv.h      |   1 +
 drivers/gpu/drm/qxl/qxl_drv.h           |   2 +
 drivers/gpu/drm/radeon/radeon.h         |   2 +
 drivers/gpu/drm/radeon/radeon_drv.c     |   2 +
 drivers/gpu/drm/tegra/gem.h             |   1 +
 drivers/gpu/drm/udl/udl_drv.h           |   1 +
 include/drm/drmP.h                      | 148 +-------------------------
 include/drm/drm_gem.h                   | 183 ++++++++++++++++++++++++++++++++
 include/drm/drm_gem_cma_helper.h        |   1 +
 22 files changed, 216 insertions(+), 147 deletions(-)
 create mode 100644 include/drm/drm_gem.h

(limited to 'include')

diff --git a/drivers/gpu/drm/armada/armada_gem.h b/drivers/gpu/drm/armada/armada_gem.h
index 00b6cd461a03..b000ea3a829a 100644
--- a/drivers/gpu/drm/armada/armada_gem.h
+++ b/drivers/gpu/drm/armada/armada_gem.h
@@ -8,6 +8,8 @@
 #ifndef ARMADA_GEM_H
 #define ARMADA_GEM_H
 
+#include <drm/drm_gem.h>
+
 /* GEM */
 struct armada_gem_object {
 	struct drm_gem_object	obj;
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 7485ff945ca9..86205a28e56b 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -36,6 +36,8 @@
 #include <drm/ttm/ttm_memory.h>
 #include <drm/ttm/ttm_module.h>
 
+#include <drm/drm_gem.h>
+
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 
diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h
index 4f6e7b3a3635..71f2687fc3cc 100644
--- a/drivers/gpu/drm/bochs/bochs.h
+++ b/drivers/gpu/drm/bochs/bochs.h
@@ -7,6 +7,8 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 
+#include <drm/drm_gem.h>
+
 #include <ttm/ttm_bo_driver.h>
 #include <ttm/ttm_page_alloc.h>
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index dd2cfc9024aa..d44e69daa239 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -21,6 +21,8 @@
 #include <drm/ttm/ttm_memory.h>
 #include <drm/ttm/ttm_module.h>
 
+#include <drm/drm_gem.h>
+
 #define DRIVER_AUTHOR		"Matthew Garrett"
 
 #define DRIVER_NAME		"cirrus"
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index f9af78541505..cd45e45e2cce 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -38,6 +38,7 @@
 #include <linux/dma-buf.h>
 #include <drm/drmP.h>
 #include <drm/drm_vma_manager.h>
+#include <drm/drm_gem.h>
 #include "drm_internal.h"
 
 /** @file drm_gem.c
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index 0780541f7935..51efebd434f3 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -35,6 +35,8 @@
 
 #include <linux/seq_file.h>
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
+
 #include "drm_legacy.h"
 
 /**
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 2807a771f505..7826de9da276 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -29,6 +29,8 @@
 #include <linux/export.h>
 #include <linux/dma-buf.h>
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
+
 #include "drm_internal.h"
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 09d021bbccf5..ec58fe9c40df 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -12,6 +12,8 @@
 #ifndef _EXYNOS_DRM_GEM_H_
 #define _EXYNOS_DRM_GEM_H_
 
+#include <drm/drm_gem.h>
+
 #define to_exynos_gem_obj(x)	container_of(x,\
 			struct exynos_drm_gem_obj, base)
 
diff --git a/drivers/gpu/drm/gma500/gtt.h b/drivers/gpu/drm/gma500/gtt.h
index f5860a739bd8..cdbb350c9d5d 100644
--- a/drivers/gpu/drm/gma500/gtt.h
+++ b/drivers/gpu/drm/gma500/gtt.h
@@ -21,6 +21,7 @@
 #define _PSB_GTT_H_
 
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
 
 /* This wants cleaning up with respect to the psb_dev and un-needed stuff */
 struct psb_gtt {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 88a8b72b553e..19c0dd8e255e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -43,6 +43,7 @@
 #include <linux/i2c-algo-bit.h>
 #include <drm/intel-gtt.h>
 #include <drm/drm_legacy.h> /* for struct drm_dma_handle */
+#include <drm/drm_gem.h>
 #include <linux/backlight.h>
 #include <linux/hashtable.h>
 #include <linux/intel-iommu.h>
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index c03e347f3ffd..e9eea1d4e7c3 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -22,6 +22,8 @@
 #include <drm/ttm/ttm_memory.h>
 #include <drm/ttm/ttm_module.h>
 
+#include <drm/drm_gem.h>
+
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 8a2c5fd0893e..afaafd42dee7 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -51,6 +51,7 @@ static inline struct device *msm_iommu_get_ctx(const char *ctx_name)
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/msm_drm.h>
+#include <drm/drm_gem.h>
 
 struct msm_kms;
 struct msm_gpu;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h
index ae95b2d43b36..f238def41a92 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.h
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.h
@@ -1,6 +1,8 @@
 #ifndef __NOUVEAU_BO_H__
 #define __NOUVEAU_BO_H__
 
+#include <drm/drm_gem.h>
+
 struct nouveau_channel;
 struct nouveau_fence;
 struct nouveau_vma;
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index 84d73a61b34b..60e47b33c801 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -26,6 +26,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/omap_drm.h>
+#include <drm/drm_gem.h>
 #include <linux/platform_data/omap_drm.h>
 
 
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index d75c0a9f674f..ff0772728eb0 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -43,6 +43,8 @@
 #include <ttm/ttm_placement.h>
 #include <ttm/ttm_module.h>
 
+#include <drm/drm_gem.h>
+
 /* just for ttm_validate_buffer */
 #include <ttm/ttm_execbuf_util.h>
 
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 82b0e11ade89..ef91ebb7c671 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -74,6 +74,8 @@
 #include <ttm/ttm_module.h>
 #include <ttm/ttm_execbuf_util.h>
 
+#include <drm/drm_gem.h>
+
 #include "radeon_family.h"
 #include "radeon_mode.h"
 #include "radeon_reg.h"
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index dd082049fd5b..de108427a197 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -38,6 +38,8 @@
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/vga_switcheroo.h>
+#include <drm/drm_gem.h>
+
 #include "drm_crtc_helper.h"
 /*
  * KMS wrapper.
diff --git a/drivers/gpu/drm/tegra/gem.h b/drivers/gpu/drm/tegra/gem.h
index 43a25c853357..6538b56780c2 100644
--- a/drivers/gpu/drm/tegra/gem.h
+++ b/drivers/gpu/drm/tegra/gem.h
@@ -15,6 +15,7 @@
 
 #include <drm/drm.h>
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
 
 #define TEGRA_BO_BOTTOM_UP (1 << 0)
 
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 51e10ee77f39..c7490a2489a7 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -15,6 +15,7 @@
 #define UDL_DRV_H
 
 #include <linux/usb.h>
+#include <drm/drm_gem.h>
 
 #define DRIVER_NAME		"udl"
 #define DRIVER_DESC		"DisplayLink"
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 6656fd7d64d4..d2c2b7f3a4e2 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -82,6 +82,7 @@ struct drm_agp_head;
 struct drm_local_map;
 struct drm_device_dma;
 struct drm_dma_handle;
+struct drm_gem_object;
 
 struct device_node;
 struct videomode;
@@ -330,93 +331,6 @@ struct drm_lock_data {
 	int idle_has_lock;
 };
 
-/**
- * This structure defines the drm_mm memory object, which will be used by the
- * DRM for its buffer objects.
- */
-struct drm_gem_object {
-	/** Reference count of this object */
-	struct kref refcount;
-
-	/**
-	 * handle_count - gem file_priv handle count of this object
-	 *
-	 * Each handle also holds a reference. Note that when the handle_count
-	 * drops to 0 any global names (e.g. the id in the flink namespace) will
-	 * be cleared.
-	 *
-	 * Protected by dev->object_name_lock.
-	 * */
-	unsigned handle_count;
-
-	/** Related drm device */
-	struct drm_device *dev;
-
-	/** File representing the shmem storage */
-	struct file *filp;
-
-	/* Mapping info for this object */
-	struct drm_vma_offset_node vma_node;
-
-	/**
-	 * Size of the object, in bytes.  Immutable over the object's
-	 * lifetime.
-	 */
-	size_t size;
-
-	/**
-	 * Global name for this object, starts at 1. 0 means unnamed.
-	 * Access is covered by the object_name_lock in the related drm_device
-	 */
-	int name;
-
-	/**
-	 * Memory domains. These monitor which caches contain read/write data
-	 * related to the object. When transitioning from one set of domains
-	 * to another, the driver is called to ensure that caches are suitably
-	 * flushed and invalidated
-	 */
-	uint32_t read_domains;
-	uint32_t write_domain;
-
-	/**
-	 * While validating an exec operation, the
-	 * new read/write domain values are computed here.
-	 * They will be transferred to the above values
-	 * at the point that any cache flushing occurs
-	 */
-	uint32_t pending_read_domains;
-	uint32_t pending_write_domain;
-
-	/**
-	 * dma_buf - dma buf associated with this GEM object
-	 *
-	 * Pointer to the dma-buf associated with this gem object (either
-	 * through importing or exporting). We break the resulting reference
-	 * loop when the last gem handle for this object is released.
-	 *
-	 * Protected by obj->object_name_lock
-	 */
-	struct dma_buf *dma_buf;
-
-	/**
-	 * import_attach - dma buf attachment backing this object
-	 *
-	 * Any foreign dma_buf imported as a gem object has this set to the
-	 * attachment point for the device. This is invariant over the lifetime
-	 * of a gem object.
-	 *
-	 * The driver's ->gem_free_object callback is responsible for cleaning
-	 * up the dma_buf attachment and references acquired at import time.
-	 *
-	 * Note that the drm gem/prime core does not depend upon drivers setting
-	 * this field any more. So for drivers where this doesn't make sense
-	 * (e.g. virtual devices or a displaylink behind an usb bus) they can
-	 * simply leave it as NULL.
-	 */
-	struct dma_buf_attachment *import_attach;
-};
-
 /**
  * struct drm_master - drm master structure
  *
@@ -1073,10 +987,6 @@ extern int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **
 extern struct sg_table *drm_prime_pages_to_sg(struct page **pages, int nr_pages);
 extern void drm_prime_gem_destroy(struct drm_gem_object *obj, struct sg_table *sg);
 
-int drm_gem_dumb_destroy(struct drm_file *file,
-			 struct drm_device *dev,
-			 uint32_t handle);
-
 
 extern struct drm_dma_handle *drm_pci_alloc(struct drm_device *dev, size_t size,
 					    size_t align);
@@ -1085,62 +995,6 @@ extern void drm_pci_free(struct drm_device *dev, struct drm_dma_handle * dmah);
 			       /* sysfs support (drm_sysfs.c) */
 extern void drm_sysfs_hotplug_event(struct drm_device *dev);
 
-/* Graphics Execution Manager library functions (drm_gem.c) */
-void drm_gem_object_release(struct drm_gem_object *obj);
-void drm_gem_object_free(struct kref *kref);
-int drm_gem_object_init(struct drm_device *dev,
-			struct drm_gem_object *obj, size_t size);
-void drm_gem_private_object_init(struct drm_device *dev,
-				 struct drm_gem_object *obj, size_t size);
-void drm_gem_vm_open(struct vm_area_struct *vma);
-void drm_gem_vm_close(struct vm_area_struct *vma);
-int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
-		     struct vm_area_struct *vma);
-int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
-
-static inline void
-drm_gem_object_reference(struct drm_gem_object *obj)
-{
-	kref_get(&obj->refcount);
-}
-
-static inline void
-drm_gem_object_unreference(struct drm_gem_object *obj)
-{
-	if (obj != NULL)
-		kref_put(&obj->refcount, drm_gem_object_free);
-}
-
-static inline void
-drm_gem_object_unreference_unlocked(struct drm_gem_object *obj)
-{
-	if (obj && !atomic_add_unless(&obj->refcount.refcount, -1, 1)) {
-		struct drm_device *dev = obj->dev;
-
-		mutex_lock(&dev->struct_mutex);
-		if (likely(atomic_dec_and_test(&obj->refcount.refcount)))
-			drm_gem_object_free(&obj->refcount);
-		mutex_unlock(&dev->struct_mutex);
-	}
-}
-
-int drm_gem_handle_create(struct drm_file *file_priv,
-			  struct drm_gem_object *obj,
-			  u32 *handlep);
-int drm_gem_handle_delete(struct drm_file *filp, u32 handle);
-
-
-void drm_gem_free_mmap_offset(struct drm_gem_object *obj);
-int drm_gem_create_mmap_offset(struct drm_gem_object *obj);
-int drm_gem_create_mmap_offset_size(struct drm_gem_object *obj, size_t size);
-
-struct page **drm_gem_get_pages(struct drm_gem_object *obj);
-void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages,
-		bool dirty, bool accessed);
-
-struct drm_gem_object *drm_gem_object_lookup(struct drm_device *dev,
-					     struct drm_file *filp,
-					     u32 handle);
 
 struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 				 struct device *parent);
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
new file mode 100644
index 000000000000..1e6ae1458f7a
--- /dev/null
+++ b/include/drm/drm_gem.h
@@ -0,0 +1,183 @@
+#ifndef __DRM_GEM_H__
+#define __DRM_GEM_H__
+
+/*
+ * GEM Graphics Execution Manager Driver Interfaces
+ *
+ * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
+ * Copyright (c) 2009-2010, Code Aurora Forum.
+ * All rights reserved.
+ * Copyright © 2014 Intel Corporation
+ *   Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Gareth Hughes <gareth@valinux.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/**
+ * This structure defines the drm_mm memory object, which will be used by the
+ * DRM for its buffer objects.
+ */
+struct drm_gem_object {
+	/** Reference count of this object */
+	struct kref refcount;
+
+	/**
+	 * handle_count - gem file_priv handle count of this object
+	 *
+	 * Each handle also holds a reference. Note that when the handle_count
+	 * drops to 0 any global names (e.g. the id in the flink namespace) will
+	 * be cleared.
+	 *
+	 * Protected by dev->object_name_lock.
+	 * */
+	unsigned handle_count;
+
+	/** Related drm device */
+	struct drm_device *dev;
+
+	/** File representing the shmem storage */
+	struct file *filp;
+
+	/* Mapping info for this object */
+	struct drm_vma_offset_node vma_node;
+
+	/**
+	 * Size of the object, in bytes.  Immutable over the object's
+	 * lifetime.
+	 */
+	size_t size;
+
+	/**
+	 * Global name for this object, starts at 1. 0 means unnamed.
+	 * Access is covered by the object_name_lock in the related drm_device
+	 */
+	int name;
+
+	/**
+	 * Memory domains. These monitor which caches contain read/write data
+	 * related to the object. When transitioning from one set of domains
+	 * to another, the driver is called to ensure that caches are suitably
+	 * flushed and invalidated
+	 */
+	uint32_t read_domains;
+	uint32_t write_domain;
+
+	/**
+	 * While validating an exec operation, the
+	 * new read/write domain values are computed here.
+	 * They will be transferred to the above values
+	 * at the point that any cache flushing occurs
+	 */
+	uint32_t pending_read_domains;
+	uint32_t pending_write_domain;
+
+	/**
+	 * dma_buf - dma buf associated with this GEM object
+	 *
+	 * Pointer to the dma-buf associated with this gem object (either
+	 * through importing or exporting). We break the resulting reference
+	 * loop when the last gem handle for this object is released.
+	 *
+	 * Protected by obj->object_name_lock
+	 */
+	struct dma_buf *dma_buf;
+
+	/**
+	 * import_attach - dma buf attachment backing this object
+	 *
+	 * Any foreign dma_buf imported as a gem object has this set to the
+	 * attachment point for the device. This is invariant over the lifetime
+	 * of a gem object.
+	 *
+	 * The driver's ->gem_free_object callback is responsible for cleaning
+	 * up the dma_buf attachment and references acquired at import time.
+	 *
+	 * Note that the drm gem/prime core does not depend upon drivers setting
+	 * this field any more. So for drivers where this doesn't make sense
+	 * (e.g. virtual devices or a displaylink behind an usb bus) they can
+	 * simply leave it as NULL.
+	 */
+	struct dma_buf_attachment *import_attach;
+};
+
+void drm_gem_object_release(struct drm_gem_object *obj);
+void drm_gem_object_free(struct kref *kref);
+int drm_gem_object_init(struct drm_device *dev,
+			struct drm_gem_object *obj, size_t size);
+void drm_gem_private_object_init(struct drm_device *dev,
+				 struct drm_gem_object *obj, size_t size);
+void drm_gem_vm_open(struct vm_area_struct *vma);
+void drm_gem_vm_close(struct vm_area_struct *vma);
+int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
+		     struct vm_area_struct *vma);
+int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
+
+static inline void
+drm_gem_object_reference(struct drm_gem_object *obj)
+{
+	kref_get(&obj->refcount);
+}
+
+static inline void
+drm_gem_object_unreference(struct drm_gem_object *obj)
+{
+	if (obj != NULL)
+		kref_put(&obj->refcount, drm_gem_object_free);
+}
+
+static inline void
+drm_gem_object_unreference_unlocked(struct drm_gem_object *obj)
+{
+	if (obj && !atomic_add_unless(&obj->refcount.refcount, -1, 1)) {
+		struct drm_device *dev = obj->dev;
+
+		mutex_lock(&dev->struct_mutex);
+		if (likely(atomic_dec_and_test(&obj->refcount.refcount)))
+			drm_gem_object_free(&obj->refcount);
+		mutex_unlock(&dev->struct_mutex);
+	}
+}
+
+int drm_gem_handle_create(struct drm_file *file_priv,
+			  struct drm_gem_object *obj,
+			  u32 *handlep);
+int drm_gem_handle_delete(struct drm_file *filp, u32 handle);
+
+
+void drm_gem_free_mmap_offset(struct drm_gem_object *obj);
+int drm_gem_create_mmap_offset(struct drm_gem_object *obj);
+int drm_gem_create_mmap_offset_size(struct drm_gem_object *obj, size_t size);
+
+struct page **drm_gem_get_pages(struct drm_gem_object *obj);
+void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages,
+		bool dirty, bool accessed);
+
+struct drm_gem_object *drm_gem_object_lookup(struct drm_device *dev,
+					     struct drm_file *filp,
+					     u32 handle);
+int drm_gem_dumb_destroy(struct drm_file *file,
+			 struct drm_device *dev,
+			 uint32_t handle);
+
+#endif /* __DRM_GEM_H__ */
diff --git a/include/drm/drm_gem_cma_helper.h b/include/drm/drm_gem_cma_helper.h
index 2a3cea91606d..42f11f3a8d39 100644
--- a/include/drm/drm_gem_cma_helper.h
+++ b/include/drm/drm_gem_cma_helper.h
@@ -2,6 +2,7 @@
 #define __DRM_GEM_CMA_HELPER_H__
 
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
 
 struct drm_gem_cma_object {
 	struct drm_gem_object base;
-- 
cgit v1.2.3


From 9a37110d20c95d1ebf6c04881177fe8f62831db2 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 10 Sep 2014 14:31:39 -0400
Subject: locking: Add WARN_ON_ONCE lock assertion

An interface may need to assert a lock invariant and not flood the
system logs; add a lockdep helper macro equivalent to
lockdep_assert_held() which only WARNs once.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/lockdep.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 008388f920d7..64c7425afbce 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -362,6 +362,10 @@ extern void lockdep_trace_alloc(gfp_t mask);
 		WARN_ON(debug_locks && !lockdep_is_held(l));	\
 	} while (0)
 
+#define lockdep_assert_held_once(l)	do {				\
+		WARN_ON_ONCE(debug_locks && !lockdep_is_held(l));	\
+	} while (0)
+
 #define lockdep_recursing(tsk)	((tsk)->lockdep_recursion)
 
 #else /* !CONFIG_LOCKDEP */
@@ -412,6 +416,7 @@ struct lock_class_key { };
 #define lockdep_depth(tsk)	(0)
 
 #define lockdep_assert_held(l)			do { (void)(l); } while (0)
+#define lockdep_assert_held_once(l)		do { (void)(l); } while (0)
 
 #define lockdep_recursing(tsk)			(0)
 
-- 
cgit v1.2.3


From 2a159389bf5d962359349a76827b2f683276a1c7 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 25 Aug 2014 17:51:26 +0200
Subject: USB: core: add device-qualifier quirk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add new quirk for devices that cannot handle requests for the
device_qualifier descriptor.

A USB-2.0 compliant device must respond to requests for the
device_qualifier descriptor (even if it's with a request error), but at
least one device is known to misbehave after such a request.

Suggested-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c     | 3 +++
 include/linux/usb/quirks.h | 3 +++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index d481c99a20d7..c01b72467524 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4538,6 +4538,9 @@ check_highspeed (struct usb_hub *hub, struct usb_device *udev, int port1)
 	struct usb_qualifier_descriptor	*qual;
 	int				status;
 
+	if (udev->quirks & USB_QUIRK_DEVICE_QUALIFIER)
+		return;
+
 	qual = kmalloc (sizeof *qual, GFP_KERNEL);
 	if (qual == NULL)
 		return;
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 55a17b188daa..ffe565c94743 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -41,4 +41,7 @@
  */
 #define USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL	0x00000080
 
+/* device can't handle device_qualifier descriptor requests */
+#define USB_QUIRK_DEVICE_QUALIFIER	0x00000100
+
 #endif /* __LINUX_USB_QUIRKS_H */
-- 
cgit v1.2.3


From 299245a145b2ad4cfb4c5432eb1264299f55e7e0 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 10 Sep 2014 15:06:24 -0400
Subject: serial: core: Privatize modem status enable flags

The serial core uses the tty port flags, ASYNC_CTS_FLOW and
ASYNC_CD_CHECK, to track whether CTS and DCD changes should be
ignored or handled. However, the tty port flags are not safe for
atomic bit operations and no lock provides serialized updates.

Introduce the struct uart_port status field to track CTS and DCD
enable states, and serialize access with uart port lock. Substitute
uart_cts_enabled() helper for tty_port_cts_enabled().

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/mxs-auart.c   |  2 +-
 drivers/tty/serial/serial_core.c | 29 +++++++++++++++++------------
 include/linux/serial_core.h      | 12 ++++++++++++
 3 files changed, 30 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index b5c329248c81..10c29334fe2f 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -408,7 +408,7 @@ static void mxs_auart_set_mctrl(struct uart_port *u, unsigned mctrl)
 
 	ctrl &= ~(AUART_CTRL2_RTSEN | AUART_CTRL2_RTS);
 	if (mctrl & TIOCM_RTS) {
-		if (tty_port_cts_enabled(&u->state->port))
+		if (uart_cts_enabled(u))
 			ctrl |= AUART_CTRL2_RTSEN;
 		else
 			ctrl |= AUART_CTRL2_RTS;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index f764de32b658..dd21ed900635 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -59,6 +59,11 @@ static void uart_change_pm(struct uart_state *state,
 
 static void uart_port_shutdown(struct tty_port *port);
 
+static int uart_dcd_enabled(struct uart_port *uport)
+{
+	return uport->status & UPSTAT_DCD_ENABLE;
+}
+
 /*
  * This routine is used by the interrupt handler to schedule processing in
  * the software interrupt portion of the driver.
@@ -130,7 +135,6 @@ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state,
 		int init_hw)
 {
 	struct uart_port *uport = state->uart_port;
-	struct tty_port *port = &state->port;
 	unsigned long page;
 	int retval = 0;
 
@@ -176,12 +180,12 @@ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state,
 				uart_set_mctrl(uport, TIOCM_RTS | TIOCM_DTR);
 		}
 
-		if (tty_port_cts_enabled(port)) {
-			spin_lock_irq(&uport->lock);
+		spin_lock_irq(&uport->lock);
+		if (uart_cts_enabled(uport)) {
 			if (!(uport->ops->get_mctrl(uport) & TIOCM_CTS))
 				tty->hw_stopped = 1;
-			spin_unlock_irq(&uport->lock);
 		}
+		spin_unlock_irq(&uport->lock);
 	}
 
 	/*
@@ -435,7 +439,6 @@ EXPORT_SYMBOL(uart_get_divisor);
 static void uart_change_speed(struct tty_struct *tty, struct uart_state *state,
 					struct ktermios *old_termios)
 {
-	struct tty_port *port = &state->port;
 	struct uart_port *uport = state->uart_port;
 	struct ktermios *termios;
 
@@ -450,17 +453,19 @@ static void uart_change_speed(struct tty_struct *tty, struct uart_state *state,
 	uport->ops->set_termios(uport, termios, old_termios);
 
 	/*
-	 * Set flags based on termios cflag
+	 * Set modem status enables based on termios cflag
 	 */
+	spin_lock_irq(&uport->lock);
 	if (termios->c_cflag & CRTSCTS)
-		set_bit(ASYNCB_CTS_FLOW, &port->flags);
+		uport->status |= UPSTAT_CTS_ENABLE;
 	else
-		clear_bit(ASYNCB_CTS_FLOW, &port->flags);
+		uport->status &= ~UPSTAT_CTS_ENABLE;
 
 	if (termios->c_cflag & CLOCAL)
-		clear_bit(ASYNCB_CHECK_CD, &port->flags);
+		uport->status &= ~UPSTAT_DCD_ENABLE;
 	else
-		set_bit(ASYNCB_CHECK_CD, &port->flags);
+		uport->status |= UPSTAT_DCD_ENABLE;
+	spin_unlock_irq(&uport->lock);
 }
 
 static inline int __uart_put_char(struct uart_port *port,
@@ -2765,7 +2770,7 @@ void uart_handle_dcd_change(struct uart_port *uport, unsigned int status)
 
 	uport->icount.dcd++;
 
-	if (port->flags & ASYNC_CHECK_CD) {
+	if (uart_dcd_enabled(uport)) {
 		if (status)
 			wake_up_interruptible(&port->open_wait);
 		else if (tty)
@@ -2790,7 +2795,7 @@ void uart_handle_cts_change(struct uart_port *uport, unsigned int status)
 
 	uport->icount.cts++;
 
-	if (tty_port_cts_enabled(port)) {
+	if (uart_cts_enabled(uport)) {
 		if (tty->hw_stopped) {
 			if (status) {
 				tty->hw_stopped = 0;
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 3bd7d55eebce..452c9cc9d717 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -112,6 +112,7 @@ struct uart_icount {
 };
 
 typedef unsigned int __bitwise__ upf_t;
+typedef unsigned int __bitwise__ upstat_t;
 
 struct uart_port {
 	spinlock_t		lock;			/* port lock */
@@ -190,6 +191,12 @@ struct uart_port {
 #define UPF_CHANGE_MASK		((__force upf_t) (0x17fff))
 #define UPF_USR_MASK		((__force upf_t) (UPF_SPD_MASK|UPF_LOW_LATENCY))
 
+	/* status must be updated while holding port lock */
+	upstat_t		status;
+
+#define UPSTAT_CTS_ENABLE	((__force upstat_t) (1 << 0))
+#define UPSTAT_DCD_ENABLE	((__force upstat_t) (1 << 1))
+
 	unsigned int		mctrl;			/* current modem ctrl settings */
 	unsigned int		timeout;		/* character-based timeout */
 	unsigned int		type;			/* port type */
@@ -355,6 +362,11 @@ static inline int uart_tx_stopped(struct uart_port *port)
 	return 0;
 }
 
+static inline bool uart_cts_enabled(struct uart_port *uport)
+{
+	return uport->status & UPSTAT_CTS_ENABLE;
+}
+
 /*
  * The following are helper functions for the low level drivers.
  */
-- 
cgit v1.2.3


From d01f4d181c92877ecc678adce248a30cb7077ff1 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 10 Sep 2014 15:06:26 -0400
Subject: serial: core: Privatize tty->hw_stopped

tty->hw_stopped is not used by the tty core and is thread-unsafe;
hw_stopped is a member of a bitfield whose fields are updated
non-atomically and no lock is suitable for serializing updates.

Replace serial core usage of tty->hw_stopped with uport->hw_stopped.
Use int storage which works around Alpha EV4/5 non-atomic byte storage,
since uart_port uses different locks to protect certain fields within the
structure.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/bfin_uart.c   | 14 +++++++-------
 drivers/tty/serial/serial_core.c | 28 +++++++++++++---------------
 include/linux/serial_core.h      |  3 ++-
 3 files changed, 22 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/bfin_uart.c b/drivers/tty/serial/bfin_uart.c
index dec0fd725d80..fc9fbf3f24a7 100644
--- a/drivers/tty/serial/bfin_uart.c
+++ b/drivers/tty/serial/bfin_uart.c
@@ -108,22 +108,22 @@ static void bfin_serial_set_mctrl(struct uart_port *port, unsigned int mctrl)
 static irqreturn_t bfin_serial_mctrl_cts_int(int irq, void *dev_id)
 {
 	struct bfin_serial_port *uart = dev_id;
-	unsigned int status = bfin_serial_get_mctrl(&uart->port);
+	struct uart_port *uport = &uart->port;
+	unsigned int status = bfin_serial_get_mctrl(uport);
 #ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-	struct tty_struct *tty = uart->port.state->port.tty;
 
 	UART_CLEAR_SCTS(uart);
-	if (tty->hw_stopped) {
+	if (uport->hw_stopped) {
 		if (status) {
-			tty->hw_stopped = 0;
-			uart_write_wakeup(&uart->port);
+			uport->hw_stopped = 0;
+			uart_write_wakeup(uport);
 		}
 	} else {
 		if (!status)
-			tty->hw_stopped = 1;
+			uport->hw_stopped = 1;
 	}
 #endif
-	uart_handle_cts_change(&uart->port, status & TIOCM_CTS);
+	uart_handle_cts_change(uport, status & TIOCM_CTS);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index dd21ed900635..7d51e26627fb 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -95,7 +95,7 @@ static void __uart_start(struct tty_struct *tty)
 	struct uart_state *state = tty->driver_data;
 	struct uart_port *port = state->uart_port;
 
-	if (!tty->stopped && !tty->hw_stopped)
+	if (!uart_tx_stopped(port))
 		port->ops->start_tx(port);
 }
 
@@ -181,10 +181,11 @@ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state,
 		}
 
 		spin_lock_irq(&uport->lock);
-		if (uart_cts_enabled(uport)) {
-			if (!(uport->ops->get_mctrl(uport) & TIOCM_CTS))
-				tty->hw_stopped = 1;
-		}
+		if (uart_cts_enabled(uport) &&
+		    !(uport->ops->get_mctrl(uport) & TIOCM_CTS))
+			uport->hw_stopped = 1;
+		else
+			uport->hw_stopped = 0;
 		spin_unlock_irq(&uport->lock);
 	}
 
@@ -949,7 +950,7 @@ static int uart_get_lsr_info(struct tty_struct *tty,
 	 */
 	if (uport->x_char ||
 	    ((uart_circ_chars_pending(&state->xmit) > 0) &&
-	     !tty->stopped && !tty->hw_stopped))
+	     !uart_tx_stopped(uport)))
 		result &= ~TIOCSER_TEMT;
 
 	return put_user(result, value);
@@ -1295,7 +1296,7 @@ static void uart_set_termios(struct tty_struct *tty,
 
 	/*
 	 * If the port is doing h/w assisted flow control, do nothing.
-	 * We assume that tty->hw_stopped has never been set.
+	 * We assume that port->hw_stopped has never been set.
 	 */
 	if (uport->flags & UPF_HARD_FLOW)
 		return;
@@ -1303,7 +1304,7 @@ static void uart_set_termios(struct tty_struct *tty,
 	/* Handle turning off CRTSCTS */
 	if ((old_termios->c_cflag & CRTSCTS) && !(cflag & CRTSCTS)) {
 		spin_lock_irqsave(&uport->lock, flags);
-		tty->hw_stopped = 0;
+		uport->hw_stopped = 0;
 		__uart_start(tty);
 		spin_unlock_irqrestore(&uport->lock, flags);
 	}
@@ -1311,7 +1312,7 @@ static void uart_set_termios(struct tty_struct *tty,
 	else if (!(old_termios->c_cflag & CRTSCTS) && (cflag & CRTSCTS)) {
 		spin_lock_irqsave(&uport->lock, flags);
 		if (!(uport->ops->get_mctrl(uport) & TIOCM_CTS)) {
-			tty->hw_stopped = 1;
+			uport->hw_stopped = 1;
 			uport->ops->stop_tx(uport);
 		}
 		spin_unlock_irqrestore(&uport->lock, flags);
@@ -2788,23 +2789,20 @@ EXPORT_SYMBOL_GPL(uart_handle_dcd_change);
  */
 void uart_handle_cts_change(struct uart_port *uport, unsigned int status)
 {
-	struct tty_port *port = &uport->state->port;
-	struct tty_struct *tty = port->tty;
-
 	lockdep_assert_held_once(&uport->lock);
 
 	uport->icount.cts++;
 
 	if (uart_cts_enabled(uport)) {
-		if (tty->hw_stopped) {
+		if (uport->hw_stopped) {
 			if (status) {
-				tty->hw_stopped = 0;
+				uport->hw_stopped = 0;
 				uport->ops->start_tx(uport);
 				uart_write_wakeup(uport);
 			}
 		} else {
 			if (!status) {
-				tty->hw_stopped = 1;
+				uport->hw_stopped = 1;
 				uport->ops->stop_tx(uport);
 			}
 		}
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 452c9cc9d717..204c452a7567 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -197,6 +197,7 @@ struct uart_port {
 #define UPSTAT_CTS_ENABLE	((__force upstat_t) (1 << 0))
 #define UPSTAT_DCD_ENABLE	((__force upstat_t) (1 << 1))
 
+	int			hw_stopped;		/* sw-assisted CTS flow state */
 	unsigned int		mctrl;			/* current modem ctrl settings */
 	unsigned int		timeout;		/* character-based timeout */
 	unsigned int		type;			/* port type */
@@ -357,7 +358,7 @@ int uart_resume_port(struct uart_driver *reg, struct uart_port *port);
 static inline int uart_tx_stopped(struct uart_port *port)
 {
 	struct tty_struct *tty = port->state->port.tty;
-	if(tty->stopped || tty->hw_stopped)
+	if (tty->stopped || port->hw_stopped)
 		return 1;
 	return 0;
 }
-- 
cgit v1.2.3


From d7a855bd6ab25d10d5e3b6aeb53d9c57fa17b808 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 10 Sep 2014 15:06:30 -0400
Subject: tty: Convert tty_struct bitfield to ints

The stopped, hw_stopped, flow_stopped and packet bits are smp-unsafe
and interrupt-unsafe. For example,

CPU 0                         | CPU 1
                              |
tty->flow_stopped = 1         | tty->hw_stopped = 0

One of these updates will be corrupted, as the bitwise operation
on the bitfield is non-atomic.

Ensure each flag has a separate memory location, so concurrent
updates do not corrupt orthogonal states. Because DEC Alpha EV4 and EV5
cpus (from 1995) perform RMW on smaller-than-machine-word storage,
"separate memory location" must be int instead of byte.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 84132942902a..4cfd4a82fc31 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -261,7 +261,10 @@ struct tty_struct {
 	unsigned long flags;
 	int count;
 	struct winsize winsize;		/* winsize_mutex */
-	unsigned char stopped:1, hw_stopped:1, flow_stopped:1, packet:1;
+	int stopped;
+	int flow_stopped;
+	int hw_stopped;
+	int packet;
 	unsigned char ctrl_status;	/* ctrl_lock */
 	unsigned int receive_room;	/* Bytes free for queue */
 	int flow_change;
-- 
cgit v1.2.3


From f9e053dcfc02b0ad29daec8524fb1afe09774976 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 10 Sep 2014 15:06:31 -0400
Subject: tty: Serialize tty flow control changes with flow_lock

Without serialization, the flow control state can become inverted
wrt. the actual hardware state. For example,

CPU 0                          | CPU 1
stop_tty()                     |
  lock ctrl_lock               |
  tty->stopped = 1             |
  unlock ctrl_lock             |
                               | start_tty()
                               |   lock ctrl_lock
                               |   tty->stopped = 0
                               |   unlock ctrl_lock
                               |   driver->start()
  driver->stop()               |

In this case, the flow control state now indicates the tty has
been started, but the actual hardware state has actually been stopped.

Introduce tty->flow_lock spinlock to serialize tty flow control changes.
Split out unlocked __start_tty()/__stop_tty() flavors for use by
ioctl(TCXONC) in follow-on patch.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c       | 39 ++++++++++++++++++++++++++++-----------
 include/linux/tty.h        |  5 ++++-
 include/linux/tty_driver.h |  4 ++++
 3 files changed, 36 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index d4eb2a8b7047..b8ddfef6b5d8 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -919,18 +919,18 @@ void no_tty(void)
  *	but not always.
  *
  *	Locking:
- *		Uses the tty control lock internally
+ *		ctrl_lock
+ *		flow_lock
  */
 
-void stop_tty(struct tty_struct *tty)
+void __stop_tty(struct tty_struct *tty)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&tty->ctrl_lock, flags);
-	if (tty->stopped) {
-		spin_unlock_irqrestore(&tty->ctrl_lock, flags);
+
+	if (tty->stopped)
 		return;
-	}
 	tty->stopped = 1;
+	spin_lock_irqsave(&tty->ctrl_lock, flags);
 	if (tty->link && tty->link->packet) {
 		tty->ctrl_status &= ~TIOCPKT_START;
 		tty->ctrl_status |= TIOCPKT_STOP;
@@ -941,6 +941,14 @@ void stop_tty(struct tty_struct *tty)
 		(tty->ops->stop)(tty);
 }
 
+void stop_tty(struct tty_struct *tty)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&tty->flow_lock, flags);
+	__stop_tty(tty);
+	spin_unlock_irqrestore(&tty->flow_lock, flags);
+}
 EXPORT_SYMBOL(stop_tty);
 
 /**
@@ -954,17 +962,17 @@ EXPORT_SYMBOL(stop_tty);
  *
  *	Locking:
  *		ctrl_lock
+ *		flow_lock
  */
 
-void start_tty(struct tty_struct *tty)
+void __start_tty(struct tty_struct *tty)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&tty->ctrl_lock, flags);
-	if (!tty->stopped || tty->flow_stopped) {
-		spin_unlock_irqrestore(&tty->ctrl_lock, flags);
+
+	if (!tty->stopped || tty->flow_stopped)
 		return;
-	}
 	tty->stopped = 0;
+	spin_lock_irqsave(&tty->ctrl_lock, flags);
 	if (tty->link && tty->link->packet) {
 		tty->ctrl_status &= ~TIOCPKT_STOP;
 		tty->ctrl_status |= TIOCPKT_START;
@@ -977,6 +985,14 @@ void start_tty(struct tty_struct *tty)
 	tty_wakeup(tty);
 }
 
+void start_tty(struct tty_struct *tty)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&tty->flow_lock, flags);
+	__start_tty(tty);
+	spin_unlock_irqrestore(&tty->flow_lock, flags);
+}
 EXPORT_SYMBOL(start_tty);
 
 /* We limit tty time update visibility to every 8 seconds or so. */
@@ -3019,6 +3035,7 @@ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx)
 	INIT_WORK(&tty->hangup_work, do_tty_hangup);
 	mutex_init(&tty->atomic_write_lock);
 	spin_lock_init(&tty->ctrl_lock);
+	spin_lock_init(&tty->flow_lock);
 	INIT_LIST_HEAD(&tty->tty_files);
 	INIT_WORK(&tty->SAK_work, do_SAK_work);
 
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 4cfd4a82fc31..fd4148d3a261 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -252,6 +252,7 @@ struct tty_struct {
 	struct rw_semaphore termios_rwsem;
 	struct mutex winsize_mutex;
 	spinlock_t ctrl_lock;
+	spinlock_t flow_lock;
 	/* Termios values are protected by the termios rwsem */
 	struct ktermios termios, termios_locked;
 	struct termiox *termiox;	/* May be NULL for unsupported */
@@ -261,7 +262,7 @@ struct tty_struct {
 	unsigned long flags;
 	int count;
 	struct winsize winsize;		/* winsize_mutex */
-	int stopped;
+	int stopped;			/* flow_lock */
 	int flow_stopped;
 	int hw_stopped;
 	int packet;
@@ -400,7 +401,9 @@ extern int tty_paranoia_check(struct tty_struct *tty, struct inode *inode,
 extern char *tty_name(struct tty_struct *tty, char *buf);
 extern void tty_wait_until_sent(struct tty_struct *tty, long timeout);
 extern int tty_check_change(struct tty_struct *tty);
+extern void __stop_tty(struct tty_struct *tty);
 extern void stop_tty(struct tty_struct *tty);
+extern void __start_tty(struct tty_struct *tty);
 extern void start_tty(struct tty_struct *tty);
 extern int tty_register_driver(struct tty_driver *driver);
 extern int tty_unregister_driver(struct tty_driver *driver);
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index e48c608a8fa8..92e337c18839 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -152,6 +152,8 @@
  * 	This routine notifies the tty driver that it should stop
  * 	outputting characters to the tty device.  
  *
+ *	Called with ->flow_lock held. Serialized with start() method.
+ *
  *	Optional:
  *
  *	Note: Call stop_tty not this method.
@@ -161,6 +163,8 @@
  * 	This routine notifies the tty driver that it resume sending
  *	characters to the tty device.
  *
+ *	Called with ->flow_lock held. Serialized with stop() method.
+ *
  *	Optional:
  *
  *	Note: Call start_tty not this method.
-- 
cgit v1.2.3


From c545b66c6922b002b5fe224a6eaec58c913650b5 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 10 Sep 2014 15:06:33 -0400
Subject: tty: Serialize tcflow() with other tty flow control changes

Use newly-introduced tty->flow_lock to serialize updates to
tty->flow_stopped (via tcflow()) and with concurrent tty flow
control changes from other sources.

Merge the storage for ->stopped and ->flow_stopped, now that both
flags are serialized by ->flow_lock.

The padding bits are necessary to force the compiler to allocate the
type specified; otherwise, gcc will ignore the type specifier and
allocate the minimum number of bytes necessary to store the bitfield.
In turn, this would allow Alpha EV4 and EV5 cpus to corrupt adjacent
byte storage because those cpus use RMW to store byte and short data.

gcc versions < 4.7.2 will also corrupt storage adjacent to bitfields
smaller than unsigned long on ia64, ppc64, hppa64 and sparc64, thus
requiring more than unsigned int storage (which would otherwise be
sufficient to workaround the Alpha non-atomic byte/short storage problem).

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_ioctl.c | 8 ++++++--
 include/linux/tty.h     | 5 +++--
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index cd1285c3bfe9..dcf5c0af7de9 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -1177,16 +1177,20 @@ int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file,
 			return retval;
 		switch (arg) {
 		case TCOOFF:
+			spin_lock_irq(&tty->flow_lock);
 			if (!tty->flow_stopped) {
 				tty->flow_stopped = 1;
-				stop_tty(tty);
+				__stop_tty(tty);
 			}
+			spin_unlock_irq(&tty->flow_lock);
 			break;
 		case TCOON:
+			spin_lock_irq(&tty->flow_lock);
 			if (tty->flow_stopped) {
 				tty->flow_stopped = 0;
-				start_tty(tty);
+				__start_tty(tty);
 			}
+			spin_unlock_irq(&tty->flow_lock);
 			break;
 		case TCIOFF:
 			if (STOP_CHAR(tty) != __DISABLED_CHAR)
diff --git a/include/linux/tty.h b/include/linux/tty.h
index fd4148d3a261..d80b53642f2c 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -262,8 +262,9 @@ struct tty_struct {
 	unsigned long flags;
 	int count;
 	struct winsize winsize;		/* winsize_mutex */
-	int stopped;			/* flow_lock */
-	int flow_stopped;
+	unsigned long stopped:1,	/* flow_lock */
+		      flow_stopped:1,
+		      unused:62;
 	int hw_stopped;
 	int packet;
 	unsigned char ctrl_status;	/* ctrl_lock */
-- 
cgit v1.2.3


From 136d5258b2bc4ffae99cb69874a76624c26fbfad Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 10 Sep 2014 15:06:34 -0400
Subject: tty: Move and rename send_prio_char() as tty_send_xchar()

Relocate the file-scope function, send_prio_char(), as a global
helper tty_send_xchar(). Remove the global declarations for
tty_write_lock()/tty_write_unlock(), as these are file-scope only now.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c    | 33 +++++++++++++++++++++++++++++++--
 drivers/tty/tty_ioctl.c | 33 ++-------------------------------
 include/linux/tty.h     |  3 +--
 3 files changed, 34 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index c249ff1d51ce..2f6f9b5e4891 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1023,14 +1023,14 @@ static ssize_t tty_read(struct file *file, char __user *buf, size_t count,
 	return i;
 }
 
-void tty_write_unlock(struct tty_struct *tty)
+static void tty_write_unlock(struct tty_struct *tty)
 	__releases(&tty->atomic_write_lock)
 {
 	mutex_unlock(&tty->atomic_write_lock);
 	wake_up_interruptible_poll(&tty->write_wait, POLLOUT);
 }
 
-int tty_write_lock(struct tty_struct *tty, int ndelay)
+static int tty_write_lock(struct tty_struct *tty, int ndelay)
 	__acquires(&tty->atomic_write_lock)
 {
 	if (!mutex_trylock(&tty->atomic_write_lock)) {
@@ -1217,6 +1217,35 @@ ssize_t redirected_tty_write(struct file *file, const char __user *buf,
 	return tty_write(file, buf, count, ppos);
 }
 
+/**
+ *	tty_send_xchar	-	send priority character
+ *
+ *	Send a high priority character to the tty even if stopped
+ *
+ *	Locking: none for xchar method, write ordering for write method.
+ */
+
+int tty_send_xchar(struct tty_struct *tty, char ch)
+{
+	int	was_stopped = tty->stopped;
+
+	if (tty->ops->send_xchar) {
+		tty->ops->send_xchar(tty, ch);
+		return 0;
+	}
+
+	if (tty_write_lock(tty, 0) < 0)
+		return -ERESTARTSYS;
+
+	if (was_stopped)
+		start_tty(tty);
+	tty->ops->write(tty, &ch, 1);
+	if (was_stopped)
+		stop_tty(tty);
+	tty_write_unlock(tty);
+	return 0;
+}
+
 static char ptychar[] = "pqrstuvwxyzabcde";
 
 /**
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index dcf5c0af7de9..ad9120d1c0f1 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -911,35 +911,6 @@ static int set_ltchars(struct tty_struct *tty, struct ltchars __user *ltchars)
 }
 #endif
 
-/**
- *	send_prio_char		-	send priority character
- *
- *	Send a high priority character to the tty even if stopped
- *
- *	Locking: none for xchar method, write ordering for write method.
- */
-
-static int send_prio_char(struct tty_struct *tty, char ch)
-{
-	int	was_stopped = tty->stopped;
-
-	if (tty->ops->send_xchar) {
-		tty->ops->send_xchar(tty, ch);
-		return 0;
-	}
-
-	if (tty_write_lock(tty, 0) < 0)
-		return -ERESTARTSYS;
-
-	if (was_stopped)
-		start_tty(tty);
-	tty->ops->write(tty, &ch, 1);
-	if (was_stopped)
-		stop_tty(tty);
-	tty_write_unlock(tty);
-	return 0;
-}
-
 /**
  *	tty_change_softcar	-	carrier change ioctl helper
  *	@tty: tty to update
@@ -1194,11 +1165,11 @@ int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file,
 			break;
 		case TCIOFF:
 			if (STOP_CHAR(tty) != __DISABLED_CHAR)
-				return send_prio_char(tty, STOP_CHAR(tty));
+				return tty_send_xchar(tty, STOP_CHAR(tty));
 			break;
 		case TCION:
 			if (START_CHAR(tty) != __DISABLED_CHAR)
-				return send_prio_char(tty, START_CHAR(tty));
+				return tty_send_xchar(tty, START_CHAR(tty));
 			break;
 		default:
 			return -EINVAL;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index d80b53642f2c..4c6b9fd3c750 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -418,6 +418,7 @@ extern void tty_unregister_device(struct tty_driver *driver, unsigned index);
 extern int tty_read_raw_data(struct tty_struct *tty, unsigned char *bufp,
 			     int buflen);
 extern void tty_write_message(struct tty_struct *tty, char *msg);
+extern int tty_send_xchar(struct tty_struct *tty, char ch);
 extern int tty_put_char(struct tty_struct *tty, unsigned char c);
 extern int tty_chars_in_buffer(struct tty_struct *tty);
 extern int tty_write_room(struct tty_struct *tty);
@@ -502,8 +503,6 @@ extern struct tty_struct *tty_pair_get_pty(struct tty_struct *tty);
 extern struct mutex tty_mutex;
 extern spinlock_t tty_files_lock;
 
-extern void tty_write_unlock(struct tty_struct *tty);
-extern int tty_write_lock(struct tty_struct *tty, int ndelay);
 #define tty_is_writelocked(tty)  (mutex_is_locked(&tty->atomic_write_lock))
 
 extern void tty_port_init(struct tty_port *port);
-- 
cgit v1.2.3


From 99416322dd16b810ba74098cc50ef2a844091d35 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 10 Sep 2014 15:06:36 -0400
Subject: tty: Workaround Alpha non-atomic byte storage in tty_struct

The Alpha EV4/EV5 cpus can corrupt adjacent byte and short data because
those cpus use RMW to store byte and short data. Thus, concurrent adjacent
byte stores could become corrupted, if serialized by a different lock.
tty_struct uses different locks to protect certain fields within the
structure, and thus is vulnerable to byte stores which are not atomic.

Merge the ->ctrl_status byte and packet mode bit, both protected by the
->ctrl_lock, into an unsigned long.

The padding bits are necessary to force the compiler to allocate the
type specified; otherwise, gcc will ignore the type specifier and
allocate the minimum number of bytes required to store the bitfield.
In turn, this would allow Alpha EV4/EV5 cpus to corrupt adjacent byte
or short storage (because those cpus use RMW to store byte and short data).

gcc versions < 4.7.2 will also corrupt storage adjacent to bitfields
smaller than unsigned long on ia64, ppc64, hppa64, and sparc64, thus
requiring more than unsigned int storage (which would otherwise be
sufficient to fix the Alpha non-atomic storage problem).

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 4c6b9fd3c750..546e94557895 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -266,8 +266,9 @@ struct tty_struct {
 		      flow_stopped:1,
 		      unused:62;
 	int hw_stopped;
-	int packet;
-	unsigned char ctrl_status;	/* ctrl_lock */
+	unsigned long ctrl_status:8,	/* ctrl_lock */
+		      packet:1,
+		      unused_ctrl:55;
 	unsigned int receive_room;	/* Bytes free for queue */
 	int flow_change;
 
-- 
cgit v1.2.3


From f2693b430b33d9554daa0f21fbcae57633f8d4f1 Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@freescale.com>
Date: Tue, 19 Aug 2014 09:51:52 +0800
Subject: usb: hcd: add TPL support flag

The targeted hosts (non-PC hosts) need to have TPL (Targeted Peripheral List)
for USB OTG & EH certification and other vendor specific requirements.

The platform who needs TPL feature should set this flag at usb host
controller driver.

Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/hcd.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 485cd5e2100c..a48c89e96988 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -144,6 +144,7 @@ struct usb_hcd {
 	unsigned		has_tt:1;	/* Integrated TT in root hub */
 	unsigned		amd_resume_bug:1; /* AMD remote wakeup quirk */
 	unsigned		can_do_streams:1; /* HC supports streams */
+	unsigned		tpl_support:1; /* OTG & EH TPL support */
 
 	unsigned int		irq;		/* irq allocated */
 	void __iomem		*regs;		/* device memory/io */
-- 
cgit v1.2.3


From 05f8b35a62efb8e70ebcd78e9c957324e9caddad Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@freescale.com>
Date: Tue, 19 Aug 2014 09:51:55 +0800
Subject: usb: common: add API to get if the platform supports TPL

The TPL (Targeted Peripheral List) is used for targeted hosts
(non-PC hosts), and it can be used at USB OTG & EH certification
and some specific products which need white list.

Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/common/usb-common.c | 15 +++++++++++++++
 include/linux/usb/of.h          |  5 +++++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/common/usb-common.c b/drivers/usb/common/usb-common.c
index 6dfd30a863c7..b530fd403ffb 100644
--- a/drivers/usb/common/usb-common.c
+++ b/drivers/usb/common/usb-common.c
@@ -139,6 +139,21 @@ enum usb_device_speed of_usb_get_maximum_speed(struct device_node *np)
 }
 EXPORT_SYMBOL_GPL(of_usb_get_maximum_speed);
 
+/**
+ * of_usb_host_tpl_support - to get if Targeted Peripheral List is supported
+ * for given targeted hosts (non-PC hosts)
+ * @np: Pointer to the given device_node
+ *
+ * The function gets if the targeted hosts support TPL or not
+ */
+bool of_usb_host_tpl_support(struct device_node *np)
+{
+	if (of_find_property(np, "tpl-support", NULL))
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(of_usb_host_tpl_support);
 #endif
 
 MODULE_LICENSE("GPL");
diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h
index 8c38aa26b3bb..cfe0528cdbb1 100644
--- a/include/linux/usb/of.h
+++ b/include/linux/usb/of.h
@@ -14,6 +14,7 @@
 #if IS_ENABLED(CONFIG_OF)
 enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np);
 enum usb_device_speed of_usb_get_maximum_speed(struct device_node *np);
+bool of_usb_host_tpl_support(struct device_node *np);
 #else
 static inline enum usb_dr_mode of_usb_get_dr_mode(struct device_node *np)
 {
@@ -25,6 +26,10 @@ of_usb_get_maximum_speed(struct device_node *np)
 {
 	return USB_SPEED_UNKNOWN;
 }
+static inline bool of_usb_host_tpl_support(struct device_node *np)
+{
+	return false;
+}
 #endif
 
 #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_USB_SUPPORT)
-- 
cgit v1.2.3


From f6a9ff07832a9d30d457e976e6233b4351cd4cdf Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@freescale.com>
Date: Tue, 19 Aug 2014 09:51:56 +0800
Subject: usb: chipidea: add TPL support for targeted hosts

For OTG and Embedded hosts, they may need TPL (Targeted Peripheral List)
for usb certification and other vender specific requirements, the
platform can tell chipidea core driver if it supports tpl through DT
or platform data.

Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/core.c  | 4 ++++
 drivers/usb/chipidea/host.c  | 1 +
 include/linux/usb/chipidea.h | 1 +
 3 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 619d13e29995..41d45a16dd30 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -473,6 +473,10 @@ static int ci_get_platdata(struct device *dev,
 				PTR_ERR(platdata->reg_vbus));
 			return PTR_ERR(platdata->reg_vbus);
 		}
+		/* Get TPL support */
+		if (!platdata->tpl_support)
+			platdata->tpl_support =
+				of_usb_host_tpl_support(dev->of_node);
 	}
 
 	if (of_usb_get_maximum_speed(dev->of_node) == USB_SPEED_FULL)
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index a93d950e9468..0d6b24cb2270 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -60,6 +60,7 @@ static int host_start(struct ci_hdrc *ci)
 
 	hcd->power_budget = ci->platdata->power_budget;
 	hcd->phy = ci->transceiver;
+	hcd->tpl_support = ci->platdata->tpl_support;
 
 	ehci = hcd_to_ehci(hcd);
 	ehci->caps = ci->hw_bank.cap;
diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h
index bbe779f640be..e14c09a45c5a 100644
--- a/include/linux/usb/chipidea.h
+++ b/include/linux/usb/chipidea.h
@@ -31,6 +31,7 @@ struct ci_hdrc_platform_data {
 #define CI_HDRC_CONTROLLER_STOPPED_EVENT	1
 	void	(*notify_event) (struct ci_hdrc *ci, unsigned event);
 	struct regulator	*reg_vbus;
+	bool			tpl_support;
 };
 
 /* Default offset of capability registers */
-- 
cgit v1.2.3


From 593078525c8b234a35a36ff551b8716464e86481 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 15 Sep 2014 16:04:12 +0200
Subject: uas: Add a quirk for rejecting ATA_12 and ATA_16 commands

And set this quirk for the Seagate Expansion Desk (0bc2:2312), as that one
seems to hang upon receiving an ATA_12 or ATA_16 command.

https://bugzilla.kernel.org/show_bug.cgi?id=79511
https://bbs.archlinux.org/viewtopic.php?id=183190

While at it also add missing documentation for the u value for usb-storage
quirks.

Cc: stable@vger.kernel.org # 3.16, 3.17
Signed-off-by: Hans de Goede <hdegoede@redhat.com>

--
Changes in v2: Add documentation for new t and u usb-storage.quirks flags
Changes in v3: Fix typo in documentation
Changes in v4: Also apply the quirk to (0bc2:3312)
Changes in v5: Rebased on 3.17-rc5, drop u documentation, already upstream
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/kernel-parameters.txt |  2 ++
 drivers/usb/storage/uas.c           | 13 +++++++++++++
 drivers/usb/storage/unusual_uas.h   | 23 +++++++++++++----------
 drivers/usb/storage/usb.c           |  6 +++++-
 include/linux/usb_usual.h           |  2 ++
 5 files changed, 35 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 10d51c2f10d7..dd4fe9880e4a 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3541,6 +3541,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					bogus residue values);
 				s = SINGLE_LUN (the device has only one
 					Logical Unit);
+				t = NO_ATA_1X (don't allow ATA(12) and ATA(16)
+					commands, uas only);
 				u = IGNORE_UAS (don't bind to the uas driver);
 				w = NO_WP_DETECT (don't test whether the
 					medium is write-protected).
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 05b2d8e077d9..8c7d4a239f4c 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -28,6 +28,7 @@
 #include <scsi/scsi_tcq.h>
 
 #include "uas-detect.h"
+#include "scsiglue.h"
 
 /*
  * The r00-r01c specs define this version of the SENSE IU data structure.
@@ -49,6 +50,7 @@ struct uas_dev_info {
 	struct usb_anchor cmd_urbs;
 	struct usb_anchor sense_urbs;
 	struct usb_anchor data_urbs;
+	unsigned long flags;
 	int qdepth, resetting;
 	struct response_iu response;
 	unsigned cmd_pipe, status_pipe, data_in_pipe, data_out_pipe;
@@ -714,6 +716,15 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 
 	BUILD_BUG_ON(sizeof(struct uas_cmd_info) > sizeof(struct scsi_pointer));
 
+	if ((devinfo->flags & US_FL_NO_ATA_1X) &&
+			(cmnd->cmnd[0] == ATA_12 || cmnd->cmnd[0] == ATA_16)) {
+		memcpy(cmnd->sense_buffer, usb_stor_sense_invalidCDB,
+		       sizeof(usb_stor_sense_invalidCDB));
+		cmnd->result = SAM_STAT_CHECK_CONDITION;
+		cmnd->scsi_done(cmnd);
+		return 0;
+	}
+
 	spin_lock_irqsave(&devinfo->lock, flags);
 
 	if (devinfo->resetting) {
@@ -1080,6 +1091,8 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	devinfo->resetting = 0;
 	devinfo->running_task = 0;
 	devinfo->shutdown = 0;
+	devinfo->flags = id->driver_info;
+	usb_stor_adjust_quirks(udev, &devinfo->flags);
 	init_usb_anchor(&devinfo->cmd_urbs);
 	init_usb_anchor(&devinfo->sense_urbs);
 	init_usb_anchor(&devinfo->data_urbs);
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 7244444df8ee..3ff2dd4c78ca 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -40,13 +40,16 @@
  * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org>
  */
 
-/*
- * This is an example entry for the US_FL_IGNORE_UAS flag. Once we have an
- * actual entry using US_FL_IGNORE_UAS this entry should be removed.
- *
- * UNUSUAL_DEV(  0xabcd, 0x1234, 0x0100, 0x0100,
- *		"Example",
- *		"Storage with broken UAS",
- *		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
- *		US_FL_IGNORE_UAS),
- */
+/* https://bugzilla.kernel.org/show_bug.cgi?id=79511 */
+UNUSUAL_DEV(0x0bc2, 0x2312, 0x0000, 0x9999,
+		"Seagate",
+		"Expansion Desk",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
+/* https://bbs.archlinux.org/viewtopic.php?id=183190 */
+UNUSUAL_DEV(0x0bc2, 0x3312, 0x0000, 0x9999,
+		"Seagate",
+		"Expansion Desk",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index cedb29252a92..b9d1b9357287 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -478,7 +478,8 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags)
 			US_FL_CAPACITY_OK | US_FL_IGNORE_RESIDUE |
 			US_FL_SINGLE_LUN | US_FL_NO_WP_DETECT |
 			US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16 |
-			US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE);
+			US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE |
+			US_FL_NO_ATA_1X);
 
 	p = quirks;
 	while (*p) {
@@ -543,6 +544,9 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags)
 		case 's':
 			f |= US_FL_SINGLE_LUN;
 			break;
+		case 't':
+			f |= US_FL_NO_ATA_1X;
+			break;
 		case 'u':
 			f |= US_FL_IGNORE_UAS;
 			break;
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 9b7de1b46437..d271f88f30ad 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -73,6 +73,8 @@
 		/* Device advertises UAS but it is broken */	\
 	US_FLAG(BROKEN_FUA,	0x01000000)			\
 		/* Cannot handle FUA in WRITE or READ CDBs */	\
+	US_FLAG(NO_ATA_1X,	0x02000000)			\
+		/* Cannot handle ATA_12 or ATA_16 CDBs */	\
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
-- 
cgit v1.2.3


From 734016b00b50a3c6a0e1fc1b7b217e783f5123a1 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 16 Sep 2014 18:36:52 +0200
Subject: uas: Add no-report-opcodes quirk

Besides the ASM1051 (*) needing sdev->no_report_opcodes = 1, it turns out that
the JMicron JMS567 also needs it to work properly with uas (usb-storage always
sets it). Since some of the scsi devs were not to keen on the idea to
outrightly set sdev->no_report_opcodes = 1 for all uas devices, so add a quirk
for this, and set it for the JMS567.

*) Which has become a non-issue since we've completely blacklisted uas on
the ASM1051 for other reasons

Cc: stable@vger.kernel.org
Reported-and-tested-by: Claudio Bizzarri <claudio.bizzarri@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/kernel-parameters.txt | 2 ++
 drivers/usb/storage/uas.c           | 4 ++++
 drivers/usb/storage/unusual_uas.h   | 7 +++++++
 drivers/usb/storage/usb.c           | 5 ++++-
 include/linux/usb_usual.h           | 2 ++
 5 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index dd4fe9880e4a..1edd5fdc629d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3522,6 +3522,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					READ_DISC_INFO command);
 				e = NO_READ_CAPACITY_16 (don't use
 					READ_CAPACITY_16 command);
+				f = NO_REPORT_OPCODES (don't use report opcodes
+					command, uas only);
 				h = CAPACITY_HEURISTICS (decrease the
 					reported device capacity by one
 					sector if the number is odd);
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 8c7d4a239f4c..cad02ac88564 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -961,6 +961,10 @@ static int uas_slave_alloc(struct scsi_device *sdev)
 static int uas_slave_configure(struct scsi_device *sdev)
 {
 	struct uas_dev_info *devinfo = sdev->hostdata;
+
+	if (devinfo->flags & US_FL_NO_REPORT_OPCODES)
+		sdev->no_report_opcodes = 1;
+
 	scsi_set_tag_type(sdev, MSG_ORDERED_TAG);
 	scsi_activate_tcq(sdev, devinfo->qdepth - 2);
 	return 0;
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 3ff2dd4c78ca..3e6243719df8 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -53,3 +53,10 @@ UNUSUAL_DEV(0x0bc2, 0x3312, 0x0000, 0x9999,
 		"Expansion Desk",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_ATA_1X),
+
+/* Reported-by: Claudio Bizzarri <claudio.bizzarri@gmail.com> */
+UNUSUAL_DEV(0x152d, 0x0567, 0x0000, 0x9999,
+		"JMicron",
+		"JMS567",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index b9d1b9357287..f60e7d463636 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -479,7 +479,7 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags)
 			US_FL_SINGLE_LUN | US_FL_NO_WP_DETECT |
 			US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16 |
 			US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE |
-			US_FL_NO_ATA_1X);
+			US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES);
 
 	p = quirks;
 	while (*p) {
@@ -517,6 +517,9 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags)
 		case 'e':
 			f |= US_FL_NO_READ_CAPACITY_16;
 			break;
+		case 'f':
+			f |= US_FL_NO_REPORT_OPCODES;
+			break;
 		case 'h':
 			f |= US_FL_CAPACITY_HEURISTICS;
 			break;
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index d271f88f30ad..a7f2604c5f25 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -75,6 +75,8 @@
 		/* Cannot handle FUA in WRITE or READ CDBs */	\
 	US_FLAG(NO_ATA_1X,	0x02000000)			\
 		/* Cannot handle ATA_12 or ATA_16 CDBs */	\
+	US_FLAG(NO_REPORT_OPCODES,	0x04000000)		\
+		/* Cannot handle MI_REPORT_SUPPORTED_OPERATION_CODES */	\
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
-- 
cgit v1.2.3


From ddbe1fca0bcb87ca8c199ea873a456ca8a948567 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Fri, 19 Sep 2014 10:13:50 +0800
Subject: USB: Add device quirk for ASUS T100 Base Station keyboard

This full-speed USB device generates spurious remote wakeup event
as soon as USB_DEVICE_REMOTE_WAKEUP feature is set. As the result,
Linux can't enter system suspend and S0ix power saving modes once
this keyboard is used.

This patch tries to introduce USB_QUIRK_IGNORE_REMOTE_WAKEUP quirk.
With this quirk set, wakeup capability will be ignored during
device configure.

This patch could be back-ported to kernels as old as 2.6.39.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c     | 6 ++++--
 drivers/usb/core/quirks.c  | 4 ++++
 include/linux/usb/quirks.h | 3 +++
 3 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index db1d587cbb95..d5419292f89f 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1984,8 +1984,10 @@ void usb_set_device_state(struct usb_device *udev,
 					|| new_state == USB_STATE_SUSPENDED)
 				;	/* No change to wakeup settings */
 			else if (new_state == USB_STATE_CONFIGURED)
-				wakeup = udev->actconfig->desc.bmAttributes
-					 & USB_CONFIG_ATT_WAKEUP;
+				wakeup = (udev->quirks &
+					USB_QUIRK_IGNORE_REMOTE_WAKEUP) ? 0 :
+					udev->actconfig->desc.bmAttributes &
+					USB_CONFIG_ATT_WAKEUP;
 			else
 				wakeup = 0;
 		}
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index a342a783d496..5ae883dc21f5 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -163,6 +163,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* USB3503 */
 	{ USB_DEVICE(0x0424, 0x3503), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* ASUS Base Station(T100) */
+	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
+			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
 	{ }  /* terminating entry must be last */
 };
 
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index ffe565c94743..a4abaeb3fb00 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -44,4 +44,7 @@
 /* device can't handle device_qualifier descriptor requests */
 #define USB_QUIRK_DEVICE_QUALIFIER	0x00000100
 
+/* device generates spurious wakeup, ignore remote wakeup capability */
+#define USB_QUIRK_IGNORE_REMOTE_WAKEUP	0x00000200
+
 #endif /* __LINUX_USB_QUIRKS_H */
-- 
cgit v1.2.3


From 5cb307c4c27a9f37ef0c8e6bedc8c53c9197f48f Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 23 Sep 2014 22:23:55 -0700
Subject: USB: quirks.h: use BIT()

Use the BIT macro instead of "open coding" bit fields.  This makes it
easier to actually see that the bits are not conflicting/overlapping.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/quirks.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index a4abaeb3fb00..9948c874e3f1 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -8,27 +8,27 @@
 #define __LINUX_USB_QUIRKS_H
 
 /* string descriptors must not be fetched using a 255-byte read */
-#define USB_QUIRK_STRING_FETCH_255	0x00000001
+#define USB_QUIRK_STRING_FETCH_255		BIT(0)
 
 /* device can't resume correctly so reset it instead */
-#define USB_QUIRK_RESET_RESUME		0x00000002
+#define USB_QUIRK_RESET_RESUME			BIT(1)
 
 /* device can't handle Set-Interface requests */
-#define USB_QUIRK_NO_SET_INTF		0x00000004
+#define USB_QUIRK_NO_SET_INTF			BIT(2)
 
 /* device can't handle its Configuration or Interface strings */
-#define USB_QUIRK_CONFIG_INTF_STRINGS	0x00000008
+#define USB_QUIRK_CONFIG_INTF_STRINGS		BIT(3)
 
 /* device can't be reset(e.g morph devices), don't use reset */
-#define USB_QUIRK_RESET			0x00000010
+#define USB_QUIRK_RESET				BIT(4)
 
 /* device has more interface descriptions than the bNumInterfaces count,
    and can't handle talking to these interfaces */
-#define USB_QUIRK_HONOR_BNUMINTERFACES	0x00000020
+#define USB_QUIRK_HONOR_BNUMINTERFACES		BIT(5)
 
 /* device needs a pause during initialization, after we read the device
    descriptor */
-#define USB_QUIRK_DELAY_INIT		0x00000040
+#define USB_QUIRK_DELAY_INIT			BIT(6)
 
 /*
  * For high speed and super speed interupt endpoints, the USB 2.0 and
@@ -39,12 +39,12 @@
  * Devices with this quirk report their bInterval as the result of this
  * calculation instead of the exponent variable used in the calculation.
  */
-#define USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL	0x00000080
+#define USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL	BIT(7)
 
 /* device can't handle device_qualifier descriptor requests */
-#define USB_QUIRK_DEVICE_QUALIFIER	0x00000100
+#define USB_QUIRK_DEVICE_QUALIFIER		BIT(8)
 
 /* device generates spurious wakeup, ignore remote wakeup capability */
-#define USB_QUIRK_IGNORE_REMOTE_WAKEUP	0x00000200
+#define USB_QUIRK_IGNORE_REMOTE_WAKEUP		BIT(9)
 
 #endif /* __LINUX_USB_QUIRKS_H */
-- 
cgit v1.2.3


From 833c95456a70826d1384883b73fd23aff24d366f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 12 Sep 2014 09:01:56 +0200
Subject: device coredump: add new device coredump class

Many devices run firmware and/or complex hardware, and most of that
can have bugs. When it misbehaves, however, it is often much harder
to debug than software running on the host.

Introduce a "device coredump" mechanism to allow dumping internal
device/firmware state through a generalized mechanism. As devices
are different and information needed can vary accordingly, this
doesn't prescribe a file format - it just provides mechanism to
get data to be able to capture it in a generalized way (e.g. in
distributions.)

The dumped data will be readable in sysfs in the virtual device's
data file under /sys/class/devcoredump/devcd*/. Writing to it will
free the data and remove the device, as does a 5-minute timeout.

Note that generalized capturing of such data may result in privacy
issues, so users generally need to be involved. In order to allow
certain users/system integrators/... to disable the feature at all,
introduce a Kconfig option to override the drivers that would like
to have the feature.

For now, this provides two ways of dumping data:
 1) with a vmalloc'ed area, that is then given to the subsystem
    and freed after retrieval or timeout
 2) with a generalized reader/free function method

We could/should add more options, e.g. a list of pages, since the
vmalloc area is very limited on some architectures.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS                 |   7 ++
 drivers/base/Kconfig        |  21 ++++
 drivers/base/Makefile       |   1 +
 drivers/base/devcoredump.c  | 265 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/devcoredump.h |  35 ++++++
 5 files changed, 329 insertions(+)
 create mode 100644 drivers/base/devcoredump.c
 create mode 100644 include/linux/devcoredump.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 809ecd680d88..d810a6fa8276 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2859,6 +2859,13 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
 S:	Maintained
 F:	drivers/usb/dwc3/
 
+DEVICE COREDUMP (DEV_COREDUMP)
+M:	Johannes Berg <johannes@sipsolutions.net>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/base/devcoredump.c
+F:	include/linux/devcoredump.h
+
 DEVICE FREQUENCY (DEVFREQ)
 M:	MyungJoo Ham <myungjoo.ham@samsung.com>
 M:	Kyungmin Park <kyungmin.park@samsung.com>
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 4e7f0ff83ae7..134f763d90fd 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -165,6 +165,27 @@ config FW_LOADER_USER_HELPER_FALLBACK
 
 	  If you are unsure about this, say N here.
 
+config WANT_DEV_COREDUMP
+	bool
+	help
+	  Drivers should "select" this option if they desire to use the
+	  device coredump mechanism.
+
+config DISABLE_DEV_COREDUMP
+	bool "Disable device coredump" if EXPERT
+	help
+	  Disable the device coredump mechanism despite drivers wanting to
+	  use it; this allows for more sensitive systems or systems that
+	  don't want to ever access the information to not have the code,
+	  nor keep any data.
+
+	  If unsure, say N.
+
+config DEV_COREDUMP
+	bool
+	default y if WANT_DEV_COREDUMP
+	depends on !DISABLE_DEV_COREDUMP
+
 config DEBUG_DRIVER
 	bool "Driver Core verbose debug messages"
 	depends on DEBUG_KERNEL
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 4aab26ec0292..6922cd6850a2 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_SYS_HYPERVISOR) += hypervisor.o
 obj-$(CONFIG_REGMAP)	+= regmap/
 obj-$(CONFIG_SOC_BUS) += soc.o
 obj-$(CONFIG_PINCTRL) += pinctrl.o
+obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o
 
 ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
 
diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c
new file mode 100644
index 000000000000..96614b04544c
--- /dev/null
+++ b/drivers/base/devcoredump.c
@@ -0,0 +1,265 @@
+/*
+ * This file is provided under the GPLv2 license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Mobile Communications GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * Contact Information:
+ *  Intel Linux Wireless <ilw@linux.intel.com>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ * Author: Johannes Berg <johannes@sipsolutions.net>
+ */
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/devcoredump.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/workqueue.h>
+
+/* if data isn't read by userspace after 5 minutes then delete it */
+#define DEVCD_TIMEOUT	(HZ * 60 * 5)
+
+struct devcd_entry {
+	struct device devcd_dev;
+	const void *data;
+	size_t datalen;
+	struct module *owner;
+	ssize_t (*read)(char *buffer, loff_t offset, size_t count,
+			const void *data, size_t datalen);
+	void (*free)(const void *data);
+	struct delayed_work del_wk;
+	struct device *failing_dev;
+};
+
+static struct devcd_entry *dev_to_devcd(struct device *dev)
+{
+	return container_of(dev, struct devcd_entry, devcd_dev);
+}
+
+static void devcd_dev_release(struct device *dev)
+{
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	devcd->free(devcd->data);
+	module_put(devcd->owner);
+
+	/*
+	 * this seems racy, but I don't see a notifier or such on
+	 * a struct device to know when it goes away?
+	 */
+	if (devcd->failing_dev->kobj.sd)
+		sysfs_delete_link(&devcd->failing_dev->kobj, &dev->kobj,
+				  "devcoredump");
+
+	put_device(devcd->failing_dev);
+	kfree(devcd);
+}
+
+static void devcd_del(struct work_struct *wk)
+{
+	struct devcd_entry *devcd;
+
+	devcd = container_of(wk, struct devcd_entry, del_wk.work);
+
+	device_del(&devcd->devcd_dev);
+	put_device(&devcd->devcd_dev);
+}
+
+static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj,
+			       struct bin_attribute *bin_attr,
+			       char *buffer, loff_t offset, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	return devcd->read(buffer, offset, count, devcd->data, devcd->datalen);
+}
+
+static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *bin_attr,
+				char *buffer, loff_t offset, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	mod_delayed_work(system_wq, &devcd->del_wk, 0);
+
+	return count;
+}
+
+static struct bin_attribute devcd_attr_data = {
+	.attr = { .name = "data", .mode = S_IRUSR | S_IWUSR, },
+	.size = 0,
+	.read = devcd_data_read,
+	.write = devcd_data_write,
+};
+
+static struct bin_attribute *devcd_dev_bin_attrs[] = {
+	&devcd_attr_data, NULL,
+};
+
+static const struct attribute_group devcd_dev_group = {
+	.bin_attrs = devcd_dev_bin_attrs,
+};
+
+static const struct attribute_group *devcd_dev_groups[] = {
+	&devcd_dev_group, NULL,
+};
+
+static struct class devcd_class = {
+	.name		= "devcoredump",
+	.owner		= THIS_MODULE,
+	.dev_release	= devcd_dev_release,
+	.dev_groups	= devcd_dev_groups,
+};
+
+static ssize_t devcd_readv(char *buffer, loff_t offset, size_t count,
+			   const void *data, size_t datalen)
+{
+	if (offset > datalen)
+		return -EINVAL;
+
+	if (offset + count > datalen)
+		count = datalen - offset;
+
+	if (count)
+		memcpy(buffer, ((u8 *)data) + offset, count);
+
+	return count;
+}
+
+/**
+ * dev_coredumpv - create device coredump with vmalloc data
+ * @dev: the struct device for the crashed device
+ * @data: vmalloc data containing the device coredump
+ * @datalen: length of the data
+ * @gfp: allocation flags
+ *
+ * This function takes ownership of the vmalloc'ed data and will free
+ * it when it is no longer used. See dev_coredumpm() for more information.
+ */
+void dev_coredumpv(struct device *dev, const void *data, size_t datalen,
+		   gfp_t gfp)
+{
+	dev_coredumpm(dev, NULL, data, datalen, gfp, devcd_readv, vfree);
+}
+EXPORT_SYMBOL_GPL(dev_coredumpv);
+
+static int devcd_match_failing(struct device *dev, const void *failing)
+{
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	return devcd->failing_dev == failing;
+}
+
+/**
+ * dev_coredumpm - create device coredump with read/free methods
+ * @dev: the struct device for the crashed device
+ * @owner: the module that contains the read/free functions, use %THIS_MODULE
+ * @data: data cookie for the @read/@free functions
+ * @datalen: length of the data
+ * @gfp: allocation flags
+ * @read: function to read from the given buffer
+ * @free: function to free the given buffer
+ *
+ * Creates a new device coredump for the given device. If a previous one hasn't
+ * been read yet, the new coredump is discarded. The data lifetime is determined
+ * by the device coredump framework and when it is no longer needed the @free
+ * function will be called to free the data.
+ */
+void dev_coredumpm(struct device *dev, struct module *owner,
+		   const void *data, size_t datalen, gfp_t gfp,
+		   ssize_t (*read)(char *buffer, loff_t offset, size_t count,
+				   const void *data, size_t datalen),
+		   void (*free)(const void *data))
+{
+	static atomic_t devcd_count = ATOMIC_INIT(0);
+	struct devcd_entry *devcd;
+	struct device *existing;
+
+	existing = class_find_device(&devcd_class, NULL, dev,
+				     devcd_match_failing);
+	if (existing) {
+		put_device(existing);
+		goto free;
+	}
+
+	if (!try_module_get(owner))
+		goto free;
+
+	devcd = kzalloc(sizeof(*devcd), gfp);
+	if (!devcd)
+		goto put_module;
+
+	devcd->owner = owner;
+	devcd->data = data;
+	devcd->datalen = datalen;
+	devcd->read = read;
+	devcd->free = free;
+	devcd->failing_dev = get_device(dev);
+
+	device_initialize(&devcd->devcd_dev);
+
+	dev_set_name(&devcd->devcd_dev, "devcd%d",
+		     atomic_inc_return(&devcd_count));
+	devcd->devcd_dev.class = &devcd_class;
+
+	if (device_add(&devcd->devcd_dev))
+		goto put_device;
+
+	if (sysfs_create_link(&devcd->devcd_dev.kobj, &dev->kobj,
+			      "failing_device"))
+		/* nothing - symlink will be missing */;
+
+	if (sysfs_create_link(&dev->kobj, &devcd->devcd_dev.kobj,
+			      "devcoredump"))
+		/* nothing - symlink will be missing */;
+
+	INIT_DELAYED_WORK(&devcd->del_wk, devcd_del);
+	schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT);
+
+	return;
+ put_device:
+	put_device(&devcd->devcd_dev);
+ put_module:
+	module_put(owner);
+ free:
+	free(data);
+}
+EXPORT_SYMBOL_GPL(dev_coredumpm);
+
+static int __init devcoredump_init(void)
+{
+	return class_register(&devcd_class);
+}
+__initcall(devcoredump_init);
+
+static int devcd_free(struct device *dev, void *data)
+{
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	flush_delayed_work(&devcd->del_wk);
+	return 0;
+}
+
+static void __exit devcoredump_exit(void)
+{
+	class_for_each_device(&devcd_class, NULL, NULL, devcd_free);
+	class_unregister(&devcd_class);
+}
+__exitcall(devcoredump_exit);
diff --git a/include/linux/devcoredump.h b/include/linux/devcoredump.h
new file mode 100644
index 000000000000..c0a360e99f64
--- /dev/null
+++ b/include/linux/devcoredump.h
@@ -0,0 +1,35 @@
+#ifndef __DEVCOREDUMP_H
+#define __DEVCOREDUMP_H
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+
+#ifdef CONFIG_DEV_COREDUMP
+void dev_coredumpv(struct device *dev, const void *data, size_t datalen,
+		   gfp_t gfp);
+
+void dev_coredumpm(struct device *dev, struct module *owner,
+		   const void *data, size_t datalen, gfp_t gfp,
+		   ssize_t (*read)(char *buffer, loff_t offset, size_t count,
+				   const void *data, size_t datalen),
+		   void (*free)(const void *data));
+#else
+static inline void dev_coredumpv(struct device *dev, const void *data,
+				 size_t datalen, gfp_t gfp)
+{
+	vfree(data);
+}
+
+static inline void
+dev_coredumpm(struct device *dev, struct module *owner,
+	      const void *data, size_t datalen, gfp_t gfp,
+	      ssize_t (*read)(char *buffer, loff_t offset, size_t count,
+			      const void *data, size_t datalen),
+	      void (*free)(const void *data))
+{
+	free(data);
+}
+#endif /* CONFIG_DEV_COREDUMP */
+
+#endif /* __DEVCOREDUMP_H */
-- 
cgit v1.2.3


From 36c53b3cc3fac6952af68f43609b15ae050c9318 Mon Sep 17 00:00:00 2001
From: Federico Vaga <federico.vaga@cern.ch>
Date: Tue, 2 Sep 2014 17:31:40 +0200
Subject: ipack: save carrier owner to allow device to get it

There was not any kind of protection against carrier driver removal.
In this way, device driver can 'get' the carrier driver when it is
using it.

Signed-off-by: Federico Vaga <federico.vaga@cern.ch>
Acked-by: Samuel Iglesias Gonsalvez <siglesias@igalia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/ipack/carriers/tpci200.c |  3 ++-
 drivers/ipack/ipack.c            |  4 +++-
 include/linux/ipack.h            | 24 +++++++++++++++++++++++-
 3 files changed, 28 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/ipack/carriers/tpci200.c b/drivers/ipack/carriers/tpci200.c
index de5e32151a1e..9b23843dcad4 100644
--- a/drivers/ipack/carriers/tpci200.c
+++ b/drivers/ipack/carriers/tpci200.c
@@ -572,7 +572,8 @@ static int tpci200_pci_probe(struct pci_dev *pdev,
 	/* Register the carrier in the industry pack bus driver */
 	tpci200->info->ipack_bus = ipack_bus_register(&pdev->dev,
 						      TPCI200_NB_SLOT,
-						      &tpci200_bus_ops);
+						      &tpci200_bus_ops,
+						      THIS_MODULE);
 	if (!tpci200->info->ipack_bus) {
 		dev_err(&pdev->dev,
 			"error registering the carrier on ipack driver\n");
diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c
index d0016ba469ed..c0e7b624ce54 100644
--- a/drivers/ipack/ipack.c
+++ b/drivers/ipack/ipack.c
@@ -206,7 +206,8 @@ static struct bus_type ipack_bus_type = {
 };
 
 struct ipack_bus_device *ipack_bus_register(struct device *parent, int slots,
-					    const struct ipack_bus_ops *ops)
+					    const struct ipack_bus_ops *ops,
+					    struct module *owner)
 {
 	int bus_nr;
 	struct ipack_bus_device *bus;
@@ -225,6 +226,7 @@ struct ipack_bus_device *ipack_bus_register(struct device *parent, int slots,
 	bus->parent = parent;
 	bus->slots = slots;
 	bus->ops = ops;
+	bus->owner = owner;
 	return bus;
 }
 EXPORT_SYMBOL_GPL(ipack_bus_register);
diff --git a/include/linux/ipack.h b/include/linux/ipack.h
index 1888e06ddf64..8bddc3fbdddf 100644
--- a/include/linux/ipack.h
+++ b/include/linux/ipack.h
@@ -172,6 +172,7 @@ struct ipack_bus_ops {
  *	@ops: bus operations for the mezzanine drivers
  */
 struct ipack_bus_device {
+	struct module *owner;
 	struct device *parent;
 	int slots;
 	int bus_nr;
@@ -189,7 +190,8 @@ struct ipack_bus_device {
  * available bus device in ipack.
  */
 struct ipack_bus_device *ipack_bus_register(struct device *parent, int slots,
-					    const struct ipack_bus_ops *ops);
+					    const struct ipack_bus_ops *ops,
+					    struct module *owner);
 
 /**
  *	ipack_bus_unregister -- unregister an ipack bus
@@ -265,3 +267,23 @@ void ipack_put_device(struct ipack_device *dev);
 	 .format = (_format), \
 	 .vendor = (vend), \
 	 .device = (dev)
+
+/**
+ * ipack_get_carrier - it increase the carrier ref. counter of
+ *                     the carrier module
+ * @dev: mezzanine device which wants to get the carrier
+ */
+static inline int ipack_get_carrier(struct ipack_device *dev)
+{
+	return try_module_get(dev->bus->owner);
+}
+
+/**
+ * ipack_get_carrier - it decrease the carrier ref. counter of
+ *                     the carrier module
+ * @dev: mezzanine device which wants to get the carrier
+ */
+static inline void ipack_put_carrier(struct ipack_device *dev)
+{
+	module_put(dev->bus->owner);
+}
-- 
cgit v1.2.3


From ffdbb715fa0c53203b1ea2a6ecc54bdcc8951612 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Thu, 28 Aug 2014 14:14:09 +0100
Subject: misc: st_kim: Increase size of dev_name buffer to incorporate
 termination

Calling strncpy with a maximum size argument of 32 bytes on destination
array kim_gdata->dev_name of size 32 bytes might leave the destination
string unterminated.

Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/ti_wilink_st.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h
index 932b76392248..884d6263e962 100644
--- a/include/linux/ti_wilink_st.h
+++ b/include/linux/ti_wilink_st.h
@@ -268,7 +268,7 @@ struct kim_data_s {
 	struct st_data_s *core_data;
 	struct chip_version version;
 	unsigned char ldisc_install;
-	unsigned char dev_name[UART_DEV_NAME_LEN];
+	unsigned char dev_name[UART_DEV_NAME_LEN + 1];
 	unsigned char flow_cntrl;
 	unsigned long baud_rate;
 };
-- 
cgit v1.2.3


From 26d8f6f15112b8b0fbff360c360e8c42bf2bc370 Mon Sep 17 00:00:00 2001
From: Frank Haverkamp <haver@linux.vnet.ibm.com>
Date: Wed, 10 Sep 2014 16:37:48 +0200
Subject: GenWQE: Update author information

Updated email address of co-author.

Signed-off-by: Frank Haverkamp <haver@linux.vnet.ibm.com>
Signed-off-by: Michael Jung <mijung@gmx.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/genwqe/card_base.c         | 4 ++--
 drivers/misc/genwqe/card_base.h         | 2 +-
 drivers/misc/genwqe/card_ddcb.c         | 2 +-
 drivers/misc/genwqe/card_ddcb.h         | 2 +-
 drivers/misc/genwqe/card_debugfs.c      | 2 +-
 drivers/misc/genwqe/card_dev.c          | 2 +-
 drivers/misc/genwqe/card_sysfs.c        | 2 +-
 drivers/misc/genwqe/card_utils.c        | 2 +-
 drivers/misc/genwqe/genwqe_driver.h     | 2 +-
 include/uapi/linux/genwqe/genwqe_card.h | 2 +-
 10 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c
index c60ad4bd7ed6..12926c8c0609 100644
--- a/drivers/misc/genwqe/card_base.c
+++ b/drivers/misc/genwqe/card_base.c
@@ -5,7 +5,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -45,7 +45,7 @@
 MODULE_AUTHOR("Frank Haverkamp <haver@linux.vnet.ibm.com>");
 MODULE_AUTHOR("Michael Ruettger <michael@ibmra.de>");
 MODULE_AUTHOR("Joerg-Stephan Vogt <jsvogt@de.ibm.com>");
-MODULE_AUTHOR("Michal Jung <mijung@de.ibm.com>");
+MODULE_AUTHOR("Michael Jung <mijung@gmx.net>");
 
 MODULE_DESCRIPTION("GenWQE Card");
 MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/misc/genwqe/card_base.h b/drivers/misc/genwqe/card_base.h
index 37657d6228de..b622d204b72b 100644
--- a/drivers/misc/genwqe/card_base.h
+++ b/drivers/misc/genwqe/card_base.h
@@ -8,7 +8,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/drivers/misc/genwqe/card_ddcb.c b/drivers/misc/genwqe/card_ddcb.c
index 1102e1ef8104..75ff67485fdf 100644
--- a/drivers/misc/genwqe/card_ddcb.c
+++ b/drivers/misc/genwqe/card_ddcb.c
@@ -5,7 +5,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/drivers/misc/genwqe/card_ddcb.h b/drivers/misc/genwqe/card_ddcb.h
index c4f26720753e..0361a68d79a6 100644
--- a/drivers/misc/genwqe/card_ddcb.h
+++ b/drivers/misc/genwqe/card_ddcb.h
@@ -8,7 +8,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/drivers/misc/genwqe/card_debugfs.c b/drivers/misc/genwqe/card_debugfs.c
index 170a7915497c..40b425d35866 100644
--- a/drivers/misc/genwqe/card_debugfs.c
+++ b/drivers/misc/genwqe/card_debugfs.c
@@ -5,7 +5,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index aae42555e2ca..80fdde2873de 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -5,7 +5,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/drivers/misc/genwqe/card_sysfs.c b/drivers/misc/genwqe/card_sysfs.c
index 1d1c6069ebd7..2c33fbca9225 100644
--- a/drivers/misc/genwqe/card_sysfs.c
+++ b/drivers/misc/genwqe/card_sysfs.c
@@ -5,7 +5,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index a6400f09229c..349b342c369b 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -5,7 +5,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/drivers/misc/genwqe/genwqe_driver.h b/drivers/misc/genwqe/genwqe_driver.h
index e39d81fd93c4..15355350e076 100644
--- a/drivers/misc/genwqe/genwqe_driver.h
+++ b/drivers/misc/genwqe/genwqe_driver.h
@@ -8,7 +8,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/include/uapi/linux/genwqe/genwqe_card.h b/include/uapi/linux/genwqe/genwqe_card.h
index 4fc065f29255..baa93fb4cd4f 100644
--- a/include/uapi/linux/genwqe/genwqe_card.h
+++ b/include/uapi/linux/genwqe/genwqe_card.h
@@ -8,7 +8,7 @@
  *
  * Author: Frank Haverkamp <haver@linux.vnet.ibm.com>
  * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com>
- * Author: Michael Jung <mijung@de.ibm.com>
+ * Author: Michael Jung <mijung@gmx.net>
  * Author: Michael Ruettger <michael@ibmra.de>
  *
  * This program is free software; you can redistribute it and/or modify
-- 
cgit v1.2.3


From c9f21cb6388898bfe69886d001316dae7ecc9a4b Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Fri, 5 Sep 2014 10:31:09 -0500
Subject: crypto: ccp - Check for CCP before registering crypto algs

If the ccp is built as a built-in module, then ccp-crypto (whether
built as a module or a built-in module) will be able to load and
it will register its crypto algorithms.  If the system does not have
a CCP this will result in -ENODEV being returned whenever a command
is attempted to be queued by the registered crypto algorithms.

Add an API, ccp_present(), that checks for the presence of a CCP
on the system.  The ccp-crypto module can use this to determine if it
should register it's crypto alogorithms.

Cc: stable@vger.kernel.org
Reported-by: Scot Doyle <lkml14@scotdoyle.com>
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Scot Doyle <lkml14@scotdoyle.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/ccp-crypto-main.c |  4 ++++
 drivers/crypto/ccp/ccp-dev.c         | 14 ++++++++++++++
 include/linux/ccp.h                  | 12 ++++++++++++
 3 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/drivers/crypto/ccp/ccp-crypto-main.c b/drivers/crypto/ccp/ccp-crypto-main.c
index 20dc848481e7..4d4e016d755b 100644
--- a/drivers/crypto/ccp/ccp-crypto-main.c
+++ b/drivers/crypto/ccp/ccp-crypto-main.c
@@ -367,6 +367,10 @@ static int ccp_crypto_init(void)
 {
 	int ret;
 
+	ret = ccp_present();
+	if (ret)
+		return ret;
+
 	spin_lock_init(&req_queue_lock);
 	INIT_LIST_HEAD(&req_queue.cmds);
 	req_queue.backlog = &req_queue.cmds;
diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c
index a7d110652a74..c6e6171eb6d3 100644
--- a/drivers/crypto/ccp/ccp-dev.c
+++ b/drivers/crypto/ccp/ccp-dev.c
@@ -54,6 +54,20 @@ static inline void ccp_del_device(struct ccp_device *ccp)
 	ccp_dev = NULL;
 }
 
+/**
+ * ccp_present - check if a CCP device is present
+ *
+ * Returns zero if a CCP device is present, -ENODEV otherwise.
+ */
+int ccp_present(void)
+{
+	if (ccp_get_device())
+		return 0;
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(ccp_present);
+
 /**
  * ccp_enqueue_cmd - queue an operation for processing by the CCP
  *
diff --git a/include/linux/ccp.h b/include/linux/ccp.h
index ebcc9d146219..7f437036baa4 100644
--- a/include/linux/ccp.h
+++ b/include/linux/ccp.h
@@ -26,6 +26,13 @@ struct ccp_cmd;
 #if defined(CONFIG_CRYPTO_DEV_CCP_DD) || \
 	defined(CONFIG_CRYPTO_DEV_CCP_DD_MODULE)
 
+/**
+ * ccp_present - check if a CCP device is present
+ *
+ * Returns zero if a CCP device is present, -ENODEV otherwise.
+ */
+int ccp_present(void);
+
 /**
  * ccp_enqueue_cmd - queue an operation for processing by the CCP
  *
@@ -53,6 +60,11 @@ int ccp_enqueue_cmd(struct ccp_cmd *cmd);
 
 #else /* CONFIG_CRYPTO_DEV_CCP_DD is not enabled */
 
+static inline int ccp_present(void)
+{
+	return -ENODEV;
+}
+
 static inline int ccp_enqueue_cmd(struct ccp_cmd *cmd)
 {
 	return -ENODEV;
-- 
cgit v1.2.3


From bc5a5b02331a3175a5fca20a4beba249e573b672 Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Tue, 2 Sep 2014 19:21:47 -0700
Subject: Drivers: hv: util: Properly pack the data for file copy functionality

Properly pack the data for file copy functionality. Patch based on
investigation done by Matej Muzila <mmuzila@redhat.com>

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Reported-by: <qge@redhat.com>
Cc: <stable@vger.kernel.org>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/hyperv.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h
index 78e4a86030dd..0a8e6badb29b 100644
--- a/include/uapi/linux/hyperv.h
+++ b/include/uapi/linux/hyperv.h
@@ -137,7 +137,7 @@ struct hv_do_fcopy {
 	__u64	offset;
 	__u32	size;
 	__u8	data[DATA_FRAGMENT];
-};
+} __attribute__((packed));
 
 /*
  * An implementation of HyperV key value pair (KVP) functionality for Linux.
-- 
cgit v1.2.3


From bef59c5024be687ef4f228915af9961307a779ab Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 20 Aug 2014 15:26:35 +0200
Subject: devres: Improve devm_kasprintf()/kvasprintf() support

  - Add devm_kasprintf()/kvasprintf(), introduced by commit
    75f2a4ead5d5890ada9c2663a70fb58613c0d9f2 ("devres: Add
    devm_kasprintf and devm_kvasprintf API"), to
    Documentation/driver-model/devres.txt,
  - Improve kernel doc: the string is not an existing formatted string,
    but is formatted into the newly-allocated buffer,
  - Add a __printf() annotation to devm_kasprintf(), so the compiler
    will verify the format string argument types.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/driver-model/devres.txt |  2 ++
 drivers/base/devres.c                 | 15 ++++++++-------
 include/linux/device.h                |  4 ++--
 3 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index ffa2d0e67a5d..40677443c0c5 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -293,12 +293,14 @@ MDIO
 MEM
   devm_free_pages()
   devm_get_free_pages()
+  devm_kasprintf()
   devm_kcalloc()
   devm_kfree()
   devm_kmalloc()
   devm_kmalloc_array()
   devm_kmemdup()
   devm_kstrdup()
+  devm_kvasprintf()
   devm_kzalloc()
 
 PCI
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 69d9b0c89a01..c8a53d1e019f 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -817,13 +817,13 @@ char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp)
 EXPORT_SYMBOL_GPL(devm_kstrdup);
 
 /**
- * devm_kvasprintf - Allocate resource managed space
- *			for the formatted string.
+ * devm_kvasprintf - Allocate resource managed space and format a string
+ *		     into that.
  * @dev: Device to allocate memory for
  * @gfp: the GFP mask used in the devm_kmalloc() call when
  *       allocating memory
- * @fmt: the formatted string to duplicate
- * @ap: the list of tokens to be placed in the formatted string
+ * @fmt: The printf()-style format string
+ * @ap: Arguments for the format string
  * RETURNS:
  * Pointer to allocated string on success, NULL on failure.
  */
@@ -849,12 +849,13 @@ char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt,
 EXPORT_SYMBOL(devm_kvasprintf);
 
 /**
- * devm_kasprintf - Allocate resource managed space
- *		and copy an existing formatted string into that
+ * devm_kasprintf - Allocate resource managed space and format a string
+ *		    into that.
  * @dev: Device to allocate memory for
  * @gfp: the GFP mask used in the devm_kmalloc() call when
  *       allocating memory
- * @fmt: the string to duplicate
+ * @fmt: The printf()-style format string
+ * @...: Arguments for the format string
  * RETURNS:
  * Pointer to allocated string on success, NULL on failure.
  */
diff --git a/include/linux/device.h b/include/linux/device.h
index 43d183aeb25b..a608e237f0a8 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -607,8 +607,8 @@ extern int devres_release_group(struct device *dev, void *id);
 extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp);
 extern char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt,
 			     va_list ap);
-extern char *devm_kasprintf(struct device *dev, gfp_t gfp,
-			    const char *fmt, ...);
+extern __printf(3, 4)
+char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...);
 static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
 {
 	return devm_kmalloc(dev, size, gfp | __GFP_ZERO);
-- 
cgit v1.2.3


From 2b0bf6c85a4940e00516f68ff7103329abf8512d Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 22 Sep 2014 11:17:41 -0700
Subject: Bluetooth: Convert bt_<level> logging functions to return void

No caller or macro uses the return value so make all
the functions return void.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/bluetooth.h |  4 ++--
 net/bluetooth/lib.c               | 14 ++++----------
 2 files changed, 6 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 7e666d06b97f..58695ffeb138 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -120,9 +120,9 @@ struct bt_voice {
 #define BT_RCVMTU		13
 
 __printf(1, 2)
-int bt_info(const char *fmt, ...);
+void bt_info(const char *fmt, ...);
 __printf(1, 2)
-int bt_err(const char *fmt, ...);
+void bt_err(const char *fmt, ...);
 
 #define BT_INFO(fmt, ...)	bt_info(fmt "\n", ##__VA_ARGS__)
 #define BT_ERR(fmt, ...)	bt_err(fmt "\n", ##__VA_ARGS__)
diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c
index 941ad7530eda..b36bc0415854 100644
--- a/net/bluetooth/lib.c
+++ b/net/bluetooth/lib.c
@@ -135,40 +135,34 @@ int bt_to_errno(__u16 code)
 }
 EXPORT_SYMBOL(bt_to_errno);
 
-int bt_info(const char *format, ...)
+void bt_info(const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, format);
 
 	vaf.fmt = format;
 	vaf.va = &args;
 
-	r = pr_info("%pV", &vaf);
+	pr_info("%pV", &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(bt_info);
 
-int bt_err(const char *format, ...)
+void bt_err(const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, format);
 
 	vaf.fmt = format;
 	vaf.va = &args;
 
-	r = pr_err("%pV", &vaf);
+	pr_err("%pV", &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(bt_err);
-- 
cgit v1.2.3


From 295494af0695bc190e6b939df1036af898c2856f Mon Sep 17 00:00:00 2001
From: Octavian Purdila <octavian.purdila@intel.com>
Date: Fri, 19 Sep 2014 23:22:44 +0300
Subject: gpiolib: add irq_not_threaded flag to gpio_chip

Some GPIO chips (e.g. the DLN2 USB adapter) have blocking get/set
operation but do not need a threaded irq handler.

Signed-off-by: Octavian Purdila <octavian.purdila@intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c      | 2 +-
 include/linux/gpio/driver.h | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 4acf8b2e9226..6fdae789ccc9 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -437,7 +437,7 @@ static int gpiochip_irq_map(struct irq_domain *d, unsigned int irq,
 	irq_set_lockdep_class(irq, &gpiochip_irq_lock_class);
 	irq_set_chip_and_handler(irq, chip->irqchip, chip->irq_handler);
 	/* Chips that can sleep need nested thread handlers */
-	if (chip->can_sleep)
+	if (chip->can_sleep && !chip->irq_not_threaded)
 		irq_set_nested_thread(irq, 1);
 #ifdef CONFIG_ARM
 	set_irq_flags(irq, IRQF_VALID);
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 560bf7fa614f..719fab209158 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -56,6 +56,8 @@ struct seq_file;
  *	as the chip access may sleep when e.g. reading out the IRQ status
  *	registers.
  * @exported: flags if the gpiochip is exported for use from sysfs. Private.
+ * @irq_not_threaded: flag must be set if @can_sleep is set but the
+ *	IRQs don't need to be threaded
  *
  * A gpio_chip can help platforms abstract various sources of GPIOs so
  * they can all be accessed through a common programing interface.
@@ -101,6 +103,7 @@ struct gpio_chip {
 	struct gpio_desc	*desc;
 	const char		*const *names;
 	bool			can_sleep;
+	bool			irq_not_threaded;
 	bool			exported;
 
 #ifdef CONFIG_GPIOLIB_IRQCHIP
-- 
cgit v1.2.3


From 8af465db967bf25a4617416c0cbaaaa506d444f5 Mon Sep 17 00:00:00 2001
From: Roger Tseng <rogerable@realtek.com>
Date: Wed, 24 Sep 2014 17:07:13 +0800
Subject: mmc: core: Add new power_mode MMC_POWER_UNDEFINED

Add MMC_POWER_UNDEFINED for power_mode in struct mmc_ios and use it as
the initial value of host->ios.power_mode.

For hosts with MMC_CAP2_NO_PRESCAN_POWERUP, this makes the later
mmc_power_off() do real power-off things instead of NOP, and further
prevents state messed up in cards that was already initialized (eg. by
BIOS of UEFI driver).

Signed-off-by: Roger Tseng <rogerable@realtek.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/core.c  | 1 +
 include/linux/mmc/host.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index b1e209f479ad..cbb23215ad87 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2482,6 +2482,7 @@ void mmc_start_host(struct mmc_host *host)
 {
 	host->f_init = max(freqs[0], host->f_min);
 	host->rescan_disable = 0;
+	host->ios.power_mode = MMC_POWER_UNDEFINED;
 	if (host->caps2 & MMC_CAP2_NO_PRESCAN_POWERUP)
 		mmc_power_off(host);
 	else
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 797ae657dc3d..df0c15396bbf 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -42,6 +42,7 @@ struct mmc_ios {
 #define MMC_POWER_OFF		0
 #define MMC_POWER_UP		1
 #define MMC_POWER_ON		2
+#define MMC_POWER_UNDEFINED	3
 
 	unsigned char	bus_width;		/* data bus width */
 
-- 
cgit v1.2.3


From db4fa45ed3182d8206af241811dfc99369ffa849 Mon Sep 17 00:00:00 2001
From: Anders Berg <anders.berg@avagotech.com>
Date: Wed, 17 Sep 2014 08:46:58 +0200
Subject: spi: pl022: Add support for chip select extension

Add support for a extended PL022 which has an extra register for controlling up
to five chip select signals. This controller is found on the AXM5516 SoC.
Unfortunately the PrimeCell identification registers are identical to a
standard ARM PL022. To work around this, the peripheral ID must be overridden
in the device tree using the "arm,primecell-periphid" property with the value
0x000b6022.

Signed-off-by: Anders Berg <anders.berg@avagotech.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-pl022.c  | 59 +++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/amba/bus.h |  5 ++++
 2 files changed, 63 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 7f13f3f7198b..d0741b2eabb4 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -82,6 +82,7 @@
 #define SSP_MIS(r)	(r + 0x01C)
 #define SSP_ICR(r)	(r + 0x020)
 #define SSP_DMACR(r)	(r + 0x024)
+#define SSP_CSR(r)	(r + 0x030) /* vendor extension */
 #define SSP_ITCR(r)	(r + 0x080)
 #define SSP_ITIP(r)	(r + 0x084)
 #define SSP_ITOP(r)	(r + 0x088)
@@ -197,6 +198,12 @@
 /* Transmit DMA Enable bit */
 #define SSP_DMACR_MASK_TXDMAE		(0x1UL << 1)
 
+/*
+ * SSP Chip Select Control Register - SSP_CSR
+ * (vendor extension)
+ */
+#define SSP_CSR_CSVALUE_MASK		(0x1FUL << 0)
+
 /*
  * SSP Integration Test control Register - SSP_ITCR
  */
@@ -313,6 +320,7 @@ enum ssp_writing {
  * @extended_cr: 32 bit wide control register 0 with extra
  * features and extra features in CR1 as found in the ST variants
  * @pl023: supports a subset of the ST extensions called "PL023"
+ * @internal_cs_ctrl: supports chip select control register
  */
 struct vendor_data {
 	int fifodepth;
@@ -321,6 +329,7 @@ struct vendor_data {
 	bool extended_cr;
 	bool pl023;
 	bool loopback;
+	bool internal_cs_ctrl;
 };
 
 /**
@@ -440,9 +449,32 @@ static void null_cs_control(u32 command)
 	pr_debug("pl022: dummy chip select control, CS=0x%x\n", command);
 }
 
+/**
+ * internal_cs_control - Control chip select signals via SSP_CSR.
+ * @pl022: SSP driver private data structure
+ * @command: select/delect the chip
+ *
+ * Used on controller with internal chip select control via SSP_CSR register
+ * (vendor extension). Each of the 5 LSB in the register controls one chip
+ * select signal.
+ */
+static void internal_cs_control(struct pl022 *pl022, u32 command)
+{
+	u32 tmp;
+
+	tmp = readw(SSP_CSR(pl022->virtbase));
+	if (command == SSP_CHIP_SELECT)
+		tmp &= ~BIT(pl022->cur_cs);
+	else
+		tmp |= BIT(pl022->cur_cs);
+	writew(tmp, SSP_CSR(pl022->virtbase));
+}
+
 static void pl022_cs_control(struct pl022 *pl022, u32 command)
 {
-	if (gpio_is_valid(pl022->cur_cs))
+	if (pl022->vendor->internal_cs_ctrl)
+		internal_cs_control(pl022, command);
+	else if (gpio_is_valid(pl022->cur_cs))
 		gpio_set_value(pl022->cur_cs, command);
 	else
 		pl022->cur_chip->cs_control(command);
@@ -2122,6 +2154,9 @@ static int pl022_probe(struct amba_device *adev, const struct amba_id *id)
 	if (platform_info->num_chipselect && platform_info->chipselects) {
 		for (i = 0; i < num_cs; i++)
 			pl022->chipselects[i] = platform_info->chipselects[i];
+	} else if (pl022->vendor->internal_cs_ctrl) {
+		for (i = 0; i < num_cs; i++)
+			pl022->chipselects[i] = i;
 	} else if (IS_ENABLED(CONFIG_OF)) {
 		for (i = 0; i < num_cs; i++) {
 			int cs_gpio = of_get_named_gpio(np, "cs-gpios", i);
@@ -2352,6 +2387,7 @@ static struct vendor_data vendor_arm = {
 	.extended_cr = false,
 	.pl023 = false,
 	.loopback = true,
+	.internal_cs_ctrl = false,
 };
 
 static struct vendor_data vendor_st = {
@@ -2361,6 +2397,7 @@ static struct vendor_data vendor_st = {
 	.extended_cr = true,
 	.pl023 = false,
 	.loopback = true,
+	.internal_cs_ctrl = false,
 };
 
 static struct vendor_data vendor_st_pl023 = {
@@ -2370,6 +2407,17 @@ static struct vendor_data vendor_st_pl023 = {
 	.extended_cr = true,
 	.pl023 = true,
 	.loopback = false,
+	.internal_cs_ctrl = false,
+};
+
+static struct vendor_data vendor_lsi = {
+	.fifodepth = 8,
+	.max_bpw = 16,
+	.unidir = false,
+	.extended_cr = false,
+	.pl023 = false,
+	.loopback = true,
+	.internal_cs_ctrl = true,
 };
 
 static struct amba_id pl022_ids[] = {
@@ -2403,6 +2451,15 @@ static struct amba_id pl022_ids[] = {
 		.mask	= 0xffffffff,
 		.data	= &vendor_st_pl023,
 	},
+	{
+		/*
+		 * PL022 variant that has a chip select control register whih
+		 * allows control of 5 output signals nCS[0:4].
+		 */
+		.id	= 0x000b6022,
+		.mask	= 0x000fffff,
+		.data	= &vendor_lsi,
+	},
 	{ 0, 0 },
 };
 
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index fdd7e1b61f60..c324f5700d1a 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -44,10 +44,15 @@ struct amba_driver {
 	const struct amba_id	*id_table;
 };
 
+/*
+ * Constants for the designer field of the Peripheral ID register. When bit 7
+ * is set to '1', bits [6:0] should be the JEP106 manufacturer identity code.
+ */
 enum amba_vendor {
 	AMBA_VENDOR_ARM = 0x41,
 	AMBA_VENDOR_ST = 0x80,
 	AMBA_VENDOR_QCOM = 0x51,
+	AMBA_VENDOR_LSI = 0xb6,
 };
 
 extern struct bus_type amba_bustype;
-- 
cgit v1.2.3


From d41c15cf95bd91b9c333f6f749670e22c8a47ad9 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 24 Sep 2014 13:14:46 +0300
Subject: Bluetooth: Fix reason code used for rejecting SCO connections

The core specification defines valid values for the
HCI_Reject_Synchronous_Connection_Request command to be 0x0D-0x0F. So
far the code has been using HCI_ERROR_REMOTE_USER_TERM (0x13) which is
not a valid value and is therefore being rejected by some controllers:

 > HCI Event: Connect Request (0x04) plen 10
	bdaddr 40:6F:2A:6A:E5:E0 class 0x000000 type eSCO
 < HCI Command: Reject Synchronous Connection (0x01|0x002a) plen 7
	bdaddr 40:6F:2A:6A:E5:E0 reason 0x13
	Reason: Remote User Terminated Connection
 > HCI Event: Command Status (0x0f) plen 4
	Reject Synchronous Connection (0x01|0x002a) status 0x12 ncmd 1
	Error: Invalid HCI Command Parameters

This patch introduces a new define for a value from the valid range
(0x0d == Connection Rejected Due To Limited Resources) and uses it
instead for rejecting incoming connections.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 1 +
 net/bluetooth/hci_conn.c    | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 3f8547f1c6f8..6e8f24967308 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -385,6 +385,7 @@ enum {
 #define HCI_ERROR_AUTH_FAILURE		0x05
 #define HCI_ERROR_MEMORY_EXCEEDED	0x07
 #define HCI_ERROR_CONNECTION_TIMEOUT	0x08
+#define HCI_ERROR_REJ_LIMITED_RESOURCES	0x0d
 #define HCI_ERROR_REJ_BAD_ADDR		0x0f
 #define HCI_ERROR_REMOTE_USER_TERM	0x13
 #define HCI_ERROR_REMOTE_LOW_RESOURCES	0x14
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 22b253750f78..445829cd363c 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -121,7 +121,7 @@ static void hci_reject_sco(struct hci_conn *conn)
 {
 	struct hci_cp_reject_sync_conn_req cp;
 
-	cp.reason = HCI_ERROR_REMOTE_USER_TERM;
+	cp.reason = HCI_ERROR_REJ_LIMITED_RESOURCES;
 	bacpy(&cp.bdaddr, &conn->dst);
 
 	hci_send_cmd(conn->hdev, HCI_OP_REJECT_SYNC_CONN_REQ, sizeof(cp), &cp);
-- 
cgit v1.2.3


From 234b239bea395316d7f78018c672f4a88b3cdf0d Mon Sep 17 00:00:00 2001
From: Andres Lagar-Cavilla <andreslc@google.com>
Date: Wed, 17 Sep 2014 10:51:48 -0700
Subject: kvm: Faults which trigger IO release the mmap_sem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When KVM handles a tdp fault it uses FOLL_NOWAIT. If the guest memory
has been swapped out or is behind a filemap, this will trigger async
readahead and return immediately. The rationale is that KVM will kick
back the guest with an "async page fault" and allow for some other
guest process to take over.

If async PFs are enabled the fault is retried asap from an async
workqueue. If not, it's retried immediately in the same code path. In
either case the retry will not relinquish the mmap semaphore and will
block on the IO. This is a bad thing, as other mmap semaphore users
now stall as a function of swap or filemap latency.

This patch ensures both the regular and async PF path re-enter the
fault allowing for the mmap semaphore to be relinquished in the case
of IO wait.

Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Andres Lagar-Cavilla <andreslc@google.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 11 +++++++++++
 include/linux/mm.h       |  1 +
 mm/gup.c                 |  4 ++++
 virt/kvm/async_pf.c      |  4 +---
 virt/kvm/kvm_main.c      | 49 +++++++++++++++++++++++++++++++++++++++++++++---
 5 files changed, 63 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d44a2d640551..45aaeb3360c9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -198,6 +198,17 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
+/*
+ * Carry out a gup that requires IO. Allow the mm to relinquish the mmap
+ * semaphore if the filemap/swap has to wait on a page lock. pagep == NULL
+ * controls whether we retry the gup one more time to completion in that case.
+ * Typically this is called after a FAULT_FLAG_RETRY_NOWAIT in the main tdp
+ * handler.
+ */
+int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm,
+			 unsigned long addr, bool write_fault,
+			 struct page **pagep);
+
 enum {
 	OUTSIDE_GUEST_MODE,
 	IN_GUEST_MODE,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8981cc882ed2..0f4196a0bc20 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1985,6 +1985,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
 #define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
+#define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/mm/gup.c b/mm/gup.c
index 91d044b1600d..af7ea3e0826b 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -281,6 +281,10 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
 	if (*flags & FOLL_NOWAIT)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
+	if (*flags & FOLL_TRIED) {
+		VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_ALLOW_RETRY);
+		fault_flags |= FAULT_FLAG_TRIED;
+	}
 
 	ret = handle_mm_fault(mm, vma, address, fault_flags);
 	if (ret & VM_FAULT_ERROR) {
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index d6a3d0993d88..5ff7f7f2689a 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -80,9 +80,7 @@ static void async_pf_execute(struct work_struct *work)
 
 	might_sleep();
 
-	down_read(&mm->mmap_sem);
-	get_user_pages(NULL, mm, addr, 1, 1, 0, NULL, NULL);
-	up_read(&mm->mmap_sem);
+	kvm_get_user_page_io(NULL, mm, addr, 1, NULL);
 	kvm_async_page_present_sync(vcpu, apf);
 
 	spin_lock(&vcpu->async_pf.lock);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 499db0977f3c..1c6e8476b244 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1122,6 +1122,43 @@ static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
 	return __get_user_pages(tsk, mm, start, 1, flags, page, NULL, NULL);
 }
 
+int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm,
+			 unsigned long addr, bool write_fault,
+			 struct page **pagep)
+{
+	int npages;
+	int locked = 1;
+	int flags = FOLL_TOUCH | FOLL_HWPOISON |
+		    (pagep ? FOLL_GET : 0) |
+		    (write_fault ? FOLL_WRITE : 0);
+
+	/*
+	 * If retrying the fault, we get here *not* having allowed the filemap
+	 * to wait on the page lock. We should now allow waiting on the IO with
+	 * the mmap semaphore released.
+	 */
+	down_read(&mm->mmap_sem);
+	npages = __get_user_pages(tsk, mm, addr, 1, flags, pagep, NULL,
+				  &locked);
+	if (!locked) {
+		VM_BUG_ON(npages != -EBUSY);
+
+		if (!pagep)
+			return 0;
+
+		/*
+		 * The previous call has now waited on the IO. Now we can
+		 * retry and complete. Pass TRIED to ensure we do not re
+		 * schedule async IO (see e.g. filemap_fault).
+		 */
+		down_read(&mm->mmap_sem);
+		npages = __get_user_pages(tsk, mm, addr, 1, flags | FOLL_TRIED,
+					  pagep, NULL, NULL);
+	}
+	up_read(&mm->mmap_sem);
+	return npages;
+}
+
 static inline int check_user_page_hwpoison(unsigned long addr)
 {
 	int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE;
@@ -1184,9 +1221,15 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
 		npages = get_user_page_nowait(current, current->mm,
 					      addr, write_fault, page);
 		up_read(&current->mm->mmap_sem);
-	} else
-		npages = get_user_pages_fast(addr, 1, write_fault,
-					     page);
+	} else {
+		/*
+		 * By now we have tried gup_fast, and possibly async_pf, and we
+		 * are certainly not atomic. Time to retry the gup, allowing
+		 * mmap semaphore to be relinquished in the case of IO.
+		 */
+		npages = kvm_get_user_page_io(current, current->mm, addr,
+					      write_fault, page);
+	}
 	if (npages != 1)
 		return npages;
 
-- 
cgit v1.2.3


From 8a9522d2fe6a1b643d3aef5ab7f097f73c601e7a Mon Sep 17 00:00:00 2001
From: Andres Lagar-Cavilla <andreslc@google.com>
Date: Tue, 23 Sep 2014 12:34:54 -0700
Subject: kvm/x86/mmu: Pass gfn and level to rmapp callback.

Callbacks don't have to do extra computation to learn what the caller
(lvm_handle_hva_range()) knows very well. Useful for
debugging/tracing/printk/future.

Signed-off-by: Andres Lagar-Cavilla <andreslc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu.c         | 37 ++++++++++++++++++++++++-------------
 include/trace/events/kvm.h | 16 +++++++++-------
 2 files changed, 33 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index bdd1acbab84d..47d534066325 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1262,7 +1262,8 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
 }
 
 static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			   struct kvm_memory_slot *slot, unsigned long data)
+			   struct kvm_memory_slot *slot, gfn_t gfn, int level,
+			   unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1270,7 +1271,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 
 	while ((sptep = rmap_get_first(*rmapp, &iter))) {
 		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-		rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", sptep, *sptep);
+		rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n",
+			     sptep, *sptep, gfn, level);
 
 		drop_spte(kvm, sptep);
 		need_tlb_flush = 1;
@@ -1280,7 +1282,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 }
 
 static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			     struct kvm_memory_slot *slot, unsigned long data)
+			     struct kvm_memory_slot *slot, gfn_t gfn, int level,
+			     unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1294,7 +1297,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
 		BUG_ON(!is_shadow_present_pte(*sptep));
-		rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", sptep, *sptep);
+		rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n",
+			     sptep, *sptep, gfn, level);
 
 		need_flush = 1;
 
@@ -1328,6 +1332,8 @@ static int kvm_handle_hva_range(struct kvm *kvm,
 				int (*handler)(struct kvm *kvm,
 					       unsigned long *rmapp,
 					       struct kvm_memory_slot *slot,
+					       gfn_t gfn,
+					       int level,
 					       unsigned long data))
 {
 	int j;
@@ -1357,6 +1363,7 @@ static int kvm_handle_hva_range(struct kvm *kvm,
 		     j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
 			unsigned long idx, idx_end;
 			unsigned long *rmapp;
+			gfn_t gfn = gfn_start;
 
 			/*
 			 * {idx(page_j) | page_j intersects with
@@ -1367,8 +1374,10 @@ static int kvm_handle_hva_range(struct kvm *kvm,
 
 			rmapp = __gfn_to_rmap(gfn_start, j, memslot);
 
-			for (; idx <= idx_end; ++idx)
-				ret |= handler(kvm, rmapp++, memslot, data);
+			for (; idx <= idx_end;
+			       ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j)))
+				ret |= handler(kvm, rmapp++, memslot,
+					       gfn, j, data);
 		}
 	}
 
@@ -1379,6 +1388,7 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 			  unsigned long data,
 			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
 					 struct kvm_memory_slot *slot,
+					 gfn_t gfn, int level,
 					 unsigned long data))
 {
 	return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
@@ -1400,7 +1410,8 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 }
 
 static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			 struct kvm_memory_slot *slot, unsigned long data)
+			 struct kvm_memory_slot *slot, gfn_t gfn, int level,
+			 unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator uninitialized_var(iter);
@@ -1415,7 +1426,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	 * out actively used pages or breaking up actively used hugepages.
 	 */
 	if (!shadow_accessed_mask) {
-		young = kvm_unmap_rmapp(kvm, rmapp, slot, data);
+		young = kvm_unmap_rmapp(kvm, rmapp, slot, gfn, level, data);
 		goto out;
 	}
 
@@ -1430,13 +1441,13 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 		}
 	}
 out:
-	/* @data has hva passed to kvm_age_hva(). */
-	trace_kvm_age_page(data, slot, young);
+	trace_kvm_age_page(gfn, level, slot, young);
 	return young;
 }
 
 static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			      struct kvm_memory_slot *slot, unsigned long data)
+			      struct kvm_memory_slot *slot, gfn_t gfn,
+			      int level, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1474,13 +1485,13 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 
 	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
 
-	kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, 0);
+	kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0);
 	kvm_flush_remote_tlbs(vcpu->kvm);
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvm_handle_hva(kvm, hva, hva, kvm_age_rmapp);
+	return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index ab679c395042..6edf1f2028cd 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -225,24 +225,26 @@ TRACE_EVENT(kvm_fpu,
 );
 
 TRACE_EVENT(kvm_age_page,
-	TP_PROTO(ulong hva, struct kvm_memory_slot *slot, int ref),
-	TP_ARGS(hva, slot, ref),
+	TP_PROTO(ulong gfn, int level, struct kvm_memory_slot *slot, int ref),
+	TP_ARGS(gfn, level, slot, ref),
 
 	TP_STRUCT__entry(
 		__field(	u64,	hva		)
 		__field(	u64,	gfn		)
+		__field(	u8,	level		)
 		__field(	u8,	referenced	)
 	),
 
 	TP_fast_assign(
-		__entry->hva		= hva;
-		__entry->gfn		=
-		  slot->base_gfn + ((hva - slot->userspace_addr) >> PAGE_SHIFT);
+		__entry->gfn		= gfn;
+		__entry->level		= level;
+		__entry->hva		= ((gfn - slot->base_gfn) <<
+					    PAGE_SHIFT) + slot->userspace_addr;
 		__entry->referenced	= ref;
 	),
 
-	TP_printk("hva %llx gfn %llx %s",
-		  __entry->hva, __entry->gfn,
+	TP_printk("hva %llx gfn %llx level %u %s",
+		  __entry->hva, __entry->gfn, __entry->level,
 		  __entry->referenced ? "YOUNG" : "OLD")
 );
 
-- 
cgit v1.2.3


From 57128468080a8b6ea452223036d3e417f748af55 Mon Sep 17 00:00:00 2001
From: Andres Lagar-Cavilla <andreslc@google.com>
Date: Mon, 22 Sep 2014 14:54:42 -0700
Subject: kvm: Fix page ageing bugs

1. We were calling clear_flush_young_notify in unmap_one, but we are
within an mmu notifier invalidate range scope. The spte exists no more
(due to range_start) and the accessed bit info has already been
propagated (due to kvm_pfn_set_accessed). Simply call
clear_flush_young.

2. We clear_flush_young on a primary MMU PMD, but this may be mapped
as a collection of PTEs by the secondary MMU (e.g. during log-dirty).
This required expanding the interface of the clear_flush_young mmu
notifier, so a lot of code has been trivially touched.

3. In the absence of shadow_accessed_mask (e.g. EPT A bit), we emulate
the access bit by blowing the spte. This requires proper synchronizing
with MMU notifier consumers, like every other removal of spte's does.

Signed-off-by: Andres Lagar-Cavilla <andreslc@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm/include/asm/kvm_host.h     |  3 ++-
 arch/arm64/include/asm/kvm_host.h   |  3 ++-
 arch/powerpc/include/asm/kvm_host.h |  2 +-
 arch/powerpc/include/asm/kvm_ppc.h  |  2 +-
 arch/powerpc/kvm/book3s.c           |  4 ++--
 arch/powerpc/kvm/book3s.h           |  3 ++-
 arch/powerpc/kvm/book3s_64_mmu_hv.c |  4 ++--
 arch/powerpc/kvm/book3s_pr.c        |  3 ++-
 arch/powerpc/kvm/e500_mmu_host.c    |  2 +-
 arch/x86/include/asm/kvm_host.h     |  2 +-
 arch/x86/kvm/mmu.c                  | 38 ++++++++++++++++++++++---------------
 drivers/iommu/amd_iommu_v2.c        |  6 ++++--
 include/linux/mmu_notifier.h        | 24 ++++++++++++++++-------
 mm/mmu_notifier.c                   |  5 +++--
 mm/rmap.c                           |  6 +++++-
 virt/kvm/kvm_main.c                 |  5 +++--
 16 files changed, 71 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 032a8538318a..8c3f7eb62b54 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -170,7 +170,8 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 
 /* We do not have shadow page tables, hence the empty hooks */
-static inline int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+static inline int kvm_age_hva(struct kvm *kvm, unsigned long start,
+			      unsigned long end)
 {
 	return 0;
 }
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index be9970a59497..a3c671b3acc9 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -180,7 +180,8 @@ int kvm_unmap_hva_range(struct kvm *kvm,
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 
 /* We do not have shadow page tables, hence the empty hooks */
-static inline int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+static inline int kvm_age_hva(struct kvm *kvm, unsigned long start,
+			      unsigned long end)
 {
 	return 0;
 }
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 604000882352..d329bc5543a2 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -56,7 +56,7 @@
 extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 extern int kvm_unmap_hva_range(struct kvm *kvm,
 			       unsigned long start, unsigned long end);
-extern int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index fb86a2299d8a..d4a92d7cea6a 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -243,7 +243,7 @@ struct kvmppc_ops {
 	int (*unmap_hva)(struct kvm *kvm, unsigned long hva);
 	int (*unmap_hva_range)(struct kvm *kvm, unsigned long start,
 			   unsigned long end);
-	int (*age_hva)(struct kvm *kvm, unsigned long hva);
+	int (*age_hva)(struct kvm *kvm, unsigned long start, unsigned long end);
 	int (*test_age_hva)(struct kvm *kvm, unsigned long hva);
 	void (*set_spte_hva)(struct kvm *kvm, unsigned long hva, pte_t pte);
 	void (*mmu_destroy)(struct kvm_vcpu *vcpu);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index dd03f6b299ba..c16cfbfeb781 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -851,9 +851,9 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 	return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end);
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	return kvm->arch.kvm_ops->age_hva(kvm, hva);
+	return kvm->arch.kvm_ops->age_hva(kvm, start, end);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index 4bf956cf94d6..d2b3ec088b8c 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -17,7 +17,8 @@ extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
 extern int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva);
 extern int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start,
 				  unsigned long end);
-extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva);
+extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long start,
+			  unsigned long end);
 extern int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva);
 extern void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte);
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 72c20bb16d26..81460c5359c0 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1002,11 +1002,11 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return ret;
 }
 
-int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva_hv(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	if (!kvm->arch.using_mmu_notifiers)
 		return 0;
-	return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
+	return kvm_handle_hva_range(kvm, start, end, kvm_age_rmapp);
 }
 
 static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index faffb27badd9..852fcd8951c4 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -295,7 +295,8 @@ static int kvm_unmap_hva_range_pr(struct kvm *kvm, unsigned long start,
 	return 0;
 }
 
-static int kvm_age_hva_pr(struct kvm *kvm, unsigned long hva)
+static int kvm_age_hva_pr(struct kvm *kvm, unsigned long start,
+			  unsigned long end)
 {
 	/* XXX could be more clever ;) */
 	return 0;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 08f14bb57897..b1f3f630315e 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -732,7 +732,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 	return 0;
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	/* XXX could be more clever ;) */
 	return 0;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index eeeb573fcf6f..763d273cab1d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1035,7 +1035,7 @@ asmlinkage void kvm_spurious_fault(void);
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
-int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 47d534066325..3201e93ebd07 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1417,18 +1417,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	struct rmap_iterator uninitialized_var(iter);
 	int young = 0;
 
-	/*
-	 * In case of absence of EPT Access and Dirty Bits supports,
-	 * emulate the accessed bit for EPT, by checking if this page has
-	 * an EPT mapping, and clearing it if it does. On the next access,
-	 * a new EPT mapping will be established.
-	 * This has some overhead, but not as much as the cost of swapping
-	 * out actively used pages or breaking up actively used hugepages.
-	 */
-	if (!shadow_accessed_mask) {
-		young = kvm_unmap_rmapp(kvm, rmapp, slot, gfn, level, data);
-		goto out;
-	}
+	BUG_ON(!shadow_accessed_mask);
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
 	     sptep = rmap_get_next(&iter)) {
@@ -1440,7 +1429,6 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 				 (unsigned long *)sptep);
 		}
 	}
-out:
 	trace_kvm_age_page(gfn, level, slot, young);
 	return young;
 }
@@ -1489,9 +1477,29 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 	kvm_flush_remote_tlbs(vcpu->kvm);
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
+	/*
+	 * In case of absence of EPT Access and Dirty Bits supports,
+	 * emulate the accessed bit for EPT, by checking if this page has
+	 * an EPT mapping, and clearing it if it does. On the next access,
+	 * a new EPT mapping will be established.
+	 * This has some overhead, but not as much as the cost of swapping
+	 * out actively used pages or breaking up actively used hugepages.
+	 */
+	if (!shadow_accessed_mask) {
+		/*
+		 * We are holding the kvm->mmu_lock, and we are blowing up
+		 * shadow PTEs. MMU notifier consumers need to be kept at bay.
+		 * This is correct as long as we don't decouple the mmu_lock
+		 * protected regions (like invalidate_range_start|end does).
+		 */
+		kvm->mmu_notifier_seq++;
+		return kvm_handle_hva_range(kvm, start, end, 0,
+					    kvm_unmap_rmapp);
+	}
+
+	return kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 5f578e850fc5..90d734bbf467 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -402,9 +402,11 @@ static void __mn_flush_page(struct mmu_notifier *mn,
 
 static int mn_clear_flush_young(struct mmu_notifier *mn,
 				struct mm_struct *mm,
-				unsigned long address)
+				unsigned long start,
+				unsigned long end)
 {
-	__mn_flush_page(mn, address);
+	for (; start < end; start += PAGE_SIZE)
+		__mn_flush_page(mn, start);
 
 	return 0;
 }
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 27288692241e..88787bb4b3b9 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -57,10 +57,13 @@ struct mmu_notifier_ops {
 	 * pte. This way the VM will provide proper aging to the
 	 * accesses to the page through the secondary MMUs and not
 	 * only to the ones through the Linux pte.
+	 * Start-end is necessary in case the secondary MMU is mapping the page
+	 * at a smaller granularity than the primary MMU.
 	 */
 	int (*clear_flush_young)(struct mmu_notifier *mn,
 				 struct mm_struct *mm,
-				 unsigned long address);
+				 unsigned long start,
+				 unsigned long end);
 
 	/*
 	 * test_young is called to check the young/accessed bitflag in
@@ -175,7 +178,8 @@ extern void mmu_notifier_unregister_no_release(struct mmu_notifier *mn,
 extern void __mmu_notifier_mm_destroy(struct mm_struct *mm);
 extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
-					  unsigned long address);
+					  unsigned long start,
+					  unsigned long end);
 extern int __mmu_notifier_test_young(struct mm_struct *mm,
 				     unsigned long address);
 extern void __mmu_notifier_change_pte(struct mm_struct *mm,
@@ -194,10 +198,11 @@ static inline void mmu_notifier_release(struct mm_struct *mm)
 }
 
 static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
-					  unsigned long address)
+					  unsigned long start,
+					  unsigned long end)
 {
 	if (mm_has_notifiers(mm))
-		return __mmu_notifier_clear_flush_young(mm, address);
+		return __mmu_notifier_clear_flush_young(mm, start, end);
 	return 0;
 }
 
@@ -255,7 +260,9 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	unsigned long ___address = __address;				\
 	__young = ptep_clear_flush_young(___vma, ___address, __ptep);	\
 	__young |= mmu_notifier_clear_flush_young(___vma->vm_mm,	\
-						  ___address);		\
+						  ___address,		\
+						  ___address +		\
+							PAGE_SIZE);	\
 	__young;							\
 })
 
@@ -266,7 +273,9 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	unsigned long ___address = __address;				\
 	__young = pmdp_clear_flush_young(___vma, ___address, __pmdp);	\
 	__young |= mmu_notifier_clear_flush_young(___vma->vm_mm,	\
-						  ___address);		\
+						  ___address,		\
+						  ___address +		\
+							PMD_SIZE);	\
 	__young;							\
 })
 
@@ -301,7 +310,8 @@ static inline void mmu_notifier_release(struct mm_struct *mm)
 }
 
 static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
-					  unsigned long address)
+					  unsigned long start,
+					  unsigned long end)
 {
 	return 0;
 }
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 950813b1eb36..2c8da9825fe3 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -107,7 +107,8 @@ void __mmu_notifier_release(struct mm_struct *mm)
  * existed or not.
  */
 int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
-					unsigned long address)
+					unsigned long start,
+					unsigned long end)
 {
 	struct mmu_notifier *mn;
 	int young = 0, id;
@@ -115,7 +116,7 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->clear_flush_young)
-			young |= mn->ops->clear_flush_young(mn, mm, address);
+			young |= mn->ops->clear_flush_young(mn, mm, start, end);
 	}
 	srcu_read_unlock(&srcu, id);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 3e8491c504f8..bc74e0012809 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1355,7 +1355,11 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 			continue;	/* don't unmap */
 		}
 
-		if (ptep_clear_flush_young_notify(vma, address, pte))
+		/*
+		 * No need for _notify because we're within an
+		 * mmu_notifier_invalidate_range_ {start|end} scope.
+		 */
+		if (ptep_clear_flush_young(vma, address, pte))
 			continue;
 
 		/* Nuke the page table entry. */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ff42b11d2b9c..0316314d48f4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -369,7 +369,8 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 
 static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 					      struct mm_struct *mm,
-					      unsigned long address)
+					      unsigned long start,
+					      unsigned long end)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
 	int young, idx;
@@ -377,7 +378,7 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 	idx = srcu_read_lock(&kvm->srcu);
 	spin_lock(&kvm->mmu_lock);
 
-	young = kvm_age_hva(kvm, address);
+	young = kvm_age_hva(kvm, start, end);
 	if (young)
 		kvm_flush_remote_tlbs(kvm);
 
-- 
cgit v1.2.3


From 445b8236959bfe624a5aa9bce89f44a3bec9b2b1 Mon Sep 17 00:00:00 2001
From: Tang Chen <tangchen@cn.fujitsu.com>
Date: Wed, 24 Sep 2014 15:57:55 +0800
Subject: kvm: Rename make_all_cpus_request() to kvm_make_all_cpus_request()
 and make it non-static

Different architectures need different requests, and in fact we
will use this function in architecture-specific code later. This
will be outside kvm_main.c, so make it non-static and rename it to
kvm_make_all_cpus_request().

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  1 +
 virt/kvm/kvm_main.c      | 10 +++++-----
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 45aaeb3360c9..12c591fc2571 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -586,6 +586,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
 void kvm_make_mclock_inprogress_request(struct kvm *kvm);
 void kvm_make_scan_ioapic_request(struct kvm *kvm);
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0316314d48f4..5b8ca365932a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -153,7 +153,7 @@ static void ack_flush(void *_completed)
 {
 }
 
-static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
 {
 	int i, cpu, me;
 	cpumask_var_t cpus;
@@ -190,7 +190,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	long dirty_count = kvm->tlbs_dirty;
 
 	smp_mb();
-	if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
+	if (kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
 		++kvm->stat.remote_tlb_flush;
 	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
@@ -198,17 +198,17 @@ EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 
 void kvm_reload_remote_mmus(struct kvm *kvm)
 {
-	make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
+	kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
 }
 
 void kvm_make_mclock_inprogress_request(struct kvm *kvm)
 {
-	make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
+	kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
 }
 
 void kvm_make_scan_ioapic_request(struct kvm *kvm)
 {
-	make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
+	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
 }
 
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
-- 
cgit v1.2.3


From 4256f43f9fab91e1c17b5846a240cf4b66a768a8 Mon Sep 17 00:00:00 2001
From: Tang Chen <tangchen@cn.fujitsu.com>
Date: Wed, 24 Sep 2014 15:57:54 +0800
Subject: kvm: x86: Add request bit to reload APIC access page address

Currently, the APIC access page is pinned by KVM for the entire life
of the guest.  We want to make it migratable in order to make memory
hot-unplug available for machines that run KVM.

This patch prepares to handle this in generic code, through a new
request bit (that will be set by the MMU notifier) and a new hook
that is called whenever the request bit is processed.

Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/x86.c              | 14 ++++++++++++++
 include/linux/kvm_host.h        |  1 +
 3 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 022c356e0fed..60f9d73c6282 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -736,6 +736,7 @@ struct kvm_x86_ops {
 	void (*hwapic_isr_update)(struct kvm *kvm, int isr);
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
+	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
 	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
@@ -1044,6 +1045,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
 void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 					   unsigned long address);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 142569e6f8f9..c1412f5d93db 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6026,6 +6026,18 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->tlb_flush(vcpu);
 }
 
+void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_x86_ops->set_apic_access_page_addr)
+		return;
+
+	vcpu->kvm->arch.apic_access_page = gfn_to_page(vcpu->kvm,
+			APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	kvm_x86_ops->set_apic_access_page_addr(vcpu,
+			page_to_phys(vcpu->kvm->arch.apic_access_page));
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
+
 void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 					   unsigned long address)
 {
@@ -6091,6 +6103,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_deliver_pmi(vcpu);
 		if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu))
 			vcpu_scan_ioapic(vcpu);
+		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
+			kvm_vcpu_reload_apic_access_page(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 12c591fc2571..d594f9f34429 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -136,6 +136,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_GLOBAL_CLOCK_UPDATE 22
 #define KVM_REQ_ENABLE_IBS        23
 #define KVM_REQ_DISABLE_IBS       24
+#define KVM_REQ_APIC_PAGE_RELOAD  25
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
-- 
cgit v1.2.3


From 25cc24c200dcba21bd1f1a59a01741185062dc0e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 12 Sep 2014 08:53:53 +0200
Subject: mfd: max14577: Add defines for MAX77836 charger

Prepare for adding support for MAX77836 charger to the max14577 charger
driver by adding necessary new defines and prefixes to existing ones.

The MAX77836 uses slightly different values for ChgTyp field of STATUS2
register. On the MAX14577 value of 0x6 is reserved and 0x7 dead battery.
On the MAX77836 the opposite:
 - 0x6 means special charger,
 - 0x7 is reserved.
Regardless of these differences use one common enum
max14577_muic_charger_type.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mfd/max14577-private.h | 54 ++++++++++++++++++++++++++----------
 1 file changed, 40 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h
index 499253604026..d6f321699b89 100644
--- a/include/linux/mfd/max14577-private.h
+++ b/include/linux/mfd/max14577-private.h
@@ -72,15 +72,33 @@ enum max14577_muic_reg {
 	MAX14577_MUIC_REG_END,
 };
 
+/*
+ * Combined charger types for max14577 and max77836.
+ *
+ * On max14577 three lower bits map to STATUS2/CHGTYP field.
+ * However the max77836 has different two last values of STATUS2/CHGTYP.
+ * To indicate the difference enum has two additional values for max77836.
+ * These values are just a register value bitwise OR with 0x8.
+ */
 enum max14577_muic_charger_type {
-	MAX14577_CHARGER_TYPE_NONE = 0,
-	MAX14577_CHARGER_TYPE_USB,
-	MAX14577_CHARGER_TYPE_DOWNSTREAM_PORT,
-	MAX14577_CHARGER_TYPE_DEDICATED_CHG,
-	MAX14577_CHARGER_TYPE_SPECIAL_500MA,
-	MAX14577_CHARGER_TYPE_SPECIAL_1A,
-	MAX14577_CHARGER_TYPE_RESERVED,
-	MAX14577_CHARGER_TYPE_DEAD_BATTERY = 7,
+	MAX14577_CHARGER_TYPE_NONE		= 0x0,
+	MAX14577_CHARGER_TYPE_USB		= 0x1,
+	MAX14577_CHARGER_TYPE_DOWNSTREAM_PORT	= 0x2,
+	MAX14577_CHARGER_TYPE_DEDICATED_CHG	= 0x3,
+	MAX14577_CHARGER_TYPE_SPECIAL_500MA	= 0x4,
+	/* Special 1A or 2A charger */
+	MAX14577_CHARGER_TYPE_SPECIAL_1A	= 0x5,
+	/* max14577: reserved, used on max77836 */
+	MAX14577_CHARGER_TYPE_RESERVED		= 0x6,
+	/* max14577: dead-battery charing with maximum current 100mA */
+	MAX14577_CHARGER_TYPE_DEAD_BATTERY	= 0x7,
+	/*
+	 * max77836: special charger (bias on D+/D-),
+	 * matches register value of 0x6
+	 */
+	MAX77836_CHARGER_TYPE_SPECIAL_BIAS	= 0xe,
+	/* max77836: reserved, register value 0x7 */
+	MAX77836_CHARGER_TYPE_RESERVED		= 0xf,
 };
 
 /* MAX14577 interrupts */
@@ -121,13 +139,15 @@ enum max14577_muic_charger_type {
 #define STATUS2_CHGTYP_SHIFT		0
 #define STATUS2_CHGDETRUN_SHIFT		3
 #define STATUS2_DCDTMR_SHIFT		4
-#define STATUS2_DBCHG_SHIFT		5
+#define MAX14577_STATUS2_DBCHG_SHIFT	5
+#define MAX77836_STATUS2_DXOVP_SHIFT	5
 #define STATUS2_VBVOLT_SHIFT		6
 #define MAX77836_STATUS2_VIDRM_SHIFT	7
 #define STATUS2_CHGTYP_MASK		(0x7 << STATUS2_CHGTYP_SHIFT)
 #define STATUS2_CHGDETRUN_MASK		BIT(STATUS2_CHGDETRUN_SHIFT)
 #define STATUS2_DCDTMR_MASK		BIT(STATUS2_DCDTMR_SHIFT)
-#define STATUS2_DBCHG_MASK		BIT(STATUS2_DBCHG_SHIFT)
+#define MAX14577_STATUS2_DBCHG_MASK	BIT(MAX14577_STATUS2_DBCHG_SHIFT)
+#define MAX77836_STATUS2_DXOVP_MASK	BIT(MAX77836_STATUS2_DXOVP_SHIFT)
 #define STATUS2_VBVOLT_MASK		BIT(STATUS2_VBVOLT_SHIFT)
 #define MAX77836_STATUS2_VIDRM_MASK	BIT(MAX77836_STATUS2_VIDRM_SHIFT)
 
@@ -177,9 +197,11 @@ enum max14577_muic_charger_type {
 #define CTRL3_JIGSET_SHIFT		0
 #define CTRL3_BOOTSET_SHIFT		2
 #define CTRL3_ADCDBSET_SHIFT		4
+#define CTRL3_WBTH_SHIFT		6
 #define CTRL3_JIGSET_MASK		(0x3 << CTRL3_JIGSET_SHIFT)
 #define CTRL3_BOOTSET_MASK		(0x3 << CTRL3_BOOTSET_SHIFT)
 #define CTRL3_ADCDBSET_MASK		(0x3 << CTRL3_ADCDBSET_SHIFT)
+#define CTRL3_WBTH_MASK			(0x3 << CTRL3_WBTH_SHIFT)
 
 /* Slave addr = 0x4A: Charger */
 enum max14577_charger_reg {
@@ -210,16 +232,20 @@ enum max14577_charger_reg {
 #define CDETCTRL1_CHGTYPMAN_SHIFT	1
 #define CDETCTRL1_DCDEN_SHIFT		2
 #define CDETCTRL1_DCD2SCT_SHIFT		3
-#define CDETCTRL1_DCHKTM_SHIFT		4
-#define CDETCTRL1_DBEXIT_SHIFT		5
+#define MAX14577_CDETCTRL1_DCHKTM_SHIFT	4
+#define MAX77836_CDETCTRL1_CDLY_SHIFT	4
+#define MAX14577_CDETCTRL1_DBEXIT_SHIFT	5
+#define MAX77836_CDETCTRL1_DCDCPL_SHIFT	5
 #define CDETCTRL1_DBIDLE_SHIFT		6
 #define CDETCTRL1_CDPDET_SHIFT		7
 #define CDETCTRL1_CHGDETEN_MASK		BIT(CDETCTRL1_CHGDETEN_SHIFT)
 #define CDETCTRL1_CHGTYPMAN_MASK	BIT(CDETCTRL1_CHGTYPMAN_SHIFT)
 #define CDETCTRL1_DCDEN_MASK		BIT(CDETCTRL1_DCDEN_SHIFT)
 #define CDETCTRL1_DCD2SCT_MASK		BIT(CDETCTRL1_DCD2SCT_SHIFT)
-#define CDETCTRL1_DCHKTM_MASK		BIT(CDETCTRL1_DCHKTM_SHIFT)
-#define CDETCTRL1_DBEXIT_MASK		BIT(CDETCTRL1_DBEXIT_SHIFT)
+#define MAX14577_CDETCTRL1_DCHKTM_MASK	BIT(MAX14577_CDETCTRL1_DCHKTM_SHIFT)
+#define MAX77836_CDETCTRL1_CDDLY_MASK	BIT(MAX77836_CDETCTRL1_CDDLY_SHIFT)
+#define MAX14577_CDETCTRL1_DBEXIT_MASK	BIT(MAX14577_CDETCTRL1_DBEXIT_SHIFT)
+#define MAX77836_CDETCTRL1_DCDCPL_MASK	BIT(MAX77836_CDETCTRL1_DCDCPL_SHIFT)
 #define CDETCTRL1_DBIDLE_MASK		BIT(CDETCTRL1_DBIDLE_SHIFT)
 #define CDETCTRL1_CDPDET_MASK		BIT(CDETCTRL1_CDPDET_SHIFT)
 
-- 
cgit v1.2.3


From 521e8bac67a71a6544274f39d5c61473e0e54ac0 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Wed, 17 Sep 2014 11:06:16 +0200
Subject: perf/x86/intel/uncore: Update support for client uncore IMC PMU

This patch restructures the memory controller (IMC) uncore PMU support
for client SNB/IVB/HSW processors. The main change is that it can now
cope with more than one PCI device ID per processor model. There are
many flavors of memory controllers for each processor. They have
different PCI device ID, yet they behave the same w.r.t. the memory
controller PMU that we are interested in.

The patch now supports two distinct memory controllers for IVB
processors: one for mobile, one for desktop.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140917090616.GA11281@quad
Cc: ak@linux.intel.com
Cc: kan.liang@intel.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c | 69 +++++++++++++++++------
 include/linux/pci_ids.h                           |  1 +
 2 files changed, 52 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index e0e934c8ee77..3001015b755c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -460,6 +460,10 @@ static const struct pci_device_id ivb_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_E3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -486,34 +490,63 @@ static struct pci_driver hsw_uncore_pci_driver = {
 	.id_table	= hsw_uncore_pci_ids,
 };
 
-int snb_uncore_pci_init(void)
+struct imc_uncore_pci_dev {
+	__u32 pci_id;
+	struct pci_driver *driver;
+};
+#define IMC_DEV(a, d) \
+	{ .pci_id = PCI_DEVICE_ID_INTEL_##a, .driver = (d) }
+
+static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
+	IMC_DEV(SNB_IMC, &snb_uncore_pci_driver),
+	IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver),    /* 3rd Gen Core processor */
+	IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
+	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
+	{  /* end marker */ }
+};
+
+
+#define for_each_imc_pci_id(x, t) \
+	for (x = (t); (x)->pci_id; x++)
+
+static struct pci_driver *imc_uncore_find_dev(void)
 {
-	int ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC);
-	if (ret)
-		return ret;
-	uncore_pci_uncores = snb_pci_uncores;
-	uncore_pci_driver = &snb_uncore_pci_driver;
-	return 0;
+	const struct imc_uncore_pci_dev *p;
+	int ret;
+
+	for_each_imc_pci_id(p, desktop_imc_pci_ids) {
+		ret = snb_pci2phy_map_init(p->pci_id);
+		if (ret == 0)
+			return p->driver;
+	}
+	return NULL;
 }
 
-int ivb_uncore_pci_init(void)
+static int imc_uncore_pci_init(void)
 {
-	int ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC);
-	if (ret)
-		return ret;
+	struct pci_driver *imc_drv = imc_uncore_find_dev();
+
+	if (!imc_drv)
+		return -ENODEV;
+
 	uncore_pci_uncores = snb_pci_uncores;
-	uncore_pci_driver = &ivb_uncore_pci_driver;
+	uncore_pci_driver = imc_drv;
+
 	return 0;
 }
 
+int snb_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+
+int ivb_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
 int hsw_uncore_pci_init(void)
 {
-	int ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC);
-	if (ret)
-		return ret;
-	uncore_pci_uncores = snb_pci_uncores;
-	uncore_pci_driver = &hsw_uncore_pci_driver;
-	return 0;
+	return imc_uncore_pci_init();
 }
 
 /* end of Sandy Bridge uncore support */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 6ed0bb73a864..3102b7e3b460 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2536,6 +2536,7 @@
 #define PCI_DEVICE_ID_INTEL_EESSC	0x0008
 #define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
 #define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
 #define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_PXHD_0	0x0320
 #define PCI_DEVICE_ID_INTEL_PXHD_1	0x0321
-- 
cgit v1.2.3


From 41f93af900a20d1a0a358b522b5129c89677e9dc Mon Sep 17 00:00:00 2001
From: Sandeep Nair <sandeep_n@ti.com>
Date: Fri, 28 Feb 2014 10:47:50 -0500
Subject: soc: ti: add Keystone Navigator QMSS driver

The QMSS (Queue Manager Sub System) found on Keystone SOCs is one of
the main hardware sub system which forms the backbone of the Keystone
Multi-core Navigator. QMSS consist of queue managers, packed-data structure
processors(PDSP), linking RAM, descriptor pools and infrastructure
Packet DMA.

The Queue Manager is a hardware module that is responsible for accelerating
management of the packet queues. Packets are queued/de-queued by writing or
reading descriptor address to a particular memory mapped location. The PDSPs
perform QMSS related functions like accumulation, QoS, or event management.
Linking RAM registers are used to link the descriptors which are stored in
descriptor RAM. Descriptor RAM is configurable as internal or external memory.

The QMSS driver manages the PDSP setups, linking RAM regions,
queue pool management (allocation, push, pop and notify) and descriptor
pool management. The specifics on the device tree bindings for
QMSS can be found in:
	Documentation/devicetree/bindings/soc/keystone-navigator-qmss.txt

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Kumar Gala <galak@codeaurora.org>
Cc: Olof Johansson <olof@lixom.net>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Sandeep Nair <sandeep_n@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
---
 drivers/Kconfig                  |    2 +
 drivers/soc/Kconfig              |    1 +
 drivers/soc/Makefile             |    1 +
 drivers/soc/ti/Kconfig           |   21 +
 drivers/soc/ti/Makefile          |    4 +
 drivers/soc/ti/knav_qmss.h       |  386 ++++++++
 drivers/soc/ti/knav_qmss_acc.c   |  591 +++++++++++++
 drivers/soc/ti/knav_qmss_queue.c | 1816 ++++++++++++++++++++++++++++++++++++++
 include/linux/soc/ti/knav_qmss.h |   90 ++
 9 files changed, 2912 insertions(+)
 create mode 100644 drivers/soc/ti/Kconfig
 create mode 100644 drivers/soc/ti/Makefile
 create mode 100644 drivers/soc/ti/knav_qmss.h
 create mode 100644 drivers/soc/ti/knav_qmss_acc.c
 create mode 100644 drivers/soc/ti/knav_qmss_queue.c
 create mode 100644 include/linux/soc/ti/knav_qmss.h

(limited to 'include')

diff --git a/drivers/Kconfig b/drivers/Kconfig
index 622fa266b29e..1a693d3f9d51 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -148,6 +148,8 @@ source "drivers/remoteproc/Kconfig"
 
 source "drivers/rpmsg/Kconfig"
 
+source "drivers/soc/Kconfig"
+
 source "drivers/devfreq/Kconfig"
 
 source "drivers/extcon/Kconfig"
diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig
index c8543855aa82..49e3f0cc71af 100644
--- a/drivers/soc/Kconfig
+++ b/drivers/soc/Kconfig
@@ -1,5 +1,6 @@
 menu "SOC (System On Chip) specific Drivers"
 
 source "drivers/soc/qcom/Kconfig"
+source "drivers/soc/ti/Kconfig"
 
 endmenu
diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile
index 3b1b95d932d1..0d6e35dfea8c 100644
--- a/drivers/soc/Makefile
+++ b/drivers/soc/Makefile
@@ -4,3 +4,4 @@
 
 obj-$(CONFIG_ARCH_QCOM)		+= qcom/
 obj-$(CONFIG_ARCH_TEGRA)	+= tegra/
+obj-$(CONFIG_SOC_TI)		+= ti/
diff --git a/drivers/soc/ti/Kconfig b/drivers/soc/ti/Kconfig
new file mode 100644
index 000000000000..f73896f762e8
--- /dev/null
+++ b/drivers/soc/ti/Kconfig
@@ -0,0 +1,21 @@
+#
+# TI SOC drivers
+#
+menuconfig SOC_TI
+	bool "TI SOC drivers support"
+
+if SOC_TI
+
+config KEYSTONE_NAVIGATOR_QMSS
+	tristate "Keystone Queue Manager Sub System"
+	depends on ARCH_KEYSTONE
+	help
+	  Say y here to support the Keystone multicore Navigator Queue
+	  Manager support. The Queue Manager is a hardware module that
+	  is responsible for accelerating management of the packet queues.
+	  Packets are queued/de-queued by writing/reading descriptor address
+	  to a particular memory mapped location in the Queue Manager module.
+
+	  If unsure, say N.
+
+endif # SOC_TI
diff --git a/drivers/soc/ti/Makefile b/drivers/soc/ti/Makefile
new file mode 100644
index 000000000000..bf85cacd5b85
--- /dev/null
+++ b/drivers/soc/ti/Makefile
@@ -0,0 +1,4 @@
+#
+# TI Keystone SOC drivers
+#
+obj-$(CONFIG_KEYSTONE_NAVIGATOR_QMSS)	+= knav_qmss_queue.o knav_qmss_acc.o
diff --git a/drivers/soc/ti/knav_qmss.h b/drivers/soc/ti/knav_qmss.h
new file mode 100644
index 000000000000..bc9dcc8cc3ce
--- /dev/null
+++ b/drivers/soc/ti/knav_qmss.h
@@ -0,0 +1,386 @@
+/*
+ * Keystone Navigator QMSS driver internal header
+ *
+ * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Author:	Sandeep Nair <sandeep_n@ti.com>
+ *		Cyril Chemparathy <cyril@ti.com>
+ *		Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef __KNAV_QMSS_H__
+#define __KNAV_QMSS_H__
+
+#define THRESH_GTE	BIT(7)
+#define THRESH_LT	0
+
+#define PDSP_CTRL_PC_MASK	0xffff0000
+#define PDSP_CTRL_SOFT_RESET	BIT(0)
+#define PDSP_CTRL_ENABLE	BIT(1)
+#define PDSP_CTRL_RUNNING	BIT(15)
+
+#define ACC_MAX_CHANNEL		48
+#define ACC_DEFAULT_PERIOD	25 /* usecs */
+
+#define ACC_CHANNEL_INT_BASE		2
+
+#define ACC_LIST_ENTRY_TYPE		1
+#define ACC_LIST_ENTRY_WORDS		(1 << ACC_LIST_ENTRY_TYPE)
+#define ACC_LIST_ENTRY_QUEUE_IDX	0
+#define ACC_LIST_ENTRY_DESC_IDX	(ACC_LIST_ENTRY_WORDS - 1)
+
+#define ACC_CMD_DISABLE_CHANNEL	0x80
+#define ACC_CMD_ENABLE_CHANNEL	0x81
+#define ACC_CFG_MULTI_QUEUE		BIT(21)
+
+#define ACC_INTD_OFFSET_EOI		(0x0010)
+#define ACC_INTD_OFFSET_COUNT(ch)	(0x0300 + 4 * (ch))
+#define ACC_INTD_OFFSET_STATUS(ch)	(0x0200 + 4 * ((ch) / 32))
+
+#define RANGE_MAX_IRQS			64
+
+#define ACC_DESCS_MAX		SZ_1K
+#define ACC_DESCS_MASK		(ACC_DESCS_MAX - 1)
+#define DESC_SIZE_MASK		0xful
+#define DESC_PTR_MASK		(~DESC_SIZE_MASK)
+
+#define KNAV_NAME_SIZE			32
+
+enum knav_acc_result {
+	ACC_RET_IDLE,
+	ACC_RET_SUCCESS,
+	ACC_RET_INVALID_COMMAND,
+	ACC_RET_INVALID_CHANNEL,
+	ACC_RET_INACTIVE_CHANNEL,
+	ACC_RET_ACTIVE_CHANNEL,
+	ACC_RET_INVALID_QUEUE,
+	ACC_RET_INVALID_RET,
+};
+
+struct knav_reg_config {
+	u32		revision;
+	u32		__pad1;
+	u32		divert;
+	u32		link_ram_base0;
+	u32		link_ram_size0;
+	u32		link_ram_base1;
+	u32		__pad2[2];
+	u32		starvation[0];
+};
+
+struct knav_reg_region {
+	u32		base;
+	u32		start_index;
+	u32		size_count;
+	u32		__pad;
+};
+
+struct knav_reg_pdsp_regs {
+	u32		control;
+	u32		status;
+	u32		cycle_count;
+	u32		stall_count;
+};
+
+struct knav_reg_acc_command {
+	u32		command;
+	u32		queue_mask;
+	u32		list_phys;
+	u32		queue_num;
+	u32		timer_config;
+};
+
+struct knav_link_ram_block {
+	dma_addr_t	 phys;
+	void		*virt;
+	size_t		 size;
+};
+
+struct knav_acc_info {
+	u32			 pdsp_id;
+	u32			 start_channel;
+	u32			 list_entries;
+	u32			 pacing_mode;
+	u32			 timer_count;
+	int			 mem_size;
+	int			 list_size;
+	struct knav_pdsp_info	*pdsp;
+};
+
+struct knav_acc_channel {
+	u32			channel;
+	u32			list_index;
+	u32			open_mask;
+	u32			*list_cpu[2];
+	dma_addr_t		list_dma[2];
+	char			name[KNAV_NAME_SIZE];
+	atomic_t		retrigger_count;
+};
+
+struct knav_pdsp_info {
+	const char					*name;
+	struct knav_reg_pdsp_regs  __iomem		*regs;
+	union {
+		void __iomem				*command;
+		struct knav_reg_acc_command __iomem	*acc_command;
+		u32 __iomem				*qos_command;
+	};
+	void __iomem					*intd;
+	u32 __iomem					*iram;
+	const char					*firmware;
+	u32						id;
+	struct list_head				list;
+};
+
+struct knav_qmgr_info {
+	unsigned			start_queue;
+	unsigned			num_queues;
+	struct knav_reg_config __iomem	*reg_config;
+	struct knav_reg_region __iomem	*reg_region;
+	struct knav_reg_queue __iomem	*reg_push, *reg_pop, *reg_peek;
+	void __iomem			*reg_status;
+	struct list_head		list;
+};
+
+#define KNAV_NUM_LINKRAM	2
+
+/**
+ * struct knav_queue_stats:	queue statistics
+ * pushes:			number of push operations
+ * pops:			number of pop operations
+ * push_errors:			number of push errors
+ * pop_errors:			number of pop errors
+ * notifies:			notifier counts
+ */
+struct knav_queue_stats {
+	atomic_t	 pushes;
+	atomic_t	 pops;
+	atomic_t	 push_errors;
+	atomic_t	 pop_errors;
+	atomic_t	 notifies;
+};
+
+/**
+ * struct knav_reg_queue:	queue registers
+ * @entry_count:		valid entries in the queue
+ * @byte_count:			total byte count in thhe queue
+ * @packet_size:		packet size for the queue
+ * @ptr_size_thresh:		packet pointer size threshold
+ */
+struct knav_reg_queue {
+	u32		entry_count;
+	u32		byte_count;
+	u32		packet_size;
+	u32		ptr_size_thresh;
+};
+
+/**
+ * struct knav_region:		qmss region info
+ * @dma_start, dma_end:		start and end dma address
+ * @virt_start, virt_end:	start and end virtual address
+ * @desc_size:			descriptor size
+ * @used_desc:			consumed descriptors
+ * @id:				region number
+ * @num_desc:			total descriptors
+ * @link_index:			index of the first descriptor
+ * @name:			region name
+ * @list:			instance in the device's region list
+ * @pools:			list of descriptor pools in the region
+ */
+struct knav_region {
+	dma_addr_t		dma_start, dma_end;
+	void			*virt_start, *virt_end;
+	unsigned		desc_size;
+	unsigned		used_desc;
+	unsigned		id;
+	unsigned		num_desc;
+	unsigned		link_index;
+	const char		*name;
+	struct list_head	list;
+	struct list_head	pools;
+};
+
+/**
+ * struct knav_pool:		qmss pools
+ * @dev:			device pointer
+ * @region:			qmss region info
+ * @queue:			queue registers
+ * @kdev:			qmss device pointer
+ * @region_offset:		offset from the base
+ * @num_desc:			total descriptors
+ * @desc_size:			descriptor size
+ * @region_id:			region number
+ * @name:			pool name
+ * @list:			list head
+ * @region_inst:		instance in the region's pool list
+ */
+struct knav_pool {
+	struct device			*dev;
+	struct knav_region		*region;
+	struct knav_queue		*queue;
+	struct knav_device		*kdev;
+	int				region_offset;
+	int				num_desc;
+	int				desc_size;
+	int				region_id;
+	const char			*name;
+	struct list_head		list;
+	struct list_head		region_inst;
+};
+
+/**
+ * struct knav_queue_inst:		qmss queue instace properties
+ * @descs:				descriptor pointer
+ * @desc_head, desc_tail, desc_count:	descriptor counters
+ * @acc:				accumulator channel pointer
+ * @kdev:				qmss device pointer
+ * @range:				range info
+ * @qmgr:				queue manager info
+ * @id:					queue instace id
+ * @irq_num:				irq line number
+ * @notify_needed:			notifier needed based on queue type
+ * @num_notifiers:			total notifiers
+ * @handles:				list head
+ * @name:				queue instance name
+ * @irq_name:				irq line name
+ */
+struct knav_queue_inst {
+	u32				*descs;
+	atomic_t			desc_head, desc_tail, desc_count;
+	struct knav_acc_channel	*acc;
+	struct knav_device		*kdev;
+	struct knav_range_info		*range;
+	struct knav_qmgr_info		*qmgr;
+	u32				id;
+	int				irq_num;
+	int				notify_needed;
+	atomic_t			num_notifiers;
+	struct list_head		handles;
+	const char			*name;
+	const char			*irq_name;
+};
+
+/**
+ * struct knav_queue:			qmss queue properties
+ * @reg_push, reg_pop, reg_peek:	push, pop queue registers
+ * @inst:				qmss queue instace properties
+ * @notifier_fn:			notifier function
+ * @notifier_fn_arg:			notifier function argument
+ * @notifier_enabled:			notier enabled for a give queue
+ * @rcu:				rcu head
+ * @flags:				queue flags
+ * @list:				list head
+ */
+struct knav_queue {
+	struct knav_reg_queue __iomem	*reg_push, *reg_pop, *reg_peek;
+	struct knav_queue_inst		*inst;
+	struct knav_queue_stats	stats;
+	knav_queue_notify_fn		notifier_fn;
+	void				*notifier_fn_arg;
+	atomic_t			notifier_enabled;
+	struct rcu_head			rcu;
+	unsigned			flags;
+	struct list_head		list;
+};
+
+struct knav_device {
+	struct device				*dev;
+	unsigned				base_id;
+	unsigned				num_queues;
+	unsigned				num_queues_in_use;
+	unsigned				inst_shift;
+	struct knav_link_ram_block		link_rams[KNAV_NUM_LINKRAM];
+	void					*instances;
+	struct list_head			regions;
+	struct list_head			queue_ranges;
+	struct list_head			pools;
+	struct list_head			pdsps;
+	struct list_head			qmgrs;
+};
+
+struct knav_range_ops {
+	int	(*init_range)(struct knav_range_info *range);
+	int	(*free_range)(struct knav_range_info *range);
+	int	(*init_queue)(struct knav_range_info *range,
+			      struct knav_queue_inst *inst);
+	int	(*open_queue)(struct knav_range_info *range,
+			      struct knav_queue_inst *inst, unsigned flags);
+	int	(*close_queue)(struct knav_range_info *range,
+			       struct knav_queue_inst *inst);
+	int	(*set_notify)(struct knav_range_info *range,
+			      struct knav_queue_inst *inst, bool enabled);
+};
+
+struct knav_irq_info {
+	int	irq;
+	u32	cpu_map;
+};
+
+struct knav_range_info {
+	const char			*name;
+	struct knav_device		*kdev;
+	unsigned			queue_base;
+	unsigned			num_queues;
+	void				*queue_base_inst;
+	unsigned			flags;
+	struct list_head		list;
+	struct knav_range_ops		*ops;
+	struct knav_acc_info		acc_info;
+	struct knav_acc_channel	*acc;
+	unsigned			num_irqs;
+	struct knav_irq_info		irqs[RANGE_MAX_IRQS];
+};
+
+#define RANGE_RESERVED		BIT(0)
+#define RANGE_HAS_IRQ		BIT(1)
+#define RANGE_HAS_ACCUMULATOR	BIT(2)
+#define RANGE_MULTI_QUEUE	BIT(3)
+
+#define for_each_region(kdev, region)				\
+	list_for_each_entry(region, &kdev->regions, list)
+
+#define first_region(kdev)					\
+	list_first_entry(&kdev->regions, \
+			struct knav_region, list)
+
+#define for_each_queue_range(kdev, range)			\
+	list_for_each_entry(range, &kdev->queue_ranges, list)
+
+#define first_queue_range(kdev)					\
+	list_first_entry(&kdev->queue_ranges, \
+			struct knav_range_info, list)
+
+#define for_each_pool(kdev, pool)				\
+	list_for_each_entry(pool, &kdev->pools, list)
+
+#define for_each_pdsp(kdev, pdsp)				\
+	list_for_each_entry(pdsp, &kdev->pdsps, list)
+
+#define for_each_qmgr(kdev, qmgr)				\
+	list_for_each_entry(qmgr, &kdev->qmgrs, list)
+
+static inline struct knav_pdsp_info *
+knav_find_pdsp(struct knav_device *kdev, unsigned pdsp_id)
+{
+	struct knav_pdsp_info *pdsp;
+
+	for_each_pdsp(kdev, pdsp)
+		if (pdsp_id == pdsp->id)
+			return pdsp;
+	return NULL;
+}
+
+extern int knav_init_acc_range(struct knav_device *kdev,
+					struct device_node *node,
+					struct knav_range_info *range);
+extern void knav_queue_notify(struct knav_queue_inst *inst);
+
+#endif /* __KNAV_QMSS_H__ */
diff --git a/drivers/soc/ti/knav_qmss_acc.c b/drivers/soc/ti/knav_qmss_acc.c
new file mode 100644
index 000000000000..6fbfde6e748f
--- /dev/null
+++ b/drivers/soc/ti/knav_qmss_acc.c
@@ -0,0 +1,591 @@
+/*
+ * Keystone accumulator queue manager
+ *
+ * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Author:	Sandeep Nair <sandeep_n@ti.com>
+ *		Cyril Chemparathy <cyril@ti.com>
+ *		Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/soc/ti/knav_qmss.h>
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_address.h>
+#include <linux/firmware.h>
+
+#include "knav_qmss.h"
+
+#define knav_range_offset_to_inst(kdev, range, q)	\
+	(range->queue_base_inst + (q << kdev->inst_shift))
+
+static void __knav_acc_notify(struct knav_range_info *range,
+				struct knav_acc_channel *acc)
+{
+	struct knav_device *kdev = range->kdev;
+	struct knav_queue_inst *inst;
+	int range_base, queue;
+
+	range_base = kdev->base_id + range->queue_base;
+
+	if (range->flags & RANGE_MULTI_QUEUE) {
+		for (queue = 0; queue < range->num_queues; queue++) {
+			inst = knav_range_offset_to_inst(kdev, range,
+								queue);
+			if (inst->notify_needed) {
+				inst->notify_needed = 0;
+				dev_dbg(kdev->dev, "acc-irq: notifying %d\n",
+					range_base + queue);
+				knav_queue_notify(inst);
+			}
+		}
+	} else {
+		queue = acc->channel - range->acc_info.start_channel;
+		inst = knav_range_offset_to_inst(kdev, range, queue);
+		dev_dbg(kdev->dev, "acc-irq: notifying %d\n",
+			range_base + queue);
+		knav_queue_notify(inst);
+	}
+}
+
+static int knav_acc_set_notify(struct knav_range_info *range,
+				struct knav_queue_inst *kq,
+				bool enabled)
+{
+	struct knav_pdsp_info *pdsp = range->acc_info.pdsp;
+	struct knav_device *kdev = range->kdev;
+	u32 mask, offset;
+
+	/*
+	 * when enabling, we need to re-trigger an interrupt if we
+	 * have descriptors pending
+	 */
+	if (!enabled || atomic_read(&kq->desc_count) <= 0)
+		return 0;
+
+	kq->notify_needed = 1;
+	atomic_inc(&kq->acc->retrigger_count);
+	mask = BIT(kq->acc->channel % 32);
+	offset = ACC_INTD_OFFSET_STATUS(kq->acc->channel);
+	dev_dbg(kdev->dev, "setup-notify: re-triggering irq for %s\n",
+		kq->acc->name);
+	writel_relaxed(mask, pdsp->intd + offset);
+	return 0;
+}
+
+static irqreturn_t knav_acc_int_handler(int irq, void *_instdata)
+{
+	struct knav_acc_channel *acc;
+	struct knav_queue_inst *kq = NULL;
+	struct knav_range_info *range;
+	struct knav_pdsp_info *pdsp;
+	struct knav_acc_info *info;
+	struct knav_device *kdev;
+
+	u32 *list, *list_cpu, val, idx, notifies;
+	int range_base, channel, queue = 0;
+	dma_addr_t list_dma;
+
+	range = _instdata;
+	info  = &range->acc_info;
+	kdev  = range->kdev;
+	pdsp  = range->acc_info.pdsp;
+	acc   = range->acc;
+
+	range_base = kdev->base_id + range->queue_base;
+	if ((range->flags & RANGE_MULTI_QUEUE) == 0) {
+		for (queue = 0; queue < range->num_irqs; queue++)
+			if (range->irqs[queue].irq == irq)
+				break;
+		kq = knav_range_offset_to_inst(kdev, range, queue);
+		acc += queue;
+	}
+
+	channel = acc->channel;
+	list_dma = acc->list_dma[acc->list_index];
+	list_cpu = acc->list_cpu[acc->list_index];
+	dev_dbg(kdev->dev, "acc-irq: channel %d, list %d, virt %p, phys %x\n",
+		channel, acc->list_index, list_cpu, list_dma);
+	if (atomic_read(&acc->retrigger_count)) {
+		atomic_dec(&acc->retrigger_count);
+		__knav_acc_notify(range, acc);
+		writel_relaxed(1, pdsp->intd + ACC_INTD_OFFSET_COUNT(channel));
+		/* ack the interrupt */
+		writel_relaxed(ACC_CHANNEL_INT_BASE + channel,
+			       pdsp->intd + ACC_INTD_OFFSET_EOI);
+
+		return IRQ_HANDLED;
+	}
+
+	notifies = readl_relaxed(pdsp->intd + ACC_INTD_OFFSET_COUNT(channel));
+	WARN_ON(!notifies);
+	dma_sync_single_for_cpu(kdev->dev, list_dma, info->list_size,
+				DMA_FROM_DEVICE);
+
+	for (list = list_cpu; list < list_cpu + (info->list_size / sizeof(u32));
+	     list += ACC_LIST_ENTRY_WORDS) {
+		if (ACC_LIST_ENTRY_WORDS == 1) {
+			dev_dbg(kdev->dev,
+				"acc-irq: list %d, entry @%p, %08x\n",
+				acc->list_index, list, list[0]);
+		} else if (ACC_LIST_ENTRY_WORDS == 2) {
+			dev_dbg(kdev->dev,
+				"acc-irq: list %d, entry @%p, %08x %08x\n",
+				acc->list_index, list, list[0], list[1]);
+		} else if (ACC_LIST_ENTRY_WORDS == 4) {
+			dev_dbg(kdev->dev,
+				"acc-irq: list %d, entry @%p, %08x %08x %08x %08x\n",
+				acc->list_index, list, list[0], list[1],
+				list[2], list[3]);
+		}
+
+		val = list[ACC_LIST_ENTRY_DESC_IDX];
+		if (!val)
+			break;
+
+		if (range->flags & RANGE_MULTI_QUEUE) {
+			queue = list[ACC_LIST_ENTRY_QUEUE_IDX] >> 16;
+			if (queue < range_base ||
+			    queue >= range_base + range->num_queues) {
+				dev_err(kdev->dev,
+					"bad queue %d, expecting %d-%d\n",
+					queue, range_base,
+					range_base + range->num_queues);
+				break;
+			}
+			queue -= range_base;
+			kq = knav_range_offset_to_inst(kdev, range,
+								queue);
+		}
+
+		if (atomic_inc_return(&kq->desc_count) >= ACC_DESCS_MAX) {
+			atomic_dec(&kq->desc_count);
+			dev_err(kdev->dev,
+				"acc-irq: queue %d full, entry dropped\n",
+				queue + range_base);
+			continue;
+		}
+
+		idx = atomic_inc_return(&kq->desc_tail) & ACC_DESCS_MASK;
+		kq->descs[idx] = val;
+		kq->notify_needed = 1;
+		dev_dbg(kdev->dev, "acc-irq: enqueue %08x at %d, queue %d\n",
+			val, idx, queue + range_base);
+	}
+
+	__knav_acc_notify(range, acc);
+	memset(list_cpu, 0, info->list_size);
+	dma_sync_single_for_device(kdev->dev, list_dma, info->list_size,
+				   DMA_TO_DEVICE);
+
+	/* flip to the other list */
+	acc->list_index ^= 1;
+
+	/* reset the interrupt counter */
+	writel_relaxed(1, pdsp->intd + ACC_INTD_OFFSET_COUNT(channel));
+
+	/* ack the interrupt */
+	writel_relaxed(ACC_CHANNEL_INT_BASE + channel,
+		       pdsp->intd + ACC_INTD_OFFSET_EOI);
+
+	return IRQ_HANDLED;
+}
+
+int knav_range_setup_acc_irq(struct knav_range_info *range,
+				int queue, bool enabled)
+{
+	struct knav_device *kdev = range->kdev;
+	struct knav_acc_channel *acc;
+	unsigned long cpu_map;
+	int ret = 0, irq;
+	u32 old, new;
+
+	if (range->flags & RANGE_MULTI_QUEUE) {
+		acc = range->acc;
+		irq = range->irqs[0].irq;
+		cpu_map = range->irqs[0].cpu_map;
+	} else {
+		acc = range->acc + queue;
+		irq = range->irqs[queue].irq;
+		cpu_map = range->irqs[queue].cpu_map;
+	}
+
+	old = acc->open_mask;
+	if (enabled)
+		new = old | BIT(queue);
+	else
+		new = old & ~BIT(queue);
+	acc->open_mask = new;
+
+	dev_dbg(kdev->dev,
+		"setup-acc-irq: open mask old %08x, new %08x, channel %s\n",
+		old, new, acc->name);
+
+	if (likely(new == old))
+		return 0;
+
+	if (new && !old) {
+		dev_dbg(kdev->dev,
+			"setup-acc-irq: requesting %s for channel %s\n",
+			acc->name, acc->name);
+		ret = request_irq(irq, knav_acc_int_handler, 0, acc->name,
+				  range);
+		if (!ret && cpu_map) {
+			ret = irq_set_affinity_hint(irq, to_cpumask(&cpu_map));
+			if (ret) {
+				dev_warn(range->kdev->dev,
+					 "Failed to set IRQ affinity\n");
+				return ret;
+			}
+		}
+	}
+
+	if (old && !new) {
+		dev_dbg(kdev->dev, "setup-acc-irq: freeing %s for channel %s\n",
+			acc->name, acc->name);
+		free_irq(irq, range);
+	}
+
+	return ret;
+}
+
+static const char *knav_acc_result_str(enum knav_acc_result result)
+{
+	static const char * const result_str[] = {
+		[ACC_RET_IDLE]			= "idle",
+		[ACC_RET_SUCCESS]		= "success",
+		[ACC_RET_INVALID_COMMAND]	= "invalid command",
+		[ACC_RET_INVALID_CHANNEL]	= "invalid channel",
+		[ACC_RET_INACTIVE_CHANNEL]	= "inactive channel",
+		[ACC_RET_ACTIVE_CHANNEL]	= "active channel",
+		[ACC_RET_INVALID_QUEUE]		= "invalid queue",
+		[ACC_RET_INVALID_RET]		= "invalid return code",
+	};
+
+	if (result >= ARRAY_SIZE(result_str))
+		return result_str[ACC_RET_INVALID_RET];
+	else
+		return result_str[result];
+}
+
+static enum knav_acc_result
+knav_acc_write(struct knav_device *kdev, struct knav_pdsp_info *pdsp,
+		struct knav_reg_acc_command *cmd)
+{
+	u32 result;
+
+	dev_dbg(kdev->dev, "acc command %08x %08x %08x %08x %08x\n",
+		cmd->command, cmd->queue_mask, cmd->list_phys,
+		cmd->queue_num, cmd->timer_config);
+
+	writel_relaxed(cmd->timer_config, &pdsp->acc_command->timer_config);
+	writel_relaxed(cmd->queue_num, &pdsp->acc_command->queue_num);
+	writel_relaxed(cmd->list_phys, &pdsp->acc_command->list_phys);
+	writel_relaxed(cmd->queue_mask, &pdsp->acc_command->queue_mask);
+	writel_relaxed(cmd->command, &pdsp->acc_command->command);
+
+	/* wait for the command to clear */
+	do {
+		result = readl_relaxed(&pdsp->acc_command->command);
+	} while ((result >> 8) & 0xff);
+
+	return (result >> 24) & 0xff;
+}
+
+static void knav_acc_setup_cmd(struct knav_device *kdev,
+				struct knav_range_info *range,
+				struct knav_reg_acc_command *cmd,
+				int queue)
+{
+	struct knav_acc_info *info = &range->acc_info;
+	struct knav_acc_channel *acc;
+	int queue_base;
+	u32 queue_mask;
+
+	if (range->flags & RANGE_MULTI_QUEUE) {
+		acc = range->acc;
+		queue_base = range->queue_base;
+		queue_mask = BIT(range->num_queues) - 1;
+	} else {
+		acc = range->acc + queue;
+		queue_base = range->queue_base + queue;
+		queue_mask = 0;
+	}
+
+	memset(cmd, 0, sizeof(*cmd));
+	cmd->command    = acc->channel;
+	cmd->queue_mask = queue_mask;
+	cmd->list_phys  = acc->list_dma[0];
+	cmd->queue_num  = info->list_entries << 16;
+	cmd->queue_num |= queue_base;
+
+	cmd->timer_config = ACC_LIST_ENTRY_TYPE << 18;
+	if (range->flags & RANGE_MULTI_QUEUE)
+		cmd->timer_config |= ACC_CFG_MULTI_QUEUE;
+	cmd->timer_config |= info->pacing_mode << 16;
+	cmd->timer_config |= info->timer_count;
+}
+
+static void knav_acc_stop(struct knav_device *kdev,
+				struct knav_range_info *range,
+				int queue)
+{
+	struct knav_reg_acc_command cmd;
+	struct knav_acc_channel *acc;
+	enum knav_acc_result result;
+
+	acc = range->acc + queue;
+
+	knav_acc_setup_cmd(kdev, range, &cmd, queue);
+	cmd.command |= ACC_CMD_DISABLE_CHANNEL << 8;
+	result = knav_acc_write(kdev, range->acc_info.pdsp, &cmd);
+
+	dev_dbg(kdev->dev, "stopped acc channel %s, result %s\n",
+		acc->name, knav_acc_result_str(result));
+}
+
+static enum knav_acc_result knav_acc_start(struct knav_device *kdev,
+						struct knav_range_info *range,
+						int queue)
+{
+	struct knav_reg_acc_command cmd;
+	struct knav_acc_channel *acc;
+	enum knav_acc_result result;
+
+	acc = range->acc + queue;
+
+	knav_acc_setup_cmd(kdev, range, &cmd, queue);
+	cmd.command |= ACC_CMD_ENABLE_CHANNEL << 8;
+	result = knav_acc_write(kdev, range->acc_info.pdsp, &cmd);
+
+	dev_dbg(kdev->dev, "started acc channel %s, result %s\n",
+		acc->name, knav_acc_result_str(result));
+
+	return result;
+}
+
+static int knav_acc_init_range(struct knav_range_info *range)
+{
+	struct knav_device *kdev = range->kdev;
+	struct knav_acc_channel *acc;
+	enum knav_acc_result result;
+	int queue;
+
+	for (queue = 0; queue < range->num_queues; queue++) {
+		acc = range->acc + queue;
+
+		knav_acc_stop(kdev, range, queue);
+		acc->list_index = 0;
+		result = knav_acc_start(kdev, range, queue);
+
+		if (result != ACC_RET_SUCCESS)
+			return -EIO;
+
+		if (range->flags & RANGE_MULTI_QUEUE)
+			return 0;
+	}
+	return 0;
+}
+
+static int knav_acc_init_queue(struct knav_range_info *range,
+				struct knav_queue_inst *kq)
+{
+	unsigned id = kq->id - range->queue_base;
+
+	kq->descs = devm_kzalloc(range->kdev->dev,
+				 ACC_DESCS_MAX * sizeof(u32), GFP_KERNEL);
+	if (!kq->descs)
+		return -ENOMEM;
+
+	kq->acc = range->acc;
+	if ((range->flags & RANGE_MULTI_QUEUE) == 0)
+		kq->acc += id;
+	return 0;
+}
+
+static int knav_acc_open_queue(struct knav_range_info *range,
+				struct knav_queue_inst *inst, unsigned flags)
+{
+	unsigned id = inst->id - range->queue_base;
+
+	return knav_range_setup_acc_irq(range, id, true);
+}
+
+static int knav_acc_close_queue(struct knav_range_info *range,
+					struct knav_queue_inst *inst)
+{
+	unsigned id = inst->id - range->queue_base;
+
+	return knav_range_setup_acc_irq(range, id, false);
+}
+
+static int knav_acc_free_range(struct knav_range_info *range)
+{
+	struct knav_device *kdev = range->kdev;
+	struct knav_acc_channel *acc;
+	struct knav_acc_info *info;
+	int channel, channels;
+
+	info = &range->acc_info;
+
+	if (range->flags & RANGE_MULTI_QUEUE)
+		channels = 1;
+	else
+		channels = range->num_queues;
+
+	for (channel = 0; channel < channels; channel++) {
+		acc = range->acc + channel;
+		if (!acc->list_cpu[0])
+			continue;
+		dma_unmap_single(kdev->dev, acc->list_dma[0],
+				 info->mem_size, DMA_BIDIRECTIONAL);
+		free_pages_exact(acc->list_cpu[0], info->mem_size);
+	}
+	devm_kfree(range->kdev->dev, range->acc);
+	return 0;
+}
+
+struct knav_range_ops knav_acc_range_ops = {
+	.set_notify	= knav_acc_set_notify,
+	.init_queue	= knav_acc_init_queue,
+	.open_queue	= knav_acc_open_queue,
+	.close_queue	= knav_acc_close_queue,
+	.init_range	= knav_acc_init_range,
+	.free_range	= knav_acc_free_range,
+};
+
+/**
+ * knav_init_acc_range: Initialise accumulator ranges
+ *
+ * @kdev:		qmss device
+ * @node:		device node
+ * @range:		qmms range information
+ *
+ * Return 0 on success or error
+ */
+int knav_init_acc_range(struct knav_device *kdev,
+				struct device_node *node,
+				struct knav_range_info *range)
+{
+	struct knav_acc_channel *acc;
+	struct knav_pdsp_info *pdsp;
+	struct knav_acc_info *info;
+	int ret, channel, channels;
+	int list_size, mem_size;
+	dma_addr_t list_dma;
+	void *list_mem;
+	u32 config[5];
+
+	range->flags |= RANGE_HAS_ACCUMULATOR;
+	info = &range->acc_info;
+
+	ret = of_property_read_u32_array(node, "accumulator", config, 5);
+	if (ret)
+		return ret;
+
+	info->pdsp_id		= config[0];
+	info->start_channel	= config[1];
+	info->list_entries	= config[2];
+	info->pacing_mode	= config[3];
+	info->timer_count	= config[4] / ACC_DEFAULT_PERIOD;
+
+	if (info->start_channel > ACC_MAX_CHANNEL) {
+		dev_err(kdev->dev, "channel %d invalid for range %s\n",
+			info->start_channel, range->name);
+		return -EINVAL;
+	}
+
+	if (info->pacing_mode > 3) {
+		dev_err(kdev->dev, "pacing mode %d invalid for range %s\n",
+			info->pacing_mode, range->name);
+		return -EINVAL;
+	}
+
+	pdsp = knav_find_pdsp(kdev, info->pdsp_id);
+	if (!pdsp) {
+		dev_err(kdev->dev, "pdsp id %d not found for range %s\n",
+			info->pdsp_id, range->name);
+		return -EINVAL;
+	}
+
+	info->pdsp = pdsp;
+	channels = range->num_queues;
+	if (of_get_property(node, "multi-queue", NULL)) {
+		range->flags |= RANGE_MULTI_QUEUE;
+		channels = 1;
+		if (range->queue_base & (32 - 1)) {
+			dev_err(kdev->dev,
+				"misaligned multi-queue accumulator range %s\n",
+				range->name);
+			return -EINVAL;
+		}
+		if (range->num_queues > 32) {
+			dev_err(kdev->dev,
+				"too many queues in accumulator range %s\n",
+				range->name);
+			return -EINVAL;
+		}
+	}
+
+	/* figure out list size */
+	list_size  = info->list_entries;
+	list_size *= ACC_LIST_ENTRY_WORDS * sizeof(u32);
+	info->list_size = list_size;
+	mem_size   = PAGE_ALIGN(list_size * 2);
+	info->mem_size  = mem_size;
+	range->acc = devm_kzalloc(kdev->dev, channels * sizeof(*range->acc),
+				  GFP_KERNEL);
+	if (!range->acc)
+		return -ENOMEM;
+
+	for (channel = 0; channel < channels; channel++) {
+		acc = range->acc + channel;
+		acc->channel = info->start_channel + channel;
+
+		/* allocate memory for the two lists */
+		list_mem = alloc_pages_exact(mem_size, GFP_KERNEL | GFP_DMA);
+		if (!list_mem)
+			return -ENOMEM;
+
+		list_dma = dma_map_single(kdev->dev, list_mem, mem_size,
+					  DMA_BIDIRECTIONAL);
+		if (dma_mapping_error(kdev->dev, list_dma)) {
+			free_pages_exact(list_mem, mem_size);
+			return -ENOMEM;
+		}
+
+		memset(list_mem, 0, mem_size);
+		dma_sync_single_for_device(kdev->dev, list_dma, mem_size,
+					   DMA_TO_DEVICE);
+		scnprintf(acc->name, sizeof(acc->name), "hwqueue-acc-%d",
+			  acc->channel);
+		acc->list_cpu[0] = list_mem;
+		acc->list_cpu[1] = list_mem + list_size;
+		acc->list_dma[0] = list_dma;
+		acc->list_dma[1] = list_dma + list_size;
+		dev_dbg(kdev->dev, "%s: channel %d, phys %08x, virt %8p\n",
+			acc->name, acc->channel, list_dma, list_mem);
+	}
+
+	range->ops = &knav_acc_range_ops;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(knav_init_acc_range);
diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c
new file mode 100644
index 000000000000..0a2c8634c48b
--- /dev/null
+++ b/drivers/soc/ti/knav_qmss_queue.c
@@ -0,0 +1,1816 @@
+/*
+ * Keystone Queue Manager subsystem driver
+ *
+ * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Authors:	Sandeep Nair <sandeep_n@ti.com>
+ *		Cyril Chemparathy <cyril@ti.com>
+ *		Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_device.h>
+#include <linux/of_address.h>
+#include <linux/pm_runtime.h>
+#include <linux/firmware.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/string.h>
+#include <linux/soc/ti/knav_qmss.h>
+
+#include "knav_qmss.h"
+
+static struct knav_device *kdev;
+static DEFINE_MUTEX(knav_dev_lock);
+
+/* Queue manager register indices in DTS */
+#define KNAV_QUEUE_PEEK_REG_INDEX	0
+#define KNAV_QUEUE_STATUS_REG_INDEX	1
+#define KNAV_QUEUE_CONFIG_REG_INDEX	2
+#define KNAV_QUEUE_REGION_REG_INDEX	3
+#define KNAV_QUEUE_PUSH_REG_INDEX	4
+#define KNAV_QUEUE_POP_REG_INDEX	5
+
+/* PDSP register indices in DTS */
+#define KNAV_QUEUE_PDSP_IRAM_REG_INDEX	0
+#define KNAV_QUEUE_PDSP_REGS_REG_INDEX	1
+#define KNAV_QUEUE_PDSP_INTD_REG_INDEX	2
+#define KNAV_QUEUE_PDSP_CMD_REG_INDEX	3
+
+#define knav_queue_idx_to_inst(kdev, idx)			\
+	(kdev->instances + (idx << kdev->inst_shift))
+
+#define for_each_handle_rcu(qh, inst)			\
+	list_for_each_entry_rcu(qh, &inst->handles, list)
+
+#define for_each_instance(idx, inst, kdev)		\
+	for (idx = 0, inst = kdev->instances;		\
+	     idx < (kdev)->num_queues_in_use;			\
+	     idx++, inst = knav_queue_idx_to_inst(kdev, idx))
+
+/**
+ * knav_queue_notify: qmss queue notfier call
+ *
+ * @inst:		qmss queue instance like accumulator
+ */
+void knav_queue_notify(struct knav_queue_inst *inst)
+{
+	struct knav_queue *qh;
+
+	if (!inst)
+		return;
+
+	rcu_read_lock();
+	for_each_handle_rcu(qh, inst) {
+		if (atomic_read(&qh->notifier_enabled) <= 0)
+			continue;
+		if (WARN_ON(!qh->notifier_fn))
+			continue;
+		atomic_inc(&qh->stats.notifies);
+		qh->notifier_fn(qh->notifier_fn_arg);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(knav_queue_notify);
+
+static irqreturn_t knav_queue_int_handler(int irq, void *_instdata)
+{
+	struct knav_queue_inst *inst = _instdata;
+
+	knav_queue_notify(inst);
+	return IRQ_HANDLED;
+}
+
+static int knav_queue_setup_irq(struct knav_range_info *range,
+			  struct knav_queue_inst *inst)
+{
+	unsigned queue = inst->id - range->queue_base;
+	unsigned long cpu_map;
+	int ret = 0, irq;
+
+	if (range->flags & RANGE_HAS_IRQ) {
+		irq = range->irqs[queue].irq;
+		cpu_map = range->irqs[queue].cpu_map;
+		ret = request_irq(irq, knav_queue_int_handler, 0,
+					inst->irq_name, inst);
+		if (ret)
+			return ret;
+		disable_irq(irq);
+		if (cpu_map) {
+			ret = irq_set_affinity_hint(irq, to_cpumask(&cpu_map));
+			if (ret) {
+				dev_warn(range->kdev->dev,
+					 "Failed to set IRQ affinity\n");
+				return ret;
+			}
+		}
+	}
+	return ret;
+}
+
+static void knav_queue_free_irq(struct knav_queue_inst *inst)
+{
+	struct knav_range_info *range = inst->range;
+	unsigned queue = inst->id - inst->range->queue_base;
+	int irq;
+
+	if (range->flags & RANGE_HAS_IRQ) {
+		irq = range->irqs[queue].irq;
+		irq_set_affinity_hint(irq, NULL);
+		free_irq(irq, inst);
+	}
+}
+
+static inline bool knav_queue_is_busy(struct knav_queue_inst *inst)
+{
+	return !list_empty(&inst->handles);
+}
+
+static inline bool knav_queue_is_reserved(struct knav_queue_inst *inst)
+{
+	return inst->range->flags & RANGE_RESERVED;
+}
+
+static inline bool knav_queue_is_shared(struct knav_queue_inst *inst)
+{
+	struct knav_queue *tmp;
+
+	rcu_read_lock();
+	for_each_handle_rcu(tmp, inst) {
+		if (tmp->flags & KNAV_QUEUE_SHARED) {
+			rcu_read_unlock();
+			return true;
+		}
+	}
+	rcu_read_unlock();
+	return false;
+}
+
+static inline bool knav_queue_match_type(struct knav_queue_inst *inst,
+						unsigned type)
+{
+	if ((type == KNAV_QUEUE_QPEND) &&
+	    (inst->range->flags & RANGE_HAS_IRQ)) {
+		return true;
+	} else if ((type == KNAV_QUEUE_ACC) &&
+		(inst->range->flags & RANGE_HAS_ACCUMULATOR)) {
+		return true;
+	} else if ((type == KNAV_QUEUE_GP) &&
+		!(inst->range->flags &
+			(RANGE_HAS_ACCUMULATOR | RANGE_HAS_IRQ))) {
+		return true;
+	}
+	return false;
+}
+
+static inline struct knav_queue_inst *
+knav_queue_match_id_to_inst(struct knav_device *kdev, unsigned id)
+{
+	struct knav_queue_inst *inst;
+	int idx;
+
+	for_each_instance(idx, inst, kdev) {
+		if (inst->id == id)
+			return inst;
+	}
+	return NULL;
+}
+
+static inline struct knav_queue_inst *knav_queue_find_by_id(int id)
+{
+	if (kdev->base_id <= id &&
+	    kdev->base_id + kdev->num_queues > id) {
+		id -= kdev->base_id;
+		return knav_queue_match_id_to_inst(kdev, id);
+	}
+	return NULL;
+}
+
+static struct knav_queue *__knav_queue_open(struct knav_queue_inst *inst,
+				      const char *name, unsigned flags)
+{
+	struct knav_queue *qh;
+	unsigned id;
+	int ret = 0;
+
+	qh = devm_kzalloc(inst->kdev->dev, sizeof(*qh), GFP_KERNEL);
+	if (!qh)
+		return ERR_PTR(-ENOMEM);
+
+	qh->flags = flags;
+	qh->inst = inst;
+	id = inst->id - inst->qmgr->start_queue;
+	qh->reg_push = &inst->qmgr->reg_push[id];
+	qh->reg_pop = &inst->qmgr->reg_pop[id];
+	qh->reg_peek = &inst->qmgr->reg_peek[id];
+
+	/* first opener? */
+	if (!knav_queue_is_busy(inst)) {
+		struct knav_range_info *range = inst->range;
+
+		inst->name = kstrndup(name, KNAV_NAME_SIZE, GFP_KERNEL);
+		if (range->ops && range->ops->open_queue)
+			ret = range->ops->open_queue(range, inst, flags);
+
+		if (ret) {
+			devm_kfree(inst->kdev->dev, qh);
+			return ERR_PTR(ret);
+		}
+	}
+	list_add_tail_rcu(&qh->list, &inst->handles);
+	return qh;
+}
+
+static struct knav_queue *
+knav_queue_open_by_id(const char *name, unsigned id, unsigned flags)
+{
+	struct knav_queue_inst *inst;
+	struct knav_queue *qh;
+
+	mutex_lock(&knav_dev_lock);
+
+	qh = ERR_PTR(-ENODEV);
+	inst = knav_queue_find_by_id(id);
+	if (!inst)
+		goto unlock_ret;
+
+	qh = ERR_PTR(-EEXIST);
+	if (!(flags & KNAV_QUEUE_SHARED) && knav_queue_is_busy(inst))
+		goto unlock_ret;
+
+	qh = ERR_PTR(-EBUSY);
+	if ((flags & KNAV_QUEUE_SHARED) &&
+	    (knav_queue_is_busy(inst) && !knav_queue_is_shared(inst)))
+		goto unlock_ret;
+
+	qh = __knav_queue_open(inst, name, flags);
+
+unlock_ret:
+	mutex_unlock(&knav_dev_lock);
+
+	return qh;
+}
+
+static struct knav_queue *knav_queue_open_by_type(const char *name,
+						unsigned type, unsigned flags)
+{
+	struct knav_queue_inst *inst;
+	struct knav_queue *qh = ERR_PTR(-EINVAL);
+	int idx;
+
+	mutex_lock(&knav_dev_lock);
+
+	for_each_instance(idx, inst, kdev) {
+		if (knav_queue_is_reserved(inst))
+			continue;
+		if (!knav_queue_match_type(inst, type))
+			continue;
+		if (knav_queue_is_busy(inst))
+			continue;
+		qh = __knav_queue_open(inst, name, flags);
+		goto unlock_ret;
+	}
+
+unlock_ret:
+	mutex_unlock(&knav_dev_lock);
+	return qh;
+}
+
+static void knav_queue_set_notify(struct knav_queue_inst *inst, bool enabled)
+{
+	struct knav_range_info *range = inst->range;
+
+	if (range->ops && range->ops->set_notify)
+		range->ops->set_notify(range, inst, enabled);
+}
+
+static int knav_queue_enable_notifier(struct knav_queue *qh)
+{
+	struct knav_queue_inst *inst = qh->inst;
+	bool first;
+
+	if (WARN_ON(!qh->notifier_fn))
+		return -EINVAL;
+
+	/* Adjust the per handle notifier count */
+	first = (atomic_inc_return(&qh->notifier_enabled) == 1);
+	if (!first)
+		return 0; /* nothing to do */
+
+	/* Now adjust the per instance notifier count */
+	first = (atomic_inc_return(&inst->num_notifiers) == 1);
+	if (first)
+		knav_queue_set_notify(inst, true);
+
+	return 0;
+}
+
+static int knav_queue_disable_notifier(struct knav_queue *qh)
+{
+	struct knav_queue_inst *inst = qh->inst;
+	bool last;
+
+	last = (atomic_dec_return(&qh->notifier_enabled) == 0);
+	if (!last)
+		return 0; /* nothing to do */
+
+	last = (atomic_dec_return(&inst->num_notifiers) == 0);
+	if (last)
+		knav_queue_set_notify(inst, false);
+
+	return 0;
+}
+
+static int knav_queue_set_notifier(struct knav_queue *qh,
+				struct knav_queue_notify_config *cfg)
+{
+	knav_queue_notify_fn old_fn = qh->notifier_fn;
+
+	if (!cfg)
+		return -EINVAL;
+
+	if (!(qh->inst->range->flags & (RANGE_HAS_ACCUMULATOR | RANGE_HAS_IRQ)))
+		return -ENOTSUPP;
+
+	if (!cfg->fn && old_fn)
+		knav_queue_disable_notifier(qh);
+
+	qh->notifier_fn = cfg->fn;
+	qh->notifier_fn_arg = cfg->fn_arg;
+
+	if (cfg->fn && !old_fn)
+		knav_queue_enable_notifier(qh);
+
+	return 0;
+}
+
+static int knav_gp_set_notify(struct knav_range_info *range,
+			       struct knav_queue_inst *inst,
+			       bool enabled)
+{
+	unsigned queue;
+
+	if (range->flags & RANGE_HAS_IRQ) {
+		queue = inst->id - range->queue_base;
+		if (enabled)
+			enable_irq(range->irqs[queue].irq);
+		else
+			disable_irq_nosync(range->irqs[queue].irq);
+	}
+	return 0;
+}
+
+static int knav_gp_open_queue(struct knav_range_info *range,
+				struct knav_queue_inst *inst, unsigned flags)
+{
+	return knav_queue_setup_irq(range, inst);
+}
+
+static int knav_gp_close_queue(struct knav_range_info *range,
+				struct knav_queue_inst *inst)
+{
+	knav_queue_free_irq(inst);
+	return 0;
+}
+
+struct knav_range_ops knav_gp_range_ops = {
+	.set_notify	= knav_gp_set_notify,
+	.open_queue	= knav_gp_open_queue,
+	.close_queue	= knav_gp_close_queue,
+};
+
+
+static int knav_queue_get_count(void *qhandle)
+{
+	struct knav_queue *qh = qhandle;
+	struct knav_queue_inst *inst = qh->inst;
+
+	return readl_relaxed(&qh->reg_peek[0].entry_count) +
+		atomic_read(&inst->desc_count);
+}
+
+static void knav_queue_debug_show_instance(struct seq_file *s,
+					struct knav_queue_inst *inst)
+{
+	struct knav_device *kdev = inst->kdev;
+	struct knav_queue *qh;
+
+	if (!knav_queue_is_busy(inst))
+		return;
+
+	seq_printf(s, "\tqueue id %d (%s)\n",
+		   kdev->base_id + inst->id, inst->name);
+	for_each_handle_rcu(qh, inst) {
+		seq_printf(s, "\t\thandle %p: ", qh);
+		seq_printf(s, "pushes %8d, ",
+			   atomic_read(&qh->stats.pushes));
+		seq_printf(s, "pops %8d, ",
+			   atomic_read(&qh->stats.pops));
+		seq_printf(s, "count %8d, ",
+			   knav_queue_get_count(qh));
+		seq_printf(s, "notifies %8d, ",
+			   atomic_read(&qh->stats.notifies));
+		seq_printf(s, "push errors %8d, ",
+			   atomic_read(&qh->stats.push_errors));
+		seq_printf(s, "pop errors %8d\n",
+			   atomic_read(&qh->stats.pop_errors));
+	}
+}
+
+static int knav_queue_debug_show(struct seq_file *s, void *v)
+{
+	struct knav_queue_inst *inst;
+	int idx;
+
+	mutex_lock(&knav_dev_lock);
+	seq_printf(s, "%s: %u-%u\n",
+		   dev_name(kdev->dev), kdev->base_id,
+		   kdev->base_id + kdev->num_queues - 1);
+	for_each_instance(idx, inst, kdev)
+		knav_queue_debug_show_instance(s, inst);
+	mutex_unlock(&knav_dev_lock);
+
+	return 0;
+}
+
+static int knav_queue_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, knav_queue_debug_show, NULL);
+}
+
+static const struct file_operations knav_queue_debug_ops = {
+	.open		= knav_queue_debug_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static inline int knav_queue_pdsp_wait(u32 * __iomem addr, unsigned timeout,
+					u32 flags)
+{
+	unsigned long end;
+	u32 val = 0;
+
+	end = jiffies + msecs_to_jiffies(timeout);
+	while (time_after(end, jiffies)) {
+		val = readl_relaxed(addr);
+		if (flags)
+			val &= flags;
+		if (!val)
+			break;
+		cpu_relax();
+	}
+	return val ? -ETIMEDOUT : 0;
+}
+
+
+static int knav_queue_flush(struct knav_queue *qh)
+{
+	struct knav_queue_inst *inst = qh->inst;
+	unsigned id = inst->id - inst->qmgr->start_queue;
+
+	atomic_set(&inst->desc_count, 0);
+	writel_relaxed(0, &inst->qmgr->reg_push[id].ptr_size_thresh);
+	return 0;
+}
+
+/**
+ * knav_queue_open()	- open a hardware queue
+ * @name		- name to give the queue handle
+ * @id			- desired queue number if any or specifes the type
+ *			  of queue
+ * @flags		- the following flags are applicable to queues:
+ *	KNAV_QUEUE_SHARED - allow the queue to be shared. Queues are
+ *			     exclusive by default.
+ *			     Subsequent attempts to open a shared queue should
+ *			     also have this flag.
+ *
+ * Returns a handle to the open hardware queue if successful. Use IS_ERR()
+ * to check the returned value for error codes.
+ */
+void *knav_queue_open(const char *name, unsigned id,
+					unsigned flags)
+{
+	struct knav_queue *qh = ERR_PTR(-EINVAL);
+
+	switch (id) {
+	case KNAV_QUEUE_QPEND:
+	case KNAV_QUEUE_ACC:
+	case KNAV_QUEUE_GP:
+		qh = knav_queue_open_by_type(name, id, flags);
+		break;
+
+	default:
+		qh = knav_queue_open_by_id(name, id, flags);
+		break;
+	}
+	return qh;
+}
+EXPORT_SYMBOL_GPL(knav_queue_open);
+
+/**
+ * knav_queue_close()	- close a hardware queue handle
+ * @qh			- handle to close
+ */
+void knav_queue_close(void *qhandle)
+{
+	struct knav_queue *qh = qhandle;
+	struct knav_queue_inst *inst = qh->inst;
+
+	while (atomic_read(&qh->notifier_enabled) > 0)
+		knav_queue_disable_notifier(qh);
+
+	mutex_lock(&knav_dev_lock);
+	list_del_rcu(&qh->list);
+	mutex_unlock(&knav_dev_lock);
+	synchronize_rcu();
+	if (!knav_queue_is_busy(inst)) {
+		struct knav_range_info *range = inst->range;
+
+		if (range->ops && range->ops->close_queue)
+			range->ops->close_queue(range, inst);
+	}
+	devm_kfree(inst->kdev->dev, qh);
+}
+EXPORT_SYMBOL_GPL(knav_queue_close);
+
+/**
+ * knav_queue_device_control()	- Perform control operations on a queue
+ * @qh				- queue handle
+ * @cmd				- control commands
+ * @arg				- command argument
+ *
+ * Returns 0 on success, errno otherwise.
+ */
+int knav_queue_device_control(void *qhandle, enum knav_queue_ctrl_cmd cmd,
+				unsigned long arg)
+{
+	struct knav_queue *qh = qhandle;
+	struct knav_queue_notify_config *cfg;
+	int ret;
+
+	switch ((int)cmd) {
+	case KNAV_QUEUE_GET_ID:
+		ret = qh->inst->kdev->base_id + qh->inst->id;
+		break;
+
+	case KNAV_QUEUE_FLUSH:
+		ret = knav_queue_flush(qh);
+		break;
+
+	case KNAV_QUEUE_SET_NOTIFIER:
+		cfg = (void *)arg;
+		ret = knav_queue_set_notifier(qh, cfg);
+		break;
+
+	case KNAV_QUEUE_ENABLE_NOTIFY:
+		ret = knav_queue_enable_notifier(qh);
+		break;
+
+	case KNAV_QUEUE_DISABLE_NOTIFY:
+		ret = knav_queue_disable_notifier(qh);
+		break;
+
+	case KNAV_QUEUE_GET_COUNT:
+		ret = knav_queue_get_count(qh);
+		break;
+
+	default:
+		ret = -ENOTSUPP;
+		break;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(knav_queue_device_control);
+
+
+
+/**
+ * knav_queue_push()	- push data (or descriptor) to the tail of a queue
+ * @qh			- hardware queue handle
+ * @data		- data to push
+ * @size		- size of data to push
+ * @flags		- can be used to pass additional information
+ *
+ * Returns 0 on success, errno otherwise.
+ */
+int knav_queue_push(void *qhandle, dma_addr_t dma,
+					unsigned size, unsigned flags)
+{
+	struct knav_queue *qh = qhandle;
+	u32 val;
+
+	val = (u32)dma | ((size / 16) - 1);
+	writel_relaxed(val, &qh->reg_push[0].ptr_size_thresh);
+
+	atomic_inc(&qh->stats.pushes);
+	return 0;
+}
+
+/**
+ * knav_queue_pop()	- pop data (or descriptor) from the head of a queue
+ * @qh			- hardware queue handle
+ * @size		- (optional) size of the data pop'ed.
+ *
+ * Returns a DMA address on success, 0 on failure.
+ */
+dma_addr_t knav_queue_pop(void *qhandle, unsigned *size)
+{
+	struct knav_queue *qh = qhandle;
+	struct knav_queue_inst *inst = qh->inst;
+	dma_addr_t dma;
+	u32 val, idx;
+
+	/* are we accumulated? */
+	if (inst->descs) {
+		if (unlikely(atomic_dec_return(&inst->desc_count) < 0)) {
+			atomic_inc(&inst->desc_count);
+			return 0;
+		}
+		idx  = atomic_inc_return(&inst->desc_head);
+		idx &= ACC_DESCS_MASK;
+		val = inst->descs[idx];
+	} else {
+		val = readl_relaxed(&qh->reg_pop[0].ptr_size_thresh);
+		if (unlikely(!val))
+			return 0;
+	}
+
+	dma = val & DESC_PTR_MASK;
+	if (size)
+		*size = ((val & DESC_SIZE_MASK) + 1) * 16;
+
+	atomic_inc(&qh->stats.pops);
+	return dma;
+}
+
+/* carve out descriptors and push into queue */
+static void kdesc_fill_pool(struct knav_pool *pool)
+{
+	struct knav_region *region;
+	int i;
+
+	region = pool->region;
+	pool->desc_size = region->desc_size;
+	for (i = 0; i < pool->num_desc; i++) {
+		int index = pool->region_offset + i;
+		dma_addr_t dma_addr;
+		unsigned dma_size;
+		dma_addr = region->dma_start + (region->desc_size * index);
+		dma_size = ALIGN(pool->desc_size, SMP_CACHE_BYTES);
+		dma_sync_single_for_device(pool->dev, dma_addr, dma_size,
+					   DMA_TO_DEVICE);
+		knav_queue_push(pool->queue, dma_addr, dma_size, 0);
+	}
+}
+
+/* pop out descriptors and close the queue */
+static void kdesc_empty_pool(struct knav_pool *pool)
+{
+	dma_addr_t dma;
+	unsigned size;
+	void *desc;
+	int i;
+
+	if (!pool->queue)
+		return;
+
+	for (i = 0;; i++) {
+		dma = knav_queue_pop(pool->queue, &size);
+		if (!dma)
+			break;
+		desc = knav_pool_desc_dma_to_virt(pool, dma);
+		if (!desc) {
+			dev_dbg(pool->kdev->dev,
+				"couldn't unmap desc, continuing\n");
+			continue;
+		}
+	}
+	WARN_ON(i != pool->num_desc);
+	knav_queue_close(pool->queue);
+}
+
+
+/* Get the DMA address of a descriptor */
+dma_addr_t knav_pool_desc_virt_to_dma(void *ph, void *virt)
+{
+	struct knav_pool *pool = ph;
+	return pool->region->dma_start + (virt - pool->region->virt_start);
+}
+
+void *knav_pool_desc_dma_to_virt(void *ph, dma_addr_t dma)
+{
+	struct knav_pool *pool = ph;
+	return pool->region->virt_start + (dma - pool->region->dma_start);
+}
+
+/**
+ * knav_pool_create()	- Create a pool of descriptors
+ * @name		- name to give the pool handle
+ * @num_desc		- numbers of descriptors in the pool
+ * @region_id		- QMSS region id from which the descriptors are to be
+ *			  allocated.
+ *
+ * Returns a pool handle on success.
+ * Use IS_ERR_OR_NULL() to identify error values on return.
+ */
+void *knav_pool_create(const char *name,
+					int num_desc, int region_id)
+{
+	struct knav_region *reg_itr, *region = NULL;
+	struct knav_pool *pool, *pi;
+	struct list_head *node;
+	unsigned last_offset;
+	bool slot_found;
+	int ret;
+
+	if (!kdev->dev)
+		return ERR_PTR(-ENODEV);
+
+	pool = devm_kzalloc(kdev->dev, sizeof(*pool), GFP_KERNEL);
+	if (!pool) {
+		dev_err(kdev->dev, "out of memory allocating pool\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for_each_region(kdev, reg_itr) {
+		if (reg_itr->id != region_id)
+			continue;
+		region = reg_itr;
+		break;
+	}
+
+	if (!region) {
+		dev_err(kdev->dev, "region-id(%d) not found\n", region_id);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	pool->queue = knav_queue_open(name, KNAV_QUEUE_GP, 0);
+	if (IS_ERR_OR_NULL(pool->queue)) {
+		dev_err(kdev->dev,
+			"failed to open queue for pool(%s), error %ld\n",
+			name, PTR_ERR(pool->queue));
+		ret = PTR_ERR(pool->queue);
+		goto err;
+	}
+
+	pool->name = kstrndup(name, KNAV_NAME_SIZE, GFP_KERNEL);
+	pool->kdev = kdev;
+	pool->dev = kdev->dev;
+
+	mutex_lock(&knav_dev_lock);
+
+	if (num_desc > (region->num_desc - region->used_desc)) {
+		dev_err(kdev->dev, "out of descs in region(%d) for pool(%s)\n",
+			region_id, name);
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	/* Region maintains a sorted (by region offset) list of pools
+	 * use the first free slot which is large enough to accomodate
+	 * the request
+	 */
+	last_offset = 0;
+	slot_found = false;
+	node = &region->pools;
+	list_for_each_entry(pi, &region->pools, region_inst) {
+		if ((pi->region_offset - last_offset) >= num_desc) {
+			slot_found = true;
+			break;
+		}
+		last_offset = pi->region_offset + pi->num_desc;
+	}
+	node = &pi->region_inst;
+
+	if (slot_found) {
+		pool->region = region;
+		pool->num_desc = num_desc;
+		pool->region_offset = last_offset;
+		region->used_desc += num_desc;
+		list_add_tail(&pool->list, &kdev->pools);
+		list_add_tail(&pool->region_inst, node);
+	} else {
+		dev_err(kdev->dev, "pool(%s) create failed: fragmented desc pool in region(%d)\n",
+			name, region_id);
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	mutex_unlock(&knav_dev_lock);
+	kdesc_fill_pool(pool);
+	return pool;
+
+err:
+	mutex_unlock(&knav_dev_lock);
+	kfree(pool->name);
+	devm_kfree(kdev->dev, pool);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(knav_pool_create);
+
+/**
+ * knav_pool_destroy()	- Free a pool of descriptors
+ * @pool		- pool handle
+ */
+void knav_pool_destroy(void *ph)
+{
+	struct knav_pool *pool = ph;
+
+	if (!pool)
+		return;
+
+	if (!pool->region)
+		return;
+
+	kdesc_empty_pool(pool);
+	mutex_lock(&knav_dev_lock);
+
+	pool->region->used_desc -= pool->num_desc;
+	list_del(&pool->region_inst);
+	list_del(&pool->list);
+
+	mutex_unlock(&knav_dev_lock);
+	kfree(pool->name);
+	devm_kfree(kdev->dev, pool);
+}
+EXPORT_SYMBOL_GPL(knav_pool_destroy);
+
+
+/**
+ * knav_pool_desc_get()	- Get a descriptor from the pool
+ * @pool			- pool handle
+ *
+ * Returns descriptor from the pool.
+ */
+void *knav_pool_desc_get(void *ph)
+{
+	struct knav_pool *pool = ph;
+	dma_addr_t dma;
+	unsigned size;
+	void *data;
+
+	dma = knav_queue_pop(pool->queue, &size);
+	if (unlikely(!dma))
+		return ERR_PTR(-ENOMEM);
+	data = knav_pool_desc_dma_to_virt(pool, dma);
+	return data;
+}
+
+/**
+ * knav_pool_desc_put()	- return a descriptor to the pool
+ * @pool			- pool handle
+ */
+void knav_pool_desc_put(void *ph, void *desc)
+{
+	struct knav_pool *pool = ph;
+	dma_addr_t dma;
+	dma = knav_pool_desc_virt_to_dma(pool, desc);
+	knav_queue_push(pool->queue, dma, pool->region->desc_size, 0);
+}
+
+/**
+ * knav_pool_desc_map()	- Map descriptor for DMA transfer
+ * @pool			- pool handle
+ * @desc			- address of descriptor to map
+ * @size			- size of descriptor to map
+ * @dma				- DMA address return pointer
+ * @dma_sz			- adjusted return pointer
+ *
+ * Returns 0 on success, errno otherwise.
+ */
+int knav_pool_desc_map(void *ph, void *desc, unsigned size,
+					dma_addr_t *dma, unsigned *dma_sz)
+{
+	struct knav_pool *pool = ph;
+	*dma = knav_pool_desc_virt_to_dma(pool, desc);
+	size = min(size, pool->region->desc_size);
+	size = ALIGN(size, SMP_CACHE_BYTES);
+	*dma_sz = size;
+	dma_sync_single_for_device(pool->dev, *dma, size, DMA_TO_DEVICE);
+
+	/* Ensure the descriptor reaches to the memory */
+	__iowmb();
+
+	return 0;
+}
+
+/**
+ * knav_pool_desc_unmap()	- Unmap descriptor after DMA transfer
+ * @pool			- pool handle
+ * @dma				- DMA address of descriptor to unmap
+ * @dma_sz			- size of descriptor to unmap
+ *
+ * Returns descriptor address on success, Use IS_ERR_OR_NULL() to identify
+ * error values on return.
+ */
+void *knav_pool_desc_unmap(void *ph, dma_addr_t dma, unsigned dma_sz)
+{
+	struct knav_pool *pool = ph;
+	unsigned desc_sz;
+	void *desc;
+
+	desc_sz = min(dma_sz, pool->region->desc_size);
+	desc = knav_pool_desc_dma_to_virt(pool, dma);
+	dma_sync_single_for_cpu(pool->dev, dma, desc_sz, DMA_FROM_DEVICE);
+	prefetch(desc);
+	return desc;
+}
+
+/**
+ * knav_pool_count()	- Get the number of descriptors in pool.
+ * @pool		- pool handle
+ * Returns number of elements in the pool.
+ */
+int knav_pool_count(void *ph)
+{
+	struct knav_pool *pool = ph;
+	return knav_queue_get_count(pool->queue);
+}
+
+static void knav_queue_setup_region(struct knav_device *kdev,
+					struct knav_region *region)
+{
+	unsigned hw_num_desc, hw_desc_size, size;
+	struct knav_reg_region __iomem  *regs;
+	struct knav_qmgr_info *qmgr;
+	struct knav_pool *pool;
+	int id = region->id;
+	struct page *page;
+
+	/* unused region? */
+	if (!region->num_desc) {
+		dev_warn(kdev->dev, "unused region %s\n", region->name);
+		return;
+	}
+
+	/* get hardware descriptor value */
+	hw_num_desc = ilog2(region->num_desc - 1) + 1;
+
+	/* did we force fit ourselves into nothingness? */
+	if (region->num_desc < 32) {
+		region->num_desc = 0;
+		dev_warn(kdev->dev, "too few descriptors in region %s\n",
+			 region->name);
+		return;
+	}
+
+	size = region->num_desc * region->desc_size;
+	region->virt_start = alloc_pages_exact(size, GFP_KERNEL | GFP_DMA |
+						GFP_DMA32);
+	if (!region->virt_start) {
+		region->num_desc = 0;
+		dev_err(kdev->dev, "memory alloc failed for region %s\n",
+			region->name);
+		return;
+	}
+	region->virt_end = region->virt_start + size;
+	page = virt_to_page(region->virt_start);
+
+	region->dma_start = dma_map_page(kdev->dev, page, 0, size,
+					 DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(kdev->dev, region->dma_start)) {
+		dev_err(kdev->dev, "dma map failed for region %s\n",
+			region->name);
+		goto fail;
+	}
+	region->dma_end = region->dma_start + size;
+
+	pool = devm_kzalloc(kdev->dev, sizeof(*pool), GFP_KERNEL);
+	if (!pool) {
+		dev_err(kdev->dev, "out of memory allocating dummy pool\n");
+		goto fail;
+	}
+	pool->num_desc = 0;
+	pool->region_offset = region->num_desc;
+	list_add(&pool->region_inst, &region->pools);
+
+	dev_dbg(kdev->dev,
+		"region %s (%d): size:%d, link:%d@%d, phys:%08x-%08x, virt:%p-%p\n",
+		region->name, id, region->desc_size, region->num_desc,
+		region->link_index, region->dma_start, region->dma_end,
+		region->virt_start, region->virt_end);
+
+	hw_desc_size = (region->desc_size / 16) - 1;
+	hw_num_desc -= 5;
+
+	for_each_qmgr(kdev, qmgr) {
+		regs = qmgr->reg_region + id;
+		writel_relaxed(region->dma_start, &regs->base);
+		writel_relaxed(region->link_index, &regs->start_index);
+		writel_relaxed(hw_desc_size << 16 | hw_num_desc,
+			       &regs->size_count);
+	}
+	return;
+
+fail:
+	if (region->dma_start)
+		dma_unmap_page(kdev->dev, region->dma_start, size,
+				DMA_BIDIRECTIONAL);
+	if (region->virt_start)
+		free_pages_exact(region->virt_start, size);
+	region->num_desc = 0;
+	return;
+}
+
+static const char *knav_queue_find_name(struct device_node *node)
+{
+	const char *name;
+
+	if (of_property_read_string(node, "label", &name) < 0)
+		name = node->name;
+	if (!name)
+		name = "unknown";
+	return name;
+}
+
+static int knav_queue_setup_regions(struct knav_device *kdev,
+					struct device_node *regions)
+{
+	struct device *dev = kdev->dev;
+	struct knav_region *region;
+	struct device_node *child;
+	u32 temp[2];
+	int ret;
+
+	for_each_child_of_node(regions, child) {
+		region = devm_kzalloc(dev, sizeof(*region), GFP_KERNEL);
+		if (!region) {
+			dev_err(dev, "out of memory allocating region\n");
+			return -ENOMEM;
+		}
+
+		region->name = knav_queue_find_name(child);
+		of_property_read_u32(child, "id", &region->id);
+		ret = of_property_read_u32_array(child, "region-spec", temp, 2);
+		if (!ret) {
+			region->num_desc  = temp[0];
+			region->desc_size = temp[1];
+		} else {
+			dev_err(dev, "invalid region info %s\n", region->name);
+			devm_kfree(dev, region);
+			continue;
+		}
+
+		if (!of_get_property(child, "link-index", NULL)) {
+			dev_err(dev, "No link info for %s\n", region->name);
+			devm_kfree(dev, region);
+			continue;
+		}
+		ret = of_property_read_u32(child, "link-index",
+					   &region->link_index);
+		if (ret) {
+			dev_err(dev, "link index not found for %s\n",
+				region->name);
+			devm_kfree(dev, region);
+			continue;
+		}
+
+		INIT_LIST_HEAD(&region->pools);
+		list_add_tail(&region->list, &kdev->regions);
+	}
+	if (list_empty(&kdev->regions)) {
+		dev_err(dev, "no valid region information found\n");
+		return -ENODEV;
+	}
+
+	/* Next, we run through the regions and set things up */
+	for_each_region(kdev, region)
+		knav_queue_setup_region(kdev, region);
+
+	return 0;
+}
+
+static int knav_get_link_ram(struct knav_device *kdev,
+				       const char *name,
+				       struct knav_link_ram_block *block)
+{
+	struct platform_device *pdev = to_platform_device(kdev->dev);
+	struct device_node *node = pdev->dev.of_node;
+	u32 temp[2];
+
+	/*
+	 * Note: link ram resources are specified in "entry" sized units. In
+	 * reality, although entries are ~40bits in hardware, we treat them as
+	 * 64-bit entities here.
+	 *
+	 * For example, to specify the internal link ram for Keystone-I class
+	 * devices, we would set the linkram0 resource to 0x80000-0x83fff.
+	 *
+	 * This gets a bit weird when other link rams are used.  For example,
+	 * if the range specified is 0x0c000000-0x0c003fff (i.e., 16K entries
+	 * in MSMC SRAM), the actual memory used is 0x0c000000-0x0c020000,
+	 * which accounts for 64-bits per entry, for 16K entries.
+	 */
+	if (!of_property_read_u32_array(node, name , temp, 2)) {
+		if (temp[0]) {
+			/*
+			 * queue_base specified => using internal or onchip
+			 * link ram WARNING - we do not "reserve" this block
+			 */
+			block->phys = (dma_addr_t)temp[0];
+			block->virt = NULL;
+			block->size = temp[1];
+		} else {
+			block->size = temp[1];
+			/* queue_base not specific => allocate requested size */
+			block->virt = dmam_alloc_coherent(kdev->dev,
+						  8 * block->size, &block->phys,
+						  GFP_KERNEL);
+			if (!block->virt) {
+				dev_err(kdev->dev, "failed to alloc linkram\n");
+				return -ENOMEM;
+			}
+		}
+	} else {
+		return -ENODEV;
+	}
+	return 0;
+}
+
+static int knav_queue_setup_link_ram(struct knav_device *kdev)
+{
+	struct knav_link_ram_block *block;
+	struct knav_qmgr_info *qmgr;
+
+	for_each_qmgr(kdev, qmgr) {
+		block = &kdev->link_rams[0];
+		dev_dbg(kdev->dev, "linkram0: phys:%x, virt:%p, size:%x\n",
+			block->phys, block->virt, block->size);
+		writel_relaxed(block->phys, &qmgr->reg_config->link_ram_base0);
+		writel_relaxed(block->size, &qmgr->reg_config->link_ram_size0);
+
+		block++;
+		if (!block->size)
+			return 0;
+
+		dev_dbg(kdev->dev, "linkram1: phys:%x, virt:%p, size:%x\n",
+			block->phys, block->virt, block->size);
+		writel_relaxed(block->phys, &qmgr->reg_config->link_ram_base1);
+	}
+
+	return 0;
+}
+
+static int knav_setup_queue_range(struct knav_device *kdev,
+					struct device_node *node)
+{
+	struct device *dev = kdev->dev;
+	struct knav_range_info *range;
+	struct knav_qmgr_info *qmgr;
+	u32 temp[2], start, end, id, index;
+	int ret, i;
+
+	range = devm_kzalloc(dev, sizeof(*range), GFP_KERNEL);
+	if (!range) {
+		dev_err(dev, "out of memory allocating range\n");
+		return -ENOMEM;
+	}
+
+	range->kdev = kdev;
+	range->name = knav_queue_find_name(node);
+	ret = of_property_read_u32_array(node, "qrange", temp, 2);
+	if (!ret) {
+		range->queue_base = temp[0] - kdev->base_id;
+		range->num_queues = temp[1];
+	} else {
+		dev_err(dev, "invalid queue range %s\n", range->name);
+		devm_kfree(dev, range);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < RANGE_MAX_IRQS; i++) {
+		struct of_phandle_args oirq;
+
+		if (of_irq_parse_one(node, i, &oirq))
+			break;
+
+		range->irqs[i].irq = irq_create_of_mapping(&oirq);
+		if (range->irqs[i].irq == IRQ_NONE)
+			break;
+
+		range->num_irqs++;
+
+		if (oirq.args_count == 3)
+			range->irqs[i].cpu_map =
+				(oirq.args[2] & 0x0000ff00) >> 8;
+	}
+
+	range->num_irqs = min(range->num_irqs, range->num_queues);
+	if (range->num_irqs)
+		range->flags |= RANGE_HAS_IRQ;
+
+	if (of_get_property(node, "qalloc-by-id", NULL))
+		range->flags |= RANGE_RESERVED;
+
+	if (of_get_property(node, "accumulator", NULL)) {
+		ret = knav_init_acc_range(kdev, node, range);
+		if (ret < 0) {
+			devm_kfree(dev, range);
+			return ret;
+		}
+	} else {
+		range->ops = &knav_gp_range_ops;
+	}
+
+	/* set threshold to 1, and flush out the queues */
+	for_each_qmgr(kdev, qmgr) {
+		start = max(qmgr->start_queue, range->queue_base);
+		end   = min(qmgr->start_queue + qmgr->num_queues,
+			    range->queue_base + range->num_queues);
+		for (id = start; id < end; id++) {
+			index = id - qmgr->start_queue;
+			writel_relaxed(THRESH_GTE | 1,
+				       &qmgr->reg_peek[index].ptr_size_thresh);
+			writel_relaxed(0,
+				       &qmgr->reg_push[index].ptr_size_thresh);
+		}
+	}
+
+	list_add_tail(&range->list, &kdev->queue_ranges);
+	dev_dbg(dev, "added range %s: %d-%d, %d irqs%s%s%s\n",
+		range->name, range->queue_base,
+		range->queue_base + range->num_queues - 1,
+		range->num_irqs,
+		(range->flags & RANGE_HAS_IRQ) ? ", has irq" : "",
+		(range->flags & RANGE_RESERVED) ? ", reserved" : "",
+		(range->flags & RANGE_HAS_ACCUMULATOR) ? ", acc" : "");
+	kdev->num_queues_in_use += range->num_queues;
+	return 0;
+}
+
+static int knav_setup_queue_pools(struct knav_device *kdev,
+				   struct device_node *queue_pools)
+{
+	struct device_node *type, *range;
+	int ret;
+
+	for_each_child_of_node(queue_pools, type) {
+		for_each_child_of_node(type, range) {
+			ret = knav_setup_queue_range(kdev, range);
+			/* return value ignored, we init the rest... */
+		}
+	}
+
+	/* ... and barf if they all failed! */
+	if (list_empty(&kdev->queue_ranges)) {
+		dev_err(kdev->dev, "no valid queue range found\n");
+		return -ENODEV;
+	}
+	return 0;
+}
+
+static void knav_free_queue_range(struct knav_device *kdev,
+				  struct knav_range_info *range)
+{
+	if (range->ops && range->ops->free_range)
+		range->ops->free_range(range);
+	list_del(&range->list);
+	devm_kfree(kdev->dev, range);
+}
+
+static void knav_free_queue_ranges(struct knav_device *kdev)
+{
+	struct knav_range_info *range;
+
+	for (;;) {
+		range = first_queue_range(kdev);
+		if (!range)
+			break;
+		knav_free_queue_range(kdev, range);
+	}
+}
+
+static void knav_queue_free_regions(struct knav_device *kdev)
+{
+	struct knav_region *region;
+	struct knav_pool *pool;
+	unsigned size;
+
+	for (;;) {
+		region = first_region(kdev);
+		if (!region)
+			break;
+		list_for_each_entry(pool, &region->pools, region_inst)
+			knav_pool_destroy(pool);
+
+		size = region->virt_end - region->virt_start;
+		if (size)
+			free_pages_exact(region->virt_start, size);
+		list_del(&region->list);
+		devm_kfree(kdev->dev, region);
+	}
+}
+
+static void __iomem *knav_queue_map_reg(struct knav_device *kdev,
+					struct device_node *node, int index)
+{
+	struct resource res;
+	void __iomem *regs;
+	int ret;
+
+	ret = of_address_to_resource(node, index, &res);
+	if (ret) {
+		dev_err(kdev->dev, "Can't translate of node(%s) address for index(%d)\n",
+			node->name, index);
+		return ERR_PTR(ret);
+	}
+
+	regs = devm_ioremap_resource(kdev->dev, &res);
+	if (IS_ERR(regs))
+		dev_err(kdev->dev, "Failed to map register base for index(%d) node(%s)\n",
+			index, node->name);
+	return regs;
+}
+
+static int knav_queue_init_qmgrs(struct knav_device *kdev,
+					struct device_node *qmgrs)
+{
+	struct device *dev = kdev->dev;
+	struct knav_qmgr_info *qmgr;
+	struct device_node *child;
+	u32 temp[2];
+	int ret;
+
+	for_each_child_of_node(qmgrs, child) {
+		qmgr = devm_kzalloc(dev, sizeof(*qmgr), GFP_KERNEL);
+		if (!qmgr) {
+			dev_err(dev, "out of memory allocating qmgr\n");
+			return -ENOMEM;
+		}
+
+		ret = of_property_read_u32_array(child, "managed-queues",
+						 temp, 2);
+		if (!ret) {
+			qmgr->start_queue = temp[0];
+			qmgr->num_queues = temp[1];
+		} else {
+			dev_err(dev, "invalid qmgr queue range\n");
+			devm_kfree(dev, qmgr);
+			continue;
+		}
+
+		dev_info(dev, "qmgr start queue %d, number of queues %d\n",
+			 qmgr->start_queue, qmgr->num_queues);
+
+		qmgr->reg_peek =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_PEEK_REG_INDEX);
+		qmgr->reg_status =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_STATUS_REG_INDEX);
+		qmgr->reg_config =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_CONFIG_REG_INDEX);
+		qmgr->reg_region =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_REGION_REG_INDEX);
+		qmgr->reg_push =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_PUSH_REG_INDEX);
+		qmgr->reg_pop =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_POP_REG_INDEX);
+
+		if (IS_ERR(qmgr->reg_peek) || IS_ERR(qmgr->reg_status) ||
+		    IS_ERR(qmgr->reg_config) || IS_ERR(qmgr->reg_region) ||
+		    IS_ERR(qmgr->reg_push) || IS_ERR(qmgr->reg_pop)) {
+			dev_err(dev, "failed to map qmgr regs\n");
+			if (!IS_ERR(qmgr->reg_peek))
+				devm_iounmap(dev, qmgr->reg_peek);
+			if (!IS_ERR(qmgr->reg_status))
+				devm_iounmap(dev, qmgr->reg_status);
+			if (!IS_ERR(qmgr->reg_config))
+				devm_iounmap(dev, qmgr->reg_config);
+			if (!IS_ERR(qmgr->reg_region))
+				devm_iounmap(dev, qmgr->reg_region);
+			if (!IS_ERR(qmgr->reg_push))
+				devm_iounmap(dev, qmgr->reg_push);
+			if (!IS_ERR(qmgr->reg_pop))
+				devm_iounmap(dev, qmgr->reg_pop);
+			devm_kfree(dev, qmgr);
+			continue;
+		}
+
+		list_add_tail(&qmgr->list, &kdev->qmgrs);
+		dev_info(dev, "added qmgr start queue %d, num of queues %d, reg_peek %p, reg_status %p, reg_config %p, reg_region %p, reg_push %p, reg_pop %p\n",
+			 qmgr->start_queue, qmgr->num_queues,
+			 qmgr->reg_peek, qmgr->reg_status,
+			 qmgr->reg_config, qmgr->reg_region,
+			 qmgr->reg_push, qmgr->reg_pop);
+	}
+	return 0;
+}
+
+static int knav_queue_init_pdsps(struct knav_device *kdev,
+					struct device_node *pdsps)
+{
+	struct device *dev = kdev->dev;
+	struct knav_pdsp_info *pdsp;
+	struct device_node *child;
+	int ret;
+
+	for_each_child_of_node(pdsps, child) {
+		pdsp = devm_kzalloc(dev, sizeof(*pdsp), GFP_KERNEL);
+		if (!pdsp) {
+			dev_err(dev, "out of memory allocating pdsp\n");
+			return -ENOMEM;
+		}
+		pdsp->name = knav_queue_find_name(child);
+		ret = of_property_read_string(child, "firmware",
+					      &pdsp->firmware);
+		if (ret < 0 || !pdsp->firmware) {
+			dev_err(dev, "unknown firmware for pdsp %s\n",
+				pdsp->name);
+			devm_kfree(dev, pdsp);
+			continue;
+		}
+		dev_dbg(dev, "pdsp name %s fw name :%s\n", pdsp->name,
+			pdsp->firmware);
+
+		pdsp->iram =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_PDSP_IRAM_REG_INDEX);
+		pdsp->regs =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_PDSP_REGS_REG_INDEX);
+		pdsp->intd =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_PDSP_INTD_REG_INDEX);
+		pdsp->command =
+			knav_queue_map_reg(kdev, child,
+					   KNAV_QUEUE_PDSP_CMD_REG_INDEX);
+
+		if (IS_ERR(pdsp->command) || IS_ERR(pdsp->iram) ||
+		    IS_ERR(pdsp->regs) || IS_ERR(pdsp->intd)) {
+			dev_err(dev, "failed to map pdsp %s regs\n",
+				pdsp->name);
+			if (!IS_ERR(pdsp->command))
+				devm_iounmap(dev, pdsp->command);
+			if (!IS_ERR(pdsp->iram))
+				devm_iounmap(dev, pdsp->iram);
+			if (!IS_ERR(pdsp->regs))
+				devm_iounmap(dev, pdsp->regs);
+			if (!IS_ERR(pdsp->intd))
+				devm_iounmap(dev, pdsp->intd);
+			devm_kfree(dev, pdsp);
+			continue;
+		}
+		of_property_read_u32(child, "id", &pdsp->id);
+		list_add_tail(&pdsp->list, &kdev->pdsps);
+		dev_dbg(dev, "added pdsp %s: command %p, iram %p, regs %p, intd %p, firmware %s\n",
+			pdsp->name, pdsp->command, pdsp->iram, pdsp->regs,
+			pdsp->intd, pdsp->firmware);
+	}
+	return 0;
+}
+
+static int knav_queue_stop_pdsp(struct knav_device *kdev,
+			  struct knav_pdsp_info *pdsp)
+{
+	u32 val, timeout = 1000;
+	int ret;
+
+	val = readl_relaxed(&pdsp->regs->control) & ~PDSP_CTRL_ENABLE;
+	writel_relaxed(val, &pdsp->regs->control);
+	ret = knav_queue_pdsp_wait(&pdsp->regs->control, timeout,
+					PDSP_CTRL_RUNNING);
+	if (ret < 0) {
+		dev_err(kdev->dev, "timed out on pdsp %s stop\n", pdsp->name);
+		return ret;
+	}
+	return 0;
+}
+
+static int knav_queue_load_pdsp(struct knav_device *kdev,
+			  struct knav_pdsp_info *pdsp)
+{
+	int i, ret, fwlen;
+	const struct firmware *fw;
+	u32 *fwdata;
+
+	ret = request_firmware(&fw, pdsp->firmware, kdev->dev);
+	if (ret) {
+		dev_err(kdev->dev, "failed to get firmware %s for pdsp %s\n",
+			pdsp->firmware, pdsp->name);
+		return ret;
+	}
+	writel_relaxed(pdsp->id + 1, pdsp->command + 0x18);
+	/* download the firmware */
+	fwdata = (u32 *)fw->data;
+	fwlen = (fw->size + sizeof(u32) - 1) / sizeof(u32);
+	for (i = 0; i < fwlen; i++)
+		writel_relaxed(be32_to_cpu(fwdata[i]), pdsp->iram + i);
+
+	release_firmware(fw);
+	return 0;
+}
+
+static int knav_queue_start_pdsp(struct knav_device *kdev,
+			   struct knav_pdsp_info *pdsp)
+{
+	u32 val, timeout = 1000;
+	int ret;
+
+	/* write a command for sync */
+	writel_relaxed(0xffffffff, pdsp->command);
+	while (readl_relaxed(pdsp->command) != 0xffffffff)
+		cpu_relax();
+
+	/* soft reset the PDSP */
+	val  = readl_relaxed(&pdsp->regs->control);
+	val &= ~(PDSP_CTRL_PC_MASK | PDSP_CTRL_SOFT_RESET);
+	writel_relaxed(val, &pdsp->regs->control);
+
+	/* enable pdsp */
+	val = readl_relaxed(&pdsp->regs->control) | PDSP_CTRL_ENABLE;
+	writel_relaxed(val, &pdsp->regs->control);
+
+	/* wait for command register to clear */
+	ret = knav_queue_pdsp_wait(pdsp->command, timeout, 0);
+	if (ret < 0) {
+		dev_err(kdev->dev,
+			"timed out on pdsp %s command register wait\n",
+			pdsp->name);
+		return ret;
+	}
+	return 0;
+}
+
+static void knav_queue_stop_pdsps(struct knav_device *kdev)
+{
+	struct knav_pdsp_info *pdsp;
+
+	/* disable all pdsps */
+	for_each_pdsp(kdev, pdsp)
+		knav_queue_stop_pdsp(kdev, pdsp);
+}
+
+static int knav_queue_start_pdsps(struct knav_device *kdev)
+{
+	struct knav_pdsp_info *pdsp;
+	int ret;
+
+	knav_queue_stop_pdsps(kdev);
+	/* now load them all */
+	for_each_pdsp(kdev, pdsp) {
+		ret = knav_queue_load_pdsp(kdev, pdsp);
+		if (ret < 0)
+			return ret;
+	}
+
+	for_each_pdsp(kdev, pdsp) {
+		ret = knav_queue_start_pdsp(kdev, pdsp);
+		WARN_ON(ret);
+	}
+	return 0;
+}
+
+static inline struct knav_qmgr_info *knav_find_qmgr(unsigned id)
+{
+	struct knav_qmgr_info *qmgr;
+
+	for_each_qmgr(kdev, qmgr) {
+		if ((id >= qmgr->start_queue) &&
+		    (id < qmgr->start_queue + qmgr->num_queues))
+			return qmgr;
+	}
+	return NULL;
+}
+
+static int knav_queue_init_queue(struct knav_device *kdev,
+					struct knav_range_info *range,
+					struct knav_queue_inst *inst,
+					unsigned id)
+{
+	char irq_name[KNAV_NAME_SIZE];
+	inst->qmgr = knav_find_qmgr(id);
+	if (!inst->qmgr)
+		return -1;
+
+	INIT_LIST_HEAD(&inst->handles);
+	inst->kdev = kdev;
+	inst->range = range;
+	inst->irq_num = -1;
+	inst->id = id;
+	scnprintf(irq_name, sizeof(irq_name), "hwqueue-%d", id);
+	inst->irq_name = kstrndup(irq_name, sizeof(irq_name), GFP_KERNEL);
+
+	if (range->ops && range->ops->init_queue)
+		return range->ops->init_queue(range, inst);
+	else
+		return 0;
+}
+
+static int knav_queue_init_queues(struct knav_device *kdev)
+{
+	struct knav_range_info *range;
+	int size, id, base_idx;
+	int idx = 0, ret = 0;
+
+	/* how much do we need for instance data? */
+	size = sizeof(struct knav_queue_inst);
+
+	/* round this up to a power of 2, keep the index to instance
+	 * arithmetic fast.
+	 * */
+	kdev->inst_shift = order_base_2(size);
+	size = (1 << kdev->inst_shift) * kdev->num_queues_in_use;
+	kdev->instances = devm_kzalloc(kdev->dev, size, GFP_KERNEL);
+	if (!kdev->instances)
+		return -1;
+
+	for_each_queue_range(kdev, range) {
+		if (range->ops && range->ops->init_range)
+			range->ops->init_range(range);
+		base_idx = idx;
+		for (id = range->queue_base;
+		     id < range->queue_base + range->num_queues; id++, idx++) {
+			ret = knav_queue_init_queue(kdev, range,
+					knav_queue_idx_to_inst(kdev, idx), id);
+			if (ret < 0)
+				return ret;
+		}
+		range->queue_base_inst =
+			knav_queue_idx_to_inst(kdev, base_idx);
+	}
+	return 0;
+}
+
+static int knav_queue_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct device_node *qmgrs, *queue_pools, *regions, *pdsps;
+	struct device *dev = &pdev->dev;
+	u32 temp[2];
+	int ret;
+
+	if (!node) {
+		dev_err(dev, "device tree info unavailable\n");
+		return -ENODEV;
+	}
+
+	kdev = devm_kzalloc(dev, sizeof(struct knav_device), GFP_KERNEL);
+	if (!kdev) {
+		dev_err(dev, "memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	platform_set_drvdata(pdev, kdev);
+	kdev->dev = dev;
+	INIT_LIST_HEAD(&kdev->queue_ranges);
+	INIT_LIST_HEAD(&kdev->qmgrs);
+	INIT_LIST_HEAD(&kdev->pools);
+	INIT_LIST_HEAD(&kdev->regions);
+	INIT_LIST_HEAD(&kdev->pdsps);
+
+	pm_runtime_enable(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_err(dev, "Failed to enable QMSS\n");
+		return ret;
+	}
+
+	if (of_property_read_u32_array(node, "queue-range", temp, 2)) {
+		dev_err(dev, "queue-range not specified\n");
+		ret = -ENODEV;
+		goto err;
+	}
+	kdev->base_id    = temp[0];
+	kdev->num_queues = temp[1];
+
+	/* Initialize queue managers using device tree configuration */
+	qmgrs =  of_get_child_by_name(node, "qmgrs");
+	if (!qmgrs) {
+		dev_err(dev, "queue manager info not specified\n");
+		ret = -ENODEV;
+		goto err;
+	}
+	ret = knav_queue_init_qmgrs(kdev, qmgrs);
+	of_node_put(qmgrs);
+	if (ret)
+		goto err;
+
+	/* get pdsp configuration values from device tree */
+	pdsps =  of_get_child_by_name(node, "pdsps");
+	if (pdsps) {
+		ret = knav_queue_init_pdsps(kdev, pdsps);
+		if (ret)
+			goto err;
+
+		ret = knav_queue_start_pdsps(kdev);
+		if (ret)
+			goto err;
+	}
+	of_node_put(pdsps);
+
+	/* get usable queue range values from device tree */
+	queue_pools = of_get_child_by_name(node, "queue-pools");
+	if (!queue_pools) {
+		dev_err(dev, "queue-pools not specified\n");
+		ret = -ENODEV;
+		goto err;
+	}
+	ret = knav_setup_queue_pools(kdev, queue_pools);
+	of_node_put(queue_pools);
+	if (ret)
+		goto err;
+
+	ret = knav_get_link_ram(kdev, "linkram0", &kdev->link_rams[0]);
+	if (ret) {
+		dev_err(kdev->dev, "could not setup linking ram\n");
+		goto err;
+	}
+
+	ret = knav_get_link_ram(kdev, "linkram1", &kdev->link_rams[1]);
+	if (ret) {
+		/*
+		 * nothing really, we have one linking ram already, so we just
+		 * live within our means
+		 */
+	}
+
+	ret = knav_queue_setup_link_ram(kdev);
+	if (ret)
+		goto err;
+
+	regions =  of_get_child_by_name(node, "descriptor-regions");
+	if (!regions) {
+		dev_err(dev, "descriptor-regions not specified\n");
+		goto err;
+	}
+	ret = knav_queue_setup_regions(kdev, regions);
+	of_node_put(regions);
+	if (ret)
+		goto err;
+
+	ret = knav_queue_init_queues(kdev);
+	if (ret < 0) {
+		dev_err(dev, "hwqueue initialization failed\n");
+		goto err;
+	}
+
+	debugfs_create_file("qmss", S_IFREG | S_IRUGO, NULL, NULL,
+			    &knav_queue_debug_ops);
+	return 0;
+
+err:
+	knav_queue_stop_pdsps(kdev);
+	knav_queue_free_regions(kdev);
+	knav_free_queue_ranges(kdev);
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+	return ret;
+}
+
+static int knav_queue_remove(struct platform_device *pdev)
+{
+	/* TODO: Free resources */
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+	return 0;
+}
+
+/* Match table for of_platform binding */
+static struct of_device_id keystone_qmss_of_match[] = {
+	{ .compatible = "ti,keystone-navigator-qmss", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, keystone_qmss_of_match);
+
+static struct platform_driver keystone_qmss_driver = {
+	.probe		= knav_queue_probe,
+	.remove		= knav_queue_remove,
+	.driver		= {
+		.name	= "keystone-navigator-qmss",
+		.owner	= THIS_MODULE,
+		.of_match_table = keystone_qmss_of_match,
+	},
+};
+module_platform_driver(keystone_qmss_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("TI QMSS driver for Keystone SOCs");
+MODULE_AUTHOR("Sandeep Nair <sandeep_n@ti.com>");
+MODULE_AUTHOR("Santosh Shilimkar <santosh.shilimkar@ti.com>");
diff --git a/include/linux/soc/ti/knav_qmss.h b/include/linux/soc/ti/knav_qmss.h
new file mode 100644
index 000000000000..9f0ebb3bad27
--- /dev/null
+++ b/include/linux/soc/ti/knav_qmss.h
@@ -0,0 +1,90 @@
+/*
+ * Keystone Navigator Queue Management Sub-System header
+ *
+ * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Author:	Sandeep Nair <sandeep_n@ti.com>
+ *		Cyril Chemparathy <cyril@ti.com>
+ *		Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __SOC_TI_KNAV_QMSS_H__
+#define __SOC_TI_KNAV_QMSS_H__
+
+#include <linux/err.h>
+#include <linux/time.h>
+#include <linux/atomic.h>
+#include <linux/device.h>
+#include <linux/fcntl.h>
+#include <linux/dma-mapping.h>
+
+/* queue types */
+#define KNAV_QUEUE_QPEND	((unsigned)-2) /* interruptible qpend queue */
+#define KNAV_QUEUE_ACC		((unsigned)-3) /* Accumulated queue */
+#define KNAV_QUEUE_GP		((unsigned)-4) /* General purpose queue */
+
+/* queue flags */
+#define KNAV_QUEUE_SHARED	0x0001		/* Queue can be shared */
+
+/**
+ * enum knav_queue_ctrl_cmd -	queue operations.
+ * @KNAV_QUEUE_GET_ID:		Get the ID number for an open queue
+ * @KNAV_QUEUE_FLUSH:		forcibly empty a queue if possible
+ * @KNAV_QUEUE_SET_NOTIFIER:	Set a notifier callback to a queue handle.
+ * @KNAV_QUEUE_ENABLE_NOTIFY:	Enable notifier callback for a queue handle.
+ * @KNAV_QUEUE_DISABLE_NOTIFY:	Disable notifier callback for a queue handle.
+ * @KNAV_QUEUE_GET_COUNT:	Get number of queues.
+ */
+enum knav_queue_ctrl_cmd {
+	KNAV_QUEUE_GET_ID,
+	KNAV_QUEUE_FLUSH,
+	KNAV_QUEUE_SET_NOTIFIER,
+	KNAV_QUEUE_ENABLE_NOTIFY,
+	KNAV_QUEUE_DISABLE_NOTIFY,
+	KNAV_QUEUE_GET_COUNT
+};
+
+/* Queue notifier callback prototype */
+typedef void (*knav_queue_notify_fn)(void *arg);
+
+/**
+ * struct knav_queue_notify_config:	Notifier configuration
+ * @fn:					Notifier function
+ * @fn_arg:				Notifier function arguments
+ */
+struct knav_queue_notify_config {
+	knav_queue_notify_fn fn;
+	void *fn_arg;
+};
+
+void *knav_queue_open(const char *name, unsigned id,
+					unsigned flags);
+void knav_queue_close(void *qhandle);
+int knav_queue_device_control(void *qhandle,
+				enum knav_queue_ctrl_cmd cmd,
+				unsigned long arg);
+dma_addr_t knav_queue_pop(void *qhandle, unsigned *size);
+int knav_queue_push(void *qhandle, dma_addr_t dma,
+				unsigned size, unsigned flags);
+
+void *knav_pool_create(const char *name,
+				int num_desc, int region_id);
+void knav_pool_destroy(void *ph);
+int knav_pool_count(void *ph);
+void *knav_pool_desc_get(void *ph);
+void knav_pool_desc_put(void *ph, void *desc);
+int knav_pool_desc_map(void *ph, void *desc, unsigned size,
+					dma_addr_t *dma, unsigned *dma_sz);
+void *knav_pool_desc_unmap(void *ph, dma_addr_t dma, unsigned dma_sz);
+dma_addr_t knav_pool_desc_virt_to_dma(void *ph, void *virt);
+void *knav_pool_desc_dma_to_virt(void *ph, dma_addr_t dma);
+
+#endif /* __SOC_TI_KNAV_QMSS_H__ */
-- 
cgit v1.2.3


From 88139ed030583557751e279968e13e892ae10825 Mon Sep 17 00:00:00 2001
From: Santosh Shilimkar <santosh.shilimkar@ti.com>
Date: Sun, 30 Mar 2014 17:29:04 -0400
Subject: soc: ti: add Keystone Navigator DMA support

The Keystone Navigator DMA driver sets up the dma channels and flows for
the QMSS(Queue Manager SubSystem) who triggers the actual data movements
across clients using destination queues. Every client modules like
NETCP(Network Coprocessor), SRIO(Serial Rapid IO) and CRYPTO
Engines has its own instance of packet dma hardware. QMSS has also
an internal packet DMA module which is used as an infrastructure
DMA with zero copy.

Initially this driver was proposed as DMA engine driver but since the
hardware is not typical DMA engine and hence doesn't comply with typical
DMA engine driver needs, that approach was naked. Link to that
discussion -
	https://lkml.org/lkml/2014/3/18/340

As aligned, now we pair the Navigator DMA with its companion Navigator
QMSS subsystem driver.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Kumar Gala <galak@codeaurora.org>
Cc: Olof Johansson <olof@lixom.net>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Sandeep Nair <sandeep_n@ti.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
---
 drivers/soc/ti/Kconfig          |  10 +
 drivers/soc/ti/Makefile         |   1 +
 drivers/soc/ti/knav_dma.c       | 815 ++++++++++++++++++++++++++++++++++++++++
 include/linux/soc/ti/knav_dma.h | 175 +++++++++
 4 files changed, 1001 insertions(+)
 create mode 100644 drivers/soc/ti/knav_dma.c
 create mode 100644 include/linux/soc/ti/knav_dma.h

(limited to 'include')

diff --git a/drivers/soc/ti/Kconfig b/drivers/soc/ti/Kconfig
index f73896f762e8..7266b2165183 100644
--- a/drivers/soc/ti/Kconfig
+++ b/drivers/soc/ti/Kconfig
@@ -18,4 +18,14 @@ config KEYSTONE_NAVIGATOR_QMSS
 
 	  If unsure, say N.
 
+config KEYSTONE_NAVIGATOR_DMA
+	tristate "TI Keystone Navigator Packet DMA support"
+	depends on ARCH_KEYSTONE
+	help
+	  Say y tp enable support for the Keystone Navigator Packet DMA on
+	  on Keystone family of devices. It sets up the dma channels for the
+	  Queue Manager Sub System.
+
+	  If unsure, say N.
+
 endif # SOC_TI
diff --git a/drivers/soc/ti/Makefile b/drivers/soc/ti/Makefile
index bf85cacd5b85..6bed611e1934 100644
--- a/drivers/soc/ti/Makefile
+++ b/drivers/soc/ti/Makefile
@@ -2,3 +2,4 @@
 # TI Keystone SOC drivers
 #
 obj-$(CONFIG_KEYSTONE_NAVIGATOR_QMSS)	+= knav_qmss_queue.o knav_qmss_acc.o
+obj-$(CONFIG_KEYSTONE_NAVIGATOR_DMA)	+= knav_dma.o
diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c
new file mode 100644
index 000000000000..17264275f32b
--- /dev/null
+++ b/drivers/soc/ti/knav_dma.c
@@ -0,0 +1,815 @@
+/*
+ * Copyright (C) 2014 Texas Instruments Incorporated
+ * Authors:	Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *		Sandeep Nair <sandeep_n@ti.com>
+ *		Cyril Chemparathy <cyril@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/io.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/dma-direction.h>
+#include <linux/interrupt.h>
+#include <linux/pm_runtime.h>
+#include <linux/of_dma.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/soc/ti/knav_dma.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#define REG_MASK		0xffffffff
+
+#define DMA_LOOPBACK		BIT(31)
+#define DMA_ENABLE		BIT(31)
+#define DMA_TEARDOWN		BIT(30)
+
+#define DMA_TX_FILT_PSWORDS	BIT(29)
+#define DMA_TX_FILT_EINFO	BIT(30)
+#define DMA_TX_PRIO_SHIFT	0
+#define DMA_RX_PRIO_SHIFT	16
+#define DMA_PRIO_MASK		GENMASK(3, 0)
+#define DMA_PRIO_DEFAULT	0
+#define DMA_RX_TIMEOUT_DEFAULT	17500 /* cycles */
+#define DMA_RX_TIMEOUT_MASK	GENMASK(16, 0)
+#define DMA_RX_TIMEOUT_SHIFT	0
+
+#define CHAN_HAS_EPIB		BIT(30)
+#define CHAN_HAS_PSINFO		BIT(29)
+#define CHAN_ERR_RETRY		BIT(28)
+#define CHAN_PSINFO_AT_SOP	BIT(25)
+#define CHAN_SOP_OFF_SHIFT	16
+#define CHAN_SOP_OFF_MASK	GENMASK(9, 0)
+#define DESC_TYPE_SHIFT		26
+#define DESC_TYPE_MASK		GENMASK(2, 0)
+
+/*
+ * QMGR & QNUM together make up 14 bits with QMGR as the 2 MSb's in the logical
+ * navigator cloud mapping scheme.
+ * using the 14bit physical queue numbers directly maps into this scheme.
+ */
+#define CHAN_QNUM_MASK		GENMASK(14, 0)
+#define DMA_MAX_QMS		4
+#define DMA_TIMEOUT		1	/* msecs */
+#define DMA_INVALID_ID		0xffff
+
+struct reg_global {
+	u32	revision;
+	u32	perf_control;
+	u32	emulation_control;
+	u32	priority_control;
+	u32	qm_base_address[DMA_MAX_QMS];
+};
+
+struct reg_chan {
+	u32	control;
+	u32	mode;
+	u32	__rsvd[6];
+};
+
+struct reg_tx_sched {
+	u32	prio;
+};
+
+struct reg_rx_flow {
+	u32	control;
+	u32	tags;
+	u32	tag_sel;
+	u32	fdq_sel[2];
+	u32	thresh[3];
+};
+
+struct knav_dma_pool_device {
+	struct device			*dev;
+	struct list_head		list;
+};
+
+struct knav_dma_device {
+	bool				loopback, enable_all;
+	unsigned			tx_priority, rx_priority, rx_timeout;
+	unsigned			logical_queue_managers;
+	unsigned			qm_base_address[DMA_MAX_QMS];
+	struct reg_global __iomem	*reg_global;
+	struct reg_chan __iomem		*reg_tx_chan;
+	struct reg_rx_flow __iomem	*reg_rx_flow;
+	struct reg_chan __iomem		*reg_rx_chan;
+	struct reg_tx_sched __iomem	*reg_tx_sched;
+	unsigned			max_rx_chan, max_tx_chan;
+	unsigned			max_rx_flow;
+	char				name[32];
+	atomic_t			ref_count;
+	struct list_head		list;
+	struct list_head		chan_list;
+	spinlock_t			lock;
+};
+
+struct knav_dma_chan {
+	enum dma_transfer_direction	direction;
+	struct knav_dma_device		*dma;
+	atomic_t			ref_count;
+
+	/* registers */
+	struct reg_chan __iomem		*reg_chan;
+	struct reg_tx_sched __iomem	*reg_tx_sched;
+	struct reg_rx_flow __iomem	*reg_rx_flow;
+
+	/* configuration stuff */
+	unsigned			channel, flow;
+	struct knav_dma_cfg		cfg;
+	struct list_head		list;
+	spinlock_t			lock;
+};
+
+#define chan_number(ch)	((ch->direction == DMA_MEM_TO_DEV) ? \
+			ch->channel : ch->flow)
+
+static struct knav_dma_pool_device *kdev;
+
+static bool check_config(struct knav_dma_chan *chan, struct knav_dma_cfg *cfg)
+{
+	if (!memcmp(&chan->cfg, cfg, sizeof(*cfg)))
+		return true;
+	else
+		return false;
+}
+
+static int chan_start(struct knav_dma_chan *chan,
+			struct knav_dma_cfg *cfg)
+{
+	u32 v = 0;
+
+	spin_lock(&chan->lock);
+	if ((chan->direction == DMA_MEM_TO_DEV) && chan->reg_chan) {
+		if (cfg->u.tx.filt_pswords)
+			v |= DMA_TX_FILT_PSWORDS;
+		if (cfg->u.tx.filt_einfo)
+			v |= DMA_TX_FILT_EINFO;
+		writel_relaxed(v, &chan->reg_chan->mode);
+		writel_relaxed(DMA_ENABLE, &chan->reg_chan->control);
+	}
+
+	if (chan->reg_tx_sched)
+		writel_relaxed(cfg->u.tx.priority, &chan->reg_tx_sched->prio);
+
+	if (chan->reg_rx_flow) {
+		v = 0;
+
+		if (cfg->u.rx.einfo_present)
+			v |= CHAN_HAS_EPIB;
+		if (cfg->u.rx.psinfo_present)
+			v |= CHAN_HAS_PSINFO;
+		if (cfg->u.rx.err_mode == DMA_RETRY)
+			v |= CHAN_ERR_RETRY;
+		v |= (cfg->u.rx.desc_type & DESC_TYPE_MASK) << DESC_TYPE_SHIFT;
+		if (cfg->u.rx.psinfo_at_sop)
+			v |= CHAN_PSINFO_AT_SOP;
+		v |= (cfg->u.rx.sop_offset & CHAN_SOP_OFF_MASK)
+			<< CHAN_SOP_OFF_SHIFT;
+		v |= cfg->u.rx.dst_q & CHAN_QNUM_MASK;
+
+		writel_relaxed(v, &chan->reg_rx_flow->control);
+		writel_relaxed(0, &chan->reg_rx_flow->tags);
+		writel_relaxed(0, &chan->reg_rx_flow->tag_sel);
+
+		v =  cfg->u.rx.fdq[0] << 16;
+		v |=  cfg->u.rx.fdq[1] & CHAN_QNUM_MASK;
+		writel_relaxed(v, &chan->reg_rx_flow->fdq_sel[0]);
+
+		v =  cfg->u.rx.fdq[2] << 16;
+		v |=  cfg->u.rx.fdq[3] & CHAN_QNUM_MASK;
+		writel_relaxed(v, &chan->reg_rx_flow->fdq_sel[1]);
+
+		writel_relaxed(0, &chan->reg_rx_flow->thresh[0]);
+		writel_relaxed(0, &chan->reg_rx_flow->thresh[1]);
+		writel_relaxed(0, &chan->reg_rx_flow->thresh[2]);
+	}
+
+	/* Keep a copy of the cfg */
+	memcpy(&chan->cfg, cfg, sizeof(*cfg));
+	spin_unlock(&chan->lock);
+
+	return 0;
+}
+
+static int chan_teardown(struct knav_dma_chan *chan)
+{
+	unsigned long end, value;
+
+	if (!chan->reg_chan)
+		return 0;
+
+	/* indicate teardown */
+	writel_relaxed(DMA_TEARDOWN, &chan->reg_chan->control);
+
+	/* wait for the dma to shut itself down */
+	end = jiffies + msecs_to_jiffies(DMA_TIMEOUT);
+	do {
+		value = readl_relaxed(&chan->reg_chan->control);
+		if ((value & DMA_ENABLE) == 0)
+			break;
+	} while (time_after(end, jiffies));
+
+	if (readl_relaxed(&chan->reg_chan->control) & DMA_ENABLE) {
+		dev_err(kdev->dev, "timeout waiting for teardown\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static void chan_stop(struct knav_dma_chan *chan)
+{
+	spin_lock(&chan->lock);
+	if (chan->reg_rx_flow) {
+		/* first detach fdqs, starve out the flow */
+		writel_relaxed(0, &chan->reg_rx_flow->fdq_sel[0]);
+		writel_relaxed(0, &chan->reg_rx_flow->fdq_sel[1]);
+		writel_relaxed(0, &chan->reg_rx_flow->thresh[0]);
+		writel_relaxed(0, &chan->reg_rx_flow->thresh[1]);
+		writel_relaxed(0, &chan->reg_rx_flow->thresh[2]);
+	}
+
+	/* teardown the dma channel */
+	chan_teardown(chan);
+
+	/* then disconnect the completion side */
+	if (chan->reg_rx_flow) {
+		writel_relaxed(0, &chan->reg_rx_flow->control);
+		writel_relaxed(0, &chan->reg_rx_flow->tags);
+		writel_relaxed(0, &chan->reg_rx_flow->tag_sel);
+	}
+
+	memset(&chan->cfg, 0, sizeof(struct knav_dma_cfg));
+	spin_unlock(&chan->lock);
+
+	dev_dbg(kdev->dev, "channel stopped\n");
+}
+
+static void dma_hw_enable_all(struct knav_dma_device *dma)
+{
+	int i;
+
+	for (i = 0; i < dma->max_tx_chan; i++) {
+		writel_relaxed(0, &dma->reg_tx_chan[i].mode);
+		writel_relaxed(DMA_ENABLE, &dma->reg_tx_chan[i].control);
+	}
+}
+
+
+static void knav_dma_hw_init(struct knav_dma_device *dma)
+{
+	unsigned v;
+	int i;
+
+	spin_lock(&dma->lock);
+	v  = dma->loopback ? DMA_LOOPBACK : 0;
+	writel_relaxed(v, &dma->reg_global->emulation_control);
+
+	v = readl_relaxed(&dma->reg_global->perf_control);
+	v |= ((dma->rx_timeout & DMA_RX_TIMEOUT_MASK) << DMA_RX_TIMEOUT_SHIFT);
+	writel_relaxed(v, &dma->reg_global->perf_control);
+
+	v = ((dma->tx_priority << DMA_TX_PRIO_SHIFT) |
+	     (dma->rx_priority << DMA_RX_PRIO_SHIFT));
+
+	writel_relaxed(v, &dma->reg_global->priority_control);
+
+	/* Always enable all Rx channels. Rx paths are managed using flows */
+	for (i = 0; i < dma->max_rx_chan; i++)
+		writel_relaxed(DMA_ENABLE, &dma->reg_rx_chan[i].control);
+
+	for (i = 0; i < dma->logical_queue_managers; i++)
+		writel_relaxed(dma->qm_base_address[i],
+			       &dma->reg_global->qm_base_address[i]);
+	spin_unlock(&dma->lock);
+}
+
+static void knav_dma_hw_destroy(struct knav_dma_device *dma)
+{
+	int i;
+	unsigned v;
+
+	spin_lock(&dma->lock);
+	v = ~DMA_ENABLE & REG_MASK;
+
+	for (i = 0; i < dma->max_rx_chan; i++)
+		writel_relaxed(v, &dma->reg_rx_chan[i].control);
+
+	for (i = 0; i < dma->max_tx_chan; i++)
+		writel_relaxed(v, &dma->reg_tx_chan[i].control);
+	spin_unlock(&dma->lock);
+}
+
+static void dma_debug_show_channels(struct seq_file *s,
+					struct knav_dma_chan *chan)
+{
+	int i;
+
+	seq_printf(s, "\t%s %d:\t",
+		((chan->direction == DMA_MEM_TO_DEV) ? "tx chan" : "rx flow"),
+		chan_number(chan));
+
+	if (chan->direction == DMA_MEM_TO_DEV) {
+		seq_printf(s, "einfo - %d, pswords - %d, priority - %d\n",
+			chan->cfg.u.tx.filt_einfo,
+			chan->cfg.u.tx.filt_pswords,
+			chan->cfg.u.tx.priority);
+	} else {
+		seq_printf(s, "einfo - %d, psinfo - %d, desc_type - %d\n",
+			chan->cfg.u.rx.einfo_present,
+			chan->cfg.u.rx.psinfo_present,
+			chan->cfg.u.rx.desc_type);
+		seq_printf(s, "\t\t\tdst_q: [%d], thresh: %d fdq: ",
+			chan->cfg.u.rx.dst_q,
+			chan->cfg.u.rx.thresh);
+		for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN; i++)
+			seq_printf(s, "[%d]", chan->cfg.u.rx.fdq[i]);
+		seq_printf(s, "\n");
+	}
+}
+
+static void dma_debug_show_devices(struct seq_file *s,
+					struct knav_dma_device *dma)
+{
+	struct knav_dma_chan *chan;
+
+	list_for_each_entry(chan, &dma->chan_list, list) {
+		if (atomic_read(&chan->ref_count))
+			dma_debug_show_channels(s, chan);
+	}
+}
+
+static int dma_debug_show(struct seq_file *s, void *v)
+{
+	struct knav_dma_device *dma;
+
+	list_for_each_entry(dma, &kdev->list, list) {
+		if (atomic_read(&dma->ref_count)) {
+			seq_printf(s, "%s : max_tx_chan: (%d), max_rx_flows: (%d)\n",
+			dma->name, dma->max_tx_chan, dma->max_rx_flow);
+			dma_debug_show_devices(s, dma);
+		}
+	}
+
+	return 0;
+}
+
+static int knav_dma_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, dma_debug_show, NULL);
+}
+
+static const struct file_operations knav_dma_debug_ops = {
+	.open		= knav_dma_debug_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int of_channel_match_helper(struct device_node *np, const char *name,
+					const char **dma_instance)
+{
+	struct of_phandle_args args;
+	struct device_node *dma_node;
+	int index;
+
+	dma_node = of_parse_phandle(np, "ti,navigator-dmas", 0);
+	if (!dma_node)
+		return -ENODEV;
+
+	*dma_instance = dma_node->name;
+	index = of_property_match_string(np, "ti,navigator-dma-names", name);
+	if (index < 0) {
+		dev_err(kdev->dev, "No 'ti,navigator-dma-names' propery\n");
+		return -ENODEV;
+	}
+
+	if (of_parse_phandle_with_fixed_args(np, "ti,navigator-dmas",
+					1, index, &args)) {
+		dev_err(kdev->dev, "Missing the pahndle args name %s\n", name);
+		return -ENODEV;
+	}
+
+	if (args.args[0] < 0) {
+		dev_err(kdev->dev, "Missing args for %s\n", name);
+		return -ENODEV;
+	}
+
+	return args.args[0];
+}
+
+/**
+ * knav_dma_open_channel() - try to setup an exclusive slave channel
+ * @dev:	pointer to client device structure
+ * @name:	slave channel name
+ * @config:	dma configuration parameters
+ *
+ * Returns pointer to appropriate DMA channel on success or NULL.
+ */
+void *knav_dma_open_channel(struct device *dev, const char *name,
+					struct knav_dma_cfg *config)
+{
+	struct knav_dma_chan *chan;
+	struct knav_dma_device *dma;
+	bool found = false;
+	int chan_num = -1;
+	const char *instance;
+
+	if (!kdev) {
+		pr_err("keystone-navigator-dma driver not registered\n");
+		return (void *)-EINVAL;
+	}
+
+	chan_num = of_channel_match_helper(dev->of_node, name, &instance);
+	if (chan_num < 0) {
+		dev_err(kdev->dev, "No DMA instace with name %s\n", name);
+		return (void *)-EINVAL;
+	}
+
+	dev_dbg(kdev->dev, "initializing %s channel %d from DMA %s\n",
+		  config->direction == DMA_MEM_TO_DEV   ? "transmit" :
+		  config->direction == DMA_DEV_TO_MEM ? "receive"  :
+		  "unknown", chan_num, instance);
+
+	if (config->direction != DMA_MEM_TO_DEV &&
+	    config->direction != DMA_DEV_TO_MEM) {
+		dev_err(kdev->dev, "bad direction\n");
+		return (void *)-EINVAL;
+	}
+
+	/* Look for correct dma instance */
+	list_for_each_entry(dma, &kdev->list, list) {
+		if (!strcmp(dma->name, instance)) {
+			found = true;
+			break;
+		}
+	}
+	if (!found) {
+		dev_err(kdev->dev, "No DMA instace with name %s\n", instance);
+		return (void *)-EINVAL;
+	}
+
+	/* Look for correct dma channel from dma instance */
+	found = false;
+	list_for_each_entry(chan, &dma->chan_list, list) {
+		if (config->direction == DMA_MEM_TO_DEV) {
+			if (chan->channel == chan_num) {
+				found = true;
+				break;
+			}
+		} else {
+			if (chan->flow == chan_num) {
+				found = true;
+				break;
+			}
+		}
+	}
+	if (!found) {
+		dev_err(kdev->dev, "channel %d is not in DMA %s\n",
+				chan_num, instance);
+		return (void *)-EINVAL;
+	}
+
+	if (atomic_read(&chan->ref_count) >= 1) {
+		if (!check_config(chan, config)) {
+			dev_err(kdev->dev, "channel %d config miss-match\n",
+				chan_num);
+			return (void *)-EINVAL;
+		}
+	}
+
+	if (atomic_inc_return(&chan->dma->ref_count) <= 1)
+		knav_dma_hw_init(chan->dma);
+
+	if (atomic_inc_return(&chan->ref_count) <= 1)
+		chan_start(chan, config);
+
+	dev_dbg(kdev->dev, "channel %d opened from DMA %s\n",
+				chan_num, instance);
+
+	return chan;
+}
+EXPORT_SYMBOL_GPL(knav_dma_open_channel);
+
+/**
+ * knav_dma_close_channel()	- Destroy a dma channel
+ *
+ * channel:	dma channel handle
+ *
+ */
+void knav_dma_close_channel(void *channel)
+{
+	struct knav_dma_chan *chan = channel;
+
+	if (!kdev) {
+		pr_err("keystone-navigator-dma driver not registered\n");
+		return;
+	}
+
+	if (atomic_dec_return(&chan->ref_count) <= 0)
+		chan_stop(chan);
+
+	if (atomic_dec_return(&chan->dma->ref_count) <= 0)
+		knav_dma_hw_destroy(chan->dma);
+
+	dev_dbg(kdev->dev, "channel %d or flow %d closed from DMA %s\n",
+			chan->channel, chan->flow, chan->dma->name);
+}
+EXPORT_SYMBOL_GPL(knav_dma_close_channel);
+
+static void __iomem *pktdma_get_regs(struct knav_dma_device *dma,
+				struct device_node *node,
+				unsigned index, resource_size_t *_size)
+{
+	struct device *dev = kdev->dev;
+	struct resource res;
+	void __iomem *regs;
+	int ret;
+
+	ret = of_address_to_resource(node, index, &res);
+	if (ret) {
+		dev_err(dev, "Can't translate of node(%s) address for index(%d)\n",
+			node->name, index);
+		return ERR_PTR(ret);
+	}
+
+	regs = devm_ioremap_resource(kdev->dev, &res);
+	if (IS_ERR(regs))
+		dev_err(dev, "Failed to map register base for index(%d) node(%s)\n",
+			index, node->name);
+	if (_size)
+		*_size = resource_size(&res);
+
+	return regs;
+}
+
+static int pktdma_init_rx_chan(struct knav_dma_chan *chan, u32 flow)
+{
+	struct knav_dma_device *dma = chan->dma;
+
+	chan->flow = flow;
+	chan->reg_rx_flow = dma->reg_rx_flow + flow;
+	chan->channel = DMA_INVALID_ID;
+	dev_dbg(kdev->dev, "rx flow(%d) (%p)\n", chan->flow, chan->reg_rx_flow);
+
+	return 0;
+}
+
+static int pktdma_init_tx_chan(struct knav_dma_chan *chan, u32 channel)
+{
+	struct knav_dma_device *dma = chan->dma;
+
+	chan->channel = channel;
+	chan->reg_chan = dma->reg_tx_chan + channel;
+	chan->reg_tx_sched = dma->reg_tx_sched + channel;
+	chan->flow = DMA_INVALID_ID;
+	dev_dbg(kdev->dev, "tx channel(%d) (%p)\n", chan->channel, chan->reg_chan);
+
+	return 0;
+}
+
+static int pktdma_init_chan(struct knav_dma_device *dma,
+				enum dma_transfer_direction dir,
+				unsigned chan_num)
+{
+	struct device *dev = kdev->dev;
+	struct knav_dma_chan *chan;
+	int ret = -EINVAL;
+
+	chan = devm_kzalloc(dev, sizeof(*chan), GFP_KERNEL);
+	if (!chan)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&chan->list);
+	chan->dma	= dma;
+	chan->direction	= DMA_NONE;
+	atomic_set(&chan->ref_count, 0);
+	spin_lock_init(&chan->lock);
+
+	if (dir == DMA_MEM_TO_DEV) {
+		chan->direction = dir;
+		ret = pktdma_init_tx_chan(chan, chan_num);
+	} else if (dir == DMA_DEV_TO_MEM) {
+		chan->direction = dir;
+		ret = pktdma_init_rx_chan(chan, chan_num);
+	} else {
+		dev_err(dev, "channel(%d) direction unknown\n", chan_num);
+	}
+
+	list_add_tail(&chan->list, &dma->chan_list);
+
+	return ret;
+}
+
+static int dma_init(struct device_node *cloud, struct device_node *dma_node)
+{
+	unsigned max_tx_chan, max_rx_chan, max_rx_flow, max_tx_sched;
+	struct device_node *node = dma_node;
+	struct knav_dma_device *dma;
+	int ret, len, num_chan = 0;
+	resource_size_t size;
+	u32 timeout;
+	u32 i;
+
+	dma = devm_kzalloc(kdev->dev, sizeof(*dma), GFP_KERNEL);
+	if (!dma) {
+		dev_err(kdev->dev, "could not allocate driver mem\n");
+		return -ENOMEM;
+	}
+	INIT_LIST_HEAD(&dma->list);
+	INIT_LIST_HEAD(&dma->chan_list);
+
+	if (!of_find_property(cloud, "ti,navigator-cloud-address", &len)) {
+		dev_err(kdev->dev, "unspecified navigator cloud addresses\n");
+		return -ENODEV;
+	}
+
+	dma->logical_queue_managers = len / sizeof(u32);
+	if (dma->logical_queue_managers > DMA_MAX_QMS) {
+		dev_warn(kdev->dev, "too many queue mgrs(>%d) rest ignored\n",
+			 dma->logical_queue_managers);
+		dma->logical_queue_managers = DMA_MAX_QMS;
+	}
+
+	ret = of_property_read_u32_array(cloud, "ti,navigator-cloud-address",
+					dma->qm_base_address,
+					dma->logical_queue_managers);
+	if (ret) {
+		dev_err(kdev->dev, "invalid navigator cloud addresses\n");
+		return -ENODEV;
+	}
+
+	dma->reg_global	 = pktdma_get_regs(dma, node, 0, &size);
+	if (!dma->reg_global)
+		return -ENODEV;
+	if (size < sizeof(struct reg_global)) {
+		dev_err(kdev->dev, "bad size %pa for global regs\n", &size);
+		return -ENODEV;
+	}
+
+	dma->reg_tx_chan = pktdma_get_regs(dma, node, 1, &size);
+	if (!dma->reg_tx_chan)
+		return -ENODEV;
+
+	max_tx_chan = size / sizeof(struct reg_chan);
+	dma->reg_rx_chan = pktdma_get_regs(dma, node, 2, &size);
+	if (!dma->reg_rx_chan)
+		return -ENODEV;
+
+	max_rx_chan = size / sizeof(struct reg_chan);
+	dma->reg_tx_sched = pktdma_get_regs(dma, node, 3, &size);
+	if (!dma->reg_tx_sched)
+		return -ENODEV;
+
+	max_tx_sched = size / sizeof(struct reg_tx_sched);
+	dma->reg_rx_flow = pktdma_get_regs(dma, node, 4, &size);
+	if (!dma->reg_rx_flow)
+		return -ENODEV;
+
+	max_rx_flow = size / sizeof(struct reg_rx_flow);
+	dma->rx_priority = DMA_PRIO_DEFAULT;
+	dma->tx_priority = DMA_PRIO_DEFAULT;
+
+	dma->enable_all	= (of_get_property(node, "ti,enable-all", NULL) != NULL);
+	dma->loopback	= (of_get_property(node, "ti,loop-back",  NULL) != NULL);
+
+	ret = of_property_read_u32(node, "ti,rx-retry-timeout", &timeout);
+	if (ret < 0) {
+		dev_dbg(kdev->dev, "unspecified rx timeout using value %d\n",
+			DMA_RX_TIMEOUT_DEFAULT);
+		timeout = DMA_RX_TIMEOUT_DEFAULT;
+	}
+
+	dma->rx_timeout = timeout;
+	dma->max_rx_chan = max_rx_chan;
+	dma->max_rx_flow = max_rx_flow;
+	dma->max_tx_chan = min(max_tx_chan, max_tx_sched);
+	atomic_set(&dma->ref_count, 0);
+	strcpy(dma->name, node->name);
+	spin_lock_init(&dma->lock);
+
+	for (i = 0; i < dma->max_tx_chan; i++) {
+		if (pktdma_init_chan(dma, DMA_MEM_TO_DEV, i) >= 0)
+			num_chan++;
+	}
+
+	for (i = 0; i < dma->max_rx_flow; i++) {
+		if (pktdma_init_chan(dma, DMA_DEV_TO_MEM, i) >= 0)
+			num_chan++;
+	}
+
+	list_add_tail(&dma->list, &kdev->list);
+
+	/*
+	 * For DSP software usecases or userpace transport software, setup all
+	 * the DMA hardware resources.
+	 */
+	if (dma->enable_all) {
+		atomic_inc(&dma->ref_count);
+		knav_dma_hw_init(dma);
+		dma_hw_enable_all(dma);
+	}
+
+	dev_info(kdev->dev, "DMA %s registered %d logical channels, flows %d, tx chans: %d, rx chans: %d%s\n",
+		dma->name, num_chan, dma->max_rx_flow,
+		dma->max_tx_chan, dma->max_rx_chan,
+		dma->loopback ? ", loopback" : "");
+
+	return 0;
+}
+
+static int knav_dma_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *node = pdev->dev.of_node;
+	struct device_node *child;
+	int ret = 0;
+
+	if (!node) {
+		dev_err(&pdev->dev, "could not find device info\n");
+		return -EINVAL;
+	}
+
+	kdev = devm_kzalloc(dev,
+			sizeof(struct knav_dma_pool_device), GFP_KERNEL);
+	if (!kdev) {
+		dev_err(dev, "could not allocate driver mem\n");
+		return -ENOMEM;
+	}
+
+	kdev->dev = dev;
+	INIT_LIST_HEAD(&kdev->list);
+
+	pm_runtime_enable(kdev->dev);
+	ret = pm_runtime_get_sync(kdev->dev);
+	if (ret < 0) {
+		dev_err(kdev->dev, "unable to enable pktdma, err %d\n", ret);
+		return ret;
+	}
+
+	/* Initialise all packet dmas */
+	for_each_child_of_node(node, child) {
+		ret = dma_init(node, child);
+		if (ret) {
+			dev_err(&pdev->dev, "init failed with %d\n", ret);
+			break;
+		}
+	}
+
+	if (list_empty(&kdev->list)) {
+		dev_err(dev, "no valid dma instance\n");
+		return -ENODEV;
+	}
+
+	debugfs_create_file("knav_dma", S_IFREG | S_IRUGO, NULL, NULL,
+			    &knav_dma_debug_ops);
+
+	return ret;
+}
+
+static int knav_dma_remove(struct platform_device *pdev)
+{
+	struct knav_dma_device *dma;
+
+	list_for_each_entry(dma, &kdev->list, list) {
+		if (atomic_dec_return(&dma->ref_count) == 0)
+			knav_dma_hw_destroy(dma);
+	}
+
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static struct of_device_id of_match[] = {
+	{ .compatible = "ti,keystone-navigator-dma", },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, of_match);
+
+static struct platform_driver knav_dma_driver = {
+	.probe	= knav_dma_probe,
+	.remove	= knav_dma_remove,
+	.driver = {
+		.name		= "keystone-navigator-dma",
+		.owner		= THIS_MODULE,
+		.of_match_table	= of_match,
+	},
+};
+module_platform_driver(knav_dma_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("TI Keystone Navigator Packet DMA driver");
+MODULE_AUTHOR("Sandeep Nair <sandeep_n@ti.com>");
+MODULE_AUTHOR("Santosh Shilimkar <santosh.shilimkar@ti.com>");
diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h
new file mode 100644
index 000000000000..e864a3eb9ac4
--- /dev/null
+++ b/include/linux/soc/ti/knav_dma.h
@@ -0,0 +1,175 @@
+/*
+ * Copyright (C) 2014 Texas Instruments Incorporated
+ * Authors:	Sandeep Nair <sandeep_n@ti.com
+ *		Cyril Chemparathy <cyril@ti.com
+		Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__
+#define __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__
+
+/*
+ * PKTDMA descriptor manipulation macros for host packet descriptor
+ */
+#define MASK(x)					(BIT(x) - 1)
+#define KNAV_DMA_DESC_PKT_LEN_MASK		MASK(22)
+#define KNAV_DMA_DESC_PKT_LEN_SHIFT		0
+#define KNAV_DMA_DESC_PS_INFO_IN_SOP		BIT(22)
+#define KNAV_DMA_DESC_PS_INFO_IN_DESC		0
+#define KNAV_DMA_DESC_TAG_MASK			MASK(8)
+#define KNAV_DMA_DESC_SAG_HI_SHIFT		24
+#define KNAV_DMA_DESC_STAG_LO_SHIFT		16
+#define KNAV_DMA_DESC_DTAG_HI_SHIFT		8
+#define KNAV_DMA_DESC_DTAG_LO_SHIFT		0
+#define KNAV_DMA_DESC_HAS_EPIB			BIT(31)
+#define KNAV_DMA_DESC_NO_EPIB			0
+#define KNAV_DMA_DESC_PSLEN_SHIFT		24
+#define KNAV_DMA_DESC_PSLEN_MASK		MASK(6)
+#define KNAV_DMA_DESC_ERR_FLAG_SHIFT		20
+#define KNAV_DMA_DESC_ERR_FLAG_MASK		MASK(4)
+#define KNAV_DMA_DESC_PSFLAG_SHIFT		16
+#define KNAV_DMA_DESC_PSFLAG_MASK		MASK(4)
+#define KNAV_DMA_DESC_RETQ_SHIFT		0
+#define KNAV_DMA_DESC_RETQ_MASK			MASK(14)
+#define KNAV_DMA_DESC_BUF_LEN_MASK		MASK(22)
+
+#define KNAV_DMA_NUM_EPIB_WORDS			4
+#define KNAV_DMA_NUM_PS_WORDS			16
+#define KNAV_DMA_FDQ_PER_CHAN			4
+
+/* Tx channel scheduling priority */
+enum knav_dma_tx_priority {
+	DMA_PRIO_HIGH	= 0,
+	DMA_PRIO_MED_H,
+	DMA_PRIO_MED_L,
+	DMA_PRIO_LOW
+};
+
+/* Rx channel error handling mode during buffer starvation */
+enum knav_dma_rx_err_mode {
+	DMA_DROP = 0,
+	DMA_RETRY
+};
+
+/* Rx flow size threshold configuration */
+enum knav_dma_rx_thresholds {
+	DMA_THRESH_NONE		= 0,
+	DMA_THRESH_0		= 1,
+	DMA_THRESH_0_1		= 3,
+	DMA_THRESH_0_1_2	= 7
+};
+
+/* Descriptor type */
+enum knav_dma_desc_type {
+	DMA_DESC_HOST = 0,
+	DMA_DESC_MONOLITHIC = 2
+};
+
+/**
+ * struct knav_dma_tx_cfg:	Tx channel configuration
+ * @filt_einfo:			Filter extended packet info
+ * @filt_pswords:		Filter PS words present
+ * @knav_dma_tx_priority:	Tx channel scheduling priority
+ */
+struct knav_dma_tx_cfg {
+	bool				filt_einfo;
+	bool				filt_pswords;
+	enum knav_dma_tx_priority	priority;
+};
+
+/**
+ * struct knav_dma_rx_cfg:	Rx flow configuration
+ * @einfo_present:		Extended packet info present
+ * @psinfo_present:		PS words present
+ * @knav_dma_rx_err_mode:	Error during buffer starvation
+ * @knav_dma_desc_type:	Host or Monolithic desc
+ * @psinfo_at_sop:		PS word located at start of packet
+ * @sop_offset:			Start of packet offset
+ * @dst_q:			Destination queue for a given flow
+ * @thresh:			Rx flow size threshold
+ * @fdq[]:			Free desc Queue array
+ * @sz_thresh0:			RX packet size threshold 0
+ * @sz_thresh1:			RX packet size threshold 1
+ * @sz_thresh2:			RX packet size threshold 2
+ */
+struct knav_dma_rx_cfg {
+	bool				einfo_present;
+	bool				psinfo_present;
+	enum knav_dma_rx_err_mode	err_mode;
+	enum knav_dma_desc_type		desc_type;
+	bool				psinfo_at_sop;
+	unsigned int			sop_offset;
+	unsigned int			dst_q;
+	enum knav_dma_rx_thresholds	thresh;
+	unsigned int			fdq[KNAV_DMA_FDQ_PER_CHAN];
+	unsigned int			sz_thresh0;
+	unsigned int			sz_thresh1;
+	unsigned int			sz_thresh2;
+};
+
+/**
+ * struct knav_dma_cfg:	Pktdma channel configuration
+ * @sl_cfg:			Slave configuration
+ * @tx:				Tx channel configuration
+ * @rx:				Rx flow configuration
+ */
+struct knav_dma_cfg {
+	enum dma_transfer_direction direction;
+	union {
+		struct knav_dma_tx_cfg	tx;
+		struct knav_dma_rx_cfg	rx;
+	} u;
+};
+
+/**
+ * struct knav_dma_desc:	Host packet descriptor layout
+ * @desc_info:			Descriptor information like id, type, length
+ * @tag_info:			Flow tag info written in during RX
+ * @packet_info:		Queue Manager, policy, flags etc
+ * @buff_len:			Buffer length in bytes
+ * @buff:			Buffer pointer
+ * @next_desc:			For chaining the descriptors
+ * @orig_len:			length since 'buff_len' can be overwritten
+ * @orig_buff:			buff pointer since 'buff' can be overwritten
+ * @epib:			Extended packet info block
+ * @psdata:			Protocol specific
+ */
+struct knav_dma_desc {
+	u32	desc_info;
+	u32	tag_info;
+	u32	packet_info;
+	u32	buff_len;
+	u32	buff;
+	u32	next_desc;
+	u32	orig_len;
+	u32	orig_buff;
+	u32	epib[KNAV_DMA_NUM_EPIB_WORDS];
+	u32	psdata[KNAV_DMA_NUM_PS_WORDS];
+	u32	pad[4];
+} ____cacheline_aligned;
+
+#ifdef CONFIG_KEYSTONE_NAVIGATOR_DMA
+void *knav_dma_open_channel(struct device *dev, const char *name,
+				struct knav_dma_cfg *config);
+void knav_dma_close_channel(void *channel);
+#else
+static inline void *knav_dma_open_channel(struct device *dev, const char *name,
+				struct knav_dma_cfg *config)
+{
+	return (void *) NULL;
+}
+static inline void knav_dma_close_channel(void *channel)
+{}
+
+#endif
+
+#endif /* __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__ */
-- 
cgit v1.2.3


From b8f139f68f2099b7f8b4ef470a1e53210e3aa025 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 12 Sep 2014 08:53:56 +0200
Subject: regulator/mfd: max14577: Export symbols for calculating charger
 current

This patch prepares for changing the max14577 charger driver to allow
configuring battery-dependent settings from DTS.

The patch moves from regulator driver to MFD core driver and exports:
 - function for calculating register value for charger's current;
 - table of limits for chargers (MAX14577, MAX77836).

Previously they were used only by the max14577 regulator driver. In next
patch the charger driver will use them as well. Exporting them will
reduce unnecessary code duplication.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Acked-by: Mark Brown <broonie@linaro.org>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/max14577.c               | 95 ++++++++++++++++++++++++++++++++++++
 drivers/regulator/max14577.c         | 80 ++----------------------------
 include/linux/mfd/max14577-private.h | 22 ++++-----
 include/linux/mfd/max14577.h         | 23 +++++++++
 4 files changed, 133 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c
index 6599407b5624..b8af263be594 100644
--- a/drivers/mfd/max14577.c
+++ b/drivers/mfd/max14577.c
@@ -26,6 +26,87 @@
 #include <linux/mfd/max14577.h>
 #include <linux/mfd/max14577-private.h>
 
+/*
+ * Table of valid charger currents for different Maxim chipsets.
+ * It is placed here because it is used by both charger and regulator driver.
+ */
+const struct maxim_charger_current maxim_charger_currents[] = {
+	[MAXIM_DEVICE_TYPE_UNKNOWN] = { 0, 0, 0, 0 },
+	[MAXIM_DEVICE_TYPE_MAX14577] = {
+		.min		= MAX14577_CHARGER_CURRENT_LIMIT_MIN,
+		.high_start	= MAX14577_CHARGER_CURRENT_LIMIT_HIGH_START,
+		.high_step	= MAX14577_CHARGER_CURRENT_LIMIT_HIGH_STEP,
+		.max		= MAX14577_CHARGER_CURRENT_LIMIT_MAX,
+	},
+	[MAXIM_DEVICE_TYPE_MAX77836] = {
+		.min		= MAX77836_CHARGER_CURRENT_LIMIT_MIN,
+		.high_start	= MAX77836_CHARGER_CURRENT_LIMIT_HIGH_START,
+		.high_step	= MAX77836_CHARGER_CURRENT_LIMIT_HIGH_STEP,
+		.max		= MAX77836_CHARGER_CURRENT_LIMIT_MAX,
+	},
+};
+EXPORT_SYMBOL_GPL(maxim_charger_currents);
+
+/*
+ * maxim_charger_calc_reg_current - Calculate register value for current
+ * @limits:	constraints for charger, matching the MBCICHWRC register
+ * @min_ua:	minimal requested current, micro Amps
+ * @max_ua:	maximum requested current, micro Amps
+ * @dst:	destination to store calculated register value
+ *
+ * Calculates the value of MBCICHWRC (Fast Battery Charge Current) register
+ * for given current and stores it under pointed 'dst'. The stored value
+ * combines low bit (MBCICHWRCL) and high bits (MBCICHWRCH). It is also
+ * properly shifted.
+ *
+ * The calculated register value matches the current which:
+ *  - is always between <limits.min, limits.max>;
+ *  - is always less or equal to max_ua;
+ *  - is the highest possible value;
+ *  - may be lower than min_ua.
+ *
+ * On success returns 0. On error returns -EINVAL (requested min/max current
+ * is outside of given charger limits) and 'dst' is not set.
+ */
+int maxim_charger_calc_reg_current(const struct maxim_charger_current *limits,
+		unsigned int min_ua, unsigned int max_ua, u8 *dst)
+{
+	unsigned int current_bits = 0xf;
+
+	if (min_ua > max_ua)
+		return -EINVAL;
+
+	if (min_ua > limits->max || max_ua < limits->min)
+		return -EINVAL;
+
+	if (max_ua < limits->high_start) {
+		/*
+		 * Less than high_start, so set the minimal current
+		 * (turn Low Bit off, 0 as high bits).
+		 */
+		*dst = 0x0;
+		return 0;
+	}
+
+	/* max_ua is in range: <high_start, infinite>, cut it to limits.max */
+	max_ua = min(limits->max, max_ua);
+	max_ua -= limits->high_start;
+	/*
+	 * There is no risk of overflow 'max_ua' here because:
+	 *  - max_ua >= limits.high_start
+	 *  - BUILD_BUG checks that 'limits' are: max >= high_start + high_step
+	 */
+	current_bits = max_ua / limits->high_step;
+
+	/* Turn Low Bit on (use range <limits.high_start, limits.max>) ... */
+	*dst = 0x1 << CHGCTRL4_MBCICHWRCL_SHIFT;
+	/* and set proper High Bits */
+	*dst |= current_bits << CHGCTRL4_MBCICHWRCH_SHIFT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(maxim_charger_calc_reg_current);
+
 static const struct mfd_cell max14577_devs[] = {
 	{
 		.name = "max14577-muic",
@@ -466,6 +547,20 @@ static int __init max14577_i2c_init(void)
 	BUILD_BUG_ON(ARRAY_SIZE(max14577_i2c_id) != MAXIM_DEVICE_TYPE_NUM);
 	BUILD_BUG_ON(ARRAY_SIZE(max14577_dt_match) != MAXIM_DEVICE_TYPE_NUM);
 
+	/* Valid charger current values must be provided for each chipset */
+	BUILD_BUG_ON(ARRAY_SIZE(maxim_charger_currents) != MAXIM_DEVICE_TYPE_NUM);
+
+	/* Check for valid values for charger */
+	BUILD_BUG_ON(MAX14577_CHARGER_CURRENT_LIMIT_HIGH_START +
+			MAX14577_CHARGER_CURRENT_LIMIT_HIGH_STEP * 0xf !=
+			MAX14577_CHARGER_CURRENT_LIMIT_MAX);
+	BUILD_BUG_ON(MAX14577_CHARGER_CURRENT_LIMIT_HIGH_STEP == 0);
+
+	BUILD_BUG_ON(MAX77836_CHARGER_CURRENT_LIMIT_HIGH_START +
+			MAX77836_CHARGER_CURRENT_LIMIT_HIGH_STEP * 0xf !=
+			MAX77836_CHARGER_CURRENT_LIMIT_MAX);
+	BUILD_BUG_ON(MAX77836_CHARGER_CURRENT_LIMIT_HIGH_STEP == 0);
+
 	return i2c_add_driver(&max14577_i2c_driver);
 }
 subsys_initcall(max14577_i2c_init);
diff --git a/drivers/regulator/max14577.c b/drivers/regulator/max14577.c
index 5d9c605cf534..0ff5a20ac958 100644
--- a/drivers/regulator/max14577.c
+++ b/drivers/regulator/max14577.c
@@ -22,42 +22,6 @@
 #include <linux/mfd/max14577-private.h>
 #include <linux/regulator/of_regulator.h>
 
-/*
- * Valid limits of current for max14577 and max77836 chargers.
- * They must correspond to MBCICHWRCL and MBCICHWRCH fields in CHGCTRL4
- * register for given chipset.
- */
-struct maxim_charger_current {
-	/* Minimal current, set in CHGCTRL4/MBCICHWRCL, uA */
-	unsigned int min;
-	/*
-	 * Minimal current when high setting is active,
-	 * set in CHGCTRL4/MBCICHWRCH, uA
-	 */
-	unsigned int high_start;
-	/* Value of one step in high setting, uA */
-	unsigned int high_step;
-	/* Maximum current of high setting, uA */
-	unsigned int max;
-};
-
-/* Table of valid charger currents for different Maxim chipsets */
-static const struct maxim_charger_current maxim_charger_currents[] = {
-	[MAXIM_DEVICE_TYPE_UNKNOWN] = { 0, 0, 0, 0 },
-	[MAXIM_DEVICE_TYPE_MAX14577] = {
-		.min		= MAX14577_REGULATOR_CURRENT_LIMIT_MIN,
-		.high_start	= MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_START,
-		.high_step	= MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_STEP,
-		.max		= MAX14577_REGULATOR_CURRENT_LIMIT_MAX,
-	},
-	[MAXIM_DEVICE_TYPE_MAX77836] = {
-		.min		= MAX77836_REGULATOR_CURRENT_LIMIT_MIN,
-		.high_start	= MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_START,
-		.high_step	= MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_STEP,
-		.max		= MAX77836_REGULATOR_CURRENT_LIMIT_MAX,
-	},
-};
-
 static int max14577_reg_is_enabled(struct regulator_dev *rdev)
 {
 	int rid = rdev_get_id(rdev);
@@ -103,8 +67,8 @@ static int max14577_reg_get_current_limit(struct regulator_dev *rdev)
 static int max14577_reg_set_current_limit(struct regulator_dev *rdev,
 		int min_uA, int max_uA)
 {
-	int i, current_bits = 0xf;
 	u8 reg_data;
+	int ret;
 	struct max14577 *max14577 = rdev_get_drvdata(rdev);
 	const struct maxim_charger_current *limits =
 		&maxim_charger_currents[max14577->dev_type];
@@ -112,35 +76,9 @@ static int max14577_reg_set_current_limit(struct regulator_dev *rdev,
 	if (rdev_get_id(rdev) != MAX14577_CHARGER)
 		return -EINVAL;
 
-	if (min_uA > limits->max || max_uA < limits->min)
-		return -EINVAL;
-
-	if (max_uA < limits->high_start) {
-		/*
-		 * Less than high_start,
-		 * so set the minimal current (turn only Low Bit off)
-		 */
-		u8 reg_data = 0x0 << CHGCTRL4_MBCICHWRCL_SHIFT;
-		return max14577_update_reg(rdev->regmap,
-				MAX14577_CHG_REG_CHG_CTRL4,
-				CHGCTRL4_MBCICHWRCL_MASK, reg_data);
-	}
-
-	/*
-	 * max_uA is in range: <high_start, inifinite>, so search for
-	 * valid current starting from maximum current.
-	 */
-	for (i = limits->max; i >= limits->high_start; i -= limits->high_step) {
-		if (i <= max_uA)
-			break;
-		current_bits--;
-	}
-	BUG_ON(current_bits < 0); /* Cannot happen */
-
-	/* Turn Low Bit on (use range high_start-max)... */
-	reg_data = 0x1 << CHGCTRL4_MBCICHWRCL_SHIFT;
-	/* and set proper High Bits */
-	reg_data |= current_bits << CHGCTRL4_MBCICHWRCH_SHIFT;
+	ret = maxim_charger_calc_reg_current(limits, min_uA, max_uA, &reg_data);
+	if (ret)
+		return ret;
 
 	return max14577_update_reg(rdev->regmap, MAX14577_CHG_REG_CHG_CTRL4,
 			CHGCTRL4_MBCICHWRCL_MASK | CHGCTRL4_MBCICHWRCH_MASK,
@@ -442,16 +380,6 @@ static struct platform_driver max14577_regulator_driver = {
 
 static int __init max14577_regulator_init(void)
 {
-	/* Check for valid values for charger */
-	BUILD_BUG_ON(MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_START +
-			MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_STEP * 0xf !=
-			MAX14577_REGULATOR_CURRENT_LIMIT_MAX);
-	BUILD_BUG_ON(MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_START +
-			MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_STEP * 0xf !=
-			MAX77836_REGULATOR_CURRENT_LIMIT_MAX);
-	/* Valid charger current values must be provided for each chipset */
-	BUILD_BUG_ON(ARRAY_SIZE(maxim_charger_currents) != MAXIM_DEVICE_TYPE_NUM);
-
 	BUILD_BUG_ON(ARRAY_SIZE(max14577_supported_regulators) != MAX14577_REGULATOR_NUM);
 	BUILD_BUG_ON(ARRAY_SIZE(max77836_supported_regulators) != MAX77836_REGULATOR_NUM);
 
diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h
index d6f321699b89..7d514839c764 100644
--- a/include/linux/mfd/max14577-private.h
+++ b/include/linux/mfd/max14577-private.h
@@ -281,17 +281,17 @@ enum max14577_charger_reg {
 #define CHGCTRL7_OTPCGHCVS_SHIFT	0
 #define CHGCTRL7_OTPCGHCVS_MASK		(0x3 << CHGCTRL7_OTPCGHCVS_SHIFT)
 
-/* MAX14577 regulator current limits (as in CHGCTRL4 register), uA */
-#define MAX14577_REGULATOR_CURRENT_LIMIT_MIN		 90000
-#define MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_START	200000
-#define MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_STEP	 50000
-#define MAX14577_REGULATOR_CURRENT_LIMIT_MAX		950000
-
-/* MAX77836 regulator current limits (as in CHGCTRL4 register), uA */
-#define MAX77836_REGULATOR_CURRENT_LIMIT_MIN		 45000
-#define MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_START	100000
-#define MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_STEP	 25000
-#define MAX77836_REGULATOR_CURRENT_LIMIT_MAX		475000
+/* MAX14577 charger current limits (as in CHGCTRL4 register), uA */
+#define MAX14577_CHARGER_CURRENT_LIMIT_MIN		 90000U
+#define MAX14577_CHARGER_CURRENT_LIMIT_HIGH_START	200000U
+#define MAX14577_CHARGER_CURRENT_LIMIT_HIGH_STEP	 50000U
+#define MAX14577_CHARGER_CURRENT_LIMIT_MAX		950000U
+
+/* MAX77836 charger current limits (as in CHGCTRL4 register), uA */
+#define MAX77836_CHARGER_CURRENT_LIMIT_MIN		 45000U
+#define MAX77836_CHARGER_CURRENT_LIMIT_HIGH_START	100000U
+#define MAX77836_CHARGER_CURRENT_LIMIT_HIGH_STEP	 25000U
+#define MAX77836_CHARGER_CURRENT_LIMIT_MAX		475000U
 
 /* MAX14577 regulator SFOUT LDO voltage, fixed, uV */
 #define MAX14577_REGULATOR_SAFEOUT_VOLTAGE		4900000
diff --git a/include/linux/mfd/max14577.h b/include/linux/mfd/max14577.h
index c83fbed1c7b6..3c098d57b1d1 100644
--- a/include/linux/mfd/max14577.h
+++ b/include/linux/mfd/max14577.h
@@ -74,4 +74,27 @@ struct max14577_platform_data {
 	struct max14577_regulator_platform_data *regulators;
 };
 
+/*
+ * Valid limits of current for max14577 and max77836 chargers.
+ * They must correspond to MBCICHWRCL and MBCICHWRCH fields in CHGCTRL4
+ * register for given chipset.
+ */
+struct maxim_charger_current {
+	/* Minimal current, set in CHGCTRL4/MBCICHWRCL, uA */
+	unsigned int min;
+	/*
+	 * Minimal current when high setting is active,
+	 * set in CHGCTRL4/MBCICHWRCH, uA
+	 */
+	unsigned int high_start;
+	/* Value of one step in high setting, uA */
+	unsigned int high_step;
+	/* Maximum current of high setting, uA */
+	unsigned int max;
+};
+
+extern const struct maxim_charger_current maxim_charger_currents[];
+extern int maxim_charger_calc_reg_current(const struct maxim_charger_current *limits,
+		unsigned int min_ua, unsigned int max_ua, u8 *dst);
+
 #endif /* __MAX14577_H__ */
-- 
cgit v1.2.3


From e30110e9c96f48aea01abc3e6dfadb369cbafec3 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 12 Sep 2014 08:53:57 +0200
Subject: charger: max14577: Configure battery-dependent settings from DTS and
 sysfs

Remove hard-coded values for:
 - Fast Charge current,
 - End Of Charge current,
 - Fast Charge timer,
 - Overvoltage Protection Threshold,
 - Battery Constant Voltage,
and use DTS or sysfs to configure them. This allows using the max14577 charger
driver with different batteries.

Now the charger driver requires valid configuration data from DTS. In
case of wrong configuration data it fails during probe.

The fast charge timer is configured through sysfs entry.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/power/Kconfig                |   1 +
 drivers/power/max14577_charger.c     | 311 +++++++++++++++++++++++++++++++----
 include/linux/mfd/max14577-private.h |  19 +++
 include/linux/mfd/max14577.h         |   7 +
 4 files changed, 310 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 69fa8a9ef7a6..04e1d2fe2201 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -327,6 +327,7 @@ config CHARGER_MANAGER
 config CHARGER_MAX14577
 	tristate "Maxim MAX14577/77836 battery charger driver"
 	depends on MFD_MAX14577
+	select SYSFS
 	help
 	  Say Y to enable support for the battery charger control sysfs and
 	  platform data of MAX14577/77836 MUICs.
diff --git a/drivers/power/max14577_charger.c b/drivers/power/max14577_charger.c
index 193530549b1f..0a2bc7277026 100644
--- a/drivers/power/max14577_charger.c
+++ b/drivers/power/max14577_charger.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
 #include <linux/mfd/max14577-private.h>
+#include <linux/mfd/max14577.h>
 
 struct max14577_charger {
 	struct device *dev;
@@ -27,6 +28,8 @@ struct max14577_charger {
 
 	unsigned int		charging_state;
 	unsigned int		battery_state;
+
+	struct max14577_charger_platform_data	*pdata;
 };
 
 /*
@@ -178,15 +181,131 @@ static int max14577_get_present(struct max14577_charger *chg)
 	return 1;
 }
 
+static int max14577_set_fast_charge_timer(struct max14577_charger *chg,
+		unsigned long hours)
+{
+	u8 reg_data;
+
+	switch (hours) {
+	case 5 ... 7:
+		reg_data = hours - 3;
+		break;
+	case 0:
+		/* Disable */
+		reg_data = 0x7;
+		break;
+	default:
+		dev_err(chg->dev, "Wrong value for Fast-Charge Timer: %lu\n",
+				hours);
+		return -EINVAL;
+	}
+	reg_data <<= CHGCTRL1_TCHW_SHIFT;
+
+	return max14577_update_reg(chg->max14577->regmap,
+			MAX14577_REG_CHGCTRL1, CHGCTRL1_TCHW_MASK, reg_data);
+}
+
+static int max14577_init_constant_voltage(struct max14577_charger *chg,
+		unsigned int uvolt)
+{
+	u8 reg_data;
+
+	if (uvolt < MAXIM_CHARGER_CONSTANT_VOLTAGE_MIN ||
+			uvolt > MAXIM_CHARGER_CONSTANT_VOLTAGE_MAX)
+		return -EINVAL;
+
+	if (uvolt == 4200000)
+		reg_data = 0x0;
+	else if (uvolt == MAXIM_CHARGER_CONSTANT_VOLTAGE_MAX)
+		reg_data = 0x1f;
+	else if (uvolt <= 4280000) {
+		unsigned int val = uvolt;
+
+		val -= MAXIM_CHARGER_CONSTANT_VOLTAGE_MIN;
+		val /= MAXIM_CHARGER_CONSTANT_VOLTAGE_STEP;
+		if (uvolt <= 4180000)
+			reg_data = 0x1 + val;
+		else
+			reg_data = val; /* Fix for gap between 4.18V and 4.22V */
+	} else
+		return -EINVAL;
+
+	reg_data <<= CHGCTRL3_MBCCVWRC_SHIFT;
+
+	return max14577_write_reg(chg->max14577->regmap,
+			MAX14577_CHG_REG_CHG_CTRL3, reg_data);
+}
+
+static int max14577_init_eoc(struct max14577_charger *chg,
+		unsigned int uamp)
+{
+	unsigned int current_bits = 0xf;
+	u8 reg_data;
+
+	switch (chg->max14577->dev_type) {
+	case MAXIM_DEVICE_TYPE_MAX77836:
+		if (uamp < 5000)
+			return -EINVAL; /* Requested current is too low */
+
+		if (uamp >= 7500 && uamp < 10000)
+			current_bits = 0x0;
+		else if (uamp <= 50000) {
+			/* <5000, 7499> and <10000, 50000> */
+			current_bits = uamp / 5000;
+		} else {
+			uamp = min(uamp, 100000U) - 50000U;
+			current_bits = 0xa + uamp / 10000;
+		}
+		break;
+
+	case MAXIM_DEVICE_TYPE_MAX14577:
+	default:
+		if (uamp < MAX14577_CHARGER_EOC_CURRENT_LIMIT_MIN)
+			return -EINVAL; /* Requested current is too low */
+
+		uamp = min(uamp, MAX14577_CHARGER_EOC_CURRENT_LIMIT_MAX);
+		uamp -= MAX14577_CHARGER_EOC_CURRENT_LIMIT_MIN;
+		current_bits = uamp / MAX14577_CHARGER_EOC_CURRENT_LIMIT_STEP;
+		break;
+	}
+
+	reg_data = current_bits << CHGCTRL5_EOCS_SHIFT;
+
+	return max14577_update_reg(chg->max14577->regmap,
+			MAX14577_CHG_REG_CHG_CTRL5, CHGCTRL5_EOCS_MASK,
+			reg_data);
+}
+
+static int max14577_init_fast_charge(struct max14577_charger *chg,
+		unsigned int uamp)
+{
+	u8 reg_data;
+	int ret;
+	const struct maxim_charger_current *limits =
+		&maxim_charger_currents[chg->max14577->dev_type];
+
+	ret = maxim_charger_calc_reg_current(limits, uamp, uamp, &reg_data);
+	if (ret) {
+		dev_err(chg->dev, "Wrong value for fast charge: %u\n", uamp);
+		return ret;
+	}
+
+	return max14577_update_reg(chg->max14577->regmap,
+			MAX14577_CHG_REG_CHG_CTRL4,
+			CHGCTRL4_MBCICHWRCL_MASK | CHGCTRL4_MBCICHWRCH_MASK,
+			reg_data);
+}
+
 /*
  * Sets charger registers to proper and safe default values.
  * Some of these values are equal to defaults in MAX14577E
  * data sheet but there are minor differences.
  */
-static void max14577_charger_reg_init(struct max14577_charger *chg)
+static int max14577_charger_reg_init(struct max14577_charger *chg)
 {
 	struct regmap *rmap = chg->max14577->regmap;
 	u8 reg_data;
+	int ret;
 
 	/*
 	 * Charger-Type Manual Detection, default off (set CHGTYPMAN to 0)
@@ -198,10 +317,6 @@ static void max14577_charger_reg_init(struct max14577_charger *chg)
 			CDETCTRL1_CHGDETEN_MASK | CDETCTRL1_CHGTYPMAN_MASK,
 			reg_data);
 
-	/* Battery Fast-Charge Timer, set to: 6hrs */
-	reg_data = 0x3 << CHGCTRL1_TCHW_SHIFT;
-	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL1, reg_data);
-
 	/*
 	 * Wall-Adapter Rapid Charge, default on
 	 * Battery-Charger, default on
@@ -210,32 +325,46 @@ static void max14577_charger_reg_init(struct max14577_charger *chg)
 	reg_data |= 0x1 << CHGCTRL2_MBCHOSTEN_SHIFT;
 	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL2, reg_data);
 
-	/* Battery-Charger Constant Voltage (CV) Mode, set to: 4.35V */
-	reg_data = 0xf << CHGCTRL3_MBCCVWRC_SHIFT;
-	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL3, reg_data);
-
-	/*
-	 * Fast Battery-Charge Current Low,
-	 * default 200-950mA (max14577) / 100-475mA (max77836)
-	 *
-	 * Fast Battery-Charge Current High,
-	 * set to 450mA (max14577) / 225mA (max77836)
-	 */
-	reg_data = 0x1 << CHGCTRL4_MBCICHWRCL_SHIFT;
-	reg_data |= 0x5 << CHGCTRL4_MBCICHWRCH_SHIFT;
-	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL4, reg_data);
-
-	/* End-of-Charge Current, set to 50mA (max14577) / 7.5mA (max77836) */
-	reg_data = 0x0 << CHGCTRL5_EOCS_SHIFT;
-	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL5, reg_data);
-
 	/* Auto Charging Stop, default off */
 	reg_data = 0x0 << CHGCTRL6_AUTOSTOP_SHIFT;
 	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL6, reg_data);
 
-	/* Overvoltage-Protection Threshold, set to 6.5V */
-	reg_data = 0x2 << CHGCTRL7_OTPCGHCVS_SHIFT;
+	ret = max14577_init_constant_voltage(chg, chg->pdata->constant_uvolt);
+	if (ret)
+		return ret;
+
+	ret = max14577_init_eoc(chg, chg->pdata->eoc_uamp);
+	if (ret)
+		return ret;
+
+	ret = max14577_init_fast_charge(chg, chg->pdata->fast_charge_uamp);
+	if (ret)
+		return ret;
+
+	ret = max14577_set_fast_charge_timer(chg,
+			MAXIM_CHARGER_FAST_CHARGE_TIMER_DEFAULT);
+	if (ret)
+		return ret;
+
+	/* Initialize Overvoltage-Protection Threshold */
+	switch (chg->pdata->ovp_uvolt) {
+	case 7500000:
+		reg_data = 0x0;
+		break;
+	case 6000000:
+	case 6500000:
+	case 7000000:
+		reg_data = 0x1 + (chg->pdata->ovp_uvolt - 6000000) / 500000;
+		break;
+	default:
+		dev_err(chg->dev, "Wrong value for OVP: %u\n",
+				chg->pdata->ovp_uvolt);
+		return -EINVAL;
+	}
+	reg_data <<= CHGCTRL7_OTPCGHCVS_SHIFT;
 	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL7, reg_data);
+
+	return 0;
 }
 
 /* Support property from charger */
@@ -295,6 +424,110 @@ static int max14577_charger_get_property(struct power_supply *psy,
 	return ret;
 }
 
+#ifdef CONFIG_OF
+static struct max14577_charger_platform_data *max14577_charger_dt_init(
+		struct platform_device *pdev)
+{
+	struct max14577_charger_platform_data *pdata;
+	struct device_node *np = pdev->dev.of_node;
+	int ret;
+
+	if (!np) {
+		dev_err(&pdev->dev, "No charger OF node\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	ret = of_property_read_u32(np, "maxim,constant-uvolt",
+			&pdata->constant_uvolt);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot parse maxim,constant-uvolt field from DT\n");
+		return ERR_PTR(ret);
+	}
+
+	ret = of_property_read_u32(np, "maxim,fast-charge-uamp",
+			&pdata->fast_charge_uamp);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot parse maxim,fast-charge-uamp field from DT\n");
+		return ERR_PTR(ret);
+	}
+
+	ret = of_property_read_u32(np, "maxim,eoc-uamp", &pdata->eoc_uamp);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot parse maxim,eoc-uamp field from DT\n");
+		return ERR_PTR(ret);
+	}
+
+	ret = of_property_read_u32(np, "maxim,ovp-uvolt", &pdata->ovp_uvolt);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot parse maxim,ovp-uvolt field from DT\n");
+		return ERR_PTR(ret);
+	}
+
+	return pdata;
+}
+#else /* CONFIG_OF */
+static struct max14577_charger_platform_data *max14577_charger_dt_init(
+		struct platform_device *pdev)
+{
+	return NULL;
+}
+#endif /* CONFIG_OF */
+
+static ssize_t show_fast_charge_timer(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct max14577_charger *chg = dev_get_drvdata(dev);
+	u8 reg_data;
+	int ret;
+	unsigned int val;
+
+	ret = max14577_read_reg(chg->max14577->regmap, MAX14577_REG_CHGCTRL1,
+			&reg_data);
+	if (ret)
+		return ret;
+
+	reg_data &= CHGCTRL1_TCHW_MASK;
+	reg_data >>= CHGCTRL1_TCHW_SHIFT;
+	switch (reg_data) {
+	case 0x2 ... 0x4:
+		val = reg_data + 3;
+		break;
+	case 0x7:
+		val = 0;
+		break;
+	default:
+		val = 5;
+		break;
+	}
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+}
+
+static ssize_t store_fast_charge_timer(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct max14577_charger *chg = dev_get_drvdata(dev);
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	ret = max14577_set_fast_charge_timer(chg, val);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static DEVICE_ATTR(fast_charge_timer, S_IRUGO | S_IWUSR,
+		show_fast_charge_timer, store_fast_charge_timer);
+
 static int max14577_charger_probe(struct platform_device *pdev)
 {
 	struct max14577_charger *chg;
@@ -309,7 +542,13 @@ static int max14577_charger_probe(struct platform_device *pdev)
 	chg->dev = &pdev->dev;
 	chg->max14577 = max14577;
 
-	max14577_charger_reg_init(chg);
+	chg->pdata = max14577_charger_dt_init(pdev);
+	if (IS_ERR_OR_NULL(chg->pdata))
+		return PTR_ERR(chg->pdata);
+
+	ret = max14577_charger_reg_init(chg);
+	if (ret)
+		return ret;
 
 	chg->charger.name = "max14577-charger",
 	chg->charger.type = POWER_SUPPLY_TYPE_BATTERY,
@@ -317,19 +556,35 @@ static int max14577_charger_probe(struct platform_device *pdev)
 	chg->charger.num_properties = ARRAY_SIZE(max14577_charger_props),
 	chg->charger.get_property = max14577_charger_get_property,
 
+	ret = device_create_file(&pdev->dev, &dev_attr_fast_charge_timer);
+	if (ret) {
+		dev_err(&pdev->dev, "failed: create sysfs entry\n");
+		return ret;
+	}
+
 	ret = power_supply_register(&pdev->dev, &chg->charger);
 	if (ret) {
 		dev_err(&pdev->dev, "failed: power supply register\n");
-		return ret;
+		goto err;
 	}
 
+	/* Check for valid values for charger */
+	BUILD_BUG_ON(MAX14577_CHARGER_EOC_CURRENT_LIMIT_MIN +
+			MAX14577_CHARGER_EOC_CURRENT_LIMIT_STEP * 0xf !=
+			MAX14577_CHARGER_EOC_CURRENT_LIMIT_MAX);
 	return 0;
+
+err:
+	device_remove_file(&pdev->dev, &dev_attr_fast_charge_timer);
+
+	return ret;
 }
 
 static int max14577_charger_remove(struct platform_device *pdev)
 {
 	struct max14577_charger *chg = platform_get_drvdata(pdev);
 
+	device_remove_file(&pdev->dev, &dev_attr_fast_charge_timer);
 	power_supply_unregister(&chg->charger);
 
 	return 0;
diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h
index 7d514839c764..f01c1fae4d84 100644
--- a/include/linux/mfd/max14577-private.h
+++ b/include/linux/mfd/max14577-private.h
@@ -293,6 +293,25 @@ enum max14577_charger_reg {
 #define MAX77836_CHARGER_CURRENT_LIMIT_HIGH_STEP	 25000U
 #define MAX77836_CHARGER_CURRENT_LIMIT_MAX		475000U
 
+/*
+ * MAX14577 charger End-Of-Charge current limits
+ * (as in CHGCTRL5 register), uA
+ */
+#define MAX14577_CHARGER_EOC_CURRENT_LIMIT_MIN		50000U
+#define MAX14577_CHARGER_EOC_CURRENT_LIMIT_STEP		10000U
+#define MAX14577_CHARGER_EOC_CURRENT_LIMIT_MAX		200000U
+
+/*
+ * MAX14577/MAX77836 Battery Constant Voltage
+ * (as in CHGCTRL3 register), uV
+ */
+#define MAXIM_CHARGER_CONSTANT_VOLTAGE_MIN		4000000U
+#define MAXIM_CHARGER_CONSTANT_VOLTAGE_STEP		20000U
+#define MAXIM_CHARGER_CONSTANT_VOLTAGE_MAX		4350000U
+
+/* Default value for fast charge timer, in hours */
+#define MAXIM_CHARGER_FAST_CHARGE_TIMER_DEFAULT		5
+
 /* MAX14577 regulator SFOUT LDO voltage, fixed, uV */
 #define MAX14577_REGULATOR_SAFEOUT_VOLTAGE		4900000
 
diff --git a/include/linux/mfd/max14577.h b/include/linux/mfd/max14577.h
index 3c098d57b1d1..ccfaf952c31b 100644
--- a/include/linux/mfd/max14577.h
+++ b/include/linux/mfd/max14577.h
@@ -54,6 +54,13 @@ struct max14577_regulator_platform_data {
 	struct device_node *of_node;
 };
 
+struct max14577_charger_platform_data {
+	u32 constant_uvolt;
+	u32 fast_charge_uamp;
+	u32 eoc_uamp;
+	u32 ovp_uvolt;
+};
+
 /*
  * MAX14577 MFD platform data
  */
-- 
cgit v1.2.3


From 0a30288da1aec914e158c2d7a3482a85f632750f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 23 Sep 2014 15:24:32 -0400
Subject: blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during
 probe

blk-mq uses percpu_ref for its usage counter which tracks the number
of in-flight commands and used to synchronously drain the queue on
freeze.  percpu_ref shutdown takes measureable wallclock time as it
involves a sched RCU grace period.  This means that draining a blk-mq
takes measureable wallclock time.  One would think that this shouldn't
matter as queue shutdown should be a rare event which takes place
asynchronously w.r.t. userland.

Unfortunately, SCSI probing involves synchronously setting up and then
tearing down a lot of request_queues back-to-back for non-existent
LUNs.  This means that SCSI probing may take more than ten seconds
when scsi-mq is used.

This will be properly fixed by implementing a mechanism to keep
q->mq_usage_counter in atomic mode till genhd registration; however,
that involves rather big updates to percpu_ref which is difficult to
apply late in the devel cycle (v3.17-rc6 at the moment).  As a
stop-gap measure till the proper fix can be implemented in the next
cycle, this patch introduces __percpu_ref_kill_expedited() and makes
blk_mq_freeze_queue() use it.  This is heavy-handed but should work
for testing the experimental SCSI blk-mq implementation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Christoph Hellwig <hch@infradead.org>
Link: http://lkml.kernel.org/g/20140919113815.GA10791@lst.de
Fixes: add703fda981 ("blk-mq: use percpu_ref for mq usage count")
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Tested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c                  | 11 ++++++++++-
 include/linux/percpu-refcount.h |  1 +
 lib/percpu-refcount.c           | 16 ++++++++++++++++
 3 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index c88e6089746d..df8e1e09dd17 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -119,7 +119,16 @@ void blk_mq_freeze_queue(struct request_queue *q)
 	spin_unlock_irq(q->queue_lock);
 
 	if (freeze) {
-		percpu_ref_kill(&q->mq_usage_counter);
+		/*
+		 * XXX: Temporary kludge to work around SCSI blk-mq stall.
+		 * SCSI synchronously creates and destroys many queues
+		 * back-to-back during probe leading to lengthy stalls.
+		 * This will be fixed by keeping ->mq_usage_counter in
+		 * atomic mode until genhd registration, but, for now,
+		 * let's work around using expedited synchronization.
+		 */
+		__percpu_ref_kill_expedited(&q->mq_usage_counter);
+
 		blk_mq_run_queues(q, false);
 	}
 	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 3dfbf237cd8f..ef5894ca8e50 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -71,6 +71,7 @@ void percpu_ref_reinit(struct percpu_ref *ref);
 void percpu_ref_exit(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
+void __percpu_ref_kill_expedited(struct percpu_ref *ref);
 
 /**
  * percpu_ref_kill - drop the initial ref
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index fe5a3342e960..a89cf09a8268 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -184,3 +184,19 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
+
+/*
+ * XXX: Temporary kludge to work around SCSI blk-mq stall.  Used only by
+ * block/blk-mq.c::blk_mq_freeze_queue().  Will be removed during v3.18
+ * devel cycle.  Do not use anywhere else.
+ */
+void __percpu_ref_kill_expedited(struct percpu_ref *ref)
+{
+	WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
+		  "percpu_ref_kill() called more than once on %pf!",
+		  ref->release);
+
+	ref->pcpu_count_ptr |= PCPU_REF_DEAD;
+	synchronize_sched_expedited();
+	percpu_ref_kill_rcu(&ref->rcu);
+}
-- 
cgit v1.2.3


From 9eca80461a45177e456219a9cd944c27675d6512 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:07:33 -0400
Subject: Revert "blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall
 during probe"

This reverts commit 0a30288da1aec914e158c2d7a3482a85f632750f, which
was a temporary fix for SCSI blk-mq stall issue.  The following
patches will fix the issue properly by introducing atomic mode to
percpu_ref.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>
---
 block/blk-mq.c                  | 11 +----------
 include/linux/percpu-refcount.h |  1 -
 lib/percpu-refcount.c           | 16 ----------------
 3 files changed, 1 insertion(+), 27 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 255d79c14dc1..44a78ae3f899 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -119,16 +119,7 @@ void blk_mq_freeze_queue(struct request_queue *q)
 	spin_unlock_irq(q->queue_lock);
 
 	if (freeze) {
-		/*
-		 * XXX: Temporary kludge to work around SCSI blk-mq stall.
-		 * SCSI synchronously creates and destroys many queues
-		 * back-to-back during probe leading to lengthy stalls.
-		 * This will be fixed by keeping ->mq_usage_counter in
-		 * atomic mode until genhd registration, but, for now,
-		 * let's work around using expedited synchronization.
-		 */
-		__percpu_ref_kill_expedited(&q->mq_usage_counter);
-
+		percpu_ref_kill(&q->mq_usage_counter);
 		blk_mq_run_queues(q, false);
 	}
 	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 11b38ceca7e2..5df6784bd9d2 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -72,7 +72,6 @@ void percpu_ref_reinit(struct percpu_ref *ref);
 void percpu_ref_exit(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
-void __percpu_ref_kill_expedited(struct percpu_ref *ref);
 
 /**
  * percpu_ref_kill - drop the initial ref
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index c6c31e2829b1..559ee0b20318 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -189,19 +189,3 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
-
-/*
- * XXX: Temporary kludge to work around SCSI blk-mq stall.  Used only by
- * block/blk-mq.c::blk_mq_freeze_queue().  Will be removed during v3.18
- * devel cycle.  Do not use anywhere else.
- */
-void __percpu_ref_kill_expedited(struct percpu_ref *ref)
-{
-	WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
-		  "percpu_ref_kill() called more than once on %pf!",
-		  ref->release);
-
-	ref->pcpu_count_ptr |= PCPU_REF_DEAD;
-	synchronize_sched_expedited();
-	percpu_ref_kill_rcu(&ref->rcu);
-}
-- 
cgit v1.2.3


From a2237370194484ee6aeeff04b617e4b14d178966 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:48 -0400
Subject: percpu_ref: relocate percpu_ref_reinit()

percpu_ref is gonna go through restructuring.  Move
percpu_ref_reinit() after percpu_ref_kill_and_confirm().  This will
make later changes easier to follow and result in cleaner
organization.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
---
 include/linux/percpu-refcount.h |  2 +-
 lib/percpu-refcount.c           | 70 ++++++++++++++++++++---------------------
 2 files changed, 36 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 5df6784bd9d2..f015f139d491 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -68,10 +68,10 @@ struct percpu_ref {
 
 int __must_check percpu_ref_init(struct percpu_ref *ref,
 				 percpu_ref_func_t *release, gfp_t gfp);
-void percpu_ref_reinit(struct percpu_ref *ref);
 void percpu_ref_exit(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
+void percpu_ref_reinit(struct percpu_ref *ref);
 
 /**
  * percpu_ref_kill - drop the initial ref
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 559ee0b20318..070dab5e7d77 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -62,41 +62,6 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 }
 EXPORT_SYMBOL_GPL(percpu_ref_init);
 
-/**
- * percpu_ref_reinit - re-initialize a percpu refcount
- * @ref: perpcu_ref to re-initialize
- *
- * Re-initialize @ref so that it's in the same state as when it finished
- * percpu_ref_init().  @ref must have been initialized successfully, killed
- * and reached 0 but not exited.
- *
- * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while
- * this function is in progress.
- */
-void percpu_ref_reinit(struct percpu_ref *ref)
-{
-	unsigned long __percpu *pcpu_count = pcpu_count_ptr(ref);
-	int cpu;
-
-	BUG_ON(!pcpu_count);
-	WARN_ON(!percpu_ref_is_zero(ref));
-
-	atomic_long_set(&ref->count, 1 + PCPU_COUNT_BIAS);
-
-	/*
-	 * Restore per-cpu operation.  smp_store_release() is paired with
-	 * smp_read_barrier_depends() in __pcpu_ref_alive() and guarantees
-	 * that the zeroing is visible to all percpu accesses which can see
-	 * the following PCPU_REF_DEAD clearing.
-	 */
-	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(pcpu_count, cpu) = 0;
-
-	smp_store_release(&ref->pcpu_count_ptr,
-			  ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
-}
-EXPORT_SYMBOL_GPL(percpu_ref_reinit);
-
 /**
  * percpu_ref_exit - undo percpu_ref_init()
  * @ref: percpu_ref to exit
@@ -189,3 +154,38 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
+
+/**
+ * percpu_ref_reinit - re-initialize a percpu refcount
+ * @ref: perpcu_ref to re-initialize
+ *
+ * Re-initialize @ref so that it's in the same state as when it finished
+ * percpu_ref_init().  @ref must have been initialized successfully, killed
+ * and reached 0 but not exited.
+ *
+ * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while
+ * this function is in progress.
+ */
+void percpu_ref_reinit(struct percpu_ref *ref)
+{
+	unsigned long __percpu *pcpu_count = pcpu_count_ptr(ref);
+	int cpu;
+
+	BUG_ON(!pcpu_count);
+	WARN_ON(!percpu_ref_is_zero(ref));
+
+	atomic_long_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+
+	/*
+	 * Restore per-cpu operation.  smp_store_release() is paired with
+	 * smp_read_barrier_depends() in __pcpu_ref_alive() and guarantees
+	 * that the zeroing is visible to all percpu accesses which can see
+	 * the following PCPU_REF_DEAD clearing.
+	 */
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(pcpu_count, cpu) = 0;
+
+	smp_store_release(&ref->pcpu_count_ptr,
+			  ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
+}
+EXPORT_SYMBOL_GPL(percpu_ref_reinit);
-- 
cgit v1.2.3


From 6251f9976af7656b6970a8820153f356430f5de2 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:48 -0400
Subject: percpu_ref: minor code and comment updates

* Some comments became stale.  Updated.
* percpu_ref_tryget() unnecessarily initializes @ret.  Removed.
* A blank line removed from percpu_ref_kill_rcu().
* Explicit function name in a WARN format string replaced with __func__.
* WARN_ON() in percpu_ref_reinit() converted to WARN_ON_ONCE().

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
---
 include/linux/percpu-refcount.h | 25 ++++++++++++++++---------
 lib/percpu-refcount.c           | 14 ++++++--------
 2 files changed, 22 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index f015f139d491..d44b027f74fd 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -115,8 +115,10 @@ static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
  * percpu_ref_get - increment a percpu refcount
  * @ref: percpu_ref to get
  *
- * Analagous to atomic_inc().
-  */
+ * Analagous to atomic_long_inc().
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
 static inline void percpu_ref_get(struct percpu_ref *ref)
 {
 	unsigned long __percpu *pcpu_count;
@@ -138,12 +140,12 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
  * Increment a percpu refcount unless its count already reached zero.
  * Returns %true on success; %false on failure.
  *
- * The caller is responsible for ensuring that @ref stays accessible.
+ * This function is safe to call as long as @ref is between init and exit.
  */
 static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 {
 	unsigned long __percpu *pcpu_count;
-	int ret = false;
+	int ret;
 
 	rcu_read_lock_sched();
 
@@ -166,12 +168,13 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
  * Increment a percpu refcount unless it has already been killed.  Returns
  * %true on success; %false on failure.
  *
- * Completion of percpu_ref_kill() in itself doesn't guarantee that tryget
- * will fail.  For such guarantee, percpu_ref_kill_and_confirm() should be
- * used.  After the confirm_kill callback is invoked, it's guaranteed that
- * no new reference will be given out by percpu_ref_tryget().
+ * Completion of percpu_ref_kill() in itself doesn't guarantee that this
+ * function will fail.  For such guarantee, percpu_ref_kill_and_confirm()
+ * should be used.  After the confirm_kill callback is invoked, it's
+ * guaranteed that no new reference will be given out by
+ * percpu_ref_tryget_live().
  *
- * The caller is responsible for ensuring that @ref stays accessible.
+ * This function is safe to call as long as @ref is between init and exit.
  */
 static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 {
@@ -196,6 +199,8 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
  *
  * Decrement the refcount, and if 0, call the release function (which was passed
  * to percpu_ref_init())
+ *
+ * This function is safe to call as long as @ref is between init and exit.
  */
 static inline void percpu_ref_put(struct percpu_ref *ref)
 {
@@ -216,6 +221,8 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
  * @ref: percpu_ref to test
  *
  * Returns %true if @ref reached zero.
+ *
+ * This function is safe to call as long as @ref is between init and exit.
  */
 static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
 {
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 070dab5e7d77..8ef3f5c20df6 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -108,7 +108,6 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 	 * reaching 0 before we add the percpu counts. But doing it at the same
 	 * time is equivalent and saves us atomic operations:
 	 */
-
 	atomic_long_add((long)count - PCPU_COUNT_BIAS, &ref->count);
 
 	WARN_ONCE(atomic_long_read(&ref->count) <= 0,
@@ -120,8 +119,8 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 		ref->confirm_kill(ref);
 
 	/*
-	 * Now we're in single atomic_t mode with a consistent refcount, so it's
-	 * safe to drop our initial ref:
+	 * Now we're in single atomic_long_t mode with a consistent
+	 * refcount, so it's safe to drop our initial ref:
 	 */
 	percpu_ref_put(ref);
 }
@@ -134,8 +133,8 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
  * Equivalent to percpu_ref_kill() but also schedules kill confirmation if
  * @confirm_kill is not NULL.  @confirm_kill, which may not block, will be
  * called after @ref is seen as dead from all CPUs - all further
- * invocations of percpu_ref_tryget() will fail.  See percpu_ref_tryget()
- * for more details.
+ * invocations of percpu_ref_tryget_live() will fail.  See
+ * percpu_ref_tryget_live() for more details.
  *
  * Due to the way percpu_ref is implemented, @confirm_kill will be called
  * after at least one full RCU grace period has passed but this is an
@@ -145,8 +144,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill)
 {
 	WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
-		  "percpu_ref_kill() called more than once on %pf!",
-		  ref->release);
+		  "%s called more than once on %pf!", __func__, ref->release);
 
 	ref->pcpu_count_ptr |= PCPU_REF_DEAD;
 	ref->confirm_kill = confirm_kill;
@@ -172,7 +170,7 @@ void percpu_ref_reinit(struct percpu_ref *ref)
 	int cpu;
 
 	BUG_ON(!pcpu_count);
-	WARN_ON(!percpu_ref_is_zero(ref));
+	WARN_ON_ONCE(!percpu_ref_is_zero(ref));
 
 	atomic_long_set(&ref->count, 1 + PCPU_COUNT_BIAS);
 
-- 
cgit v1.2.3


From eecc16ba9a49b05dd847a317af166a6728eb56ca Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:48 -0400
Subject: percpu_ref: replace pcpu_ prefix with percpu_

percpu_ref uses pcpu_ prefix for internal stuff and percpu_ for
externally visible ones.  This is the same convention used in the
percpu allocator implementation.  It works fine there but percpu_ref
doesn't have too much internal-only stuff and scattered usages of
pcpu_ prefix are confusing than helpful.

This patch replaces all pcpu_ prefixes with percpu_.  This is pure
rename and there's no functional change.  Note that PCPU_REF_DEAD is
renamed to __PERCPU_REF_DEAD to signify that the flag is internal.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
---
 include/linux/percpu-refcount.h | 46 ++++++++++++++++-----------------
 lib/percpu-refcount.c           | 56 +++++++++++++++++++++--------------------
 2 files changed, 52 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index d44b027f74fd..3d463a39e0f7 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -13,7 +13,7 @@
  *
  * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less
  * than an atomic_t - this is because of the way shutdown works, see
- * percpu_ref_kill()/PCPU_COUNT_BIAS.
+ * percpu_ref_kill()/PERCPU_COUNT_BIAS.
  *
  * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the
  * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill()
@@ -60,7 +60,7 @@ struct percpu_ref {
 	 * The low bit of the pointer indicates whether the ref is in percpu
 	 * mode; if set, then get/put will manipulate the atomic_t.
 	 */
-	unsigned long		pcpu_count_ptr;
+	unsigned long		percpu_count_ptr;
 	percpu_ref_func_t	*release;
 	percpu_ref_func_t	*confirm_kill;
 	struct rcu_head		rcu;
@@ -88,26 +88,26 @@ static inline void percpu_ref_kill(struct percpu_ref *ref)
 	return percpu_ref_kill_and_confirm(ref, NULL);
 }
 
-#define PCPU_REF_DEAD		1
+#define __PERCPU_REF_DEAD	1
 
 /*
  * Internal helper.  Don't use outside percpu-refcount proper.  The
  * function doesn't return the pointer and let the caller test it for NULL
  * because doing so forces the compiler to generate two conditional
- * branches as it can't assume that @ref->pcpu_count is not NULL.
+ * branches as it can't assume that @ref->percpu_count is not NULL.
  */
-static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
-				    unsigned long __percpu **pcpu_countp)
+static inline bool __percpu_ref_alive(struct percpu_ref *ref,
+				      unsigned long __percpu **percpu_countp)
 {
-	unsigned long pcpu_ptr = ACCESS_ONCE(ref->pcpu_count_ptr);
+	unsigned long percpu_ptr = ACCESS_ONCE(ref->percpu_count_ptr);
 
 	/* paired with smp_store_release() in percpu_ref_reinit() */
 	smp_read_barrier_depends();
 
-	if (unlikely(pcpu_ptr & PCPU_REF_DEAD))
+	if (unlikely(percpu_ptr & __PERCPU_REF_DEAD))
 		return false;
 
-	*pcpu_countp = (unsigned long __percpu *)pcpu_ptr;
+	*percpu_countp = (unsigned long __percpu *)percpu_ptr;
 	return true;
 }
 
@@ -121,12 +121,12 @@ static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
  */
 static inline void percpu_ref_get(struct percpu_ref *ref)
 {
-	unsigned long __percpu *pcpu_count;
+	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
-	if (__pcpu_ref_alive(ref, &pcpu_count))
-		this_cpu_inc(*pcpu_count);
+	if (__percpu_ref_alive(ref, &percpu_count))
+		this_cpu_inc(*percpu_count);
 	else
 		atomic_long_inc(&ref->count);
 
@@ -144,13 +144,13 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 {
-	unsigned long __percpu *pcpu_count;
+	unsigned long __percpu *percpu_count;
 	int ret;
 
 	rcu_read_lock_sched();
 
-	if (__pcpu_ref_alive(ref, &pcpu_count)) {
-		this_cpu_inc(*pcpu_count);
+	if (__percpu_ref_alive(ref, &percpu_count)) {
+		this_cpu_inc(*percpu_count);
 		ret = true;
 	} else {
 		ret = atomic_long_inc_not_zero(&ref->count);
@@ -178,13 +178,13 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 {
-	unsigned long __percpu *pcpu_count;
+	unsigned long __percpu *percpu_count;
 	int ret = false;
 
 	rcu_read_lock_sched();
 
-	if (__pcpu_ref_alive(ref, &pcpu_count)) {
-		this_cpu_inc(*pcpu_count);
+	if (__percpu_ref_alive(ref, &percpu_count)) {
+		this_cpu_inc(*percpu_count);
 		ret = true;
 	}
 
@@ -204,12 +204,12 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
  */
 static inline void percpu_ref_put(struct percpu_ref *ref)
 {
-	unsigned long __percpu *pcpu_count;
+	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
-	if (__pcpu_ref_alive(ref, &pcpu_count))
-		this_cpu_dec(*pcpu_count);
+	if (__percpu_ref_alive(ref, &percpu_count))
+		this_cpu_dec(*percpu_count);
 	else if (unlikely(atomic_long_dec_and_test(&ref->count)))
 		ref->release(ref);
 
@@ -226,9 +226,9 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
  */
 static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
 {
-	unsigned long __percpu *pcpu_count;
+	unsigned long __percpu *percpu_count;
 
-	if (__pcpu_ref_alive(ref, &pcpu_count))
+	if (__percpu_ref_alive(ref, &percpu_count))
 		return false;
 	return !atomic_long_read(&ref->count);
 }
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 8ef3f5c20df6..5aea6b7356c7 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -11,8 +11,8 @@
  * percpu counters will all sum to the correct value
  *
  * (More precisely: because moduler arithmatic is commutative the sum of all the
- * pcpu_count vars will be equal to what it would have been if all the gets and
- * puts were done to a single integer, even if some of the percpu integers
+ * percpu_count vars will be equal to what it would have been if all the gets
+ * and puts were done to a single integer, even if some of the percpu integers
  * overflow or underflow).
  *
  * The real trick to implementing percpu refcounts is shutdown. We can't detect
@@ -29,11 +29,12 @@
  * atomic_long_t can't hit 0 before we've added up all the percpu refs.
  */
 
-#define PCPU_COUNT_BIAS		(1LU << (BITS_PER_LONG - 1))
+#define PERCPU_COUNT_BIAS	(1LU << (BITS_PER_LONG - 1))
 
-static unsigned long __percpu *pcpu_count_ptr(struct percpu_ref *ref)
+static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
 {
-	return (unsigned long __percpu *)(ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
+	return (unsigned long __percpu *)
+		(ref->percpu_count_ptr & ~__PERCPU_REF_DEAD);
 }
 
 /**
@@ -51,10 +52,11 @@ static unsigned long __percpu *pcpu_count_ptr(struct percpu_ref *ref)
 int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 		    gfp_t gfp)
 {
-	atomic_long_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+	atomic_long_set(&ref->count, 1 + PERCPU_COUNT_BIAS);
 
-	ref->pcpu_count_ptr = (unsigned long)alloc_percpu_gfp(unsigned long, gfp);
-	if (!ref->pcpu_count_ptr)
+	ref->percpu_count_ptr =
+		(unsigned long)alloc_percpu_gfp(unsigned long, gfp);
+	if (!ref->percpu_count_ptr)
 		return -ENOMEM;
 
 	ref->release = release;
@@ -74,11 +76,11 @@ EXPORT_SYMBOL_GPL(percpu_ref_init);
  */
 void percpu_ref_exit(struct percpu_ref *ref)
 {
-	unsigned long __percpu *pcpu_count = pcpu_count_ptr(ref);
+	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
 
-	if (pcpu_count) {
-		free_percpu(pcpu_count);
-		ref->pcpu_count_ptr = PCPU_REF_DEAD;
+	if (percpu_count) {
+		free_percpu(percpu_count);
+		ref->percpu_count_ptr = __PERCPU_REF_DEAD;
 	}
 }
 EXPORT_SYMBOL_GPL(percpu_ref_exit);
@@ -86,14 +88,14 @@ EXPORT_SYMBOL_GPL(percpu_ref_exit);
 static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 {
 	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
-	unsigned long __percpu *pcpu_count = pcpu_count_ptr(ref);
+	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
 	unsigned long count = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		count += *per_cpu_ptr(pcpu_count, cpu);
+		count += *per_cpu_ptr(percpu_count, cpu);
 
-	pr_debug("global %ld pcpu %ld",
+	pr_debug("global %ld percpu %ld",
 		 atomic_long_read(&ref->count), (long)count);
 
 	/*
@@ -108,7 +110,7 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 	 * reaching 0 before we add the percpu counts. But doing it at the same
 	 * time is equivalent and saves us atomic operations:
 	 */
-	atomic_long_add((long)count - PCPU_COUNT_BIAS, &ref->count);
+	atomic_long_add((long)count - PERCPU_COUNT_BIAS, &ref->count);
 
 	WARN_ONCE(atomic_long_read(&ref->count) <= 0,
 		  "percpu ref (%pf) <= 0 (%ld) after killed",
@@ -143,10 +145,10 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill)
 {
-	WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
+	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD,
 		  "%s called more than once on %pf!", __func__, ref->release);
 
-	ref->pcpu_count_ptr |= PCPU_REF_DEAD;
+	ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
 	ref->confirm_kill = confirm_kill;
 
 	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
@@ -166,24 +168,24 @@ EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
  */
 void percpu_ref_reinit(struct percpu_ref *ref)
 {
-	unsigned long __percpu *pcpu_count = pcpu_count_ptr(ref);
+	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
 	int cpu;
 
-	BUG_ON(!pcpu_count);
+	BUG_ON(!percpu_count);
 	WARN_ON_ONCE(!percpu_ref_is_zero(ref));
 
-	atomic_long_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+	atomic_long_set(&ref->count, 1 + PERCPU_COUNT_BIAS);
 
 	/*
 	 * Restore per-cpu operation.  smp_store_release() is paired with
-	 * smp_read_barrier_depends() in __pcpu_ref_alive() and guarantees
-	 * that the zeroing is visible to all percpu accesses which can see
-	 * the following PCPU_REF_DEAD clearing.
+	 * smp_read_barrier_depends() in __percpu_ref_alive() and
+	 * guarantees that the zeroing is visible to all percpu accesses
+	 * which can see the following __PERCPU_REF_DEAD clearing.
 	 */
 	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(pcpu_count, cpu) = 0;
+		*per_cpu_ptr(percpu_count, cpu) = 0;
 
-	smp_store_release(&ref->pcpu_count_ptr,
-			  ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
+	smp_store_release(&ref->percpu_count_ptr,
+			  ref->percpu_count_ptr & ~__PERCPU_REF_DEAD);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_reinit);
-- 
cgit v1.2.3


From 9e804d1f58da1eca079f796347c1cf1d1df564e2 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:48 -0400
Subject: percpu_ref: rename things to prepare for decoupling percpu/atomic
 mode switch

percpu_ref will be restructured so that percpu/atomic mode switching
and reference killing are dedoupled.  In preparation, do the following
renames.

* percpu_ref->confirm_kill	-> percpu_ref->confirm_switch
* __PERCPU_REF_DEAD		-> __PERCPU_REF_ATOMIC
* __percpu_ref_alive()		-> __ref_is_percpu()

This patch is pure rename and doesn't introduce any functional
changes.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
---
 include/linux/percpu-refcount.h | 25 ++++++++++++++-----------
 lib/percpu-refcount.c           | 22 +++++++++++-----------
 2 files changed, 25 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 3d463a39e0f7..910e5f72055d 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -54,6 +54,11 @@
 struct percpu_ref;
 typedef void (percpu_ref_func_t)(struct percpu_ref *);
 
+/* flags set in the lower bits of percpu_ref->percpu_count_ptr */
+enum {
+	__PERCPU_REF_ATOMIC	= 1LU << 0,	/* operating in atomic mode */
+};
+
 struct percpu_ref {
 	atomic_long_t		count;
 	/*
@@ -62,7 +67,7 @@ struct percpu_ref {
 	 */
 	unsigned long		percpu_count_ptr;
 	percpu_ref_func_t	*release;
-	percpu_ref_func_t	*confirm_kill;
+	percpu_ref_func_t	*confirm_switch;
 	struct rcu_head		rcu;
 };
 
@@ -88,23 +93,21 @@ static inline void percpu_ref_kill(struct percpu_ref *ref)
 	return percpu_ref_kill_and_confirm(ref, NULL);
 }
 
-#define __PERCPU_REF_DEAD	1
-
 /*
  * Internal helper.  Don't use outside percpu-refcount proper.  The
  * function doesn't return the pointer and let the caller test it for NULL
  * because doing so forces the compiler to generate two conditional
  * branches as it can't assume that @ref->percpu_count is not NULL.
  */
-static inline bool __percpu_ref_alive(struct percpu_ref *ref,
-				      unsigned long __percpu **percpu_countp)
+static inline bool __ref_is_percpu(struct percpu_ref *ref,
+					  unsigned long __percpu **percpu_countp)
 {
 	unsigned long percpu_ptr = ACCESS_ONCE(ref->percpu_count_ptr);
 
 	/* paired with smp_store_release() in percpu_ref_reinit() */
 	smp_read_barrier_depends();
 
-	if (unlikely(percpu_ptr & __PERCPU_REF_DEAD))
+	if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC))
 		return false;
 
 	*percpu_countp = (unsigned long __percpu *)percpu_ptr;
@@ -125,7 +128,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
 
 	rcu_read_lock_sched();
 
-	if (__percpu_ref_alive(ref, &percpu_count))
+	if (__ref_is_percpu(ref, &percpu_count))
 		this_cpu_inc(*percpu_count);
 	else
 		atomic_long_inc(&ref->count);
@@ -149,7 +152,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 
 	rcu_read_lock_sched();
 
-	if (__percpu_ref_alive(ref, &percpu_count)) {
+	if (__ref_is_percpu(ref, &percpu_count)) {
 		this_cpu_inc(*percpu_count);
 		ret = true;
 	} else {
@@ -183,7 +186,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 
 	rcu_read_lock_sched();
 
-	if (__percpu_ref_alive(ref, &percpu_count)) {
+	if (__ref_is_percpu(ref, &percpu_count)) {
 		this_cpu_inc(*percpu_count);
 		ret = true;
 	}
@@ -208,7 +211,7 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
 
 	rcu_read_lock_sched();
 
-	if (__percpu_ref_alive(ref, &percpu_count))
+	if (__ref_is_percpu(ref, &percpu_count))
 		this_cpu_dec(*percpu_count);
 	else if (unlikely(atomic_long_dec_and_test(&ref->count)))
 		ref->release(ref);
@@ -228,7 +231,7 @@ static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
 {
 	unsigned long __percpu *percpu_count;
 
-	if (__percpu_ref_alive(ref, &percpu_count))
+	if (__ref_is_percpu(ref, &percpu_count))
 		return false;
 	return !atomic_long_read(&ref->count);
 }
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 5aea6b7356c7..7aef590c1ef8 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -34,7 +34,7 @@
 static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
 {
 	return (unsigned long __percpu *)
-		(ref->percpu_count_ptr & ~__PERCPU_REF_DEAD);
+		(ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC);
 }
 
 /**
@@ -80,7 +80,7 @@ void percpu_ref_exit(struct percpu_ref *ref)
 
 	if (percpu_count) {
 		free_percpu(percpu_count);
-		ref->percpu_count_ptr = __PERCPU_REF_DEAD;
+		ref->percpu_count_ptr = __PERCPU_REF_ATOMIC;
 	}
 }
 EXPORT_SYMBOL_GPL(percpu_ref_exit);
@@ -117,8 +117,8 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 		  ref->release, atomic_long_read(&ref->count));
 
 	/* @ref is viewed as dead on all CPUs, send out kill confirmation */
-	if (ref->confirm_kill)
-		ref->confirm_kill(ref);
+	if (ref->confirm_switch)
+		ref->confirm_switch(ref);
 
 	/*
 	 * Now we're in single atomic_long_t mode with a consistent
@@ -145,11 +145,11 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill)
 {
-	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD,
+	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC,
 		  "%s called more than once on %pf!", __func__, ref->release);
 
-	ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
-	ref->confirm_kill = confirm_kill;
+	ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
+	ref->confirm_switch = confirm_kill;
 
 	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
 }
@@ -178,14 +178,14 @@ void percpu_ref_reinit(struct percpu_ref *ref)
 
 	/*
 	 * Restore per-cpu operation.  smp_store_release() is paired with
-	 * smp_read_barrier_depends() in __percpu_ref_alive() and
-	 * guarantees that the zeroing is visible to all percpu accesses
-	 * which can see the following __PERCPU_REF_DEAD clearing.
+	 * smp_read_barrier_depends() in __ref_is_percpu() and guarantees
+	 * that the zeroing is visible to all percpu accesses which can see
+	 * the following __PERCPU_REF_ATOMIC clearing.
 	 */
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(percpu_count, cpu) = 0;
 
 	smp_store_release(&ref->percpu_count_ptr,
-			  ref->percpu_count_ptr & ~__PERCPU_REF_DEAD);
+			  ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_reinit);
-- 
cgit v1.2.3


From 27344a9017cdaff82a167827da3001a0918afdc3 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:49 -0400
Subject: percpu_ref: add PCPU_REF_DEAD

percpu_ref will be restructured so that percpu/atomic mode switching
and reference killing are dedoupled.  In preparation, add
PCPU_REF_DEAD and PCPU_REF_ATOMIC_DEAD which is OR of ATOMIC and DEAD.
For now, ATOMIC and DEAD are changed together and all PCPU_REF_ATOMIC
uses are converted to PCPU_REF_ATOMIC_DEAD without causing any
behavior changes.

percpu_ref_init() now specifies an explicit alignment when allocating
the percpu counters so that the pointer has enough unused low bits to
accomodate the flags.  Note that one flag was fine as min alignment
for percpu memory is 2 bytes but two flags are already too many for
the natural alignment of unsigned longs on archs like cris and m68k.

v2: The original patch had BUILD_BUG_ON() which triggers if unsigned
    long's alignment isn't enough to accomodate the flags, which
    triggered on cris and m64k.  percpu_ref_init() updated to specify
    the required alignment explicitly.  Reported by Fengguang.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: kbuild test robot <fengguang.wu@intel.com>
---
 include/linux/percpu-refcount.h |  6 +++++-
 lib/percpu-refcount.c           | 19 +++++++++++--------
 2 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 910e5f72055d..bd9483d390b4 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -57,6 +57,10 @@ typedef void (percpu_ref_func_t)(struct percpu_ref *);
 /* flags set in the lower bits of percpu_ref->percpu_count_ptr */
 enum {
 	__PERCPU_REF_ATOMIC	= 1LU << 0,	/* operating in atomic mode */
+	__PERCPU_REF_DEAD	= 1LU << 1,	/* (being) killed */
+	__PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD,
+
+	__PERCPU_REF_FLAG_BITS	= 2,
 };
 
 struct percpu_ref {
@@ -107,7 +111,7 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 	/* paired with smp_store_release() in percpu_ref_reinit() */
 	smp_read_barrier_depends();
 
-	if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC))
+	if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD))
 		return false;
 
 	*percpu_countp = (unsigned long __percpu *)percpu_ptr;
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 7aef590c1ef8..e2ff19f970cf 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -34,7 +34,7 @@
 static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
 {
 	return (unsigned long __percpu *)
-		(ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC);
+		(ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC_DEAD);
 }
 
 /**
@@ -52,10 +52,13 @@ static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
 int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 		    gfp_t gfp)
 {
+	size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS,
+			     __alignof__(unsigned long));
+
 	atomic_long_set(&ref->count, 1 + PERCPU_COUNT_BIAS);
 
-	ref->percpu_count_ptr =
-		(unsigned long)alloc_percpu_gfp(unsigned long, gfp);
+	ref->percpu_count_ptr = (unsigned long)
+		__alloc_percpu_gfp(sizeof(unsigned long), align, gfp);
 	if (!ref->percpu_count_ptr)
 		return -ENOMEM;
 
@@ -80,7 +83,7 @@ void percpu_ref_exit(struct percpu_ref *ref)
 
 	if (percpu_count) {
 		free_percpu(percpu_count);
-		ref->percpu_count_ptr = __PERCPU_REF_ATOMIC;
+		ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD;
 	}
 }
 EXPORT_SYMBOL_GPL(percpu_ref_exit);
@@ -145,10 +148,10 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill)
 {
-	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC,
+	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC_DEAD,
 		  "%s called more than once on %pf!", __func__, ref->release);
 
-	ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
+	ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC_DEAD;
 	ref->confirm_switch = confirm_kill;
 
 	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
@@ -180,12 +183,12 @@ void percpu_ref_reinit(struct percpu_ref *ref)
 	 * Restore per-cpu operation.  smp_store_release() is paired with
 	 * smp_read_barrier_depends() in __ref_is_percpu() and guarantees
 	 * that the zeroing is visible to all percpu accesses which can see
-	 * the following __PERCPU_REF_ATOMIC clearing.
+	 * the following __PERCPU_REF_ATOMIC_DEAD clearing.
 	 */
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(percpu_count, cpu) = 0;
 
 	smp_store_release(&ref->percpu_count_ptr,
-			  ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC);
+			  ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC_DEAD);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_reinit);
-- 
cgit v1.2.3


From 490c79a65708873228cf114cf00e32c204e4e907 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:49 -0400
Subject: percpu_ref: decouple switching to atomic mode and killing

percpu_ref has treated the dropping of the base reference and
switching to atomic mode as an integral operation; however, there's
nothing inherent tying the two together.

The use cases for percpu_ref have been expanding continuously.  While
the current init/kill/reinit/exit model can cover a lot, the coupling
of kill/reinit with atomic/percpu mode switching is turning out to be
too restrictive for use cases where many percpu_refs are created and
destroyed back-to-back with only some of them reaching extended
operation.  The coupling also makes implementing always-atomic debug
mode difficult.

This patch separates out atomic mode switching into
percpu_ref_switch_to_atomic() and reimplements
percpu_ref_kill_and_confirm() on top of it.

* The handling of __PERCPU_REF_ATOMIC and __PERCPU_REF_DEAD is now
  differentiated.  Among get/put operations, percpu_ref_tryget_live()
  is the only one which cares about DEAD.

* percpu_ref_switch_to_atomic() can be called multiple times on the
  same ref.  This means that multiple @confirm_switch may get queued
  up which we can't do reliably without extra memory area.  This is
  handled by making the later invocation synchronously wait for the
  completion of the previous one.  This isn't particularly desirable
  but such synchronous waits shouldn't happen in most cases.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
---
 include/linux/percpu-refcount.h |   8 ++-
 lib/percpu-refcount.c           | 141 +++++++++++++++++++++++++++++++---------
 2 files changed, 116 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index bd9483d390b4..d1252e1335e8 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -78,9 +78,11 @@ struct percpu_ref {
 int __must_check percpu_ref_init(struct percpu_ref *ref,
 				 percpu_ref_func_t *release, gfp_t gfp);
 void percpu_ref_exit(struct percpu_ref *ref);
+void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
+				 percpu_ref_func_t *confirm_switch);
+void percpu_ref_reinit(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
-void percpu_ref_reinit(struct percpu_ref *ref);
 
 /**
  * percpu_ref_kill - drop the initial ref
@@ -111,7 +113,7 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 	/* paired with smp_store_release() in percpu_ref_reinit() */
 	smp_read_barrier_depends();
 
-	if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD))
+	if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC))
 		return false;
 
 	*percpu_countp = (unsigned long __percpu *)percpu_ptr;
@@ -193,6 +195,8 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 	if (__ref_is_percpu(ref, &percpu_count)) {
 		this_cpu_inc(*percpu_count);
 		ret = true;
+	} else if (!(ACCESS_ONCE(ref->percpu_count_ptr) & __PERCPU_REF_DEAD)) {
+		ret = atomic_long_inc_not_zero(&ref->count);
 	}
 
 	rcu_read_unlock_sched();
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index e2ff19f970cf..6e0d14366c5d 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -1,6 +1,8 @@
 #define pr_fmt(fmt) "%s: " fmt "\n", __func__
 
 #include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
 #include <linux/percpu-refcount.h>
 
 /*
@@ -31,6 +33,8 @@
 
 #define PERCPU_COUNT_BIAS	(1LU << (BITS_PER_LONG - 1))
 
+static DECLARE_WAIT_QUEUE_HEAD(percpu_ref_switch_waitq);
+
 static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
 {
 	return (unsigned long __percpu *)
@@ -88,7 +92,19 @@ void percpu_ref_exit(struct percpu_ref *ref)
 }
 EXPORT_SYMBOL_GPL(percpu_ref_exit);
 
-static void percpu_ref_kill_rcu(struct rcu_head *rcu)
+static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu)
+{
+	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
+
+	ref->confirm_switch(ref);
+	ref->confirm_switch = NULL;
+	wake_up_all(&percpu_ref_switch_waitq);
+
+	/* drop ref from percpu_ref_switch_to_atomic() */
+	percpu_ref_put(ref);
+}
+
+static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 {
 	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
 	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
@@ -116,47 +132,79 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 	atomic_long_add((long)count - PERCPU_COUNT_BIAS, &ref->count);
 
 	WARN_ONCE(atomic_long_read(&ref->count) <= 0,
-		  "percpu ref (%pf) <= 0 (%ld) after killed",
+		  "percpu ref (%pf) <= 0 (%ld) after switching to atomic",
 		  ref->release, atomic_long_read(&ref->count));
 
-	/* @ref is viewed as dead on all CPUs, send out kill confirmation */
-	if (ref->confirm_switch)
-		ref->confirm_switch(ref);
+	/* @ref is viewed as dead on all CPUs, send out switch confirmation */
+	percpu_ref_call_confirm_rcu(rcu);
+}
 
-	/*
-	 * Now we're in single atomic_long_t mode with a consistent
-	 * refcount, so it's safe to drop our initial ref:
-	 */
-	percpu_ref_put(ref);
+static void percpu_ref_noop_confirm_switch(struct percpu_ref *ref)
+{
+}
+
+static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
+					  percpu_ref_func_t *confirm_switch)
+{
+	if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) {
+		/* switching from percpu to atomic */
+		ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
+
+		/*
+		 * Non-NULL ->confirm_switch is used to indicate that
+		 * switching is in progress.  Use noop one if unspecified.
+		 */
+		WARN_ON_ONCE(ref->confirm_switch);
+		ref->confirm_switch =
+			confirm_switch ?: percpu_ref_noop_confirm_switch;
+
+		percpu_ref_get(ref);	/* put after confirmation */
+		call_rcu_sched(&ref->rcu, percpu_ref_switch_to_atomic_rcu);
+	} else if (confirm_switch) {
+		/*
+		 * Somebody already set ATOMIC.  Switching may still be in
+		 * progress.  @confirm_switch must be invoked after the
+		 * switching is complete and a full sched RCU grace period
+		 * has passed.  Wait synchronously for the previous
+		 * switching and schedule @confirm_switch invocation.
+		 */
+		wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
+		ref->confirm_switch = confirm_switch;
+
+		percpu_ref_get(ref);	/* put after confirmation */
+		call_rcu_sched(&ref->rcu, percpu_ref_call_confirm_rcu);
+	}
 }
 
 /**
- * percpu_ref_kill_and_confirm - drop the initial ref and schedule confirmation
- * @ref: percpu_ref to kill
- * @confirm_kill: optional confirmation callback
+ * percpu_ref_switch_to_atomic - switch a percpu_ref to atomic mode
+ * @ref: percpu_ref to switch to atomic mode
+ * @confirm_switch: optional confirmation callback
  *
- * Equivalent to percpu_ref_kill() but also schedules kill confirmation if
- * @confirm_kill is not NULL.  @confirm_kill, which may not block, will be
- * called after @ref is seen as dead from all CPUs - all further
- * invocations of percpu_ref_tryget_live() will fail.  See
- * percpu_ref_tryget_live() for more details.
+ * There's no reason to use this function for the usual reference counting.
+ * Use percpu_ref_kill[_and_confirm]().
+ *
+ * Schedule switching of @ref to atomic mode.  All its percpu counts will
+ * be collected to the main atomic counter.  On completion, when all CPUs
+ * are guaraneed to be in atomic mode, @confirm_switch, which may not
+ * block, is invoked.  This function may be invoked concurrently with all
+ * the get/put operations and can safely be mixed with kill and reinit
+ * operations.
  *
- * Due to the way percpu_ref is implemented, @confirm_kill will be called
- * after at least one full RCU grace period has passed but this is an
- * implementation detail and callers must not depend on it.
+ * This function normally doesn't block and can be called from any context
+ * but it may block if @confirm_kill is specified and @ref is already in
+ * the process of switching to atomic mode.  In such cases, @confirm_switch
+ * will be invoked after the switching is complete.
+ *
+ * Due to the way percpu_ref is implemented, @confirm_switch will be called
+ * after at least one full sched RCU grace period has passed but this is an
+ * implementation detail and must not be depended upon.
  */
-void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
-				 percpu_ref_func_t *confirm_kill)
+void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
+				 percpu_ref_func_t *confirm_switch)
 {
-	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC_DEAD,
-		  "%s called more than once on %pf!", __func__, ref->release);
-
-	ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC_DEAD;
-	ref->confirm_switch = confirm_kill;
-
-	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
+	__percpu_ref_switch_to_atomic(ref, confirm_switch);
 }
-EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
 
 /**
  * percpu_ref_reinit - re-initialize a percpu refcount
@@ -192,3 +240,34 @@ void percpu_ref_reinit(struct percpu_ref *ref)
 			  ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC_DEAD);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_reinit);
+
+/**
+ * percpu_ref_kill_and_confirm - drop the initial ref and schedule confirmation
+ * @ref: percpu_ref to kill
+ * @confirm_kill: optional confirmation callback
+ *
+ * Equivalent to percpu_ref_kill() but also schedules kill confirmation if
+ * @confirm_kill is not NULL.  @confirm_kill, which may not block, will be
+ * called after @ref is seen as dead from all CPUs at which point all
+ * further invocations of percpu_ref_tryget_live() will fail.  See
+ * percpu_ref_tryget_live() for details.
+ *
+ * This function normally doesn't block and can be called from any context
+ * but it may block if @confirm_kill is specified and @ref is already in
+ * the process of switching to atomic mode by percpu_ref_switch_atomic().
+ *
+ * Due to the way percpu_ref is implemented, @confirm_switch will be called
+ * after at least one full sched RCU grace period has passed but this is an
+ * implementation detail and must not be depended upon.
+ */
+void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
+				 percpu_ref_func_t *confirm_kill)
+{
+	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD,
+		  "%s called more than once on %pf!", __func__, ref->release);
+
+	ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
+	__percpu_ref_switch_to_atomic(ref, confirm_kill);
+	percpu_ref_put(ref);
+}
+EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
-- 
cgit v1.2.3


From f47ad45784611297b699f3dffb6c7222b76afe64 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:49 -0400
Subject: percpu_ref: decouple switching to percpu mode and reinit

percpu_ref has treated the dropping of the base reference and
switching to atomic mode as an integral operation; however, there's
nothing inherent tying the two together.

The use cases for percpu_ref have been expanding continuously.  While
the current init/kill/reinit/exit model can cover a lot, the coupling
of kill/reinit with atomic/percpu mode switching is turning out to be
too restrictive for use cases where many percpu_refs are created and
destroyed back-to-back with only some of them reaching extended
operation.  The coupling also makes implementing always-atomic debug
mode difficult.

This patch separates out percpu mode switching into
percpu_ref_switch_to_percpu() and reimplements percpu_ref_reinit() on
top of it.

* DEAD still requires ATOMIC.  A dead ref can't be switched to percpu
  mode w/o going through reinit.

v2: __percpu_ref_switch_to_percpu() was missing static.  Fixed.
    Reported by Fengguang aka kbuild test robot.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: kbuild test robot <fengguang.wu@intel.com>
---
 include/linux/percpu-refcount.h |  3 +-
 lib/percpu-refcount.c           | 73 ++++++++++++++++++++++++++++++-----------
 2 files changed, 56 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index d1252e1335e8..cd7e20f0fe47 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -80,9 +80,10 @@ int __must_check percpu_ref_init(struct percpu_ref *ref,
 void percpu_ref_exit(struct percpu_ref *ref);
 void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_switch);
-void percpu_ref_reinit(struct percpu_ref *ref);
+void percpu_ref_switch_to_percpu(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
+void percpu_ref_reinit(struct percpu_ref *ref);
 
 /**
  * percpu_ref_kill - drop the initial ref
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 6e0d14366c5d..5a6d43baccc5 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -206,40 +206,54 @@ void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 	__percpu_ref_switch_to_atomic(ref, confirm_switch);
 }
 
-/**
- * percpu_ref_reinit - re-initialize a percpu refcount
- * @ref: perpcu_ref to re-initialize
- *
- * Re-initialize @ref so that it's in the same state as when it finished
- * percpu_ref_init().  @ref must have been initialized successfully, killed
- * and reached 0 but not exited.
- *
- * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while
- * this function is in progress.
- */
-void percpu_ref_reinit(struct percpu_ref *ref)
+static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 {
 	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
 	int cpu;
 
 	BUG_ON(!percpu_count);
-	WARN_ON_ONCE(!percpu_ref_is_zero(ref));
 
-	atomic_long_set(&ref->count, 1 + PERCPU_COUNT_BIAS);
+	if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC))
+		return;
+
+	wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
+
+	atomic_long_add(PERCPU_COUNT_BIAS, &ref->count);
 
 	/*
 	 * Restore per-cpu operation.  smp_store_release() is paired with
 	 * smp_read_barrier_depends() in __ref_is_percpu() and guarantees
 	 * that the zeroing is visible to all percpu accesses which can see
-	 * the following __PERCPU_REF_ATOMIC_DEAD clearing.
+	 * the following __PERCPU_REF_ATOMIC clearing.
 	 */
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(percpu_count, cpu) = 0;
 
 	smp_store_release(&ref->percpu_count_ptr,
-			  ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC_DEAD);
+			  ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC);
+}
+
+/**
+ * percpu_ref_switch_to_percpu - switch a percpu_ref to percpu mode
+ * @ref: percpu_ref to switch to percpu mode
+ *
+ * There's no reason to use this function for the usual reference counting.
+ * To re-use an expired ref, use percpu_ref_reinit().
+ *
+ * Switch @ref to percpu mode.  This function may be invoked concurrently
+ * with all the get/put operations and can safely be mixed with kill and
+ * reinit operations.
+ *
+ * This function normally doesn't block and can be called from any context
+ * but it may block if @ref is in the process of switching to atomic mode
+ * by percpu_ref_switch_atomic().
+ */
+void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
+{
+	/* a dying or dead ref can't be switched to percpu mode w/o reinit */
+	if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD))
+		__percpu_ref_switch_to_percpu(ref);
 }
-EXPORT_SYMBOL_GPL(percpu_ref_reinit);
 
 /**
  * percpu_ref_kill_and_confirm - drop the initial ref and schedule confirmation
@@ -253,8 +267,8 @@ EXPORT_SYMBOL_GPL(percpu_ref_reinit);
  * percpu_ref_tryget_live() for details.
  *
  * This function normally doesn't block and can be called from any context
- * but it may block if @confirm_kill is specified and @ref is already in
- * the process of switching to atomic mode by percpu_ref_switch_atomic().
+ * but it may block if @confirm_kill is specified and @ref is in the
+ * process of switching to atomic mode by percpu_ref_switch_atomic().
  *
  * Due to the way percpu_ref is implemented, @confirm_switch will be called
  * after at least one full sched RCU grace period has passed but this is an
@@ -271,3 +285,24 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 	percpu_ref_put(ref);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
+
+/**
+ * percpu_ref_reinit - re-initialize a percpu refcount
+ * @ref: perpcu_ref to re-initialize
+ *
+ * Re-initialize @ref so that it's in the same state as when it finished
+ * percpu_ref_init().  @ref must have been initialized successfully and
+ * reached 0 but not exited.
+ *
+ * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while
+ * this function is in progress.
+ */
+void percpu_ref_reinit(struct percpu_ref *ref)
+{
+	WARN_ON_ONCE(!percpu_ref_is_zero(ref));
+
+	ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD;
+	percpu_ref_get(ref);
+	__percpu_ref_switch_to_percpu(ref);
+}
+EXPORT_SYMBOL_GPL(percpu_ref_reinit);
-- 
cgit v1.2.3


From 2aad2a86f6685c10360ec8a5a55eb9ab7059cb72 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:50 -0400
Subject: percpu_ref: add PERCPU_REF_INIT_* flags

With the recent addition of percpu_ref_reinit(), percpu_ref now can be
used as a persistent switch which can be turned on and off repeatedly
where turning off maps to killing the ref and waiting for it to drain;
however, there currently isn't a way to initialize a percpu_ref in its
off (killed and drained) state, which can be inconvenient for certain
persistent switch use cases.

Similarly, percpu_ref_switch_to_atomic/percpu() allow dynamic
selection of operation mode; however, currently a newly initialized
percpu_ref is always in percpu mode making it impossible to avoid the
latency overhead of switching to atomic mode.

This patch adds @flags to percpu_ref_init() and implements the
following flags.

* PERCPU_REF_INIT_ATOMIC	: start ref in atomic mode
* PERCPU_REF_INIT_DEAD		: start ref killed and drained

These flags should be able to serve the above two use cases.

v2: target_core_tpg.c conversion was missing.  Fixed.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
---
 block/blk-mq.c                   |  2 +-
 drivers/target/target_core_tpg.c |  2 +-
 fs/aio.c                         |  4 ++--
 include/linux/percpu-refcount.h  | 18 +++++++++++++++++-
 kernel/cgroup.c                  |  7 ++++---
 lib/percpu-refcount.c            | 23 ++++++++++++++++++-----
 6 files changed, 43 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 44a78ae3f899..d85fe01c44ef 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1796,7 +1796,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 		goto err_hctxs;
 
 	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
-			    GFP_KERNEL))
+			    0, GFP_KERNEL))
 		goto err_map;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index 4ab6da338585..be783f717f19 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -819,7 +819,7 @@ int core_tpg_add_lun(
 {
 	int ret;
 
-	ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release,
+	ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release, 0,
 			      GFP_KERNEL);
 	if (ret < 0)
 		return ret;
diff --git a/fs/aio.c b/fs/aio.c
index 8d217ed04e6e..84a751005f5b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -661,10 +661,10 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 
 	INIT_LIST_HEAD(&ctx->active_reqs);
 
-	if (percpu_ref_init(&ctx->users, free_ioctx_users, GFP_KERNEL))
+	if (percpu_ref_init(&ctx->users, free_ioctx_users, 0, GFP_KERNEL))
 		goto err;
 
-	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs, GFP_KERNEL))
+	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs, 0, GFP_KERNEL))
 		goto err;
 
 	ctx->cpu = alloc_percpu(struct kioctx_cpu);
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index cd7e20f0fe47..b0293f268cd2 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -63,6 +63,21 @@ enum {
 	__PERCPU_REF_FLAG_BITS	= 2,
 };
 
+/* @flags for percpu_ref_init() */
+enum {
+	/*
+	 * Start w/ ref == 1 in atomic mode.  Can be switched to percpu
+	 * operation using percpu_ref_switch_to_percpu().
+	 */
+	PERCPU_REF_INIT_ATOMIC	= 1 << 0,
+
+	/*
+	 * Start dead w/ ref == 0 in atomic mode.  Must be revived with
+	 * percpu_ref_reinit() before used.  Implies INIT_ATOMIC.
+	 */
+	PERCPU_REF_INIT_DEAD	= 1 << 1,
+};
+
 struct percpu_ref {
 	atomic_long_t		count;
 	/*
@@ -76,7 +91,8 @@ struct percpu_ref {
 };
 
 int __must_check percpu_ref_init(struct percpu_ref *ref,
-				 percpu_ref_func_t *release, gfp_t gfp);
+				 percpu_ref_func_t *release, unsigned int flags,
+				 gfp_t gfp);
 void percpu_ref_exit(struct percpu_ref *ref);
 void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_switch);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a99d504294de..753df01a9831 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1634,7 +1634,8 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned int ss_mask)
 		goto out;
 	root_cgrp->id = ret;
 
-	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, GFP_KERNEL);
+	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0,
+			      GFP_KERNEL);
 	if (ret)
 		goto out;
 
@@ -4510,7 +4511,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
 
 	init_and_link_css(css, ss, cgrp);
 
-	err = percpu_ref_init(&css->refcnt, css_release, GFP_KERNEL);
+	err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL);
 	if (err)
 		goto err_free_css;
 
@@ -4583,7 +4584,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 		goto out_unlock;
 	}
 
-	ret = percpu_ref_init(&cgrp->self.refcnt, css_release, GFP_KERNEL);
+	ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL);
 	if (ret)
 		goto out_free_cgrp;
 
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 5a6d43baccc5..ed280fb1e5b5 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -45,27 +45,40 @@ static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
  * percpu_ref_init - initialize a percpu refcount
  * @ref: percpu_ref to initialize
  * @release: function which will be called when refcount hits 0
+ * @flags: PERCPU_REF_INIT_* flags
  * @gfp: allocation mask to use
  *
- * Initializes the refcount in single atomic counter mode with a refcount of 1;
- * analagous to atomic_long_set(ref, 1).
+ * Initializes @ref.  If @flags is zero, @ref starts in percpu mode with a
+ * refcount of 1; analagous to atomic_long_set(ref, 1).  See the
+ * definitions of PERCPU_REF_INIT_* flags for flag behaviors.
  *
  * Note that @release must not sleep - it may potentially be called from RCU
  * callback context by percpu_ref_kill().
  */
 int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
-		    gfp_t gfp)
+		    unsigned int flags, gfp_t gfp)
 {
 	size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS,
 			     __alignof__(unsigned long));
-
-	atomic_long_set(&ref->count, 1 + PERCPU_COUNT_BIAS);
+	unsigned long start_count = 0;
 
 	ref->percpu_count_ptr = (unsigned long)
 		__alloc_percpu_gfp(sizeof(unsigned long), align, gfp);
 	if (!ref->percpu_count_ptr)
 		return -ENOMEM;
 
+	if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD))
+		ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
+	else
+		start_count += PERCPU_COUNT_BIAS;
+
+	if (flags & PERCPU_REF_INIT_DEAD)
+		ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
+	else
+		start_count++;
+
+	atomic_long_set(&ref->count, start_count);
+
 	ref->release = release;
 	return 0;
 }
-- 
cgit v1.2.3


From 1cae13e75b7a7848c03138636d4eb8d8a5054dd5 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:50 -0400
Subject: percpu_ref: make INIT_ATOMIC and switch_to_atomic() sticky

Currently, a percpu_ref which is initialized with
PERPCU_REF_INIT_ATOMIC or switched to atomic mode via
switch_to_atomic() automatically reverts to percpu mode on the first
percpu_ref_reinit().  This makes the atomic mode difficult to use for
cases where a percpu_ref is used as a persistent on/off switch which
may be cycled multiple times.

This patch makes such atomic state sticky so that it survives through
kill/reinit cycles.  After this patch, atomic state is cleared only by
an explicit percpu_ref_switch_to_percpu() call.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
---
 include/linux/percpu-refcount.h |  5 ++++-
 lib/percpu-refcount.c           | 20 +++++++++++++++-----
 2 files changed, 19 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index b0293f268cd2..00c01fc6d88c 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -67,7 +67,9 @@ enum {
 enum {
 	/*
 	 * Start w/ ref == 1 in atomic mode.  Can be switched to percpu
-	 * operation using percpu_ref_switch_to_percpu().
+	 * operation using percpu_ref_switch_to_percpu().  If initialized
+	 * with this flag, the ref will stay in atomic mode until
+	 * percpu_ref_switch_to_percpu() is invoked on it.
 	 */
 	PERCPU_REF_INIT_ATOMIC	= 1 << 0,
 
@@ -87,6 +89,7 @@ struct percpu_ref {
 	unsigned long		percpu_count_ptr;
 	percpu_ref_func_t	*release;
 	percpu_ref_func_t	*confirm_switch;
+	bool			force_atomic:1;
 	struct rcu_head		rcu;
 };
 
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index ed280fb1e5b5..6111bcb28376 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -67,6 +67,8 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 	if (!ref->percpu_count_ptr)
 		return -ENOMEM;
 
+	ref->force_atomic = flags & PERCPU_REF_INIT_ATOMIC;
+
 	if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD))
 		ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
 	else
@@ -202,7 +204,8 @@ static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
  * are guaraneed to be in atomic mode, @confirm_switch, which may not
  * block, is invoked.  This function may be invoked concurrently with all
  * the get/put operations and can safely be mixed with kill and reinit
- * operations.
+ * operations.  Note that @ref will stay in atomic mode across kill/reinit
+ * cycles until percpu_ref_switch_to_percpu() is called.
  *
  * This function normally doesn't block and can be called from any context
  * but it may block if @confirm_kill is specified and @ref is already in
@@ -216,6 +219,7 @@ static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_switch)
 {
+	ref->force_atomic = true;
 	__percpu_ref_switch_to_atomic(ref, confirm_switch);
 }
 
@@ -255,7 +259,10 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
  *
  * Switch @ref to percpu mode.  This function may be invoked concurrently
  * with all the get/put operations and can safely be mixed with kill and
- * reinit operations.
+ * reinit operations.  This function reverses the sticky atomic state set
+ * by PERCPU_REF_INIT_ATOMIC or percpu_ref_switch_to_atomic().  If @ref is
+ * dying or dead, the actual switching takes place on the following
+ * percpu_ref_reinit().
  *
  * This function normally doesn't block and can be called from any context
  * but it may block if @ref is in the process of switching to atomic mode
@@ -263,6 +270,8 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
  */
 void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 {
+	ref->force_atomic = false;
+
 	/* a dying or dead ref can't be switched to percpu mode w/o reinit */
 	if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD))
 		__percpu_ref_switch_to_percpu(ref);
@@ -304,8 +313,8 @@ EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
  * @ref: perpcu_ref to re-initialize
  *
  * Re-initialize @ref so that it's in the same state as when it finished
- * percpu_ref_init().  @ref must have been initialized successfully and
- * reached 0 but not exited.
+ * percpu_ref_init() ignoring %PERCPU_REF_INIT_DEAD.  @ref must have been
+ * initialized successfully and reached 0 but not exited.
  *
  * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while
  * this function is in progress.
@@ -316,6 +325,7 @@ void percpu_ref_reinit(struct percpu_ref *ref)
 
 	ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD;
 	percpu_ref_get(ref);
-	__percpu_ref_switch_to_percpu(ref);
+	if (!ref->force_atomic)
+		__percpu_ref_switch_to_percpu(ref);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_reinit);
-- 
cgit v1.2.3


From 17497acbdce9506fd6a75115dee4ab80c3cc5ee5 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Sep 2014 13:31:50 -0400
Subject: blk-mq, percpu_ref: start q->mq_usage_counter in atomic mode

blk-mq uses percpu_ref for its usage counter which tracks the number
of in-flight commands and used to synchronously drain the queue on
freeze.  percpu_ref shutdown takes measureable wallclock time as it
involves a sched RCU grace period.  This means that draining a blk-mq
takes measureable wallclock time.  One would think that this shouldn't
matter as queue shutdown should be a rare event which takes place
asynchronously w.r.t. userland.

Unfortunately, SCSI probing involves synchronously setting up and then
tearing down a lot of request_queues back-to-back for non-existent
LUNs.  This means that SCSI probing may take above ten seconds when
scsi-mq is used.

  [    0.949892] scsi host0: Virtio SCSI HBA
  [    1.007864] scsi 0:0:0:0: Direct-Access     QEMU     QEMU HARDDISK    1.1. PQ: 0 ANSI: 5
  [    1.021299] scsi 0:0:1:0: Direct-Access     QEMU     QEMU HARDDISK    1.1. PQ: 0 ANSI: 5
  [    1.520356] tsc: Refined TSC clocksource calibration: 2491.910 MHz

  <stall>

  [   16.186549] sd 0:0:0:0: Attached scsi generic sg0 type 0
  [   16.190478] sd 0:0:1:0: Attached scsi generic sg1 type 0
  [   16.194099] osd: LOADED open-osd 0.2.1
  [   16.203202] sd 0:0:0:0: [sda] 31457280 512-byte logical blocks: (16.1 GB/15.0 GiB)
  [   16.208478] sd 0:0:0:0: [sda] Write Protect is off
  [   16.211439] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
  [   16.218771] sd 0:0:1:0: [sdb] 31457280 512-byte logical blocks: (16.1 GB/15.0 GiB)
  [   16.223264] sd 0:0:1:0: [sdb] Write Protect is off
  [   16.225682] sd 0:0:1:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

This is also the reason why request_queues start in bypass mode which
is ended on blk_register_queue() as shutting down a fully functional
queue also involves a RCU grace period and the queues for non-existent
SCSI devices never reach registration.

blk-mq basically needs to do the same thing - start the mq in a
degraded mode which is faster to shut down and then make it fully
functional only after the queue reaches registration.  percpu_ref
recently grew facilities to force atomic operation until explicitly
switched to percpu mode, which can be used for this purpose.  This
patch makes blk-mq initialize q->mq_usage_counter in atomic mode and
switch it to percpu mode only once blk_register_queue() is reached.

Note that this issue was previously worked around by 0a30288da1ae
("blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during
probe") for v3.17.  The temp fix was reverted in preparation of adding
persistent atomic mode to percpu_ref by 9eca80461a45 ("Revert "blk-mq,
percpu_ref: implement a kludge for SCSI blk-mq stall during probe"").
This patch and the prerequisite percpu_ref changes will be merged
during v3.18 devel cycle.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Christoph Hellwig <hch@infradead.org>
Link: http://lkml.kernel.org/g/20140919113815.GA10791@lst.de
Fixes: add703fda981 ("blk-mq: use percpu_ref for mq usage count")
Reviewed-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
---
 block/blk-mq-sysfs.c   |  6 ++++++
 block/blk-mq.c         |  6 +++++-
 block/blk-sysfs.c      | 11 +++++++++--
 include/linux/blk-mq.h |  1 +
 4 files changed, 21 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index ed5217867555..371d8800b48a 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -402,6 +402,12 @@ static void blk_mq_sysfs_init(struct request_queue *q)
 	}
 }
 
+/* see blk_register_queue() */
+void blk_mq_finish_init(struct request_queue *q)
+{
+	percpu_ref_switch_to_percpu(&q->mq_usage_counter);
+}
+
 int blk_mq_register_disk(struct gendisk *disk)
 {
 	struct device *dev = disk_to_dev(disk);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index d85fe01c44ef..38f4a165640d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1795,8 +1795,12 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	if (!q)
 		goto err_hctxs;
 
+	/*
+	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
+	 * See blk_register_queue() for details.
+	 */
 	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
-			    0, GFP_KERNEL))
+			    PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
 		goto err_map;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 17f5c84ce7bf..521ae9089c50 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -551,12 +551,19 @@ int blk_register_queue(struct gendisk *disk)
 		return -ENXIO;
 
 	/*
-	 * Initialization must be complete by now.  Finish the initial
-	 * bypass from queue allocation.
+	 * SCSI probing may synchronously create and destroy a lot of
+	 * request_queues for non-existent devices.  Shutting down a fully
+	 * functional queue takes measureable wallclock time as RCU grace
+	 * periods are involved.  To avoid excessive latency in these
+	 * cases, a request_queue starts out in a degraded mode which is
+	 * faster to shut down and is made fully functional here as
+	 * request_queues for non-existent devices never get registered.
 	 */
 	if (!blk_queue_init_done(q)) {
 		queue_flag_set_unlocked(QUEUE_FLAG_INIT_DONE, q);
 		blk_queue_bypass_end(q);
+		if (q->mq_ops)
+			blk_mq_finish_init(q);
 	}
 
 	ret = blk_trace_init_sysfs(dev);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a1e31f274fcd..c13a0c09faea 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -140,6 +140,7 @@ enum {
 };
 
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+void blk_mq_finish_init(struct request_queue *q);
 int blk_mq_register_disk(struct gendisk *);
 void blk_mq_unregister_disk(struct gendisk *);
 
-- 
cgit v1.2.3


From 94e57fea62020dbf6e5d0093eabcd28366e86044 Mon Sep 17 00:00:00 2001
From: Francesco Ruggeri <fruggeri@arista.com>
Date: Wed, 24 Sep 2014 10:12:41 -0700
Subject: PCI: Move PCI_VENDOR_ID_VMWARE to pci_ids.h

Move PCI_VENDOR_ID_VMWARE from device-specific files to pci_ids.h.
It is useful to always have access to it, especially when accessing
subsystem_vendor_id on emulated devices.

[bhelgaas: keep pci_ids.h sorted and use lower-case hex]
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/gpu/drm/vmwgfx/svga_reg.h  | 1 -
 drivers/misc/vmw_vmci/vmci_guest.c | 1 -
 drivers/net/vmxnet3/vmxnet3_int.h  | 1 -
 drivers/scsi/vmw_pvscsi.h          | 1 -
 include/linux/pci_ids.h            | 2 ++
 5 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/vmwgfx/svga_reg.h b/drivers/gpu/drm/vmwgfx/svga_reg.h
index 11323dd5196f..e4259c2c1acc 100644
--- a/drivers/gpu/drm/vmwgfx/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/svga_reg.h
@@ -35,7 +35,6 @@
 /*
  * PCI device IDs.
  */
-#define PCI_VENDOR_ID_VMWARE            0x15AD
 #define PCI_DEVICE_ID_VMWARE_SVGA2      0x0405
 
 /*
diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c
index 248399a881af..189b32519748 100644
--- a/drivers/misc/vmw_vmci/vmci_guest.c
+++ b/drivers/misc/vmw_vmci/vmci_guest.c
@@ -35,7 +35,6 @@
 #include "vmci_driver.h"
 #include "vmci_event.h"
 
-#define PCI_VENDOR_ID_VMWARE		0x15AD
 #define PCI_DEVICE_ID_VMWARE_VMCI	0x0740
 
 #define VMCI_UTIL_NUM_RESOURCES 1
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 29ee77f2c97f..c388ef509d66 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -117,7 +117,6 @@ enum {
 /*
  * PCI vendor and device IDs.
  */
-#define PCI_VENDOR_ID_VMWARE            0x15AD
 #define PCI_DEVICE_ID_VMWARE_VMXNET3    0x07B0
 #define MAX_ETHERNET_CARDS		10
 #define MAX_PCI_PASSTHRU_DEVICE		6
diff --git a/drivers/scsi/vmw_pvscsi.h b/drivers/scsi/vmw_pvscsi.h
index ce4588851274..ee16f0c5c47d 100644
--- a/drivers/scsi/vmw_pvscsi.h
+++ b/drivers/scsi/vmw_pvscsi.h
@@ -32,7 +32,6 @@
 
 #define MASK(n)        ((1 << (n)) - 1)        /* make an n-bit mask */
 
-#define PCI_VENDOR_ID_VMWARE		0x15AD
 #define PCI_DEVICE_ID_VMWARE_PVSCSI	0x07C0
 
 /*
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 6ed0bb73a864..da9e6f753196 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2245,6 +2245,8 @@
 #define PCI_VENDOR_ID_MORETON		0x15aa
 #define PCI_DEVICE_ID_RASTEL_2PORT	0x2000
 
+#define PCI_VENDOR_ID_VMWARE		0x15ad
+
 #define PCI_VENDOR_ID_ZOLTRIX		0x15b0
 #define PCI_DEVICE_ID_ZOLTRIX_2BD0	0x2bd0
 
-- 
cgit v1.2.3


From b2fc3f3c6d397d434174147eca3db1ec778195ce Mon Sep 17 00:00:00 2001
From: Olof Johansson <olof@lixom.net>
Date: Wed, 24 Sep 2014 11:42:38 -0700
Subject: drivers/soc: ti: fix build break with modules

Fixes below build break by not switching to stubs when the driver is a module:

drivers/soc/ti/knav_dma.c:418:7: error: redefinition of 'knav_dma_open_channel'
 void *knav_dma_open_channel(struct device *dev, const char *name,
       ^
In file included from drivers/soc/ti/knav_dma.c:26:0:
include/linux/soc/ti/knav_dma.h:165:21: note: previous definition of 'knav_dma_open_channel' was here
 static inline void *knav_dma_open_channel(struct device *dev, const char *name,
                     ^

Cc: Santosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
---
 include/linux/soc/ti/knav_dma.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h
index e864a3eb9ac4..dad035c16d94 100644
--- a/include/linux/soc/ti/knav_dma.h
+++ b/include/linux/soc/ti/knav_dma.h
@@ -157,7 +157,7 @@ struct knav_dma_desc {
 	u32	pad[4];
 } ____cacheline_aligned;
 
-#ifdef CONFIG_KEYSTONE_NAVIGATOR_DMA
+#if IS_ENABLED(CONFIG_KEYSTONE_NAVIGATOR_DMA)
 void *knav_dma_open_channel(struct device *dev, const char *name,
 				struct knav_dma_cfg *config);
 void knav_dma_close_channel(void *channel);
-- 
cgit v1.2.3


From a2b86f772227bcaf962c8b134f8d187046ac5f0e Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Thu, 25 Sep 2014 09:40:17 +0800
Subject: sched: fix confusing PFA_NO_NEW_PRIVS constant

Commit 1d4457f99928 ("sched: move no_new_privs into new atomic flags")
defined PFA_NO_NEW_PRIVS as hexadecimal value, but it is confusing
because it is used as bit number. Redefine it as decimal bit number.

Note this changes the bit position of PFA_NOW_NEW_PRIVS from 1 to 0.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Kees Cook <keescook@chromium.org>
[ lizf: slightly modified subject and changelog ]
Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/sched.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c2c885ee52b..45577650f629 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1957,7 +1957,7 @@ static inline void memalloc_noio_restore(unsigned int flags)
 }
 
 /* Per-process atomic flags. */
-#define PFA_NO_NEW_PRIVS 0x00000001	/* May not gain new privileges. */
+#define PFA_NO_NEW_PRIVS 0	/* May not gain new privileges. */
 
 static inline bool task_no_new_privs(struct task_struct *p)
 {
-- 
cgit v1.2.3


From e0e5070b20e01f0321f97db4e4e174f3f6b49e50 Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Thu, 25 Sep 2014 09:40:40 +0800
Subject: sched: add macros to define bitops for task atomic flags

This will simplify code when we add new flags.

v3:
- Kees pointed out that no_new_privs should never be cleared, so we
shouldn't define task_clear_no_new_privs(). we define 3 macros instead
of a single one.

v2:
- updated scripts/tags.sh, suggested by Peter

Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/sched.h | 21 ++++++++++++---------
 scripts/tags.sh       |  6 ++++++
 2 files changed, 18 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 45577650f629..5630763956d9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1959,15 +1959,18 @@ static inline void memalloc_noio_restore(unsigned int flags)
 /* Per-process atomic flags. */
 #define PFA_NO_NEW_PRIVS 0	/* May not gain new privileges. */
 
-static inline bool task_no_new_privs(struct task_struct *p)
-{
-	return test_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
-}
-
-static inline void task_set_no_new_privs(struct task_struct *p)
-{
-	set_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
-}
+#define TASK_PFA_TEST(name, func)					\
+	static inline bool task_##func(struct task_struct *p)		\
+	{ return test_bit(PFA_##name, &p->atomic_flags); }
+#define TASK_PFA_SET(name, func)					\
+	static inline void task_set_##func(struct task_struct *p)	\
+	{ set_bit(PFA_##name, &p->atomic_flags); }
+#define TASK_PFA_CLEAR(name, func)					\
+	static inline void task_clear_##func(struct task_struct *p)	\
+	{ clear_bit(PFA_##name, &p->atomic_flags); }
+
+TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs)
+TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs)
 
 /*
  * task->jobctl flags
diff --git a/scripts/tags.sh b/scripts/tags.sh
index cbfd269a6011..293828bfd4ac 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -197,6 +197,9 @@ exuberant()
 	--regex-c++='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/'		\
 	--regex-c++='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/'	\
 	--regex-c++='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \
+	--regex-c++='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/'	\
+	--regex-c++='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/'	\
+	--regex-c++='/TASK_PFA_CLEAR\([^,]*,\s*([^)]*)\)/task_clear_\1/'\
 	--regex-c='/PCI_OP_READ\((\w*).*[1-4]\)/pci_bus_read_config_\1/' \
 	--regex-c='/PCI_OP_WRITE\((\w*).*[1-4]\)/pci_bus_write_config_\1/' \
 	--regex-c='/DEFINE_(MUTEX|SEMAPHORE|SPINLOCK)\((\w*)/\2/v/'	\
@@ -260,6 +263,9 @@ emacs()
 	--regex='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/'	\
 	--regex='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/'	\
 	--regex='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \
+	--regex='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/'		\
+	--regex='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/'	\
+	--regex='/TASK_PFA_CLEAR\([^,]*,\s*([^)]*)\)/task_clear_\1/'	\
 	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'		\
 	--regex='/PCI_OP_READ(\([a-z]*[a-z]\).*[1-4])/pci_bus_read_config_\1/' \
 	--regex='/PCI_OP_WRITE(\([a-z]*[a-z]\).*[1-4])/pci_bus_write_config_\1/'\
-- 
cgit v1.2.3


From 2ad654bc5e2b211e92f66da1d819e47d79a866f0 Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Thu, 25 Sep 2014 09:41:02 +0800
Subject: cpuset: PF_SPREAD_PAGE and PF_SPREAD_SLAB should be atomic flags

When we change cpuset.memory_spread_{page,slab}, cpuset will flip
PF_SPREAD_{PAGE,SLAB} bit of tsk->flags for each task in that cpuset.
This should be done using atomic bitops, but currently we don't,
which is broken.

Tetsuo reported a hard-to-reproduce kernel crash on RHEL6, which happened
when one thread tried to clear PF_USED_MATH while at the same time another
thread tried to flip PF_SPREAD_PAGE/PF_SPREAD_SLAB. They both operate on
the same task.

Here's the full report:
https://lkml.org/lkml/2014/9/19/230

To fix this, we make PF_SPREAD_PAGE and PF_SPREAD_SLAB atomic flags.

v4:
- updated mm/slab.c. (Fengguang Wu)
- updated Documentation.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miao Xie <miaox@cn.fujitsu.com>
Cc: Kees Cook <keescook@chromium.org>
Fixes: 950592f7b991 ("cpusets: update tasks' page/slab spread flags in time")
Cc: <stable@vger.kernel.org> # 2.6.31+
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 Documentation/cgroups/cpusets.txt |  6 +++---
 include/linux/cpuset.h            |  4 ++--
 include/linux/sched.h             | 13 +++++++++++--
 kernel/cpuset.c                   |  9 +++++----
 mm/slab.c                         |  4 ++--
 5 files changed, 23 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 7740038d82bc..3c94ff3f9693 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -345,14 +345,14 @@ the named feature on.
 The implementation is simple.
 
 Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag
-PF_SPREAD_PAGE for each task that is in that cpuset or subsequently
+PFA_SPREAD_PAGE for each task that is in that cpuset or subsequently
 joins that cpuset.  The page allocation calls for the page cache
-is modified to perform an inline check for this PF_SPREAD_PAGE task
+is modified to perform an inline check for this PFA_SPREAD_PAGE task
 flag, and if set, a call to a new routine cpuset_mem_spread_node()
 returns the node to prefer for the allocation.
 
 Similarly, setting 'cpuset.memory_spread_slab' turns on the flag
-PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
+PFA_SPREAD_SLAB, and appropriately marked slab caches will allocate
 pages from the node returned by cpuset_mem_spread_node().
 
 The cpuset_mem_spread_node() routine is also simple.  It uses the
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index ade2390ffe92..6e39c9bb0dae 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -93,12 +93,12 @@ extern int cpuset_slab_spread_node(void);
 
 static inline int cpuset_do_page_mem_spread(void)
 {
-	return current->flags & PF_SPREAD_PAGE;
+	return task_spread_page(current);
 }
 
 static inline int cpuset_do_slab_mem_spread(void)
 {
-	return current->flags & PF_SPREAD_SLAB;
+	return task_spread_slab(current);
 }
 
 extern int current_cpuset_is_being_rebound(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5630763956d9..7b1cafefb05e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1903,8 +1903,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_KTHREAD	0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE	0x00400000	/* randomize virtual address space */
 #define PF_SWAPWRITE	0x00800000	/* Allowed to write to swap */
-#define PF_SPREAD_PAGE	0x01000000	/* Spread page cache over cpuset */
-#define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
 #define PF_NO_SETAFFINITY 0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
@@ -1958,6 +1956,9 @@ static inline void memalloc_noio_restore(unsigned int flags)
 
 /* Per-process atomic flags. */
 #define PFA_NO_NEW_PRIVS 0	/* May not gain new privileges. */
+#define PFA_SPREAD_PAGE  1      /* Spread page cache over cpuset */
+#define PFA_SPREAD_SLAB  2      /* Spread some slab caches over cpuset */
+
 
 #define TASK_PFA_TEST(name, func)					\
 	static inline bool task_##func(struct task_struct *p)		\
@@ -1972,6 +1973,14 @@ static inline void memalloc_noio_restore(unsigned int flags)
 TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs)
 TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs)
 
+TASK_PFA_TEST(SPREAD_PAGE, spread_page)
+TASK_PFA_SET(SPREAD_PAGE, spread_page)
+TASK_PFA_CLEAR(SPREAD_PAGE, spread_page)
+
+TASK_PFA_TEST(SPREAD_SLAB, spread_slab)
+TASK_PFA_SET(SPREAD_SLAB, spread_slab)
+TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
+
 /*
  * task->jobctl flags
  */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 22874d7cf2c0..52cb04c993b7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -365,13 +365,14 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs,
 					struct task_struct *tsk)
 {
 	if (is_spread_page(cs))
-		tsk->flags |= PF_SPREAD_PAGE;
+		task_set_spread_page(tsk);
 	else
-		tsk->flags &= ~PF_SPREAD_PAGE;
+		task_clear_spread_page(tsk);
+
 	if (is_spread_slab(cs))
-		tsk->flags |= PF_SPREAD_SLAB;
+		task_set_spread_slab(tsk);
 	else
-		tsk->flags &= ~PF_SPREAD_SLAB;
+		task_clear_spread_slab(tsk);
 }
 
 /*
diff --git a/mm/slab.c b/mm/slab.c
index a467b308c682..881951e67f12 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2994,7 +2994,7 @@ out:
 
 #ifdef CONFIG_NUMA
 /*
- * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set.
+ * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set.
  *
  * If we are in_interrupt, then process context, including cpusets and
  * mempolicy, may not apply and should not be used for allocation policy.
@@ -3226,7 +3226,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags)
 {
 	void *objp;
 
-	if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) {
+	if (current->mempolicy || cpuset_do_slab_mem_spread()) {
 		objp = alternate_node_alloc(cache, flags);
 		if (objp)
 			goto out;
-- 
cgit v1.2.3


From a743419f420a64d442280845c0377a915b76644f Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Tue, 23 Sep 2014 12:26:19 -0400
Subject: SUNRPC: Don't wake tasks during connection abort

When aborting a connection to preserve source ports, don't wake the task in
xs_error_report.  This allows tasks with RPC_TASK_SOFTCONN to succeed if the
connection needs to be re-established since it preserves the task's status
instead of setting it to the status of the aborting kernel_connect().

This may also avoid a potential conflict on the socket's lock.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Cc: stable@vger.kernel.org # 3.14+
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/sunrpc/xprt.h | 1 +
 net/sunrpc/xprtsock.c       | 4 ++++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index fcbfe8783243..cf391eef2e6d 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -357,6 +357,7 @@ int			xs_swapper(struct rpc_xprt *xprt, int enable);
 #define XPRT_CONNECTION_ABORT	(7)
 #define XPRT_CONNECTION_CLOSE	(8)
 #define XPRT_CONGESTED		(9)
+#define XPRT_CONNECTION_REUSE	(10)
 
 static inline void xprt_set_connected(struct rpc_xprt *xprt)
 {
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 7ed47b4943da..bffba4e4bfc6 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -845,6 +845,8 @@ static void xs_error_report(struct sock *sk)
 	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
 			xprt, -err);
 	trace_rpc_socket_error(xprt, sk->sk_socket, err);
+	if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state))
+		goto out;
 	xprt_wake_pending_tasks(xprt, err);
  out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -2261,7 +2263,9 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 		abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
 				&xprt->state);
 		/* "close" the socket, preserving the local port */
+		set_bit(XPRT_CONNECTION_REUSE, &xprt->state);
 		xs_tcp_reuse_connection(transport);
+		clear_bit(XPRT_CONNECTION_REUSE, &xprt->state);
 
 		if (abort_and_exit)
 			goto out_eagain;
-- 
cgit v1.2.3


From 8478eaa16e701ecfe054b62ec764bc1291b79e19 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Thu, 18 Sep 2014 16:09:27 +1000
Subject: NFSv4: use exponential retry on NFS4ERR_DELAY for async requests.

Currently asynchronous NFSv4 request will be retried with
exponential timeout (from 1/10 to 15 seconds), but async
requests will always use a 15second retry.

Some "async" requests are really synchronous though.  The
async mechanism is used to allow the request to continue if
the requesting process is killed.
In those cases, an exponential retry is appropriate.

For example, if two different clients both open a file and
get a READ delegation, and one client then unlinks the file
(while still holding an open file descriptor), that unlink
will used the "silly-rename" handling which is async.
The first rename will result in NFS4ERR_DELAY while the
delegation is reclaimed from the other client.  The rename
will not be retried for 15 seconds, causing an unlink to take
15 seconds rather than 100msec.

This patch only added exponential timeout for async unlink and
async rename.  Other async calls, such as 'close' are sometimes
waited for so they might benefit from exponential timeout too.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/nfs4proc.c       | 65 ++++++++++++++++++++++++++++++++-----------------
 include/linux/nfs_xdr.h |  2 ++
 2 files changed, 44 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 288be08bda95..45bce9ed6791 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -77,7 +77,7 @@ struct nfs4_opendata;
 static int _nfs4_proc_open(struct nfs4_opendata *data);
 static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
 static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
-static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *);
+static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *, long *);
 static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
 static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label);
 static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label);
@@ -314,20 +314,30 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
 	kunmap_atomic(start);
 }
 
+static long nfs4_update_delay(long *timeout)
+{
+	long ret;
+	if (!timeout)
+		return NFS4_POLL_RETRY_MAX;
+	if (*timeout <= 0)
+		*timeout = NFS4_POLL_RETRY_MIN;
+	if (*timeout > NFS4_POLL_RETRY_MAX)
+		*timeout = NFS4_POLL_RETRY_MAX;
+	ret = *timeout;
+	*timeout <<= 1;
+	return ret;
+}
+
 static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
 {
 	int res = 0;
 
 	might_sleep();
 
-	if (*timeout <= 0)
-		*timeout = NFS4_POLL_RETRY_MIN;
-	if (*timeout > NFS4_POLL_RETRY_MAX)
-		*timeout = NFS4_POLL_RETRY_MAX;
-	freezable_schedule_timeout_killable_unsafe(*timeout);
+	freezable_schedule_timeout_killable_unsafe(
+		nfs4_update_delay(timeout));
 	if (fatal_signal_pending(current))
 		res = -ERESTARTSYS;
-	*timeout <<= 1;
 	return res;
 }
 
@@ -2583,7 +2593,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			if (calldata->arg.fmode == 0)
 				break;
 		default:
-			if (nfs4_async_handle_error(task, server, state) == -EAGAIN) {
+			if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) {
 				rpc_restart_call_prepare(task);
 				goto out_release;
 			}
@@ -3572,7 +3582,8 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 
 	if (!nfs4_sequence_done(task, &res->seq_res))
 		return 0;
-	if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
+	if (nfs4_async_handle_error(task, res->server, NULL,
+				    &data->timeout) == -EAGAIN)
 		return 0;
 	update_changeattr(dir, &res->cinfo);
 	return 1;
@@ -3605,7 +3616,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 
 	if (!nfs4_sequence_done(task, &res->seq_res))
 		return 0;
-	if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
+	if (nfs4_async_handle_error(task, res->server, NULL, &data->timeout) == -EAGAIN)
 		return 0;
 
 	update_changeattr(old_dir, &res->old_cinfo);
@@ -4109,7 +4120,8 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr)
 
 	trace_nfs4_read(hdr, task->tk_status);
 	if (nfs4_async_handle_error(task, server,
-				    hdr->args.context->state) == -EAGAIN) {
+				    hdr->args.context->state,
+				    NULL) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
@@ -4177,10 +4189,11 @@ static int nfs4_write_done_cb(struct rpc_task *task,
 			      struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
-	
+
 	trace_nfs4_write(hdr, task->tk_status);
 	if (nfs4_async_handle_error(task, NFS_SERVER(inode),
-				    hdr->args.context->state) == -EAGAIN) {
+				    hdr->args.context->state,
+				    NULL) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
@@ -4260,7 +4273,8 @@ static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *da
 	struct inode *inode = data->inode;
 
 	trace_nfs4_commit(data, task->tk_status);
-	if (nfs4_async_handle_error(task, NFS_SERVER(inode), NULL) == -EAGAIN) {
+	if (nfs4_async_handle_error(task, NFS_SERVER(inode),
+				    NULL, NULL) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
@@ -4813,7 +4827,8 @@ out:
 
 
 static int
-nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, struct nfs4_state *state)
+nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
+			struct nfs4_state *state, long *timeout)
 {
 	struct nfs_client *clp = server->nfs_client;
 
@@ -4863,6 +4878,8 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 #endif /* CONFIG_NFS_V4_1 */
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
+			rpc_delay(task, nfs4_update_delay(timeout));
+			goto restart_call;
 		case -NFS4ERR_GRACE:
 			rpc_delay(task, NFS4_POLL_RETRY_MAX);
 		case -NFS4ERR_RETRY_UNCACHED_REP:
@@ -5103,8 +5120,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 			pnfs_roc_set_barrier(data->inode, data->roc_barrier);
 		break;
 	default:
-		if (nfs4_async_handle_error(task, data->res.server, NULL) ==
-				-EAGAIN) {
+		if (nfs4_async_handle_error(task, data->res.server,
+					    NULL, NULL) == -EAGAIN) {
 			rpc_restart_call_prepare(task);
 			return;
 		}
@@ -5368,7 +5385,8 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 		case -NFS4ERR_EXPIRED:
 			break;
 		default:
-			if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN)
+			if (nfs4_async_handle_error(task, calldata->server,
+						    NULL, NULL) == -EAGAIN)
 				rpc_restart_call_prepare(task);
 	}
 	nfs_release_seqid(calldata->arg.seqid);
@@ -5974,7 +5992,8 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata)
 		break;
 	case -NFS4ERR_LEASE_MOVED:
 	case -NFS4ERR_DELAY:
-		if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN)
+		if (nfs4_async_handle_error(task, server,
+					    NULL, NULL) == -EAGAIN)
 			rpc_restart_call_prepare(task);
 	}
 }
@@ -7591,7 +7610,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 			rpc_restart_call_prepare(task);
 		}
 	}
-	if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+	if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
 		rpc_restart_call_prepare(task);
 out:
 	dprintk("<-- %s\n", __func__);
@@ -7751,7 +7770,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 	case 0:
 		break;
 	case -NFS4ERR_DELAY:
-		if (nfs4_async_handle_error(task, server, NULL) != -EAGAIN)
+		if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN)
 			break;
 		rpc_restart_call_prepare(task);
 		return;
@@ -7882,7 +7901,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 	case 0:
 		break;
 	default:
-		if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+		if (nfs4_async_handle_error(task, server, NULL, NULL) == -EAGAIN) {
 			rpc_restart_call_prepare(task);
 			return;
 		}
@@ -8178,7 +8197,7 @@ static void nfs41_free_stateid_done(struct rpc_task *task, void *calldata)
 
 	switch (task->tk_status) {
 	case -NFS4ERR_DELAY:
-		if (nfs4_async_handle_error(task, data->server, NULL) == -EAGAIN)
+		if (nfs4_async_handle_error(task, data->server, NULL, NULL) == -EAGAIN)
 			rpc_restart_call_prepare(task);
 	}
 }
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 7ae249ccb78d..6951c7d9097d 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1339,6 +1339,7 @@ struct nfs_unlinkdata {
 	struct inode *dir;
 	struct rpc_cred	*cred;
 	struct nfs_fattr dir_attr;
+	long timeout;
 };
 
 struct nfs_renamedata {
@@ -1352,6 +1353,7 @@ struct nfs_renamedata {
 	struct dentry		*new_dentry;
 	struct nfs_fattr	new_fattr;
 	void (*complete)(struct rpc_task *, struct nfs_renamedata *);
+	long timeout;
 };
 
 struct nfs_access_entry;
-- 
cgit v1.2.3


From cc952e7017fa2e8871ee6a94f2c606ff5911f61e Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 24 Sep 2014 06:26:21 -0400
Subject: tty: Fix width of unsigned long bitfield padding

Commit c545b66c6922b002b5fe224a6eaec58c913650b5,
'tty: Serialize tcflow() with other tty flow control changes' and
commit 99416322dd16b810ba74098cc50ef2a844091d35,
'tty: Workaround Alpha non-atomic byte storage in tty_struct' work around
compiler bugs and non-atomic storage on multiple arches by padding
bitfields out to the declared type which is unsigned long. However, the
width varies by arch.

Pad bitfields to actual width of unsigned long (which is BITS_PER_LONG).

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 546e94557895..5171ef8f7b85 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -264,11 +264,11 @@ struct tty_struct {
 	struct winsize winsize;		/* winsize_mutex */
 	unsigned long stopped:1,	/* flow_lock */
 		      flow_stopped:1,
-		      unused:62;
+		      unused:BITS_PER_LONG - 2;
 	int hw_stopped;
 	unsigned long ctrl_status:8,	/* ctrl_lock */
 		      packet:1,
-		      unused_ctrl:55;
+		      unused_ctrl:BITS_PER_LONG - 9;
 	unsigned int receive_room;	/* Bytes free for queue */
 	int flow_change;
 
-- 
cgit v1.2.3


From cbbce82209490df8b68da9aec0d642451fe0a668 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Thu, 25 Sep 2014 13:55:19 +1000
Subject: SCHED: add some "wait..on_bit...timeout()" interfaces.

In commit c1221321b7c25b53204447cff9949a6d5a7ddddc
   sched: Allow wait_on_bit_action() functions to support a timeout

I suggested that a "wait_on_bit_timeout()" interface would not meet my
need.  This isn't true - I was just over-engineering.

Including a 'private' field in wait_bit_key instead of a focused
"timeout" field was just premature generalization.  If some other
use is ever found, it can be generalized or added later.

So this patch renames "private" to "timeout" with a meaning "stop
waiting when "jiffies" reaches or passes "timeout",
and adds two of the many possible wait..bit..timeout() interfaces:

wait_on_page_bit_killable_timeout(), which is the one I want to use,
and out_of_line_wait_on_bit_timeout() which is a reasonably general
example.  Others can be added as needed.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NeilBrown <neilb@suse.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/pagemap.h |  2 ++
 include/linux/wait.h    |  5 ++++-
 kernel/sched/wait.c     | 36 ++++++++++++++++++++++++++++++++++++
 mm/filemap.c            | 13 +++++++++++++
 4 files changed, 55 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 3df8c7db7a4e..87f9e4230d3a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -502,6 +502,8 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
 extern void wait_on_page_bit(struct page *page, int bit_nr);
 
 extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
+extern int wait_on_page_bit_killable_timeout(struct page *page,
+					     int bit_nr, unsigned long timeout);
 
 static inline int wait_on_page_locked_killable(struct page *page)
 {
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 6fb1ba5f9b2f..80115bf88671 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -25,7 +25,7 @@ struct wait_bit_key {
 	void			*flags;
 	int			bit_nr;
 #define WAIT_ATOMIC_T_BIT_NR	-1
-	unsigned long		private;
+	unsigned long		timeout;
 };
 
 struct wait_bit_queue {
@@ -154,6 +154,7 @@ int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_ac
 void wake_up_bit(void *, int);
 void wake_up_atomic_t(atomic_t *);
 int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned);
+int out_of_line_wait_on_bit_timeout(void *, int, wait_bit_action_f *, unsigned, unsigned long);
 int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned);
 int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned);
 wait_queue_head_t *bit_waitqueue(void *, int);
@@ -859,6 +860,8 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 
 extern int bit_wait(struct wait_bit_key *);
 extern int bit_wait_io(struct wait_bit_key *);
+extern int bit_wait_timeout(struct wait_bit_key *);
+extern int bit_wait_io_timeout(struct wait_bit_key *);
 
 /**
  * wait_on_bit - wait for a bit to be cleared
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 15cab1a4f84e..5a62915f47a8 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -343,6 +343,18 @@ int __sched out_of_line_wait_on_bit(void *word, int bit,
 }
 EXPORT_SYMBOL(out_of_line_wait_on_bit);
 
+int __sched out_of_line_wait_on_bit_timeout(
+	void *word, int bit, wait_bit_action_f *action,
+	unsigned mode, unsigned long timeout)
+{
+	wait_queue_head_t *wq = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wait, word, bit);
+
+	wait.key.timeout = jiffies + timeout;
+	return __wait_on_bit(wq, &wait, action, mode);
+}
+EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
+
 int __sched
 __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
 			wait_bit_action_f *action, unsigned mode)
@@ -520,3 +532,27 @@ __sched int bit_wait_io(struct wait_bit_key *word)
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait_io);
+
+__sched int bit_wait_timeout(struct wait_bit_key *word)
+{
+	unsigned long now = ACCESS_ONCE(jiffies);
+	if (signal_pending_state(current->state, current))
+		return 1;
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	schedule_timeout(word->timeout - now);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_timeout);
+
+__sched int bit_wait_io_timeout(struct wait_bit_key *word)
+{
+	unsigned long now = ACCESS_ONCE(jiffies);
+	if (signal_pending_state(current->state, current))
+		return 1;
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	io_schedule_timeout(word->timeout - now);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_io_timeout);
diff --git a/mm/filemap.c b/mm/filemap.c
index 90effcdf948d..cbe5a9013f70 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -703,6 +703,19 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr)
 			     bit_wait_io, TASK_KILLABLE);
 }
 
+int wait_on_page_bit_killable_timeout(struct page *page,
+				       int bit_nr, unsigned long timeout)
+{
+	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
+
+	wait.key.timeout = jiffies + timeout;
+	if (!test_bit(bit_nr, &page->flags))
+		return 0;
+	return __wait_on_bit(page_waitqueue(page), &wait,
+			     bit_wait_io_timeout, TASK_KILLABLE);
+}
+EXPORT_SYMBOL_GPL(wait_on_page_bit_killable_timeout);
+
 /**
  * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
  * @page: Page defining the wait queue of interest
-- 
cgit v1.2.3


From a4796e37c12e177572b80864cbab9c907ea250b0 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Wed, 24 Sep 2014 11:28:32 +1000
Subject: MM: export page_wakeup functions

This will allow NFS to wait for PG_private to be cleared and,
particularly, to send a wake-up when it is.

Signed-off-by: NeilBrown <neilb@suse.de>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/pagemap.h | 10 ++++++++--
 mm/filemap.c            |  8 ++------
 2 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 87f9e4230d3a..2dca0cef3506 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -496,8 +496,8 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
 }
 
 /*
- * This is exported only for wait_on_page_locked/wait_on_page_writeback.
- * Never use this directly!
+ * This is exported only for wait_on_page_locked/wait_on_page_writeback,
+ * and for filesystems which need to wait on PG_private.
  */
 extern void wait_on_page_bit(struct page *page, int bit_nr);
 
@@ -512,6 +512,12 @@ static inline int wait_on_page_locked_killable(struct page *page)
 	return 0;
 }
 
+extern wait_queue_head_t *page_waitqueue(struct page *page);
+static inline void wake_up_page(struct page *page, int bit)
+{
+	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
+}
+
 /* 
  * Wait for a page to be unlocked.
  *
diff --git a/mm/filemap.c b/mm/filemap.c
index cbe5a9013f70..b9b1413080be 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -670,17 +670,13 @@ EXPORT_SYMBOL(__page_cache_alloc);
  * at a cost of "thundering herd" phenomena during rare hash
  * collisions.
  */
-static wait_queue_head_t *page_waitqueue(struct page *page)
+wait_queue_head_t *page_waitqueue(struct page *page)
 {
 	const struct zone *zone = page_zone(page);
 
 	return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
 }
-
-static inline void wake_up_page(struct page *page, int bit)
-{
-	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
-}
+EXPORT_SYMBOL(page_waitqueue);
 
 void wait_on_page_bit(struct page *page, int bit_nr)
 {
-- 
cgit v1.2.3


From e03f73a01f010b29504ceebda3c4fca25468516d Mon Sep 17 00:00:00 2001
From: Anatol Pomozov <anatol.pomozov@gmail.com>
Date: Wed, 24 Sep 2014 11:17:14 -0700
Subject: ASoC: trace: Remove trailing new-lines in trace messages

These new-lines add empty lines to trace output

Signed-off-by: Anatol Pomozov <anatol.pomozov@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/trace/events/asoc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h
index 0194a641e4e2..b04ee7e5a466 100644
--- a/include/trace/events/asoc.h
+++ b/include/trace/events/asoc.h
@@ -175,7 +175,7 @@ TRACE_EVENT(snd_soc_dapm_output_path,
 		__entry->path_sink = (long)path->sink;
 	),
 
-	TP_printk("%c%s -> %s -> %s\n",
+	TP_printk("%c%s -> %s -> %s",
 		(int) __entry->path_sink &&
 		(int) __entry->path_connect ? '*' : ' ',
 		__get_str(wname), __get_str(pname), __get_str(psname))
@@ -204,7 +204,7 @@ TRACE_EVENT(snd_soc_dapm_input_path,
 		__entry->path_source = (long)path->source;
 	),
 
-	TP_printk("%c%s <- %s <- %s\n",
+	TP_printk("%c%s <- %s <- %s",
 		(int) __entry->path_source &&
 		(int) __entry->path_connect ? '*' : ' ',
 		__get_str(wname), __get_str(pname), __get_str(psname))
@@ -226,7 +226,7 @@ TRACE_EVENT(snd_soc_dapm_connected,
 		__entry->stream = stream;
 	),
 
-	TP_printk("%s: found %d paths\n",
+	TP_printk("%s: found %d paths",
 		__entry->stream ? "capture" : "playback", __entry->paths)
 );
 
-- 
cgit v1.2.3


From 1aed074869a9cbe0a846ea7b254d8fd9a4a4d31f Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 3 Sep 2014 18:34:04 +0200
Subject: iommu: Convert iommu-caps from define to enum

Allow compile-time type-checking.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c |  2 +-
 include/linux/iommu.h | 11 +++++++----
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0639b9274b11..bc45478e26db 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -948,7 +948,7 @@ phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
 
 int iommu_domain_has_cap(struct iommu_domain *domain,
-			 unsigned long cap)
+			 enum iommu_cap cap)
 {
 	if (unlikely(domain->ops->domain_has_cap == NULL))
 		return 0;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 20f9a527922a..98fc126655ae 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -57,8 +57,11 @@ struct iommu_domain {
 	struct iommu_domain_geometry geometry;
 };
 
-#define IOMMU_CAP_CACHE_COHERENCY	0x1
-#define IOMMU_CAP_INTR_REMAP		0x2	/* isolates device intrs */
+enum iommu_cap {
+	IOMMU_CAP_CACHE_COHERENCY,	/* IOMMU can enforce cache coherent DMA
+					   transactions */
+	IOMMU_CAP_INTR_REMAP,		/* IOMMU supports interrupt isolation */
+};
 
 /*
  * Following constraints are specifc to FSL_PAMUV1:
@@ -155,7 +158,7 @@ extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 		       size_t size);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
 extern int iommu_domain_has_cap(struct iommu_domain *domain,
-				unsigned long cap);
+				enum iommu_cap cap);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
 
@@ -305,7 +308,7 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_ad
 }
 
 static inline int iommu_domain_has_cap(struct iommu_domain *domain,
-				       unsigned long cap)
+				       enum iommu_cap cap)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From 3c0e0ca0a4e757159d868c4870556515d66b6c97 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 3 Sep 2014 18:47:25 +0200
Subject: iommu: Introduce iommu_capable API function

This function will replace the current iommu_domain_has_cap
function and clean up the interface while at it.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 18 +++++++++++++++---
 include/linux/iommu.h |  7 +++++++
 2 files changed, 22 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index bc45478e26db..aeb243f46332 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -817,6 +817,15 @@ bool iommu_present(struct bus_type *bus)
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
+bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
+{
+	if (!bus->iommu_ops || !bus->iommu_ops->capable)
+		return false;
+
+	return bus->iommu_ops->capable(cap);
+}
+EXPORT_SYMBOL_GPL(iommu_capable);
+
 /**
  * iommu_set_fault_handler() - set a fault handler for an iommu domain
  * @domain: iommu domain
@@ -950,10 +959,13 @@ EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
 int iommu_domain_has_cap(struct iommu_domain *domain,
 			 enum iommu_cap cap)
 {
-	if (unlikely(domain->ops->domain_has_cap == NULL))
-		return 0;
+	if (domain->ops->domain_has_cap != NULL)
+		return domain->ops->domain_has_cap(domain, cap);
+
+	if (domain->ops->capable != NULL)
+		return domain->ops->capable(cap);
 
-	return domain->ops->domain_has_cap(domain, cap);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 98fc126655ae..d5534d554693 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -105,6 +105,7 @@ enum iommu_attr {
  * @pgsize_bitmap: bitmap of supported page sizes
  */
 struct iommu_ops {
+	bool (*capable)(enum iommu_cap);
 	int (*domain_init)(struct iommu_domain *domain);
 	void (*domain_destroy)(struct iommu_domain *domain);
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
@@ -145,6 +146,7 @@ struct iommu_ops {
 
 extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops);
 extern bool iommu_present(struct bus_type *bus);
+extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap);
 extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus);
 extern struct iommu_group *iommu_group_get_by_id(int id);
 extern void iommu_domain_free(struct iommu_domain *domain);
@@ -253,6 +255,11 @@ static inline bool iommu_present(struct bus_type *bus)
 	return false;
 }
 
+static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
+{
+	return false;
+}
+
 static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
 {
 	return NULL;
-- 
cgit v1.2.3


From 24278a24d88ae730229417e5d3bd452d7545fbcc Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Fri, 5 Sep 2014 10:57:11 +0200
Subject: iommu: Remove iommu_domain_has_cap() API function

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 13 -------------
 include/linux/iommu.h | 11 -----------
 2 files changed, 24 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index aeb243f46332..d2d242fcaa3d 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -956,19 +956,6 @@ phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 }
 EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
 
-int iommu_domain_has_cap(struct iommu_domain *domain,
-			 enum iommu_cap cap)
-{
-	if (domain->ops->domain_has_cap != NULL)
-		return domain->ops->domain_has_cap(domain, cap);
-
-	if (domain->ops->capable != NULL)
-		return domain->ops->capable(cap);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
-
 static size_t iommu_pgsize(struct iommu_domain *domain,
 			   unsigned long addr_merge, size_t size)
 {
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index d5534d554693..379a6179fd96 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -97,7 +97,6 @@ enum iommu_attr {
  * @map: map a physically contiguous memory region to an iommu domain
  * @unmap: unmap a physically contiguous memory region from an iommu domain
  * @iova_to_phys: translate iova to physical address
- * @domain_has_cap: domain capabilities query
  * @add_device: add device to iommu grouping
  * @remove_device: remove device from iommu grouping
  * @domain_get_attr: Query domain attributes
@@ -115,8 +114,6 @@ struct iommu_ops {
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
-	int (*domain_has_cap)(struct iommu_domain *domain,
-			      unsigned long cap);
 	int (*add_device)(struct device *dev);
 	void (*remove_device)(struct device *dev);
 	int (*device_group)(struct device *dev, unsigned int *groupid);
@@ -159,8 +156,6 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 		       size_t size);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
-extern int iommu_domain_has_cap(struct iommu_domain *domain,
-				enum iommu_cap cap);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
 
@@ -314,12 +309,6 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_ad
 	return 0;
 }
 
-static inline int iommu_domain_has_cap(struct iommu_domain *domain,
-				       enum iommu_cap cap)
-{
-	return 0;
-}
-
 static inline void iommu_set_fault_handler(struct iommu_domain *domain,
 				iommu_fault_handler_t handler, void *token)
 {
-- 
cgit v1.2.3


From 17f4a5c47f28de9ea59182f48d07f8c44ee5dcc9 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Mon, 22 Sep 2014 19:41:00 +0200
Subject: i2c: move acpi code back into the core

Commit 5d98e61d337c ("I2C/ACPI: Add i2c ACPI operation region support")
renamed the i2c-core module. This may cause regressions for
distributions, so put the ACPI code back into the core.

Reported-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Tested-by: Lan Tianyu <tianyu.lan@intel.com>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 MAINTAINERS            |   1 -
 drivers/i2c/Makefile   |   5 +-
 drivers/i2c/i2c-acpi.c | 364 -------------------------------------------------
 drivers/i2c/i2c-core.c | 354 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/i2c.h    |  16 ---
 5 files changed, 355 insertions(+), 385 deletions(-)
 delete mode 100644 drivers/i2c/i2c-acpi.c

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 809ecd680d88..e3682d0dea1e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4477,7 +4477,6 @@ M:	Mika Westerberg <mika.westerberg@linux.intel.com>
 L:	linux-i2c@vger.kernel.org
 L:	linux-acpi@vger.kernel.org
 S:	Maintained
-F:	drivers/i2c/i2c-acpi.c
 
 I2C-TAOS-EVM DRIVER
 M:	Jean Delvare <jdelvare@suse.de>
diff --git a/drivers/i2c/Makefile b/drivers/i2c/Makefile
index e0228b228256..1722f50f2473 100644
--- a/drivers/i2c/Makefile
+++ b/drivers/i2c/Makefile
@@ -2,11 +2,8 @@
 # Makefile for the i2c core.
 #
 
-i2ccore-y := i2c-core.o
-i2ccore-$(CONFIG_ACPI)	 	+= i2c-acpi.o
-
 obj-$(CONFIG_I2C_BOARDINFO)	+= i2c-boardinfo.o
-obj-$(CONFIG_I2C)		+= i2ccore.o
+obj-$(CONFIG_I2C)		+= i2c-core.o
 obj-$(CONFIG_I2C_SMBUS)		+= i2c-smbus.o
 obj-$(CONFIG_I2C_CHARDEV)	+= i2c-dev.o
 obj-$(CONFIG_I2C_MUX)		+= i2c-mux.o
diff --git a/drivers/i2c/i2c-acpi.c b/drivers/i2c/i2c-acpi.c
deleted file mode 100644
index 0dbc18c15c43..000000000000
--- a/drivers/i2c/i2c-acpi.c
+++ /dev/null
@@ -1,364 +0,0 @@
-/*
- * I2C ACPI code
- *
- * Copyright (C) 2014 Intel Corp
- *
- * Author: Lan Tianyu <tianyu.lan@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
- * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- */
-#define pr_fmt(fmt) "I2C/ACPI : " fmt
-
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <linux/i2c.h>
-#include <linux/acpi.h>
-
-struct acpi_i2c_handler_data {
-	struct acpi_connection_info info;
-	struct i2c_adapter *adapter;
-};
-
-struct gsb_buffer {
-	u8	status;
-	u8	len;
-	union {
-		u16	wdata;
-		u8	bdata;
-		u8	data[0];
-	};
-} __packed;
-
-static int acpi_i2c_add_resource(struct acpi_resource *ares, void *data)
-{
-	struct i2c_board_info *info = data;
-
-	if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) {
-		struct acpi_resource_i2c_serialbus *sb;
-
-		sb = &ares->data.i2c_serial_bus;
-		if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_I2C) {
-			info->addr = sb->slave_address;
-			if (sb->access_mode == ACPI_I2C_10BIT_MODE)
-				info->flags |= I2C_CLIENT_TEN;
-		}
-	} else if (info->irq < 0) {
-		struct resource r;
-
-		if (acpi_dev_resource_interrupt(ares, 0, &r))
-			info->irq = r.start;
-	}
-
-	/* Tell the ACPI core to skip this resource */
-	return 1;
-}
-
-static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
-				       void *data, void **return_value)
-{
-	struct i2c_adapter *adapter = data;
-	struct list_head resource_list;
-	struct i2c_board_info info;
-	struct acpi_device *adev;
-	int ret;
-
-	if (acpi_bus_get_device(handle, &adev))
-		return AE_OK;
-	if (acpi_bus_get_status(adev) || !adev->status.present)
-		return AE_OK;
-
-	memset(&info, 0, sizeof(info));
-	info.acpi_node.companion = adev;
-	info.irq = -1;
-
-	INIT_LIST_HEAD(&resource_list);
-	ret = acpi_dev_get_resources(adev, &resource_list,
-				     acpi_i2c_add_resource, &info);
-	acpi_dev_free_resource_list(&resource_list);
-
-	if (ret < 0 || !info.addr)
-		return AE_OK;
-
-	adev->power.flags.ignore_parent = true;
-	strlcpy(info.type, dev_name(&adev->dev), sizeof(info.type));
-	if (!i2c_new_device(adapter, &info)) {
-		adev->power.flags.ignore_parent = false;
-		dev_err(&adapter->dev,
-			"failed to add I2C device %s from ACPI\n",
-			dev_name(&adev->dev));
-	}
-
-	return AE_OK;
-}
-
-/**
- * acpi_i2c_register_devices - enumerate I2C slave devices behind adapter
- * @adap: pointer to adapter
- *
- * Enumerate all I2C slave devices behind this adapter by walking the ACPI
- * namespace. When a device is found it will be added to the Linux device
- * model and bound to the corresponding ACPI handle.
- */
-void acpi_i2c_register_devices(struct i2c_adapter *adap)
-{
-	acpi_handle handle;
-	acpi_status status;
-
-	if (!adap->dev.parent)
-		return;
-
-	handle = ACPI_HANDLE(adap->dev.parent);
-	if (!handle)
-		return;
-
-	status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
-				     acpi_i2c_add_device, NULL,
-				     adap, NULL);
-	if (ACPI_FAILURE(status))
-		dev_warn(&adap->dev, "failed to enumerate I2C slaves\n");
-}
-
-#ifdef CONFIG_ACPI_I2C_OPREGION
-static int acpi_gsb_i2c_read_bytes(struct i2c_client *client,
-		u8 cmd, u8 *data, u8 data_len)
-{
-
-	struct i2c_msg msgs[2];
-	int ret;
-	u8 *buffer;
-
-	buffer = kzalloc(data_len, GFP_KERNEL);
-	if (!buffer)
-		return AE_NO_MEMORY;
-
-	msgs[0].addr = client->addr;
-	msgs[0].flags = client->flags;
-	msgs[0].len = 1;
-	msgs[0].buf = &cmd;
-
-	msgs[1].addr = client->addr;
-	msgs[1].flags = client->flags | I2C_M_RD;
-	msgs[1].len = data_len;
-	msgs[1].buf = buffer;
-
-	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
-	if (ret < 0)
-		dev_err(&client->adapter->dev, "i2c read failed\n");
-	else
-		memcpy(data, buffer, data_len);
-
-	kfree(buffer);
-	return ret;
-}
-
-static int acpi_gsb_i2c_write_bytes(struct i2c_client *client,
-		u8 cmd, u8 *data, u8 data_len)
-{
-
-	struct i2c_msg msgs[1];
-	u8 *buffer;
-	int ret = AE_OK;
-
-	buffer = kzalloc(data_len + 1, GFP_KERNEL);
-	if (!buffer)
-		return AE_NO_MEMORY;
-
-	buffer[0] = cmd;
-	memcpy(buffer + 1, data, data_len);
-
-	msgs[0].addr = client->addr;
-	msgs[0].flags = client->flags;
-	msgs[0].len = data_len + 1;
-	msgs[0].buf = buffer;
-
-	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
-	if (ret < 0)
-		dev_err(&client->adapter->dev, "i2c write failed\n");
-
-	kfree(buffer);
-	return ret;
-}
-
-static acpi_status
-acpi_i2c_space_handler(u32 function, acpi_physical_address command,
-			u32 bits, u64 *value64,
-			void *handler_context, void *region_context)
-{
-	struct gsb_buffer *gsb = (struct gsb_buffer *)value64;
-	struct acpi_i2c_handler_data *data = handler_context;
-	struct acpi_connection_info *info = &data->info;
-	struct acpi_resource_i2c_serialbus *sb;
-	struct i2c_adapter *adapter = data->adapter;
-	struct i2c_client client;
-	struct acpi_resource *ares;
-	u32 accessor_type = function >> 16;
-	u8 action = function & ACPI_IO_MASK;
-	acpi_status ret = AE_OK;
-	int status;
-
-	ret = acpi_buffer_to_resource(info->connection, info->length, &ares);
-	if (ACPI_FAILURE(ret))
-		return ret;
-
-	if (!value64 || ares->type != ACPI_RESOURCE_TYPE_SERIAL_BUS) {
-		ret = AE_BAD_PARAMETER;
-		goto err;
-	}
-
-	sb = &ares->data.i2c_serial_bus;
-	if (sb->type != ACPI_RESOURCE_SERIAL_TYPE_I2C) {
-		ret = AE_BAD_PARAMETER;
-		goto err;
-	}
-
-	memset(&client, 0, sizeof(client));
-	client.adapter = adapter;
-	client.addr = sb->slave_address;
-	client.flags = 0;
-
-	if (sb->access_mode == ACPI_I2C_10BIT_MODE)
-		client.flags |= I2C_CLIENT_TEN;
-
-	switch (accessor_type) {
-	case ACPI_GSB_ACCESS_ATTRIB_SEND_RCV:
-		if (action == ACPI_READ) {
-			status = i2c_smbus_read_byte(&client);
-			if (status >= 0) {
-				gsb->bdata = status;
-				status = 0;
-			}
-		} else {
-			status = i2c_smbus_write_byte(&client, gsb->bdata);
-		}
-		break;
-
-	case ACPI_GSB_ACCESS_ATTRIB_BYTE:
-		if (action == ACPI_READ) {
-			status = i2c_smbus_read_byte_data(&client, command);
-			if (status >= 0) {
-				gsb->bdata = status;
-				status = 0;
-			}
-		} else {
-			status = i2c_smbus_write_byte_data(&client, command,
-					gsb->bdata);
-		}
-		break;
-
-	case ACPI_GSB_ACCESS_ATTRIB_WORD:
-		if (action == ACPI_READ) {
-			status = i2c_smbus_read_word_data(&client, command);
-			if (status >= 0) {
-				gsb->wdata = status;
-				status = 0;
-			}
-		} else {
-			status = i2c_smbus_write_word_data(&client, command,
-					gsb->wdata);
-		}
-		break;
-
-	case ACPI_GSB_ACCESS_ATTRIB_BLOCK:
-		if (action == ACPI_READ) {
-			status = i2c_smbus_read_block_data(&client, command,
-					gsb->data);
-			if (status >= 0) {
-				gsb->len = status;
-				status = 0;
-			}
-		} else {
-			status = i2c_smbus_write_block_data(&client, command,
-					gsb->len, gsb->data);
-		}
-		break;
-
-	case ACPI_GSB_ACCESS_ATTRIB_MULTIBYTE:
-		if (action == ACPI_READ) {
-			status = acpi_gsb_i2c_read_bytes(&client, command,
-					gsb->data, info->access_length);
-			if (status > 0)
-				status = 0;
-		} else {
-			status = acpi_gsb_i2c_write_bytes(&client, command,
-					gsb->data, info->access_length);
-		}
-		break;
-
-	default:
-		pr_info("protocol(0x%02x) is not supported.\n", accessor_type);
-		ret = AE_BAD_PARAMETER;
-		goto err;
-	}
-
-	gsb->status = status;
-
- err:
-	ACPI_FREE(ares);
-	return ret;
-}
-
-
-int acpi_i2c_install_space_handler(struct i2c_adapter *adapter)
-{
-	acpi_handle handle = ACPI_HANDLE(adapter->dev.parent);
-	struct acpi_i2c_handler_data *data;
-	acpi_status status;
-
-	if (!handle)
-		return -ENODEV;
-
-	data = kzalloc(sizeof(struct acpi_i2c_handler_data),
-			    GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	data->adapter = adapter;
-	status = acpi_bus_attach_private_data(handle, (void *)data);
-	if (ACPI_FAILURE(status)) {
-		kfree(data);
-		return -ENOMEM;
-	}
-
-	status = acpi_install_address_space_handler(handle,
-				ACPI_ADR_SPACE_GSBUS,
-				&acpi_i2c_space_handler,
-				NULL,
-				data);
-	if (ACPI_FAILURE(status)) {
-		dev_err(&adapter->dev, "Error installing i2c space handler\n");
-		acpi_bus_detach_private_data(handle);
-		kfree(data);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter)
-{
-	acpi_handle handle = ACPI_HANDLE(adapter->dev.parent);
-	struct acpi_i2c_handler_data *data;
-	acpi_status status;
-
-	if (!handle)
-		return;
-
-	acpi_remove_address_space_handler(handle,
-				ACPI_ADR_SPACE_GSBUS,
-				&acpi_i2c_space_handler);
-
-	status = acpi_bus_get_private_data(handle, (void **)&data);
-	if (ACPI_SUCCESS(status))
-		kfree(data);
-
-	acpi_bus_detach_private_data(handle);
-}
-#endif
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 632057a44615..b696ac7e6d86 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -27,6 +27,8 @@
    OF support is copyright (c) 2008 Jochen Friedrich <jochen@scram.de>
    (based on a previous patch from Jon Smirl <jonsmirl@gmail.com>) and
    (c) 2013  Wolfram Sang <wsa@the-dreams.de>
+   I2C ACPI code Copyright (C) 2014 Intel Corp
+   Author: Lan Tianyu <tianyu.lan@intel.com>
  */
 
 #include <linux/module.h>
@@ -78,6 +80,358 @@ void i2c_transfer_trace_unreg(void)
 	static_key_slow_dec(&i2c_trace_msg);
 }
 
+#if defined(CONFIG_ACPI)
+struct acpi_i2c_handler_data {
+	struct acpi_connection_info info;
+	struct i2c_adapter *adapter;
+};
+
+struct gsb_buffer {
+	u8	status;
+	u8	len;
+	union {
+		u16	wdata;
+		u8	bdata;
+		u8	data[0];
+	};
+} __packed;
+
+static int acpi_i2c_add_resource(struct acpi_resource *ares, void *data)
+{
+	struct i2c_board_info *info = data;
+
+	if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) {
+		struct acpi_resource_i2c_serialbus *sb;
+
+		sb = &ares->data.i2c_serial_bus;
+		if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_I2C) {
+			info->addr = sb->slave_address;
+			if (sb->access_mode == ACPI_I2C_10BIT_MODE)
+				info->flags |= I2C_CLIENT_TEN;
+		}
+	} else if (info->irq < 0) {
+		struct resource r;
+
+		if (acpi_dev_resource_interrupt(ares, 0, &r))
+			info->irq = r.start;
+	}
+
+	/* Tell the ACPI core to skip this resource */
+	return 1;
+}
+
+static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
+				       void *data, void **return_value)
+{
+	struct i2c_adapter *adapter = data;
+	struct list_head resource_list;
+	struct i2c_board_info info;
+	struct acpi_device *adev;
+	int ret;
+
+	if (acpi_bus_get_device(handle, &adev))
+		return AE_OK;
+	if (acpi_bus_get_status(adev) || !adev->status.present)
+		return AE_OK;
+
+	memset(&info, 0, sizeof(info));
+	info.acpi_node.companion = adev;
+	info.irq = -1;
+
+	INIT_LIST_HEAD(&resource_list);
+	ret = acpi_dev_get_resources(adev, &resource_list,
+				     acpi_i2c_add_resource, &info);
+	acpi_dev_free_resource_list(&resource_list);
+
+	if (ret < 0 || !info.addr)
+		return AE_OK;
+
+	adev->power.flags.ignore_parent = true;
+	strlcpy(info.type, dev_name(&adev->dev), sizeof(info.type));
+	if (!i2c_new_device(adapter, &info)) {
+		adev->power.flags.ignore_parent = false;
+		dev_err(&adapter->dev,
+			"failed to add I2C device %s from ACPI\n",
+			dev_name(&adev->dev));
+	}
+
+	return AE_OK;
+}
+
+/**
+ * acpi_i2c_register_devices - enumerate I2C slave devices behind adapter
+ * @adap: pointer to adapter
+ *
+ * Enumerate all I2C slave devices behind this adapter by walking the ACPI
+ * namespace. When a device is found it will be added to the Linux device
+ * model and bound to the corresponding ACPI handle.
+ */
+static void acpi_i2c_register_devices(struct i2c_adapter *adap)
+{
+	acpi_handle handle;
+	acpi_status status;
+
+	if (!adap->dev.parent)
+		return;
+
+	handle = ACPI_HANDLE(adap->dev.parent);
+	if (!handle)
+		return;
+
+	status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
+				     acpi_i2c_add_device, NULL,
+				     adap, NULL);
+	if (ACPI_FAILURE(status))
+		dev_warn(&adap->dev, "failed to enumerate I2C slaves\n");
+}
+
+#else /* CONFIG_ACPI */
+static inline void acpi_i2c_register_devices(struct i2c_adapter *adap) { }
+#endif /* CONFIG_ACPI */
+
+#ifdef CONFIG_ACPI_I2C_OPREGION
+static int acpi_gsb_i2c_read_bytes(struct i2c_client *client,
+		u8 cmd, u8 *data, u8 data_len)
+{
+
+	struct i2c_msg msgs[2];
+	int ret;
+	u8 *buffer;
+
+	buffer = kzalloc(data_len, GFP_KERNEL);
+	if (!buffer)
+		return AE_NO_MEMORY;
+
+	msgs[0].addr = client->addr;
+	msgs[0].flags = client->flags;
+	msgs[0].len = 1;
+	msgs[0].buf = &cmd;
+
+	msgs[1].addr = client->addr;
+	msgs[1].flags = client->flags | I2C_M_RD;
+	msgs[1].len = data_len;
+	msgs[1].buf = buffer;
+
+	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret < 0)
+		dev_err(&client->adapter->dev, "i2c read failed\n");
+	else
+		memcpy(data, buffer, data_len);
+
+	kfree(buffer);
+	return ret;
+}
+
+static int acpi_gsb_i2c_write_bytes(struct i2c_client *client,
+		u8 cmd, u8 *data, u8 data_len)
+{
+
+	struct i2c_msg msgs[1];
+	u8 *buffer;
+	int ret = AE_OK;
+
+	buffer = kzalloc(data_len + 1, GFP_KERNEL);
+	if (!buffer)
+		return AE_NO_MEMORY;
+
+	buffer[0] = cmd;
+	memcpy(buffer + 1, data, data_len);
+
+	msgs[0].addr = client->addr;
+	msgs[0].flags = client->flags;
+	msgs[0].len = data_len + 1;
+	msgs[0].buf = buffer;
+
+	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret < 0)
+		dev_err(&client->adapter->dev, "i2c write failed\n");
+
+	kfree(buffer);
+	return ret;
+}
+
+static acpi_status
+acpi_i2c_space_handler(u32 function, acpi_physical_address command,
+			u32 bits, u64 *value64,
+			void *handler_context, void *region_context)
+{
+	struct gsb_buffer *gsb = (struct gsb_buffer *)value64;
+	struct acpi_i2c_handler_data *data = handler_context;
+	struct acpi_connection_info *info = &data->info;
+	struct acpi_resource_i2c_serialbus *sb;
+	struct i2c_adapter *adapter = data->adapter;
+	struct i2c_client client;
+	struct acpi_resource *ares;
+	u32 accessor_type = function >> 16;
+	u8 action = function & ACPI_IO_MASK;
+	acpi_status ret = AE_OK;
+	int status;
+
+	ret = acpi_buffer_to_resource(info->connection, info->length, &ares);
+	if (ACPI_FAILURE(ret))
+		return ret;
+
+	if (!value64 || ares->type != ACPI_RESOURCE_TYPE_SERIAL_BUS) {
+		ret = AE_BAD_PARAMETER;
+		goto err;
+	}
+
+	sb = &ares->data.i2c_serial_bus;
+	if (sb->type != ACPI_RESOURCE_SERIAL_TYPE_I2C) {
+		ret = AE_BAD_PARAMETER;
+		goto err;
+	}
+
+	memset(&client, 0, sizeof(client));
+	client.adapter = adapter;
+	client.addr = sb->slave_address;
+	client.flags = 0;
+
+	if (sb->access_mode == ACPI_I2C_10BIT_MODE)
+		client.flags |= I2C_CLIENT_TEN;
+
+	switch (accessor_type) {
+	case ACPI_GSB_ACCESS_ATTRIB_SEND_RCV:
+		if (action == ACPI_READ) {
+			status = i2c_smbus_read_byte(&client);
+			if (status >= 0) {
+				gsb->bdata = status;
+				status = 0;
+			}
+		} else {
+			status = i2c_smbus_write_byte(&client, gsb->bdata);
+		}
+		break;
+
+	case ACPI_GSB_ACCESS_ATTRIB_BYTE:
+		if (action == ACPI_READ) {
+			status = i2c_smbus_read_byte_data(&client, command);
+			if (status >= 0) {
+				gsb->bdata = status;
+				status = 0;
+			}
+		} else {
+			status = i2c_smbus_write_byte_data(&client, command,
+					gsb->bdata);
+		}
+		break;
+
+	case ACPI_GSB_ACCESS_ATTRIB_WORD:
+		if (action == ACPI_READ) {
+			status = i2c_smbus_read_word_data(&client, command);
+			if (status >= 0) {
+				gsb->wdata = status;
+				status = 0;
+			}
+		} else {
+			status = i2c_smbus_write_word_data(&client, command,
+					gsb->wdata);
+		}
+		break;
+
+	case ACPI_GSB_ACCESS_ATTRIB_BLOCK:
+		if (action == ACPI_READ) {
+			status = i2c_smbus_read_block_data(&client, command,
+					gsb->data);
+			if (status >= 0) {
+				gsb->len = status;
+				status = 0;
+			}
+		} else {
+			status = i2c_smbus_write_block_data(&client, command,
+					gsb->len, gsb->data);
+		}
+		break;
+
+	case ACPI_GSB_ACCESS_ATTRIB_MULTIBYTE:
+		if (action == ACPI_READ) {
+			status = acpi_gsb_i2c_read_bytes(&client, command,
+					gsb->data, info->access_length);
+			if (status > 0)
+				status = 0;
+		} else {
+			status = acpi_gsb_i2c_write_bytes(&client, command,
+					gsb->data, info->access_length);
+		}
+		break;
+
+	default:
+		pr_info("protocol(0x%02x) is not supported.\n", accessor_type);
+		ret = AE_BAD_PARAMETER;
+		goto err;
+	}
+
+	gsb->status = status;
+
+ err:
+	ACPI_FREE(ares);
+	return ret;
+}
+
+
+static int acpi_i2c_install_space_handler(struct i2c_adapter *adapter)
+{
+	acpi_handle handle = ACPI_HANDLE(adapter->dev.parent);
+	struct acpi_i2c_handler_data *data;
+	acpi_status status;
+
+	if (!handle)
+		return -ENODEV;
+
+	data = kzalloc(sizeof(struct acpi_i2c_handler_data),
+			    GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->adapter = adapter;
+	status = acpi_bus_attach_private_data(handle, (void *)data);
+	if (ACPI_FAILURE(status)) {
+		kfree(data);
+		return -ENOMEM;
+	}
+
+	status = acpi_install_address_space_handler(handle,
+				ACPI_ADR_SPACE_GSBUS,
+				&acpi_i2c_space_handler,
+				NULL,
+				data);
+	if (ACPI_FAILURE(status)) {
+		dev_err(&adapter->dev, "Error installing i2c space handler\n");
+		acpi_bus_detach_private_data(handle);
+		kfree(data);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter)
+{
+	acpi_handle handle = ACPI_HANDLE(adapter->dev.parent);
+	struct acpi_i2c_handler_data *data;
+	acpi_status status;
+
+	if (!handle)
+		return;
+
+	acpi_remove_address_space_handler(handle,
+				ACPI_ADR_SPACE_GSBUS,
+				&acpi_i2c_space_handler);
+
+	status = acpi_bus_get_private_data(handle, (void **)&data);
+	if (ACPI_SUCCESS(status))
+		kfree(data);
+
+	acpi_bus_detach_private_data(handle);
+}
+#else /* CONFIG_ACPI_I2C_OPREGION */
+static inline void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter)
+{ }
+
+static inline int acpi_i2c_install_space_handler(struct i2c_adapter *adapter)
+{ return 0; }
+#endif /* CONFIG_ACPI_I2C_OPREGION */
+
 /* ------------------------------------------------------------------------- */
 
 static const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id,
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index a95efeb53a8b..b556e0ab946f 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -577,20 +577,4 @@ static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node
 }
 #endif /* CONFIG_OF */
 
-#ifdef CONFIG_ACPI
-void acpi_i2c_register_devices(struct i2c_adapter *adap);
-#else
-static inline void acpi_i2c_register_devices(struct i2c_adapter *adap) { }
-#endif /* CONFIG_ACPI */
-
-#ifdef CONFIG_ACPI_I2C_OPREGION
-int acpi_i2c_install_space_handler(struct i2c_adapter *adapter);
-void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter);
-#else
-static inline void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter)
-{ }
-static inline int acpi_i2c_install_space_handler(struct i2c_adapter *adapter)
-{ return 0; }
-#endif /* CONFIG_ACPI_I2C_OPREGION */
-
 #endif /* _LINUX_I2C_H */
-- 
cgit v1.2.3


From 3fc2aa5522ab958374d93ef5d2e12df7ee233c91 Mon Sep 17 00:00:00 2001
From: Michal Sojka <sojka@merica.cz>
Date: Wed, 24 Sep 2014 22:43:18 +0200
Subject: usb: gadget: Introduce usb_gadget_giveback_request()

All USB peripheral controller drivers call completion routines directly.
This patch adds usb_gadget_giveback_request() which will be used instead
of direct invocation in the next patch. The goal here is to have a place
where common functionality can be added.

Signed-off-by: Michal Sojka <sojka@merica.cz>
Acked-by: Felipe Balbi <balbi@ti.com>
Tested-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/udc-core.c | 16 ++++++++++++++++
 include/linux/usb/gadget.h        |  8 ++++++++
 2 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index ad1ceac15468..16d3f6fedd1c 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -106,6 +106,22 @@ EXPORT_SYMBOL_GPL(usb_gadget_unmap_request);
 
 /* ------------------------------------------------------------------------- */
 
+/**
+ * usb_gadget_giveback_request - give the request back to the gadget layer
+ * Context: in_interrupt()
+ *
+ * This is called by device controller drivers in order to return the
+ * completed request back to the gadget layer.
+ */
+void usb_gadget_giveback_request(struct usb_ep *ep,
+		struct usb_request *req)
+{
+	req->complete(ep, req);
+}
+EXPORT_SYMBOL_GPL(usb_gadget_giveback_request);
+
+/* ------------------------------------------------------------------------- */
+
 static void usb_gadget_state_work(struct work_struct *work)
 {
 	struct usb_gadget	*gadget = work_to_gadget(work);
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index d18811433324..522cafe26790 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -1023,6 +1023,14 @@ extern void usb_gadget_udc_reset(struct usb_gadget *gadget,
 
 /*-------------------------------------------------------------------------*/
 
+/* utility to give requests back to the gadget layer */
+
+extern void usb_gadget_giveback_request(struct usb_ep *ep,
+		struct usb_request *req);
+
+
+/*-------------------------------------------------------------------------*/
+
 /* utility wrapping a simple endpoint selection policy */
 
 extern struct usb_ep *usb_ep_autoconfig(struct usb_gadget *,
-- 
cgit v1.2.3


From 0cfbd328d60f85b0dcf66df61a3615e9a8e5d4e4 Mon Sep 17 00:00:00 2001
From: Michal Sojka <sojka@merica.cz>
Date: Wed, 24 Sep 2014 22:43:21 +0200
Subject: usb: Add LED triggers for USB activity
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With this patch, USB activity can be signaled by blinking a LED. There
are two triggers, one for activity on USB host and one for USB gadget.

Both triggers should work with all host/device controllers. Tested only
with musb.

Performace: I measured performance overheads on ARM Cortex-A8 (TI
AM335x) running on 600 MHz.

Duration of usb_led_activity():
- with no LED attached to the trigger:        2 ± 1 µs
- with one GPIO LED attached to the trigger:  2 ± 1 µs or 8 ± 2 µs (two peaks in histogram)

Duration of functions calling usb_led_activity() (with this patch
applied and no LED attached to the trigger):
- __usb_hcd_giveback_urb():    10 - 25 µs
- usb_gadget_giveback_request(): 2 - 6 µs

Signed-off-by: Michal Sojka <sojka@merica.cz>
Acked-by: Felipe Balbi <balbi@ti.com>
Tested-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/Kconfig               | 10 +++++++
 drivers/usb/common/Makefile       |  1 +
 drivers/usb/common/led.c          | 57 +++++++++++++++++++++++++++++++++++++++
 drivers/usb/core/hcd.c            |  2 ++
 drivers/usb/gadget/udc/udc-core.c |  4 +++
 include/linux/usb.h               | 12 +++++++++
 6 files changed, 86 insertions(+)
 create mode 100644 drivers/usb/common/led.c

(limited to 'include')

diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index cf1b19bca306..ae481c37a208 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -149,4 +149,14 @@ source "drivers/usb/phy/Kconfig"
 
 source "drivers/usb/gadget/Kconfig"
 
+config USB_LED_TRIG
+	bool "USB LED Triggers"
+	depends on LEDS_CLASS && USB_COMMON && LEDS_TRIGGERS
+	help
+	  This option adds LED triggers for USB host and/or gadget activity.
+
+	  Say Y here if you are working on a system with led-class supported
+	  LEDs and you want to use them as activity indicators for USB host or
+	  gadget.
+
 endif # USB_SUPPORT
diff --git a/drivers/usb/common/Makefile b/drivers/usb/common/Makefile
index 052c12069c24..ca2f8bd0e431 100644
--- a/drivers/usb/common/Makefile
+++ b/drivers/usb/common/Makefile
@@ -4,5 +4,6 @@
 
 obj-$(CONFIG_USB_COMMON)	  += usb-common.o
 usb-common-y			  += common.o
+usb-common-$(CONFIG_USB_LED_TRIG) += led.o
 
 obj-$(CONFIG_USB_OTG_FSM) += usb-otg-fsm.o
diff --git a/drivers/usb/common/led.c b/drivers/usb/common/led.c
new file mode 100644
index 000000000000..df23da00a901
--- /dev/null
+++ b/drivers/usb/common/led.c
@@ -0,0 +1,57 @@
+/*
+ * LED Triggers for USB Activity
+ *
+ * Copyright 2014 Michal Sojka <sojka@merica.cz>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/leds.h>
+#include <linux/usb.h>
+
+#define BLINK_DELAY 30
+
+static unsigned long usb_blink_delay = BLINK_DELAY;
+
+DEFINE_LED_TRIGGER(ledtrig_usb_gadget);
+DEFINE_LED_TRIGGER(ledtrig_usb_host);
+
+void usb_led_activity(enum usb_led_event ev)
+{
+	struct led_trigger *trig = NULL;
+
+	switch (ev) {
+	case USB_LED_EVENT_GADGET:
+		trig = ledtrig_usb_gadget;
+		break;
+	case USB_LED_EVENT_HOST:
+		trig = ledtrig_usb_host;
+		break;
+	}
+	/* led_trigger_blink_oneshot() handles trig == NULL gracefully */
+	led_trigger_blink_oneshot(trig, &usb_blink_delay, &usb_blink_delay, 0);
+}
+EXPORT_SYMBOL_GPL(usb_led_activity);
+
+
+static int __init ledtrig_usb_init(void)
+{
+	led_trigger_register_simple("usb-gadget", &ledtrig_usb_gadget);
+	led_trigger_register_simple("usb-host", &ledtrig_usb_host);
+	return 0;
+}
+
+static void __exit ledtrig_usb_exit(void)
+{
+	led_trigger_unregister_simple(ledtrig_usb_gadget);
+	led_trigger_unregister_simple(ledtrig_usb_host);
+}
+
+module_init(ledtrig_usb_init);
+module_exit(ledtrig_usb_exit);
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index d3fe161bec05..bcb96ff207ba 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1664,6 +1664,8 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
 	usbmon_urb_complete(&hcd->self, urb, status);
 	usb_anchor_suspend_wakeups(anchor);
 	usb_unanchor_urb(urb);
+	if (likely(status == 0))
+		usb_led_activity(USB_LED_EVENT_HOST);
 
 	/* pass ownership to the completion handler */
 	urb->status = status;
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index 16d3f6fedd1c..f107bb60a5ab 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -27,6 +27,7 @@
 
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
+#include <linux/usb.h>
 
 /**
  * struct usb_udc - describes one usb device controller
@@ -116,6 +117,9 @@ EXPORT_SYMBOL_GPL(usb_gadget_unmap_request);
 void usb_gadget_giveback_request(struct usb_ep *ep,
 		struct usb_request *req)
 {
+	if (likely(req->status == 0))
+		usb_led_activity(USB_LED_EVENT_GADGET);
+
 	req->complete(ep, req);
 }
 EXPORT_SYMBOL_GPL(usb_gadget_giveback_request);
diff --git a/include/linux/usb.h b/include/linux/usb.h
index d2465bc0e73c..447a7e2fc19b 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1862,6 +1862,18 @@ extern void usb_unregister_notify(struct notifier_block *nb);
 /* debugfs stuff */
 extern struct dentry *usb_debug_root;
 
+/* LED triggers */
+enum usb_led_event {
+	USB_LED_EVENT_HOST = 0,
+	USB_LED_EVENT_GADGET = 1,
+};
+
+#ifdef CONFIG_USB_LED_TRIG
+extern void usb_led_activity(enum usb_led_event ev);
+#else
+static inline void usb_led_activity(enum usb_led_event ev) {}
+#endif
+
 #endif  /* __KERNEL__ */
 
 #endif
-- 
cgit v1.2.3


From 99d440242c08c8a95576c0bc89278f8912f65bda Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Wed, 13 Aug 2014 02:22:37 -0400
Subject: trace, RAS: Replace bare numbers with #defines for PCIe AER error
 strings

Replace bare numbers like "BIT(0)" with the existing #defines, e.g.,
PCI_ERR_COR_RCVR, to improve maintainability.  This way grep will find more
uses of the #defines.

No functional change.

[bhelgaas: changelog]
Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/ras/ras_event.h | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 47da53c27ffa..0f2cca4ccbf0 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -8,6 +8,7 @@
 #include <linux/tracepoint.h>
 #include <linux/edac.h>
 #include <linux/ktime.h>
+#include <linux/pci.h>
 #include <linux/aer.h>
 #include <linux/cper.h>
 
@@ -174,24 +175,24 @@ TRACE_EVENT(mc_event,
  */
 
 #define aer_correctable_errors		\
-	{BIT(0),	"Receiver Error"},		\
-	{BIT(6),	"Bad TLP"},			\
-	{BIT(7),	"Bad DLLP"},			\
-	{BIT(8),	"RELAY_NUM Rollover"},		\
-	{BIT(12),	"Replay Timer Timeout"},	\
-	{BIT(13),	"Advisory Non-Fatal"}
+	{PCI_ERR_COR_RCVR,	"Receiver Error"},	\
+	{PCI_ERR_COR_BAD_TLP,	"Bad TLP"},		\
+	{PCI_ERR_COR_BAD_DLLP,	"Bad DLLP"},		\
+	{PCI_ERR_COR_REP_ROLL,	"RELAY_NUM Rollover"},	\
+	{PCI_ERR_COR_REP_TIMER,	"Replay Timer Timeout"},\
+	{PCI_ERR_COR_ADV_NFAT,	"Advisory Non-Fatal"}
 
 #define aer_uncorrectable_errors		\
-	{BIT(4),	"Data Link Protocol"},		\
-	{BIT(12),	"Poisoned TLP"},		\
-	{BIT(13),	"Flow Control Protocol"},	\
-	{BIT(14),	"Completion Timeout"},		\
-	{BIT(15),	"Completer Abort"},		\
-	{BIT(16),	"Unexpected Completion"},	\
-	{BIT(17),	"Receiver Overflow"},		\
-	{BIT(18),	"Malformed TLP"},		\
-	{BIT(19),	"ECRC"},			\
-	{BIT(20),	"Unsupported Request"}
+	{PCI_ERR_UNC_DLP,	"Data Link Protocol"},		\
+	{PCI_ERR_UNC_POISON_TLP,"Poisoned TLP"},		\
+	{PCI_ERR_UNC_FCP,	"Flow Control Protocol"},	\
+	{PCI_ERR_UNC_COMP_TIME,	"Completion Timeout"},		\
+	{PCI_ERR_UNC_COMP_ABORT,"Completer Abort"},		\
+	{PCI_ERR_UNC_UNX_COMP,	"Unexpected Completion"},	\
+	{PCI_ERR_UNC_RX_OVER,	"Receiver Overflow"},		\
+	{PCI_ERR_UNC_MALF_TLP,	"Malformed TLP"},		\
+	{PCI_ERR_UNC_ECRC,	"ECRC"},			\
+	{PCI_ERR_UNC_UNSUP,	"Unsupported Request"}
 
 TRACE_EVENT(aer_event,
 	TP_PROTO(const char *dev_name,
-- 
cgit v1.2.3


From cb9a684acb3d79a5431ac78832148817debf3a06 Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Wed, 13 Aug 2014 02:22:39 -0400
Subject: trace, RAS: Add additional PCIe AER error strings

Add all AER error bits defined in PCIe r3.0.

[bhelgaas: changelog]
Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/ras/ras_event.h | 35 ++++++++++++++++++++++-------------
 1 file changed, 22 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 0f2cca4ccbf0..0f04a9755d1e 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -174,25 +174,34 @@ TRACE_EVENT(mc_event,
  * u8 severity -	error severity 0:NONFATAL 1:FATAL 2:CORRECTED
  */
 
-#define aer_correctable_errors		\
-	{PCI_ERR_COR_RCVR,	"Receiver Error"},	\
-	{PCI_ERR_COR_BAD_TLP,	"Bad TLP"},		\
-	{PCI_ERR_COR_BAD_DLLP,	"Bad DLLP"},		\
-	{PCI_ERR_COR_REP_ROLL,	"RELAY_NUM Rollover"},	\
-	{PCI_ERR_COR_REP_TIMER,	"Replay Timer Timeout"},\
-	{PCI_ERR_COR_ADV_NFAT,	"Advisory Non-Fatal"}
-
-#define aer_uncorrectable_errors		\
-	{PCI_ERR_UNC_DLP,	"Data Link Protocol"},		\
+#define aer_correctable_errors					\
+	{PCI_ERR_COR_RCVR,	"Receiver Error"},		\
+	{PCI_ERR_COR_BAD_TLP,	"Bad TLP"},			\
+	{PCI_ERR_COR_BAD_DLLP,	"Bad DLLP"},			\
+	{PCI_ERR_COR_REP_ROLL,	"RELAY_NUM Rollover"},		\
+	{PCI_ERR_COR_REP_TIMER,	"Replay Timer Timeout"},	\
+	{PCI_ERR_COR_ADV_NFAT,	"Advisory Non-Fatal Error"},	\
+	{PCI_ERR_COR_INTERNAL,	"Corrected Internal Error"},	\
+	{PCI_ERR_COR_LOG_OVER,	"Header Log Overflow"}
+
+#define aer_uncorrectable_errors				\
+	{PCI_ERR_UNC_TRAIN,	"Undefined"},			\
+	{PCI_ERR_UNC_DLP,	"Data Link Protocol Error"},	\
+	{PCI_ERR_UNC_SURPDN,	"Surprise Down Error"},		\
 	{PCI_ERR_UNC_POISON_TLP,"Poisoned TLP"},		\
-	{PCI_ERR_UNC_FCP,	"Flow Control Protocol"},	\
+	{PCI_ERR_UNC_FCP,	"Flow Control Protocol Error"},	\
 	{PCI_ERR_UNC_COMP_TIME,	"Completion Timeout"},		\
 	{PCI_ERR_UNC_COMP_ABORT,"Completer Abort"},		\
 	{PCI_ERR_UNC_UNX_COMP,	"Unexpected Completion"},	\
 	{PCI_ERR_UNC_RX_OVER,	"Receiver Overflow"},		\
 	{PCI_ERR_UNC_MALF_TLP,	"Malformed TLP"},		\
-	{PCI_ERR_UNC_ECRC,	"ECRC"},			\
-	{PCI_ERR_UNC_UNSUP,	"Unsupported Request"}
+	{PCI_ERR_UNC_ECRC,	"ECRC Error"},			\
+	{PCI_ERR_UNC_UNSUP,	"Unsupported Request Error"},	\
+	{PCI_ERR_UNC_ACSV,	"ACS Violation"},		\
+	{PCI_ERR_UNC_INTN,	"Uncorrectable Internal Error"},\
+	{PCI_ERR_UNC_MCBTLP,	"MC Blocked TLP"},		\
+	{PCI_ERR_UNC_ATOMEG,	"AtomicOp Egress Blocked"},	\
+	{PCI_ERR_UNC_TLPPRE,	"TLP Prefix Blocked Error"}
 
 TRACE_EVENT(aer_event,
 	TP_PROTO(const char *dev_name,
-- 
cgit v1.2.3


From 846fc70986a65563a19ae86928c3acf34f12296d Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Wed, 13 Aug 2014 02:22:40 -0400
Subject: PCI/AER: Rename PCI_ERR_UNC_TRAIN to PCI_ERR_UNC_UND

In PCIe r1.0, sec 5.10.2, bit 0 of the Uncorrectable Error Status, Mask,
and Severity Registers was for "Training Error." In PCIe r1.1, sec 7.10.2,
bit 0 was redefined to be "Undefined."

Rename PCI_ERR_UNC_TRAIN to PCI_ERR_UNC_UND to reflect this change.

No functional change.

[bhelgaas: changelog]
Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/vfio/pci/vfio_pci_config.c | 2 +-
 include/ras/ras_event.h            | 2 +-
 include/uapi/linux/pci_regs.h      | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index e50790e91f76..1de3f94aa7de 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -727,7 +727,7 @@ static int __init init_pci_ext_cap_err_perm(struct perm_bits *perm)
 	p_setd(perm, 0, ALL_VIRT, NO_WRITE);
 
 	/* Writable bits mask */
-	mask =	PCI_ERR_UNC_TRAIN |		/* Training */
+	mask =	PCI_ERR_UNC_UND |		/* Undefined */
 		PCI_ERR_UNC_DLP |		/* Data Link Protocol */
 		PCI_ERR_UNC_SURPDN |		/* Surprise Down */
 		PCI_ERR_UNC_POISON_TLP |	/* Poisoned TLP */
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 0f04a9755d1e..79abb9c71772 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -185,7 +185,7 @@ TRACE_EVENT(mc_event,
 	{PCI_ERR_COR_LOG_OVER,	"Header Log Overflow"}
 
 #define aer_uncorrectable_errors				\
-	{PCI_ERR_UNC_TRAIN,	"Undefined"},			\
+	{PCI_ERR_UNC_UND,	"Undefined"},			\
 	{PCI_ERR_UNC_DLP,	"Data Link Protocol Error"},	\
 	{PCI_ERR_UNC_SURPDN,	"Surprise Down Error"},		\
 	{PCI_ERR_UNC_POISON_TLP,"Poisoned TLP"},		\
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 30db069bce62..99e3182f2c96 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -630,7 +630,7 @@
 
 /* Advanced Error Reporting */
 #define PCI_ERR_UNCOR_STATUS	4	/* Uncorrectable Error Status */
-#define  PCI_ERR_UNC_TRAIN	0x00000001	/* Training */
+#define  PCI_ERR_UNC_UND	0x00000001	/* Undefined */
 #define  PCI_ERR_UNC_DLP	0x00000010	/* Data Link Protocol */
 #define  PCI_ERR_UNC_SURPDN	0x00000020	/* Surprise Down */
 #define  PCI_ERR_UNC_POISON_TLP	0x00001000	/* Poisoned TLP */
-- 
cgit v1.2.3


From d79b6fe17aa279c7015a9c4ee88809dad4be9959 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 25 Sep 2014 18:28:28 +0200
Subject: PM / Domains: Add genpd attach/detach callbacks

While a PM domain can enable PM runtime management of its devices' module
clocks by setting

	genpd->dev_ops.stop = pm_clk_suspend;
	genpd->dev_ops.start = pm_clk_resume;

this also requires registering the clocks with the pm_clk subsystem.
In the legacy case, this is handled by the platform code, after
attaching the device to its PM domain.

When the devices are instantiated from DT, devices are attached to their
PM domains by generic code, leaving no method for the platform-specific
PM domain code to register their clocks.

Add two callbacks, allowing a PM domain to perform platform-specific
tasks when a device is attached to or detached from a PM domain.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 6 ++++++
 include/linux/pm_domain.h   | 2 ++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index cd400575ee0e..2a9f4c5025e3 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1436,6 +1436,9 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 
 	spin_unlock_irq(&dev->power.lock);
 
+	if (genpd->attach_dev)
+		genpd->attach_dev(dev);
+
 	mutex_lock(&gpd_data->lock);
 	gpd_data->base.dev = dev;
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
@@ -1528,6 +1531,9 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	genpd->device_count--;
 	genpd->max_off_time_changed = true;
 
+	if (genpd->detach_dev)
+		genpd->detach_dev(dev);
+
 	spin_lock_irq(&dev->power.lock);
 
 	dev->pm_domain = NULL;
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 292079d8da6b..9a93e622bdea 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -73,6 +73,8 @@ struct generic_pm_domain {
 	bool cached_power_down_ok;
 	struct device_node *of_node; /* Node in device tree */
 	struct gpd_cpu_data *cpu_data;
+	void (*attach_dev)(struct device *dev);
+	void (*detach_dev)(struct device *dev);
 };
 
 static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd)
-- 
cgit v1.2.3


From 263c589bae9eb404df2c1e8d49ec775bb7b288d4 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 25 Sep 2014 17:49:59 +0200
Subject: PM / Domains: Remove legacy API for adding devices through DT

There are no active clients of the legacy API and we now also have a
better way to handle genpd DT support. So let's remove the legacy API.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 33 ---------------------------------
 include/linux/pm_domain.h   | 17 -----------------
 2 files changed, 50 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 2a9f4c5025e3..18cc68d058d6 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1456,39 +1456,6 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	return ret;
 }
 
-/**
- * __pm_genpd_of_add_device - Add a device to an I/O PM domain.
- * @genpd_node: Device tree node pointer representing a PM domain to which the
- *   the device is added to.
- * @dev: Device to be added.
- * @td: Set of PM QoS timing parameters to attach to the device.
- */
-int __pm_genpd_of_add_device(struct device_node *genpd_node, struct device *dev,
-			     struct gpd_timing_data *td)
-{
-	struct generic_pm_domain *genpd = NULL, *gpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	if (IS_ERR_OR_NULL(genpd_node) || IS_ERR_OR_NULL(dev))
-		return -EINVAL;
-
-	mutex_lock(&gpd_list_lock);
-	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
-		if (gpd->of_node == genpd_node) {
-			genpd = gpd;
-			break;
-		}
-	}
-	mutex_unlock(&gpd_list_lock);
-
-	if (!genpd)
-		return -EINVAL;
-
-	return __pm_genpd_add_device(genpd, dev, td);
-}
-
-
 /**
  * __pm_genpd_name_add_device - Find I/O PM domain and add a device to it.
  * @domain_name: Name of the PM domain to add the device to.
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 9a93e622bdea..ed4f4a79c528 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -71,7 +71,6 @@ struct generic_pm_domain {
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
 	bool max_off_time_changed;
 	bool cached_power_down_ok;
-	struct device_node *of_node; /* Node in device tree */
 	struct gpd_cpu_data *cpu_data;
 	void (*attach_dev)(struct device *dev);
 	void (*detach_dev)(struct device *dev);
@@ -124,10 +123,6 @@ extern int __pm_genpd_add_device(struct generic_pm_domain *genpd,
 				 struct device *dev,
 				 struct gpd_timing_data *td);
 
-extern int __pm_genpd_of_add_device(struct device_node *genpd_node,
-				    struct device *dev,
-				    struct gpd_timing_data *td);
-
 extern int __pm_genpd_name_add_device(const char *domain_name,
 				      struct device *dev,
 				      struct gpd_timing_data *td);
@@ -169,12 +164,6 @@ static inline int __pm_genpd_add_device(struct generic_pm_domain *genpd,
 {
 	return -ENOSYS;
 }
-static inline int __pm_genpd_of_add_device(struct device_node *genpd_node,
-					   struct device *dev,
-					   struct gpd_timing_data *td)
-{
-	return -ENOSYS;
-}
 static inline int __pm_genpd_name_add_device(const char *domain_name,
 					     struct device *dev,
 					     struct gpd_timing_data *td)
@@ -240,12 +229,6 @@ static inline int pm_genpd_add_device(struct generic_pm_domain *genpd,
 	return __pm_genpd_add_device(genpd, dev, NULL);
 }
 
-static inline int pm_genpd_of_add_device(struct device_node *genpd_node,
-					 struct device *dev)
-{
-	return __pm_genpd_of_add_device(genpd_node, dev, NULL);
-}
-
 static inline int pm_genpd_name_add_device(const char *domain_name,
 					   struct device *dev)
 {
-- 
cgit v1.2.3


From 7c94e1c157a227837b04f02f5edeff8301410ba2 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@canonical.com>
Date: Thu, 25 Sep 2014 23:23:43 +0800
Subject: block: introduce blk_flush_queue to drive flush machinery

This patch introduces 'struct blk_flush_queue' and puts all
flush machinery related fields into this structure, so that

	- flush implementation details aren't exposed to driver
	- it is easy to convert to per dispatch-queue flush machinery

This patch is basically a mechanical replacement.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c       |   4 +-
 block/blk-flush.c      | 109 ++++++++++++++++++++++++++++++-------------------
 block/blk-mq.c         |  10 +++--
 block/blk.h            |  22 +++++++++-
 include/linux/blkdev.h |  10 +----
 5 files changed, 99 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 222fe84d6ac4..cfaca8ca6cc4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -390,11 +390,13 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
 		 * be drained.  Check all the queues and counters.
 		 */
 		if (drain_all) {
+			struct blk_flush_queue *fq = blk_get_flush_queue(q);
 			drain |= !list_empty(&q->queue_head);
 			for (i = 0; i < 2; i++) {
 				drain |= q->nr_rqs[i];
 				drain |= q->in_flight[i];
-				drain |= !list_empty(&q->flush_queue[i]);
+				if (fq)
+				    drain |= !list_empty(&fq->flush_queue[i]);
 			}
 		}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index caf44756d329..b01a86d6bf86 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -28,7 +28,7 @@
  *
  * The actual execution of flush is double buffered.  Whenever a request
  * needs to execute PRE or POSTFLUSH, it queues at
- * q->flush_queue[q->flush_pending_idx].  Once certain criteria are met, a
+ * fq->flush_queue[fq->flush_pending_idx].  Once certain criteria are met, a
  * flush is issued and the pending_idx is toggled.  When the flush
  * completes, all the requests which were pending are proceeded to the next
  * step.  This allows arbitrary merging of different types of FLUSH/FUA
@@ -155,7 +155,7 @@ static bool blk_flush_queue_rq(struct request *rq, bool add_front)
  * completion and trigger the next step.
  *
  * CONTEXT:
- * spin_lock_irq(q->queue_lock or q->mq_flush_lock)
+ * spin_lock_irq(q->queue_lock or fq->mq_flush_lock)
  *
  * RETURNS:
  * %true if requests were added to the dispatch queue, %false otherwise.
@@ -164,7 +164,8 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 				   int error)
 {
 	struct request_queue *q = rq->q;
-	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
+	struct blk_flush_queue *fq = blk_get_flush_queue(q);
+	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
 	bool queued = false, kicked;
 
 	BUG_ON(rq->flush.seq & seq);
@@ -180,12 +181,12 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 	case REQ_FSEQ_POSTFLUSH:
 		/* queue for flush */
 		if (list_empty(pending))
-			q->flush_pending_since = jiffies;
+			fq->flush_pending_since = jiffies;
 		list_move_tail(&rq->flush.list, pending);
 		break;
 
 	case REQ_FSEQ_DATA:
-		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
+		list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
 		queued = blk_flush_queue_rq(rq, true);
 		break;
 
@@ -220,17 +221,18 @@ static void flush_end_io(struct request *flush_rq, int error)
 	bool queued = false;
 	struct request *rq, *n;
 	unsigned long flags = 0;
+	struct blk_flush_queue *fq = blk_get_flush_queue(q);
 
 	if (q->mq_ops) {
-		spin_lock_irqsave(&q->mq_flush_lock, flags);
+		spin_lock_irqsave(&fq->mq_flush_lock, flags);
 		flush_rq->tag = -1;
 	}
 
-	running = &q->flush_queue[q->flush_running_idx];
-	BUG_ON(q->flush_pending_idx == q->flush_running_idx);
+	running = &fq->flush_queue[fq->flush_running_idx];
+	BUG_ON(fq->flush_pending_idx == fq->flush_running_idx);
 
 	/* account completion of the flush request */
-	q->flush_running_idx ^= 1;
+	fq->flush_running_idx ^= 1;
 
 	if (!q->mq_ops)
 		elv_completed_request(q, flush_rq);
@@ -254,13 +256,13 @@ static void flush_end_io(struct request *flush_rq, int error)
 	 * directly into request_fn may confuse the driver.  Always use
 	 * kblockd.
 	 */
-	if (queued || q->flush_queue_delayed) {
+	if (queued || fq->flush_queue_delayed) {
 		WARN_ON(q->mq_ops);
 		blk_run_queue_async(q);
 	}
-	q->flush_queue_delayed = 0;
+	fq->flush_queue_delayed = 0;
 	if (q->mq_ops)
-		spin_unlock_irqrestore(&q->mq_flush_lock, flags);
+		spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 }
 
 /**
@@ -271,33 +273,34 @@ static void flush_end_io(struct request *flush_rq, int error)
  * Please read the comment at the top of this file for more info.
  *
  * CONTEXT:
- * spin_lock_irq(q->queue_lock or q->mq_flush_lock)
+ * spin_lock_irq(q->queue_lock or fq->mq_flush_lock)
  *
  * RETURNS:
  * %true if flush was issued, %false otherwise.
  */
 static bool blk_kick_flush(struct request_queue *q)
 {
-	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
+	struct blk_flush_queue *fq = blk_get_flush_queue(q);
+	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
 	struct request *first_rq =
 		list_first_entry(pending, struct request, flush.list);
-	struct request *flush_rq = q->flush_rq;
+	struct request *flush_rq = fq->flush_rq;
 
 	/* C1 described at the top of this file */
-	if (q->flush_pending_idx != q->flush_running_idx || list_empty(pending))
+	if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending))
 		return false;
 
 	/* C2 and C3 */
-	if (!list_empty(&q->flush_data_in_flight) &&
+	if (!list_empty(&fq->flush_data_in_flight) &&
 	    time_before(jiffies,
-			q->flush_pending_since + FLUSH_PENDING_TIMEOUT))
+			fq->flush_pending_since + FLUSH_PENDING_TIMEOUT))
 		return false;
 
 	/*
 	 * Issue flush and toggle pending_idx.  This makes pending_idx
 	 * different from running_idx, which means flush is in flight.
 	 */
-	q->flush_pending_idx ^= 1;
+	fq->flush_pending_idx ^= 1;
 
 	blk_rq_init(q, flush_rq);
 	if (q->mq_ops)
@@ -329,6 +332,7 @@ static void mq_flush_data_end_io(struct request *rq, int error)
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	unsigned long flags;
+	struct blk_flush_queue *fq = blk_get_flush_queue(q);
 
 	ctx = rq->mq_ctx;
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
@@ -337,10 +341,10 @@ static void mq_flush_data_end_io(struct request *rq, int error)
 	 * After populating an empty queue, kick it to avoid stall.  Read
 	 * the comment in flush_end_io().
 	 */
-	spin_lock_irqsave(&q->mq_flush_lock, flags);
+	spin_lock_irqsave(&fq->mq_flush_lock, flags);
 	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error))
 		blk_mq_run_hw_queue(hctx, true);
-	spin_unlock_irqrestore(&q->mq_flush_lock, flags);
+	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 }
 
 /**
@@ -408,11 +412,13 @@ void blk_insert_flush(struct request *rq)
 	rq->cmd_flags |= REQ_FLUSH_SEQ;
 	rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
 	if (q->mq_ops) {
+		struct blk_flush_queue *fq = blk_get_flush_queue(q);
+
 		rq->end_io = mq_flush_data_end_io;
 
-		spin_lock_irq(&q->mq_flush_lock);
+		spin_lock_irq(&fq->mq_flush_lock);
 		blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
-		spin_unlock_irq(&q->mq_flush_lock);
+		spin_unlock_irq(&fq->mq_flush_lock);
 		return;
 	}
 	rq->end_io = flush_data_end_io;
@@ -473,31 +479,52 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 }
 EXPORT_SYMBOL(blkdev_issue_flush);
 
-static int blk_mq_init_flush(struct request_queue *q)
+static struct blk_flush_queue *blk_alloc_flush_queue(
+		struct request_queue *q)
 {
-	struct blk_mq_tag_set *set = q->tag_set;
+	struct blk_flush_queue *fq;
+	int rq_sz = sizeof(struct request);
 
-	spin_lock_init(&q->mq_flush_lock);
+	fq = kzalloc(sizeof(*fq), GFP_KERNEL);
+	if (!fq)
+		goto fail;
 
-	q->flush_rq = kzalloc(round_up(sizeof(struct request) +
-				set->cmd_size, cache_line_size()),
-				GFP_KERNEL);
-	if (!q->flush_rq)
-		return -ENOMEM;
-	return 0;
+	if (q->mq_ops) {
+		spin_lock_init(&fq->mq_flush_lock);
+		rq_sz = round_up(rq_sz + q->tag_set->cmd_size,
+				cache_line_size());
+	}
+
+	fq->flush_rq = kzalloc(rq_sz, GFP_KERNEL);
+	if (!fq->flush_rq)
+		goto fail_rq;
+
+	INIT_LIST_HEAD(&fq->flush_queue[0]);
+	INIT_LIST_HEAD(&fq->flush_queue[1]);
+	INIT_LIST_HEAD(&fq->flush_data_in_flight);
+
+	return fq;
+
+ fail_rq:
+	kfree(fq);
+ fail:
+	return NULL;
 }
 
-int blk_init_flush(struct request_queue *q)
+static void blk_free_flush_queue(struct blk_flush_queue *fq)
 {
-	INIT_LIST_HEAD(&q->flush_queue[0]);
-	INIT_LIST_HEAD(&q->flush_queue[1]);
-	INIT_LIST_HEAD(&q->flush_data_in_flight);
+	/* bio based request queue hasn't flush queue */
+	if (!fq)
+		return;
 
-	if (q->mq_ops)
-		return blk_mq_init_flush(q);
+	kfree(fq->flush_rq);
+	kfree(fq);
+}
 
-	q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
-	if (!q->flush_rq)
+int blk_init_flush(struct request_queue *q)
+{
+	q->fq = blk_alloc_flush_queue(q);
+	if (!q->fq)
 		return -ENOMEM;
 
 	return 0;
@@ -505,5 +532,5 @@ int blk_init_flush(struct request_queue *q)
 
 void blk_exit_flush(struct request_queue *q)
 {
-	kfree(q->flush_rq);
+	blk_free_flush_queue(q->fq);
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 2758cdf2de94..d39e8a5eaeaa 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -508,20 +508,22 @@ void blk_mq_kick_requeue_list(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_mq_kick_requeue_list);
 
-static inline bool is_flush_request(struct request *rq, unsigned int tag)
+static inline bool is_flush_request(struct request *rq,
+		struct blk_flush_queue *fq, unsigned int tag)
 {
 	return ((rq->cmd_flags & REQ_FLUSH_SEQ) &&
-			rq->q->flush_rq->tag == tag);
+			fq->flush_rq->tag == tag);
 }
 
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
 {
 	struct request *rq = tags->rqs[tag];
+	struct blk_flush_queue *fq = blk_get_flush_queue(rq->q);
 
-	if (!is_flush_request(rq, tag))
+	if (!is_flush_request(rq, fq, tag))
 		return rq;
 
-	return rq->q->flush_rq;
+	return fq->flush_rq;
 }
 EXPORT_SYMBOL(blk_mq_tag_to_rq);
 
diff --git a/block/blk.h b/block/blk.h
index c6fa3d4c6a89..833c4ac6c4eb 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -12,11 +12,28 @@
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
 
+struct blk_flush_queue {
+	unsigned int		flush_queue_delayed:1;
+	unsigned int		flush_pending_idx:1;
+	unsigned int		flush_running_idx:1;
+	unsigned long		flush_pending_since;
+	struct list_head	flush_queue[2];
+	struct list_head	flush_data_in_flight;
+	struct request		*flush_rq;
+	spinlock_t		mq_flush_lock;
+};
+
 extern struct kmem_cache *blk_requestq_cachep;
 extern struct kmem_cache *request_cachep;
 extern struct kobj_type blk_queue_ktype;
 extern struct ida blk_queue_ida;
 
+static inline struct blk_flush_queue *blk_get_flush_queue(
+		struct request_queue *q)
+{
+	return q->fq;
+}
+
 static inline void __blk_get_queue(struct request_queue *q)
 {
 	kobject_get(&q->kobj);
@@ -89,6 +106,7 @@ void blk_insert_flush(struct request *rq);
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
 	struct request *rq;
+	struct blk_flush_queue *fq = blk_get_flush_queue(q);
 
 	while (1) {
 		if (!list_empty(&q->queue_head)) {
@@ -111,9 +129,9 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 		 * should be restarted later. Please see flush_end_io() for
 		 * details.
 		 */
-		if (q->flush_pending_idx != q->flush_running_idx &&
+		if (fq->flush_pending_idx != fq->flush_running_idx &&
 				!queue_flush_queueable(q)) {
-			q->flush_queue_delayed = 1;
+			fq->flush_queue_delayed = 1;
 			return NULL;
 		}
 		if (unlikely(blk_queue_bypass(q)) ||
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e267bf0db559..49f3461e4272 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -36,6 +36,7 @@ struct request;
 struct sg_io_hdr;
 struct bsg_job;
 struct blkcg_gq;
+struct blk_flush_queue;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -455,14 +456,7 @@ struct request_queue {
 	 */
 	unsigned int		flush_flags;
 	unsigned int		flush_not_queueable:1;
-	unsigned int		flush_queue_delayed:1;
-	unsigned int		flush_pending_idx:1;
-	unsigned int		flush_running_idx:1;
-	unsigned long		flush_pending_since;
-	struct list_head	flush_queue[2];
-	struct list_head	flush_data_in_flight;
-	struct request		*flush_rq;
-	spinlock_t		mq_flush_lock;
+	struct blk_flush_queue	*fq;
 
 	struct list_head	requeue_list;
 	spinlock_t		requeue_lock;
-- 
cgit v1.2.3


From f70ced09170761acb69840cafaace4abc72cba4b Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@canonical.com>
Date: Thu, 25 Sep 2014 23:23:47 +0800
Subject: blk-mq: support per-distpatch_queue flush machinery

This patch supports to run one single flush machinery for
each blk-mq dispatch queue, so that:

- current init_request and exit_request callbacks can
cover flush request too, then the buggy copying way of
initializing flush request's pdu can be fixed

- flushing performance gets improved in case of multi hw-queue

In fio sync write test over virtio-blk(4 hw queues, ioengine=sync,
iodepth=64, numjobs=4, bs=4K), it is observed that througput gets
increased a lot over my test environment:
	- throughput: +70% in case of virtio-blk over null_blk
	- throughput: +30% in case of virtio-blk over SSD image

The multi virtqueue feature isn't merged to QEMU yet, and patches for
the feature can be found in below tree:

	git://kernel.ubuntu.com/ming/qemu.git  	v2.1.0-mq.4

And simply passing 'num_queues=4 vectors=5' should be enough to
enable multi queue(quad queue) feature for QEMU virtio-blk.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c       |  2 +-
 block/blk-flush.c      | 21 ++++++++++++++-------
 block/blk-mq.c         | 50 ++++++++++++++++++++++++--------------------------
 block/blk-sysfs.c      |  4 ++--
 block/blk.h            | 16 +++++++++++++---
 include/linux/blk-mq.h |  6 ++++++
 6 files changed, 60 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index b1dd4e086740..e1c2775c7597 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -704,7 +704,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	if (!q)
 		return NULL;
 
-	q->fq = blk_alloc_flush_queue(q);
+	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, 0);
 	if (!q->fq)
 		return NULL;
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 004d95e4098e..20badd7b9d1b 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -305,8 +305,15 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	fq->flush_pending_idx ^= 1;
 
 	blk_rq_init(q, flush_rq);
-	if (q->mq_ops)
-		blk_mq_clone_flush_request(flush_rq, first_rq);
+
+	/*
+	 * Borrow tag from the first request since they can't
+	 * be in flight at the same time.
+	 */
+	if (q->mq_ops) {
+		flush_rq->mq_ctx = first_rq->mq_ctx;
+		flush_rq->tag = first_rq->tag;
+	}
 
 	flush_rq->cmd_type = REQ_TYPE_FS;
 	flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
@@ -480,22 +487,22 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 }
 EXPORT_SYMBOL(blkdev_issue_flush);
 
-struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q)
+struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
+		int node, int cmd_size)
 {
 	struct blk_flush_queue *fq;
 	int rq_sz = sizeof(struct request);
 
-	fq = kzalloc(sizeof(*fq), GFP_KERNEL);
+	fq = kzalloc_node(sizeof(*fq), GFP_KERNEL, node);
 	if (!fq)
 		goto fail;
 
 	if (q->mq_ops) {
 		spin_lock_init(&fq->mq_flush_lock);
-		rq_sz = round_up(rq_sz + q->tag_set->cmd_size,
-				cache_line_size());
+		rq_sz = round_up(rq_sz + cmd_size, cache_line_size());
 	}
 
-	fq->flush_rq = kzalloc(rq_sz, GFP_KERNEL);
+	fq->flush_rq = kzalloc_node(rq_sz, GFP_KERNEL, node);
 	if (!fq->flush_rq)
 		goto fail_rq;
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 53b6def12fc4..4e7a31466139 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -281,26 +281,6 @@ void blk_mq_free_request(struct request *rq)
 	__blk_mq_free_request(hctx, ctx, rq);
 }
 
-/*
- * Clone all relevant state from a request that has been put on hold in
- * the flush state machine into the preallocated flush request that hangs
- * off the request queue.
- *
- * For a driver the flush request should be invisible, that's why we are
- * impersonating the original request here.
- */
-void blk_mq_clone_flush_request(struct request *flush_rq,
-		struct request *orig_rq)
-{
-	struct blk_mq_hw_ctx *hctx =
-		orig_rq->q->mq_ops->map_queue(orig_rq->q, orig_rq->mq_ctx->cpu);
-
-	flush_rq->mq_ctx = orig_rq->mq_ctx;
-	flush_rq->tag = orig_rq->tag;
-	memcpy(blk_mq_rq_to_pdu(flush_rq), blk_mq_rq_to_pdu(orig_rq),
-		hctx->cmd_size);
-}
-
 inline void __blk_mq_end_request(struct request *rq, int error)
 {
 	blk_account_io_done(rq);
@@ -1516,12 +1496,20 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 {
+	unsigned flush_start_tag = set->queue_depth;
+
 	blk_mq_tag_idle(hctx);
 
+	if (set->ops->exit_request)
+		set->ops->exit_request(set->driver_data,
+				       hctx->fq->flush_rq, hctx_idx,
+				       flush_start_tag + hctx_idx);
+
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
 	blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
+	blk_free_flush_queue(hctx->fq);
 	kfree(hctx->ctxs);
 	blk_mq_free_bitmap(&hctx->ctx_map);
 }
@@ -1556,6 +1544,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
 {
 	int node;
+	unsigned flush_start_tag = set->queue_depth;
 
 	node = hctx->numa_node;
 	if (node == NUMA_NO_NODE)
@@ -1594,8 +1583,23 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
 		goto free_bitmap;
 
+	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size);
+	if (!hctx->fq)
+		goto exit_hctx;
+
+	if (set->ops->init_request &&
+	    set->ops->init_request(set->driver_data,
+				   hctx->fq->flush_rq, hctx_idx,
+				   flush_start_tag + hctx_idx, node))
+		goto free_fq;
+
 	return 0;
 
+ free_fq:
+	kfree(hctx->fq);
+ exit_hctx:
+	if (set->ops->exit_hctx)
+		set->ops->exit_hctx(hctx, hctx_idx);
  free_bitmap:
 	blk_mq_free_bitmap(&hctx->ctx_map);
  free_ctxs:
@@ -1862,16 +1866,10 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 
 	blk_mq_add_queue_tag_set(set, q);
 
-	q->fq = blk_alloc_flush_queue(q);
-	if (!q->fq)
-		goto err_hw_queues;
-
 	blk_mq_map_swqueue(q);
 
 	return q;
 
-err_hw_queues:
-	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
 err_hw:
 	blk_cleanup_queue(q);
 err_hctxs:
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 718cffc4c678..e8f38a36c625 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -517,10 +517,10 @@ static void blk_release_queue(struct kobject *kobj)
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
-	blk_free_flush_queue(q->fq);
-
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
+	else
+		blk_free_flush_queue(q->fq);
 
 	blk_trace_shutdown(q);
 
diff --git a/block/blk.h b/block/blk.h
index 7ecdd8517e69..43b036185712 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -2,6 +2,8 @@
 #define BLK_INTERNAL_H
 
 #include <linux/idr.h>
+#include <linux/blk-mq.h>
+#include "blk-mq.h"
 
 /* Amount of time in which a process may batch requests */
 #define BLK_BATCH_TIME	(HZ/50UL)
@@ -31,7 +33,14 @@ extern struct ida blk_queue_ida;
 static inline struct blk_flush_queue *blk_get_flush_queue(
 		struct request_queue *q, struct blk_mq_ctx *ctx)
 {
-	return q->fq;
+	struct blk_mq_hw_ctx *hctx;
+
+	if (!q->mq_ops)
+		return q->fq;
+
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+	return hctx->fq;
 }
 
 static inline void __blk_get_queue(struct request_queue *q)
@@ -39,8 +48,9 @@ static inline void __blk_get_queue(struct request_queue *q)
 	kobject_get(&q->kobj);
 }
 
-struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q);
-void blk_free_flush_queue(struct blk_flush_queue *fq);
+struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
+		int node, int cmd_size);
+void blk_free_flush_queue(struct blk_flush_queue *q);
 
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 325349559fb0..02c5d950f444 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -4,6 +4,7 @@
 #include <linux/blkdev.h>
 
 struct blk_mq_tags;
+struct blk_flush_queue;
 
 struct blk_mq_cpu_notifier {
 	struct list_head list;
@@ -34,6 +35,7 @@ struct blk_mq_hw_ctx {
 
 	struct request_queue	*queue;
 	unsigned int		queue_num;
+	struct blk_flush_queue	*fq;
 
 	void			*driver_data;
 
@@ -119,6 +121,10 @@ struct blk_mq_ops {
 	/*
 	 * Called for every command allocated by the block layer to allow
 	 * the driver to set up driver specific data.
+	 *
+	 * Tag greater than or equal to queue_depth is for setting up
+	 * flush request.
+	 *
 	 * Ditto for exit/teardown.
 	 */
 	init_request_fn		*init_request;
-- 
cgit v1.2.3


From 4b47c3f5f7a330ce953b799872ded7bdc59bfd27 Mon Sep 17 00:00:00 2001
From: Mark yao <mark.yao@rock-chips.com>
Date: Fri, 12 Sep 2014 19:45:27 +0800
Subject: clk: rockchip: rk3288: add reset indices for SOFTRST9-11

The patch add the rest of the indices of the additional reset
registers from the updated TRM.

Signed-off-by: Mark yao <mark.yao@rock-chips.com>
Reviewed-by: Doug Anderson <dianders@chromium.org>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 include/dt-bindings/clock/rk3288-cru.h | 43 ++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/rk3288-cru.h b/include/dt-bindings/clock/rk3288-cru.h
index ebcb460ea4ad..e65d5224e848 100644
--- a/include/dt-bindings/clock/rk3288-cru.h
+++ b/include/dt-bindings/clock/rk3288-cru.h
@@ -276,3 +276,46 @@
 #define SRST_USBHOST1_CON	140
 #define SRST_USB_ADP		141
 #define SRST_ACC_EFUSE		142
+
+#define SRST_CORESIGHT		144
+#define SRST_PD_CORE_AHB_NOC	145
+#define SRST_PD_CORE_APB_NOC	146
+#define SRST_PD_CORE_MP_AXI	147
+#define SRST_GIC		148
+#define SRST_LCDC_PWM0		149
+#define SRST_LCDC_PWM1		150
+#define SRST_VIO0_H2P_BRG	151
+#define SRST_VIO1_H2P_BRG	152
+#define SRST_RGA_H2P_BRG	153
+#define SRST_HEVC		154
+#define SRST_TSADC		159
+
+#define SRST_DDRPHY0		160
+#define SRST_DDRPHY0_APB	161
+#define SRST_DDRCTRL0		162
+#define SRST_DDRCTRL0_APB	163
+#define SRST_DDRPHY0_CTRL	164
+#define SRST_DDRPHY1		165
+#define SRST_DDRPHY1_APB	166
+#define SRST_DDRCTRL1		167
+#define SRST_DDRCTRL1_APB	168
+#define SRST_DDRPHY1_CTRL	169
+#define SRST_DDRMSCH0		170
+#define SRST_DDRMSCH1		171
+#define SRST_CRYPTO		174
+#define SRST_C2C_HOST		175
+
+#define SRST_LCDC1_AXI		176
+#define SRST_LCDC1_AHB		177
+#define SRST_LCDC1_DCLK		178
+#define SRST_UART0		179
+#define SRST_UART1		180
+#define SRST_UART2		181
+#define SRST_UART3		182
+#define SRST_UART4		183
+#define SRST_SIMC		186
+#define SRST_PS2C		187
+#define SRST_TSP		188
+#define SRST_TSP_CLKIN0		189
+#define SRST_TSP_CLKIN1		190
+#define SRST_TSP_27M		191
-- 
cgit v1.2.3


From 5e9a3d70710ef7196170a8feca4aecb73d8eb9c4 Mon Sep 17 00:00:00 2001
From: Kever Yang <kever.yang@rock-chips.com>
Date: Wed, 24 Sep 2014 21:36:34 +0800
Subject: clk: rockchip: add some needed clock binding id for rk3288

This patch add some clock binding id for different modules
that under development and going to send upstream.

Signed-off-by: Kever Yang <kever.yang@rock-chips.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 include/dt-bindings/clock/rk3288-cru.h | 38 +++++++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/dt-bindings/clock/rk3288-cru.h b/include/dt-bindings/clock/rk3288-cru.h
index e65d5224e848..750e5587a7aa 100644
--- a/include/dt-bindings/clock/rk3288-cru.h
+++ b/include/dt-bindings/clock/rk3288-cru.h
@@ -61,6 +61,15 @@
 #define SCLK_LCDC_PWM1		101
 #define SCLK_MAC_RX		102
 #define SCLK_MAC_TX		103
+#define SCLK_EDP_24M		104
+#define SCLK_EDP		105
+#define SCLK_RGA		106
+#define SCLK_ISP		107
+#define SCLK_ISP_JPE		108
+#define SCLK_HDMI_HDCP		109
+#define SCLK_HDMI_CEC		110
+#define SCLK_HEVC_CABAC		111
+#define SCLK_HEVC_CORE		112
 
 #define DCLK_VOP0		190
 #define DCLK_VOP1		191
@@ -75,6 +84,16 @@
 #define ACLK_VOP1		198
 #define ACLK_CRYPTO		199
 #define ACLK_RGA		200
+#define ACLK_RGA_NIU		201
+#define ACLK_IEP		202
+#define ACLK_VIO0_NIU		203
+#define ACLK_VIP		204
+#define ACLK_ISP		205
+#define ACLK_VIO1_NIU		206
+#define ACLK_HEVC		207
+#define ACLK_VCODEC		208
+#define ACLK_CPU		209
+#define ACLK_PERI		210
 
 /* pclk gates */
 #define PCLK_GPIO0		320
@@ -112,6 +131,15 @@
 #define PCLK_PS2C		352
 #define PCLK_TIMER		353
 #define PCLK_TZPC		354
+#define PCLK_EDP_CTRL		355
+#define PCLK_MIPI_DSI0		356
+#define PCLK_MIPI_DSI1		357
+#define PCLK_MIPI_CSI		358
+#define PCLK_LVDS_PHY		359
+#define PCLK_HDMI_CTRL		360
+#define PCLK_VIO2_H2P		361
+#define PCLK_CPU		362
+#define PCLK_PERI		363
 
 /* hclk gates */
 #define HCLK_GPS		448
@@ -137,8 +165,16 @@
 #define HCLK_IEP		468
 #define HCLK_ISP		469
 #define HCLK_RGA		470
+#define HCLK_VIO_AHB_ARBI	471
+#define HCLK_VIO_NIU		472
+#define HCLK_VIP		473
+#define HCLK_VIO2_H2P		474
+#define HCLK_HEVC		475
+#define HCLK_VCODEC		476
+#define HCLK_CPU		477
+#define HCLK_PERI		478
 
-#define CLK_NR_CLKS		(HCLK_RGA + 1)
+#define CLK_NR_CLKS		(HCLK_PERI + 1)
 
 /* soft-reset indices */
 #define SRST_CORE0		0
-- 
cgit v1.2.3


From b52f4914f3be3ff50e7308e3ce03a2ce71195ecc Mon Sep 17 00:00:00 2001
From: Mike Turquette <mturquette@linaro.org>
Date: Mon, 8 Sep 2014 23:11:26 -0700
Subject: asm-generic: COMMON_CLK defines __clk_{get,put}
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If CONFIG_COMMON_CLK is selected then __clk_get and __clk_put are
defined in drivers/clk/clk.c and declared in include/linux/clkdev.h.

Sylwester's series[0] to properly support clk_{get,put} in the common
clock framework made changes to the asm-specific clkdev.h headers, but
not the asm-generic version. Tomeu's recent changes[1] to introduce a
provider/consumer split in the clock framework uncovered this problem,
causing the following build error on any architecture using the
asm-generic clkdev.h (e.g. x86 architecture and the ACPI LPSS driver):

In file included from drivers/acpi/acpi_lpss.c:15:0:
include/linux/clkdev.h:59:5: error: conflicting types for ‘__clk_get’
 int __clk_get(struct clk_core *clk);
     ^
In file included from arch/x86/include/generated/asm/clkdev.h:1:0,
                 from include/linux/clkdev.h:15,
                 from drivers/acpi/acpi_lpss.c:15:
include/asm-generic/clkdev.h:20:19: note: previous definition of ‘__clk_get’ was here
 static inline int __clk_get(struct clk *clk) { return 1; }
                   ^

Fixed by only declarating  __clk_get and __clk_put when
CONFIG_COMMON_CLK is set.

[0] http://lkml.kernel.org/r/<1386177127-2894-5-git-send-email-s.nawrocki@samsung.com>
[1] http://lkml.kernel.org/r/<1409758148-20104-1-git-send-email-tomeu.vizoso@collabora.com>

Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 include/asm-generic/clkdev.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/clkdev.h b/include/asm-generic/clkdev.h
index 90a32a61dd21..4ff334749ed5 100644
--- a/include/asm-generic/clkdev.h
+++ b/include/asm-generic/clkdev.h
@@ -15,10 +15,12 @@
 
 #include <linux/slab.h>
 
+#ifndef CONFIG_COMMON_CLK
 struct clk;
 
 static inline int __clk_get(struct clk *clk) { return 1; }
 static inline void __clk_put(struct clk *clk) { }
+#endif
 
 static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
 {
-- 
cgit v1.2.3


From 53e50398968d43338c4d932114e68bc099fc5fbd Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Sat, 20 Sep 2014 14:52:30 -0700
Subject: net: Remove gso_send_check as an offload callback

The send_check logic was only interesting in cases of TCP offload and
UDP UFO where the checksum needed to be initialized to the pseudo
header checksum. Now we've moved that logic into the related
gso_segment functions so gso_send_check is no longer needed.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 -
 net/core/dev.c            | 10 ----------
 net/ipv4/af_inet.c        | 36 ------------------------------------
 net/ipv4/gre_offload.c    | 11 +++--------
 net/ipv4/tcp_offload.c    |  6 ------
 net/ipv4/udp_offload.c    |  6 ------
 net/ipv6/ip6_offload.c    | 27 ---------------------------
 net/ipv6/tcpv6_offload.c  |  6 ------
 net/ipv6/udp_offload.c    |  6 ------
 net/mpls/mpls_gso.c       |  7 -------
 10 files changed, 3 insertions(+), 113 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4354b4307e37..9f5d293a0281 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1911,7 +1911,6 @@ struct packet_type {
 struct offload_callbacks {
 	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
 						netdev_features_t features);
-	int			(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
 					       struct sk_buff *skb);
 	int			(*gro_complete)(struct sk_buff *skb, int nhoff);
diff --git a/net/core/dev.c b/net/core/dev.c
index db0388607329..e2ced01c01e4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2422,16 +2422,6 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, &offload_base, list) {
 		if (ptype->type == type && ptype->callbacks.gso_segment) {
-			if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
-				int err;
-
-				err = ptype->callbacks.gso_send_check(skb);
-				segs = ERR_PTR(err);
-				if (err || skb_gso_ok(skb, features))
-					break;
-				__skb_push(skb, (skb->data -
-						 skb_network_header(skb)));
-			}
 			segs = ptype->callbacks.gso_segment(skb, features);
 			break;
 		}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 72011cc4c13b..28e589c5f32d 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1197,40 +1197,6 @@ int inet_sk_rebuild_header(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_sk_rebuild_header);
 
-static int inet_gso_send_check(struct sk_buff *skb)
-{
-	const struct net_offload *ops;
-	const struct iphdr *iph;
-	int proto;
-	int ihl;
-	int err = -EINVAL;
-
-	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
-		goto out;
-
-	iph = ip_hdr(skb);
-	ihl = iph->ihl * 4;
-	if (ihl < sizeof(*iph))
-		goto out;
-
-	proto = iph->protocol;
-
-	/* Warning: after this point, iph might be no longer valid */
-	if (unlikely(!pskb_may_pull(skb, ihl)))
-		goto out;
-	__skb_pull(skb, ihl);
-
-	skb_reset_transport_header(skb);
-	err = -EPROTONOSUPPORT;
-
-	ops = rcu_dereference(inet_offloads[proto]);
-	if (likely(ops && ops->callbacks.gso_send_check))
-		err = ops->callbacks.gso_send_check(skb);
-
-out:
-	return err;
-}
-
 static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 					netdev_features_t features)
 {
@@ -1655,7 +1621,6 @@ static int ipv4_proc_init(void);
 static struct packet_offload ip_packet_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IP),
 	.callbacks = {
-		.gso_send_check = inet_gso_send_check,
 		.gso_segment = inet_gso_segment,
 		.gro_receive = inet_gro_receive,
 		.gro_complete = inet_gro_complete,
@@ -1664,7 +1629,6 @@ static struct packet_offload ip_packet_offload __read_mostly = {
 
 static const struct net_offload ipip_offload = {
 	.callbacks = {
-		.gso_send_check = inet_gso_send_check,
 		.gso_segment	= inet_gso_segment,
 		.gro_receive	= inet_gro_receive,
 		.gro_complete	= inet_gro_complete,
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index d3fe2ac05167..a77729503071 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -15,13 +15,6 @@
 #include <net/protocol.h>
 #include <net/gre.h>
 
-static int gre_gso_send_check(struct sk_buff *skb)
-{
-	if (!skb->encapsulation)
-		return -EINVAL;
-	return 0;
-}
-
 static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
@@ -46,6 +39,9 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_IPIP)))
 		goto out;
 
+	if (!skb->encapsulation)
+		goto out;
+
 	if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
 		goto out;
 
@@ -256,7 +252,6 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload gre_offload = {
 	.callbacks = {
-		.gso_send_check = gre_gso_send_check,
 		.gso_segment = gre_gso_segment,
 		.gro_receive = gre_gro_receive,
 		.gro_complete = gre_gro_complete,
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 7cd12b0458ff..5b90f2f447a5 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -288,11 +288,6 @@ int tcp_gro_complete(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_gro_complete);
 
-static int tcp_v4_gso_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 {
 	/* Don't bother verifying checksum if we're going to flush anyway. */
@@ -320,7 +315,6 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 
 static const struct net_offload tcpv4_offload = {
 	.callbacks = {
-		.gso_send_check	=	tcp_v4_gso_send_check,
 		.gso_segment	=	tcp4_gso_segment,
 		.gro_receive	=	tcp4_gro_receive,
 		.gro_complete	=	tcp4_gro_complete,
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 2918cc914824..19ebe6a39ddc 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -25,11 +25,6 @@ struct udp_offload_priv {
 	struct udp_offload_priv __rcu *next;
 };
 
-static int udp4_ufo_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
@@ -346,7 +341,6 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
-		.gso_send_check = udp4_ufo_send_check,
 		.gso_segment = udp4_ufo_fragment,
 		.gro_receive  =	udp4_gro_receive,
 		.gro_complete =	udp4_gro_complete,
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 9952f3fce30a..9034f76ae013 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -53,31 +53,6 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
 	return proto;
 }
 
-static int ipv6_gso_send_check(struct sk_buff *skb)
-{
-	const struct ipv6hdr *ipv6h;
-	const struct net_offload *ops;
-	int err = -EINVAL;
-
-	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
-		goto out;
-
-	ipv6h = ipv6_hdr(skb);
-	__skb_pull(skb, sizeof(*ipv6h));
-	err = -EPROTONOSUPPORT;
-
-	ops = rcu_dereference(inet6_offloads[
-		ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]);
-
-	if (likely(ops && ops->callbacks.gso_send_check)) {
-		skb_reset_transport_header(skb);
-		err = ops->callbacks.gso_send_check(skb);
-	}
-
-out:
-	return err;
-}
-
 static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	netdev_features_t features)
 {
@@ -306,7 +281,6 @@ out_unlock:
 static struct packet_offload ipv6_packet_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
 	.callbacks = {
-		.gso_send_check = ipv6_gso_send_check,
 		.gso_segment = ipv6_gso_segment,
 		.gro_receive = ipv6_gro_receive,
 		.gro_complete = ipv6_gro_complete,
@@ -315,7 +289,6 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
 
 static const struct net_offload sit_offload = {
 	.callbacks = {
-		.gso_send_check = ipv6_gso_send_check,
 		.gso_segment	= ipv6_gso_segment,
 		.gro_receive	= ipv6_gro_receive,
 		.gro_complete	= ipv6_gro_complete,
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 96253154db3a..c1ab77105b4c 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -15,11 +15,6 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static int tcp_v6_gso_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
 {
@@ -71,7 +66,6 @@ struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
 }
 static const struct net_offload tcpv6_offload = {
 	.callbacks = {
-		.gso_send_check	=	tcp_v6_gso_send_check,
 		.gso_segment	=	tcp6_gso_segment,
 		.gro_receive	=	tcp6_gro_receive,
 		.gro_complete	=	tcp6_gro_complete,
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e4af6437ea3b..212ebfc7973f 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -17,11 +17,6 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static int udp6_ufo_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 					 netdev_features_t features)
 {
@@ -166,7 +161,6 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv6_offload = {
 	.callbacks = {
-		.gso_send_check =	udp6_ufo_send_check,
 		.gso_segment	=	udp6_ufo_fragment,
 		.gro_receive	=	udp6_gro_receive,
 		.gro_complete	=	udp6_gro_complete,
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 6b38d083e1c9..e28ed2ef5b06 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -65,15 +65,9 @@ out:
 	return segs;
 }
 
-static int mpls_gso_send_check(struct sk_buff *skb)
-{
-	return 0;
-}
-
 static struct packet_offload mpls_mc_offload = {
 	.type = cpu_to_be16(ETH_P_MPLS_MC),
 	.callbacks = {
-		.gso_send_check =	mpls_gso_send_check,
 		.gso_segment    =	mpls_gso_segment,
 	},
 };
@@ -81,7 +75,6 @@ static struct packet_offload mpls_mc_offload = {
 static struct packet_offload mpls_uc_offload = {
 	.type = cpu_to_be16(ETH_P_MPLS_UC),
 	.callbacks = {
-		.gso_send_check =	mpls_gso_send_check,
 		.gso_segment    =	mpls_gso_segment,
 	},
 };
-- 
cgit v1.2.3


From b63adb979583ef185718d774d8162387db5589c0 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 26 Sep 2014 00:03:16 +0000
Subject: kernel: add support for kernel restart handler call chain

Various drivers implement architecture and/or device specific means to
restart (reset) the system.  Various mechanisms have been implemented to
support those schemes.  The best known mechanism is arm_pm_restart, which
is a function pointer to be set either from platform specific code or from
drivers.  Another mechanism is to use hardware watchdogs to issue a reset;
this mechanism is used if there is no other method available to reset a
board or system.  Two examples are alim7101_wdt, which currently uses the
reboot notifier to trigger a reset, and moxart_wdt, which registers the
arm_pm_restart function.

The existing mechanisms have a number of drawbacks.  Typically only one
scheme to restart the system is supported (at least if arm_pm_restart is
used).  At least in theory there can be multiple means to restart the
system, some of which may be less desirable (for example one mechanism may
only reset the CPU, while another may reset the entire system).  Using
arm_pm_restart can also be racy if the function pointer is set from a
driver, as the driver may be in the process of being unloaded when
arm_pm_restart is called.  Using the reboot notifier is always racy, as it
is unknown if and when other functions using the reboot notifier have
completed execution by the time the watchdog fires.

Introduce a system restart handler call chain to solve the described
problems.  This call chain is expected to be executed from the
architecture specific machine_restart() function.  Drivers providing
system restart functionality (such as the watchdog drivers mentioned
above) are expected to register with this call chain.  By using the
priority field in the notifier block, callers can control restart handler
execution sequence and thus ensure that the restart handler with the
optimal restart capabilities for a given system is called first.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Wim Van Sebroeck <wim@iguana.be>
Cc: Maxime Ripard <maxime.ripard@free-electrons.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Jonas Jensen <jonas.jensen@gmail.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Tomasz Figa <t.figa@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/reboot.h |  3 ++
 kernel/reboot.c        | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+)

(limited to 'include')

diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 48bf152761c7..67fc8fcdc4b0 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -38,6 +38,9 @@ extern int reboot_force;
 extern int register_reboot_notifier(struct notifier_block *);
 extern int unregister_reboot_notifier(struct notifier_block *);
 
+extern int register_restart_handler(struct notifier_block *);
+extern int unregister_restart_handler(struct notifier_block *);
+extern void do_kernel_restart(char *cmd);
 
 /*
  * Architecture-specific implementations of sys_reboot commands.
diff --git a/kernel/reboot.c b/kernel/reboot.c
index a3a9e240fcdb..5925f5ae8dff 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -104,6 +104,87 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
+/*
+ *	Notifier list for kernel code which wants to be called
+ *	to restart the system.
+ */
+static ATOMIC_NOTIFIER_HEAD(restart_handler_list);
+
+/**
+ *	register_restart_handler - Register function to be called to reset
+ *				   the system
+ *	@nb: Info about handler function to be called
+ *	@nb->priority:	Handler priority. Handlers should follow the
+ *			following guidelines for setting priorities.
+ *			0:	Restart handler of last resort,
+ *				with limited restart capabilities
+ *			128:	Default restart handler; use if no other
+ *				restart handler is expected to be available,
+ *				and/or if restart functionality is
+ *				sufficient to restart the entire system
+ *			255:	Highest priority restart handler, will
+ *				preempt all other restart handlers
+ *
+ *	Registers a function with code to be called to restart the
+ *	system.
+ *
+ *	Registered functions will be called from machine_restart as last
+ *	step of the restart sequence (if the architecture specific
+ *	machine_restart function calls do_kernel_restart - see below
+ *	for details).
+ *	Registered functions are expected to restart the system immediately.
+ *	If more than one function is registered, the restart handler priority
+ *	selects which function will be called first.
+ *
+ *	Restart handlers are expected to be registered from non-architecture
+ *	code, typically from drivers. A typical use case would be a system
+ *	where restart functionality is provided through a watchdog. Multiple
+ *	restart handlers may exist; for example, one restart handler might
+ *	restart the entire system, while another only restarts the CPU.
+ *	In such cases, the restart handler which only restarts part of the
+ *	hardware is expected to register with low priority to ensure that
+ *	it only runs if no other means to restart the system is available.
+ *
+ *	Currently always returns zero, as atomic_notifier_chain_register()
+ *	always returns zero.
+ */
+int register_restart_handler(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&restart_handler_list, nb);
+}
+EXPORT_SYMBOL(register_restart_handler);
+
+/**
+ *	unregister_restart_handler - Unregister previously registered
+ *				     restart handler
+ *	@nb: Hook to be unregistered
+ *
+ *	Unregisters a previously registered restart handler function.
+ *
+ *	Returns zero on success, or %-ENOENT on failure.
+ */
+int unregister_restart_handler(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&restart_handler_list, nb);
+}
+EXPORT_SYMBOL(unregister_restart_handler);
+
+/**
+ *	do_kernel_restart - Execute kernel restart handler call chain
+ *
+ *	Calls functions registered with register_restart_handler.
+ *
+ *	Expected to be called from machine_restart as last step of the restart
+ *	sequence.
+ *
+ *	Restarts the system immediately if a restart handler function has been
+ *	registered. Otherwise does nothing.
+ */
+void do_kernel_restart(char *cmd)
+{
+	atomic_notifier_call_chain(&restart_handler_list, reboot_mode, cmd);
+}
+
 void migrate_to_reboot_cpu(void)
 {
 	/* The boot cpu is always logical cpu 0 */
-- 
cgit v1.2.3


From 6ae61fbf38d0cd2aa922eb5e7241e9b0bfd7009d Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Wed, 13 Aug 2014 12:45:19 +0100
Subject: misc: st_kim: Increase size of dev_name buffer to incorporate
 termination

Calling strncpy with a maximum size argument of 32 bytes on destination
array kim_gdata->dev_name of size 32 bytes might leave the destination
string unterminated.

Cc: gregkh@linuxfoundation.org
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/ti_wilink_st.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h
index 932b76392248..884d6263e962 100644
--- a/include/linux/ti_wilink_st.h
+++ b/include/linux/ti_wilink_st.h
@@ -268,7 +268,7 @@ struct kim_data_s {
 	struct st_data_s *core_data;
 	struct chip_version version;
 	unsigned char ldisc_install;
-	unsigned char dev_name[UART_DEV_NAME_LEN];
+	unsigned char dev_name[UART_DEV_NAME_LEN + 1];
 	unsigned char flow_cntrl;
 	unsigned long baud_rate;
 };
-- 
cgit v1.2.3


From 48018943eb906d81e48f40675c17b92abfeafcf1 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Wed, 13 Aug 2014 11:42:46 +0100
Subject: mfd: wm5102: Mark register write sequencer control 3 readable

During init the core checks if the wm5102 has finished starting by reading
register 0x19 and looking at the value. This read always fails since this
is not a readable register, mark it as being one. While we're at it provide
a constant for the register name (as supplied by Charles Keepax).

Signed-off-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/arizona-core.c            | 3 ++-
 drivers/mfd/wm5102-tables.c           | 1 +
 include/linux/mfd/arizona/registers.h | 1 +
 3 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index 10a0cb90619a..7eabc36b97c1 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -784,7 +784,8 @@ int arizona_dev_init(struct arizona *arizona)
 	/* Ensure device startup is complete */
 	switch (arizona->type) {
 	case WM5102:
-		ret = regmap_read(arizona->regmap, 0x19, &val);
+		ret = regmap_read(arizona->regmap,
+				  ARIZONA_WRITE_SEQUENCER_CTRL_3, &val);
 		if (ret != 0)
 			dev_err(dev,
 				"Failed to check write sequencer state: %d\n",
diff --git a/drivers/mfd/wm5102-tables.c b/drivers/mfd/wm5102-tables.c
index a219888d7f4b..77e16e59a45d 100644
--- a/drivers/mfd/wm5102-tables.c
+++ b/drivers/mfd/wm5102-tables.c
@@ -1017,6 +1017,7 @@ static bool wm5102_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_WRITE_SEQUENCER_CTRL_0:
 	case ARIZONA_WRITE_SEQUENCER_CTRL_1:
 	case ARIZONA_WRITE_SEQUENCER_CTRL_2:
+	case ARIZONA_WRITE_SEQUENCER_CTRL_3:
 	case ARIZONA_WRITE_SEQUENCER_PROM:
 	case ARIZONA_TONE_GENERATOR_1:
 	case ARIZONA_TONE_GENERATOR_2:
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index dbd23c36de21..68913ec90969 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -27,6 +27,7 @@
 #define ARIZONA_WRITE_SEQUENCER_CTRL_0           0x16
 #define ARIZONA_WRITE_SEQUENCER_CTRL_1           0x17
 #define ARIZONA_WRITE_SEQUENCER_CTRL_2           0x18
+#define ARIZONA_WRITE_SEQUENCER_CTRL_3           0x19
 #define ARIZONA_WRITE_SEQUENCER_PROM             0x1A
 #define ARIZONA_TONE_GENERATOR_1                 0x20
 #define ARIZONA_TONE_GENERATOR_2                 0x21
-- 
cgit v1.2.3


From 4b5c1f1e080f79c3c226596047a20ccd1c8a9486 Mon Sep 17 00:00:00 2001
From: Jacek Anaszewski <j.anaszewski@samsung.com>
Date: Wed, 20 Aug 2014 15:43:39 +0200
Subject: mfd: max77693: Fix register enum name

According to the MAX77693 documentation the name of
the register is FLASH_STATUS.

Signed-off-by: Jacek Anaszewski <j.anaszewski@samsung.com>
Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/max77693-private.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index c466ff3e16b8..615f12141854 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -46,7 +46,7 @@ enum max77693_pmic_reg {
 	MAX77693_LED_REG_VOUT_FLASH2			= 0x0C,
 	MAX77693_LED_REG_FLASH_INT			= 0x0E,
 	MAX77693_LED_REG_FLASH_INT_MASK			= 0x0F,
-	MAX77693_LED_REG_FLASH_INT_STATUS		= 0x10,
+	MAX77693_LED_REG_FLASH_STATUS			= 0x10,
 
 	MAX77693_PMIC_REG_PMIC_ID1			= 0x20,
 	MAX77693_PMIC_REG_PMIC_ID2			= 0x21,
-- 
cgit v1.2.3


From a0bc607208e295f70d0355fa4e632a0c8c27533b Mon Sep 17 00:00:00 2001
From: Jacek Anaszewski <j.anaszewski@samsung.com>
Date: Fri, 22 Aug 2014 11:06:18 +0200
Subject: mfd: max77693: Improve support for the flash cell

This patch improves support for the flash cell of
max77693 mfd by adding relevant of_compatible field
and a structure for caching related platform data.
Added are also FLASH registers related macro definitions.

Signed-off-by: Jacek Anaszewski <j.anaszewski@samsung.com>
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/max77693.c               |  5 ++-
 include/linux/mfd/max77693-private.h | 59 ++++++++++++++++++++++++++++++++++++
 include/linux/mfd/max77693.h         | 40 ++++++++++++++++++++++++
 3 files changed, 103 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c
index 249c139ef04a..cf008f45968c 100644
--- a/drivers/mfd/max77693.c
+++ b/drivers/mfd/max77693.c
@@ -44,9 +44,12 @@
 static const struct mfd_cell max77693_devs[] = {
 	{ .name = "max77693-pmic", },
 	{ .name = "max77693-charger", },
-	{ .name = "max77693-flash", },
 	{ .name = "max77693-muic", },
 	{ .name = "max77693-haptic", },
+	{
+		.name = "max77693-flash",
+		.of_compatible = "maxim,max77693-flash",
+	},
 };
 
 static const struct regmap_config max77693_regmap_config = {
diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index 615f12141854..de063773f3b1 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -85,6 +85,65 @@ enum max77693_pmic_reg {
 	MAX77693_PMIC_REG_END,
 };
 
+/* MAX77693 ITORCH register */
+#define TORCH_IOUT1_SHIFT	0
+#define TORCH_IOUT2_SHIFT	4
+#define TORCH_IOUT_MIN		15625
+#define TORCH_IOUT_MAX		250000
+#define TORCH_IOUT_STEP		15625
+
+/* MAX77693 IFLASH1 and IFLASH2 registers */
+#define FLASH_IOUT_MIN		15625
+#define FLASH_IOUT_MAX_1LED	1000000
+#define FLASH_IOUT_MAX_2LEDS	625000
+#define FLASH_IOUT_STEP		15625
+
+/* MAX77693 TORCH_TIMER register */
+#define TORCH_TMR_NO_TIMER	0x40
+#define TORCH_TIMEOUT_MIN	262000
+#define TORCH_TIMEOUT_MAX	15728000
+
+/* MAX77693 FLASH_TIMER register */
+#define FLASH_TMR_LEVEL		0x80
+#define FLASH_TIMEOUT_MIN	62500
+#define FLASH_TIMEOUT_MAX	1000000
+#define FLASH_TIMEOUT_STEP	62500
+
+/* MAX77693 FLASH_EN register */
+#define FLASH_EN_OFF		0x0
+#define FLASH_EN_FLASH		0x1
+#define FLASH_EN_TORCH		0x2
+#define FLASH_EN_ON		0x3
+#define FLASH_EN_SHIFT(x)	(6 - ((x) - 1) * 2)
+#define TORCH_EN_SHIFT(x)	(2 - ((x) - 1) * 2)
+
+/* MAX77693 MAX_FLASH1 register */
+#define MAX_FLASH1_MAX_FL_EN	0x80
+#define MAX_FLASH1_VSYS_MIN	2400
+#define MAX_FLASH1_VSYS_MAX	3400
+#define MAX_FLASH1_VSYS_STEP	33
+
+/* MAX77693 VOUT_CNTL register */
+#define FLASH_BOOST_FIXED	0x04
+#define FLASH_BOOST_LEDNUM_2	0x80
+
+/* MAX77693 VOUT_FLASH1 register */
+#define FLASH_VOUT_MIN		3300
+#define FLASH_VOUT_MAX		5500
+#define FLASH_VOUT_STEP		25
+#define FLASH_VOUT_RMIN		0x0c
+
+/* MAX77693 FLASH_STATUS register */
+#define FLASH_STATUS_FLASH_ON	BIT(3)
+#define FLASH_STATUS_TORCH_ON	BIT(2)
+
+/* MAX77693 FLASH_INT register */
+#define FLASH_INT_FLED2_OPEN	BIT(0)
+#define FLASH_INT_FLED2_SHORT	BIT(1)
+#define FLASH_INT_FLED1_OPEN	BIT(2)
+#define FLASH_INT_FLED1_SHORT	BIT(3)
+#define FLASH_INT_OVER_CURRENT	BIT(4)
+
 /* MAX77693 CHG_CNFG_00 register */
 #define CHG_CNFG_00_CHG_MASK		0x1
 #define CHG_CNFG_00_BUCK_MASK		0x4
diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h
index 3f3dc45f93ee..f0b6585cd874 100644
--- a/include/linux/mfd/max77693.h
+++ b/include/linux/mfd/max77693.h
@@ -63,6 +63,45 @@ struct max77693_muic_platform_data {
 	int path_uart;
 };
 
+/* MAX77693 led flash */
+
+/* triggers */
+enum max77693_led_trigger {
+	MAX77693_LED_TRIG_OFF,
+	MAX77693_LED_TRIG_FLASH,
+	MAX77693_LED_TRIG_TORCH,
+	MAX77693_LED_TRIG_EXT,
+	MAX77693_LED_TRIG_SOFT,
+};
+
+/* trigger types */
+enum max77693_led_trigger_type {
+	MAX77693_LED_TRIG_TYPE_EDGE,
+	MAX77693_LED_TRIG_TYPE_LEVEL,
+};
+
+/* boost modes */
+enum max77693_led_boost_mode {
+	MAX77693_LED_BOOST_NONE,
+	MAX77693_LED_BOOST_ADAPTIVE,
+	MAX77693_LED_BOOST_FIXED,
+};
+
+struct max77693_led_platform_data {
+	u32 fleds[2];
+	u32 iout_torch[2];
+	u32 iout_flash[2];
+	u32 trigger[2];
+	u32 trigger_type[2];
+	u32 num_leds;
+	u32 boost_mode;
+	u32 flash_timeout;
+	u32 boost_vout;
+	u32 low_vsys;
+};
+
+/* MAX77693 */
+
 struct max77693_platform_data {
 	/* regulator data */
 	struct max77693_regulator_data *regulators;
@@ -70,5 +109,6 @@ struct max77693_platform_data {
 
 	/* muic data */
 	struct max77693_muic_platform_data *muic_data;
+	struct max77693_led_platform_data *led_data;
 };
 #endif	/* __LINUX_MFD_MAX77693_H */
-- 
cgit v1.2.3


From dfa52c852dd3fcf3c0e696ab2d7df0bf91b2aed9 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 28 Aug 2014 13:52:50 +0200
Subject: mfd: ti_ssp: Remove unused header

The header file include/linux/mfd/ti_ssp.h does not seem to be used
anywhere. It was orphaned by 3033ee62 "mfd: Remove obsolete ti-ssp
driver". Remove it.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/ti_ssp.h | 93 ----------------------------------------------
 1 file changed, 93 deletions(-)
 delete mode 100644 include/linux/mfd/ti_ssp.h

(limited to 'include')

diff --git a/include/linux/mfd/ti_ssp.h b/include/linux/mfd/ti_ssp.h
deleted file mode 100644
index dbb4b43bd20e..000000000000
--- a/include/linux/mfd/ti_ssp.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * Sequencer Serial Port (SSP) driver for Texas Instruments' SoCs
- *
- * Copyright (C) 2010 Texas Instruments Inc
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#ifndef __TI_SSP_H__
-#define __TI_SSP_H__
-
-struct ti_ssp_dev_data {
-	const char	*dev_name;
-	void		*pdata;
-	size_t		pdata_size;
-};
-
-struct ti_ssp_data {
-	unsigned long		out_clock;
-	struct ti_ssp_dev_data	dev_data[2];
-};
-
-struct ti_ssp_spi_data {
-	unsigned long	iosel;
-	int		num_cs;
-	void		(*select)(int cs);
-};
-
-/*
- * Sequencer port IO pin configuration bits.  These do not correlate 1-1 with
- * the hardware.  The iosel field in the port data combines iosel1 and iosel2,
- * and is therefore not a direct map to register space.  It is best to use the
- * macros below to construct iosel values.
- *
- * least significant 16 bits --> iosel1
- * most significant 16 bits  --> iosel2
- */
-
-#define SSP_IN			0x0000
-#define SSP_DATA		0x0001
-#define SSP_CLOCK		0x0002
-#define SSP_CHIPSEL		0x0003
-#define SSP_OUT			0x0004
-#define SSP_PIN_SEL(pin, v)	((v) << ((pin) * 3))
-#define SSP_PIN_MASK(pin)	SSP_PIN_SEL(pin, 0x7)
-#define SSP_INPUT_SEL(pin)	((pin) << 16)
-
-/* Sequencer port config bits */
-#define SSP_EARLY_DIN		BIT(8)
-#define SSP_DELAY_DOUT		BIT(9)
-
-/* Sequence map definitions */
-#define SSP_CLK_HIGH		BIT(0)
-#define SSP_CLK_LOW		0
-#define SSP_DATA_HIGH		BIT(1)
-#define SSP_DATA_LOW		0
-#define SSP_CS_HIGH		BIT(2)
-#define SSP_CS_LOW		0
-#define SSP_OUT_MODE		BIT(3)
-#define SSP_IN_MODE		0
-#define SSP_DATA_REG		BIT(4)
-#define SSP_ADDR_REG		0
-
-#define SSP_OPCODE_DIRECT	((0x0) << 5)
-#define SSP_OPCODE_TOGGLE	((0x1) << 5)
-#define SSP_OPCODE_SHIFT	((0x2) << 5)
-#define SSP_OPCODE_BRANCH0	((0x4) << 5)
-#define SSP_OPCODE_BRANCH1	((0x5) << 5)
-#define SSP_OPCODE_BRANCH	((0x6) << 5)
-#define SSP_OPCODE_STOP		((0x7) << 5)
-#define SSP_BRANCH(addr)	((addr) << 8)
-#define SSP_COUNT(cycles)	((cycles) << 8)
-
-int ti_ssp_raw_read(struct device *dev);
-int ti_ssp_raw_write(struct device *dev, u32 val);
-int ti_ssp_load(struct device *dev, int offs, u32* prog, int len);
-int ti_ssp_run(struct device *dev, u32 pc, u32 input, u32 *output);
-int ti_ssp_set_mode(struct device *dev, int mode);
-int ti_ssp_set_iosel(struct device *dev, u32 iosel);
-
-#endif /* __TI_SSP_H__ */
-- 
cgit v1.2.3


From c593aca4e42a24b229a8070c4eb50d01f54877f2 Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Fri, 22 Aug 2014 18:49:03 +0200
Subject: mfd: davinci_voicecodec: Fix 'if defined' guard type in header

The include guard doesn't work as intended due to the transposition
typo DAVINCI -> DAVINIC.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/davinci_voicecodec.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mfd/davinci_voicecodec.h b/include/linux/mfd/davinci_voicecodec.h
index 5166935ce66d..cb01496bfa49 100644
--- a/include/linux/mfd/davinci_voicecodec.h
+++ b/include/linux/mfd/davinci_voicecodec.h
@@ -21,7 +21,7 @@
  */
 
 #ifndef __LINUX_MFD_DAVINCI_VOICECODEC_H_
-#define __LINUX_MFD_DAVINIC_VOICECODEC_H_
+#define __LINUX_MFD_DAVINCI_VOICECODEC_H_
 
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
-- 
cgit v1.2.3


From 9bb9e29c78f8d8ee310987fd58a2b908a4ce0c40 Mon Sep 17 00:00:00 2001
From: Beniamino Galvani <b.galvani@gmail.com>
Date: Sat, 30 Aug 2014 14:50:23 +0200
Subject: mfd: Add Ricoh RN5T618 PMIC core driver

Ricoh RN5T618 is a power management IC which integrates 3 step-down
DCDC converters, 7 low-dropout regulators, a Li-ion battery charger,
fuel gauge, ADC, GPIOs and a watchdog timer.

This commit adds a MFD core driver to support the I2C communication
with the device.

Signed-off-by: Beniamino Galvani <b.galvani@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig         |  11 +++
 drivers/mfd/Makefile        |   1 +
 drivers/mfd/rn5t618.c       | 134 ++++++++++++++++++++++++++
 include/linux/mfd/rn5t618.h | 228 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 374 insertions(+)
 create mode 100644 drivers/mfd/rn5t618.c
 create mode 100644 include/linux/mfd/rn5t618.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index fc419da8d722..82f70dcab136 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -597,6 +597,17 @@ config MFD_RC5T583
 	  Additional drivers must be enabled in order to use the
 	  different functionality of the device.
 
+config MFD_RN5T618
+	tristate "Ricoh RN5T5618 PMIC"
+	depends on I2C
+	select MFD_CORE
+	select REGMAP_I2C
+	help
+	  Say yes here to add support for the Ricoh RN5T618 PMIC. This
+	  driver provides common support for accessing the device,
+	  additional drivers must be enabled in order to use the
+	  functionality of the device.
+
 config MFD_SEC_CORE
 	bool "SAMSUNG Electronics PMIC Series Support"
 	depends on I2C=y
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index d58068aa8aa9..aa5a73a5ba47 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -160,6 +160,7 @@ obj-$(CONFIG_MFD_INTEL_MSIC)	+= intel_msic.o
 obj-$(CONFIG_MFD_PALMAS)	+= palmas.o
 obj-$(CONFIG_MFD_VIPERBOARD)    += viperboard.o
 obj-$(CONFIG_MFD_RC5T583)	+= rc5t583.o rc5t583-irq.o
+obj-$(CONFIG_MFD_RN5T618)	+= rn5t618.o
 obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
 obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
diff --git a/drivers/mfd/rn5t618.c b/drivers/mfd/rn5t618.c
new file mode 100644
index 000000000000..666857192dbe
--- /dev/null
+++ b/drivers/mfd/rn5t618.c
@@ -0,0 +1,134 @@
+/*
+ * MFD core driver for Ricoh RN5T618 PMIC
+ *
+ * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/rn5t618.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+static const struct mfd_cell rn5t618_cells[] = {
+	{ .name = "rn5t618-regulator" },
+	{ .name = "rn5t618-wdt" },
+};
+
+static bool rn5t618_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case RN5T618_WATCHDOGCNT:
+	case RN5T618_DCIRQ:
+	case RN5T618_ILIMDATAH ... RN5T618_AIN0DATAL:
+	case RN5T618_IR_ADC1 ... RN5T618_IR_ADC3:
+	case RN5T618_IR_GPR:
+	case RN5T618_IR_GPF:
+	case RN5T618_MON_IOIN:
+	case RN5T618_INTMON:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config rn5t618_regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.volatile_reg	= rn5t618_volatile_reg,
+	.max_register	= RN5T618_MAX_REG,
+	.cache_type	= REGCACHE_RBTREE,
+};
+
+static struct rn5t618 *rn5t618_pm_power_off;
+
+static void rn5t618_power_off(void)
+{
+	/* disable automatic repower-on */
+	regmap_update_bits(rn5t618_pm_power_off->regmap, RN5T618_REPCNT,
+			   RN5T618_REPCNT_REPWRON, 0);
+	/* start power-off sequence */
+	regmap_update_bits(rn5t618_pm_power_off->regmap, RN5T618_SLPCNT,
+			   RN5T618_SLPCNT_SWPWROFF, RN5T618_SLPCNT_SWPWROFF);
+}
+
+static int rn5t618_i2c_probe(struct i2c_client *i2c,
+			     const struct i2c_device_id *id)
+{
+	struct rn5t618 *priv;
+	int ret;
+
+	priv = devm_kzalloc(&i2c->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, priv);
+
+	priv->regmap = devm_regmap_init_i2c(i2c, &rn5t618_regmap_config);
+	if (IS_ERR(priv->regmap)) {
+		ret = PTR_ERR(priv->regmap);
+		dev_err(&i2c->dev, "regmap init failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = mfd_add_devices(&i2c->dev, -1, rn5t618_cells,
+			      ARRAY_SIZE(rn5t618_cells), NULL, 0, NULL);
+	if (ret) {
+		dev_err(&i2c->dev, "failed to add sub-devices: %d\n", ret);
+		return ret;
+	}
+
+	if (!pm_power_off) {
+		rn5t618_pm_power_off = priv;
+		pm_power_off = rn5t618_power_off;
+	}
+
+	return 0;
+}
+
+static int rn5t618_i2c_remove(struct i2c_client *i2c)
+{
+	struct rn5t618 *priv = i2c_get_clientdata(i2c);
+
+	if (priv == rn5t618_pm_power_off) {
+		rn5t618_pm_power_off = NULL;
+		pm_power_off = NULL;
+	}
+
+	mfd_remove_devices(&i2c->dev);
+	return 0;
+}
+
+static const struct of_device_id rn5t618_of_match[] = {
+	{ .compatible = "ricoh,rn5t618" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, rn5t618_of_match);
+
+static const struct i2c_device_id rn5t618_i2c_id[] = {
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, rn5t618_i2c_id);
+
+static struct i2c_driver rn5t618_i2c_driver = {
+	.driver = {
+		.name = "rn5t618",
+		.of_match_table = of_match_ptr(rn5t618_of_match),
+	},
+	.probe = rn5t618_i2c_probe,
+	.remove = rn5t618_i2c_remove,
+	.id_table = rn5t618_i2c_id,
+};
+
+module_i2c_driver(rn5t618_i2c_driver);
+
+MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>");
+MODULE_DESCRIPTION("Ricoh RN5T618 MFD driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/rn5t618.h b/include/linux/mfd/rn5t618.h
new file mode 100644
index 000000000000..c72d5344f3b3
--- /dev/null
+++ b/include/linux/mfd/rn5t618.h
@@ -0,0 +1,228 @@
+/*
+ * MFD core driver for Ricoh RN5T618 PMIC
+ *
+ * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __LINUX_MFD_RN5T618_H
+#define __LINUX_MFD_RN5T618_H
+
+#include <linux/regmap.h>
+
+#define RN5T618_LSIVER			0x00
+#define RN5T618_OTPVER			0x01
+#define RN5T618_IODAC			0x02
+#define RN5T618_VINDAC			0x03
+#define RN5T618_CPUCNT			0x06
+#define RN5T618_PSWR			0x07
+#define RN5T618_PONHIS			0x09
+#define RN5T618_POFFHIS			0x0a
+#define RN5T618_WATCHDOG		0x0b
+#define RN5T618_WATCHDOGCNT		0x0c
+#define RN5T618_PWRFUNC			0x0d
+#define RN5T618_SLPCNT			0x0e
+#define RN5T618_REPCNT			0x0f
+#define RN5T618_PWRONTIMSET		0x10
+#define RN5T618_NOETIMSETCNT		0x11
+#define RN5T618_PWRIREN			0x12
+#define RN5T618_PWRIRQ			0x13
+#define RN5T618_PWRMON			0x14
+#define RN5T618_PWRIRSEL		0x15
+#define RN5T618_DC1_SLOT		0x16
+#define RN5T618_DC2_SLOT		0x17
+#define RN5T618_DC3_SLOT		0x18
+#define RN5T618_LDO1_SLOT		0x1b
+#define RN5T618_LDO2_SLOT		0x1c
+#define RN5T618_LDO3_SLOT		0x1d
+#define RN5T618_LDO4_SLOT		0x1e
+#define RN5T618_LDO5_SLOT		0x1f
+#define RN5T618_PSO0_SLOT		0x25
+#define RN5T618_PSO1_SLOT		0x26
+#define RN5T618_PSO2_SLOT		0x27
+#define RN5T618_PSO3_SLOT		0x28
+#define RN5T618_LDORTC1_SLOT		0x2a
+#define RN5T618_DC1CTL			0x2c
+#define RN5T618_DC1CTL2			0x2d
+#define RN5T618_DC2CTL			0x2e
+#define RN5T618_DC2CTL2			0x2f
+#define RN5T618_DC3CTL			0x30
+#define RN5T618_DC3CTL2			0x31
+#define RN5T618_DC1DAC			0x36
+#define RN5T618_DC2DAC			0x37
+#define RN5T618_DC3DAC			0x38
+#define RN5T618_DC1DAC_SLP		0x3b
+#define RN5T618_DC2DAC_SLP		0x3c
+#define RN5T618_DC3DAC_SLP		0x3d
+#define RN5T618_DCIREN			0x40
+#define RN5T618_DCIRQ			0x41
+#define RN5T618_DCIRMON			0x42
+#define RN5T618_LDOEN1			0x44
+#define RN5T618_LDOEN2			0x45
+#define RN5T618_LDODIS			0x46
+#define RN5T618_LDO1DAC			0x4c
+#define RN5T618_LDO2DAC			0x4d
+#define RN5T618_LDO3DAC			0x4e
+#define RN5T618_LDO4DAC			0x4f
+#define RN5T618_LDO5DAC			0x50
+#define RN5T618_LDORTCDAC		0x56
+#define RN5T618_LDORTC2DAC		0x57
+#define RN5T618_LDO1DAC_SLP		0x58
+#define RN5T618_LDO2DAC_SLP		0x59
+#define RN5T618_LDO3DAC_SLP		0x5a
+#define RN5T618_LDO4DAC_SLP		0x5b
+#define RN5T618_LDO5DAC_SLP		0x5c
+#define RN5T618_ADCCNT1			0x64
+#define RN5T618_ADCCNT2			0x65
+#define RN5T618_ADCCNT3			0x66
+#define RN5T618_ILIMDATAH		0x68
+#define RN5T618_ILIMDATAL		0x69
+#define RN5T618_VBATDATAH		0x6a
+#define RN5T618_VBATDATAL		0x6b
+#define RN5T618_VADPDATAH		0x6c
+#define RN5T618_VADPDATAL		0x6d
+#define RN5T618_VUSBDATAH		0x6e
+#define RN5T618_VUSBDATAL		0x6f
+#define RN5T618_VSYSDATAH		0x70
+#define RN5T618_VSYSDATAL		0x71
+#define RN5T618_VTHMDATAH		0x72
+#define RN5T618_VTHMDATAL		0x73
+#define RN5T618_AIN1DATAH		0x74
+#define RN5T618_AIN1DATAL		0x75
+#define RN5T618_AIN0DATAH		0x76
+#define RN5T618_AIN0DATAL		0x77
+#define RN5T618_ILIMTHL			0x78
+#define RN5T618_ILIMTHH			0x79
+#define RN5T618_VBATTHL			0x7a
+#define RN5T618_VBATTHH			0x7b
+#define RN5T618_VADPTHL			0x7c
+#define RN5T618_VADPTHH			0x7d
+#define RN5T618_VUSBTHL			0x7e
+#define RN5T618_VUSBTHH			0x7f
+#define RN5T618_VSYSTHL			0x80
+#define RN5T618_VSYSTHH			0x81
+#define RN5T618_VTHMTHL			0x82
+#define RN5T618_VTHMTHH			0x83
+#define RN5T618_AIN1THL			0x84
+#define RN5T618_AIN1THH			0x85
+#define RN5T618_AIN0THL			0x86
+#define RN5T618_AIN0THH			0x87
+#define RN5T618_EN_ADCIR1		0x88
+#define RN5T618_EN_ADCIR2		0x89
+#define RN5T618_EN_ADCIR3		0x8a
+#define RN5T618_IR_ADC1			0x8c
+#define RN5T618_IR_ADC2			0x8d
+#define RN5T618_IR_ADC3			0x8e
+#define RN5T618_IOSEL			0x90
+#define RN5T618_IOOUT			0x91
+#define RN5T618_GPEDGE1			0x92
+#define RN5T618_GPEDGE2			0x93
+#define RN5T618_EN_GPIR			0x94
+#define RN5T618_IR_GPR			0x95
+#define RN5T618_IR_GPF			0x96
+#define RN5T618_MON_IOIN		0x97
+#define RN5T618_GPLED_FUNC		0x98
+#define RN5T618_INTPOL			0x9c
+#define RN5T618_INTEN			0x9d
+#define RN5T618_INTMON			0x9e
+#define RN5T618_PREVINDAC		0xb0
+#define RN5T618_BATDAC			0xb1
+#define RN5T618_CHGCTL1			0xb3
+#define RN5T618_CHGCTL2			0xb4
+#define RN5T618_VSYSSET			0xb5
+#define RN5T618_REGISET1		0xb6
+#define RN5T618_REGISET2		0xb7
+#define RN5T618_CHGISET			0xb8
+#define RN5T618_TIMSET			0xb9
+#define RN5T618_BATSET1			0xba
+#define RN5T618_BATSET2			0xbb
+#define RN5T618_DIESET			0xbc
+#define RN5T618_CHGSTATE		0xbd
+#define RN5T618_CHGCTRL_IRFMASK		0xbe
+#define RN5T618_CHGSTAT_IRFMASK1	0xbf
+#define RN5T618_CHGSTAT_IRFMASK2	0xc0
+#define RN5T618_CHGERR_IRFMASK		0xc1
+#define RN5T618_CHGCTRL_IRR		0xc2
+#define RN5T618_CHGSTAT_IRR1		0xc3
+#define RN5T618_CHGSTAT_IRR2		0xc4
+#define RN5T618_CHGERR_IRR		0xc5
+#define RN5T618_CHGCTRL_MONI		0xc6
+#define RN5T618_CHGSTAT_MONI1		0xc7
+#define RN5T618_CHGSTAT_MONI2		0xc8
+#define RN5T618_CHGERR_MONI		0xc9
+#define RN5T618_CHGCTRL_DETMOD1		0xca
+#define RN5T618_CHGCTRL_DETMOD2		0xcb
+#define RN5T618_CHGSTAT_DETMOD1		0xcc
+#define RN5T618_CHGSTAT_DETMOD2		0xcd
+#define RN5T618_CHGSTAT_DETMOD3		0xce
+#define RN5T618_CHGERR_DETMOD1		0xcf
+#define RN5T618_CHGERR_DETMOD2		0xd0
+#define RN5T618_CHGOSCCTL		0xd4
+#define RN5T618_CHGOSCSCORESET1		0xd5
+#define RN5T618_CHGOSCSCORESET2		0xd6
+#define RN5T618_CHGOSCSCORESET3		0xd7
+#define RN5T618_CHGOSCFREQSET1		0xd8
+#define RN5T618_CHGOSCFREQSET2		0xd9
+#define RN5T618_CONTROL			0xe0
+#define RN5T618_SOC			0xe1
+#define RN5T618_RE_CAP_H		0xe2
+#define RN5T618_RE_CAP_L		0xe3
+#define RN5T618_FA_CAP_H		0xe4
+#define RN5T618_FA_CAP_L		0xe5
+#define RN5T618_AGE			0xe6
+#define RN5T618_TT_EMPTY_H		0xe7
+#define RN5T618_TT_EMPTY_L		0xe8
+#define RN5T618_TT_FULL_H		0xe9
+#define RN5T618_TT_FULL_L		0xea
+#define RN5T618_VOLTAGE_1		0xeb
+#define RN5T618_VOLTAGE_0		0xec
+#define RN5T618_TEMP_1			0xed
+#define RN5T618_TEMP_0			0xee
+#define RN5T618_CC_CTRL			0xef
+#define RN5T618_CC_COUNT2		0xf0
+#define RN5T618_CC_COUNT1		0xf1
+#define RN5T618_CC_COUNT0		0xf2
+#define RN5T618_CC_SUMREG3		0xf3
+#define RN5T618_CC_SUMREG2		0xf4
+#define RN5T618_CC_SUMREG1		0xf5
+#define RN5T618_CC_SUMREG0		0xf6
+#define RN5T618_CC_OFFREG1		0xf7
+#define RN5T618_CC_OFFREG0		0xf8
+#define RN5T618_CC_GAINREG1		0xf9
+#define RN5T618_CC_GAINREG0		0xfa
+#define RN5T618_CC_AVEREG1		0xfb
+#define RN5T618_CC_AVEREG0		0xfc
+#define RN5T618_MAX_REG			0xfc
+
+#define RN5T618_REPCNT_REPWRON		BIT(0)
+#define RN5T618_SLPCNT_SWPWROFF		BIT(0)
+#define RN5T618_WATCHDOG_WDOGEN		BIT(2)
+#define RN5T618_WATCHDOG_WDOGTIM_M	(BIT(0) | BIT(1))
+#define RN5T618_WATCHDOG_WDOGTIM_S	0
+#define RN5T618_PWRIRQ_IR_WDOG		BIT(6)
+
+enum {
+	RN5T618_DCDC1,
+	RN5T618_DCDC2,
+	RN5T618_DCDC3,
+	RN5T618_LDO1,
+	RN5T618_LDO2,
+	RN5T618_LDO3,
+	RN5T618_LDO4,
+	RN5T618_LDO5,
+	RN5T618_LDORTC1,
+	RN5T618_LDORTC2,
+	RN5T618_REG_NUM,
+};
+
+struct rn5t618 {
+	struct regmap *regmap;
+};
+
+#endif /* __LINUX_MFD_RN5T618_H */
-- 
cgit v1.2.3


From c24084db223aec7793201b94f0712cfdfa7e9fe7 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Mon, 1 Sep 2014 15:48:52 +0100
Subject: mfd: arizona: Add ASYNC_SAMPLE_RATE_2 registers

Some arizona devices have a second asynchronous sample rate, add the
registers necessary to support this.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Acked-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/wm5102-tables.c           |  3 +++
 drivers/mfd/wm5110-tables.c           |  4 ++++
 include/linux/mfd/arizona/registers.h | 28 ++++++++++++++++++++++------
 sound/soc/codecs/arizona.c            |  2 +-
 4 files changed, 30 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/wm5102-tables.c b/drivers/mfd/wm5102-tables.c
index 6d9b7f832bf5..d6f35bbf795b 100644
--- a/drivers/mfd/wm5102-tables.c
+++ b/drivers/mfd/wm5102-tables.c
@@ -1059,6 +1059,8 @@ static bool wm5102_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_ASYNC_CLOCK_1:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_OUTPUT_SYSTEM_CLOCK:
 	case ARIZONA_OUTPUT_ASYNC_CLOCK:
 	case ARIZONA_RATE_ESTIMATOR_1:
@@ -1892,6 +1894,7 @@ static bool wm5102_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_SAMPLE_RATE_3_STATUS:
 	case ARIZONA_HAPTICS_STATUS:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_FLL1_NCO_TEST_0:
 	case ARIZONA_FLL2_NCO_TEST_0:
 	case ARIZONA_DAC_COMP_1:
diff --git a/drivers/mfd/wm5110-tables.c b/drivers/mfd/wm5110-tables.c
index beae0a397ee1..4642b5b816a0 100644
--- a/drivers/mfd/wm5110-tables.c
+++ b/drivers/mfd/wm5110-tables.c
@@ -702,6 +702,7 @@ static const struct reg_default wm5110_reg_default[] = {
 	{ 0x00000104, 0x0011 },    /* R260   - Sample rate 3 */
 	{ 0x00000112, 0x0305 },    /* R274   - Async clock 1 */
 	{ 0x00000113, 0x0011 },    /* R275   - Async sample rate 1 */
+	{ 0x00000114, 0x0011 },    /* R276   - Async sample rate 2 */
 	{ 0x00000149, 0x0000 },    /* R329   - Output system clock */
 	{ 0x0000014A, 0x0000 },    /* R330   - Output async clock */
 	{ 0x00000152, 0x0000 },    /* R338   - Rate Estimator 1 */
@@ -1738,6 +1739,8 @@ static bool wm5110_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_ASYNC_CLOCK_1:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_OUTPUT_SYSTEM_CLOCK:
 	case ARIZONA_OUTPUT_ASYNC_CLOCK:
 	case ARIZONA_RATE_ESTIMATOR_1:
@@ -2820,6 +2823,7 @@ static bool wm5110_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_SAMPLE_RATE_3_STATUS:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_MIC_DETECT_3:
 	case ARIZONA_HEADPHONE_DETECT_2:
 	case ARIZONA_INPUT_ENABLES_STATUS:
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index 68913ec90969..c0b075f6bc35 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -71,7 +71,9 @@
 #define ARIZONA_SAMPLE_RATE_3_STATUS             0x10C
 #define ARIZONA_ASYNC_CLOCK_1                    0x112
 #define ARIZONA_ASYNC_SAMPLE_RATE_1              0x113
+#define ARIZONA_ASYNC_SAMPLE_RATE_2              0x114
 #define ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS       0x11B
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS       0x11C
 #define ARIZONA_OUTPUT_SYSTEM_CLOCK              0x149
 #define ARIZONA_OUTPUT_ASYNC_CLOCK               0x14A
 #define ARIZONA_RATE_ESTIMATOR_1                 0x152
@@ -1665,16 +1667,30 @@
 /*
  * R275 (0x113) - Async sample rate 1
  */
-#define ARIZONA_ASYNC_SAMPLE_RATE_MASK           0x001F  /* ASYNC_SAMPLE_RATE - [4:0] */
-#define ARIZONA_ASYNC_SAMPLE_RATE_SHIFT               0  /* ASYNC_SAMPLE_RATE - [4:0] */
-#define ARIZONA_ASYNC_SAMPLE_RATE_WIDTH               5  /* ASYNC_SAMPLE_RATE - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_MASK         0x001F  /* ASYNC_SAMPLE_RATE_1 - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_SHIFT             0  /* ASYNC_SAMPLE_RATE_1 - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_WIDTH             5  /* ASYNC_SAMPLE_RATE_1 - [4:0] */
+
+/*
+ * R276 (0x114) - Async sample rate 2
+ */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_MASK         0x001F  /* ASYNC_SAMPLE_RATE_2 - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_SHIFT             0  /* ASYNC_SAMPLE_RATE_2 - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_WIDTH             5  /* ASYNC_SAMPLE_RATE_2 - [4:0] */
 
 /*
  * R283 (0x11B) - Async sample rate 1 status
  */
-#define ARIZONA_ASYNC_SAMPLE_RATE_STS_MASK       0x001F  /* ASYNC_SAMPLE_RATE_STS - [4:0] */
-#define ARIZONA_ASYNC_SAMPLE_RATE_STS_SHIFT           0  /* ASYNC_SAMPLE_RATE_STS - [4:0] */
-#define ARIZONA_ASYNC_SAMPLE_RATE_STS_WIDTH           5  /* ASYNC_SAMPLE_RATE_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_STS_MASK     0x001F  /* ASYNC_SAMPLE_RATE_1_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_STS_SHIFT         0  /* ASYNC_SAMPLE_RATE_1_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_STS_WIDTH         5  /* ASYNC_SAMPLE_RATE_1_STS - [4:0] */
+
+/*
+ * R284 (0x11C) - Async sample rate 2 status
+ */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_STS_MASK     0x001F  /* ASYNC_SAMPLE_RATE_2_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_STS_SHIFT         0  /* ASYNC_SAMPLE_RATE_2_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_STS_WIDTH         5  /* ASYNC_SAMPLE_RATE_2_STS - [4:0] */
 
 /*
  * R329 (0x149) - Output system clock
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 2c71f16bd661..0c05e7a7945f 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1220,7 +1220,7 @@ static int arizona_hw_params_rate(struct snd_pcm_substream *substream,
 		break;
 	case ARIZONA_CLK_ASYNCCLK:
 		snd_soc_update_bits(codec, ARIZONA_ASYNC_SAMPLE_RATE_1,
-				    ARIZONA_ASYNC_SAMPLE_RATE_MASK, sr_val);
+				    ARIZONA_ASYNC_SAMPLE_RATE_1_MASK, sr_val);
 		if (base)
 			snd_soc_update_bits(codec, base + ARIZONA_AIF_RATE_CTRL,
 					    ARIZONA_AIF1_RATE_MASK,
-- 
cgit v1.2.3


From e9e9d3973594cadd9e892bc79f914f299bb61124 Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Sat, 16 Aug 2014 21:23:40 +0800
Subject: mfd: da9052: Avoid setting read_flag_mask for da9052-i2c driver

Current code init regmap with &da9052_regmap_config for both da9052-spi and
da9052-i2c drivers. da9052-spi sets the read_flag_mask.
The same setting may be applied for da9052-i2c if da9052-spi driver is loaded
first because they actually use the same regmap_config setting.
Fix this issue by using a local variable for regmap_config in da9052-spi driver,
so the settings in spi driver won't impact the settings in i2c driver.
Also makes da9052_regmap_config const to avoid similar issue.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Acked-by: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/da9052-core.c         | 2 +-
 drivers/mfd/da9052-spi.c          | 7 ++++---
 include/linux/mfd/da9052/da9052.h | 2 +-
 3 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c
index e8af816d73a9..52a0c2f6264f 100644
--- a/drivers/mfd/da9052-core.c
+++ b/drivers/mfd/da9052-core.c
@@ -522,7 +522,7 @@ static const struct mfd_cell da9052_subdev_info[] = {
 	},
 };
 
-struct regmap_config da9052_regmap_config = {
+const struct regmap_config da9052_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 
diff --git a/drivers/mfd/da9052-spi.c b/drivers/mfd/da9052-spi.c
index 17666b40b70c..45ae0b7d13ef 100644
--- a/drivers/mfd/da9052-spi.c
+++ b/drivers/mfd/da9052-spi.c
@@ -23,6 +23,7 @@
 
 static int da9052_spi_probe(struct spi_device *spi)
 {
+	struct regmap_config config;
 	int ret;
 	const struct spi_device_id *id = spi_get_device_id(spi);
 	struct da9052 *da9052;
@@ -40,10 +41,10 @@ static int da9052_spi_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, da9052);
 
-	da9052_regmap_config.read_flag_mask = 1;
-	da9052_regmap_config.write_flag_mask = 0;
+	config = da9052_regmap_config;
+	config.read_flag_mask = 1;
 
-	da9052->regmap = devm_regmap_init_spi(spi, &da9052_regmap_config);
+	da9052->regmap = devm_regmap_init_spi(spi, &config);
 	if (IS_ERR(da9052->regmap)) {
 		ret = PTR_ERR(da9052->regmap);
 		dev_err(&spi->dev, "Failed to allocate register map: %d\n",
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index bba65f51a0b5..c18a4c19d6fc 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -211,7 +211,7 @@ static inline int da9052_reg_update(struct da9052 *da9052, unsigned char reg,
 int da9052_device_init(struct da9052 *da9052, u8 chip_id);
 void da9052_device_exit(struct da9052 *da9052);
 
-extern struct regmap_config da9052_regmap_config;
+extern const struct regmap_config da9052_regmap_config;
 
 int da9052_irq_init(struct da9052 *da9052);
 int da9052_irq_exit(struct da9052 *da9052);
-- 
cgit v1.2.3


From a53b9a97ac33fa74d136c2e3fd0d76ba7872a1d0 Mon Sep 17 00:00:00 2001
From: Chris Zhong <zyw@rock-chips.com>
Date: Wed, 3 Sep 2014 21:51:43 +0800
Subject: mfd: dt-bindings: Add RK808 device tree bindings document

Add device tree bindings documentation and a header file
for rockchip's RK808 pmic.

Signed-off-by: Doug Anderson <dianders@chromium.org>
Signed-off-by: Chris Zhong <zyw@rock-chips.com>
Signed-off-by: Zhang Qing <zhangqing@rock-chips.com>
Tested-by: Heiko <heiko@sntech.de>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 Documentation/devicetree/bindings/mfd/rk808.txt | 177 ++++++++++++++++++++++++
 include/dt-bindings/clock/rockchip,rk808.h      |  11 ++
 2 files changed, 188 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mfd/rk808.txt
 create mode 100644 include/dt-bindings/clock/rockchip,rk808.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/mfd/rk808.txt b/Documentation/devicetree/bindings/mfd/rk808.txt
new file mode 100644
index 000000000000..9e6e2592e5c8
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/rk808.txt
@@ -0,0 +1,177 @@
+RK808 Power Management Integrated Circuit
+
+Required properties:
+- compatible: "rockchip,rk808"
+- reg: I2C slave address
+- interrupt-parent: The parent interrupt controller.
+- interrupts: the interrupt outputs of the controller.
+- #clock-cells: from common clock binding; shall be set to 1 (multiple clock
+  outputs). See <dt-bindings/clock/rockchip,rk808.h> for clock IDs.
+
+Optional properties:
+- clock-output-names: From common clock binding to override the
+  default output clock name
+- rockchip,system-power-controller: Telling whether or not this pmic is controlling
+  the system power.
+- vcc1-supply:  The input supply for DCDC_REG1
+- vcc2-supply:  The input supply for DCDC_REG2
+- vcc3-supply:  The input supply for DCDC_REG3
+- vcc4-supply:  The input supply for DCDC_REG4
+- vcc6-supply:  The input supply for LDO_REG1 and LDO_REG2
+- vcc7-supply:  The input supply for LDO_REG3 and LDO_REG7
+- vcc8-supply:  The input supply for SWITCH_REG1
+- vcc9-supply:  The input supply for LDO_REG4 and LDO_REG5
+- vcc10-supply: The input supply for LDO_REG6
+- vcc11-supply: The input supply for LDO_REG8
+- vcc12-supply: The input supply for SWITCH_REG2
+
+Regulators: All the regulators of RK808 to be instantiated shall be
+listed in a child node named 'regulators'. Each regulator is represented
+by a child node of the 'regulators' node.
+
+	regulator-name {
+		/* standard regulator bindings here */
+	};
+
+Following regulators of the RK808 PMIC block are supported. Note that
+the 'n' in regulator name, as in DCDC_REGn or LDOn, represents the DCDC or LDO
+number as described in RK808 datasheet.
+
+	- DCDC_REGn
+		- valid values for n are 1 to 4.
+	- LDO_REGn
+		- valid values for n are 1 to 8.
+	- SWITCH_REGn
+		- valid values for n are 1 to 2
+
+Standard regulator bindings are used inside regulator subnodes. Check
+  Documentation/devicetree/bindings/regulator/regulator.txt
+for more details
+
+Example:
+	rk808: pmic@1b {
+		compatible = "rockchip,rk808";
+		clock-output-names = "xin32k", "rk808-clkout2";
+		interrupt-parent = <&gpio0>;
+		interrupts = <4 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_int>;
+		reg = <0x1b>;
+		rockchip,system-power-controller;
+		wakeup-source;
+		#clock-cells = <1>;
+
+		vcc8-supply = <&vcc_18>;
+		vcc9-supply = <&vcc_io>;
+		vcc10-supply = <&vcc_io>;
+		vcc12-supply = <&vcc_io>;
+		vddio-supply = <&vccio_pmu>;
+
+		regulators {
+			vdd_cpu: DCDC_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <1300000>;
+				regulator-name = "vdd_arm";
+			};
+
+			vdd_gpu: DCDC_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1250000>;
+				regulator-name = "vdd_gpu";
+			};
+
+			vcc_ddr: DCDC_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vcc_ddr";
+			};
+
+			vcc_io: DCDC_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_io";
+			};
+
+			vccio_pmu: LDO_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_pmu";
+			};
+
+			vcc_tp: LDO_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_tp";
+			};
+
+			vdd_10: LDO_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-name = "vdd_10";
+			};
+
+			vcc18_lcd: LDO_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc18_lcd";
+			};
+
+			vccio_sd: LDO_REG5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_sd";
+			};
+
+			vdd10_lcd: LDO_REG6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-name = "vdd10_lcd";
+			};
+
+			vcc_18: LDO_REG7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_18";
+			};
+
+			vcca_codec: LDO_REG8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcca_codec";
+			};
+
+			vcc_wl: SWITCH_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vcc_wl";
+			};
+
+			vcc_lcd: SWITCH_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vcc_lcd";
+			};
+		};
+	};
diff --git a/include/dt-bindings/clock/rockchip,rk808.h b/include/dt-bindings/clock/rockchip,rk808.h
new file mode 100644
index 000000000000..1a873432f965
--- /dev/null
+++ b/include/dt-bindings/clock/rockchip,rk808.h
@@ -0,0 +1,11 @@
+/*
+ * This header provides constants clk index RK808 pmic clkout
+ */
+#ifndef _CLK_ROCKCHIP_RK808
+#define _CLK_ROCKCHIP_RK808
+
+/* CLOCKOUT index */
+#define RK808_CLKOUT0		0
+#define RK808_CLKOUT1		1
+
+#endif
-- 
cgit v1.2.3


From f69a7cf74d5536faa180437581be2a9c0aad1bb1 Mon Sep 17 00:00:00 2001
From: Chris Zhong <zyw@rock-chips.com>
Date: Wed, 3 Sep 2014 21:51:44 +0800
Subject: mfd: RK808: Add new mfd driver for RK808

The RK808 chip is a power management IC for multimedia and handheld
devices. It contains the following components:

- Regulators
- RTC
- Clkout

The RK808 core driver is registered as a platform driver and provides
communication through I2C with the host device for the different
components.

Signed-off-by: Chris Zhong <zyw@rock-chips.com>
Signed-off-by: Zhang Qing <zhangqing@rock-chips.com>
Tested-by: Heiko <heiko@sntech.de>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig       |  13 +++
 drivers/mfd/Makefile      |   1 +
 drivers/mfd/rk808.c       | 245 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/rk808.h | 196 +++++++++++++++++++++++++++++++++++++
 4 files changed, 455 insertions(+)
 create mode 100644 drivers/mfd/rk808.c
 create mode 100644 include/linux/mfd/rk808.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 82f70dcab136..049796a28215 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -597,6 +597,19 @@ config MFD_RC5T583
 	  Additional drivers must be enabled in order to use the
 	  different functionality of the device.
 
+config MFD_RK808
+	tristate "Rockchip RK808 Power Management chip"
+	depends on I2C && OF
+	select MFD_CORE
+	select REGMAP_I2C
+	select REGMAP_IRQ
+	help
+	  If you say yes here you get support for the RK808
+	  Power Management chips.
+	  This driver provides common support for accessing the device
+	  through I2C interface. The device supports multiple sub-devices
+	  including interrupts, RTC, LDO & DCDC regulators, and onkey.
+
 config MFD_RN5T618
 	tristate "Ricoh RN5T5618 PMIC"
 	depends on I2C
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index aa5a73a5ba47..bd111213bd58 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -160,6 +160,7 @@ obj-$(CONFIG_MFD_INTEL_MSIC)	+= intel_msic.o
 obj-$(CONFIG_MFD_PALMAS)	+= palmas.o
 obj-$(CONFIG_MFD_VIPERBOARD)    += viperboard.o
 obj-$(CONFIG_MFD_RC5T583)	+= rc5t583.o rc5t583-irq.o
+obj-$(CONFIG_MFD_RK808)		+= rk808.o
 obj-$(CONFIG_MFD_RN5T618)	+= rn5t618.o
 obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
diff --git a/drivers/mfd/rk808.c b/drivers/mfd/rk808.c
new file mode 100644
index 000000000000..0324422b3b10
--- /dev/null
+++ b/drivers/mfd/rk808.c
@@ -0,0 +1,245 @@
+/*
+ * MFD core driver for Rockchip RK808
+ *
+ * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Chris Zhong <zyw@rock-chips.com>
+ * Author: Zhang Qing <zhangqing@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/rk808.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+struct rk808_reg_data {
+	int addr;
+	int mask;
+	int value;
+};
+
+static const struct regmap_config rk808_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = RK808_IO_POL_REG,
+};
+
+static struct resource rtc_resources[] = {
+	{
+		.start  = RK808_IRQ_RTC_ALARM,
+		.end    = RK808_IRQ_RTC_ALARM,
+		.flags  = IORESOURCE_IRQ,
+	}
+};
+
+static const struct mfd_cell rk808s[] = {
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
+	{
+		.name = "rk808-rtc",
+		.num_resources = ARRAY_SIZE(rtc_resources),
+		.resources = &rtc_resources[0],
+	},
+};
+
+static const struct rk808_reg_data pre_init_reg[] = {
+	{ RK808_BUCK3_CONFIG_REG, BUCK_ILMIN_MASK,  BUCK_ILMIN_150MA },
+	{ RK808_BUCK4_CONFIG_REG, BUCK_ILMIN_MASK,  BUCK_ILMIN_200MA },
+	{ RK808_BOOST_CONFIG_REG, BOOST_ILMIN_MASK, BOOST_ILMIN_100MA },
+	{ RK808_BUCK1_CONFIG_REG, BUCK1_RATE_MASK,  BUCK_ILMIN_200MA },
+	{ RK808_BUCK2_CONFIG_REG, BUCK2_RATE_MASK,  BUCK_ILMIN_200MA },
+	{ RK808_VB_MON_REG,       MASK_ALL,         VB_LO_ACT |
+						    VB_LO_SEL_3500MV },
+};
+
+static const struct regmap_irq rk808_irqs[] = {
+	/* INT_STS */
+	[RK808_IRQ_VOUT_LO] = {
+		.mask = RK808_IRQ_VOUT_LO_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_VB_LO] = {
+		.mask = RK808_IRQ_VB_LO_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_PWRON] = {
+		.mask = RK808_IRQ_PWRON_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_PWRON_LP] = {
+		.mask = RK808_IRQ_PWRON_LP_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_HOTDIE] = {
+		.mask = RK808_IRQ_HOTDIE_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_RTC_ALARM] = {
+		.mask = RK808_IRQ_RTC_ALARM_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_RTC_PERIOD] = {
+		.mask = RK808_IRQ_RTC_PERIOD_MSK,
+		.reg_offset = 0,
+	},
+
+	/* INT_STS2 */
+	[RK808_IRQ_PLUG_IN_INT] = {
+		.mask = RK808_IRQ_PLUG_IN_INT_MSK,
+		.reg_offset = 1,
+	},
+	[RK808_IRQ_PLUG_OUT_INT] = {
+		.mask = RK808_IRQ_PLUG_OUT_INT_MSK,
+		.reg_offset = 1,
+	},
+};
+
+static struct regmap_irq_chip rk808_irq_chip = {
+	.name = "rk808",
+	.irqs = rk808_irqs,
+	.num_irqs = ARRAY_SIZE(rk808_irqs),
+	.num_regs = 2,
+	.irq_reg_stride = 2,
+	.status_base = RK808_INT_STS_REG1,
+	.mask_base = RK808_INT_STS_MSK_REG1,
+	.ack_base = RK808_INT_STS_REG1,
+	.init_ack_masked = true,
+};
+
+static struct i2c_client *rk808_i2c_client;
+static void rk808_device_shutdown(void)
+{
+	int ret;
+	struct rk808 *rk808 = i2c_get_clientdata(rk808_i2c_client);
+
+	if (!rk808) {
+		dev_warn(&rk808_i2c_client->dev,
+			 "have no rk808, so do nothing here\n");
+		return;
+	}
+
+	ret = regmap_update_bits(rk808->regmap,
+				 RK808_DEVCTRL_REG,
+				 DEV_OFF_RST, DEV_OFF_RST);
+	if (ret)
+		dev_err(&rk808_i2c_client->dev, "power off error!\n");
+}
+
+static int rk808_probe(struct i2c_client *client,
+		       const struct i2c_device_id *id)
+{
+	struct device_node *np = client->dev.of_node;
+	struct rk808 *rk808;
+	int pm_off = 0;
+	int ret;
+	int i;
+
+	if (!client->irq) {
+		dev_err(&client->dev, "No interrupt support, no core IRQ\n");
+		return -EINVAL;
+	}
+
+	rk808 = devm_kzalloc(&client->dev, sizeof(*rk808), GFP_KERNEL);
+	if (!rk808)
+		return -ENOMEM;
+
+	rk808->regmap = devm_regmap_init_i2c(client, &rk808_regmap_config);
+	if (IS_ERR(rk808->regmap)) {
+		dev_err(&client->dev, "regmap initialization failed\n");
+		return PTR_ERR(rk808->regmap);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(pre_init_reg); i++) {
+		ret = regmap_update_bits(rk808->regmap, pre_init_reg[i].addr,
+					 pre_init_reg[i].mask,
+					 pre_init_reg[i].value);
+		if (ret) {
+			dev_err(&client->dev,
+				"0x%x write err\n", pre_init_reg[i].addr);
+			return ret;
+		}
+	}
+
+	ret = regmap_add_irq_chip(rk808->regmap, client->irq,
+				  IRQF_ONESHOT, -1,
+				  &rk808_irq_chip, &rk808->irq_data);
+	if (ret) {
+		dev_err(&client->dev, "Failed to add irq_chip %d\n", ret);
+		return ret;
+	}
+
+	rk808->i2c = client;
+	i2c_set_clientdata(client, rk808);
+
+	ret = mfd_add_devices(&client->dev, -1,
+			      rk808s, ARRAY_SIZE(rk808s),
+			      NULL, 0, regmap_irq_get_domain(rk808->irq_data));
+	if (ret) {
+		dev_err(&client->dev, "failed to add MFD devices %d\n", ret);
+		goto err_irq;
+	}
+
+	pm_off = of_property_read_bool(np,
+				"rockchip,system-power-controller");
+	if (pm_off && !pm_power_off) {
+		rk808_i2c_client = client;
+		pm_power_off = rk808_device_shutdown;
+	}
+
+	return 0;
+
+err_irq:
+	regmap_del_irq_chip(client->irq, rk808->irq_data);
+	return ret;
+}
+
+static int rk808_remove(struct i2c_client *client)
+{
+	struct rk808 *rk808 = i2c_get_clientdata(client);
+
+	regmap_del_irq_chip(client->irq, rk808->irq_data);
+	mfd_remove_devices(&client->dev);
+	pm_power_off = NULL;
+
+	return 0;
+}
+
+static struct of_device_id rk808_of_match[] = {
+	{ .compatible = "rockchip,rk808" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, rk808_of_match);
+
+static const struct i2c_device_id rk808_ids[] = {
+	{ "rk808" },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, rk808_ids);
+
+static struct i2c_driver rk808_i2c_driver = {
+	.driver = {
+		.name = "rk808",
+		.of_match_table = rk808_of_match,
+	},
+	.probe    = rk808_probe,
+	.remove   = rk808_remove,
+	.id_table = rk808_ids,
+};
+
+module_i2c_driver(rk808_i2c_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Chris Zhong <zyw@rock-chips.com>");
+MODULE_AUTHOR("Zhang Qing <zhangqing@rock-chips.com>");
+MODULE_DESCRIPTION("RK808 PMIC driver");
diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h
new file mode 100644
index 000000000000..fb09312d854b
--- /dev/null
+++ b/include/linux/mfd/rk808.h
@@ -0,0 +1,196 @@
+/*
+ * rk808.h for Rockchip RK808
+ *
+ * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Chris Zhong <zyw@rock-chips.com>
+ * Author: Zhang Qing <zhangqing@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __LINUX_REGULATOR_rk808_H
+#define __LINUX_REGULATOR_rk808_H
+
+#include <linux/regulator/machine.h>
+#include <linux/regmap.h>
+
+/*
+ * rk808 Global Register Map.
+ */
+
+#define RK808_DCDC1	0 /* (0+RK808_START) */
+#define RK808_LDO1	4 /* (4+RK808_START) */
+#define RK808_NUM_REGULATORS   14
+
+enum rk808_reg {
+	RK808_ID_DCDC1,
+	RK808_ID_DCDC2,
+	RK808_ID_DCDC3,
+	RK808_ID_DCDC4,
+	RK808_ID_LDO1,
+	RK808_ID_LDO2,
+	RK808_ID_LDO3,
+	RK808_ID_LDO4,
+	RK808_ID_LDO5,
+	RK808_ID_LDO6,
+	RK808_ID_LDO7,
+	RK808_ID_LDO8,
+	RK808_ID_SWITCH1,
+	RK808_ID_SWITCH2,
+};
+
+#define RK808_SECONDS_REG	0x00
+#define RK808_MINUTES_REG	0x01
+#define RK808_HOURS_REG		0x02
+#define RK808_DAYS_REG		0x03
+#define RK808_MONTHS_REG	0x04
+#define RK808_YEARS_REG		0x05
+#define RK808_WEEKS_REG		0x06
+#define RK808_ALARM_SECONDS_REG	0x08
+#define RK808_ALARM_MINUTES_REG	0x09
+#define RK808_ALARM_HOURS_REG	0x0a
+#define RK808_ALARM_DAYS_REG	0x0b
+#define RK808_ALARM_MONTHS_REG	0x0c
+#define RK808_ALARM_YEARS_REG	0x0d
+#define RK808_RTC_CTRL_REG	0x10
+#define RK808_RTC_STATUS_REG	0x11
+#define RK808_RTC_INT_REG	0x12
+#define RK808_RTC_COMP_LSB_REG	0x13
+#define RK808_RTC_COMP_MSB_REG	0x14
+#define RK808_CLK32OUT_REG	0x20
+#define RK808_VB_MON_REG	0x21
+#define RK808_THERMAL_REG	0x22
+#define RK808_DCDC_EN_REG	0x23
+#define RK808_LDO_EN_REG	0x24
+#define RK808_SLEEP_SET_OFF_REG1	0x25
+#define RK808_SLEEP_SET_OFF_REG2	0x26
+#define RK808_DCDC_UV_STS_REG	0x27
+#define RK808_DCDC_UV_ACT_REG	0x28
+#define RK808_LDO_UV_STS_REG	0x29
+#define RK808_LDO_UV_ACT_REG	0x2a
+#define RK808_DCDC_PG_REG	0x2b
+#define RK808_LDO_PG_REG	0x2c
+#define RK808_VOUT_MON_TDB_REG	0x2d
+#define RK808_BUCK1_CONFIG_REG		0x2e
+#define RK808_BUCK1_ON_VSEL_REG		0x2f
+#define RK808_BUCK1_SLP_VSEL_REG	0x30
+#define RK808_BUCK1_DVS_VSEL_REG	0x31
+#define RK808_BUCK2_CONFIG_REG		0x32
+#define RK808_BUCK2_ON_VSEL_REG		0x33
+#define RK808_BUCK2_SLP_VSEL_REG	0x34
+#define RK808_BUCK2_DVS_VSEL_REG	0x35
+#define RK808_BUCK3_CONFIG_REG		0x36
+#define RK808_BUCK4_CONFIG_REG		0x37
+#define RK808_BUCK4_ON_VSEL_REG		0x38
+#define RK808_BUCK4_SLP_VSEL_REG	0x39
+#define RK808_BOOST_CONFIG_REG		0x3a
+#define RK808_LDO1_ON_VSEL_REG		0x3b
+#define RK808_LDO1_SLP_VSEL_REG		0x3c
+#define RK808_LDO2_ON_VSEL_REG		0x3d
+#define RK808_LDO2_SLP_VSEL_REG		0x3e
+#define RK808_LDO3_ON_VSEL_REG		0x3f
+#define RK808_LDO3_SLP_VSEL_REG		0x40
+#define RK808_LDO4_ON_VSEL_REG		0x41
+#define RK808_LDO4_SLP_VSEL_REG		0x42
+#define RK808_LDO5_ON_VSEL_REG		0x43
+#define RK808_LDO5_SLP_VSEL_REG		0x44
+#define RK808_LDO6_ON_VSEL_REG		0x45
+#define RK808_LDO6_SLP_VSEL_REG		0x46
+#define RK808_LDO7_ON_VSEL_REG		0x47
+#define RK808_LDO7_SLP_VSEL_REG		0x48
+#define RK808_LDO8_ON_VSEL_REG		0x49
+#define RK808_LDO8_SLP_VSEL_REG		0x4a
+#define RK808_DEVCTRL_REG	0x4b
+#define RK808_INT_STS_REG1	0x4c
+#define RK808_INT_STS_MSK_REG1	0x4d
+#define RK808_INT_STS_REG2	0x4e
+#define RK808_INT_STS_MSK_REG2	0x4f
+#define RK808_IO_POL_REG	0x50
+
+/* IRQ Definitions */
+#define RK808_IRQ_VOUT_LO	0
+#define RK808_IRQ_VB_LO		1
+#define RK808_IRQ_PWRON		2
+#define RK808_IRQ_PWRON_LP	3
+#define RK808_IRQ_HOTDIE	4
+#define RK808_IRQ_RTC_ALARM	5
+#define RK808_IRQ_RTC_PERIOD	6
+#define RK808_IRQ_PLUG_IN_INT	7
+#define RK808_IRQ_PLUG_OUT_INT	8
+#define RK808_NUM_IRQ		9
+
+#define RK808_IRQ_VOUT_LO_MSK		BIT(0)
+#define RK808_IRQ_VB_LO_MSK		BIT(1)
+#define RK808_IRQ_PWRON_MSK		BIT(2)
+#define RK808_IRQ_PWRON_LP_MSK		BIT(3)
+#define RK808_IRQ_HOTDIE_MSK		BIT(4)
+#define RK808_IRQ_RTC_ALARM_MSK		BIT(5)
+#define RK808_IRQ_RTC_PERIOD_MSK	BIT(6)
+#define RK808_IRQ_PLUG_IN_INT_MSK	BIT(0)
+#define RK808_IRQ_PLUG_OUT_INT_MSK	BIT(1)
+
+#define RK808_VBAT_LOW_2V8	0x00
+#define RK808_VBAT_LOW_2V9	0x01
+#define RK808_VBAT_LOW_3V0	0x02
+#define RK808_VBAT_LOW_3V1	0x03
+#define RK808_VBAT_LOW_3V2	0x04
+#define RK808_VBAT_LOW_3V3	0x05
+#define RK808_VBAT_LOW_3V4	0x06
+#define RK808_VBAT_LOW_3V5	0x07
+#define VBAT_LOW_VOL_MASK	(0x07 << 0)
+#define EN_VABT_LOW_SHUT_DOWN	(0x00 << 4)
+#define EN_VBAT_LOW_IRQ		(0x1 << 4)
+#define VBAT_LOW_ACT_MASK	(0x1 << 4)
+
+#define BUCK_ILMIN_MASK		(7 << 0)
+#define BOOST_ILMIN_MASK	(7 << 0)
+#define BUCK1_RATE_MASK		(3 << 3)
+#define BUCK2_RATE_MASK		(3 << 3)
+#define MASK_ALL	0xff
+
+#define SWITCH2_EN	BIT(6)
+#define SWITCH1_EN	BIT(5)
+#define DEV_OFF_RST	BIT(3)
+
+#define VB_LO_ACT		BIT(4)
+#define VB_LO_SEL_3500MV	(7 << 0)
+
+#define VOUT_LO_INT	BIT(0)
+#define CLK32KOUT2_EN	BIT(0)
+
+enum {
+	BUCK_ILMIN_50MA,
+	BUCK_ILMIN_100MA,
+	BUCK_ILMIN_150MA,
+	BUCK_ILMIN_200MA,
+	BUCK_ILMIN_250MA,
+	BUCK_ILMIN_300MA,
+	BUCK_ILMIN_350MA,
+	BUCK_ILMIN_400MA,
+};
+
+enum {
+	BOOST_ILMIN_75MA,
+	BOOST_ILMIN_100MA,
+	BOOST_ILMIN_125MA,
+	BOOST_ILMIN_150MA,
+	BOOST_ILMIN_175MA,
+	BOOST_ILMIN_200MA,
+	BOOST_ILMIN_225MA,
+	BOOST_ILMIN_250MA,
+};
+
+struct rk808 {
+	struct i2c_client *i2c;
+	struct regmap_irq_chip_data *irq_data;
+	struct regmap *regmap;
+};
+#endif /* __LINUX_REGULATOR_rk808_H */
-- 
cgit v1.2.3


From bb048713bba3ead39f6112910906d9fe3f88ede7 Mon Sep 17 00:00:00 2001
From: Josef Ahmad <josef.ahmad@intel.com>
Date: Tue, 2 Sep 2014 13:45:20 +0300
Subject: pci_ids: Add support for Intel Quark ILB

This patch adds the PCI id for Intel Quark ILB.
It will be used for GPIO and Multifunction device driver.

Signed-off-by: Josef Ahmad <josef.ahmad@intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/pci_ids.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 6ed0bb73a864..4e82195b1695 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2557,6 +2557,7 @@
 #define PCI_DEVICE_ID_INTEL_MFD_EMMC0	0x0823
 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1	0x0824
 #define PCI_DEVICE_ID_INTEL_MRST_SD2	0x084F
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB	0x095E
 #define PCI_DEVICE_ID_INTEL_I960	0x0960
 #define PCI_DEVICE_ID_INTEL_I960RM	0x0962
 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB	0x0c60
-- 
cgit v1.2.3


From 8bdf87b400271ebc7fbf71e117c299d19a97ebb4 Mon Sep 17 00:00:00 2001
From: Guodong Xu <guodong.xu@linaro.org>
Date: Mon, 1 Sep 2014 16:28:34 +0800
Subject: mfd: Add HI6421 PMIC Core driver

This adds driver to support HiSilicon Hi6421 PMIC. Hi6421 includes multi-
functions, such as regulators, codec, ADCs, Coulomb counter, etc.
This driver includes core APIs _only_.

Drivers for individul components, like voltage regulators, are
implemented in corresponding driver directories and files.

Registers in Hi6421 are memory mapped, so using regmap-mmio API.

Signed-off-by: Guodong Xu <guodong.xu@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig             |  13 +++++
 drivers/mfd/Makefile            |   1 +
 drivers/mfd/hi6421-pmic-core.c  | 113 ++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/hi6421-pmic.h |  41 +++++++++++++++
 4 files changed, 168 insertions(+)
 create mode 100644 drivers/mfd/hi6421-pmic-core.c
 create mode 100644 include/linux/mfd/hi6421-pmic.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 049796a28215..609b7a2144d6 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -210,6 +210,19 @@ config MFD_MC13XXX_I2C
 	help
 	  Select this if your MC13xxx is connected via an I2C bus.
 
+config MFD_HI6421_PMIC
+	tristate "HiSilicon Hi6421 PMU/Codec IC"
+	depends on OF
+	select MFD_CORE
+	select REGMAP_MMIO
+	help
+	  Add support for HiSilicon Hi6421 PMIC. Hi6421 includes multi-
+	  functions, such as regulators, RTC, codec, Coulomb counter, etc.
+	  This driver includes core APIs _only_. You have to select
+	  individul components like voltage regulators under corresponding
+	  menus in order to enable them.
+	  We communicate with the Hi6421 via memory-mapped I/O.
+
 config HTC_EGPIO
 	bool "HTC EGPIO support"
 	depends on GPIOLIB && ARM
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index bd111213bd58..1d11a247abbb 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -172,6 +172,7 @@ obj-$(CONFIG_MFD_AS3722)	+= as3722.o
 obj-$(CONFIG_MFD_STW481X)	+= stw481x.o
 obj-$(CONFIG_MFD_IPAQ_MICRO)	+= ipaq-micro.o
 obj-$(CONFIG_MFD_MENF21BMC)	+= menf21bmc.o
+obj-$(CONFIG_MFD_HI6421_PMIC)	+= hi6421-pmic-core.o
 
 intel-soc-pmic-objs		:= intel_soc_pmic_core.o intel_soc_pmic_crc.o
 obj-$(CONFIG_INTEL_SOC_PMIC)	+= intel-soc-pmic.o
diff --git a/drivers/mfd/hi6421-pmic-core.c b/drivers/mfd/hi6421-pmic-core.c
new file mode 100644
index 000000000000..321a2656fd00
--- /dev/null
+++ b/drivers/mfd/hi6421-pmic-core.c
@@ -0,0 +1,113 @@
+/*
+ * Device driver for Hi6421 IC
+ *
+ * Copyright (c) <2011-2014> HiSilicon Technologies Co., Ltd.
+ *              http://www.hisilicon.com
+ * Copyright (c) <2013-2014> Linaro Ltd.
+ *              http://www.linaro.org
+ *
+ * Author: Guodong Xu <guodong.xu@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/mfd/hi6421-pmic.h>
+
+static const struct mfd_cell hi6421_devs[] = {
+	{ .name = "hi6421-regulator", },
+};
+
+static struct regmap_config hi6421_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 8,
+	.max_register = HI6421_REG_TO_BUS_ADDR(HI6421_REG_MAX),
+};
+
+static int hi6421_pmic_probe(struct platform_device *pdev)
+{
+	struct hi6421_pmic *pmic;
+	struct resource *res;
+	void __iomem *base;
+	int ret;
+
+	pmic = devm_kzalloc(&pdev->dev, sizeof(*pmic), GFP_KERNEL);
+	if (!pmic)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	pmic->regmap = devm_regmap_init_mmio_clk(&pdev->dev, NULL, base,
+						 &hi6421_regmap_config);
+	if (IS_ERR(pmic->regmap)) {
+		dev_err(&pdev->dev,
+			"regmap init failed: %ld\n", PTR_ERR(pmic->regmap));
+		return PTR_ERR(pmic->regmap);
+	}
+
+	/* set over-current protection debounce 8ms */
+	regmap_update_bits(pmic->regmap, HI6421_OCP_DEB_CTRL_REG,
+				(HI6421_OCP_DEB_SEL_MASK
+				 | HI6421_OCP_EN_DEBOUNCE_MASK
+				 | HI6421_OCP_AUTO_STOP_MASK),
+				(HI6421_OCP_DEB_SEL_8MS
+				 | HI6421_OCP_EN_DEBOUNCE_ENABLE));
+
+	platform_set_drvdata(pdev, pmic);
+
+	ret = mfd_add_devices(&pdev->dev, 0, hi6421_devs,
+			ARRAY_SIZE(hi6421_devs), NULL, 0, NULL);
+	if (ret) {
+		dev_err(&pdev->dev, "add mfd devices failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int hi6421_pmic_remove(struct platform_device *pdev)
+{
+	mfd_remove_devices(&pdev->dev);
+
+	return 0;
+}
+
+static struct of_device_id of_hi6421_pmic_match_tbl[] = {
+	{ .compatible = "hisilicon,hi6421-pmic", },
+	{ },
+};
+
+static struct platform_driver hi6421_pmic_driver = {
+	.driver = {
+		.name	= "hi6421_pmic",
+		.of_match_table = of_hi6421_pmic_match_tbl,
+	},
+	.probe	= hi6421_pmic_probe,
+	.remove	= hi6421_pmic_remove,
+};
+module_platform_driver(hi6421_pmic_driver);
+
+MODULE_AUTHOR("Guodong Xu <guodong.xu@linaro.org>");
+MODULE_DESCRIPTION("Hi6421 PMIC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/hi6421-pmic.h b/include/linux/mfd/hi6421-pmic.h
new file mode 100644
index 000000000000..587273e35acf
--- /dev/null
+++ b/include/linux/mfd/hi6421-pmic.h
@@ -0,0 +1,41 @@
+/*
+ * Header file for device driver Hi6421 PMIC
+ *
+ * Copyright (c) <2011-2014> HiSilicon Technologies Co., Ltd.
+ *              http://www.hisilicon.com
+ * Copyright (c) <2013-2014> Linaro Ltd.
+ *              http://www.linaro.org
+ *
+ * Author: Guodong Xu <guodong.xu@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef	__HI6421_PMIC_H
+#define	__HI6421_PMIC_H
+
+/* Hi6421 registers are mapped to memory bus in 4 bytes stride */
+#define HI6421_REG_TO_BUS_ADDR(x)	(x << 2)
+
+/* Hi6421 maximum register number */
+#define HI6421_REG_MAX			0xFF
+
+/* Hi6421 OCP (over current protection) and DEB (debounce) control register */
+#define	HI6421_OCP_DEB_CTRL_REG		HI6421_REG_TO_BUS_ADDR(0x51)
+#define	HI6421_OCP_DEB_SEL_MASK		0x0C
+#define HI6421_OCP_DEB_SEL_8MS		0x00
+#define HI6421_OCP_DEB_SEL_16MS		0x04
+#define HI6421_OCP_DEB_SEL_32MS		0x08
+#define HI6421_OCP_DEB_SEL_64MS		0x0C
+#define HI6421_OCP_EN_DEBOUNCE_MASK	0x02
+#define HI6421_OCP_EN_DEBOUNCE_ENABLE	0x02
+#define HI6421_OCP_AUTO_STOP_MASK	0x01
+#define HI6421_OCP_AUTO_STOP_ENABLE	0x01
+
+struct hi6421_pmic {
+	struct regmap		*regmap;
+};
+
+#endif		/* __HI6421_PMIC_H */
-- 
cgit v1.2.3


From 0b496b4c95c74ba795bc642a6092263ebf905759 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Fri, 5 Sep 2014 22:16:18 +0100
Subject: mfd: tps65217: Tell regmap what registers are valid

Allow regmap to provide debugfs access to the register map by telling it
what registers are valid.

Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/tps65217.c       | 2 ++
 include/linux/mfd/tps65217.h | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c
index 3cc4c7084b92..a8ee52c95f2f 100644
--- a/drivers/mfd/tps65217.c
+++ b/drivers/mfd/tps65217.c
@@ -146,6 +146,8 @@ EXPORT_SYMBOL_GPL(tps65217_clear_bits);
 static struct regmap_config tps65217_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
+
+	.max_register = TPS65217_REG_MAX,
 };
 
 static const struct of_device_id tps65217_of_match[] = {
diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h
index 95d6938737fd..ac7fba44d7e4 100644
--- a/include/linux/mfd/tps65217.h
+++ b/include/linux/mfd/tps65217.h
@@ -60,6 +60,8 @@
 #define TPS65217_REG_SEQ5		0X1D
 #define TPS65217_REG_SEQ6		0X1E
 
+#define TPS65217_REG_MAX		TPS65217_REG_SEQ6
+
 /* Register field definitions */
 #define TPS65217_CHIPID_CHIP_MASK	0xF0
 #define TPS65217_CHIPID_REV_MASK	0x0F
-- 
cgit v1.2.3


From f0933a60d1902c918249d11fb6d9a5ffd581ef5b Mon Sep 17 00:00:00 2001
From: Jeff Lance <j-lance1@ti.com>
Date: Thu, 4 Sep 2014 19:01:57 +0200
Subject: mfd: ti_am335x_tscadc: Update logic in CTRL register for 5-wire TS

The logic in AFE_Pen_Ctrl bitmask in the CTRL register is different for five
wire versus four or eight wire touschscreens. This patch should fix this for
five-wire touch screens. There should be no change needed here for four and
eight wire tousch screens.

Signed-off-by: Jeff Lance <j-lance1@ti.com>
[bigeasy: keep the change mfd only]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/ti_am335x_tscadc.c       | 30 +++++++++++++++++-------------
 include/linux/mfd/ti_am335x_tscadc.h |  1 +
 2 files changed, 18 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index 121add8be456..d877e777cce6 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -242,18 +242,20 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 	tscadc_writel(tscadc, REG_CLKDIV, tscadc->clk_div);
 
 	/* Set the control register bits */
-	ctrl = CNTRLREG_STEPCONFIGWRT |
-			CNTRLREG_STEPID;
-	if (tsc_wires > 0)
-		ctrl |= CNTRLREG_4WIRE | CNTRLREG_TSCENB;
+	ctrl = CNTRLREG_STEPCONFIGWRT |	CNTRLREG_STEPID;
 	tscadc_writel(tscadc, REG_CTRL, ctrl);
 
 	/* Set register bits for Idle Config Mode */
-	if (tsc_wires > 0)
+	if (tsc_wires > 0) {
+		tscadc->tsc_wires = tsc_wires;
+		if (tsc_wires == 5)
+			ctrl |= CNTRLREG_5WIRE | CNTRLREG_TSCENB;
+		else
+			ctrl |= CNTRLREG_4WIRE | CNTRLREG_TSCENB;
 		tscadc_idle_config(tscadc);
+	}
 
 	/* Enable the TSC module enable bit */
-	ctrl = tscadc_readl(tscadc, REG_CTRL);
 	ctrl |= CNTRLREG_TSCSSENB;
 	tscadc_writel(tscadc, REG_CTRL, ctrl);
 
@@ -325,21 +327,23 @@ static int tscadc_suspend(struct device *dev)
 static int tscadc_resume(struct device *dev)
 {
 	struct ti_tscadc_dev	*tscadc_dev = dev_get_drvdata(dev);
-	unsigned int restore, ctrl;
+	u32 ctrl;
 
 	pm_runtime_get_sync(dev);
 
 	/* context restore */
 	ctrl = CNTRLREG_STEPCONFIGWRT |	CNTRLREG_STEPID;
-	if (tscadc_dev->tsc_cell != -1)
-		ctrl |= CNTRLREG_TSCENB | CNTRLREG_4WIRE;
 	tscadc_writel(tscadc_dev, REG_CTRL, ctrl);
 
-	if (tscadc_dev->tsc_cell != -1)
+	if (tscadc_dev->tsc_cell != -1) {
+		if (tscadc_dev->tsc_wires == 5)
+			ctrl |= CNTRLREG_5WIRE | CNTRLREG_TSCENB;
+		else
+			ctrl |= CNTRLREG_4WIRE | CNTRLREG_TSCENB;
 		tscadc_idle_config(tscadc_dev);
-	restore = tscadc_readl(tscadc_dev, REG_CTRL);
-	tscadc_writel(tscadc_dev, REG_CTRL,
-			(restore | CNTRLREG_TSCSSENB));
+	}
+	ctrl |= CNTRLREG_TSCSSENB;
+	tscadc_writel(tscadc_dev, REG_CTRL, ctrl);
 
 	tscadc_writel(tscadc_dev, REG_CLKDIV, tscadc_dev->clk_div);
 
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index fb96c84dada5..e2e70053470e 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -155,6 +155,7 @@ struct ti_tscadc_dev {
 	void __iomem *tscadc_base;
 	int irq;
 	int used_cells;	/* 1-2 */
+	int tsc_wires;
 	int tsc_cell;	/* -1 if not used */
 	int adc_cell;	/* -1 if not used */
 	struct mfd_cell cells[TSCADC_CELLS];
-- 
cgit v1.2.3


From 6ab3430129e258ea31dd214adf1c760dfafde67a Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Tue, 16 Sep 2014 14:52:36 +0300
Subject: mfd: Add ACPI support

If an MFD device is backed by ACPI namespace, we should allow subdevice
drivers to access their corresponding ACPI companion devices through normal
means (e.g using ACPI_COMPANION()).

This patch adds such support to the MFD core. If the MFD parent device
does not specify any ACPI _HID/_CID for the child device, the child
device will share the parent ACPI companion device. Otherwise the child
device will be assigned with the corresponding ACPI companion, if found
in the namespace below the parent.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Darren Hart <dvhart@linux.intel.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 Documentation/acpi/enumeration.txt | 27 +++++++++++++++++++++++++
 drivers/mfd/mfd-core.c             | 40 ++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/core.h           |  3 +++
 3 files changed, 70 insertions(+)

(limited to 'include')

diff --git a/Documentation/acpi/enumeration.txt b/Documentation/acpi/enumeration.txt
index e182be5e3c83..b60d2ab69497 100644
--- a/Documentation/acpi/enumeration.txt
+++ b/Documentation/acpi/enumeration.txt
@@ -312,3 +312,30 @@ a code like this:
 
 There are also devm_* versions of these functions which release the
 descriptors once the device is released.
+
+MFD devices
+~~~~~~~~~~~
+The MFD devices register their children as platform devices. For the child
+devices there needs to be an ACPI handle that they can use to reference
+parts of the ACPI namespace that relate to them. In the Linux MFD subsystem
+we provide two ways:
+
+	o The children share the parent ACPI handle.
+	o The MFD cell can specify the ACPI id of the device.
+
+For the first case, the MFD drivers do not need to do anything. The
+resulting child platform device will have its ACPI_COMPANION() set to point
+to the parent device.
+
+If the ACPI namespace has a device that we can match using an ACPI id,
+the id should be set like:
+
+	static struct mfd_cell my_subdevice_cell = {
+		.name = "my_subdevice",
+		/* set the resources relative to the parent */
+		.acpi_pnpid = "XYZ0001",
+	};
+
+The ACPI id "XYZ0001" is then used to lookup an ACPI device directly under
+the MFD device and if found, that ACPI companion device is bound to the
+resulting child platform device.
diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index 5d0fbe1e097a..f3338fe9d069 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -78,6 +78,44 @@ static int mfd_platform_add_cell(struct platform_device *pdev,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_ACPI)
+static void mfd_acpi_add_device(const struct mfd_cell *cell,
+				struct platform_device *pdev)
+{
+	struct acpi_device *parent_adev;
+	struct acpi_device *adev;
+
+	parent_adev = ACPI_COMPANION(pdev->dev.parent);
+	if (!parent_adev)
+		return;
+
+	/*
+	 * MFD child device gets its ACPI handle either from the ACPI
+	 * device directly under the parent that matches the acpi_pnpid or
+	 * it will use the parent handle if is no acpi_pnpid is given.
+	 */
+	adev = parent_adev;
+	if (cell->acpi_pnpid) {
+		struct acpi_device_id ids[2] = {};
+		struct acpi_device *child_adev;
+
+		strlcpy(ids[0].id, cell->acpi_pnpid, sizeof(ids[0].id));
+		list_for_each_entry(child_adev, &parent_adev->children, node)
+			if (acpi_match_device_ids(child_adev, ids)) {
+				adev = child_adev;
+				break;
+			}
+	}
+
+	ACPI_COMPANION_SET(&pdev->dev, adev);
+}
+#else
+static inline void mfd_acpi_add_device(const struct mfd_cell *cell,
+				       struct platform_device *pdev)
+{
+}
+#endif
+
 static int mfd_add_device(struct device *parent, int id,
 			  const struct mfd_cell *cell, atomic_t *usage_count,
 			  struct resource *mem_base,
@@ -119,6 +157,8 @@ static int mfd_add_device(struct device *parent, int id,
 		}
 	}
 
+	mfd_acpi_add_device(cell, pdev);
+
 	if (cell->pdata_size) {
 		ret = platform_device_add_data(pdev,
 					cell->platform_data, cell->pdata_size);
diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index f543de91ce19..73e1709d4c09 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -44,6 +44,9 @@ struct mfd_cell {
 	 */
 	const char		*of_compatible;
 
+	/* Matches ACPI PNP id, either _HID or _CID */
+	const char		*acpi_pnpid;
+
 	/*
 	 * These resources can be specified relative to the parent device.
 	 * For accessing hardware you should use resources from the platform dev
-- 
cgit v1.2.3


From 5c2cacc1028917168b0f7650008dceaa6f7e3fe2 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Date: Wed, 24 Sep 2014 09:47:27 -0300
Subject: [media] v4l2-dv-timings: fix a sparse warning

This is detected with:
	gcc-4.8.3-7.fc20.x86_64
	sparse-0.5.0-3.fc20.x86_64

drivers/media/v4l2-core/v4l2-dv-timings.c:34:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:35:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:36:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:37:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:38:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:39:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:40:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:41:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:42:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:43:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:44:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:45:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:46:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:47:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:48:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:49:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:50:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:51:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:52:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:53:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:54:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:55:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:56:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:57:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:58:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:59:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:60:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:61:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:62:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:63:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:64:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:65:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:66:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:67:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:68:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:69:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:70:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:71:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:72:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:73:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:74:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:75:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:76:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:77:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:78:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:79:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:80:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:81:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:82:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:83:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:84:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:85:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:86:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:87:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:88:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:89:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:90:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:91:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:92:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:93:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:94:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:95:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:96:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:97:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:98:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:99:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:100:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:101:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:102:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:103:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:104:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:105:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:106:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:107:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:108:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:109:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:110:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:111:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:112:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:113:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:114:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:115:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:116:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:117:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:118:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:119:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:120:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:121:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:122:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:123:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:124:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:125:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:126:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:127:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:128:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:129:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:130:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:131:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:132:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:133:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:134:9: error: unknown field name in initializer
drivers/media/v4l2-core/v4l2-dv-timings.c:135:9: error: too many errors
drivers/media/usb/hdpvr/hdpvr-video.c:42:9: error: unknown field name in initializer
drivers/media/usb/hdpvr/hdpvr-video.c:43:9: error: unknown field name in initializer
drivers/media/usb/hdpvr/hdpvr-video.c:44:9: error: unknown field name in initializer
drivers/media/usb/hdpvr/hdpvr-video.c:45:9: error: unknown field name in initializer
drivers/media/usb/hdpvr/hdpvr-video.c:46:9: error: unknown field name in initializer
drivers/media/usb/hdpvr/hdpvr-video.c:47:9: error: unknown field name in initializer
drivers/media/usb/hdpvr/hdpvr-video.c:48:9: error: unknown field name in initializer
drivers/media/usb/hdpvr/hdpvr-video.c:49:9: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:484:18: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:485:18: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:486:18: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:487:18: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:488:18: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:489:18: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:490:18: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:491:18: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:492:18: error: unknown field name in initializer
drivers/media/platform/s5p-tv/hdmi_drv.c:493:18: error: unknown field name in initializer

Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/uapi/linux/v4l2-dv-timings.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/v4l2-dv-timings.h b/include/uapi/linux/v4l2-dv-timings.h
index 6c8f159e416e..6a0764c89fcb 100644
--- a/include/uapi/linux/v4l2-dv-timings.h
+++ b/include/uapi/linux/v4l2-dv-timings.h
@@ -21,17 +21,8 @@
 #ifndef _V4L2_DV_TIMINGS_H
 #define _V4L2_DV_TIMINGS_H
 
-#if __GNUC__ < 4 || (__GNUC__ == 4 && (__GNUC_MINOR__ < 6))
-/* Sadly gcc versions older than 4.6 have a bug in how they initialize
-   anonymous unions where they require additional curly brackets.
-   This violates the C1x standard. This workaround adds the curly brackets
-   if needed. */
 #define V4L2_INIT_BT_TIMINGS(_width, args...) \
 	{ .bt = { _width , ## args } }
-#else
-#define V4L2_INIT_BT_TIMINGS(_width, args...) \
-	.bt = { _width , ## args }
-#endif
 
 /* CEA-861-E timings (i.e. standard HDTV timings) */
 
-- 
cgit v1.2.3


From 234abab143aef82c0ef1f2de409c0db96b666f3c Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 10 Sep 2014 21:29:56 +0200
Subject: tty: serial: 8250_core: allow to set ->throttle / ->unthrottle
 callbacks

The OMAP UART provides support for HW assisted flow control. What is
missing is the support to throttle / unthrottle callbacks which are used
by the omap-serial driver at the moment.
This patch adds the callbacks. It should be safe to add them since they
are only invoked from the serial_core (uart_throttle()) if the feature
flags are set.

Reviewed-by: Tony Lindgren <tony@atomide.com>
Tested-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_core.c | 14 ++++++++++++++
 include/linux/serial_core.h         |  2 ++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index a0c1d64f34c5..68c44d97091b 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -1319,6 +1319,16 @@ static void serial8250_start_tx(struct uart_port *port)
 	}
 }
 
+static void serial8250_throttle(struct uart_port *port)
+{
+	port->throttle(port);
+}
+
+static void serial8250_unthrottle(struct uart_port *port)
+{
+	port->unthrottle(port);
+}
+
 static void serial8250_stop_rx(struct uart_port *port)
 {
 	struct uart_8250_port *up = up_to_u8250p(port);
@@ -2912,6 +2922,8 @@ static struct uart_ops serial8250_pops = {
 	.get_mctrl	= serial8250_get_mctrl,
 	.stop_tx	= serial8250_stop_tx,
 	.start_tx	= serial8250_start_tx,
+	.throttle	= serial8250_throttle,
+	.unthrottle	= serial8250_unthrottle,
 	.stop_rx	= serial8250_stop_rx,
 	.enable_ms	= serial8250_enable_ms,
 	.break_ctl	= serial8250_break_ctl,
@@ -3462,6 +3474,8 @@ int serial8250_register_8250_port(struct uart_8250_port *up)
 		uart->capabilities	= up->capabilities;
 		uart->rs485_config	= up->rs485_config;
 		uart->rs485		= up->rs485;
+		uart->port.throttle	= up->port.throttle;
+		uart->port.unthrottle	= up->port.unthrottle;
 
 		/* Take tx_loadsz from fifosize if it wasn't set separately */
 		if (uart->port.fifosize && !uart->tx_loadsz)
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 204c452a7567..21c2e05c1bc3 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -125,6 +125,8 @@ struct uart_port {
 				               struct ktermios *old);
 	int			(*startup)(struct uart_port *port);
 	void			(*shutdown)(struct uart_port *port);
+	void			(*throttle)(struct uart_port *port);
+	void			(*unthrottle)(struct uart_port *port);
 	int			(*handle_irq)(struct uart_port *);
 	void			(*pm)(struct uart_port *, unsigned int state,
 				      unsigned int old);
-- 
cgit v1.2.3


From d74d5d1b7288ff9d4439c8c7e0e314cde9743467 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 10 Sep 2014 21:29:57 +0200
Subject: tty: serial: 8250_core: add run time pm
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While comparing the OMAP-serial and the 8250 part of this I noticed that
the latter does not use run time-pm. Here are the pieces. It is
basically a get before first register access and a last_busy + put after
last access. This has to be enabled from userland _and_ UART_CAP_RPM is
required for this.
The runtime PM can usually work transparently in the background however
there is one exception to this: After serial8250_tx_chars() completes
there still may be unsent bytes in the FIFO (depending on CPU speed vs
baud rate + flow control). Even if the TTY-buffer is empty we do not
want RPM to disable the device because it won't send the remaining
bytes. Instead we leave serial8250_tx_chars() with RPM enabled and wait
for the FIFO empty interrupt. Once we enter serial8250_tx_chars() with
an empty buffer we know that the FIFO is empty and since we are not going
to send anything, we can disable the device.
That xchg() is to ensure that serial8250_tx_chars() can be called
multiple times and only the first invocation will actually invoke the
runtime PM function. So that the last invocation of __stop_tx() will
disable runtime pm.

NOTE: do not enable RPM on the device unless you know what you do! If
the device goes idle, it won't be woken up by incomming RX data _unless_
there is a wakeup irq configured which is usually the RX pin configure
for wakeup via the reset module. The RX activity will then wake up the
device from idle. However the first character is garbage and lost. The
following bytes will be received once the device is up in time. On the
beagle board xm (omap3) it takes approx 13ms from the first wakeup byte
until the first byte that is received properly if the device was in
core-off.

v5…v8:
	- drop RPM from serial8250_set_mctrl() it will be used in
	  restore path which already has RPM active and holds
	  dev->power.lock
v4…v5:
	- add a wrapper around rpm function and introduce UART_CAP_RPM
	  to ensure RPM put is invoked after the TX FIFO is empty.
v3…v4:
	- added runtime to the console code
	- removed device_may_wakeup() from serial8250_set_sleep()

Cc: mika.westerberg@linux.intel.com
Reviewed-by: Tony Lindgren <tony@atomide.com>
Tested-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250.h      |   1 +
 drivers/tty/serial/8250/8250_core.c | 133 ++++++++++++++++++++++++++++++++----
 include/linux/serial_8250.h         |   1 +
 3 files changed, 122 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index 85bfec58d77c..1bcb4b2141a6 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -72,6 +72,7 @@ struct serial8250_config {
 #define UART_CAP_UUE	(1 << 12)	/* UART needs IER bit 6 set (Xscale) */
 #define UART_CAP_RTOIE	(1 << 13)	/* UART needs IER bit 4 set (Xscale, Tegra) */
 #define UART_CAP_HFIFO	(1 << 14)	/* UART has a "hidden" FIFO */
+#define UART_CAP_RPM	(1 << 15)	/* Runtime PM is active while idle */
 
 #define UART_BUG_QUOT	(1 << 0)	/* UART has buggy quot LSB */
 #define UART_BUG_TXEN	(1 << 1)	/* UART has buggy TX IIR status */
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 68c44d97091b..3cf5c98013e4 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -38,6 +38,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/pm_runtime.h>
 #ifdef CONFIG_SPARC
 #include <linux/sunserialcore.h>
 #endif
@@ -540,6 +541,53 @@ void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p)
 }
 EXPORT_SYMBOL_GPL(serial8250_clear_and_reinit_fifos);
 
+static void serial8250_rpm_get(struct uart_8250_port *p)
+{
+	if (!(p->capabilities & UART_CAP_RPM))
+		return;
+	pm_runtime_get_sync(p->port.dev);
+}
+
+static void serial8250_rpm_put(struct uart_8250_port *p)
+{
+	if (!(p->capabilities & UART_CAP_RPM))
+		return;
+	pm_runtime_mark_last_busy(p->port.dev);
+	pm_runtime_put_autosuspend(p->port.dev);
+}
+
+/*
+ * This two wrapper ensure, that enable_runtime_pm_tx() can be called more than
+ * once and disable_runtime_pm_tx() will still disable RPM because the fifo is
+ * empty and the HW can idle again.
+ */
+static void serial8250_rpm_get_tx(struct uart_8250_port *p)
+{
+	unsigned char rpm_active;
+
+	if (!(p->capabilities & UART_CAP_RPM))
+		return;
+
+	rpm_active = xchg(&p->rpm_tx_active, 1);
+	if (rpm_active)
+		return;
+	pm_runtime_get_sync(p->port.dev);
+}
+
+static void serial8250_rpm_put_tx(struct uart_8250_port *p)
+{
+	unsigned char rpm_active;
+
+	if (!(p->capabilities & UART_CAP_RPM))
+		return;
+
+	rpm_active = xchg(&p->rpm_tx_active, 0);
+	if (!rpm_active)
+		return;
+	pm_runtime_mark_last_busy(p->port.dev);
+	pm_runtime_put_autosuspend(p->port.dev);
+}
+
 /*
  * IER sleep support.  UARTs which have EFRs need the "extended
  * capability" bit enabled.  Note that on XR16C850s, we need to
@@ -554,10 +602,11 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep)
 	 * offset but the UART channel may only write to the corresponding
 	 * bit.
 	 */
+	serial8250_rpm_get(p);
 	if ((p->port.type == PORT_XR17V35X) ||
 	   (p->port.type == PORT_XR17D15X)) {
 		serial_out(p, UART_EXAR_SLEEP, sleep ? 0xff : 0);
-		return;
+		goto out;
 	}
 
 	if (p->capabilities & UART_CAP_SLEEP) {
@@ -573,6 +622,8 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep)
 			serial_out(p, UART_LCR, 0);
 		}
 	}
+out:
+	serial8250_rpm_put(p);
 }
 
 #ifdef CONFIG_SERIAL_8250_RSA
@@ -1273,6 +1324,7 @@ static inline void __stop_tx(struct uart_8250_port *p)
 	if (p->ier & UART_IER_THRI) {
 		p->ier &= ~UART_IER_THRI;
 		serial_out(p, UART_IER, p->ier);
+		serial8250_rpm_put_tx(p);
 	}
 }
 
@@ -1280,6 +1332,7 @@ static void serial8250_stop_tx(struct uart_port *port)
 {
 	struct uart_8250_port *up = up_to_u8250p(port);
 
+	serial8250_rpm_get(up);
 	__stop_tx(up);
 
 	/*
@@ -1289,12 +1342,14 @@ static void serial8250_stop_tx(struct uart_port *port)
 		up->acr |= UART_ACR_TXDIS;
 		serial_icr_write(up, UART_ACR, up->acr);
 	}
+	serial8250_rpm_put(up);
 }
 
 static void serial8250_start_tx(struct uart_port *port)
 {
 	struct uart_8250_port *up = up_to_u8250p(port);
 
+	serial8250_rpm_get_tx(up);
 	if (up->dma && !serial8250_tx_dma(up)) {
 		return;
 	} else if (!(up->ier & UART_IER_THRI)) {
@@ -1333,9 +1388,13 @@ static void serial8250_stop_rx(struct uart_port *port)
 {
 	struct uart_8250_port *up = up_to_u8250p(port);
 
+	serial8250_rpm_get(up);
+
 	up->ier &= ~UART_IER_RLSI;
 	up->port.read_status_mask &= ~UART_LSR_DR;
 	serial_port_out(port, UART_IER, up->ier);
+
+	serial8250_rpm_put(up);
 }
 
 static void serial8250_enable_ms(struct uart_port *port)
@@ -1347,7 +1406,10 @@ static void serial8250_enable_ms(struct uart_port *port)
 		return;
 
 	up->ier |= UART_IER_MSI;
+
+	serial8250_rpm_get(up);
 	serial_port_out(port, UART_IER, up->ier);
+	serial8250_rpm_put(up);
 }
 
 /*
@@ -1469,7 +1531,12 @@ void serial8250_tx_chars(struct uart_8250_port *up)
 
 	DEBUG_INTR("THRE...");
 
-	if (uart_circ_empty(xmit))
+	/*
+	 * With RPM enabled, we have to wait once the FIFO is empty before the
+	 * HW can go idle. So we get here once again with empty FIFO and disable
+	 * the interrupt and RPM in __stop_tx()
+	 */
+	if (uart_circ_empty(xmit) && !(up->capabilities & UART_CAP_RPM))
 		__stop_tx(up);
 }
 EXPORT_SYMBOL_GPL(serial8250_tx_chars);
@@ -1537,9 +1604,17 @@ EXPORT_SYMBOL_GPL(serial8250_handle_irq);
 
 static int serial8250_default_handle_irq(struct uart_port *port)
 {
-	unsigned int iir = serial_port_in(port, UART_IIR);
+	struct uart_8250_port *up = up_to_u8250p(port);
+	unsigned int iir;
+	int ret;
+
+	serial8250_rpm_get(up);
 
-	return serial8250_handle_irq(port, iir);
+	iir = serial_port_in(port, UART_IIR);
+	ret = serial8250_handle_irq(port, iir);
+
+	serial8250_rpm_put(up);
+	return ret;
 }
 
 /*
@@ -1796,11 +1871,15 @@ static unsigned int serial8250_tx_empty(struct uart_port *port)
 	unsigned long flags;
 	unsigned int lsr;
 
+	serial8250_rpm_get(up);
+
 	spin_lock_irqsave(&port->lock, flags);
 	lsr = serial_port_in(port, UART_LSR);
 	up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS;
 	spin_unlock_irqrestore(&port->lock, flags);
 
+	serial8250_rpm_put(up);
+
 	return (lsr & BOTH_EMPTY) == BOTH_EMPTY ? TIOCSER_TEMT : 0;
 }
 
@@ -1810,7 +1889,9 @@ static unsigned int serial8250_get_mctrl(struct uart_port *port)
 	unsigned int status;
 	unsigned int ret;
 
+	serial8250_rpm_get(up);
 	status = serial8250_modem_status(up);
+	serial8250_rpm_put(up);
 
 	ret = 0;
 	if (status & UART_MSR_DCD)
@@ -1850,6 +1931,7 @@ static void serial8250_break_ctl(struct uart_port *port, int break_state)
 	struct uart_8250_port *up = up_to_u8250p(port);
 	unsigned long flags;
 
+	serial8250_rpm_get(up);
 	spin_lock_irqsave(&port->lock, flags);
 	if (break_state == -1)
 		up->lcr |= UART_LCR_SBC;
@@ -1857,6 +1939,7 @@ static void serial8250_break_ctl(struct uart_port *port, int break_state)
 		up->lcr &= ~UART_LCR_SBC;
 	serial_port_out(port, UART_LCR, up->lcr);
 	spin_unlock_irqrestore(&port->lock, flags);
+	serial8250_rpm_put(up);
 }
 
 /*
@@ -1901,12 +1984,23 @@ static void wait_for_xmitr(struct uart_8250_port *up, int bits)
 
 static int serial8250_get_poll_char(struct uart_port *port)
 {
-	unsigned char lsr = serial_port_in(port, UART_LSR);
+	struct uart_8250_port *up = up_to_u8250p(port);
+	unsigned char lsr;
+	int status;
+
+	serial8250_rpm_get(up);
 
-	if (!(lsr & UART_LSR_DR))
-		return NO_POLL_CHAR;
+	lsr = serial_port_in(port, UART_LSR);
 
-	return serial_port_in(port, UART_RX);
+	if (!(lsr & UART_LSR_DR)) {
+		status = NO_POLL_CHAR;
+		goto out;
+	}
+
+	status = serial_port_in(port, UART_RX);
+out:
+	serial8250_rpm_put(up);
+	return status;
 }
 
 
@@ -1916,6 +2010,7 @@ static void serial8250_put_poll_char(struct uart_port *port,
 	unsigned int ier;
 	struct uart_8250_port *up = up_to_u8250p(port);
 
+	serial8250_rpm_get(up);
 	/*
 	 *	First save the IER then disable the interrupts
 	 */
@@ -1937,6 +2032,7 @@ static void serial8250_put_poll_char(struct uart_port *port,
 	 */
 	wait_for_xmitr(up, BOTH_EMPTY);
 	serial_port_out(port, UART_IER, ier);
+	serial8250_rpm_put(up);
 }
 
 #endif /* CONFIG_CONSOLE_POLL */
@@ -1962,6 +2058,7 @@ int serial8250_do_startup(struct uart_port *port)
 	if (port->iotype != up->cur_iotype)
 		set_io_from_upio(port);
 
+	serial8250_rpm_get(up);
 	if (port->type == PORT_16C950) {
 		/* Wake up and initialize UART */
 		up->acr = 0;
@@ -1982,7 +2079,6 @@ int serial8250_do_startup(struct uart_port *port)
 	 */
 	enable_rsa(up);
 #endif
-
 	/*
 	 * Clear the FIFO buffers and disable them.
 	 * (they will be reenabled in set_termios())
@@ -2006,7 +2102,8 @@ int serial8250_do_startup(struct uart_port *port)
 	    (serial_port_in(port, UART_LSR) == 0xff)) {
 		printk_ratelimited(KERN_INFO "ttyS%d: LSR safety check engaged!\n",
 				   serial_index(port));
-		return -ENODEV;
+		retval = -ENODEV;
+		goto out;
 	}
 
 	/*
@@ -2091,7 +2188,7 @@ int serial8250_do_startup(struct uart_port *port)
 	} else {
 		retval = serial_link_irq_chain(up);
 		if (retval)
-			return retval;
+			goto out;
 	}
 
 	/*
@@ -2189,8 +2286,10 @@ dont_test_tx_en:
 		outb_p(0x80, icp);
 		inb_p(icp);
 	}
-
-	return 0;
+	retval = 0;
+out:
+	serial8250_rpm_put(up);
+	return retval;
 }
 EXPORT_SYMBOL_GPL(serial8250_do_startup);
 
@@ -2206,6 +2305,7 @@ void serial8250_do_shutdown(struct uart_port *port)
 	struct uart_8250_port *up = up_to_u8250p(port);
 	unsigned long flags;
 
+	serial8250_rpm_get(up);
 	/*
 	 * Disable interrupts from this port
 	 */
@@ -2245,6 +2345,7 @@ void serial8250_do_shutdown(struct uart_port *port)
 	 * the IRQ chain.
 	 */
 	serial_port_in(port, UART_RX);
+	serial8250_rpm_put(up);
 
 	del_timer_sync(&up->timer);
 	up->timer.function = serial8250_timeout;
@@ -2360,6 +2461,7 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios,
 	 * Ok, we're now changing the port state.  Do it with
 	 * interrupts disabled.
 	 */
+	serial8250_rpm_get(up);
 	spin_lock_irqsave(&port->lock, flags);
 
 	/*
@@ -2481,6 +2583,8 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios,
 	}
 	serial8250_set_mctrl(port, port->mctrl);
 	spin_unlock_irqrestore(&port->lock, flags);
+	serial8250_rpm_put(up);
+
 	/* Don't rewrite B0 */
 	if (tty_termios_baud_rate(termios))
 		tty_termios_encode_baud_rate(termios, baud, baud);
@@ -3091,6 +3195,8 @@ serial8250_console_write(struct console *co, const char *s, unsigned int count)
 
 	touch_nmi_watchdog();
 
+	serial8250_rpm_get(up);
+
 	if (port->sysrq || oops_in_progress)
 		locked = spin_trylock_irqsave(&port->lock, flags);
 	else
@@ -3127,6 +3233,7 @@ serial8250_console_write(struct console *co, const char *s, unsigned int count)
 
 	if (locked)
 		spin_unlock_irqrestore(&port->lock, flags);
+	serial8250_rpm_put(up);
 }
 
 static int __init serial8250_console_setup(struct console *co, char *options)
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index 6fc9d7bee05e..c267412a3ef4 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -84,6 +84,7 @@ struct uart_8250_port {
 	unsigned char		mcr_mask;	/* mask of user bits */
 	unsigned char		mcr_force;	/* mask of forced bits */
 	unsigned char		cur_iotype;	/* Running I/O type */
+	unsigned char		rpm_tx_active;
 
 	/*
 	 * Some bits in registers are cleared on a read, so they must
-- 
cgit v1.2.3


From 7276ca3fa23864133f5ee7431c51546d9b7f695f Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 22 Sep 2014 13:28:16 +0200
Subject: netfilter: bridge: nf_bridge_copy_header as static inline in header

Move nf_bridge_copy_header() as static inline in netfilter_bridge.h
header file. This patch prepares the modularization of the br_netfilter
code.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_bridge.h | 48 +++++++++++++++++++++++++++++++---------
 net/bridge/br_netfilter.c        | 28 -----------------------
 2 files changed, 38 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index 8ab1c278b66d..fe996d59de64 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -24,16 +24,6 @@ enum nf_br_hook_priorities {
 #define BRNF_8021Q			0x10
 #define BRNF_PPPoE			0x20
 
-/* Only used in br_forward.c */
-int nf_bridge_copy_header(struct sk_buff *skb);
-static inline int nf_bridge_maybe_copy_header(struct sk_buff *skb)
-{
-	if (skb->nf_bridge &&
-	    skb->nf_bridge->mask & (BRNF_BRIDGED | BRNF_BRIDGED_DNAT))
-		return nf_bridge_copy_header(skb);
-  	return 0;
-}
-
 static inline unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
 {
 	switch (skb->protocol) {
@@ -46,6 +36,44 @@ static inline unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
 	}
 }
 
+static inline void nf_bridge_update_protocol(struct sk_buff *skb)
+{
+	if (skb->nf_bridge->mask & BRNF_8021Q)
+		skb->protocol = htons(ETH_P_8021Q);
+	else if (skb->nf_bridge->mask & BRNF_PPPoE)
+		skb->protocol = htons(ETH_P_PPP_SES);
+}
+
+/* Fill in the header for fragmented IP packets handled by
+ * the IPv4 connection tracking code.
+ *
+ * Only used in br_forward.c
+ */
+static inline int nf_bridge_copy_header(struct sk_buff *skb)
+{
+	int err;
+	unsigned int header_size;
+
+	nf_bridge_update_protocol(skb);
+	header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
+	err = skb_cow_head(skb, header_size);
+	if (err)
+		return err;
+
+	skb_copy_to_linear_data_offset(skb, -header_size,
+				       skb->nf_bridge->data, header_size);
+	__skb_push(skb, nf_bridge_encap_header_len(skb));
+	return 0;
+}
+
+static inline int nf_bridge_maybe_copy_header(struct sk_buff *skb)
+{
+	if (skb->nf_bridge &&
+	    skb->nf_bridge->mask & (BRNF_BRIDGED | BRNF_BRIDGED_DNAT))
+		return nf_bridge_copy_header(skb);
+  	return 0;
+}
+
 static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
 {
 	if (unlikely(skb->nf_bridge->mask & BRNF_PPPoE))
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index a615264cf01a..61929a7cd815 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -245,14 +245,6 @@ static inline void nf_bridge_save_header(struct sk_buff *skb)
 					 skb->nf_bridge->data, header_size);
 }
 
-static inline void nf_bridge_update_protocol(struct sk_buff *skb)
-{
-	if (skb->nf_bridge->mask & BRNF_8021Q)
-		skb->protocol = htons(ETH_P_8021Q);
-	else if (skb->nf_bridge->mask & BRNF_PPPoE)
-		skb->protocol = htons(ETH_P_PPP_SES);
-}
-
 /* When handing a packet over to the IP layer
  * check whether we have a skb that is in the
  * expected format
@@ -320,26 +312,6 @@ drop:
 	return -1;
 }
 
-/* Fill in the header for fragmented IP packets handled by
- * the IPv4 connection tracking code.
- */
-int nf_bridge_copy_header(struct sk_buff *skb)
-{
-	int err;
-	unsigned int header_size;
-
-	nf_bridge_update_protocol(skb);
-	header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
-	err = skb_cow_head(skb, header_size);
-	if (err)
-		return err;
-
-	skb_copy_to_linear_data_offset(skb, -header_size,
-				       skb->nf_bridge->data, header_size);
-	__skb_push(skb, nf_bridge_encap_header_len(skb));
-	return 0;
-}
-
 /* PF_BRIDGE/PRE_ROUTING *********************************************/
 /* Undo the changes made for ip6tables PREROUTING and continue the
  * bridge PRE_ROUTING hook. */
-- 
cgit v1.2.3


From 34666d467cbf1e2e3c7bb15a63eccfb582cdd71f Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 18 Sep 2014 11:29:03 +0200
Subject: netfilter: bridge: move br_netfilter out of the core

Jesper reported that br_netfilter always registers the hooks since
this is part of the bridge core. This harms performance for people that
don't need this.

This patch modularizes br_netfilter so it can be rmmod'ed, thus,
the hooks can be unregistered. I think the bridge netfilter should have
been a separated module since the beginning, Patrick agreed on that.

Note that this is breaking compatibility for users that expect that
bridge netfilter is going to be available after explicitly 'modprobe
bridge' or via automatic load through brctl.

However, the damage can be easily undone by modprobing br_netfilter.
The bridge core also spots a message to provide a clue to people that
didn't notice that this has been deprecated.

On top of that, the plan is that nftables will not rely on this software
layer, but integrate the connection tracking into the bridge layer to
enable stateful filtering and NAT, which is was bridge netfilter users
seem to require.

This patch still keeps the fake_dst_ops in the bridge core, since this
is required by when the bridge port is initialized. So we can safely
modprobe/rmmod br_netfilter anytime.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Florian Westphal <fw@strlen.de>
---
 include/linux/netfilter_bridge.h       |  2 +-
 include/linux/skbuff.h                 | 12 ++---
 include/net/neighbour.h                |  2 +-
 include/net/netfilter/ipv4/nf_reject.h |  2 +-
 include/net/netfilter/ipv6/nf_reject.h |  2 +-
 net/Kconfig                            |  7 +--
 net/bridge/Makefile                    |  5 +-
 net/bridge/br.c                        | 14 ++---
 net/bridge/br_device.c                 |  4 +-
 net/bridge/br_forward.c                |  2 +
 net/bridge/br_input.c                  |  1 +
 net/bridge/br_netfilter.c              | 88 ++++++-------------------------
 net/bridge/br_netlink.c                |  2 +-
 net/bridge/br_nf_core.c                | 96 ++++++++++++++++++++++++++++++++++
 net/bridge/br_private.h                | 12 ++---
 net/bridge/br_sysfs_br.c               |  4 +-
 16 files changed, 151 insertions(+), 104 deletions(-)
 create mode 100644 net/bridge/br_nf_core.c

(limited to 'include')

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index fe996d59de64..c755e4971fa3 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -15,7 +15,7 @@ enum nf_br_hook_priorities {
 	NF_BR_PRI_LAST = INT_MAX,
 };
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 
 #define BRNF_PKT_TYPE			0x01
 #define BRNF_BRIDGED_DNAT		0x02
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 07c9fdd0c126..c4ff43f84573 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -156,7 +156,7 @@ struct nf_conntrack {
 };
 #endif
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 struct nf_bridge_info {
 	atomic_t		use;
 	unsigned int		mask;
@@ -560,7 +560,7 @@ struct sk_buff {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	struct nf_conntrack	*nfct;
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	struct nf_bridge_info	*nf_bridge;
 #endif
 
@@ -2977,7 +2977,7 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
 		atomic_inc(&nfct->use);
 }
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
 {
 	if (nf_bridge && atomic_dec_and_test(&nf_bridge->use))
@@ -2995,7 +2995,7 @@ static inline void nf_reset(struct sk_buff *skb)
 	nf_conntrack_put(skb->nfct);
 	skb->nfct = NULL;
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	nf_bridge_put(skb->nf_bridge);
 	skb->nf_bridge = NULL;
 #endif
@@ -3016,7 +3016,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 	nf_conntrack_get(src->nfct);
 	dst->nfctinfo = src->nfctinfo;
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	dst->nf_bridge  = src->nf_bridge;
 	nf_bridge_get(src->nf_bridge);
 #endif
@@ -3030,7 +3030,7 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(dst->nfct);
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	nf_bridge_put(dst->nf_bridge);
 #endif
 	__nf_copy(dst, src);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 47f425464f84..f60558d0254c 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -373,7 +373,7 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 	return 0;
 }
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 {
 	unsigned int seq, hh_alen;
diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h
index 931fbf812171..f713b5a31d62 100644
--- a/include/net/netfilter/ipv4/nf_reject.h
+++ b/include/net/netfilter/ipv4/nf_reject.h
@@ -98,7 +98,7 @@ static void nf_send_reset(struct sk_buff *oldskb, int hook)
 
 	nf_ct_attach(nskb, oldskb);
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	/* If we use ip_local_out for bridged traffic, the MAC source on
 	 * the RST will be ours, instead of the destination's.  This confuses
 	 * some routers/firewalls, and they drop the packet.  So we need to
diff --git a/include/net/netfilter/ipv6/nf_reject.h b/include/net/netfilter/ipv6/nf_reject.h
index 710d17ed70b4..7a10cfcd8e33 100644
--- a/include/net/netfilter/ipv6/nf_reject.h
+++ b/include/net/netfilter/ipv6/nf_reject.h
@@ -147,7 +147,7 @@ static void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 
 	nf_ct_attach(nskb, oldskb);
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	/* If we use ip6_local_out for bridged traffic, the MAC source on
 	 * the RST will be ours, instead of the destination's.  This confuses
 	 * some routers/firewalls, and they drop the packet.  So we need to
diff --git a/net/Kconfig b/net/Kconfig
index 4051fdfa4367..dc5d700d05e7 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -176,10 +176,11 @@ config NETFILTER_ADVANCED
 	  If unsure, say Y.
 
 config BRIDGE_NETFILTER
-	bool "Bridged IP/ARP packets filtering"
-	depends on BRIDGE && NETFILTER && INET
+	tristate "Bridged IP/ARP packets filtering"
+	depends on (BRIDGE || BRIDGE=n)
+	depends on NETFILTER && INET
 	depends on NETFILTER_ADVANCED
-	default y
+	default m
 	---help---
 	  Enabling this option will let arptables resp. iptables see bridged
 	  ARP resp. IP traffic. If you want a bridging firewall, you probably
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index 8590b942bffa..5e3eac5dc8b9 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -6,11 +6,12 @@ obj-$(CONFIG_BRIDGE) += bridge.o
 
 bridge-y	:= br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \
 			br_ioctl.o br_stp.o br_stp_bpdu.o \
-			br_stp_if.o br_stp_timer.o br_netlink.o
+			br_stp_if.o br_stp_timer.o br_netlink.o \
+			br_nf_core.o
 
 bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o
 
-bridge-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o
+obj-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o
 
 bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o
 
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 1a755a1e5410..44425aff7cba 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -161,7 +161,7 @@ static int __init br_init(void)
 	if (err)
 		goto err_out1;
 
-	err = br_netfilter_init();
+	err = br_nf_core_init();
 	if (err)
 		goto err_out2;
 
@@ -179,11 +179,16 @@ static int __init br_init(void)
 	br_fdb_test_addr_hook = br_fdb_test_addr;
 #endif
 
+	pr_info("bridge: automatic filtering via arp/ip/ip6tables has been "
+		"deprecated. Update your scripts to load br_netfilter if you "
+		"need this.\n");
+
 	return 0;
+
 err_out4:
 	unregister_netdevice_notifier(&br_device_notifier);
 err_out3:
-	br_netfilter_fini();
+	br_nf_core_fini();
 err_out2:
 	unregister_pernet_subsys(&br_net_ops);
 err_out1:
@@ -196,20 +201,17 @@ err_out:
 static void __exit br_deinit(void)
 {
 	stp_proto_unregister(&br_stp_proto);
-
 	br_netlink_fini();
 	unregister_netdevice_notifier(&br_device_notifier);
 	brioctl_set(NULL);
-
 	unregister_pernet_subsys(&br_net_ops);
 
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 
-	br_netfilter_fini();
+	br_nf_core_fini();
 #if IS_ENABLED(CONFIG_ATM_LANE)
 	br_fdb_test_addr_hook = NULL;
 #endif
-
 	br_fdb_fini();
 }
 
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 568cccd39a3d..659cac15c0df 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -36,7 +36,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	u16 vid = 0;
 
 	rcu_read_lock();
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) {
 		br_nf_pre_routing_finish_bridge_slow(skb);
 		rcu_read_unlock();
@@ -167,7 +167,7 @@ static int br_change_mtu(struct net_device *dev, int new_mtu)
 
 	dev->mtu = new_mtu;
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	/* remember the MTU in the rtable for PMTU */
 	dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu);
 #endif
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 056b67b0e277..992ec49a96aa 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -49,6 +49,7 @@ int br_dev_queue_push_xmit(struct sk_buff *skb)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
 
 int br_forward_finish(struct sk_buff *skb)
 {
@@ -56,6 +57,7 @@ int br_forward_finish(struct sk_buff *skb)
 		       br_dev_queue_push_xmit);
 
 }
+EXPORT_SYMBOL_GPL(br_forward_finish);
 
 static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
 {
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 366c43649079..6fd5522df696 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -140,6 +140,7 @@ drop:
 	kfree_skb(skb);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(br_handle_frame_finish);
 
 /* note: already called with rcu_read_lock */
 static int br_handle_local_finish(struct sk_buff *skb)
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 61929a7cd815..97e43937aaca 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -111,66 +111,6 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb)
 	 pppoe_proto(skb) == htons(PPP_IPV6) && \
 	 brnf_filter_pppoe_tagged)
 
-static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			     struct sk_buff *skb, u32 mtu)
-{
-}
-
-static void fake_redirect(struct dst_entry *dst, struct sock *sk,
-			  struct sk_buff *skb)
-{
-}
-
-static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old)
-{
-	return NULL;
-}
-
-static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst,
-					   struct sk_buff *skb,
-					   const void *daddr)
-{
-	return NULL;
-}
-
-static unsigned int fake_mtu(const struct dst_entry *dst)
-{
-	return dst->dev->mtu;
-}
-
-static struct dst_ops fake_dst_ops = {
-	.family =		AF_INET,
-	.protocol =		cpu_to_be16(ETH_P_IP),
-	.update_pmtu =		fake_update_pmtu,
-	.redirect =		fake_redirect,
-	.cow_metrics =		fake_cow_metrics,
-	.neigh_lookup =		fake_neigh_lookup,
-	.mtu =			fake_mtu,
-};
-
-/*
- * Initialize bogus route table used to keep netfilter happy.
- * Currently, we fill in the PMTU entry because netfilter
- * refragmentation needs it, and the rt_flags entry because
- * ipt_REJECT needs it.  Future netfilter modules might
- * require us to fill additional fields.
- */
-static const u32 br_dst_default_metrics[RTAX_MAX] = {
-	[RTAX_MTU - 1] = 1500,
-};
-
-void br_netfilter_rtable_init(struct net_bridge *br)
-{
-	struct rtable *rt = &br->fake_rtable;
-
-	atomic_set(&rt->dst.__refcnt, 1);
-	rt->dst.dev = br->dev;
-	rt->dst.path = &rt->dst;
-	dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
-	rt->dst.flags	= DST_NOXFRM | DST_FAKE_RTABLE;
-	rt->dst.ops = &fake_dst_ops;
-}
-
 static inline struct rtable *bridge_parent_rtable(const struct net_device *dev)
 {
 	struct net_bridge_port *port;
@@ -1031,38 +971,42 @@ static struct ctl_table brnf_table[] = {
 };
 #endif
 
-int __init br_netfilter_init(void)
+static int __init br_netfilter_init(void)
 {
 	int ret;
 
-	ret = dst_entries_init(&fake_dst_ops);
+	ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
 	if (ret < 0)
 		return ret;
 
-	ret = nf_register_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
-	if (ret < 0) {
-		dst_entries_destroy(&fake_dst_ops);
-		return ret;
-	}
 #ifdef CONFIG_SYSCTL
 	brnf_sysctl_header = register_net_sysctl(&init_net, "net/bridge", brnf_table);
 	if (brnf_sysctl_header == NULL) {
 		printk(KERN_WARNING
 		       "br_netfilter: can't register to sysctl.\n");
-		nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
-		dst_entries_destroy(&fake_dst_ops);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err1;
 	}
 #endif
 	printk(KERN_NOTICE "Bridge firewalling registered\n");
 	return 0;
+err1:
+	nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
+	return ret;
 }
 
-void br_netfilter_fini(void)
+static void __exit br_netfilter_fini(void)
 {
 	nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops));
 #ifdef CONFIG_SYSCTL
 	unregister_net_sysctl_table(brnf_sysctl_header);
 #endif
-	dst_entries_destroy(&fake_dst_ops);
 }
+
+module_init(br_netfilter_init);
+module_exit(br_netfilter_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Lennert Buytenhek <buytenh@gnu.org>");
+MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>");
+MODULE_DESCRIPTION("Linux ethernet netfilter firewall bridge");
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 90a91e137acc..0fa66b83685f 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -602,7 +602,7 @@ out_af:
 	return err;
 }
 
-void __exit br_netlink_fini(void)
+void br_netlink_fini(void)
 {
 	br_mdb_uninit();
 	rtnl_af_unregister(&br_af_ops);
diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c
new file mode 100644
index 000000000000..387cb3bd017c
--- /dev/null
+++ b/net/bridge/br_nf_core.c
@@ -0,0 +1,96 @@
+/*
+ *	Handle firewalling core
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek		<buytenh@gnu.org>
+ *	Bart De Schuymer		<bdschuym@pandora.be>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ *	Lennert dedicates this file to Kerstin Wurdinger.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/in_route.h>
+#include <linux/inetdevice.h>
+#include <net/route.h>
+
+#include "br_private.h"
+#ifdef CONFIG_SYSCTL
+#include <linux/sysctl.h>
+#endif
+
+static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			     struct sk_buff *skb, u32 mtu)
+{
+}
+
+static void fake_redirect(struct dst_entry *dst, struct sock *sk,
+			  struct sk_buff *skb)
+{
+}
+
+static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old)
+{
+	return NULL;
+}
+
+static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst,
+					   struct sk_buff *skb,
+					   const void *daddr)
+{
+	return NULL;
+}
+
+static unsigned int fake_mtu(const struct dst_entry *dst)
+{
+	return dst->dev->mtu;
+}
+
+static struct dst_ops fake_dst_ops = {
+	.family		= AF_INET,
+	.protocol	= cpu_to_be16(ETH_P_IP),
+	.update_pmtu	= fake_update_pmtu,
+	.redirect	= fake_redirect,
+	.cow_metrics	= fake_cow_metrics,
+	.neigh_lookup	= fake_neigh_lookup,
+	.mtu		= fake_mtu,
+};
+
+/*
+ * Initialize bogus route table used to keep netfilter happy.
+ * Currently, we fill in the PMTU entry because netfilter
+ * refragmentation needs it, and the rt_flags entry because
+ * ipt_REJECT needs it.  Future netfilter modules might
+ * require us to fill additional fields.
+ */
+static const u32 br_dst_default_metrics[RTAX_MAX] = {
+	[RTAX_MTU - 1] = 1500,
+};
+
+void br_netfilter_rtable_init(struct net_bridge *br)
+{
+	struct rtable *rt = &br->fake_rtable;
+
+	atomic_set(&rt->dst.__refcnt, 1);
+	rt->dst.dev = br->dev;
+	rt->dst.path = &rt->dst;
+	dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
+	rt->dst.flags	= DST_NOXFRM | DST_FAKE_RTABLE;
+	rt->dst.ops = &fake_dst_ops;
+}
+
+int __init br_nf_core_init(void)
+{
+	return dst_entries_init(&fake_dst_ops);
+}
+
+void br_nf_core_fini(void)
+{
+	dst_entries_destroy(&fake_dst_ops);
+}
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 62a7fa2e3569..d304d752c091 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -221,7 +221,7 @@ struct net_bridge
 	struct pcpu_sw_netstats		__percpu *stats;
 	spinlock_t			hash_lock;
 	struct hlist_head		hash[BR_HASH_SIZE];
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	struct rtable 			fake_rtable;
 	bool				nf_call_iptables;
 	bool				nf_call_ip6tables;
@@ -751,13 +751,13 @@ static inline int br_vlan_enabled(struct net_bridge *br)
 #endif
 
 /* br_netfilter.c */
-#ifdef CONFIG_BRIDGE_NETFILTER
-int br_netfilter_init(void);
-void br_netfilter_fini(void);
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+int br_nf_core_init(void);
+void br_nf_core_fini(void);
 void br_netfilter_rtable_init(struct net_bridge *);
 #else
-#define br_netfilter_init()	(0)
-#define br_netfilter_fini()	do { } while (0)
+static inline int br_nf_core_init(void) { return 0; }
+static inline void br_nf_core_fini(void) {}
 #define br_netfilter_rtable_init(x)
 #endif
 
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index c9e2572b15f4..cb431c6016ee 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -629,7 +629,7 @@ static ssize_t multicast_startup_query_interval_store(
 }
 static DEVICE_ATTR_RW(multicast_startup_query_interval);
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 static ssize_t nf_call_iptables_show(
 	struct device *d, struct device_attribute *attr, char *buf)
 {
@@ -763,7 +763,7 @@ static struct attribute *bridge_attrs[] = {
 	&dev_attr_multicast_query_response_interval.attr,
 	&dev_attr_multicast_startup_query_interval.attr,
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	&dev_attr_nf_call_iptables.attr,
 	&dev_attr_nf_call_ip6tables.attr,
 	&dev_attr_nf_call_arptables.attr,
-- 
cgit v1.2.3


From 29075feaf1f55e6b1aa4054b44bc141e8d5eab0b Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 26 Sep 2014 09:05:39 -0700
Subject: next: openrisc: Fix build

openrisc:defconfig fails to build in next-20140926 with the following error.

In file included from arch/openrisc/kernel/signal.c:31:0:
./arch/openrisc/include/asm/syscall.h: In function 'syscall_get_arch':
./arch/openrisc/include/asm/syscall.h:77:9: error: 'EM_OPENRISC' undeclared

Fix by moving EM_OPENRISC to include/uapi/linux/elf-em.h.

Fixes: ce5d112827e5 ("ARCH: AUDIT: implement syscall_get_arch for all arches")
Cc: Eric Paris <eparis@redhat.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 arch/openrisc/include/uapi/asm/elf.h | 3 +--
 include/uapi/linux/elf-em.h          | 1 +
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/openrisc/include/uapi/asm/elf.h b/arch/openrisc/include/uapi/asm/elf.h
index f02ea5830420..88842760e66f 100644
--- a/arch/openrisc/include/uapi/asm/elf.h
+++ b/arch/openrisc/include/uapi/asm/elf.h
@@ -55,9 +55,8 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 /* A placeholder; OR32 does not have fp support yes, so no fp regs for now.  */
 typedef unsigned long elf_fpregset_t;
 
-/* This should be moved to include/linux/elf.h */
+/* EM_OPENRISC is defined in linux/elf-em.h */
 #define EM_OR32         0x8472
-#define EM_OPENRISC     92     /* OpenRISC 32-bit embedded processor */
 
 /*
  * These are used to set parameters in the core dumps.
diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h
index 01529bd96438..aa90bc98b6e2 100644
--- a/include/uapi/linux/elf-em.h
+++ b/include/uapi/linux/elf-em.h
@@ -32,6 +32,7 @@
 #define EM_V850		87	/* NEC v850 */
 #define EM_M32R		88	/* Renesas M32R */
 #define EM_MN10300	89	/* Panasonic/MEI MN10300, AM33 */
+#define EM_OPENRISC     92     /* OpenRISC 32-bit embedded processor */
 #define EM_BLACKFIN     106     /* ADI Blackfin Processor */
 #define EM_TI_C6000	140	/* TI C6X DSPs */
 #define EM_AARCH64	183	/* ARM 64 bit */
-- 
cgit v1.2.3


From 99c55f7d47c0dc6fc64729f37bf435abf43f4c60 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:16:57 -0700
Subject: bpf: introduce BPF syscall and maps

BPF syscall is a multiplexor for a range of different operations on eBPF.
This patch introduces syscall with single command to create a map.
Next patch adds commands to access maps.

'maps' is a generic storage of different types for sharing data between kernel
and userspace.

Userspace example:
/* this syscall wrapper creates a map with given type and attributes
 * and returns map_fd on success.
 * use close(map_fd) to delete the map
 */
int bpf_create_map(enum bpf_map_type map_type, int key_size,
                   int value_size, int max_entries)
{
    union bpf_attr attr = {
        .map_type = map_type,
        .key_size = key_size,
        .value_size = value_size,
        .max_entries = max_entries
    };

    return bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}

'union bpf_attr' is backwards compatible with future extensions.

More details in Documentation/networking/filter.txt and in manpage

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/filter.txt |  39 +++++++++
 include/linux/bpf.h                 |  41 +++++++++
 include/uapi/linux/bpf.h            |  23 +++++
 kernel/bpf/Makefile                 |   2 +-
 kernel/bpf/syscall.c                | 169 ++++++++++++++++++++++++++++++++++++
 5 files changed, 273 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/bpf.h
 create mode 100644 kernel/bpf/syscall.c

(limited to 'include')

diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 014e0319a5c4..4a01d71785e9 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -1001,6 +1001,45 @@ instruction that loads 64-bit immediate value into a dst_reg.
 Classic BPF has similar instruction: BPF_LD | BPF_W | BPF_IMM which loads
 32-bit immediate value into a register.
 
+eBPF maps
+---------
+'maps' is a generic storage of different types for sharing data between kernel
+and userspace.
+
+The maps are accessed from user space via BPF syscall, which has commands:
+- create a map with given type and attributes
+  map_fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
+  using attr->map_type, attr->key_size, attr->value_size, attr->max_entries
+  returns process-local file descriptor or negative error
+
+- lookup key in a given map
+  err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
+  using attr->map_fd, attr->key, attr->value
+  returns zero and stores found elem into value or negative error
+
+- create or update key/value pair in a given map
+  err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
+  using attr->map_fd, attr->key, attr->value
+  returns zero or negative error
+
+- find and delete element by key in a given map
+  err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
+  using attr->map_fd, attr->key
+
+- to delete map: close(fd)
+  Exiting process will delete maps automatically
+
+userspace programs use this syscall to create/access maps that eBPF programs
+are concurrently updating.
+
+maps can have different types: hash, array, bloom filter, radix-tree, etc.
+
+The map is defined by:
+  . type
+  . max number of elements
+  . key size in bytes
+  . value size in bytes
+
 Testing
 -------
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
new file mode 100644
index 000000000000..48014a71f0fe
--- /dev/null
+++ b/include/linux/bpf.h
@@ -0,0 +1,41 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _LINUX_BPF_H
+#define _LINUX_BPF_H 1
+
+#include <uapi/linux/bpf.h>
+#include <linux/workqueue.h>
+
+struct bpf_map;
+
+/* map is generic key/value storage optionally accesible by eBPF programs */
+struct bpf_map_ops {
+	/* funcs callable from userspace (via syscall) */
+	struct bpf_map *(*map_alloc)(union bpf_attr *attr);
+	void (*map_free)(struct bpf_map *);
+};
+
+struct bpf_map {
+	atomic_t refcnt;
+	enum bpf_map_type map_type;
+	u32 key_size;
+	u32 value_size;
+	u32 max_entries;
+	struct bpf_map_ops *ops;
+	struct work_struct work;
+};
+
+struct bpf_map_type_list {
+	struct list_head list_node;
+	struct bpf_map_ops *ops;
+	enum bpf_map_type type;
+};
+
+void bpf_register_map_type(struct bpf_map_type_list *tl);
+void bpf_map_put(struct bpf_map *map);
+
+#endif /* _LINUX_BPF_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 479ed0b6be16..f58a10f9670c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -62,4 +62,27 @@ struct bpf_insn {
 	__s32	imm;		/* signed immediate constant */
 };
 
+/* BPF syscall commands */
+enum bpf_cmd {
+	/* create a map with given type and attributes
+	 * fd = bpf(BPF_MAP_CREATE, union bpf_attr *, u32 size)
+	 * returns fd or negative error
+	 * map is deleted when fd is closed
+	 */
+	BPF_MAP_CREATE,
+};
+
+enum bpf_map_type {
+	BPF_MAP_TYPE_UNSPEC,
+};
+
+union bpf_attr {
+	struct { /* anonymous struct used by BPF_MAP_CREATE command */
+		__u32	map_type;	/* one of enum bpf_map_type */
+		__u32	key_size;	/* size of key in bytes */
+		__u32	value_size;	/* size of value in bytes */
+		__u32	max_entries;	/* max number of entries in a map */
+	};
+} __attribute__((aligned(8)));
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 6a71145e2769..e9f7334ed07a 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1 +1 @@
-obj-y := core.o
+obj-y := core.o syscall.o
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
new file mode 100644
index 000000000000..428a0e23adc0
--- /dev/null
+++ b/kernel/bpf/syscall.c
@@ -0,0 +1,169 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/bpf.h>
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/anon_inodes.h>
+
+static LIST_HEAD(bpf_map_types);
+
+static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
+{
+	struct bpf_map_type_list *tl;
+	struct bpf_map *map;
+
+	list_for_each_entry(tl, &bpf_map_types, list_node) {
+		if (tl->type == attr->map_type) {
+			map = tl->ops->map_alloc(attr);
+			if (IS_ERR(map))
+				return map;
+			map->ops = tl->ops;
+			map->map_type = attr->map_type;
+			return map;
+		}
+	}
+	return ERR_PTR(-EINVAL);
+}
+
+/* boot time registration of different map implementations */
+void bpf_register_map_type(struct bpf_map_type_list *tl)
+{
+	list_add(&tl->list_node, &bpf_map_types);
+}
+
+/* called from workqueue */
+static void bpf_map_free_deferred(struct work_struct *work)
+{
+	struct bpf_map *map = container_of(work, struct bpf_map, work);
+
+	/* implementation dependent freeing */
+	map->ops->map_free(map);
+}
+
+/* decrement map refcnt and schedule it for freeing via workqueue
+ * (unrelying map implementation ops->map_free() might sleep)
+ */
+void bpf_map_put(struct bpf_map *map)
+{
+	if (atomic_dec_and_test(&map->refcnt)) {
+		INIT_WORK(&map->work, bpf_map_free_deferred);
+		schedule_work(&map->work);
+	}
+}
+
+static int bpf_map_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_map *map = filp->private_data;
+
+	bpf_map_put(map);
+	return 0;
+}
+
+static const struct file_operations bpf_map_fops = {
+	.release = bpf_map_release,
+};
+
+/* helper macro to check that unused fields 'union bpf_attr' are zero */
+#define CHECK_ATTR(CMD) \
+	memchr_inv((void *) &attr->CMD##_LAST_FIELD + \
+		   sizeof(attr->CMD##_LAST_FIELD), 0, \
+		   sizeof(*attr) - \
+		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
+		   sizeof(attr->CMD##_LAST_FIELD)) != NULL
+
+#define BPF_MAP_CREATE_LAST_FIELD max_entries
+/* called via syscall */
+static int map_create(union bpf_attr *attr)
+{
+	struct bpf_map *map;
+	int err;
+
+	err = CHECK_ATTR(BPF_MAP_CREATE);
+	if (err)
+		return -EINVAL;
+
+	/* find map type and init map: hashtable vs rbtree vs bloom vs ... */
+	map = find_and_alloc_map(attr);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	atomic_set(&map->refcnt, 1);
+
+	err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC);
+
+	if (err < 0)
+		/* failed to allocate fd */
+		goto free_map;
+
+	return err;
+
+free_map:
+	map->ops->map_free(map);
+	return err;
+}
+
+SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
+{
+	union bpf_attr attr = {};
+	int err;
+
+	/* the syscall is limited to root temporarily. This restriction will be
+	 * lifted when security audit is clean. Note that eBPF+tracing must have
+	 * this restriction, since it may pass kernel data to user space
+	 */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!access_ok(VERIFY_READ, uattr, 1))
+		return -EFAULT;
+
+	if (size > PAGE_SIZE)	/* silly large */
+		return -E2BIG;
+
+	/* If we're handed a bigger struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. new
+	 * user-space does not rely on any kernel feature
+	 * extensions we dont know about yet.
+	 */
+	if (size > sizeof(attr)) {
+		unsigned char __user *addr;
+		unsigned char __user *end;
+		unsigned char val;
+
+		addr = (void __user *)uattr + sizeof(attr);
+		end  = (void __user *)uattr + size;
+
+		for (; addr < end; addr++) {
+			err = get_user(val, addr);
+			if (err)
+				return err;
+			if (val)
+				return -E2BIG;
+		}
+		size = sizeof(attr);
+	}
+
+	/* copy attributes from user space, may be less than sizeof(bpf_attr) */
+	if (copy_from_user(&attr, uattr, size) != 0)
+		return -EFAULT;
+
+	switch (cmd) {
+	case BPF_MAP_CREATE:
+		err = map_create(&attr);
+		break;
+	default:
+		err = -EINVAL;
+		break;
+	}
+
+	return err;
+}
-- 
cgit v1.2.3


From 749730ce42a2121e1c88350d69478bff3994b10a Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:16:58 -0700
Subject: bpf: enable bpf syscall on x64 and i386

done as separate commit to ease conflict resolution

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/syscalls/syscall_32.tbl  | 1 +
 arch/x86/syscalls/syscall_64.tbl  | 1 +
 include/linux/syscalls.h          | 3 ++-
 include/uapi/asm-generic/unistd.h | 4 +++-
 kernel/sys_ni.c                   | 3 +++
 5 files changed, 10 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index 028b78168d85..9fe1b5d002f0 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -363,3 +363,4 @@
 354	i386	seccomp			sys_seccomp
 355	i386	getrandom		sys_getrandom
 356	i386	memfd_create		sys_memfd_create
+357	i386	bpf			sys_bpf
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 35dd922727b9..281150b539a2 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -327,6 +327,7 @@
 318	common	getrandom		sys_getrandom
 319	common	memfd_create		sys_memfd_create
 320	common	kexec_file_load		sys_kexec_file_load
+321	common	bpf			sys_bpf
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 0f86d85a9ce4..bda9b81357cc 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -65,6 +65,7 @@ struct old_linux_dirent;
 struct perf_event_attr;
 struct file_handle;
 struct sigaltstack;
+union bpf_attr;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -875,5 +876,5 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
 			    const char __user *uargs);
 asmlinkage long sys_getrandom(char __user *buf, size_t count,
 			      unsigned int flags);
-
+asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size);
 #endif
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 11d11bc5c78f..22749c134117 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -705,9 +705,11 @@ __SYSCALL(__NR_seccomp, sys_seccomp)
 __SYSCALL(__NR_getrandom, sys_getrandom)
 #define __NR_memfd_create 279
 __SYSCALL(__NR_memfd_create, sys_memfd_create)
+#define __NR_bpf 280
+__SYSCALL(__NR_bpf, sys_bpf)
 
 #undef __NR_syscalls
-#define __NR_syscalls 280
+#define __NR_syscalls 281
 
 /*
  * All syscalls below here should go away really,
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 391d4ddb6f4b..b4b5083f5f5e 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -218,3 +218,6 @@ cond_syscall(sys_kcmp);
 
 /* operate on Secure Computing state */
 cond_syscall(sys_seccomp);
+
+/* access BPF programs and maps */
+cond_syscall(sys_bpf);
-- 
cgit v1.2.3


From db20fd2b01087bdfbe30bce314a198eefedcc42e Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:16:59 -0700
Subject: bpf: add lookup/update/delete/iterate methods to BPF maps

'maps' is a generic storage of different types for sharing data between kernel
and userspace.

The maps are accessed from user space via BPF syscall, which has commands:

- create a map with given type and attributes
  fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)
  returns fd or negative error

- lookup key in a given map referenced by fd
  err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
  using attr->map_fd, attr->key, attr->value
  returns zero and stores found elem into value or negative error

- create or update key/value pair in a given map
  err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
  using attr->map_fd, attr->key, attr->value
  returns zero or negative error

- find and delete element by key in a given map
  err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
  using attr->map_fd, attr->key

- iterate map elements (based on input key return next_key)
  err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
  using attr->map_fd, attr->key, attr->next_key

- close(fd) deletes the map

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h      |   8 ++
 include/uapi/linux/bpf.h |  38 ++++++++
 kernel/bpf/syscall.c     | 235 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 281 insertions(+)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 48014a71f0fe..2887f3f9da59 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -9,6 +9,7 @@
 
 #include <uapi/linux/bpf.h>
 #include <linux/workqueue.h>
+#include <linux/file.h>
 
 struct bpf_map;
 
@@ -17,6 +18,12 @@ struct bpf_map_ops {
 	/* funcs callable from userspace (via syscall) */
 	struct bpf_map *(*map_alloc)(union bpf_attr *attr);
 	void (*map_free)(struct bpf_map *);
+	int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
+
+	/* funcs callable from userspace and from eBPF programs */
+	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
+	int (*map_update_elem)(struct bpf_map *map, void *key, void *value);
+	int (*map_delete_elem)(struct bpf_map *map, void *key);
 };
 
 struct bpf_map {
@@ -37,5 +44,6 @@ struct bpf_map_type_list {
 
 void bpf_register_map_type(struct bpf_map_type_list *tl);
 void bpf_map_put(struct bpf_map *map);
+struct bpf_map *bpf_map_get(struct fd f);
 
 #endif /* _LINUX_BPF_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f58a10f9670c..395cabd2ca0a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -70,6 +70,35 @@ enum bpf_cmd {
 	 * map is deleted when fd is closed
 	 */
 	BPF_MAP_CREATE,
+
+	/* lookup key in a given map
+	 * err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)
+	 * Using attr->map_fd, attr->key, attr->value
+	 * returns zero and stores found elem into value
+	 * or negative error
+	 */
+	BPF_MAP_LOOKUP_ELEM,
+
+	/* create or update key/value pair in a given map
+	 * err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
+	 * Using attr->map_fd, attr->key, attr->value
+	 * returns zero or negative error
+	 */
+	BPF_MAP_UPDATE_ELEM,
+
+	/* find and delete elem by key in a given map
+	 * err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)
+	 * Using attr->map_fd, attr->key
+	 * returns zero or negative error
+	 */
+	BPF_MAP_DELETE_ELEM,
+
+	/* lookup key in a given map and return next key
+	 * err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size)
+	 * Using attr->map_fd, attr->key, attr->next_key
+	 * returns zero and stores next key or negative error
+	 */
+	BPF_MAP_GET_NEXT_KEY,
 };
 
 enum bpf_map_type {
@@ -83,6 +112,15 @@ union bpf_attr {
 		__u32	value_size;	/* size of value in bytes */
 		__u32	max_entries;	/* max number of entries in a map */
 	};
+
+	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
+		__u32		map_fd;
+		__aligned_u64	key;
+		union {
+			__aligned_u64 value;
+			__aligned_u64 next_key;
+		};
+	};
 } __attribute__((aligned(8)));
 
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 428a0e23adc0..f94349ecaf61 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -13,6 +13,7 @@
 #include <linux/syscalls.h>
 #include <linux/slab.h>
 #include <linux/anon_inodes.h>
+#include <linux/file.h>
 
 static LIST_HEAD(bpf_map_types);
 
@@ -111,6 +112,228 @@ free_map:
 	return err;
 }
 
+/* if error is returned, fd is released.
+ * On success caller should complete fd access with matching fdput()
+ */
+struct bpf_map *bpf_map_get(struct fd f)
+{
+	struct bpf_map *map;
+
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	if (f.file->f_op != &bpf_map_fops) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	map = f.file->private_data;
+
+	return map;
+}
+
+/* helper to convert user pointers passed inside __aligned_u64 fields */
+static void __user *u64_to_ptr(__u64 val)
+{
+	return (void __user *) (unsigned long) val;
+}
+
+/* last field in 'union bpf_attr' used by this command */
+#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
+
+static int map_lookup_elem(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_ptr(attr->key);
+	void __user *uvalue = u64_to_ptr(attr->value);
+	int ufd = attr->map_fd;
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+	void *key, *value;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
+		return -EINVAL;
+
+	map = bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = -ENOMEM;
+	key = kmalloc(map->key_size, GFP_USER);
+	if (!key)
+		goto err_put;
+
+	err = -EFAULT;
+	if (copy_from_user(key, ukey, map->key_size) != 0)
+		goto free_key;
+
+	err = -ESRCH;
+	rcu_read_lock();
+	value = map->ops->map_lookup_elem(map, key);
+	if (!value)
+		goto err_unlock;
+
+	err = -EFAULT;
+	if (copy_to_user(uvalue, value, map->value_size) != 0)
+		goto err_unlock;
+
+	err = 0;
+
+err_unlock:
+	rcu_read_unlock();
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
+#define BPF_MAP_UPDATE_ELEM_LAST_FIELD value
+
+static int map_update_elem(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_ptr(attr->key);
+	void __user *uvalue = u64_to_ptr(attr->value);
+	int ufd = attr->map_fd;
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+	void *key, *value;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
+		return -EINVAL;
+
+	map = bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = -ENOMEM;
+	key = kmalloc(map->key_size, GFP_USER);
+	if (!key)
+		goto err_put;
+
+	err = -EFAULT;
+	if (copy_from_user(key, ukey, map->key_size) != 0)
+		goto free_key;
+
+	err = -ENOMEM;
+	value = kmalloc(map->value_size, GFP_USER);
+	if (!value)
+		goto free_key;
+
+	err = -EFAULT;
+	if (copy_from_user(value, uvalue, map->value_size) != 0)
+		goto free_value;
+
+	/* eBPF program that use maps are running under rcu_read_lock(),
+	 * therefore all map accessors rely on this fact, so do the same here
+	 */
+	rcu_read_lock();
+	err = map->ops->map_update_elem(map, key, value);
+	rcu_read_unlock();
+
+free_value:
+	kfree(value);
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
+#define BPF_MAP_DELETE_ELEM_LAST_FIELD key
+
+static int map_delete_elem(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_ptr(attr->key);
+	int ufd = attr->map_fd;
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+	void *key;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
+		return -EINVAL;
+
+	map = bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = -ENOMEM;
+	key = kmalloc(map->key_size, GFP_USER);
+	if (!key)
+		goto err_put;
+
+	err = -EFAULT;
+	if (copy_from_user(key, ukey, map->key_size) != 0)
+		goto free_key;
+
+	rcu_read_lock();
+	err = map->ops->map_delete_elem(map, key);
+	rcu_read_unlock();
+
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
+/* last field in 'union bpf_attr' used by this command */
+#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key
+
+static int map_get_next_key(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_ptr(attr->key);
+	void __user *unext_key = u64_to_ptr(attr->next_key);
+	int ufd = attr->map_fd;
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+	void *key, *next_key;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
+		return -EINVAL;
+
+	map = bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = -ENOMEM;
+	key = kmalloc(map->key_size, GFP_USER);
+	if (!key)
+		goto err_put;
+
+	err = -EFAULT;
+	if (copy_from_user(key, ukey, map->key_size) != 0)
+		goto free_key;
+
+	err = -ENOMEM;
+	next_key = kmalloc(map->key_size, GFP_USER);
+	if (!next_key)
+		goto free_key;
+
+	rcu_read_lock();
+	err = map->ops->map_get_next_key(map, key, next_key);
+	rcu_read_unlock();
+	if (err)
+		goto free_next_key;
+
+	err = -EFAULT;
+	if (copy_to_user(unext_key, next_key, map->key_size) != 0)
+		goto free_next_key;
+
+	err = 0;
+
+free_next_key:
+	kfree(next_key);
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
@@ -160,6 +383,18 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_MAP_CREATE:
 		err = map_create(&attr);
 		break;
+	case BPF_MAP_LOOKUP_ELEM:
+		err = map_lookup_elem(&attr);
+		break;
+	case BPF_MAP_UPDATE_ELEM:
+		err = map_update_elem(&attr);
+		break;
+	case BPF_MAP_DELETE_ELEM:
+		err = map_delete_elem(&attr);
+		break;
+	case BPF_MAP_GET_NEXT_KEY:
+		err = map_get_next_key(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
-- 
cgit v1.2.3


From 09756af46893c18839062976c3252e93a1beeba7 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:17:00 -0700
Subject: bpf: expand BPF syscall with program load/unload

eBPF programs are similar to kernel modules. They are loaded by the user
process and automatically unloaded when process exits. Each eBPF program is
a safe run-to-completion set of instructions. eBPF verifier statically
determines that the program terminates and is safe to execute.

The following syscall wrapper can be used to load the program:
int bpf_prog_load(enum bpf_prog_type prog_type,
                  const struct bpf_insn *insns, int insn_cnt,
                  const char *license)
{
    union bpf_attr attr = {
        .prog_type = prog_type,
        .insns = ptr_to_u64(insns),
        .insn_cnt = insn_cnt,
        .license = ptr_to_u64(license),
    };

    return bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
}
where 'insns' is an array of eBPF instructions and 'license' is a string
that must be GPL compatible to call helper functions marked gpl_only

Upon succesful load the syscall returns prog_fd.
Use close(prog_fd) to unload the program.

User space tests and examples follow in the later patches

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h      |  38 +++++++++++
 include/linux/filter.h   |   8 +--
 include/uapi/linux/bpf.h |  26 ++++++++
 kernel/bpf/core.c        |  29 +++++----
 kernel/bpf/syscall.c     | 165 +++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 246 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2887f3f9da59..92979182be81 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -46,4 +46,42 @@ void bpf_register_map_type(struct bpf_map_type_list *tl);
 void bpf_map_put(struct bpf_map *map);
 struct bpf_map *bpf_map_get(struct fd f);
 
+/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
+ * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
+ * instructions after verifying
+ */
+struct bpf_func_proto {
+	u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+	bool gpl_only;
+};
+
+struct bpf_verifier_ops {
+	/* return eBPF function prototype for verification */
+	const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
+};
+
+struct bpf_prog_type_list {
+	struct list_head list_node;
+	struct bpf_verifier_ops *ops;
+	enum bpf_prog_type type;
+};
+
+void bpf_register_prog_type(struct bpf_prog_type_list *tl);
+
+struct bpf_prog;
+
+struct bpf_prog_aux {
+	atomic_t refcnt;
+	bool is_gpl_compatible;
+	enum bpf_prog_type prog_type;
+	struct bpf_verifier_ops *ops;
+	struct bpf_map **used_maps;
+	u32 used_map_cnt;
+	struct bpf_prog *prog;
+	struct work_struct work;
+};
+
+void bpf_prog_put(struct bpf_prog *prog);
+struct bpf_prog *bpf_prog_get(u32 ufd);
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1a0bc6d134d7..4ffc0958d85e 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -21,6 +21,7 @@
 struct sk_buff;
 struct sock;
 struct seccomp_data;
+struct bpf_prog_aux;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
@@ -300,17 +301,12 @@ struct bpf_binary_header {
 	u8 image[];
 };
 
-struct bpf_work_struct {
-	struct bpf_prog *prog;
-	struct work_struct work;
-};
-
 struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	bool			jited;		/* Is our filter JIT'ed? */
 	u32			len;		/* Number of filter blocks */
 	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
-	struct bpf_work_struct	*work;		/* Deferred free work struct */
+	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
 	unsigned int		(*bpf_func)(const struct sk_buff *skb,
 					    const struct bpf_insn *filter);
 	/* Instructions for interpreter */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 395cabd2ca0a..424f442016e7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -99,12 +99,23 @@ enum bpf_cmd {
 	 * returns zero and stores next key or negative error
 	 */
 	BPF_MAP_GET_NEXT_KEY,
+
+	/* verify and load eBPF program
+	 * prog_fd = bpf(BPF_PROG_LOAD, union bpf_attr *attr, u32 size)
+	 * Using attr->prog_type, attr->insns, attr->license
+	 * returns fd or negative error
+	 */
+	BPF_PROG_LOAD,
 };
 
 enum bpf_map_type {
 	BPF_MAP_TYPE_UNSPEC,
 };
 
+enum bpf_prog_type {
+	BPF_PROG_TYPE_UNSPEC,
+};
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -121,6 +132,21 @@ union bpf_attr {
 			__aligned_u64 next_key;
 		};
 	};
+
+	struct { /* anonymous struct used by BPF_PROG_LOAD command */
+		__u32		prog_type;	/* one of enum bpf_prog_type */
+		__u32		insn_cnt;
+		__aligned_u64	insns;
+		__aligned_u64	license;
+	};
 } __attribute__((aligned(8)));
 
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+enum bpf_func_id {
+	BPF_FUNC_unspec,
+	__BPF_FUNC_MAX_ID,
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 8b7002488251..f0c30c59b317 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -27,6 +27,7 @@
 #include <linux/random.h>
 #include <linux/moduleloader.h>
 #include <asm/unaligned.h>
+#include <linux/bpf.h>
 
 /* Registers */
 #define BPF_R0	regs[BPF_REG_0]
@@ -71,7 +72,7 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 {
 	gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
 			  gfp_extra_flags;
-	struct bpf_work_struct *ws;
+	struct bpf_prog_aux *aux;
 	struct bpf_prog *fp;
 
 	size = round_up(size, PAGE_SIZE);
@@ -79,14 +80,14 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 	if (fp == NULL)
 		return NULL;
 
-	ws = kmalloc(sizeof(*ws), GFP_KERNEL | gfp_extra_flags);
-	if (ws == NULL) {
+	aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
+	if (aux == NULL) {
 		vfree(fp);
 		return NULL;
 	}
 
 	fp->pages = size / PAGE_SIZE;
-	fp->work = ws;
+	fp->aux = aux;
 
 	return fp;
 }
@@ -110,10 +111,10 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 		memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
 		fp->pages = size / PAGE_SIZE;
 
-		/* We keep fp->work from fp_old around in the new
+		/* We keep fp->aux from fp_old around in the new
 		 * reallocated structure.
 		 */
-		fp_old->work = NULL;
+		fp_old->aux = NULL;
 		__bpf_prog_free(fp_old);
 	}
 
@@ -123,7 +124,7 @@ EXPORT_SYMBOL_GPL(bpf_prog_realloc);
 
 void __bpf_prog_free(struct bpf_prog *fp)
 {
-	kfree(fp->work);
+	kfree(fp->aux);
 	vfree(fp);
 }
 EXPORT_SYMBOL_GPL(__bpf_prog_free);
@@ -638,19 +639,19 @@ EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
 
 static void bpf_prog_free_deferred(struct work_struct *work)
 {
-	struct bpf_work_struct *ws;
+	struct bpf_prog_aux *aux;
 
-	ws = container_of(work, struct bpf_work_struct, work);
-	bpf_jit_free(ws->prog);
+	aux = container_of(work, struct bpf_prog_aux, work);
+	bpf_jit_free(aux->prog);
 }
 
 /* Free internal BPF program */
 void bpf_prog_free(struct bpf_prog *fp)
 {
-	struct bpf_work_struct *ws = fp->work;
+	struct bpf_prog_aux *aux = fp->aux;
 
-	INIT_WORK(&ws->work, bpf_prog_free_deferred);
-	ws->prog = fp;
-	schedule_work(&ws->work);
+	INIT_WORK(&aux->work, bpf_prog_free_deferred);
+	aux->prog = fp;
+	schedule_work(&aux->work);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_free);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f94349ecaf61..0afb4eaa1887 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -14,6 +14,8 @@
 #include <linux/slab.h>
 #include <linux/anon_inodes.h>
 #include <linux/file.h>
+#include <linux/license.h>
+#include <linux/filter.h>
 
 static LIST_HEAD(bpf_map_types);
 
@@ -334,6 +336,166 @@ err_put:
 	return err;
 }
 
+static LIST_HEAD(bpf_prog_types);
+
+static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
+{
+	struct bpf_prog_type_list *tl;
+
+	list_for_each_entry(tl, &bpf_prog_types, list_node) {
+		if (tl->type == type) {
+			prog->aux->ops = tl->ops;
+			prog->aux->prog_type = type;
+			return 0;
+		}
+	}
+	return -EINVAL;
+}
+
+void bpf_register_prog_type(struct bpf_prog_type_list *tl)
+{
+	list_add(&tl->list_node, &bpf_prog_types);
+}
+
+/* drop refcnt on maps used by eBPF program and free auxilary data */
+static void free_used_maps(struct bpf_prog_aux *aux)
+{
+	int i;
+
+	for (i = 0; i < aux->used_map_cnt; i++)
+		bpf_map_put(aux->used_maps[i]);
+
+	kfree(aux->used_maps);
+}
+
+void bpf_prog_put(struct bpf_prog *prog)
+{
+	if (atomic_dec_and_test(&prog->aux->refcnt)) {
+		free_used_maps(prog->aux);
+		bpf_prog_free(prog);
+	}
+}
+
+static int bpf_prog_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_prog *prog = filp->private_data;
+
+	bpf_prog_put(prog);
+	return 0;
+}
+
+static const struct file_operations bpf_prog_fops = {
+        .release = bpf_prog_release,
+};
+
+static struct bpf_prog *get_prog(struct fd f)
+{
+	struct bpf_prog *prog;
+
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	if (f.file->f_op != &bpf_prog_fops) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	prog = f.file->private_data;
+
+	return prog;
+}
+
+/* called by sockets/tracing/seccomp before attaching program to an event
+ * pairs with bpf_prog_put()
+ */
+struct bpf_prog *bpf_prog_get(u32 ufd)
+{
+	struct fd f = fdget(ufd);
+	struct bpf_prog *prog;
+
+	prog = get_prog(f);
+
+	if (IS_ERR(prog))
+		return prog;
+
+	atomic_inc(&prog->aux->refcnt);
+	fdput(f);
+	return prog;
+}
+
+/* last field in 'union bpf_attr' used by this command */
+#define	BPF_PROG_LOAD_LAST_FIELD license
+
+static int bpf_prog_load(union bpf_attr *attr)
+{
+	enum bpf_prog_type type = attr->prog_type;
+	struct bpf_prog *prog;
+	int err;
+	char license[128];
+	bool is_gpl;
+
+	if (CHECK_ATTR(BPF_PROG_LOAD))
+		return -EINVAL;
+
+	/* copy eBPF program license from user space */
+	if (strncpy_from_user(license, u64_to_ptr(attr->license),
+			      sizeof(license) - 1) < 0)
+		return -EFAULT;
+	license[sizeof(license) - 1] = 0;
+
+	/* eBPF programs must be GPL compatible to use GPL-ed functions */
+	is_gpl = license_is_gpl_compatible(license);
+
+	if (attr->insn_cnt >= BPF_MAXINSNS)
+		return -EINVAL;
+
+	/* plain bpf_prog allocation */
+	prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
+	if (!prog)
+		return -ENOMEM;
+
+	prog->len = attr->insn_cnt;
+
+	err = -EFAULT;
+	if (copy_from_user(prog->insns, u64_to_ptr(attr->insns),
+			   prog->len * sizeof(struct bpf_insn)) != 0)
+		goto free_prog;
+
+	prog->orig_prog = NULL;
+	prog->jited = false;
+
+	atomic_set(&prog->aux->refcnt, 1);
+	prog->aux->is_gpl_compatible = is_gpl;
+
+	/* find program type: socket_filter vs tracing_filter */
+	err = find_prog_type(type, prog);
+	if (err < 0)
+		goto free_prog;
+
+	/* run eBPF verifier */
+	/* err = bpf_check(prog, tb); */
+
+	if (err < 0)
+		goto free_used_maps;
+
+	/* eBPF program is ready to be JITed */
+	bpf_prog_select_runtime(prog);
+
+	err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC);
+
+	if (err < 0)
+		/* failed to allocate fd */
+		goto free_used_maps;
+
+	return err;
+
+free_used_maps:
+	free_used_maps(prog->aux);
+free_prog:
+	bpf_prog_free(prog);
+	return err;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
@@ -395,6 +557,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_MAP_GET_NEXT_KEY:
 		err = map_get_next_key(&attr);
 		break;
+	case BPF_PROG_LOAD:
+		err = bpf_prog_load(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
-- 
cgit v1.2.3


From 51580e798cb61b0fc63fa3aa6c5c975375aa0550 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:17:02 -0700
Subject: bpf: verifier (add docs)

this patch adds all of eBPF verfier documentation and empty bpf_check()

The end goal for the verifier is to statically check safety of the program.

Verifier will catch:
- loops
- out of range jumps
- unreachable instructions
- invalid instructions
- uninitialized register access
- uninitialized stack access
- misaligned stack access
- out of range stack access
- invalid calling convention

More details in Documentation/networking/filter.txt

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/filter.txt | 224 ++++++++++++++++++++++++++++++++++++
 include/linux/bpf.h                 |   2 +
 kernel/bpf/Makefile                 |   2 +-
 kernel/bpf/syscall.c                |   2 +-
 kernel/bpf/verifier.c               | 133 +++++++++++++++++++++
 5 files changed, 361 insertions(+), 2 deletions(-)
 create mode 100644 kernel/bpf/verifier.c

(limited to 'include')

diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 4a01d71785e9..5ce4d07406a5 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -1001,6 +1001,99 @@ instruction that loads 64-bit immediate value into a dst_reg.
 Classic BPF has similar instruction: BPF_LD | BPF_W | BPF_IMM which loads
 32-bit immediate value into a register.
 
+eBPF verifier
+-------------
+The safety of the eBPF program is determined in two steps.
+
+First step does DAG check to disallow loops and other CFG validation.
+In particular it will detect programs that have unreachable instructions.
+(though classic BPF checker allows them)
+
+Second step starts from the first insn and descends all possible paths.
+It simulates execution of every insn and observes the state change of
+registers and stack.
+
+At the start of the program the register R1 contains a pointer to context
+and has type PTR_TO_CTX.
+If verifier sees an insn that does R2=R1, then R2 has now type
+PTR_TO_CTX as well and can be used on the right hand side of expression.
+If R1=PTR_TO_CTX and insn is R2=R1+R1, then R2=UNKNOWN_VALUE,
+since addition of two valid pointers makes invalid pointer.
+(In 'secure' mode verifier will reject any type of pointer arithmetic to make
+sure that kernel addresses don't leak to unprivileged users)
+
+If register was never written to, it's not readable:
+  bpf_mov R0 = R2
+  bpf_exit
+will be rejected, since R2 is unreadable at the start of the program.
+
+After kernel function call, R1-R5 are reset to unreadable and
+R0 has a return type of the function.
+
+Since R6-R9 are callee saved, their state is preserved across the call.
+  bpf_mov R6 = 1
+  bpf_call foo
+  bpf_mov R0 = R6
+  bpf_exit
+is a correct program. If there was R1 instead of R6, it would have
+been rejected.
+
+load/store instructions are allowed only with registers of valid types, which
+are PTR_TO_CTX, PTR_TO_MAP, FRAME_PTR. They are bounds and alignment checked.
+For example:
+ bpf_mov R1 = 1
+ bpf_mov R2 = 2
+ bpf_xadd *(u32 *)(R1 + 3) += R2
+ bpf_exit
+will be rejected, since R1 doesn't have a valid pointer type at the time of
+execution of instruction bpf_xadd.
+
+At the start R1 type is PTR_TO_CTX (a pointer to generic 'struct bpf_context')
+A callback is used to customize verifier to restrict eBPF program access to only
+certain fields within ctx structure with specified size and alignment.
+
+For example, the following insn:
+  bpf_ld R0 = *(u32 *)(R6 + 8)
+intends to load a word from address R6 + 8 and store it into R0
+If R6=PTR_TO_CTX, via is_valid_access() callback the verifier will know
+that offset 8 of size 4 bytes can be accessed for reading, otherwise
+the verifier will reject the program.
+If R6=FRAME_PTR, then access should be aligned and be within
+stack bounds, which are [-MAX_BPF_STACK, 0). In this example offset is 8,
+so it will fail verification, since it's out of bounds.
+
+The verifier will allow eBPF program to read data from stack only after
+it wrote into it.
+Classic BPF verifier does similar check with M[0-15] memory slots.
+For example:
+  bpf_ld R0 = *(u32 *)(R10 - 4)
+  bpf_exit
+is invalid program.
+Though R10 is correct read-only register and has type FRAME_PTR
+and R10 - 4 is within stack bounds, there were no stores into that location.
+
+Pointer register spill/fill is tracked as well, since four (R6-R9)
+callee saved registers may not be enough for some programs.
+
+Allowed function calls are customized with bpf_verifier_ops->get_func_proto()
+The eBPF verifier will check that registers match argument constraints.
+After the call register R0 will be set to return type of the function.
+
+Function calls is a main mechanism to extend functionality of eBPF programs.
+Socket filters may let programs to call one set of functions, whereas tracing
+filters may allow completely different set.
+
+If a function made accessible to eBPF program, it needs to be thought through
+from safety point of view. The verifier will guarantee that the function is
+called with valid arguments.
+
+seccomp vs socket filters have different security restrictions for classic BPF.
+Seccomp solves this by two stage verifier: classic BPF verifier is followed
+by seccomp verifier. In case of eBPF one configurable verifier is shared for
+all use cases.
+
+See details of eBPF verifier in kernel/bpf/verifier.c
+
 eBPF maps
 ---------
 'maps' is a generic storage of different types for sharing data between kernel
@@ -1040,6 +1133,137 @@ The map is defined by:
   . key size in bytes
   . value size in bytes
 
+Understanding eBPF verifier messages
+------------------------------------
+
+The following are few examples of invalid eBPF programs and verifier error
+messages as seen in the log:
+
+Program with unreachable instructions:
+static struct bpf_insn prog[] = {
+  BPF_EXIT_INSN(),
+  BPF_EXIT_INSN(),
+};
+Error:
+  unreachable insn 1
+
+Program that reads uninitialized register:
+  BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+  BPF_EXIT_INSN(),
+Error:
+  0: (bf) r0 = r2
+  R2 !read_ok
+
+Program that doesn't initialize R0 before exiting:
+  BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+  BPF_EXIT_INSN(),
+Error:
+  0: (bf) r2 = r1
+  1: (95) exit
+  R0 !read_ok
+
+Program that accesses stack out of bounds:
+  BPF_ST_MEM(BPF_DW, BPF_REG_10, 8, 0),
+  BPF_EXIT_INSN(),
+Error:
+  0: (7a) *(u64 *)(r10 +8) = 0
+  invalid stack off=8 size=8
+
+Program that doesn't initialize stack before passing its address into function:
+  BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+  BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+  BPF_LD_MAP_FD(BPF_REG_1, 0),
+  BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+  BPF_EXIT_INSN(),
+Error:
+  0: (bf) r2 = r10
+  1: (07) r2 += -8
+  2: (b7) r1 = 0x0
+  3: (85) call 1
+  invalid indirect read from stack off -8+0 size 8
+
+Program that uses invalid map_fd=0 while calling to map_lookup_elem() function:
+  BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+  BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+  BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+  BPF_LD_MAP_FD(BPF_REG_1, 0),
+  BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+  BPF_EXIT_INSN(),
+Error:
+  0: (7a) *(u64 *)(r10 -8) = 0
+  1: (bf) r2 = r10
+  2: (07) r2 += -8
+  3: (b7) r1 = 0x0
+  4: (85) call 1
+  fd 0 is not pointing to valid bpf_map
+
+Program that doesn't check return value of map_lookup_elem() before accessing
+map element:
+  BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+  BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+  BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+  BPF_LD_MAP_FD(BPF_REG_1, 0),
+  BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+  BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+  BPF_EXIT_INSN(),
+Error:
+  0: (7a) *(u64 *)(r10 -8) = 0
+  1: (bf) r2 = r10
+  2: (07) r2 += -8
+  3: (b7) r1 = 0x0
+  4: (85) call 1
+  5: (7a) *(u64 *)(r0 +0) = 0
+  R0 invalid mem access 'map_value_or_null'
+
+Program that correctly checks map_lookup_elem() returned value for NULL, but
+accesses the memory with incorrect alignment:
+  BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+  BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+  BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+  BPF_LD_MAP_FD(BPF_REG_1, 0),
+  BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+  BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+  BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0),
+  BPF_EXIT_INSN(),
+Error:
+  0: (7a) *(u64 *)(r10 -8) = 0
+  1: (bf) r2 = r10
+  2: (07) r2 += -8
+  3: (b7) r1 = 1
+  4: (85) call 1
+  5: (15) if r0 == 0x0 goto pc+1
+   R0=map_ptr R10=fp
+  6: (7a) *(u64 *)(r0 +4) = 0
+  misaligned access off 4 size 8
+
+Program that correctly checks map_lookup_elem() returned value for NULL and
+accesses memory with correct alignment in one side of 'if' branch, but fails
+to do so in the other side of 'if' branch:
+  BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+  BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+  BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+  BPF_LD_MAP_FD(BPF_REG_1, 0),
+  BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+  BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+  BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+  BPF_EXIT_INSN(),
+  BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 1),
+  BPF_EXIT_INSN(),
+Error:
+  0: (7a) *(u64 *)(r10 -8) = 0
+  1: (bf) r2 = r10
+  2: (07) r2 += -8
+  3: (b7) r1 = 1
+  4: (85) call 1
+  5: (15) if r0 == 0x0 goto pc+2
+   R0=map_ptr R10=fp
+  6: (7a) *(u64 *)(r0 +0) = 0
+  7: (95) exit
+
+  from 5 to 8: R0=imm0 R10=fp
+  8: (7a) *(u64 *)(r0 +0) = 1
+  R0 invalid mem access 'imm'
+
 Testing
 -------
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 92979182be81..9dfeb36f8971 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -83,5 +83,7 @@ struct bpf_prog_aux {
 
 void bpf_prog_put(struct bpf_prog *prog);
 struct bpf_prog *bpf_prog_get(u32 ufd);
+/* verify correctness of eBPF program */
+int bpf_check(struct bpf_prog *fp, union bpf_attr *attr);
 
 #endif /* _LINUX_BPF_H */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index e9f7334ed07a..3c726b0995b7 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1 +1 @@
-obj-y := core.o syscall.o
+obj-y := core.o syscall.o verifier.o
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b513659d120f..74b3628c5fdb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -507,7 +507,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 		goto free_prog;
 
 	/* run eBPF verifier */
-	/* err = bpf_check(prog, tb); */
+	err = bpf_check(prog, attr);
 
 	if (err < 0)
 		goto free_used_maps;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
new file mode 100644
index 000000000000..d6f9c3d6b4d7
--- /dev/null
+++ b/kernel/bpf/verifier.c
@@ -0,0 +1,133 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <net/netlink.h>
+#include <linux/file.h>
+#include <linux/vmalloc.h>
+
+/* bpf_check() is a static code analyzer that walks eBPF program
+ * instruction by instruction and updates register/stack state.
+ * All paths of conditional branches are analyzed until 'bpf_exit' insn.
+ *
+ * The first pass is depth-first-search to check that the program is a DAG.
+ * It rejects the following programs:
+ * - larger than BPF_MAXINSNS insns
+ * - if loop is present (detected via back-edge)
+ * - unreachable insns exist (shouldn't be a forest. program = one function)
+ * - out of bounds or malformed jumps
+ * The second pass is all possible path descent from the 1st insn.
+ * Since it's analyzing all pathes through the program, the length of the
+ * analysis is limited to 32k insn, which may be hit even if total number of
+ * insn is less then 4K, but there are too many branches that change stack/regs.
+ * Number of 'branches to be analyzed' is limited to 1k
+ *
+ * On entry to each instruction, each register has a type, and the instruction
+ * changes the types of the registers depending on instruction semantics.
+ * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is
+ * copied to R1.
+ *
+ * All registers are 64-bit.
+ * R0 - return register
+ * R1-R5 argument passing registers
+ * R6-R9 callee saved registers
+ * R10 - frame pointer read-only
+ *
+ * At the start of BPF program the register R1 contains a pointer to bpf_context
+ * and has type PTR_TO_CTX.
+ *
+ * Verifier tracks arithmetic operations on pointers in case:
+ *    BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20),
+ * 1st insn copies R10 (which has FRAME_PTR) type into R1
+ * and 2nd arithmetic instruction is pattern matched to recognize
+ * that it wants to construct a pointer to some element within stack.
+ * So after 2nd insn, the register R1 has type PTR_TO_STACK
+ * (and -20 constant is saved for further stack bounds checking).
+ * Meaning that this reg is a pointer to stack plus known immediate constant.
+ *
+ * Most of the time the registers have UNKNOWN_VALUE type, which
+ * means the register has some value, but it's not a valid pointer.
+ * (like pointer plus pointer becomes UNKNOWN_VALUE type)
+ *
+ * When verifier sees load or store instructions the type of base register
+ * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, FRAME_PTR. These are three pointer
+ * types recognized by check_mem_access() function.
+ *
+ * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
+ * and the range of [ptr, ptr + map's value_size) is accessible.
+ *
+ * registers used to pass values to function calls are checked against
+ * function argument constraints.
+ *
+ * ARG_PTR_TO_MAP_KEY is one of such argument constraints.
+ * It means that the register type passed to this function must be
+ * PTR_TO_STACK and it will be used inside the function as
+ * 'pointer to map element key'
+ *
+ * For example the argument constraints for bpf_map_lookup_elem():
+ *   .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ *   .arg1_type = ARG_CONST_MAP_PTR,
+ *   .arg2_type = ARG_PTR_TO_MAP_KEY,
+ *
+ * ret_type says that this function returns 'pointer to map elem value or null'
+ * function expects 1st argument to be a const pointer to 'struct bpf_map' and
+ * 2nd argument should be a pointer to stack, which will be used inside
+ * the helper function as a pointer to map element key.
+ *
+ * On the kernel side the helper function looks like:
+ * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+ * {
+ *    struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
+ *    void *key = (void *) (unsigned long) r2;
+ *    void *value;
+ *
+ *    here kernel can access 'key' and 'map' pointers safely, knowing that
+ *    [key, key + map->key_size) bytes are valid and were initialized on
+ *    the stack of eBPF program.
+ * }
+ *
+ * Corresponding eBPF program may look like:
+ *    BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),  // after this insn R2 type is FRAME_PTR
+ *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
+ *    BPF_LD_MAP_FD(BPF_REG_1, map_fd),      // after this insn R1 type is CONST_PTR_TO_MAP
+ *    BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ * here verifier looks at prototype of map_lookup_elem() and sees:
+ * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok,
+ * Now verifier knows that this map has key of R1->map_ptr->key_size bytes
+ *
+ * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
+ * Now verifier checks that [R2, R2 + map's key_size) are within stack limits
+ * and were initialized prior to this call.
+ * If it's ok, then verifier allows this BPF_CALL insn and looks at
+ * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
+ * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
+ * returns ether pointer to map value or NULL.
+ *
+ * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
+ * insn, the register holding that pointer in the true branch changes state to
+ * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false
+ * branch. See check_cond_jmp_op().
+ *
+ * After the call R0 is set to return type of the function and registers R1-R5
+ * are set to NOT_INIT to indicate that they are no longer readable.
+ */
+
+int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
+{
+	int ret = -EINVAL;
+
+	return ret;
+}
-- 
cgit v1.2.3


From cbd357008604925355ae7b54a09137dabb81b580 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:17:03 -0700
Subject: bpf: verifier (add ability to receive verification log)

add optional attributes for BPF_PROG_LOAD syscall:
union bpf_attr {
    struct {
	...
	__u32         log_level; /* verbosity level of eBPF verifier */
	__u32         log_size;  /* size of user buffer */
	__aligned_u64 log_buf;   /* user supplied 'char *buffer' */
    };
};

when log_level > 0 the verifier will return its verification log in the user
supplied buffer 'log_buf' which can be used by program author to analyze why
verifier rejected given program.

'Understanding eBPF verifier messages' section of Documentation/networking/filter.txt
provides several examples of these messages, like the program:

  BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
  BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
  BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
  BPF_LD_MAP_FD(BPF_REG_1, 0),
  BPF_CALL_FUNC(BPF_FUNC_map_lookup_elem),
  BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
  BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0),
  BPF_EXIT_INSN(),

will be rejected with the following multi-line message in log_buf:

  0: (7a) *(u64 *)(r10 -8) = 0
  1: (bf) r2 = r10
  2: (07) r2 += -8
  3: (b7) r1 = 0
  4: (85) call 1
  5: (15) if r0 == 0x0 goto pc+1
   R0=map_ptr R10=fp
  6: (7a) *(u64 *)(r0 +4) = 0
  misaligned access off 4 size 8

The format of the output can change at any time as verifier evolves.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/bpf.h |   3 +
 kernel/bpf/syscall.c     |   2 +-
 kernel/bpf/verifier.c    | 235 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 239 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 424f442016e7..31b0ac208a52 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -138,6 +138,9 @@ union bpf_attr {
 		__u32		insn_cnt;
 		__aligned_u64	insns;
 		__aligned_u64	license;
+		__u32		log_level;	/* verbosity level of verifier */
+		__u32		log_size;	/* size of user buffer */
+		__aligned_u64	log_buf;	/* user supplied buffer */
 	};
 } __attribute__((aligned(8)));
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 74b3628c5fdb..ba61c8c16032 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -458,7 +458,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD license
+#define	BPF_PROG_LOAD_LAST_FIELD log_buf
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d6f9c3d6b4d7..871edc1f2e1f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -125,9 +125,244 @@
  * are set to NOT_INIT to indicate that they are no longer readable.
  */
 
+/* single container for all structs
+ * one verifier_env per bpf_check() call
+ */
+struct verifier_env {
+};
+
+/* verbose verifier prints what it's seeing
+ * bpf_check() is called under lock, so no race to access these global vars
+ */
+static u32 log_level, log_size, log_len;
+static char *log_buf;
+
+static DEFINE_MUTEX(bpf_verifier_lock);
+
+/* log_level controls verbosity level of eBPF verifier.
+ * verbose() is used to dump the verification trace to the log, so the user
+ * can figure out what's wrong with the program
+ */
+static void verbose(const char *fmt, ...)
+{
+	va_list args;
+
+	if (log_level == 0 || log_len >= log_size - 1)
+		return;
+
+	va_start(args, fmt);
+	log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args);
+	va_end(args);
+}
+
+static const char *const bpf_class_string[] = {
+	[BPF_LD]    = "ld",
+	[BPF_LDX]   = "ldx",
+	[BPF_ST]    = "st",
+	[BPF_STX]   = "stx",
+	[BPF_ALU]   = "alu",
+	[BPF_JMP]   = "jmp",
+	[BPF_RET]   = "BUG",
+	[BPF_ALU64] = "alu64",
+};
+
+static const char *const bpf_alu_string[] = {
+	[BPF_ADD >> 4]  = "+=",
+	[BPF_SUB >> 4]  = "-=",
+	[BPF_MUL >> 4]  = "*=",
+	[BPF_DIV >> 4]  = "/=",
+	[BPF_OR  >> 4]  = "|=",
+	[BPF_AND >> 4]  = "&=",
+	[BPF_LSH >> 4]  = "<<=",
+	[BPF_RSH >> 4]  = ">>=",
+	[BPF_NEG >> 4]  = "neg",
+	[BPF_MOD >> 4]  = "%=",
+	[BPF_XOR >> 4]  = "^=",
+	[BPF_MOV >> 4]  = "=",
+	[BPF_ARSH >> 4] = "s>>=",
+	[BPF_END >> 4]  = "endian",
+};
+
+static const char *const bpf_ldst_string[] = {
+	[BPF_W >> 3]  = "u32",
+	[BPF_H >> 3]  = "u16",
+	[BPF_B >> 3]  = "u8",
+	[BPF_DW >> 3] = "u64",
+};
+
+static const char *const bpf_jmp_string[] = {
+	[BPF_JA >> 4]   = "jmp",
+	[BPF_JEQ >> 4]  = "==",
+	[BPF_JGT >> 4]  = ">",
+	[BPF_JGE >> 4]  = ">=",
+	[BPF_JSET >> 4] = "&",
+	[BPF_JNE >> 4]  = "!=",
+	[BPF_JSGT >> 4] = "s>",
+	[BPF_JSGE >> 4] = "s>=",
+	[BPF_CALL >> 4] = "call",
+	[BPF_EXIT >> 4] = "exit",
+};
+
+static void print_bpf_insn(struct bpf_insn *insn)
+{
+	u8 class = BPF_CLASS(insn->code);
+
+	if (class == BPF_ALU || class == BPF_ALU64) {
+		if (BPF_SRC(insn->code) == BPF_X)
+			verbose("(%02x) %sr%d %s %sr%d\n",
+				insn->code, class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg,
+				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				class == BPF_ALU ? "(u32) " : "",
+				insn->src_reg);
+		else
+			verbose("(%02x) %sr%d %s %s%d\n",
+				insn->code, class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg,
+				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				class == BPF_ALU ? "(u32) " : "",
+				insn->imm);
+	} else if (class == BPF_STX) {
+		if (BPF_MODE(insn->code) == BPF_MEM)
+			verbose("(%02x) *(%s *)(r%d %+d) = r%d\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg,
+				insn->off, insn->src_reg);
+		else if (BPF_MODE(insn->code) == BPF_XADD)
+			verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg, insn->off,
+				insn->src_reg);
+		else
+			verbose("BUG_%02x\n", insn->code);
+	} else if (class == BPF_ST) {
+		if (BPF_MODE(insn->code) != BPF_MEM) {
+			verbose("BUG_st_%02x\n", insn->code);
+			return;
+		}
+		verbose("(%02x) *(%s *)(r%d %+d) = %d\n",
+			insn->code,
+			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+			insn->dst_reg,
+			insn->off, insn->imm);
+	} else if (class == BPF_LDX) {
+		if (BPF_MODE(insn->code) != BPF_MEM) {
+			verbose("BUG_ldx_%02x\n", insn->code);
+			return;
+		}
+		verbose("(%02x) r%d = *(%s *)(r%d %+d)\n",
+			insn->code, insn->dst_reg,
+			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+			insn->src_reg, insn->off);
+	} else if (class == BPF_LD) {
+		if (BPF_MODE(insn->code) == BPF_ABS) {
+			verbose("(%02x) r0 = *(%s *)skb[%d]\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IND) {
+			verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->src_reg, insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IMM) {
+			verbose("(%02x) r%d = 0x%x\n",
+				insn->code, insn->dst_reg, insn->imm);
+		} else {
+			verbose("BUG_ld_%02x\n", insn->code);
+			return;
+		}
+	} else if (class == BPF_JMP) {
+		u8 opcode = BPF_OP(insn->code);
+
+		if (opcode == BPF_CALL) {
+			verbose("(%02x) call %d\n", insn->code, insn->imm);
+		} else if (insn->code == (BPF_JMP | BPF_JA)) {
+			verbose("(%02x) goto pc%+d\n",
+				insn->code, insn->off);
+		} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
+			verbose("(%02x) exit\n", insn->code);
+		} else if (BPF_SRC(insn->code) == BPF_X) {
+			verbose("(%02x) if r%d %s r%d goto pc%+d\n",
+				insn->code, insn->dst_reg,
+				bpf_jmp_string[BPF_OP(insn->code) >> 4],
+				insn->src_reg, insn->off);
+		} else {
+			verbose("(%02x) if r%d %s 0x%x goto pc%+d\n",
+				insn->code, insn->dst_reg,
+				bpf_jmp_string[BPF_OP(insn->code) >> 4],
+				insn->imm, insn->off);
+		}
+	} else {
+		verbose("(%02x) %s\n", insn->code, bpf_class_string[class]);
+	}
+}
+
 int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 {
+	char __user *log_ubuf = NULL;
+	struct verifier_env *env;
 	int ret = -EINVAL;
 
+	if (prog->len <= 0 || prog->len > BPF_MAXINSNS)
+		return -E2BIG;
+
+	/* 'struct verifier_env' can be global, but since it's not small,
+	 * allocate/free it every time bpf_check() is called
+	 */
+	env = kzalloc(sizeof(struct verifier_env), GFP_KERNEL);
+	if (!env)
+		return -ENOMEM;
+
+	/* grab the mutex to protect few globals used by verifier */
+	mutex_lock(&bpf_verifier_lock);
+
+	if (attr->log_level || attr->log_buf || attr->log_size) {
+		/* user requested verbose verifier output
+		 * and supplied buffer to store the verification trace
+		 */
+		log_level = attr->log_level;
+		log_ubuf = (char __user *) (unsigned long) attr->log_buf;
+		log_size = attr->log_size;
+		log_len = 0;
+
+		ret = -EINVAL;
+		/* log_* values have to be sane */
+		if (log_size < 128 || log_size > UINT_MAX >> 8 ||
+		    log_level == 0 || log_ubuf == NULL)
+			goto free_env;
+
+		ret = -ENOMEM;
+		log_buf = vmalloc(log_size);
+		if (!log_buf)
+			goto free_env;
+	} else {
+		log_level = 0;
+	}
+
+	/* ret = do_check(env); */
+
+	if (log_level && log_len >= log_size - 1) {
+		BUG_ON(log_len >= log_size);
+		/* verifier log exceeded user supplied buffer */
+		ret = -ENOSPC;
+		/* fall through to return what was recorded */
+	}
+
+	/* copy verifier log back to user space including trailing zero */
+	if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) {
+		ret = -EFAULT;
+		goto free_log_buf;
+	}
+
+
+free_log_buf:
+	if (log_level)
+		vfree(log_buf);
+free_env:
+	kfree(env);
+	mutex_unlock(&bpf_verifier_lock);
 	return ret;
 }
-- 
cgit v1.2.3


From 0246e64d9a5fcd4805198de59b9b5cf1f974eb41 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:17:04 -0700
Subject: bpf: handle pseudo BPF_LD_IMM64 insn

eBPF programs passed from userspace are using pseudo BPF_LD_IMM64 instructions
to refer to process-local map_fd. Scan the program for such instructions and
if FDs are valid, convert them to 'struct bpf_map' pointers which will be used
by verifier to check access to maps in bpf_map_lookup/update() calls.
If program passes verifier, convert pseudo BPF_LD_IMM64 into generic by dropping
BPF_PSEUDO_MAP_FD flag.

Note that eBPF interpreter is generic and knows nothing about pseudo insns.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h |   6 ++
 kernel/bpf/verifier.c  | 147 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 153 insertions(+)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4ffc0958d85e..ca95abd2bed1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -145,6 +145,12 @@ struct bpf_prog_aux;
 		.off   = 0,					\
 		.imm   = ((__u64) (IMM)) >> 32 })
 
+#define BPF_PSEUDO_MAP_FD	1
+
+/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
+#define BPF_LD_MAP_FD(DST, MAP_FD)				\
+	BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+
 /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */
 
 #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM)			\
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 871edc1f2e1f..7227543e474b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -125,10 +125,15 @@
  * are set to NOT_INIT to indicate that they are no longer readable.
  */
 
+#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
+
 /* single container for all structs
  * one verifier_env per bpf_check() call
  */
 struct verifier_env {
+	struct bpf_prog *prog;		/* eBPF program being verified */
+	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
+	u32 used_map_cnt;		/* number of used maps */
 };
 
 /* verbose verifier prints what it's seeing
@@ -300,6 +305,115 @@ static void print_bpf_insn(struct bpf_insn *insn)
 	}
 }
 
+/* return the map pointer stored inside BPF_LD_IMM64 instruction */
+static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
+{
+	u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;
+
+	return (struct bpf_map *) (unsigned long) imm64;
+}
+
+/* look for pseudo eBPF instructions that access map FDs and
+ * replace them with actual map pointers
+ */
+static int replace_map_fd_with_map_ptr(struct verifier_env *env)
+{
+	struct bpf_insn *insn = env->prog->insnsi;
+	int insn_cnt = env->prog->len;
+	int i, j;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+			struct bpf_map *map;
+			struct fd f;
+
+			if (i == insn_cnt - 1 || insn[1].code != 0 ||
+			    insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
+			    insn[1].off != 0) {
+				verbose("invalid bpf_ld_imm64 insn\n");
+				return -EINVAL;
+			}
+
+			if (insn->src_reg == 0)
+				/* valid generic load 64-bit imm */
+				goto next_insn;
+
+			if (insn->src_reg != BPF_PSEUDO_MAP_FD) {
+				verbose("unrecognized bpf_ld_imm64 insn\n");
+				return -EINVAL;
+			}
+
+			f = fdget(insn->imm);
+
+			map = bpf_map_get(f);
+			if (IS_ERR(map)) {
+				verbose("fd %d is not pointing to valid bpf_map\n",
+					insn->imm);
+				fdput(f);
+				return PTR_ERR(map);
+			}
+
+			/* store map pointer inside BPF_LD_IMM64 instruction */
+			insn[0].imm = (u32) (unsigned long) map;
+			insn[1].imm = ((u64) (unsigned long) map) >> 32;
+
+			/* check whether we recorded this map already */
+			for (j = 0; j < env->used_map_cnt; j++)
+				if (env->used_maps[j] == map) {
+					fdput(f);
+					goto next_insn;
+				}
+
+			if (env->used_map_cnt >= MAX_USED_MAPS) {
+				fdput(f);
+				return -E2BIG;
+			}
+
+			/* remember this map */
+			env->used_maps[env->used_map_cnt++] = map;
+
+			/* hold the map. If the program is rejected by verifier,
+			 * the map will be released by release_maps() or it
+			 * will be used by the valid program until it's unloaded
+			 * and all maps are released in free_bpf_prog_info()
+			 */
+			atomic_inc(&map->refcnt);
+
+			fdput(f);
+next_insn:
+			insn++;
+			i++;
+		}
+	}
+
+	/* now all pseudo BPF_LD_IMM64 instructions load valid
+	 * 'struct bpf_map *' into a register instead of user map_fd.
+	 * These pointers will be used later by verifier to validate map access.
+	 */
+	return 0;
+}
+
+/* drop refcnt of maps used by the rejected program */
+static void release_maps(struct verifier_env *env)
+{
+	int i;
+
+	for (i = 0; i < env->used_map_cnt; i++)
+		bpf_map_put(env->used_maps[i]);
+}
+
+/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
+static void convert_pseudo_ld_imm64(struct verifier_env *env)
+{
+	struct bpf_insn *insn = env->prog->insnsi;
+	int insn_cnt = env->prog->len;
+	int i;
+
+	for (i = 0; i < insn_cnt; i++, insn++)
+		if (insn->code == (BPF_LD | BPF_IMM | BPF_DW))
+			insn->src_reg = 0;
+}
+
 int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 {
 	char __user *log_ubuf = NULL;
@@ -316,6 +430,8 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 	if (!env)
 		return -ENOMEM;
 
+	env->prog = prog;
+
 	/* grab the mutex to protect few globals used by verifier */
 	mutex_lock(&bpf_verifier_lock);
 
@@ -342,8 +458,14 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 		log_level = 0;
 	}
 
+	ret = replace_map_fd_with_map_ptr(env);
+	if (ret < 0)
+		goto skip_full_check;
+
 	/* ret = do_check(env); */
 
+skip_full_check:
+
 	if (log_level && log_len >= log_size - 1) {
 		BUG_ON(log_len >= log_size);
 		/* verifier log exceeded user supplied buffer */
@@ -357,11 +479,36 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 		goto free_log_buf;
 	}
 
+	if (ret == 0 && env->used_map_cnt) {
+		/* if program passed verifier, update used_maps in bpf_prog_info */
+		prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
+						     sizeof(env->used_maps[0]),
+						     GFP_KERNEL);
+
+		if (!prog->aux->used_maps) {
+			ret = -ENOMEM;
+			goto free_log_buf;
+		}
+
+		memcpy(prog->aux->used_maps, env->used_maps,
+		       sizeof(env->used_maps[0]) * env->used_map_cnt);
+		prog->aux->used_map_cnt = env->used_map_cnt;
+
+		/* program is valid. Convert pseudo bpf_ld_imm64 into generic
+		 * bpf_ld_imm64 instructions
+		 */
+		convert_pseudo_ld_imm64(env);
+	}
 
 free_log_buf:
 	if (log_level)
 		vfree(log_buf);
 free_env:
+	if (!prog->aux->used_maps)
+		/* if we didn't copy map pointers into bpf_prog_info, release
+		 * them now. Otherwise free_bpf_prog_info() will release them.
+		 */
+		release_maps(env);
 	kfree(env);
 	mutex_unlock(&bpf_verifier_lock);
 	return ret;
-- 
cgit v1.2.3


From 17a5267067f3c372fec9ffb798d6eaba6b5e6a4c Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 26 Sep 2014 00:17:06 -0700
Subject: bpf: verifier (add verifier core)

This patch adds verifier core which simulates execution of every insn and
records the state of registers and program stack. Every branch instruction seen
during simulation is pushed into state stack. When verifier reaches BPF_EXIT,
it pops the state from the stack and continues until it reaches BPF_EXIT again.
For program:
1: bpf_mov r1, xxx
2: if (r1 == 0) goto 5
3: bpf_mov r0, 1
4: goto 6
5: bpf_mov r0, 2
6: bpf_exit
The verifier will walk insns: 1, 2, 3, 4, 6
then it will pop the state recorded at insn#2 and will continue: 5, 6

This way it walks all possible paths through the program and checks all
possible values of registers. While doing so, it checks for:
- invalid instructions
- uninitialized register access
- uninitialized stack access
- misaligned stack access
- out of range stack access
- invalid calling convention
- instruction encoding is not using reserved fields

Kernel subsystem configures the verifier with two callbacks:

- bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
  that provides information to the verifer which fields of 'ctx'
  are accessible (remember 'ctx' is the first argument to eBPF program)

- const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
  returns argument constraints of kernel helper functions that eBPF program
  may call, so that verifier can checks that R1-R5 types match the prototype

More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h   |   47 +++
 kernel/bpf/verifier.c | 1075 ++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 1121 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9dfeb36f8971..3cf91754a957 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -46,6 +46,31 @@ void bpf_register_map_type(struct bpf_map_type_list *tl);
 void bpf_map_put(struct bpf_map *map);
 struct bpf_map *bpf_map_get(struct fd f);
 
+/* function argument constraints */
+enum bpf_arg_type {
+	ARG_ANYTHING = 0,	/* any argument is ok */
+
+	/* the following constraints used to prototype
+	 * bpf_map_lookup/update/delete_elem() functions
+	 */
+	ARG_CONST_MAP_PTR,	/* const argument used as pointer to bpf_map */
+	ARG_PTR_TO_MAP_KEY,	/* pointer to stack used as map key */
+	ARG_PTR_TO_MAP_VALUE,	/* pointer to stack used as map value */
+
+	/* the following constraints used to prototype bpf_memcmp() and other
+	 * functions that access data on eBPF program stack
+	 */
+	ARG_PTR_TO_STACK,	/* any pointer to eBPF program stack */
+	ARG_CONST_STACK_SIZE,	/* number of bytes accessed from stack */
+};
+
+/* type of values returned from helper functions */
+enum bpf_return_type {
+	RET_INTEGER,			/* function returns integer */
+	RET_VOID,			/* function doesn't return anything */
+	RET_PTR_TO_MAP_VALUE_OR_NULL,	/* returns a pointer to map elem value or NULL */
+};
+
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
  * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
  * instructions after verifying
@@ -53,11 +78,33 @@ struct bpf_map *bpf_map_get(struct fd f);
 struct bpf_func_proto {
 	u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 	bool gpl_only;
+	enum bpf_return_type ret_type;
+	enum bpf_arg_type arg1_type;
+	enum bpf_arg_type arg2_type;
+	enum bpf_arg_type arg3_type;
+	enum bpf_arg_type arg4_type;
+	enum bpf_arg_type arg5_type;
+};
+
+/* bpf_context is intentionally undefined structure. Pointer to bpf_context is
+ * the first argument to eBPF programs.
+ * For socket filters: 'struct bpf_context *' == 'struct sk_buff *'
+ */
+struct bpf_context;
+
+enum bpf_access_type {
+	BPF_READ = 1,
+	BPF_WRITE = 2
 };
 
 struct bpf_verifier_ops {
 	/* return eBPF function prototype for verification */
 	const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
+
+	/* return true if 'size' wide access at offset 'off' within bpf_context
+	 * with 'type' (read or write) is allowed
+	 */
+	bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
 };
 
 struct bpf_prog_type_list {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c689ab8e2713..a086dd3210a8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -125,6 +125,70 @@
  * are set to NOT_INIT to indicate that they are no longer readable.
  */
 
+/* types of values stored in eBPF registers */
+enum bpf_reg_type {
+	NOT_INIT = 0,		 /* nothing was written into register */
+	UNKNOWN_VALUE,		 /* reg doesn't contain a valid pointer */
+	PTR_TO_CTX,		 /* reg points to bpf_context */
+	CONST_PTR_TO_MAP,	 /* reg points to struct bpf_map */
+	PTR_TO_MAP_VALUE,	 /* reg points to map element value */
+	PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
+	FRAME_PTR,		 /* reg == frame_pointer */
+	PTR_TO_STACK,		 /* reg == frame_pointer + imm */
+	CONST_IMM,		 /* constant integer value */
+};
+
+struct reg_state {
+	enum bpf_reg_type type;
+	union {
+		/* valid when type == CONST_IMM | PTR_TO_STACK */
+		int imm;
+
+		/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
+		 *   PTR_TO_MAP_VALUE_OR_NULL
+		 */
+		struct bpf_map *map_ptr;
+	};
+};
+
+enum bpf_stack_slot_type {
+	STACK_INVALID,    /* nothing was stored in this stack slot */
+	STACK_SPILL,      /* 1st byte of register spilled into stack */
+	STACK_SPILL_PART, /* other 7 bytes of register spill */
+	STACK_MISC	  /* BPF program wrote some data into this slot */
+};
+
+struct bpf_stack_slot {
+	enum bpf_stack_slot_type stype;
+	struct reg_state reg_st;
+};
+
+/* state of the program:
+ * type of all registers and stack info
+ */
+struct verifier_state {
+	struct reg_state regs[MAX_BPF_REG];
+	struct bpf_stack_slot stack[MAX_BPF_STACK];
+};
+
+/* linked list of verifier states used to prune search */
+struct verifier_state_list {
+	struct verifier_state state;
+	struct verifier_state_list *next;
+};
+
+/* verifier_state + insn_idx are pushed to stack when branch is encountered */
+struct verifier_stack_elem {
+	/* verifer state is 'st'
+	 * before processing instruction 'insn_idx'
+	 * and after processing instruction 'prev_insn_idx'
+	 */
+	struct verifier_state st;
+	int insn_idx;
+	int prev_insn_idx;
+	struct verifier_stack_elem *next;
+};
+
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
 
 /* single container for all structs
@@ -132,6 +196,9 @@
  */
 struct verifier_env {
 	struct bpf_prog *prog;		/* eBPF program being verified */
+	struct verifier_stack_elem *head; /* stack of verifier states to be processed */
+	int stack_size;			/* number of states to be processed */
+	struct verifier_state cur_state; /* current verifier state */
 	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
 	u32 used_map_cnt;		/* number of used maps */
 };
@@ -160,6 +227,45 @@ static void verbose(const char *fmt, ...)
 	va_end(args);
 }
 
+/* string representation of 'enum bpf_reg_type' */
+static const char * const reg_type_str[] = {
+	[NOT_INIT]		= "?",
+	[UNKNOWN_VALUE]		= "inv",
+	[PTR_TO_CTX]		= "ctx",
+	[CONST_PTR_TO_MAP]	= "map_ptr",
+	[PTR_TO_MAP_VALUE]	= "map_value",
+	[PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
+	[FRAME_PTR]		= "fp",
+	[PTR_TO_STACK]		= "fp",
+	[CONST_IMM]		= "imm",
+};
+
+static void print_verifier_state(struct verifier_env *env)
+{
+	enum bpf_reg_type t;
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++) {
+		t = env->cur_state.regs[i].type;
+		if (t == NOT_INIT)
+			continue;
+		verbose(" R%d=%s", i, reg_type_str[t]);
+		if (t == CONST_IMM || t == PTR_TO_STACK)
+			verbose("%d", env->cur_state.regs[i].imm);
+		else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
+			 t == PTR_TO_MAP_VALUE_OR_NULL)
+			verbose("(ks=%d,vs=%d)",
+				env->cur_state.regs[i].map_ptr->key_size,
+				env->cur_state.regs[i].map_ptr->value_size);
+	}
+	for (i = 0; i < MAX_BPF_STACK; i++) {
+		if (env->cur_state.stack[i].stype == STACK_SPILL)
+			verbose(" fp%d=%s", -MAX_BPF_STACK + i,
+				reg_type_str[env->cur_state.stack[i].reg_st.type]);
+	}
+	verbose("\n");
+}
+
 static const char *const bpf_class_string[] = {
 	[BPF_LD]    = "ld",
 	[BPF_LDX]   = "ldx",
@@ -305,6 +411,735 @@ static void print_bpf_insn(struct bpf_insn *insn)
 	}
 }
 
+static int pop_stack(struct verifier_env *env, int *prev_insn_idx)
+{
+	struct verifier_stack_elem *elem;
+	int insn_idx;
+
+	if (env->head == NULL)
+		return -1;
+
+	memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state));
+	insn_idx = env->head->insn_idx;
+	if (prev_insn_idx)
+		*prev_insn_idx = env->head->prev_insn_idx;
+	elem = env->head->next;
+	kfree(env->head);
+	env->head = elem;
+	env->stack_size--;
+	return insn_idx;
+}
+
+static struct verifier_state *push_stack(struct verifier_env *env, int insn_idx,
+					 int prev_insn_idx)
+{
+	struct verifier_stack_elem *elem;
+
+	elem = kmalloc(sizeof(struct verifier_stack_elem), GFP_KERNEL);
+	if (!elem)
+		goto err;
+
+	memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state));
+	elem->insn_idx = insn_idx;
+	elem->prev_insn_idx = prev_insn_idx;
+	elem->next = env->head;
+	env->head = elem;
+	env->stack_size++;
+	if (env->stack_size > 1024) {
+		verbose("BPF program is too complex\n");
+		goto err;
+	}
+	return &elem->st;
+err:
+	/* pop all elements and return */
+	while (pop_stack(env, NULL) >= 0);
+	return NULL;
+}
+
+#define CALLER_SAVED_REGS 6
+static const int caller_saved[CALLER_SAVED_REGS] = {
+	BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
+};
+
+static void init_reg_state(struct reg_state *regs)
+{
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++) {
+		regs[i].type = NOT_INIT;
+		regs[i].imm = 0;
+		regs[i].map_ptr = NULL;
+	}
+
+	/* frame pointer */
+	regs[BPF_REG_FP].type = FRAME_PTR;
+
+	/* 1st arg to a function */
+	regs[BPF_REG_1].type = PTR_TO_CTX;
+}
+
+static void mark_reg_unknown_value(struct reg_state *regs, u32 regno)
+{
+	BUG_ON(regno >= MAX_BPF_REG);
+	regs[regno].type = UNKNOWN_VALUE;
+	regs[regno].imm = 0;
+	regs[regno].map_ptr = NULL;
+}
+
+enum reg_arg_type {
+	SRC_OP,		/* register is used as source operand */
+	DST_OP,		/* register is used as destination operand */
+	DST_OP_NO_MARK	/* same as above, check only, don't mark */
+};
+
+static int check_reg_arg(struct reg_state *regs, u32 regno,
+			 enum reg_arg_type t)
+{
+	if (regno >= MAX_BPF_REG) {
+		verbose("R%d is invalid\n", regno);
+		return -EINVAL;
+	}
+
+	if (t == SRC_OP) {
+		/* check whether register used as source operand can be read */
+		if (regs[regno].type == NOT_INIT) {
+			verbose("R%d !read_ok\n", regno);
+			return -EACCES;
+		}
+	} else {
+		/* check whether register used as dest operand can be written to */
+		if (regno == BPF_REG_FP) {
+			verbose("frame pointer is read only\n");
+			return -EACCES;
+		}
+		if (t == DST_OP)
+			mark_reg_unknown_value(regs, regno);
+	}
+	return 0;
+}
+
+static int bpf_size_to_bytes(int bpf_size)
+{
+	if (bpf_size == BPF_W)
+		return 4;
+	else if (bpf_size == BPF_H)
+		return 2;
+	else if (bpf_size == BPF_B)
+		return 1;
+	else if (bpf_size == BPF_DW)
+		return 8;
+	else
+		return -EINVAL;
+}
+
+/* check_stack_read/write functions track spill/fill of registers,
+ * stack boundary and alignment are checked in check_mem_access()
+ */
+static int check_stack_write(struct verifier_state *state, int off, int size,
+			     int value_regno)
+{
+	struct bpf_stack_slot *slot;
+	int i;
+
+	if (value_regno >= 0 &&
+	    (state->regs[value_regno].type == PTR_TO_MAP_VALUE ||
+	     state->regs[value_regno].type == PTR_TO_STACK ||
+	     state->regs[value_regno].type == PTR_TO_CTX)) {
+
+		/* register containing pointer is being spilled into stack */
+		if (size != 8) {
+			verbose("invalid size of register spill\n");
+			return -EACCES;
+		}
+
+		slot = &state->stack[MAX_BPF_STACK + off];
+		slot->stype = STACK_SPILL;
+		/* save register state */
+		slot->reg_st = state->regs[value_regno];
+		for (i = 1; i < 8; i++) {
+			slot = &state->stack[MAX_BPF_STACK + off + i];
+			slot->stype = STACK_SPILL_PART;
+			slot->reg_st.type = UNKNOWN_VALUE;
+			slot->reg_st.map_ptr = NULL;
+		}
+	} else {
+
+		/* regular write of data into stack */
+		for (i = 0; i < size; i++) {
+			slot = &state->stack[MAX_BPF_STACK + off + i];
+			slot->stype = STACK_MISC;
+			slot->reg_st.type = UNKNOWN_VALUE;
+			slot->reg_st.map_ptr = NULL;
+		}
+	}
+	return 0;
+}
+
+static int check_stack_read(struct verifier_state *state, int off, int size,
+			    int value_regno)
+{
+	int i;
+	struct bpf_stack_slot *slot;
+
+	slot = &state->stack[MAX_BPF_STACK + off];
+
+	if (slot->stype == STACK_SPILL) {
+		if (size != 8) {
+			verbose("invalid size of register spill\n");
+			return -EACCES;
+		}
+		for (i = 1; i < 8; i++) {
+			if (state->stack[MAX_BPF_STACK + off + i].stype !=
+			    STACK_SPILL_PART) {
+				verbose("corrupted spill memory\n");
+				return -EACCES;
+			}
+		}
+
+		if (value_regno >= 0)
+			/* restore register state from stack */
+			state->regs[value_regno] = slot->reg_st;
+		return 0;
+	} else {
+		for (i = 0; i < size; i++) {
+			if (state->stack[MAX_BPF_STACK + off + i].stype !=
+			    STACK_MISC) {
+				verbose("invalid read from stack off %d+%d size %d\n",
+					off, i, size);
+				return -EACCES;
+			}
+		}
+		if (value_regno >= 0)
+			/* have read misc data from the stack */
+			mark_reg_unknown_value(state->regs, value_regno);
+		return 0;
+	}
+}
+
+/* check read/write into map element returned by bpf_map_lookup_elem() */
+static int check_map_access(struct verifier_env *env, u32 regno, int off,
+			    int size)
+{
+	struct bpf_map *map = env->cur_state.regs[regno].map_ptr;
+
+	if (off < 0 || off + size > map->value_size) {
+		verbose("invalid access to map value, value_size=%d off=%d size=%d\n",
+			map->value_size, off, size);
+		return -EACCES;
+	}
+	return 0;
+}
+
+/* check access to 'struct bpf_context' fields */
+static int check_ctx_access(struct verifier_env *env, int off, int size,
+			    enum bpf_access_type t)
+{
+	if (env->prog->aux->ops->is_valid_access &&
+	    env->prog->aux->ops->is_valid_access(off, size, t))
+		return 0;
+
+	verbose("invalid bpf_context access off=%d size=%d\n", off, size);
+	return -EACCES;
+}
+
+/* check whether memory at (regno + off) is accessible for t = (read | write)
+ * if t==write, value_regno is a register which value is stored into memory
+ * if t==read, value_regno is a register which will receive the value from memory
+ * if t==write && value_regno==-1, some unknown value is stored into memory
+ * if t==read && value_regno==-1, don't care what we read from memory
+ */
+static int check_mem_access(struct verifier_env *env, u32 regno, int off,
+			    int bpf_size, enum bpf_access_type t,
+			    int value_regno)
+{
+	struct verifier_state *state = &env->cur_state;
+	int size, err = 0;
+
+	size = bpf_size_to_bytes(bpf_size);
+	if (size < 0)
+		return size;
+
+	if (off % size != 0) {
+		verbose("misaligned access off %d size %d\n", off, size);
+		return -EACCES;
+	}
+
+	if (state->regs[regno].type == PTR_TO_MAP_VALUE) {
+		err = check_map_access(env, regno, off, size);
+		if (!err && t == BPF_READ && value_regno >= 0)
+			mark_reg_unknown_value(state->regs, value_regno);
+
+	} else if (state->regs[regno].type == PTR_TO_CTX) {
+		err = check_ctx_access(env, off, size, t);
+		if (!err && t == BPF_READ && value_regno >= 0)
+			mark_reg_unknown_value(state->regs, value_regno);
+
+	} else if (state->regs[regno].type == FRAME_PTR) {
+		if (off >= 0 || off < -MAX_BPF_STACK) {
+			verbose("invalid stack off=%d size=%d\n", off, size);
+			return -EACCES;
+		}
+		if (t == BPF_WRITE)
+			err = check_stack_write(state, off, size, value_regno);
+		else
+			err = check_stack_read(state, off, size, value_regno);
+	} else {
+		verbose("R%d invalid mem access '%s'\n",
+			regno, reg_type_str[state->regs[regno].type]);
+		return -EACCES;
+	}
+	return err;
+}
+
+static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
+{
+	struct reg_state *regs = env->cur_state.regs;
+	int err;
+
+	if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
+	    insn->imm != 0) {
+		verbose("BPF_XADD uses reserved fields\n");
+		return -EINVAL;
+	}
+
+	/* check src1 operand */
+	err = check_reg_arg(regs, insn->src_reg, SRC_OP);
+	if (err)
+		return err;
+
+	/* check src2 operand */
+	err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
+	if (err)
+		return err;
+
+	/* check whether atomic_add can read the memory */
+	err = check_mem_access(env, insn->dst_reg, insn->off,
+			       BPF_SIZE(insn->code), BPF_READ, -1);
+	if (err)
+		return err;
+
+	/* check whether atomic_add can write into the same memory */
+	return check_mem_access(env, insn->dst_reg, insn->off,
+				BPF_SIZE(insn->code), BPF_WRITE, -1);
+}
+
+/* when register 'regno' is passed into function that will read 'access_size'
+ * bytes from that pointer, make sure that it's within stack boundary
+ * and all elements of stack are initialized
+ */
+static int check_stack_boundary(struct verifier_env *env,
+				int regno, int access_size)
+{
+	struct verifier_state *state = &env->cur_state;
+	struct reg_state *regs = state->regs;
+	int off, i;
+
+	if (regs[regno].type != PTR_TO_STACK)
+		return -EACCES;
+
+	off = regs[regno].imm;
+	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
+	    access_size <= 0) {
+		verbose("invalid stack type R%d off=%d access_size=%d\n",
+			regno, off, access_size);
+		return -EACCES;
+	}
+
+	for (i = 0; i < access_size; i++) {
+		if (state->stack[MAX_BPF_STACK + off + i].stype != STACK_MISC) {
+			verbose("invalid indirect read from stack off %d+%d size %d\n",
+				off, i, access_size);
+			return -EACCES;
+		}
+	}
+	return 0;
+}
+
+static int check_func_arg(struct verifier_env *env, u32 regno,
+			  enum bpf_arg_type arg_type, struct bpf_map **mapp)
+{
+	struct reg_state *reg = env->cur_state.regs + regno;
+	enum bpf_reg_type expected_type;
+	int err = 0;
+
+	if (arg_type == ARG_ANYTHING)
+		return 0;
+
+	if (reg->type == NOT_INIT) {
+		verbose("R%d !read_ok\n", regno);
+		return -EACCES;
+	}
+
+	if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY ||
+	    arg_type == ARG_PTR_TO_MAP_VALUE) {
+		expected_type = PTR_TO_STACK;
+	} else if (arg_type == ARG_CONST_STACK_SIZE) {
+		expected_type = CONST_IMM;
+	} else if (arg_type == ARG_CONST_MAP_PTR) {
+		expected_type = CONST_PTR_TO_MAP;
+	} else {
+		verbose("unsupported arg_type %d\n", arg_type);
+		return -EFAULT;
+	}
+
+	if (reg->type != expected_type) {
+		verbose("R%d type=%s expected=%s\n", regno,
+			reg_type_str[reg->type], reg_type_str[expected_type]);
+		return -EACCES;
+	}
+
+	if (arg_type == ARG_CONST_MAP_PTR) {
+		/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
+		*mapp = reg->map_ptr;
+
+	} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
+		/* bpf_map_xxx(..., map_ptr, ..., key) call:
+		 * check that [key, key + map->key_size) are within
+		 * stack limits and initialized
+		 */
+		if (!*mapp) {
+			/* in function declaration map_ptr must come before
+			 * map_key, so that it's verified and known before
+			 * we have to check map_key here. Otherwise it means
+			 * that kernel subsystem misconfigured verifier
+			 */
+			verbose("invalid map_ptr to access map->key\n");
+			return -EACCES;
+		}
+		err = check_stack_boundary(env, regno, (*mapp)->key_size);
+
+	} else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
+		/* bpf_map_xxx(..., map_ptr, ..., value) call:
+		 * check [value, value + map->value_size) validity
+		 */
+		if (!*mapp) {
+			/* kernel subsystem misconfigured verifier */
+			verbose("invalid map_ptr to access map->value\n");
+			return -EACCES;
+		}
+		err = check_stack_boundary(env, regno, (*mapp)->value_size);
+
+	} else if (arg_type == ARG_CONST_STACK_SIZE) {
+		/* bpf_xxx(..., buf, len) call will access 'len' bytes
+		 * from stack pointer 'buf'. Check it
+		 * note: regno == len, regno - 1 == buf
+		 */
+		if (regno == 0) {
+			/* kernel subsystem misconfigured verifier */
+			verbose("ARG_CONST_STACK_SIZE cannot be first argument\n");
+			return -EACCES;
+		}
+		err = check_stack_boundary(env, regno - 1, reg->imm);
+	}
+
+	return err;
+}
+
+static int check_call(struct verifier_env *env, int func_id)
+{
+	struct verifier_state *state = &env->cur_state;
+	const struct bpf_func_proto *fn = NULL;
+	struct reg_state *regs = state->regs;
+	struct bpf_map *map = NULL;
+	struct reg_state *reg;
+	int i, err;
+
+	/* find function prototype */
+	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
+		verbose("invalid func %d\n", func_id);
+		return -EINVAL;
+	}
+
+	if (env->prog->aux->ops->get_func_proto)
+		fn = env->prog->aux->ops->get_func_proto(func_id);
+
+	if (!fn) {
+		verbose("unknown func %d\n", func_id);
+		return -EINVAL;
+	}
+
+	/* eBPF programs must be GPL compatible to use GPL-ed functions */
+	if (!env->prog->aux->is_gpl_compatible && fn->gpl_only) {
+		verbose("cannot call GPL only function from proprietary program\n");
+		return -EINVAL;
+	}
+
+	/* check args */
+	err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &map);
+	if (err)
+		return err;
+	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &map);
+	if (err)
+		return err;
+	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &map);
+	if (err)
+		return err;
+	err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &map);
+	if (err)
+		return err;
+	err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &map);
+	if (err)
+		return err;
+
+	/* reset caller saved regs */
+	for (i = 0; i < CALLER_SAVED_REGS; i++) {
+		reg = regs + caller_saved[i];
+		reg->type = NOT_INIT;
+		reg->imm = 0;
+	}
+
+	/* update return register */
+	if (fn->ret_type == RET_INTEGER) {
+		regs[BPF_REG_0].type = UNKNOWN_VALUE;
+	} else if (fn->ret_type == RET_VOID) {
+		regs[BPF_REG_0].type = NOT_INIT;
+	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
+		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+		/* remember map_ptr, so that check_map_access()
+		 * can check 'value_size' boundary of memory access
+		 * to map element returned from bpf_map_lookup_elem()
+		 */
+		if (map == NULL) {
+			verbose("kernel subsystem misconfigured verifier\n");
+			return -EINVAL;
+		}
+		regs[BPF_REG_0].map_ptr = map;
+	} else {
+		verbose("unknown return type %d of func %d\n",
+			fn->ret_type, func_id);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* check validity of 32-bit and 64-bit arithmetic operations */
+static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn)
+{
+	u8 opcode = BPF_OP(insn->code);
+	int err;
+
+	if (opcode == BPF_END || opcode == BPF_NEG) {
+		if (opcode == BPF_NEG) {
+			if (BPF_SRC(insn->code) != 0 ||
+			    insn->src_reg != BPF_REG_0 ||
+			    insn->off != 0 || insn->imm != 0) {
+				verbose("BPF_NEG uses reserved fields\n");
+				return -EINVAL;
+			}
+		} else {
+			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
+			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) {
+				verbose("BPF_END uses reserved fields\n");
+				return -EINVAL;
+			}
+		}
+
+		/* check src operand */
+		err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
+		if (err)
+			return err;
+
+		/* check dest operand */
+		err = check_reg_arg(regs, insn->dst_reg, DST_OP);
+		if (err)
+			return err;
+
+	} else if (opcode == BPF_MOV) {
+
+		if (BPF_SRC(insn->code) == BPF_X) {
+			if (insn->imm != 0 || insn->off != 0) {
+				verbose("BPF_MOV uses reserved fields\n");
+				return -EINVAL;
+			}
+
+			/* check src operand */
+			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
+			if (err)
+				return err;
+		} else {
+			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
+				verbose("BPF_MOV uses reserved fields\n");
+				return -EINVAL;
+			}
+		}
+
+		/* check dest operand */
+		err = check_reg_arg(regs, insn->dst_reg, DST_OP);
+		if (err)
+			return err;
+
+		if (BPF_SRC(insn->code) == BPF_X) {
+			if (BPF_CLASS(insn->code) == BPF_ALU64) {
+				/* case: R1 = R2
+				 * copy register state to dest reg
+				 */
+				regs[insn->dst_reg] = regs[insn->src_reg];
+			} else {
+				regs[insn->dst_reg].type = UNKNOWN_VALUE;
+				regs[insn->dst_reg].map_ptr = NULL;
+			}
+		} else {
+			/* case: R = imm
+			 * remember the value we stored into this reg
+			 */
+			regs[insn->dst_reg].type = CONST_IMM;
+			regs[insn->dst_reg].imm = insn->imm;
+		}
+
+	} else if (opcode > BPF_END) {
+		verbose("invalid BPF_ALU opcode %x\n", opcode);
+		return -EINVAL;
+
+	} else {	/* all other ALU ops: and, sub, xor, add, ... */
+
+		bool stack_relative = false;
+
+		if (BPF_SRC(insn->code) == BPF_X) {
+			if (insn->imm != 0 || insn->off != 0) {
+				verbose("BPF_ALU uses reserved fields\n");
+				return -EINVAL;
+			}
+			/* check src1 operand */
+			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
+			if (err)
+				return err;
+		} else {
+			if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
+				verbose("BPF_ALU uses reserved fields\n");
+				return -EINVAL;
+			}
+		}
+
+		/* check src2 operand */
+		err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
+		if (err)
+			return err;
+
+		if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
+		    BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
+			verbose("div by zero\n");
+			return -EINVAL;
+		}
+
+		/* pattern match 'bpf_add Rx, imm' instruction */
+		if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 &&
+		    regs[insn->dst_reg].type == FRAME_PTR &&
+		    BPF_SRC(insn->code) == BPF_K)
+			stack_relative = true;
+
+		/* check dest operand */
+		err = check_reg_arg(regs, insn->dst_reg, DST_OP);
+		if (err)
+			return err;
+
+		if (stack_relative) {
+			regs[insn->dst_reg].type = PTR_TO_STACK;
+			regs[insn->dst_reg].imm = insn->imm;
+		}
+	}
+
+	return 0;
+}
+
+static int check_cond_jmp_op(struct verifier_env *env,
+			     struct bpf_insn *insn, int *insn_idx)
+{
+	struct reg_state *regs = env->cur_state.regs;
+	struct verifier_state *other_branch;
+	u8 opcode = BPF_OP(insn->code);
+	int err;
+
+	if (opcode > BPF_EXIT) {
+		verbose("invalid BPF_JMP opcode %x\n", opcode);
+		return -EINVAL;
+	}
+
+	if (BPF_SRC(insn->code) == BPF_X) {
+		if (insn->imm != 0) {
+			verbose("BPF_JMP uses reserved fields\n");
+			return -EINVAL;
+		}
+
+		/* check src1 operand */
+		err = check_reg_arg(regs, insn->src_reg, SRC_OP);
+		if (err)
+			return err;
+	} else {
+		if (insn->src_reg != BPF_REG_0) {
+			verbose("BPF_JMP uses reserved fields\n");
+			return -EINVAL;
+		}
+	}
+
+	/* check src2 operand */
+	err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
+	if (err)
+		return err;
+
+	/* detect if R == 0 where R was initialized to zero earlier */
+	if (BPF_SRC(insn->code) == BPF_K &&
+	    (opcode == BPF_JEQ || opcode == BPF_JNE) &&
+	    regs[insn->dst_reg].type == CONST_IMM &&
+	    regs[insn->dst_reg].imm == insn->imm) {
+		if (opcode == BPF_JEQ) {
+			/* if (imm == imm) goto pc+off;
+			 * only follow the goto, ignore fall-through
+			 */
+			*insn_idx += insn->off;
+			return 0;
+		} else {
+			/* if (imm != imm) goto pc+off;
+			 * only follow fall-through branch, since
+			 * that's where the program will go
+			 */
+			return 0;
+		}
+	}
+
+	other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx);
+	if (!other_branch)
+		return -EFAULT;
+
+	/* detect if R == 0 where R is returned value from bpf_map_lookup_elem() */
+	if (BPF_SRC(insn->code) == BPF_K &&
+	    insn->imm == 0 && (opcode == BPF_JEQ ||
+			       opcode == BPF_JNE) &&
+	    regs[insn->dst_reg].type == PTR_TO_MAP_VALUE_OR_NULL) {
+		if (opcode == BPF_JEQ) {
+			/* next fallthrough insn can access memory via
+			 * this register
+			 */
+			regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
+			/* branch targer cannot access it, since reg == 0 */
+			other_branch->regs[insn->dst_reg].type = CONST_IMM;
+			other_branch->regs[insn->dst_reg].imm = 0;
+		} else {
+			other_branch->regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
+			regs[insn->dst_reg].type = CONST_IMM;
+			regs[insn->dst_reg].imm = 0;
+		}
+	} else if (BPF_SRC(insn->code) == BPF_K &&
+		   (opcode == BPF_JEQ || opcode == BPF_JNE)) {
+
+		if (opcode == BPF_JEQ) {
+			/* detect if (R == imm) goto
+			 * and in the target state recognize that R = imm
+			 */
+			other_branch->regs[insn->dst_reg].type = CONST_IMM;
+			other_branch->regs[insn->dst_reg].imm = insn->imm;
+		} else {
+			/* detect if (R != imm) goto
+			 * and in the fall-through state recognize that R = imm
+			 */
+			regs[insn->dst_reg].type = CONST_IMM;
+			regs[insn->dst_reg].imm = insn->imm;
+		}
+	}
+	if (log_level)
+		print_verifier_state(env);
+	return 0;
+}
+
 /* return the map pointer stored inside BPF_LD_IMM64 instruction */
 static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
 {
@@ -313,6 +1148,37 @@ static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
 	return (struct bpf_map *) (unsigned long) imm64;
 }
 
+/* verify BPF_LD_IMM64 instruction */
+static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn)
+{
+	struct reg_state *regs = env->cur_state.regs;
+	int err;
+
+	if (BPF_SIZE(insn->code) != BPF_DW) {
+		verbose("invalid BPF_LD_IMM insn\n");
+		return -EINVAL;
+	}
+	if (insn->off != 0) {
+		verbose("BPF_LD_IMM64 uses reserved fields\n");
+		return -EINVAL;
+	}
+
+	err = check_reg_arg(regs, insn->dst_reg, DST_OP);
+	if (err)
+		return err;
+
+	if (insn->src_reg == 0)
+		/* generic move 64-bit immediate into a register */
+		return 0;
+
+	/* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
+	BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);
+
+	regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
+	regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
+	return 0;
+}
+
 /* non-recursive DFS pseudo code
  * 1  procedure DFS-iterative(G,v):
  * 2      label v as discovered
@@ -498,6 +1364,212 @@ err_free:
 	return ret;
 }
 
+static int do_check(struct verifier_env *env)
+{
+	struct verifier_state *state = &env->cur_state;
+	struct bpf_insn *insns = env->prog->insnsi;
+	struct reg_state *regs = state->regs;
+	int insn_cnt = env->prog->len;
+	int insn_idx, prev_insn_idx = 0;
+	int insn_processed = 0;
+	bool do_print_state = false;
+
+	init_reg_state(regs);
+	insn_idx = 0;
+	for (;;) {
+		struct bpf_insn *insn;
+		u8 class;
+		int err;
+
+		if (insn_idx >= insn_cnt) {
+			verbose("invalid insn idx %d insn_cnt %d\n",
+				insn_idx, insn_cnt);
+			return -EFAULT;
+		}
+
+		insn = &insns[insn_idx];
+		class = BPF_CLASS(insn->code);
+
+		if (++insn_processed > 32768) {
+			verbose("BPF program is too large. Proccessed %d insn\n",
+				insn_processed);
+			return -E2BIG;
+		}
+
+		if (log_level && do_print_state) {
+			verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
+			print_verifier_state(env);
+			do_print_state = false;
+		}
+
+		if (log_level) {
+			verbose("%d: ", insn_idx);
+			print_bpf_insn(insn);
+		}
+
+		if (class == BPF_ALU || class == BPF_ALU64) {
+			err = check_alu_op(regs, insn);
+			if (err)
+				return err;
+
+		} else if (class == BPF_LDX) {
+			if (BPF_MODE(insn->code) != BPF_MEM ||
+			    insn->imm != 0) {
+				verbose("BPF_LDX uses reserved fields\n");
+				return -EINVAL;
+			}
+			/* check src operand */
+			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
+			if (err)
+				return err;
+
+			err = check_reg_arg(regs, insn->dst_reg, DST_OP_NO_MARK);
+			if (err)
+				return err;
+
+			/* check that memory (src_reg + off) is readable,
+			 * the state of dst_reg will be updated by this func
+			 */
+			err = check_mem_access(env, insn->src_reg, insn->off,
+					       BPF_SIZE(insn->code), BPF_READ,
+					       insn->dst_reg);
+			if (err)
+				return err;
+
+		} else if (class == BPF_STX) {
+			if (BPF_MODE(insn->code) == BPF_XADD) {
+				err = check_xadd(env, insn);
+				if (err)
+					return err;
+				insn_idx++;
+				continue;
+			}
+
+			if (BPF_MODE(insn->code) != BPF_MEM ||
+			    insn->imm != 0) {
+				verbose("BPF_STX uses reserved fields\n");
+				return -EINVAL;
+			}
+			/* check src1 operand */
+			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
+			if (err)
+				return err;
+			/* check src2 operand */
+			err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
+			if (err)
+				return err;
+
+			/* check that memory (dst_reg + off) is writeable */
+			err = check_mem_access(env, insn->dst_reg, insn->off,
+					       BPF_SIZE(insn->code), BPF_WRITE,
+					       insn->src_reg);
+			if (err)
+				return err;
+
+		} else if (class == BPF_ST) {
+			if (BPF_MODE(insn->code) != BPF_MEM ||
+			    insn->src_reg != BPF_REG_0) {
+				verbose("BPF_ST uses reserved fields\n");
+				return -EINVAL;
+			}
+			/* check src operand */
+			err = check_reg_arg(regs, insn->dst_reg, SRC_OP);
+			if (err)
+				return err;
+
+			/* check that memory (dst_reg + off) is writeable */
+			err = check_mem_access(env, insn->dst_reg, insn->off,
+					       BPF_SIZE(insn->code), BPF_WRITE,
+					       -1);
+			if (err)
+				return err;
+
+		} else if (class == BPF_JMP) {
+			u8 opcode = BPF_OP(insn->code);
+
+			if (opcode == BPF_CALL) {
+				if (BPF_SRC(insn->code) != BPF_K ||
+				    insn->off != 0 ||
+				    insn->src_reg != BPF_REG_0 ||
+				    insn->dst_reg != BPF_REG_0) {
+					verbose("BPF_CALL uses reserved fields\n");
+					return -EINVAL;
+				}
+
+				err = check_call(env, insn->imm);
+				if (err)
+					return err;
+
+			} else if (opcode == BPF_JA) {
+				if (BPF_SRC(insn->code) != BPF_K ||
+				    insn->imm != 0 ||
+				    insn->src_reg != BPF_REG_0 ||
+				    insn->dst_reg != BPF_REG_0) {
+					verbose("BPF_JA uses reserved fields\n");
+					return -EINVAL;
+				}
+
+				insn_idx += insn->off + 1;
+				continue;
+
+			} else if (opcode == BPF_EXIT) {
+				if (BPF_SRC(insn->code) != BPF_K ||
+				    insn->imm != 0 ||
+				    insn->src_reg != BPF_REG_0 ||
+				    insn->dst_reg != BPF_REG_0) {
+					verbose("BPF_EXIT uses reserved fields\n");
+					return -EINVAL;
+				}
+
+				/* eBPF calling convetion is such that R0 is used
+				 * to return the value from eBPF program.
+				 * Make sure that it's readable at this time
+				 * of bpf_exit, which means that program wrote
+				 * something into it earlier
+				 */
+				err = check_reg_arg(regs, BPF_REG_0, SRC_OP);
+				if (err)
+					return err;
+
+				insn_idx = pop_stack(env, &prev_insn_idx);
+				if (insn_idx < 0) {
+					break;
+				} else {
+					do_print_state = true;
+					continue;
+				}
+			} else {
+				err = check_cond_jmp_op(env, insn, &insn_idx);
+				if (err)
+					return err;
+			}
+		} else if (class == BPF_LD) {
+			u8 mode = BPF_MODE(insn->code);
+
+			if (mode == BPF_ABS || mode == BPF_IND) {
+				verbose("LD_ABS is not supported yet\n");
+				return -EINVAL;
+			} else if (mode == BPF_IMM) {
+				err = check_ld_imm(env, insn);
+				if (err)
+					return err;
+
+				insn_idx++;
+			} else {
+				verbose("invalid BPF_LD mode\n");
+				return -EINVAL;
+			}
+		} else {
+			verbose("unknown insn class %d\n", class);
+			return -EINVAL;
+		}
+
+		insn_idx++;
+	}
+
+	return 0;
+}
+
 /* look for pseudo eBPF instructions that access map FDs and
  * replace them with actual map pointers
  */
@@ -651,9 +1723,10 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr)
 	if (ret < 0)
 		goto skip_full_check;
 
-	/* ret = do_check(env); */
+	ret = do_check(env);
 
 skip_full_check:
+	while (pop_stack(env, NULL) >= 0);
 
 	if (log_level && log_len >= log_size - 1) {
 		BUG_ON(log_len >= log_size);
-- 
cgit v1.2.3


From 6ea754eb761d9e7a8ac6fa462b05f9e4cf04fb6c Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 22 Sep 2014 11:10:50 -0700
Subject: net: Change netdev_<level> logging functions to return void

No caller or macro uses the return value so make all
the functions return void.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 19 +++++++++----------
 net/core/dev.c            | 44 +++++++++++++++++---------------------------
 2 files changed, 26 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9f5d293a0281..9b7fbacb6296 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3612,22 +3612,22 @@ static inline const char *netdev_reg_state(const struct net_device *dev)
 }
 
 __printf(3, 4)
-int netdev_printk(const char *level, const struct net_device *dev,
-		  const char *format, ...);
+void netdev_printk(const char *level, const struct net_device *dev,
+		   const char *format, ...);
 __printf(2, 3)
-int netdev_emerg(const struct net_device *dev, const char *format, ...);
+void netdev_emerg(const struct net_device *dev, const char *format, ...);
 __printf(2, 3)
-int netdev_alert(const struct net_device *dev, const char *format, ...);
+void netdev_alert(const struct net_device *dev, const char *format, ...);
 __printf(2, 3)
-int netdev_crit(const struct net_device *dev, const char *format, ...);
+void netdev_crit(const struct net_device *dev, const char *format, ...);
 __printf(2, 3)
-int netdev_err(const struct net_device *dev, const char *format, ...);
+void netdev_err(const struct net_device *dev, const char *format, ...);
 __printf(2, 3)
-int netdev_warn(const struct net_device *dev, const char *format, ...);
+void netdev_warn(const struct net_device *dev, const char *format, ...);
 __printf(2, 3)
-int netdev_notice(const struct net_device *dev, const char *format, ...);
+void netdev_notice(const struct net_device *dev, const char *format, ...);
 __printf(2, 3)
-int netdev_info(const struct net_device *dev, const char *format, ...);
+void netdev_info(const struct net_device *dev, const char *format, ...);
 
 #define MODULE_ALIAS_NETDEV(device) \
 	MODULE_ALIAS("netdev-" device)
@@ -3645,7 +3645,6 @@ do {								\
 ({								\
 	if (0)							\
 		netdev_printk(KERN_DEBUG, __dev, format, ##args); \
-	0;							\
 })
 #endif
 
diff --git a/net/core/dev.c b/net/core/dev.c
index e2ced01c01e4..e55c546717d4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7066,53 +7066,45 @@ const char *netdev_drivername(const struct net_device *dev)
 	return empty;
 }
 
-static int __netdev_printk(const char *level, const struct net_device *dev,
-			   struct va_format *vaf)
+static void __netdev_printk(const char *level, const struct net_device *dev,
+			    struct va_format *vaf)
 {
-	int r;
-
 	if (dev && dev->dev.parent) {
-		r = dev_printk_emit(level[1] - '0',
-				    dev->dev.parent,
-				    "%s %s %s%s: %pV",
-				    dev_driver_string(dev->dev.parent),
-				    dev_name(dev->dev.parent),
-				    netdev_name(dev), netdev_reg_state(dev),
-				    vaf);
+		dev_printk_emit(level[1] - '0',
+				dev->dev.parent,
+				"%s %s %s%s: %pV",
+				dev_driver_string(dev->dev.parent),
+				dev_name(dev->dev.parent),
+				netdev_name(dev), netdev_reg_state(dev),
+				vaf);
 	} else if (dev) {
-		r = printk("%s%s%s: %pV", level, netdev_name(dev),
-			   netdev_reg_state(dev), vaf);
+		printk("%s%s%s: %pV",
+		       level, netdev_name(dev), netdev_reg_state(dev), vaf);
 	} else {
-		r = printk("%s(NULL net_device): %pV", level, vaf);
+		printk("%s(NULL net_device): %pV", level, vaf);
 	}
-
-	return r;
 }
 
-int netdev_printk(const char *level, const struct net_device *dev,
-		  const char *format, ...)
+void netdev_printk(const char *level, const struct net_device *dev,
+		   const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, format);
 
 	vaf.fmt = format;
 	vaf.va = &args;
 
-	r = __netdev_printk(level, dev, &vaf);
+	__netdev_printk(level, dev, &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(netdev_printk);
 
 #define define_netdev_printk_level(func, level)			\
-int func(const struct net_device *dev, const char *fmt, ...)	\
+void func(const struct net_device *dev, const char *fmt, ...)	\
 {								\
-	int r;							\
 	struct va_format vaf;					\
 	va_list args;						\
 								\
@@ -7121,11 +7113,9 @@ int func(const struct net_device *dev, const char *fmt, ...)	\
 	vaf.fmt = fmt;						\
 	vaf.va = &args;						\
 								\
-	r = __netdev_printk(level, dev, &vaf);			\
+	__netdev_printk(level, dev, &vaf);			\
 								\
 	va_end(args);						\
-								\
-	return r;						\
 }								\
 EXPORT_SYMBOL(func);
 
-- 
cgit v1.2.3


From f4a775d14489a801a5b8b0540e23ab82e2703091 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 22 Sep 2014 16:29:32 -0700
Subject: net: introduce __skb_header_release()

While profiling TCP stack, I noticed one useless atomic operation
in tcp_sendmsg(), caused by skb_header_release().

It turns out all current skb_header_release() users have a fresh skb,
that no other user can see, so we can avoid one atomic operation.

Introduce __skb_header_release() to clearly document this.

This gave me a 1.5 % improvement on TCP_RR workload.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 15 +++++++++++++++
 net/core/skbuff.c      |  4 ++--
 net/ipv4/tcp.c         |  4 ++--
 net/ipv4/tcp_output.c  | 10 +++++-----
 4 files changed, 24 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f1bfa3781c75..8eaa62400fca 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1083,6 +1083,7 @@ static inline int skb_header_cloned(const struct sk_buff *skb)
  *	Drop a reference to the header part of the buffer.  This is done
  *	by acquiring a payload reference.  You must not read from the header
  *	part of skb->data after this.
+ *	Note : Check if you can use __skb_header_release() instead.
  */
 static inline void skb_header_release(struct sk_buff *skb)
 {
@@ -1091,6 +1092,20 @@ static inline void skb_header_release(struct sk_buff *skb)
 	atomic_add(1 << SKB_DATAREF_SHIFT, &skb_shinfo(skb)->dataref);
 }
 
+/**
+ *	__skb_header_release - release reference to header
+ *	@skb: buffer to operate on
+ *
+ *	Variant of skb_header_release() assuming skb is private to caller.
+ *	We can avoid one atomic operation.
+ */
+static inline void __skb_header_release(struct sk_buff *skb)
+{
+	skb->nohdr = 1;
+	atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT));
+}
+
+
 /**
  *	skb_shared - is the buffer shared
  *	@skb: buffer to check
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 06a8feb10099..512dc7dcbc32 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3179,7 +3179,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	skb_shinfo(nskb)->frag_list = p;
 	skb_shinfo(nskb)->gso_size = pinfo->gso_size;
 	pinfo->gso_size = 0;
-	skb_header_release(p);
+	__skb_header_release(p);
 	NAPI_GRO_CB(nskb)->last = p;
 
 	nskb->data_len += p->len;
@@ -3211,7 +3211,7 @@ merge:
 	else
 		NAPI_GRO_CB(p)->last->next = skb;
 	NAPI_GRO_CB(p)->last = skb;
-	skb_header_release(skb);
+	__skb_header_release(skb);
 	lp = p;
 
 done:
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 070aeff1b131..553b01f52f71 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -609,7 +609,7 @@ static inline bool forced_push(const struct tcp_sock *tp)
 	return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
 }
 
-static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
+static void skb_entail(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
@@ -618,7 +618,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
 	tcb->seq     = tcb->end_seq = tp->write_seq;
 	tcb->tcp_flags = TCPHDR_ACK;
 	tcb->sacked  = 0;
-	skb_header_release(skb);
+	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8c61a7c0c889..f173b1c4f815 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -995,7 +995,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 
 	/* Advance write_seq and place onto the write_queue. */
 	tp->write_seq = TCP_SKB_CB(skb)->end_seq;
-	skb_header_release(skb);
+	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
@@ -1167,7 +1167,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	}
 
 	/* Link BUFF into the send queue. */
-	skb_header_release(buff);
+	__skb_header_release(buff);
 	tcp_insert_write_queue_after(skb, buff, sk);
 
 	return 0;
@@ -1671,7 +1671,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	tcp_set_skb_tso_segs(sk, buff, mss_now);
 
 	/* Link BUFF into the send queue. */
-	skb_header_release(buff);
+	__skb_header_release(buff);
 	tcp_insert_write_queue_after(skb, buff, sk);
 
 	return 0;
@@ -2772,7 +2772,7 @@ int tcp_send_synack(struct sock *sk)
 			if (nskb == NULL)
 				return -ENOMEM;
 			tcp_unlink_write_queue(skb, sk);
-			skb_header_release(nskb);
+			__skb_header_release(nskb);
 			__tcp_add_write_queue_head(sk, nskb);
 			sk_wmem_free_skb(sk, skb);
 			sk->sk_wmem_queued += nskb->truesize;
@@ -2947,7 +2947,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
 	tcb->end_seq += skb->len;
-	skb_header_release(skb);
+	__skb_header_release(skb);
 	__tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
-- 
cgit v1.2.3


From 4565af0d406bed44bc8756230eae8f7caa5e0334 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Tue, 23 Sep 2014 10:54:32 +0200
Subject: net: optimise csum_replace4()

csum_partial() is a generic function which is not optimised for small fixed
length calculations, and its use requires to store "from" and "to" values in
memory while we already have them available in registers. This also has impact,
especially on RISC processors. In the same spirit as the change done by
Eric Dumazet on csum_replace2(), this patch rewrites inet_proto_csum_replace4()
taking into account RFC1624.

I spotted during a NATted tcp transfert that csum_partial() is one of top 5
consuming functions (around 8%), and the second user of csum_partial() is
inet_proto_csum_replace4().

I have proposed the same modification to inet_proto_csum_replace4() in another
patch.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/checksum.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/checksum.h b/include/net/checksum.h
index 87cb1903640d..6465bae80a4f 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -122,9 +122,7 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum)
 
 static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
 {
-	__be32 diff[] = { ~from, to };
-
-	*sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum)));
+	*sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from), to));
 }
 
 /* Implements RFC 1624 (Incremental Internet Checksum)
-- 
cgit v1.2.3


From c873d14d30b838a516a94967242322d4b73e79e7 Mon Sep 17 00:00:00 2001
From: Jyri Sarha <jsarha@ti.com>
Date: Fri, 5 Sep 2014 15:21:34 +0300
Subject: clk: add gpio gated clock

The added gpio-gate-clock is a basic clock that can be enabled and
disabled trough a gpio output. The DT binding document for the clock
is also added. For EPROBE_DEFER handling the registering of the clock
has to be delayed until of_clk_get() call time.

Signed-off-by: Jyri Sarha <jsarha@ti.com>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 .../devicetree/bindings/clock/gpio-gate-clock.txt  |  21 +++
 drivers/clk/Makefile                               |   1 +
 drivers/clk/clk-gpio-gate.c                        | 204 +++++++++++++++++++++
 include/linux/clk-provider.h                       |  22 +++
 4 files changed, 248 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/gpio-gate-clock.txt
 create mode 100644 drivers/clk/clk-gpio-gate.c

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/gpio-gate-clock.txt b/Documentation/devicetree/bindings/clock/gpio-gate-clock.txt
new file mode 100644
index 000000000000..d3379ff9b84b
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/gpio-gate-clock.txt
@@ -0,0 +1,21 @@
+Binding for simple gpio gated clock.
+
+This binding uses the common clock binding[1].
+
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Required properties:
+- compatible : shall be "gpio-gate-clock".
+- #clock-cells : from common clock binding; shall be set to 0.
+- enable-gpios : GPIO reference for enabling and disabling the clock.
+
+Optional properties:
+- clocks: Maximum of one parent clock is supported.
+
+Example:
+	clock {
+		compatible = "gpio-gate-clock";
+		clocks = <&parentclk>;
+		#clock-cells = <0>;
+		enable-gpios = <&gpio 1 GPIO_ACTIVE_HIGH>;
+	};
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 27c542ba9e73..92a7f6c02394 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_COMMON_CLK)	+= clk-gate.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-mux.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-composite.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-fractional-divider.o
+obj-$(CONFIG_COMMON_CLK)	+= clk-gpio-gate.o
 ifeq ($(CONFIG_OF), y)
 obj-$(CONFIG_COMMON_CLK)	+= clk-conf.o
 endif
diff --git a/drivers/clk/clk-gpio-gate.c b/drivers/clk/clk-gpio-gate.c
new file mode 100644
index 000000000000..9dde88533684
--- /dev/null
+++ b/drivers/clk/clk-gpio-gate.c
@@ -0,0 +1,204 @@
+/*
+ * Copyright (C) 2013 - 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Author: Jyri Sarha <jsarha@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Gpio gated clock implementation
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/err.h>
+#include <linux/device.h>
+
+/**
+ * DOC: basic gpio gated clock which can be enabled and disabled
+ *      with gpio output
+ * Traits of this clock:
+ * prepare - clk_(un)prepare only ensures parent is (un)prepared
+ * enable - clk_enable and clk_disable are functional & control gpio
+ * rate - inherits rate from parent.  No clk_set_rate support
+ * parent - fixed parent.  No clk_set_parent support
+ */
+
+#define to_clk_gpio(_hw) container_of(_hw, struct clk_gpio, hw)
+
+static int clk_gpio_gate_enable(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	gpiod_set_value(clk->gpiod, 1);
+
+	return 0;
+}
+
+static void clk_gpio_gate_disable(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	gpiod_set_value(clk->gpiod, 0);
+}
+
+static int clk_gpio_gate_is_enabled(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	return gpiod_get_value(clk->gpiod);
+}
+
+const struct clk_ops clk_gpio_gate_ops = {
+	.enable = clk_gpio_gate_enable,
+	.disable = clk_gpio_gate_disable,
+	.is_enabled = clk_gpio_gate_is_enabled,
+};
+EXPORT_SYMBOL_GPL(clk_gpio_gate_ops);
+
+/**
+ * clk_register_gpio - register a gpip clock with the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_name: name of this clock's parent
+ * @gpiod: gpio descriptor to gate this clock
+ */
+struct clk *clk_register_gpio_gate(struct device *dev, const char *name,
+		const char *parent_name, struct gpio_desc *gpiod,
+		unsigned long flags)
+{
+	struct clk_gpio *clk_gpio = NULL;
+	struct clk *clk = ERR_PTR(-EINVAL);
+	struct clk_init_data init = { NULL };
+	unsigned long gpio_flags;
+	int err;
+
+	if (gpiod_is_active_low(gpiod))
+		gpio_flags = GPIOF_OUT_INIT_HIGH;
+	else
+		gpio_flags = GPIOF_OUT_INIT_LOW;
+
+	if (dev)
+		err = devm_gpio_request_one(dev, desc_to_gpio(gpiod),
+					    gpio_flags, name);
+	else
+		err = gpio_request_one(desc_to_gpio(gpiod), gpio_flags, name);
+
+	if (err) {
+		pr_err("%s: %s: Error requesting clock control gpio %u\n",
+		       __func__, name, desc_to_gpio(gpiod));
+		return ERR_PTR(err);
+	}
+
+	if (dev)
+		clk_gpio = devm_kzalloc(dev, sizeof(struct clk_gpio),
+					GFP_KERNEL);
+	else
+		clk_gpio = kzalloc(sizeof(struct clk_gpio), GFP_KERNEL);
+
+	if (!clk_gpio) {
+		clk = ERR_PTR(-ENOMEM);
+		goto clk_register_gpio_gate_err;
+	}
+
+	init.name = name;
+	init.ops = &clk_gpio_gate_ops;
+	init.flags = flags | CLK_IS_BASIC;
+	init.parent_names = (parent_name ? &parent_name : NULL);
+	init.num_parents = (parent_name ? 1 : 0);
+
+	clk_gpio->gpiod = gpiod;
+	clk_gpio->hw.init = &init;
+
+	clk = clk_register(dev, &clk_gpio->hw);
+
+	if (!IS_ERR(clk))
+		return clk;
+
+	if (!dev)
+		kfree(clk_gpio);
+
+clk_register_gpio_gate_err:
+	gpiod_put(gpiod);
+
+	return clk;
+}
+EXPORT_SYMBOL_GPL(clk_register_gpio_gate);
+
+#ifdef CONFIG_OF
+/**
+ * The clk_register_gpio_gate has to be delayed, because the EPROBE_DEFER
+ * can not be handled properly at of_clk_init() call time.
+ */
+
+struct clk_gpio_gate_delayed_register_data {
+	struct device_node *node;
+	struct mutex lock;
+	struct clk *clk;
+};
+
+static struct clk *of_clk_gpio_gate_delayed_register_get(
+		struct of_phandle_args *clkspec,
+		void *_data)
+{
+	struct clk_gpio_gate_delayed_register_data *data = _data;
+	struct clk *clk;
+	const char *clk_name = data->node->name;
+	const char *parent_name;
+	struct gpio_desc *gpiod;
+	int gpio;
+
+	mutex_lock(&data->lock);
+
+	if (data->clk) {
+		mutex_unlock(&data->lock);
+		return data->clk;
+	}
+
+	gpio = of_get_named_gpio_flags(data->node, "enable-gpios", 0, NULL);
+	if (gpio < 0) {
+		mutex_unlock(&data->lock);
+		if (gpio != -EPROBE_DEFER)
+			pr_err("%s: %s: Can't get 'enable-gpios' DT property\n",
+			       __func__, clk_name);
+		return ERR_PTR(gpio);
+	}
+	gpiod = gpio_to_desc(gpio);
+
+	parent_name = of_clk_get_parent_name(data->node, 0);
+
+	clk = clk_register_gpio_gate(NULL, clk_name, parent_name, gpiod, 0);
+	if (IS_ERR(clk)) {
+		mutex_unlock(&data->lock);
+		return clk;
+	}
+
+	data->clk = clk;
+	mutex_unlock(&data->lock);
+
+	return clk;
+}
+
+/**
+ * of_gpio_gate_clk_setup() - Setup function for gpio controlled clock
+ */
+void __init of_gpio_gate_clk_setup(struct device_node *node)
+{
+	struct clk_gpio_gate_delayed_register_data *data;
+
+	data = kzalloc(sizeof(struct clk_gpio_gate_delayed_register_data),
+		       GFP_KERNEL);
+	if (!data)
+		return;
+
+	data->node = node;
+	mutex_init(&data->lock);
+
+	of_clk_add_provider(node, of_clk_gpio_gate_delayed_register_get, data);
+}
+EXPORT_SYMBOL_GPL(of_gpio_gate_clk_setup);
+CLK_OF_DECLARE(gpio_gate_clk, "gpio-gate-clock", of_gpio_gate_clk_setup);
+#endif
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 411dd7eb2653..ec1581bd94cd 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -488,6 +488,28 @@ struct clk *clk_register_composite(struct device *dev, const char *name,
 		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
 		unsigned long flags);
 
+/***
+ * struct clk_gpio_gate - gpio gated clock
+ *
+ * @hw:		handle between common and hardware-specific interfaces
+ * @gpiod:	gpio descriptor
+ *
+ * Clock with a gpio control for enabling and disabling the parent clock.
+ * Implements .enable, .disable and .is_enabled
+ */
+
+struct clk_gpio {
+	struct clk_hw	hw;
+	struct gpio_desc *gpiod;
+};
+
+extern const struct clk_ops clk_gpio_gate_ops;
+struct clk *clk_register_gpio_gate(struct device *dev, const char *name,
+		const char *parent_name, struct gpio_desc *gpio,
+		unsigned long flags);
+
+void of_gpio_clk_gate_setup(struct device_node *node);
+
 /**
  * clk_register - allocate a new clock, register it and return an opaque cookie
  * @dev: device that is registering this clock
-- 
cgit v1.2.3


From 2c80929c4c4d54e568b07ab85877d5fd38f4b02f Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Wed, 24 Sep 2014 17:09:11 +0200
Subject: fuse: honour max_read and max_write in direct_io mode

The third argument of fuse_get_user_pages() "nbytesp" refers to the number of
bytes a caller asked to pack into fuse request. This value may be lesser
than capacity of fuse request or iov_iter.  So fuse_get_user_pages() must
ensure that *nbytesp won't grow.

Now, when helper iov_iter_get_pages() performs all hard work of extracting
pages from iov_iter, it can be done by passing properly calculated
"maxsize" to the helper.

The other caller of iov_iter_get_pages() (dio_refill_pages()) doesn't need
this capability, so pass LONG_MAX as the maxsize argument here.

Fixes: c9c37e2e6378 ("fuse: switch to iov_iter_get_pages()")
Reported-by: Werner Baumann <werner.baumann@onlinehome.de>
Tested-by: Maxim Patlasov <mpatlasov@parallels.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/direct-io.c      |  2 +-
 fs/fuse/file.c      |  1 +
 include/linux/uio.h |  2 +-
 mm/iov_iter.c       | 14 +++++++++-----
 4 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/direct-io.c b/fs/direct-io.c
index c3116404ab49..e181b6b2e297 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -158,7 +158,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
 {
 	ssize_t ret;
 
-	ret = iov_iter_get_pages(sdio->iter, dio->pages, DIO_PAGES,
+	ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
 				&sdio->from);
 
 	if (ret < 0 && sdio->blocks_available && (dio->rw & WRITE)) {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 912061ac4baf..caa8d95b24e8 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1305,6 +1305,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 		size_t start;
 		ssize_t ret = iov_iter_get_pages(ii,
 					&req->pages[req->num_pages],
+					*nbytesp - nbytes,
 					req->max_pages - req->num_pages,
 					&start);
 		if (ret < 0)
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 48d64e6ab292..290fbf0b6b8a 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -84,7 +84,7 @@ unsigned long iov_iter_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
 			unsigned long nr_segs, size_t count);
 ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
-			unsigned maxpages, size_t *start);
+			size_t maxsize, unsigned maxpages, size_t *start);
 ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
 			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
diff --git a/mm/iov_iter.c b/mm/iov_iter.c
index ab88dc0ea1d3..9a09f2034fcc 100644
--- a/mm/iov_iter.c
+++ b/mm/iov_iter.c
@@ -310,7 +310,7 @@ void iov_iter_init(struct iov_iter *i, int direction,
 EXPORT_SYMBOL(iov_iter_init);
 
 static ssize_t get_pages_iovec(struct iov_iter *i,
-		   struct page **pages, unsigned maxpages,
+		   struct page **pages, size_t maxsize, unsigned maxpages,
 		   size_t *start)
 {
 	size_t offset = i->iov_offset;
@@ -323,6 +323,8 @@ static ssize_t get_pages_iovec(struct iov_iter *i,
 	len = iov->iov_len - offset;
 	if (len > i->count)
 		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
 	addr = (unsigned long)iov->iov_base + offset;
 	len += *start = addr & (PAGE_SIZE - 1);
 	if (len > maxpages * PAGE_SIZE)
@@ -588,13 +590,15 @@ static unsigned long alignment_bvec(const struct iov_iter *i)
 }
 
 static ssize_t get_pages_bvec(struct iov_iter *i,
-		   struct page **pages, unsigned maxpages,
+		   struct page **pages, size_t maxsize, unsigned maxpages,
 		   size_t *start)
 {
 	const struct bio_vec *bvec = i->bvec;
 	size_t len = bvec->bv_len - i->iov_offset;
 	if (len > i->count)
 		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
 	/* can't be more than PAGE_SIZE */
 	*start = bvec->bv_offset + i->iov_offset;
 
@@ -711,13 +715,13 @@ unsigned long iov_iter_alignment(const struct iov_iter *i)
 EXPORT_SYMBOL(iov_iter_alignment);
 
 ssize_t iov_iter_get_pages(struct iov_iter *i,
-		   struct page **pages, unsigned maxpages,
+		   struct page **pages, size_t maxsize, unsigned maxpages,
 		   size_t *start)
 {
 	if (i->type & ITER_BVEC)
-		return get_pages_bvec(i, pages, maxpages, start);
+		return get_pages_bvec(i, pages, maxsize, maxpages, start);
 	else
-		return get_pages_iovec(i, pages, maxpages, start);
+		return get_pages_iovec(i, pages, maxsize, maxpages, start);
 }
 EXPORT_SYMBOL(iov_iter_get_pages);
 
-- 
cgit v1.2.3


From e59c5371fb9d8268d1c043172e88cecab9dc934f Mon Sep 17 00:00:00 2001
From: Mike Turquette <mturquette@linaro.org>
Date: Tue, 18 Feb 2014 21:21:25 -0800
Subject: clk: introduce clk_set_phase function & callback

A common operation for a clock signal generator is to shift the phase of
that signal. This patch introduces a new function to the clk.h API to
dynamically adjust the phase of a clock signal. Additionally this patch
introduces support for the new function in the common clock framework
via the .set_phase call back in struct clk_ops.

Signed-off-by: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Acked-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/clk/clk.c            | 85 +++++++++++++++++++++++++++++++++++++++++---
 include/linux/clk-private.h  |  1 +
 include/linux/clk-provider.h |  5 +++
 include/linux/clk.h          | 29 +++++++++++++++
 4 files changed, 116 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index b76fa69b44cb..d87661af0c72 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -117,11 +117,11 @@ static void clk_summary_show_one(struct seq_file *s, struct clk *c, int level)
 	if (!c)
 		return;
 
-	seq_printf(s, "%*s%-*s %11d %12d %11lu %10lu\n",
+	seq_printf(s, "%*s%-*s %11d %12d %11lu %10lu %-3d\n",
 		   level * 3 + 1, "",
 		   30 - level * 3, c->name,
 		   c->enable_count, c->prepare_count, clk_get_rate(c),
-		   clk_get_accuracy(c));
+		   clk_get_accuracy(c), clk_get_phase(c));
 }
 
 static void clk_summary_show_subtree(struct seq_file *s, struct clk *c,
@@ -143,8 +143,8 @@ static int clk_summary_show(struct seq_file *s, void *data)
 	struct clk *c;
 	struct hlist_head **lists = (struct hlist_head **)s->private;
 
-	seq_puts(s, "   clock                         enable_cnt  prepare_cnt        rate   accuracy\n");
-	seq_puts(s, "--------------------------------------------------------------------------------\n");
+	seq_puts(s, "   clock                         enable_cnt  prepare_cnt        rate   accuracy   phase\n");
+	seq_puts(s, "----------------------------------------------------------------------------------------\n");
 
 	clk_prepare_lock();
 
@@ -180,6 +180,7 @@ static void clk_dump_one(struct seq_file *s, struct clk *c, int level)
 	seq_printf(s, "\"prepare_count\": %d,", c->prepare_count);
 	seq_printf(s, "\"rate\": %lu", clk_get_rate(c));
 	seq_printf(s, "\"accuracy\": %lu", clk_get_accuracy(c));
+	seq_printf(s, "\"phase\": %d", clk_get_phase(c));
 }
 
 static void clk_dump_subtree(struct seq_file *s, struct clk *c, int level)
@@ -264,6 +265,11 @@ static int clk_debug_create_one(struct clk *clk, struct dentry *pdentry)
 	if (!d)
 		goto err_out;
 
+	d = debugfs_create_u32("clk_phase", S_IRUGO, clk->dentry,
+			(u32 *)&clk->phase);
+	if (!d)
+		goto err_out;
+
 	d = debugfs_create_x32("clk_flags", S_IRUGO, clk->dentry,
 			(u32 *)&clk->flags);
 	if (!d)
@@ -1738,6 +1744,77 @@ out:
 }
 EXPORT_SYMBOL_GPL(clk_set_parent);
 
+/**
+ * clk_set_phase - adjust the phase shift of a clock signal
+ * @clk: clock signal source
+ * @degrees: number of degrees the signal is shifted
+ *
+ * Shifts the phase of a clock signal by the specified
+ * degrees. Returns 0 on success, -EERROR otherwise.
+ *
+ * This function makes no distinction about the input or reference
+ * signal that we adjust the clock signal phase against. For example
+ * phase locked-loop clock signal generators we may shift phase with
+ * respect to feedback clock signal input, but for other cases the
+ * clock phase may be shifted with respect to some other, unspecified
+ * signal.
+ *
+ * Additionally the concept of phase shift does not propagate through
+ * the clock tree hierarchy, which sets it apart from clock rates and
+ * clock accuracy. A parent clock phase attribute does not have an
+ * impact on the phase attribute of a child clock.
+ */
+int clk_set_phase(struct clk *clk, int degrees)
+{
+	int ret = 0;
+
+	if (!clk)
+		goto out;
+
+	/* sanity check degrees */
+	degrees %= 360;
+	if (degrees < 0)
+		degrees += 360;
+
+	clk_prepare_lock();
+
+	if (!clk->ops->set_phase)
+		goto out_unlock;
+
+	ret = clk->ops->set_phase(clk->hw, degrees);
+
+	if (!ret)
+		clk->phase = degrees;
+
+out_unlock:
+	clk_prepare_unlock();
+
+out:
+	return ret;
+}
+
+/**
+ * clk_get_phase - return the phase shift of a clock signal
+ * @clk: clock signal source
+ *
+ * Returns the phase shift of a clock node in degrees, otherwise returns
+ * -EERROR.
+ */
+int clk_get_phase(struct clk *clk)
+{
+	int ret = 0;
+
+	if (!clk)
+		goto out;
+
+	clk_prepare_lock();
+	ret = clk->phase;
+	clk_prepare_unlock();
+
+out:
+	return ret;
+}
+
 /**
  * __clk_init - initialize the data structures in a struct clk
  * @dev:	device initializing this clk, placeholder for now
diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h
index efbf70b9fd84..845be30be50f 100644
--- a/include/linux/clk-private.h
+++ b/include/linux/clk-private.h
@@ -46,6 +46,7 @@ struct clk {
 	unsigned int		enable_count;
 	unsigned int		prepare_count;
 	unsigned long		accuracy;
+	int			phase;
 	struct hlist_head	children;
 	struct hlist_node	child_node;
 	unsigned int		notifier_count;
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 411dd7eb2653..201a6195a3eb 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -129,6 +129,10 @@ struct dentry;
  *		set then clock accuracy will be initialized to parent accuracy
  *		or 0 (perfect clock) if clock has no parent.
  *
+ * @set_phase:	Shift the phase this clock signal in degrees specified
+ *		by the second argument. Valid values for degrees are
+ *		0-359. Return 0 on success, otherwise -EERROR.
+ *
  * @init:	Perform platform-specific initialization magic.
  *		This is not not used by any of the basic clock types.
  *		Please consider other ways of solving initialization problems
@@ -177,6 +181,7 @@ struct clk_ops {
 				    unsigned long parent_rate, u8 index);
 	unsigned long	(*recalc_accuracy)(struct clk_hw *hw,
 					   unsigned long parent_accuracy);
+	int		(*set_phase)(struct clk_hw *hw, int degrees);
 	void		(*init)(struct clk_hw *hw);
 	int		(*debug_init)(struct clk_hw *hw, struct dentry *dentry);
 };
diff --git a/include/linux/clk.h b/include/linux/clk.h
index fb5e097d8f72..38bdedd3e389 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -106,6 +106,25 @@ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb);
  */
 long clk_get_accuracy(struct clk *clk);
 
+/**
+ * clk_set_phase - adjust the phase shift of a clock signal
+ * @clk: clock signal source
+ * @degrees: number of degrees the signal is shifted
+ *
+ * Shifts the phase of a clock signal by the specified degrees. Returns 0 on
+ * success, -EERROR otherwise.
+ */
+int clk_set_phase(struct clk *clk, int degrees);
+
+/**
+ * clk_get_phase - return the phase shift of a clock signal
+ * @clk: clock signal source
+ *
+ * Returns the phase shift of a clock node in degrees, otherwise returns
+ * -EERROR.
+ */
+int clk_get_phase(struct clk *clk);
+
 #else
 
 static inline long clk_get_accuracy(struct clk *clk)
@@ -113,6 +132,16 @@ static inline long clk_get_accuracy(struct clk *clk)
 	return -ENOTSUPP;
 }
 
+static inline long clk_set_phase(struct clk *clk, int phase)
+{
+	return -ENOTSUPP;
+}
+
+static inline long clk_get_phase(struct clk *clk)
+{
+	return -ENOTSUPP;
+}
+
 #endif
 
 /**
-- 
cgit v1.2.3


From 355bb165cd8bad2500df37437a9121f0177b6741 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Sat, 30 Aug 2014 21:18:00 +0200
Subject: clk: Include of.h in clock-provider.h

CLK_OF_DECLARE relies on OF_DECLARE_1 that is defined in of.h. Fixes build
errors when one use CLK_OF_DECLARE but doesn't include of.h

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Acked-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/clk-provider.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 201a6195a3eb..69b20d4c1e1a 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -13,6 +13,7 @@
 
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/of.h>
 
 #ifdef CONFIG_COMMON_CLK
 
-- 
cgit v1.2.3


From 9824cf73c3a5e677bee6fcba43c4807e01ff1b4a Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Mon, 14 Jul 2014 13:53:27 +0200
Subject: clk: Add a function to retrieve phase

The current phase API doesn't look into the actual hardware to get the phase
value, but will rather get it from a variable only set by the set_phase
function.

This will cause issue when the client driver will never call the set_phase
function, where we can end up having a reported phase that will not match what
the hardware has been programmed to by the bootloader or what phase is
programmed out of reset.

Add a new get_phase function for the drivers to implement so that we can get
this value.

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Acked-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/clk/clk.c            | 10 ++++++++++
 include/linux/clk-provider.h |  5 +++++
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index d87661af0c72..113d75db371d 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -1933,6 +1933,16 @@ int __clk_init(struct device *dev, struct clk *clk)
 	else
 		clk->accuracy = 0;
 
+	/*
+	 * Set clk's phase.
+	 * Since a phase is by definition relative to its parent, just
+	 * query the current clock phase, or just assume it's in phase.
+	 */
+	if (clk->ops->get_phase)
+		clk->phase = clk->ops->get_phase(clk->hw);
+	else
+		clk->phase = 0;
+
 	/*
 	 * Set clk's rate.  The preferred method is to use .recalc_rate.  For
 	 * simple clocks and lazy developers the default fallback is to use the
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 69b20d4c1e1a..abec961092a7 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -130,6 +130,10 @@ struct dentry;
  *		set then clock accuracy will be initialized to parent accuracy
  *		or 0 (perfect clock) if clock has no parent.
  *
+ * @get_phase:	Queries the hardware to get the current phase of a clock.
+ *		Returned values are 0-359 degrees on success, negative
+ *		error codes on failure.
+ *
  * @set_phase:	Shift the phase this clock signal in degrees specified
  *		by the second argument. Valid values for degrees are
  *		0-359. Return 0 on success, otherwise -EERROR.
@@ -182,6 +186,7 @@ struct clk_ops {
 				    unsigned long parent_rate, u8 index);
 	unsigned long	(*recalc_accuracy)(struct clk_hw *hw,
 					   unsigned long parent_accuracy);
+	int		(*get_phase)(struct clk_hw *hw);
 	int		(*set_phase)(struct clk_hw *hw, int degrees);
 	void		(*init)(struct clk_hw *hw);
 	int		(*debug_init)(struct clk_hw *hw, struct dentry *dentry);
-- 
cgit v1.2.3


From e7258c1a269e0967856c81d182c286a78f5ecf15 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:19:55 -0400
Subject: block: Get rid of bdev_integrity_enabled()

bdev_integrity_enabled() is only used by bio_integrity_enabled().
Combine these two functions.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 Documentation/block/data-integrity.txt | 10 ---------
 block/bio-integrity.c                  | 39 +++++++++++++++-------------------
 include/linux/bio.h                    |  6 +++---
 3 files changed, 20 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
index 2d735b0ae383..b4eacf48053c 100644
--- a/Documentation/block/data-integrity.txt
+++ b/Documentation/block/data-integrity.txt
@@ -192,16 +192,6 @@ will require extra work due to the application tag.
     supported by the block device.
 
 
-    int bdev_integrity_enabled(block_device, int rw);
-
-      bdev_integrity_enabled() will return 1 if the block device
-      supports integrity metadata transfer for the data direction
-      specified in 'rw'.
-
-      bdev_integrity_enabled() honors the write_generate and
-      read_verify flags in sysfs and will respond accordingly.
-
-
     int bio_integrity_prep(bio);
 
       To generate IMD for WRITE and to set up buffers for READ, the
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index f14b4abbebd8..36b788552c3e 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -147,24 +147,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
-static int bdev_integrity_enabled(struct block_device *bdev, int rw)
-{
-	struct blk_integrity *bi = bdev_get_integrity(bdev);
-
-	if (bi == NULL)
-		return 0;
-
-	if (rw == READ && bi->verify_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_READ))
-		return 1;
-
-	if (rw == WRITE && bi->generate_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_WRITE))
-		return 1;
-
-	return 0;
-}
-
 /**
  * bio_integrity_enabled - Check whether integrity can be passed
  * @bio:	bio to check
@@ -174,16 +156,29 @@ static int bdev_integrity_enabled(struct block_device *bdev, int rw)
  * set prior to calling.  The functions honors the write_generate and
  * read_verify flags in sysfs.
  */
-int bio_integrity_enabled(struct bio *bio)
+bool bio_integrity_enabled(struct bio *bio)
 {
+	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
+
 	if (!bio_is_rw(bio))
-		return 0;
+		return false;
 
 	/* Already protected? */
 	if (bio_integrity(bio))
-		return 0;
+		return false;
+
+	if (bi == NULL)
+		return false;
+
+	if (bio_data_dir(bio) == READ && bi->verify_fn != NULL &&
+	    (bi->flags & INTEGRITY_FLAG_READ))
+		return true;
+
+	if (bio_data_dir(bio) == WRITE && bi->generate_fn != NULL &&
+	    (bi->flags & INTEGRITY_FLAG_WRITE))
+		return true;
 
-	return bdev_integrity_enabled(bio->bi_bdev, bio_data_dir(bio));
+	return false;
 }
 EXPORT_SYMBOL(bio_integrity_enabled);
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b39e5000ff58..63e399b4fde5 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -666,7 +666,7 @@ struct biovec_slab {
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
 extern void bio_integrity_free(struct bio *);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
-extern int bio_integrity_enabled(struct bio *bio);
+extern bool bio_integrity_enabled(struct bio *bio);
 extern int bio_integrity_set_tag(struct bio *, void *, unsigned int);
 extern int bio_integrity_get_tag(struct bio *, void *, unsigned int);
 extern int bio_integrity_prep(struct bio *);
@@ -685,9 +685,9 @@ static inline int bio_integrity(struct bio *bio)
 	return 0;
 }
 
-static inline int bio_integrity_enabled(struct bio *bio)
+static inline bool bio_integrity_enabled(struct bio *bio)
 {
-	return 0;
+	return false;
 }
 
 static inline int bioset_integrity_create(struct bio_set *bs, int pool_size)
-- 
cgit v1.2.3


From 180b2f95dd331010a9930a65c8a18d6d81b94dc1 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:19:56 -0400
Subject: block: Replace bi_integrity with bi_special

For commands like REQ_COPY we need a way to pass extra information along
with each bio. Like integrity metadata this information must be
available at the bottom of the stack so bi_private does not suffice.

Rename the existing bi_integrity field to bi_special and make it a union
so we can have different bio extensions for each class of command.

We previously used bi_integrity != NULL as a way to identify whether a
bio had integrity metadata or not. Introduce a REQ_INTEGRITY to be the
indicator now that bi_special can contain different things.

In addition, bio_integrity(bio) will now return a pointer to the
integrity payload (when applicable).

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 Documentation/block/data-integrity.txt | 10 +++++-----
 block/bio-integrity.c                  | 19 ++++++++++---------
 drivers/scsi/sd_dif.c                  |  8 ++++----
 include/linux/bio.h                    | 11 +++++++++--
 include/linux/blk_types.h              |  8 ++++++--
 include/linux/blkdev.h                 |  7 ++-----
 6 files changed, 36 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
index b4eacf48053c..4d4de8b09530 100644
--- a/Documentation/block/data-integrity.txt
+++ b/Documentation/block/data-integrity.txt
@@ -129,11 +129,11 @@ interface for this is being worked on.
 4.1 BIO
 
 The data integrity patches add a new field to struct bio when
-CONFIG_BLK_DEV_INTEGRITY is enabled.  bio->bi_integrity is a pointer
-to a struct bip which contains the bio integrity payload.  Essentially
-a bip is a trimmed down struct bio which holds a bio_vec containing
-the integrity metadata and the required housekeeping information (bvec
-pool, vector count, etc.)
+CONFIG_BLK_DEV_INTEGRITY is enabled.  bio_integrity(bio) returns a
+pointer to a struct bip which contains the bio integrity payload.
+Essentially a bip is a trimmed down struct bio which holds a bio_vec
+containing the integrity metadata and the required housekeeping
+information (bvec pool, vector count, etc.)
 
 A kernel subsystem can enable data integrity protection on a bio by
 calling bio_integrity_alloc(bio).  This will allocate and attach the
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 36b788552c3e..bd3125c3c124 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -79,6 +79,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	bip->bip_slab = idx;
 	bip->bip_bio = bio;
 	bio->bi_integrity = bip;
+	bio->bi_rw |= REQ_INTEGRITY;
 
 	return bip;
 err:
@@ -96,7 +97,7 @@ EXPORT_SYMBOL(bio_integrity_alloc);
  */
 void bio_integrity_free(struct bio *bio)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_set *bs = bio->bi_pool;
 
 	if (bip->bip_owns_buf)
@@ -128,7 +129,7 @@ EXPORT_SYMBOL(bio_integrity_free);
 int bio_integrity_add_page(struct bio *bio, struct page *page,
 			   unsigned int len, unsigned int offset)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_vec *iv;
 
 	if (bip->bip_vcnt >= bip->bip_max_vcnt) {
@@ -229,7 +230,7 @@ EXPORT_SYMBOL(bio_integrity_tag_size);
 static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len,
 			     int set)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	unsigned int nr_sectors;
 
@@ -304,12 +305,12 @@ static int bio_integrity_generate_verify(struct bio *bio, int operate)
 	struct bio_vec *bv;
 	sector_t sector;
 	unsigned int sectors, ret = 0, i;
-	void *prot_buf = bio->bi_integrity->bip_buf;
+	void *prot_buf = bio_integrity(bio)->bip_buf;
 
 	if (operate)
 		sector = bio->bi_iter.bi_sector;
 	else
-		sector = bio->bi_integrity->bip_iter.bi_sector;
+		sector = bio_integrity(bio)->bip_iter.bi_sector;
 
 	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
 	bix.sector_size = bi->sector_size;
@@ -505,7 +506,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  */
 void bio_integrity_endio(struct bio *bio, int error)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 
 	BUG_ON(bip->bip_bio != bio);
 
@@ -536,7 +537,7 @@ EXPORT_SYMBOL(bio_integrity_endio);
  */
 void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9);
 
@@ -558,7 +559,7 @@ EXPORT_SYMBOL(bio_integrity_advance);
 void bio_integrity_trim(struct bio *bio, unsigned int offset,
 			unsigned int sectors)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 
 	bio_integrity_advance(bio, offset << 9);
@@ -577,7 +578,7 @@ EXPORT_SYMBOL(bio_integrity_trim);
 int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 			gfp_t gfp_mask)
 {
-	struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
+	struct bio_integrity_payload *bip_src = bio_integrity(bio_src);
 	struct bio_integrity_payload *bip;
 
 	BUG_ON(bip_src == NULL);
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index a7a691d0af7d..29f0477a8708 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -383,9 +383,9 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 		if (bio_flagged(bio, BIO_MAPPED_INTEGRITY))
 			break;
 
-		virt = bio->bi_integrity->bip_iter.bi_sector & 0xffffffff;
+		virt = bio_integrity(bio)->bip_iter.bi_sector & 0xffffffff;
 
-		bip_for_each_vec(iv, bio->bi_integrity, iter) {
+		bip_for_each_vec(iv, bio_integrity(bio), iter) {
 			sdt = kmap_atomic(iv.bv_page)
 				+ iv.bv_offset;
 
@@ -434,9 +434,9 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 		struct bio_vec iv;
 		struct bvec_iter iter;
 
-		virt = bio->bi_integrity->bip_iter.bi_sector & 0xffffffff;
+		virt = bio_integrity(bio)->bip_iter.bi_sector & 0xffffffff;
 
-		bip_for_each_vec(iv, bio->bi_integrity, iter) {
+		bip_for_each_vec(iv, bio_integrity(bio), iter) {
 			sdt = kmap_atomic(iv.bv_page)
 				+ iv.bv_offset;
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 63e399b4fde5..a810a74071b2 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -293,6 +293,15 @@ static inline unsigned bio_segments(struct bio *bio)
 #define bio_get(bio)	atomic_inc(&(bio)->bi_cnt)
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
+{
+	if (bio->bi_rw & REQ_INTEGRITY)
+		return bio->bi_integrity;
+
+	return NULL;
+}
+
 /*
  * bio integrity payload
  */
@@ -661,8 +670,6 @@ struct biovec_slab {
 	for_each_bio(_bio)						\
 		bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
 
-#define bio_integrity(bio) (bio->bi_integrity != NULL)
-
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
 extern void bio_integrity_free(struct bio *);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index bb7d66460e7a..6a5d2f2de1b9 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -78,9 +78,11 @@ struct bio {
 	struct io_context	*bi_ioc;
 	struct cgroup_subsys_state *bi_css;
 #endif
+	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
-	struct bio_integrity_payload *bi_integrity;  /* data integrity */
+		struct bio_integrity_payload *bi_integrity; /* data integrity */
 #endif
+	};
 
 	unsigned short		bi_vcnt;	/* how many bio_vec's */
 
@@ -162,6 +164,7 @@ enum rq_flag_bits {
 	__REQ_WRITE_SAME,	/* write same block many times */
 
 	__REQ_NOIDLE,		/* don't anticipate more IO after this one */
+	__REQ_INTEGRITY,	/* I/O includes block integrity payload */
 	__REQ_FUA,		/* forced unit access */
 	__REQ_FLUSH,		/* request for cache flush */
 
@@ -203,13 +206,14 @@ enum rq_flag_bits {
 #define REQ_DISCARD		(1ULL << __REQ_DISCARD)
 #define REQ_WRITE_SAME		(1ULL << __REQ_WRITE_SAME)
 #define REQ_NOIDLE		(1ULL << __REQ_NOIDLE)
+#define REQ_INTEGRITY		(1ULL << __REQ_INTEGRITY)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \
 	 REQ_DISCARD | REQ_WRITE_SAME | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | \
-	 REQ_SECURE)
+	 REQ_SECURE | REQ_INTEGRITY)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
 #define BIO_NO_ADVANCE_ITER_MASK	(REQ_DISCARD|REQ_WRITE_SAME)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 49f3461e4272..7fcb2caef559 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1514,12 +1514,9 @@ static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 	return disk->integrity;
 }
 
-static inline int blk_integrity_rq(struct request *rq)
+static inline bool blk_integrity_rq(struct request *rq)
 {
-	if (rq->bio == NULL)
-		return 0;
-
-	return bio_integrity(rq->bio);
+	return rq->cmd_flags & REQ_INTEGRITY;
 }
 
 static inline void blk_queue_max_integrity_segments(struct request_queue *q,
-- 
cgit v1.2.3


From 8492b68bc4025e7bce1d57761bd7c047efda2f81 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:19:57 -0400
Subject: block: Remove integrity tagging functions

None of the filesystems appear interested in using the integrity tagging
feature. Potentially because very few storage devices actually permit
using the application tag space.

Remove the tagging functions.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 Documentation/block/data-integrity.txt | 34 ------------
 block/bio-integrity.c                  | 94 +---------------------------------
 block/blk-integrity.c                  |  2 -
 drivers/scsi/sd_dif.c                  | 65 -----------------------
 include/linux/bio.h                    |  3 --
 include/linux/blkdev.h                 |  4 --
 6 files changed, 1 insertion(+), 201 deletions(-)

(limited to 'include')

diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
index 4d4de8b09530..f56ec97f0d14 100644
--- a/Documentation/block/data-integrity.txt
+++ b/Documentation/block/data-integrity.txt
@@ -206,36 +206,6 @@ will require extra work due to the application tag.
       bio_integrity_enabled() returned 1.
 
 
-    int bio_integrity_tag_size(bio);
-
-      If the filesystem wants to use the application tag space it will
-      first have to find out how much storage space is available.
-      Because tag space is generally limited (usually 2 bytes per
-      sector regardless of sector size), the integrity framework
-      supports interleaving the information between the sectors in an
-      I/O.
-
-      Filesystems can call bio_integrity_tag_size(bio) to find out how
-      many bytes of storage are available for that particular bio.
-
-      Another option is bdev_get_tag_size(block_device) which will
-      return the number of available bytes per hardware sector.
-
-
-    int bio_integrity_set_tag(bio, void *tag_buf, len);
-
-      After a successful return from bio_integrity_prep(),
-      bio_integrity_set_tag() can be used to attach an opaque tag
-      buffer to a bio.  Obviously this only makes sense if the I/O is
-      a WRITE.
-
-
-    int bio_integrity_get_tag(bio, void *tag_buf, len);
-
-      Similarly, at READ I/O completion time the filesystem can
-      retrieve the tag buffer using bio_integrity_get_tag().
-
-
 5.3 PASSING EXISTING INTEGRITY METADATA
 
     Filesystems that either generate their own integrity metadata or
@@ -288,8 +258,6 @@ will require extra work due to the application tag.
             .name                   = "STANDARDSBODY-TYPE-VARIANT-CSUM",
             .generate_fn            = my_generate_fn,
        	    .verify_fn              = my_verify_fn,
-       	    .get_tag_fn             = my_get_tag_fn,
-       	    .set_tag_fn             = my_set_tag_fn,
 	    .tuple_size             = sizeof(struct my_tuple_size),
 	    .tag_size               = <tag bytes per hw sector>,
         };
@@ -311,7 +279,5 @@ will require extra work due to the application tag.
       are available per hardware sector.  For DIF this is either 2 or
       0 depending on the value of the Control Mode Page ATO bit.
 
-      See 6.2 for a description of get_tag_fn and set_tag_fn.
-
 ----------------------------------------------------------------------
 2007-12-24 Martin K. Petersen <martin.petersen@oracle.com>
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index bd3125c3c124..367bb24bb9f1 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -209,90 +209,6 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 	return bio_integrity_hw_sectors(bi, sectors) * bi->tuple_size;
 }
 
-/**
- * bio_integrity_tag_size - Retrieve integrity tag space
- * @bio:	bio to inspect
- *
- * Description: Returns the maximum number of tag bytes that can be
- * attached to this bio. Filesystems can use this to determine how
- * much metadata to attach to an I/O.
- */
-unsigned int bio_integrity_tag_size(struct bio *bio)
-{
-	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-
-	BUG_ON(bio->bi_iter.bi_size == 0);
-
-	return bi->tag_size * (bio->bi_iter.bi_size / bi->sector_size);
-}
-EXPORT_SYMBOL(bio_integrity_tag_size);
-
-static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len,
-			     int set)
-{
-	struct bio_integrity_payload *bip = bio_integrity(bio);
-	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	unsigned int nr_sectors;
-
-	BUG_ON(bip->bip_buf == NULL);
-
-	if (bi->tag_size == 0)
-		return -1;
-
-	nr_sectors = bio_integrity_hw_sectors(bi,
-					DIV_ROUND_UP(len, bi->tag_size));
-
-	if (nr_sectors * bi->tuple_size > bip->bip_iter.bi_size) {
-		printk(KERN_ERR "%s: tag too big for bio: %u > %u\n", __func__,
-		       nr_sectors * bi->tuple_size, bip->bip_iter.bi_size);
-		return -1;
-	}
-
-	if (set)
-		bi->set_tag_fn(bip->bip_buf, tag_buf, nr_sectors);
-	else
-		bi->get_tag_fn(bip->bip_buf, tag_buf, nr_sectors);
-
-	return 0;
-}
-
-/**
- * bio_integrity_set_tag - Attach a tag buffer to a bio
- * @bio:	bio to attach buffer to
- * @tag_buf:	Pointer to a buffer containing tag data
- * @len:	Length of the included buffer
- *
- * Description: Use this function to tag a bio by leveraging the extra
- * space provided by devices formatted with integrity protection.  The
- * size of the integrity buffer must be <= to the size reported by
- * bio_integrity_tag_size().
- */
-int bio_integrity_set_tag(struct bio *bio, void *tag_buf, unsigned int len)
-{
-	BUG_ON(bio_data_dir(bio) != WRITE);
-
-	return bio_integrity_tag(bio, tag_buf, len, 1);
-}
-EXPORT_SYMBOL(bio_integrity_set_tag);
-
-/**
- * bio_integrity_get_tag - Retrieve a tag buffer from a bio
- * @bio:	bio to retrieve buffer from
- * @tag_buf:	Pointer to a buffer for the tag data
- * @len:	Length of the target buffer
- *
- * Description: Use this function to retrieve the tag buffer from a
- * completed I/O. The size of the integrity buffer must be <= to the
- * size reported by bio_integrity_tag_size().
- */
-int bio_integrity_get_tag(struct bio *bio, void *tag_buf, unsigned int len)
-{
-	BUG_ON(bio_data_dir(bio) != READ);
-
-	return bio_integrity_tag(bio, tag_buf, len, 0);
-}
-EXPORT_SYMBOL(bio_integrity_get_tag);
-
 /**
  * bio_integrity_generate_verify - Generate/verify integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
@@ -355,14 +271,6 @@ static void bio_integrity_generate(struct bio *bio)
 	bio_integrity_generate_verify(bio, 1);
 }
 
-static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
-{
-	if (bi)
-		return bi->tuple_size;
-
-	return 0;
-}
-
 /**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
@@ -393,7 +301,7 @@ int bio_integrity_prep(struct bio *bio)
 	sectors = bio_integrity_hw_sectors(bi, bio_sectors(bio));
 
 	/* Allocate kernel buffer for protection data */
-	len = sectors * blk_integrity_tuple_size(bi);
+	len = sectors * bi->tuple_size;
 	buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
 	if (unlikely(buf == NULL)) {
 		printk(KERN_ERR "could not allocate integrity buffer\n");
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 7fbab84399e6..7ac17160ab69 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -418,8 +418,6 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		bi->generate_fn = template->generate_fn;
 		bi->verify_fn = template->verify_fn;
 		bi->tuple_size = template->tuple_size;
-		bi->set_tag_fn = template->set_tag_fn;
-		bi->get_tag_fn = template->get_tag_fn;
 		bi->tag_size = template->tag_size;
 	} else
 		bi->name = bi_unsupported_name;
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 29f0477a8708..38a7778631be 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -128,39 +128,10 @@ static int sd_dif_type1_verify_ip(struct blk_integrity_exchg *bix)
 	return sd_dif_type1_verify(bix, sd_dif_ip_fn);
 }
 
-/*
- * Functions for interleaving and deinterleaving application tags
- */
-static void sd_dif_type1_set_tag(void *prot, void *tag_buf, unsigned int sectors)
-{
-	struct sd_dif_tuple *sdt = prot;
-	u8 *tag = tag_buf;
-	unsigned int i, j;
-
-	for (i = 0, j = 0 ; i < sectors ; i++, j += 2, sdt++) {
-		sdt->app_tag = tag[j] << 8 | tag[j+1];
-		BUG_ON(sdt->app_tag == 0xffff);
-	}
-}
-
-static void sd_dif_type1_get_tag(void *prot, void *tag_buf, unsigned int sectors)
-{
-	struct sd_dif_tuple *sdt = prot;
-	u8 *tag = tag_buf;
-	unsigned int i, j;
-
-	for (i = 0, j = 0 ; i < sectors ; i++, j += 2, sdt++) {
-		tag[j] = (sdt->app_tag & 0xff00) >> 8;
-		tag[j+1] = sdt->app_tag & 0xff;
-	}
-}
-
 static struct blk_integrity dif_type1_integrity_crc = {
 	.name			= "T10-DIF-TYPE1-CRC",
 	.generate_fn		= sd_dif_type1_generate_crc,
 	.verify_fn		= sd_dif_type1_verify_crc,
-	.get_tag_fn		= sd_dif_type1_get_tag,
-	.set_tag_fn		= sd_dif_type1_set_tag,
 	.tuple_size		= sizeof(struct sd_dif_tuple),
 	.tag_size		= 0,
 };
@@ -169,8 +140,6 @@ static struct blk_integrity dif_type1_integrity_ip = {
 	.name			= "T10-DIF-TYPE1-IP",
 	.generate_fn		= sd_dif_type1_generate_ip,
 	.verify_fn		= sd_dif_type1_verify_ip,
-	.get_tag_fn		= sd_dif_type1_get_tag,
-	.set_tag_fn		= sd_dif_type1_set_tag,
 	.tuple_size		= sizeof(struct sd_dif_tuple),
 	.tag_size		= 0,
 };
@@ -245,42 +214,10 @@ static int sd_dif_type3_verify_ip(struct blk_integrity_exchg *bix)
 	return sd_dif_type3_verify(bix, sd_dif_ip_fn);
 }
 
-static void sd_dif_type3_set_tag(void *prot, void *tag_buf, unsigned int sectors)
-{
-	struct sd_dif_tuple *sdt = prot;
-	u8 *tag = tag_buf;
-	unsigned int i, j;
-
-	for (i = 0, j = 0 ; i < sectors ; i++, j += 6, sdt++) {
-		sdt->app_tag = tag[j] << 8 | tag[j+1];
-		sdt->ref_tag = tag[j+2] << 24 | tag[j+3] << 16 |
-			tag[j+4] << 8 | tag[j+5];
-	}
-}
-
-static void sd_dif_type3_get_tag(void *prot, void *tag_buf, unsigned int sectors)
-{
-	struct sd_dif_tuple *sdt = prot;
-	u8 *tag = tag_buf;
-	unsigned int i, j;
-
-	for (i = 0, j = 0 ; i < sectors ; i++, j += 2, sdt++) {
-		tag[j] = (sdt->app_tag & 0xff00) >> 8;
-		tag[j+1] = sdt->app_tag & 0xff;
-		tag[j+2] = (sdt->ref_tag & 0xff000000) >> 24;
-		tag[j+3] = (sdt->ref_tag & 0xff0000) >> 16;
-		tag[j+4] = (sdt->ref_tag & 0xff00) >> 8;
-		tag[j+5] = sdt->ref_tag & 0xff;
-		BUG_ON(sdt->app_tag == 0xffff || sdt->ref_tag == 0xffffffff);
-	}
-}
-
 static struct blk_integrity dif_type3_integrity_crc = {
 	.name			= "T10-DIF-TYPE3-CRC",
 	.generate_fn		= sd_dif_type3_generate_crc,
 	.verify_fn		= sd_dif_type3_verify_crc,
-	.get_tag_fn		= sd_dif_type3_get_tag,
-	.set_tag_fn		= sd_dif_type3_set_tag,
 	.tuple_size		= sizeof(struct sd_dif_tuple),
 	.tag_size		= 0,
 };
@@ -289,8 +226,6 @@ static struct blk_integrity dif_type3_integrity_ip = {
 	.name			= "T10-DIF-TYPE3-IP",
 	.generate_fn		= sd_dif_type3_generate_ip,
 	.verify_fn		= sd_dif_type3_verify_ip,
-	.get_tag_fn		= sd_dif_type3_get_tag,
-	.set_tag_fn		= sd_dif_type3_set_tag,
 	.tuple_size		= sizeof(struct sd_dif_tuple),
 	.tag_size		= 0,
 };
diff --git a/include/linux/bio.h b/include/linux/bio.h
index a810a74071b2..63a0e53e238c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -362,7 +362,6 @@ extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
 extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
 extern struct bio_set *fs_bio_set;
-unsigned int bio_integrity_tag_size(struct bio *bio);
 
 static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 {
@@ -674,8 +673,6 @@ extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, un
 extern void bio_integrity_free(struct bio *);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
 extern bool bio_integrity_enabled(struct bio *bio);
-extern int bio_integrity_set_tag(struct bio *, void *, unsigned int);
-extern int bio_integrity_get_tag(struct bio *, void *, unsigned int);
 extern int bio_integrity_prep(struct bio *);
 extern void bio_integrity_endio(struct bio *, int);
 extern void bio_integrity_advance(struct bio *, unsigned int);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7fcb2caef559..0bf5d79d9ba0 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1472,14 +1472,10 @@ struct blk_integrity_exchg {
 
 typedef void (integrity_gen_fn) (struct blk_integrity_exchg *);
 typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *);
-typedef void (integrity_set_tag_fn) (void *, void *, unsigned int);
-typedef void (integrity_get_tag_fn) (void *, void *, unsigned int);
 
 struct blk_integrity {
 	integrity_gen_fn	*generate_fn;
 	integrity_vrfy_fn	*verify_fn;
-	integrity_set_tag_fn	*set_tag_fn;
-	integrity_get_tag_fn	*get_tag_fn;
 
 	unsigned short		flags;
 	unsigned short		tuple_size;
-- 
cgit v1.2.3


From 5f9378fa9ca214977b5bfc12197c67eea450fc40 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:19:58 -0400
Subject: block: Remove bip_buf

bip_buf is not really needed so we can remove it.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/bio-integrity.c | 10 ++++++----
 include/linux/bio.h   |  3 ---
 2 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 367bb24bb9f1..e84f7fb8694b 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -101,7 +101,8 @@ void bio_integrity_free(struct bio *bio)
 	struct bio_set *bs = bio->bi_pool;
 
 	if (bip->bip_owns_buf)
-		kfree(bip->bip_buf);
+		kfree(page_address(bip->bip_vec->bv_page) +
+		      bip->bip_vec->bv_offset);
 
 	if (bs) {
 		if (bip->bip_slab != BIO_POOL_NONE)
@@ -219,14 +220,16 @@ static int bio_integrity_generate_verify(struct bio *bio, int operate)
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	struct blk_integrity_exchg bix;
 	struct bio_vec *bv;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	sector_t sector;
 	unsigned int sectors, ret = 0, i;
-	void *prot_buf = bio_integrity(bio)->bip_buf;
+	void *prot_buf = page_address(bip->bip_vec->bv_page) +
+		bip->bip_vec->bv_offset;
 
 	if (operate)
 		sector = bio->bi_iter.bi_sector;
 	else
-		sector = bio_integrity(bio)->bip_iter.bi_sector;
+		sector = bip->bip_iter.bi_sector;
 
 	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
 	bix.sector_size = bi->sector_size;
@@ -321,7 +324,6 @@ int bio_integrity_prep(struct bio *bio)
 	}
 
 	bip->bip_owns_buf = 1;
-	bip->bip_buf = buf;
 	bip->bip_iter.bi_size = len;
 	bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 63a0e53e238c..448d8c052cb7 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -310,9 +310,6 @@ struct bio_integrity_payload {
 
 	struct bvec_iter	bip_iter;
 
-	/* kill - should just use bip_vec */
-	void			*bip_buf;	/* generated integrity data */
-
 	bio_end_io_t		*bip_end_io;	/* saved I/O completion fn */
 
 	unsigned short		bip_slab;	/* slab the bip came from */
-- 
cgit v1.2.3


From 3be91c4a3d090bd700bd6ee5bf457c1bbf189a4f Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:19:59 -0400
Subject: block: Deprecate the use of the term sector in the context of block
 integrity

The protection interval is not necessarily tied to the logical block
size of a block device. Stop using the terms "sector" and "sectors".

Going forward we will use the term "seed" to describe the initial
reference tag value for a given I/O. "Interval" will be used to describe
the portion of the data buffer that a given piece of protection
information is associated with.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/bio-integrity.c  | 42 +++++++++++++++++++++---------------------
 block/blk-integrity.c  | 10 +++++-----
 drivers/scsi/sd_dif.c  | 46 +++++++++++++++++++++++-----------------------
 include/linux/blkdev.h |  6 +++---
 4 files changed, 52 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index e84f7fb8694b..6a3aacf57b19 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -185,20 +185,20 @@ bool bio_integrity_enabled(struct bio *bio)
 EXPORT_SYMBOL(bio_integrity_enabled);
 
 /**
- * bio_integrity_hw_sectors - Convert 512b sectors to hardware ditto
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
  * @bi:		blk_integrity profile for device
- * @sectors:	Number of 512 sectors to convert
+ * @sectors:	Size of the bio in 512-byte sectors
  *
  * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the hardware
- * sector size of the storage device.  Convert the block layer sectors
- * to physical sectors.
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device.  Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
  */
-static inline unsigned int bio_integrity_hw_sectors(struct blk_integrity *bi,
-						    unsigned int sectors)
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
 {
 	/* At this point there are only 512b or 4096b DIF/EPP devices */
-	if (bi->sector_size == 4096)
+	if (bi->interval == 4096)
 		return sectors >>= 3;
 
 	return sectors;
@@ -207,7 +207,7 @@ static inline unsigned int bio_integrity_hw_sectors(struct blk_integrity *bi,
 static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 					       unsigned int sectors)
 {
-	return bio_integrity_hw_sectors(bi, sectors) * bi->tuple_size;
+	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
 }
 
 /**
@@ -221,25 +221,25 @@ static int bio_integrity_generate_verify(struct bio *bio, int operate)
 	struct blk_integrity_exchg bix;
 	struct bio_vec *bv;
 	struct bio_integrity_payload *bip = bio_integrity(bio);
-	sector_t sector;
-	unsigned int sectors, ret = 0, i;
+	sector_t seed;
+	unsigned int intervals, ret = 0, i;
 	void *prot_buf = page_address(bip->bip_vec->bv_page) +
 		bip->bip_vec->bv_offset;
 
 	if (operate)
-		sector = bio->bi_iter.bi_sector;
+		seed = bio->bi_iter.bi_sector;
 	else
-		sector = bip->bip_iter.bi_sector;
+		seed = bip->bip_iter.bi_sector;
 
 	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
-	bix.sector_size = bi->sector_size;
+	bix.interval = bi->interval;
 
 	bio_for_each_segment_all(bv, bio, i) {
 		void *kaddr = kmap_atomic(bv->bv_page);
 		bix.data_buf = kaddr + bv->bv_offset;
 		bix.data_size = bv->bv_len;
 		bix.prot_buf = prot_buf;
-		bix.sector = sector;
+		bix.seed = seed;
 
 		if (operate)
 			bi->generate_fn(&bix);
@@ -251,9 +251,9 @@ static int bio_integrity_generate_verify(struct bio *bio, int operate)
 			}
 		}
 
-		sectors = bv->bv_len / bi->sector_size;
-		sector += sectors;
-		prot_buf += sectors * bi->tuple_size;
+		intervals = bv->bv_len / bi->interval;
+		seed += intervals;
+		prot_buf += intervals * bi->tuple_size;
 
 		kunmap_atomic(kaddr);
 	}
@@ -294,17 +294,17 @@ int bio_integrity_prep(struct bio *bio)
 	unsigned long start, end;
 	unsigned int len, nr_pages;
 	unsigned int bytes, offset, i;
-	unsigned int sectors;
+	unsigned int intervals;
 
 	bi = bdev_get_integrity(bio->bi_bdev);
 	q = bdev_get_queue(bio->bi_bdev);
 	BUG_ON(bi == NULL);
 	BUG_ON(bio_integrity(bio));
 
-	sectors = bio_integrity_hw_sectors(bi, bio_sectors(bio));
+	intervals = bio_integrity_intervals(bi, bio_sectors(bio));
 
 	/* Allocate kernel buffer for protection data */
-	len = sectors * bi->tuple_size;
+	len = intervals * bi->tuple_size;
 	buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
 	if (unlikely(buf == NULL)) {
 		printk(KERN_ERR "could not allocate integrity buffer\n");
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 7ac17160ab69..3a83a7d08177 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -154,10 +154,10 @@ int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
 	if (!b1 || !b2)
 		return -1;
 
-	if (b1->sector_size != b2->sector_size) {
-		printk(KERN_ERR "%s: %s/%s sector sz %u != %u\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->sector_size, b2->sector_size);
+	if (b1->interval != b2->interval) {
+		pr_err("%s: %s/%s protection interval %u != %u\n",
+		       __func__, gd1->disk_name, gd2->disk_name,
+		       b1->interval, b2->interval);
 		return -1;
 	}
 
@@ -407,7 +407,7 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		kobject_uevent(&bi->kobj, KOBJ_ADD);
 
 		bi->flags |= INTEGRITY_FLAG_READ | INTEGRITY_FLAG_WRITE;
-		bi->sector_size = queue_logical_block_size(disk->queue);
+		bi->interval = queue_logical_block_size(disk->queue);
 		disk->integrity = bi;
 	} else
 		bi = disk->integrity;
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 38a7778631be..1600270a46e5 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -57,16 +57,16 @@ static void sd_dif_type1_generate(struct blk_integrity_exchg *bix, csum_fn *fn)
 {
 	void *buf = bix->data_buf;
 	struct sd_dif_tuple *sdt = bix->prot_buf;
-	sector_t sector = bix->sector;
+	sector_t seed = bix->seed;
 	unsigned int i;
 
-	for (i = 0 ; i < bix->data_size ; i += bix->sector_size, sdt++) {
-		sdt->guard_tag = fn(buf, bix->sector_size);
-		sdt->ref_tag = cpu_to_be32(sector & 0xffffffff);
+	for (i = 0 ; i < bix->data_size ; i += bix->interval, sdt++) {
+		sdt->guard_tag = fn(buf, bix->interval);
+		sdt->ref_tag = cpu_to_be32(seed & 0xffffffff);
 		sdt->app_tag = 0;
 
-		buf += bix->sector_size;
-		sector++;
+		buf += bix->interval;
+		seed++;
 	}
 }
 
@@ -84,35 +84,35 @@ static int sd_dif_type1_verify(struct blk_integrity_exchg *bix, csum_fn *fn)
 {
 	void *buf = bix->data_buf;
 	struct sd_dif_tuple *sdt = bix->prot_buf;
-	sector_t sector = bix->sector;
+	sector_t seed = bix->seed;
 	unsigned int i;
 	__u16 csum;
 
-	for (i = 0 ; i < bix->data_size ; i += bix->sector_size, sdt++) {
+	for (i = 0 ; i < bix->data_size ; i += bix->interval, sdt++) {
 		/* Unwritten sectors */
 		if (sdt->app_tag == 0xffff)
 			return 0;
 
-		if (be32_to_cpu(sdt->ref_tag) != (sector & 0xffffffff)) {
+		if (be32_to_cpu(sdt->ref_tag) != (seed & 0xffffffff)) {
 			printk(KERN_ERR
 			       "%s: ref tag error on sector %lu (rcvd %u)\n",
-			       bix->disk_name, (unsigned long)sector,
+			       bix->disk_name, (unsigned long)seed,
 			       be32_to_cpu(sdt->ref_tag));
 			return -EIO;
 		}
 
-		csum = fn(buf, bix->sector_size);
+		csum = fn(buf, bix->interval);
 
 		if (sdt->guard_tag != csum) {
 			printk(KERN_ERR "%s: guard tag error on sector %lu " \
 			       "(rcvd %04x, data %04x)\n", bix->disk_name,
-			       (unsigned long)sector,
+			       (unsigned long)seed,
 			       be16_to_cpu(sdt->guard_tag), be16_to_cpu(csum));
 			return -EIO;
 		}
 
-		buf += bix->sector_size;
-		sector++;
+		buf += bix->interval;
+		seed++;
 	}
 
 	return 0;
@@ -155,12 +155,12 @@ static void sd_dif_type3_generate(struct blk_integrity_exchg *bix, csum_fn *fn)
 	struct sd_dif_tuple *sdt = bix->prot_buf;
 	unsigned int i;
 
-	for (i = 0 ; i < bix->data_size ; i += bix->sector_size, sdt++) {
-		sdt->guard_tag = fn(buf, bix->sector_size);
+	for (i = 0 ; i < bix->data_size ; i += bix->interval, sdt++) {
+		sdt->guard_tag = fn(buf, bix->interval);
 		sdt->ref_tag = 0;
 		sdt->app_tag = 0;
 
-		buf += bix->sector_size;
+		buf += bix->interval;
 	}
 }
 
@@ -178,27 +178,27 @@ static int sd_dif_type3_verify(struct blk_integrity_exchg *bix, csum_fn *fn)
 {
 	void *buf = bix->data_buf;
 	struct sd_dif_tuple *sdt = bix->prot_buf;
-	sector_t sector = bix->sector;
+	sector_t seed = bix->seed;
 	unsigned int i;
 	__u16 csum;
 
-	for (i = 0 ; i < bix->data_size ; i += bix->sector_size, sdt++) {
+	for (i = 0 ; i < bix->data_size ; i += bix->interval, sdt++) {
 		/* Unwritten sectors */
 		if (sdt->app_tag == 0xffff && sdt->ref_tag == 0xffffffff)
 			return 0;
 
-		csum = fn(buf, bix->sector_size);
+		csum = fn(buf, bix->interval);
 
 		if (sdt->guard_tag != csum) {
 			printk(KERN_ERR "%s: guard tag error on sector %lu " \
 			       "(rcvd %04x, data %04x)\n", bix->disk_name,
-			       (unsigned long)sector,
+			       (unsigned long)seed,
 			       be16_to_cpu(sdt->guard_tag), be16_to_cpu(csum));
 			return -EIO;
 		}
 
-		buf += bix->sector_size;
-		sector++;
+		buf += bix->interval;
+		seed++;
 	}
 
 	return 0;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0bf5d79d9ba0..d364c42dbf17 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1464,9 +1464,9 @@ static inline uint64_t rq_io_start_time_ns(struct request *req)
 struct blk_integrity_exchg {
 	void			*prot_buf;
 	void			*data_buf;
-	sector_t		sector;
+	sector_t		seed;
 	unsigned int		data_size;
-	unsigned short		sector_size;
+	unsigned short		interval;
 	const char		*disk_name;
 };
 
@@ -1479,7 +1479,7 @@ struct blk_integrity {
 
 	unsigned short		flags;
 	unsigned short		tuple_size;
-	unsigned short		sector_size;
+	unsigned short		interval;
 	unsigned short		tag_size;
 
 	const char		*name;
-- 
cgit v1.2.3


From 1859308853b19c4daf4afaab910d3d52ac1ec2ff Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:20:01 -0400
Subject: block: Clean up the code used to generate and verify integrity
 metadata

Instead of the "operate" parameter we pass in a seed value and a pointer
to a function that can be used to process the integrity metadata. The
generation function is changed to have a return value to fit into this
scheme.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/bio-integrity.c  |  82 ++++++++++----------------------------
 drivers/scsi/sd_dif.c  | 106 ++++++++++++++++++++++++++-----------------------
 include/linux/bio.h    |  12 ++++++
 include/linux/blkdev.h |   9 ++---
 4 files changed, 94 insertions(+), 115 deletions(-)

(limited to 'include')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index cf40837e7710..fe4de033b34c 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -207,69 +207,43 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 }
 
 /**
- * bio_integrity_generate_verify - Generate/verify integrity metadata for a bio
+ * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
- * @operate:	operate number, 1 for generate, 0 for verify
+ * @proc_fn:	Pointer to the relevant processing function
  */
-static int bio_integrity_generate_verify(struct bio *bio, int operate)
+static int bio_integrity_process(struct bio *bio,
+				 integrity_processing_fn *proc_fn)
 {
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	struct blk_integrity_exchg bix;
+	struct blk_integrity_iter iter;
 	struct bio_vec *bv;
 	struct bio_integrity_payload *bip = bio_integrity(bio);
-	sector_t seed;
-	unsigned int intervals, ret = 0, i;
+	unsigned int i, ret = 0;
 	void *prot_buf = page_address(bip->bip_vec->bv_page) +
 		bip->bip_vec->bv_offset;
 
-	if (operate)
-		seed = bio->bi_iter.bi_sector;
-	else
-		seed = bip->bip_iter.bi_sector;
-
-	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
-	bix.interval = bi->interval;
+	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
+	iter.interval = bi->interval;
+	iter.seed = bip_get_seed(bip);
+	iter.prot_buf = prot_buf;
 
 	bio_for_each_segment_all(bv, bio, i) {
 		void *kaddr = kmap_atomic(bv->bv_page);
-		bix.data_buf = kaddr + bv->bv_offset;
-		bix.data_size = bv->bv_len;
-		bix.prot_buf = prot_buf;
-		bix.seed = seed;
-
-		if (operate)
-			bi->generate_fn(&bix);
-		else {
-			ret = bi->verify_fn(&bix);
-			if (ret) {
-				kunmap_atomic(kaddr);
-				return ret;
-			}
-		}
 
-		intervals = bv->bv_len / bi->interval;
-		seed += intervals;
-		prot_buf += intervals * bi->tuple_size;
+		iter.data_buf = kaddr + bv->bv_offset;
+		iter.data_size = bv->bv_len;
+
+		ret = proc_fn(&iter);
+		if (ret) {
+			kunmap_atomic(kaddr);
+			return ret;
+		}
 
 		kunmap_atomic(kaddr);
 	}
 	return ret;
 }
 
-/**
- * bio_integrity_generate - Generate integrity metadata for a bio
- * @bio:	bio to generate integrity metadata for
- *
- * Description: Generates integrity metadata for a bio by calling the
- * block device's generation callback function.  The bio must have a
- * bip attached with enough room to accommodate the generated
- * integrity metadata.
- */
-static void bio_integrity_generate(struct bio *bio)
-{
-	bio_integrity_generate_verify(bio, 1);
-}
-
 /**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
@@ -321,7 +295,7 @@ int bio_integrity_prep(struct bio *bio)
 
 	bip->bip_owns_buf = 1;
 	bip->bip_iter.bi_size = len;
-	bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
+	bip_set_seed(bip, bio->bi_iter.bi_sector);
 
 	/* Map it */
 	offset = offset_in_page(buf);
@@ -357,25 +331,12 @@ int bio_integrity_prep(struct bio *bio)
 
 	/* Auto-generate integrity metadata if this is a write */
 	if (bio_data_dir(bio) == WRITE)
-		bio_integrity_generate(bio);
+		bio_integrity_process(bio, bi->generate_fn);
 
 	return 0;
 }
 EXPORT_SYMBOL(bio_integrity_prep);
 
-/**
- * bio_integrity_verify - Verify integrity metadata for a bio
- * @bio:	bio to verify
- *
- * Description: This function is called to verify the integrity of a
- * bio.	 The data in the bio io_vec is compared to the integrity
- * metadata returned by the HBA.
- */
-static int bio_integrity_verify(struct bio *bio)
-{
-	return bio_integrity_generate_verify(bio, 0);
-}
-
 /**
  * bio_integrity_verify_fn - Integrity I/O completion worker
  * @work:	Work struct stored in bio to be verified
@@ -389,9 +350,10 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	struct bio_integrity_payload *bip =
 		container_of(work, struct bio_integrity_payload, bip_work);
 	struct bio *bio = bip->bip_bio;
+	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	int error;
 
-	error = bio_integrity_verify(bio);
+	error = bio_integrity_process(bio, bi->verify_fn);
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 1600270a46e5..801c41851a01 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -53,42 +53,44 @@ static __u16 sd_dif_ip_fn(void *data, unsigned int len)
  * Type 1 and Type 2 protection use the same format: 16 bit guard tag,
  * 16 bit app tag, 32 bit reference tag.
  */
-static void sd_dif_type1_generate(struct blk_integrity_exchg *bix, csum_fn *fn)
+static void sd_dif_type1_generate(struct blk_integrity_iter *iter, csum_fn *fn)
 {
-	void *buf = bix->data_buf;
-	struct sd_dif_tuple *sdt = bix->prot_buf;
-	sector_t seed = bix->seed;
+	void *buf = iter->data_buf;
+	struct sd_dif_tuple *sdt = iter->prot_buf;
+	sector_t seed = iter->seed;
 	unsigned int i;
 
-	for (i = 0 ; i < bix->data_size ; i += bix->interval, sdt++) {
-		sdt->guard_tag = fn(buf, bix->interval);
+	for (i = 0 ; i < iter->data_size ; i += iter->interval, sdt++) {
+		sdt->guard_tag = fn(buf, iter->interval);
 		sdt->ref_tag = cpu_to_be32(seed & 0xffffffff);
 		sdt->app_tag = 0;
 
-		buf += bix->interval;
+		buf += iter->interval;
 		seed++;
 	}
 }
 
-static void sd_dif_type1_generate_crc(struct blk_integrity_exchg *bix)
+static int sd_dif_type1_generate_crc(struct blk_integrity_iter *iter)
 {
-	sd_dif_type1_generate(bix, sd_dif_crc_fn);
+	sd_dif_type1_generate(iter, sd_dif_crc_fn);
+	return 0;
 }
 
-static void sd_dif_type1_generate_ip(struct blk_integrity_exchg *bix)
+static int sd_dif_type1_generate_ip(struct blk_integrity_iter *iter)
 {
-	sd_dif_type1_generate(bix, sd_dif_ip_fn);
+	sd_dif_type1_generate(iter, sd_dif_ip_fn);
+	return 0;
 }
 
-static int sd_dif_type1_verify(struct blk_integrity_exchg *bix, csum_fn *fn)
+static int sd_dif_type1_verify(struct blk_integrity_iter *iter, csum_fn *fn)
 {
-	void *buf = bix->data_buf;
-	struct sd_dif_tuple *sdt = bix->prot_buf;
-	sector_t seed = bix->seed;
+	void *buf = iter->data_buf;
+	struct sd_dif_tuple *sdt = iter->prot_buf;
+	sector_t seed = iter->seed;
 	unsigned int i;
 	__u16 csum;
 
-	for (i = 0 ; i < bix->data_size ; i += bix->interval, sdt++) {
+	for (i = 0 ; i < iter->data_size ; i += iter->interval, sdt++) {
 		/* Unwritten sectors */
 		if (sdt->app_tag == 0xffff)
 			return 0;
@@ -96,36 +98,36 @@ static int sd_dif_type1_verify(struct blk_integrity_exchg *bix, csum_fn *fn)
 		if (be32_to_cpu(sdt->ref_tag) != (seed & 0xffffffff)) {
 			printk(KERN_ERR
 			       "%s: ref tag error on sector %lu (rcvd %u)\n",
-			       bix->disk_name, (unsigned long)seed,
+			       iter->disk_name, (unsigned long)seed,
 			       be32_to_cpu(sdt->ref_tag));
 			return -EIO;
 		}
 
-		csum = fn(buf, bix->interval);
+		csum = fn(buf, iter->interval);
 
 		if (sdt->guard_tag != csum) {
 			printk(KERN_ERR "%s: guard tag error on sector %lu " \
-			       "(rcvd %04x, data %04x)\n", bix->disk_name,
+			       "(rcvd %04x, data %04x)\n", iter->disk_name,
 			       (unsigned long)seed,
 			       be16_to_cpu(sdt->guard_tag), be16_to_cpu(csum));
 			return -EIO;
 		}
 
-		buf += bix->interval;
+		buf += iter->interval;
 		seed++;
 	}
 
 	return 0;
 }
 
-static int sd_dif_type1_verify_crc(struct blk_integrity_exchg *bix)
+static int sd_dif_type1_verify_crc(struct blk_integrity_iter *iter)
 {
-	return sd_dif_type1_verify(bix, sd_dif_crc_fn);
+	return sd_dif_type1_verify(iter, sd_dif_crc_fn);
 }
 
-static int sd_dif_type1_verify_ip(struct blk_integrity_exchg *bix)
+static int sd_dif_type1_verify_ip(struct blk_integrity_iter *iter)
 {
-	return sd_dif_type1_verify(bix, sd_dif_ip_fn);
+	return sd_dif_type1_verify(iter, sd_dif_ip_fn);
 }
 
 static struct blk_integrity dif_type1_integrity_crc = {
@@ -149,69 +151,71 @@ static struct blk_integrity dif_type1_integrity_ip = {
  * Type 3 protection has a 16-bit guard tag and 16 + 32 bits of opaque
  * tag space.
  */
-static void sd_dif_type3_generate(struct blk_integrity_exchg *bix, csum_fn *fn)
+static void sd_dif_type3_generate(struct blk_integrity_iter *iter, csum_fn *fn)
 {
-	void *buf = bix->data_buf;
-	struct sd_dif_tuple *sdt = bix->prot_buf;
+	void *buf = iter->data_buf;
+	struct sd_dif_tuple *sdt = iter->prot_buf;
 	unsigned int i;
 
-	for (i = 0 ; i < bix->data_size ; i += bix->interval, sdt++) {
-		sdt->guard_tag = fn(buf, bix->interval);
+	for (i = 0 ; i < iter->data_size ; i += iter->interval, sdt++) {
+		sdt->guard_tag = fn(buf, iter->interval);
 		sdt->ref_tag = 0;
 		sdt->app_tag = 0;
 
-		buf += bix->interval;
+		buf += iter->interval;
 	}
 }
 
-static void sd_dif_type3_generate_crc(struct blk_integrity_exchg *bix)
+static int sd_dif_type3_generate_crc(struct blk_integrity_iter *iter)
 {
-	sd_dif_type3_generate(bix, sd_dif_crc_fn);
+	sd_dif_type3_generate(iter, sd_dif_crc_fn);
+	return 0;
 }
 
-static void sd_dif_type3_generate_ip(struct blk_integrity_exchg *bix)
+static int sd_dif_type3_generate_ip(struct blk_integrity_iter *iter)
 {
-	sd_dif_type3_generate(bix, sd_dif_ip_fn);
+	sd_dif_type3_generate(iter, sd_dif_ip_fn);
+	return 0;
 }
 
-static int sd_dif_type3_verify(struct blk_integrity_exchg *bix, csum_fn *fn)
+static int sd_dif_type3_verify(struct blk_integrity_iter *iter, csum_fn *fn)
 {
-	void *buf = bix->data_buf;
-	struct sd_dif_tuple *sdt = bix->prot_buf;
-	sector_t seed = bix->seed;
+	void *buf = iter->data_buf;
+	struct sd_dif_tuple *sdt = iter->prot_buf;
+	sector_t seed = iter->seed;
 	unsigned int i;
 	__u16 csum;
 
-	for (i = 0 ; i < bix->data_size ; i += bix->interval, sdt++) {
+	for (i = 0 ; i < iter->data_size ; i += iter->interval, sdt++) {
 		/* Unwritten sectors */
 		if (sdt->app_tag == 0xffff && sdt->ref_tag == 0xffffffff)
 			return 0;
 
-		csum = fn(buf, bix->interval);
+		csum = fn(buf, iter->interval);
 
 		if (sdt->guard_tag != csum) {
 			printk(KERN_ERR "%s: guard tag error on sector %lu " \
-			       "(rcvd %04x, data %04x)\n", bix->disk_name,
+			       "(rcvd %04x, data %04x)\n", iter->disk_name,
 			       (unsigned long)seed,
 			       be16_to_cpu(sdt->guard_tag), be16_to_cpu(csum));
 			return -EIO;
 		}
 
-		buf += bix->interval;
+		buf += iter->interval;
 		seed++;
 	}
 
 	return 0;
 }
 
-static int sd_dif_type3_verify_crc(struct blk_integrity_exchg *bix)
+static int sd_dif_type3_verify_crc(struct blk_integrity_iter *iter)
 {
-	return sd_dif_type3_verify(bix, sd_dif_crc_fn);
+	return sd_dif_type3_verify(iter, sd_dif_crc_fn);
 }
 
-static int sd_dif_type3_verify_ip(struct blk_integrity_exchg *bix)
+static int sd_dif_type3_verify_ip(struct blk_integrity_iter *iter)
 {
-	return sd_dif_type3_verify(bix, sd_dif_ip_fn);
+	return sd_dif_type3_verify(iter, sd_dif_ip_fn);
 }
 
 static struct blk_integrity dif_type3_integrity_crc = {
@@ -310,6 +314,7 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 	phys = hw_sector & 0xffffffff;
 
 	__rq_for_each_bio(bio, rq) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
 		struct bio_vec iv;
 		struct bvec_iter iter;
 		unsigned int j;
@@ -318,9 +323,9 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 		if (bio_flagged(bio, BIO_MAPPED_INTEGRITY))
 			break;
 
-		virt = bio_integrity(bio)->bip_iter.bi_sector & 0xffffffff;
+		virt = bip_get_seed(bip) & 0xffffffff;
 
-		bip_for_each_vec(iv, bio_integrity(bio), iter) {
+		bip_for_each_vec(iv, bip, iter) {
 			sdt = kmap_atomic(iv.bv_page)
 				+ iv.bv_offset;
 
@@ -366,12 +371,13 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 		phys >>= 3;
 
 	__rq_for_each_bio(bio, scmd->request) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
 		struct bio_vec iv;
 		struct bvec_iter iter;
 
-		virt = bio_integrity(bio)->bip_iter.bi_sector & 0xffffffff;
+		virt = bip_get_seed(bip) & 0xffffffff;
 
-		bip_for_each_vec(iv, bio_integrity(bio), iter) {
+		bip_for_each_vec(iv, bip, iter) {
 			sdt = kmap_atomic(iv.bv_page)
 				+ iv.bv_offset;
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 448d8c052cb7..3fd36660fd10 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -322,6 +322,18 @@ struct bio_integrity_payload {
 	struct bio_vec		*bip_vec;
 	struct bio_vec		bip_inline_vecs[0];/* embedded bvec array */
 };
+
+static inline sector_t bip_get_seed(struct bio_integrity_payload *bip)
+{
+	return bip->bip_iter.bi_sector;
+}
+
+static inline void bip_set_seed(struct bio_integrity_payload *bip,
+				sector_t seed)
+{
+	bip->bip_iter.bi_sector = seed;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 extern void bio_trim(struct bio *bio, int offset, int size);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d364c42dbf17..24c1e055b8a7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1461,7 +1461,7 @@ static inline uint64_t rq_io_start_time_ns(struct request *req)
 #define INTEGRITY_FLAG_READ	2	/* verify data integrity on read */
 #define INTEGRITY_FLAG_WRITE	4	/* generate data integrity on write */
 
-struct blk_integrity_exchg {
+struct blk_integrity_iter {
 	void			*prot_buf;
 	void			*data_buf;
 	sector_t		seed;
@@ -1470,12 +1470,11 @@ struct blk_integrity_exchg {
 	const char		*disk_name;
 };
 
-typedef void (integrity_gen_fn) (struct blk_integrity_exchg *);
-typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *);
+typedef int (integrity_processing_fn) (struct blk_integrity_iter *);
 
 struct blk_integrity {
-	integrity_gen_fn	*generate_fn;
-	integrity_vrfy_fn	*verify_fn;
+	integrity_processing_fn	*generate_fn;
+	integrity_processing_fn	*verify_fn;
 
 	unsigned short		flags;
 	unsigned short		tuple_size;
-- 
cgit v1.2.3


From 8288f496eb1b1905c425e92eaf1abbb29119217b Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:20:02 -0400
Subject: block: Add prefix to block integrity profile flags

Add a BLK_ prefix to the integrity profile flags. Also rename the flags
to be more consistent with the generate/verify terminology in the rest
of the integrity code.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/bio-integrity.c  |  4 ++--
 block/blk-integrity.c  | 43 ++++++++++++++++++++++---------------------
 include/linux/blkdev.h |  6 ++++--
 3 files changed, 28 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index fe4de033b34c..e64733bb29b6 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -173,11 +173,11 @@ bool bio_integrity_enabled(struct bio *bio)
 		return false;
 
 	if (bio_data_dir(bio) == READ && bi->verify_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_READ))
+	    (bi->flags & BLK_INTEGRITY_VERIFY))
 		return true;
 
 	if (bio_data_dir(bio) == WRITE && bi->generate_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_WRITE))
+	    (bi->flags & BLK_INTEGRITY_GENERATE))
 		return true;
 
 	return false;
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 3a83a7d08177..a7436ccc936b 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -269,42 +269,42 @@ static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page)
 		return sprintf(page, "0\n");
 }
 
-static ssize_t integrity_read_store(struct blk_integrity *bi,
-				    const char *page, size_t count)
+static ssize_t integrity_verify_store(struct blk_integrity *bi,
+				      const char *page, size_t count)
 {
 	char *p = (char *) page;
 	unsigned long val = simple_strtoul(p, &p, 10);
 
 	if (val)
-		bi->flags |= INTEGRITY_FLAG_READ;
+		bi->flags |= BLK_INTEGRITY_VERIFY;
 	else
-		bi->flags &= ~INTEGRITY_FLAG_READ;
+		bi->flags &= ~BLK_INTEGRITY_VERIFY;
 
 	return count;
 }
 
-static ssize_t integrity_read_show(struct blk_integrity *bi, char *page)
+static ssize_t integrity_verify_show(struct blk_integrity *bi, char *page)
 {
-	return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_READ) != 0);
+	return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_VERIFY) != 0);
 }
 
-static ssize_t integrity_write_store(struct blk_integrity *bi,
-				     const char *page, size_t count)
+static ssize_t integrity_generate_store(struct blk_integrity *bi,
+					const char *page, size_t count)
 {
 	char *p = (char *) page;
 	unsigned long val = simple_strtoul(p, &p, 10);
 
 	if (val)
-		bi->flags |= INTEGRITY_FLAG_WRITE;
+		bi->flags |= BLK_INTEGRITY_GENERATE;
 	else
-		bi->flags &= ~INTEGRITY_FLAG_WRITE;
+		bi->flags &= ~BLK_INTEGRITY_GENERATE;
 
 	return count;
 }
 
-static ssize_t integrity_write_show(struct blk_integrity *bi, char *page)
+static ssize_t integrity_generate_show(struct blk_integrity *bi, char *page)
 {
-	return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_WRITE) != 0);
+	return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_GENERATE) != 0);
 }
 
 static struct integrity_sysfs_entry integrity_format_entry = {
@@ -317,23 +317,23 @@ static struct integrity_sysfs_entry integrity_tag_size_entry = {
 	.show = integrity_tag_size_show,
 };
 
-static struct integrity_sysfs_entry integrity_read_entry = {
+static struct integrity_sysfs_entry integrity_verify_entry = {
 	.attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR },
-	.show = integrity_read_show,
-	.store = integrity_read_store,
+	.show = integrity_verify_show,
+	.store = integrity_verify_store,
 };
 
-static struct integrity_sysfs_entry integrity_write_entry = {
+static struct integrity_sysfs_entry integrity_generate_entry = {
 	.attr = { .name = "write_generate", .mode = S_IRUGO | S_IWUSR },
-	.show = integrity_write_show,
-	.store = integrity_write_store,
+	.show = integrity_generate_show,
+	.store = integrity_generate_store,
 };
 
 static struct attribute *integrity_attrs[] = {
 	&integrity_format_entry.attr,
 	&integrity_tag_size_entry.attr,
-	&integrity_read_entry.attr,
-	&integrity_write_entry.attr,
+	&integrity_verify_entry.attr,
+	&integrity_generate_entry.attr,
 	NULL,
 };
 
@@ -406,7 +406,7 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 
 		kobject_uevent(&bi->kobj, KOBJ_ADD);
 
-		bi->flags |= INTEGRITY_FLAG_READ | INTEGRITY_FLAG_WRITE;
+		bi->flags |= BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE;
 		bi->interval = queue_logical_block_size(disk->queue);
 		disk->integrity = bi;
 	} else
@@ -419,6 +419,7 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		bi->verify_fn = template->verify_fn;
 		bi->tuple_size = template->tuple_size;
 		bi->tag_size = template->tag_size;
+		bi->flags |= template->flags;
 	} else
 		bi->name = bi_unsupported_name;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 24c1e055b8a7..cf92eb031ae9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1458,8 +1458,10 @@ static inline uint64_t rq_io_start_time_ns(struct request *req)
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
-#define INTEGRITY_FLAG_READ	2	/* verify data integrity on read */
-#define INTEGRITY_FLAG_WRITE	4	/* generate data integrity on write */
+enum blk_integrity_flags {
+	BLK_INTEGRITY_VERIFY		= 1 << 0,
+	BLK_INTEGRITY_GENERATE		= 1 << 1,
+};
 
 struct blk_integrity_iter {
 	void			*prot_buf;
-- 
cgit v1.2.3


From 3aec2f41a8baeb70aa77556a4e4dcec7d9d70b4d Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:20:03 -0400
Subject: block: Add a disk flag to block integrity profile

So far we have relied on the app tag size to determine whether a disk
has been formatted with T10 protection information or not. However, not
all target devices provide application tag storage.

Add a flag to the block integrity profile that indicates whether the
disk has been formatted with protection information.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@dev.mellanox.co.il>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 Documentation/ABI/testing/sysfs-block |  8 ++++++++
 block/blk-integrity.c                 | 12 ++++++++++++
 drivers/scsi/sd_dif.c                 |  8 +++++++-
 include/linux/blkdev.h                |  1 +
 4 files changed, 28 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 279da08f7541..8df003963d99 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -53,6 +53,14 @@ Description:
 		512 bytes of data.
 
 
+What:		/sys/block/<disk>/integrity/device_is_integrity_capable
+Date:		July 2014
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Indicates whether a storage device is capable of storing
+		integrity metadata. Set if the device is T10 PI-capable.
+
+
 What:		/sys/block/<disk>/integrity/write_generate
 Date:		June 2008
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index a7436ccc936b..1c6ba442cd91 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -307,6 +307,12 @@ static ssize_t integrity_generate_show(struct blk_integrity *bi, char *page)
 	return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_GENERATE) != 0);
 }
 
+static ssize_t integrity_device_show(struct blk_integrity *bi, char *page)
+{
+	return sprintf(page, "%u\n",
+		       (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) != 0);
+}
+
 static struct integrity_sysfs_entry integrity_format_entry = {
 	.attr = { .name = "format", .mode = S_IRUGO },
 	.show = integrity_format_show,
@@ -329,11 +335,17 @@ static struct integrity_sysfs_entry integrity_generate_entry = {
 	.store = integrity_generate_store,
 };
 
+static struct integrity_sysfs_entry integrity_device_entry = {
+	.attr = { .name = "device_is_integrity_capable", .mode = S_IRUGO },
+	.show = integrity_device_show,
+};
+
 static struct attribute *integrity_attrs[] = {
 	&integrity_format_entry.attr,
 	&integrity_tag_size_entry.attr,
 	&integrity_verify_entry.attr,
 	&integrity_generate_entry.attr,
+	&integrity_device_entry.attr,
 	NULL,
 };
 
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 801c41851a01..1e971c6f8c2b 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -270,7 +270,13 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
 		  "Enabling DIX %s protection\n", disk->integrity->name);
 
 	/* Signal to block layer that we support sector tagging */
-	if (dif && type && sdkp->ATO) {
+	if (dif && type) {
+
+		disk->integrity->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+
+		if (!sdkp)
+			return;
+
 		if (type == SD_DIF_TYPE3_PROTECTION)
 			disk->integrity->tag_size = sizeof(u16) + sizeof(u32);
 		else
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index cf92eb031ae9..4600fc63e3fc 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1461,6 +1461,7 @@ static inline uint64_t rq_io_start_time_ns(struct request *req)
 enum blk_integrity_flags {
 	BLK_INTEGRITY_VERIFY		= 1 << 0,
 	BLK_INTEGRITY_GENERATE		= 1 << 1,
+	BLK_INTEGRITY_DEVICE_CAPABLE	= 1 << 2,
 };
 
 struct blk_integrity_iter {
-- 
cgit v1.2.3


From b1f01388574c9329922f760fc2a7335c2d14b08b Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:20:04 -0400
Subject: block: Relocate bio integrity flags

Move flags affecting the integrity code out of the bio bi_flags and into
the block integrity payload.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/bio-integrity.c     | 4 ++--
 drivers/scsi/sd_dif.c     | 4 ++--
 include/linux/bio.h       | 9 ++++++++-
 include/linux/blk_types.h | 6 ++----
 4 files changed, 14 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index e64733bb29b6..26aa901b961f 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -100,7 +100,7 @@ void bio_integrity_free(struct bio *bio)
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_set *bs = bio->bi_pool;
 
-	if (bip->bip_owns_buf)
+	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
 		kfree(page_address(bip->bip_vec->bv_page) +
 		      bip->bip_vec->bv_offset);
 
@@ -293,7 +293,7 @@ int bio_integrity_prep(struct bio *bio)
 		return -EIO;
 	}
 
-	bip->bip_owns_buf = 1;
+	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
 	bip->bip_iter.bi_size = len;
 	bip_set_seed(bip, bio->bi_iter.bi_sector);
 
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 1e971c6f8c2b..4ce636fdc15f 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -326,7 +326,7 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 		unsigned int j;
 
 		/* Already remapped? */
-		if (bio_flagged(bio, BIO_MAPPED_INTEGRITY))
+		if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
 			break;
 
 		virt = bip_get_seed(bip) & 0xffffffff;
@@ -347,7 +347,7 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 			kunmap_atomic(sdt);
 		}
 
-		bio->bi_flags |= (1 << BIO_MAPPED_INTEGRITY);
+		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
 	}
 }
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 3fd36660fd10..b508cf69206d 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -315,7 +315,7 @@ struct bio_integrity_payload {
 	unsigned short		bip_slab;	/* slab the bip came from */
 	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
 	unsigned short		bip_max_vcnt;	/* integrity bio_vec slots */
-	unsigned		bip_owns_buf:1;	/* should free bip_buf */
+	unsigned short		bip_flags;	/* control flags */
 
 	struct work_struct	bip_work;	/* I/O completion */
 
@@ -323,6 +323,13 @@ struct bio_integrity_payload {
 	struct bio_vec		bip_inline_vecs[0];/* embedded bvec array */
 };
 
+enum bip_flags {
+	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
+	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
+	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
+	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
+};
+
 static inline sector_t bip_get_seed(struct bio_integrity_payload *bip)
 {
 	return bip->bip_iter.bi_sector;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 6a5d2f2de1b9..38bc008e4503 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -120,10 +120,8 @@ struct bio {
 #define BIO_USER_MAPPED 6	/* contains user pages */
 #define BIO_EOPNOTSUPP	7	/* not supported */
 #define BIO_NULL_MAPPED 8	/* contains invalid user pages */
-#define BIO_FS_INTEGRITY 9	/* fs owns integrity data, not block layer */
-#define BIO_QUIET	10	/* Make BIO Quiet */
-#define BIO_MAPPED_INTEGRITY 11/* integrity metadata has been remapped */
-#define BIO_SNAP_STABLE	12	/* bio data must be snapshotted during write */
+#define BIO_QUIET	9	/* Make BIO Quiet */
+#define BIO_SNAP_STABLE	10	/* bio data must be snapshotted during write */
 
 /*
  * Flags starting here get preserved by bio_reset() - this includes
-- 
cgit v1.2.3


From aae7df50190a640e51bfe11c93f94741ac82ff0b Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:20:05 -0400
Subject: block: Integrity checksum flag

Make the choice of checksum a per-I/O property by introducing a flag
that can be inspected by the SCSI layer. There are several reasons for
this:

 1. It allows us to switch choice of checksum without unloading and
    reloading the HBA driver.

 2. During error recovery we need to be able to tell the HBA that
    checksums read from disk should not be verified and converted to IP
    checksums.

 3. For error injection purposes we need to be able to write a bad guard
    tag to storage. Since the storage device only supports T10 CRC we
    need to be able to disable IP checksum conversion on the HBA.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/bio-integrity.c  | 3 +++
 drivers/scsi/sd_dif.c  | 6 ++++--
 include/linux/bio.h    | 1 +
 include/linux/blkdev.h | 1 +
 4 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 26aa901b961f..8e0548484dd3 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -297,6 +297,9 @@ int bio_integrity_prep(struct bio *bio)
 	bip->bip_iter.bi_size = len;
 	bip_set_seed(bip, bio->bi_iter.bi_sector);
 
+	if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM)
+		bip->bip_flags |= BIP_IP_CHECKSUM;
+
 	/* Map it */
 	offset = offset_in_page(buf);
 	for (i = 0 ; i < nr_pages ; i++) {
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 4ce636fdc15f..2198abee619e 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -255,12 +255,14 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
 		return;
 
 	/* Enable DMA of protection information */
-	if (scsi_host_get_guard(sdkp->device->host) & SHOST_DIX_GUARD_IP)
+	if (scsi_host_get_guard(sdkp->device->host) & SHOST_DIX_GUARD_IP) {
 		if (type == SD_DIF_TYPE3_PROTECTION)
 			blk_integrity_register(disk, &dif_type3_integrity_ip);
 		else
 			blk_integrity_register(disk, &dif_type1_integrity_ip);
-	else
+
+		disk->integrity->flags |= BLK_INTEGRITY_IP_CHECKSUM;
+	} else
 		if (type == SD_DIF_TYPE3_PROTECTION)
 			blk_integrity_register(disk, &dif_type3_integrity_crc);
 		else
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b508cf69206d..14bff3fe56d4 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -328,6 +328,7 @@ enum bip_flags {
 	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
 	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
 	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
+	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
 };
 
 static inline sector_t bip_get_seed(struct bio_integrity_payload *bip)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4600fc63e3fc..773df190a4ee 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1462,6 +1462,7 @@ enum blk_integrity_flags {
 	BLK_INTEGRITY_VERIFY		= 1 << 0,
 	BLK_INTEGRITY_GENERATE		= 1 << 1,
 	BLK_INTEGRITY_DEVICE_CAPABLE	= 1 << 2,
+	BLK_INTEGRITY_IP_CHECKSUM	= 1 << 3,
 };
 
 struct blk_integrity_iter {
-- 
cgit v1.2.3


From 4eaf99beadcefbf126fa05e66fb40fca999e09fd Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:20:06 -0400
Subject: block: Don't merge requests if integrity flags differ

We'd occasionally merge requests with conflicting integrity flags.
Introduce a merge helper which checks that the requests have compatible
integrity payloads.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-integrity.c  | 36 ++++++++++++++++++++++++++----------
 block/blk-merge.c      |  6 +++---
 include/linux/blkdev.h | 20 ++++++++++----------
 3 files changed, 39 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 1c6ba442cd91..79ffb4855af0 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -186,37 +186,53 @@ int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
 }
 EXPORT_SYMBOL(blk_integrity_compare);
 
-int blk_integrity_merge_rq(struct request_queue *q, struct request *req,
-			   struct request *next)
+bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
+			    struct request *next)
 {
-	if (blk_integrity_rq(req) != blk_integrity_rq(next))
-		return -1;
+	if (blk_integrity_rq(req) == 0 && blk_integrity_rq(next) == 0)
+		return true;
+
+	if (blk_integrity_rq(req) == 0 || blk_integrity_rq(next) == 0)
+		return false;
+
+	if (bio_integrity(req->bio)->bip_flags !=
+	    bio_integrity(next->bio)->bip_flags)
+		return false;
 
 	if (req->nr_integrity_segments + next->nr_integrity_segments >
 	    q->limits.max_integrity_segments)
-		return -1;
+		return false;
 
-	return 0;
+	return true;
 }
 EXPORT_SYMBOL(blk_integrity_merge_rq);
 
-int blk_integrity_merge_bio(struct request_queue *q, struct request *req,
-			    struct bio *bio)
+bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
+			     struct bio *bio)
 {
 	int nr_integrity_segs;
 	struct bio *next = bio->bi_next;
 
+	if (blk_integrity_rq(req) == 0 && bio_integrity(bio) == NULL)
+		return true;
+
+	if (blk_integrity_rq(req) == 0 || bio_integrity(bio) == NULL)
+		return false;
+
+	if (bio_integrity(req->bio)->bip_flags != bio_integrity(bio)->bip_flags)
+		return false;
+
 	bio->bi_next = NULL;
 	nr_integrity_segs = blk_rq_count_integrity_sg(q, bio);
 	bio->bi_next = next;
 
 	if (req->nr_integrity_segments + nr_integrity_segs >
 	    q->limits.max_integrity_segments)
-		return -1;
+		return false;
 
 	req->nr_integrity_segments += nr_integrity_segs;
 
-	return 0;
+	return true;
 }
 EXPORT_SYMBOL(blk_integrity_merge_bio);
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 77881798f793..f71bad35b4cc 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -313,7 +313,7 @@ static inline int ll_new_hw_segment(struct request_queue *q,
 	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q))
 		goto no_merge;
 
-	if (bio_integrity(bio) && blk_integrity_merge_bio(q, req, bio))
+	if (blk_integrity_merge_bio(q, req, bio) == false)
 		goto no_merge;
 
 	/*
@@ -410,7 +410,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	if (total_phys_segments > queue_max_segments(q))
 		return 0;
 
-	if (blk_integrity_rq(req) && blk_integrity_merge_rq(q, req, next))
+	if (blk_integrity_merge_rq(q, req, next) == false)
 		return 0;
 
 	/* Merge is OK... */
@@ -590,7 +590,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 		return false;
 
 	/* only merge integrity protected bio into ditto rq */
-	if (bio_integrity(bio) != blk_integrity_rq(rq))
+	if (blk_integrity_merge_bio(rq->q, rq, bio) == false)
 		return false;
 
 	/* must be using the same buffer */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 773df190a4ee..038b40f84c7a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1497,10 +1497,10 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
 extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
 				   struct scatterlist *);
 extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-extern int blk_integrity_merge_rq(struct request_queue *, struct request *,
-				  struct request *);
-extern int blk_integrity_merge_bio(struct request_queue *, struct request *,
-				   struct bio *);
+extern bool blk_integrity_merge_rq(struct request_queue *, struct request *,
+				   struct request *);
+extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
+				    struct bio *);
 
 static inline
 struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
@@ -1580,15 +1580,15 @@ static inline unsigned short queue_max_integrity_segments(struct request_queue *
 {
 	return 0;
 }
-static inline int blk_integrity_merge_rq(struct request_queue *rq,
-					 struct request *r1,
-					 struct request *r2)
+static inline bool blk_integrity_merge_rq(struct request_queue *rq,
+					  struct request *r1,
+					  struct request *r2)
 {
 	return 0;
 }
-static inline int blk_integrity_merge_bio(struct request_queue *rq,
-					  struct request *r,
-					  struct bio *b)
+static inline bool blk_integrity_merge_bio(struct request_queue *rq,
+					   struct request *r,
+					   struct bio *b)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From 2341c2f8c33196d02cf5a721746eea4e3c06674a Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:20:07 -0400
Subject: block: Add T10 Protection Information functions

The T10 Protection Information format is also used by some devices that
do not go through the SCSI layer (virtual block devices, NVMe). Relocate
the relevant functions to a block layer library that can be used without
involving SCSI.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/Kconfig              |   1 +
 block/Makefile             |   4 +-
 block/t10-pi.c             | 197 ++++++++++++++++++++++++++++++++++++
 drivers/scsi/Kconfig       |   1 -
 drivers/scsi/sd_dif.c      | 241 ++++-----------------------------------------
 include/linux/crc-t10dif.h |   5 +-
 include/linux/t10-pi.h     |  22 +++++
 7 files changed, 245 insertions(+), 226 deletions(-)
 create mode 100644 block/t10-pi.c
 create mode 100644 include/linux/t10-pi.h

(limited to 'include')

diff --git a/block/Kconfig b/block/Kconfig
index 2429515c05c2..161491d0a879 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -77,6 +77,7 @@ config BLK_DEV_BSGLIB
 
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
+	select CRC_T10DIF if BLK_DEV_INTEGRITY
 	---help---
 	Some storage devices allow extra information to be
 	stored/retrieved to help protect the data.  The block layer
diff --git a/block/Makefile b/block/Makefile
index a2ce6ac935ec..00ecc97629db 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -20,6 +20,6 @@ obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
+
diff --git a/block/t10-pi.c b/block/t10-pi.c
new file mode 100644
index 000000000000..24d6e9715318
--- /dev/null
+++ b/block/t10-pi.c
@@ -0,0 +1,197 @@
+/*
+ * t10_pi.c - Functions for generating and verifying T10 Protection
+ *	      Information.
+ *
+ * Copyright (C) 2007, 2008, 2014 Oracle Corporation
+ * Written by: Martin K. Petersen <martin.petersen@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
+ * USA.
+ *
+ */
+
+#include <linux/t10-pi.h>
+#include <linux/blkdev.h>
+#include <linux/crc-t10dif.h>
+#include <net/checksum.h>
+
+typedef __be16 (csum_fn) (void *, unsigned int);
+
+static const __be16 APP_ESCAPE = (__force __be16) 0xffff;
+static const __be32 REF_ESCAPE = (__force __be32) 0xffffffff;
+
+static __be16 t10_pi_crc_fn(void *data, unsigned int len)
+{
+	return cpu_to_be16(crc_t10dif(data, len));
+}
+
+static __be16 t10_pi_ip_fn(void *data, unsigned int len)
+{
+	return (__force __be16)ip_compute_csum(data, len);
+}
+
+/*
+ * Type 1 and Type 2 protection use the same format: 16 bit guard tag,
+ * 16 bit app tag, 32 bit reference tag. Type 3 does not define the ref
+ * tag.
+ */
+static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn,
+			   unsigned int type)
+{
+	unsigned int i;
+
+	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
+		struct t10_pi_tuple *pi = iter->prot_buf;
+
+		pi->guard_tag = fn(iter->data_buf, iter->interval);
+		pi->app_tag = 0;
+
+		if (type == 1)
+			pi->ref_tag = cpu_to_be32(lower_32_bits(iter->seed));
+		else
+			pi->ref_tag = 0;
+
+		iter->data_buf += iter->interval;
+		iter->prot_buf += sizeof(struct t10_pi_tuple);
+		iter->seed++;
+	}
+
+	return 0;
+}
+
+static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
+				unsigned int type)
+{
+	unsigned int i;
+
+	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
+		struct t10_pi_tuple *pi = iter->prot_buf;
+		__be16 csum;
+
+		switch (type) {
+		case 1:
+		case 2:
+			if (pi->app_tag == APP_ESCAPE)
+				goto next;
+
+			if (be32_to_cpu(pi->ref_tag) !=
+			    lower_32_bits(iter->seed)) {
+				pr_err("%s: ref tag error at location %llu " \
+				       "(rcvd %u)\n", iter->disk_name,
+				       (unsigned long long)
+				       iter->seed, be32_to_cpu(pi->ref_tag));
+				return -EILSEQ;
+			}
+			break;
+		case 3:
+			if (pi->app_tag == APP_ESCAPE &&
+			    pi->ref_tag == REF_ESCAPE)
+				goto next;
+			break;
+		}
+
+		csum = fn(iter->data_buf, iter->interval);
+
+		if (pi->guard_tag != csum) {
+			pr_err("%s: guard tag error at sector %llu " \
+			       "(rcvd %04x, want %04x)\n", iter->disk_name,
+			       (unsigned long long)iter->seed,
+			       be16_to_cpu(pi->guard_tag), be16_to_cpu(csum));
+			return -EILSEQ;
+		}
+
+next:
+		iter->data_buf += iter->interval;
+		iter->prot_buf += sizeof(struct t10_pi_tuple);
+		iter->seed++;
+	}
+
+	return 0;
+}
+
+static int t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_crc_fn, 1);
+}
+
+static int t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_ip_fn, 1);
+}
+
+static int t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_crc_fn, 1);
+}
+
+static int t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_ip_fn, 1);
+}
+
+static int t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_crc_fn, 3);
+}
+
+static int t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_ip_fn, 3);
+}
+
+static int t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_crc_fn, 3);
+}
+
+static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_ip_fn, 3);
+}
+
+struct blk_integrity t10_pi_type1_crc = {
+	.name			= "T10-DIF-TYPE1-CRC",
+	.generate_fn		= t10_pi_type1_generate_crc,
+	.verify_fn		= t10_pi_type1_verify_crc,
+	.tuple_size		= sizeof(struct t10_pi_tuple),
+	.tag_size		= 0,
+};
+EXPORT_SYMBOL(t10_pi_type1_crc);
+
+struct blk_integrity t10_pi_type1_ip = {
+	.name			= "T10-DIF-TYPE1-IP",
+	.generate_fn		= t10_pi_type1_generate_ip,
+	.verify_fn		= t10_pi_type1_verify_ip,
+	.tuple_size		= sizeof(struct t10_pi_tuple),
+	.tag_size		= 0,
+};
+EXPORT_SYMBOL(t10_pi_type1_ip);
+
+struct blk_integrity t10_pi_type3_crc = {
+	.name			= "T10-DIF-TYPE3-CRC",
+	.generate_fn		= t10_pi_type3_generate_crc,
+	.verify_fn		= t10_pi_type3_verify_crc,
+	.tuple_size		= sizeof(struct t10_pi_tuple),
+	.tag_size		= 0,
+};
+EXPORT_SYMBOL(t10_pi_type3_crc);
+
+struct blk_integrity t10_pi_type3_ip = {
+	.name			= "T10-DIF-TYPE3-IP",
+	.generate_fn		= t10_pi_type3_generate_ip,
+	.verify_fn		= t10_pi_type3_verify_ip,
+	.tuple_size		= sizeof(struct t10_pi_tuple),
+	.tag_size		= 0,
+};
+EXPORT_SYMBOL(t10_pi_type3_ip);
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 18a3358eb1d4..9ece13f922a6 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -62,7 +62,6 @@ comment "SCSI support type (disk, tape, CD-ROM)"
 config BLK_DEV_SD
 	tristate "SCSI disk support"
 	depends on SCSI
-	select CRC_T10DIF if BLK_DEV_INTEGRITY
 	---help---
 	  If you want to use SCSI hard disks, Fibre Channel disks,
 	  Serial ATA (SATA) or Parallel ATA (PATA) hard disks,
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 2198abee619e..b7eaeadc18f9 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -21,7 +21,7 @@
  */
 
 #include <linux/blkdev.h>
-#include <linux/crc-t10dif.h>
+#include <linux/t10-pi.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -33,207 +33,8 @@
 #include <scsi/scsi_ioctl.h>
 #include <scsi/scsicam.h>
 
-#include <net/checksum.h>
-
 #include "sd.h"
 
-typedef __u16 (csum_fn) (void *, unsigned int);
-
-static __u16 sd_dif_crc_fn(void *data, unsigned int len)
-{
-	return cpu_to_be16(crc_t10dif(data, len));
-}
-
-static __u16 sd_dif_ip_fn(void *data, unsigned int len)
-{
-	return ip_compute_csum(data, len);
-}
-
-/*
- * Type 1 and Type 2 protection use the same format: 16 bit guard tag,
- * 16 bit app tag, 32 bit reference tag.
- */
-static void sd_dif_type1_generate(struct blk_integrity_iter *iter, csum_fn *fn)
-{
-	void *buf = iter->data_buf;
-	struct sd_dif_tuple *sdt = iter->prot_buf;
-	sector_t seed = iter->seed;
-	unsigned int i;
-
-	for (i = 0 ; i < iter->data_size ; i += iter->interval, sdt++) {
-		sdt->guard_tag = fn(buf, iter->interval);
-		sdt->ref_tag = cpu_to_be32(seed & 0xffffffff);
-		sdt->app_tag = 0;
-
-		buf += iter->interval;
-		seed++;
-	}
-}
-
-static int sd_dif_type1_generate_crc(struct blk_integrity_iter *iter)
-{
-	sd_dif_type1_generate(iter, sd_dif_crc_fn);
-	return 0;
-}
-
-static int sd_dif_type1_generate_ip(struct blk_integrity_iter *iter)
-{
-	sd_dif_type1_generate(iter, sd_dif_ip_fn);
-	return 0;
-}
-
-static int sd_dif_type1_verify(struct blk_integrity_iter *iter, csum_fn *fn)
-{
-	void *buf = iter->data_buf;
-	struct sd_dif_tuple *sdt = iter->prot_buf;
-	sector_t seed = iter->seed;
-	unsigned int i;
-	__u16 csum;
-
-	for (i = 0 ; i < iter->data_size ; i += iter->interval, sdt++) {
-		/* Unwritten sectors */
-		if (sdt->app_tag == 0xffff)
-			return 0;
-
-		if (be32_to_cpu(sdt->ref_tag) != (seed & 0xffffffff)) {
-			printk(KERN_ERR
-			       "%s: ref tag error on sector %lu (rcvd %u)\n",
-			       iter->disk_name, (unsigned long)seed,
-			       be32_to_cpu(sdt->ref_tag));
-			return -EIO;
-		}
-
-		csum = fn(buf, iter->interval);
-
-		if (sdt->guard_tag != csum) {
-			printk(KERN_ERR "%s: guard tag error on sector %lu " \
-			       "(rcvd %04x, data %04x)\n", iter->disk_name,
-			       (unsigned long)seed,
-			       be16_to_cpu(sdt->guard_tag), be16_to_cpu(csum));
-			return -EIO;
-		}
-
-		buf += iter->interval;
-		seed++;
-	}
-
-	return 0;
-}
-
-static int sd_dif_type1_verify_crc(struct blk_integrity_iter *iter)
-{
-	return sd_dif_type1_verify(iter, sd_dif_crc_fn);
-}
-
-static int sd_dif_type1_verify_ip(struct blk_integrity_iter *iter)
-{
-	return sd_dif_type1_verify(iter, sd_dif_ip_fn);
-}
-
-static struct blk_integrity dif_type1_integrity_crc = {
-	.name			= "T10-DIF-TYPE1-CRC",
-	.generate_fn		= sd_dif_type1_generate_crc,
-	.verify_fn		= sd_dif_type1_verify_crc,
-	.tuple_size		= sizeof(struct sd_dif_tuple),
-	.tag_size		= 0,
-};
-
-static struct blk_integrity dif_type1_integrity_ip = {
-	.name			= "T10-DIF-TYPE1-IP",
-	.generate_fn		= sd_dif_type1_generate_ip,
-	.verify_fn		= sd_dif_type1_verify_ip,
-	.tuple_size		= sizeof(struct sd_dif_tuple),
-	.tag_size		= 0,
-};
-
-
-/*
- * Type 3 protection has a 16-bit guard tag and 16 + 32 bits of opaque
- * tag space.
- */
-static void sd_dif_type3_generate(struct blk_integrity_iter *iter, csum_fn *fn)
-{
-	void *buf = iter->data_buf;
-	struct sd_dif_tuple *sdt = iter->prot_buf;
-	unsigned int i;
-
-	for (i = 0 ; i < iter->data_size ; i += iter->interval, sdt++) {
-		sdt->guard_tag = fn(buf, iter->interval);
-		sdt->ref_tag = 0;
-		sdt->app_tag = 0;
-
-		buf += iter->interval;
-	}
-}
-
-static int sd_dif_type3_generate_crc(struct blk_integrity_iter *iter)
-{
-	sd_dif_type3_generate(iter, sd_dif_crc_fn);
-	return 0;
-}
-
-static int sd_dif_type3_generate_ip(struct blk_integrity_iter *iter)
-{
-	sd_dif_type3_generate(iter, sd_dif_ip_fn);
-	return 0;
-}
-
-static int sd_dif_type3_verify(struct blk_integrity_iter *iter, csum_fn *fn)
-{
-	void *buf = iter->data_buf;
-	struct sd_dif_tuple *sdt = iter->prot_buf;
-	sector_t seed = iter->seed;
-	unsigned int i;
-	__u16 csum;
-
-	for (i = 0 ; i < iter->data_size ; i += iter->interval, sdt++) {
-		/* Unwritten sectors */
-		if (sdt->app_tag == 0xffff && sdt->ref_tag == 0xffffffff)
-			return 0;
-
-		csum = fn(buf, iter->interval);
-
-		if (sdt->guard_tag != csum) {
-			printk(KERN_ERR "%s: guard tag error on sector %lu " \
-			       "(rcvd %04x, data %04x)\n", iter->disk_name,
-			       (unsigned long)seed,
-			       be16_to_cpu(sdt->guard_tag), be16_to_cpu(csum));
-			return -EIO;
-		}
-
-		buf += iter->interval;
-		seed++;
-	}
-
-	return 0;
-}
-
-static int sd_dif_type3_verify_crc(struct blk_integrity_iter *iter)
-{
-	return sd_dif_type3_verify(iter, sd_dif_crc_fn);
-}
-
-static int sd_dif_type3_verify_ip(struct blk_integrity_iter *iter)
-{
-	return sd_dif_type3_verify(iter, sd_dif_ip_fn);
-}
-
-static struct blk_integrity dif_type3_integrity_crc = {
-	.name			= "T10-DIF-TYPE3-CRC",
-	.generate_fn		= sd_dif_type3_generate_crc,
-	.verify_fn		= sd_dif_type3_verify_crc,
-	.tuple_size		= sizeof(struct sd_dif_tuple),
-	.tag_size		= 0,
-};
-
-static struct blk_integrity dif_type3_integrity_ip = {
-	.name			= "T10-DIF-TYPE3-IP",
-	.generate_fn		= sd_dif_type3_generate_ip,
-	.verify_fn		= sd_dif_type3_verify_ip,
-	.tuple_size		= sizeof(struct sd_dif_tuple),
-	.tag_size		= 0,
-};
-
 /*
  * Configure exchange of protection information between OS and HBA.
  */
@@ -257,16 +58,16 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
 	/* Enable DMA of protection information */
 	if (scsi_host_get_guard(sdkp->device->host) & SHOST_DIX_GUARD_IP) {
 		if (type == SD_DIF_TYPE3_PROTECTION)
-			blk_integrity_register(disk, &dif_type3_integrity_ip);
+			blk_integrity_register(disk, &t10_pi_type3_ip);
 		else
-			blk_integrity_register(disk, &dif_type1_integrity_ip);
+			blk_integrity_register(disk, &t10_pi_type1_ip);
 
 		disk->integrity->flags |= BLK_INTEGRITY_IP_CHECKSUM;
 	} else
 		if (type == SD_DIF_TYPE3_PROTECTION)
-			blk_integrity_register(disk, &dif_type3_integrity_crc);
+			blk_integrity_register(disk, &t10_pi_type3_crc);
 		else
-			blk_integrity_register(disk, &dif_type1_integrity_crc);
+			blk_integrity_register(disk, &t10_pi_type1_crc);
 
 	sd_printk(KERN_NOTICE, sdkp,
 		  "Enabling DIX %s protection\n", disk->integrity->name);
@@ -308,10 +109,10 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
 void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 		    unsigned int sector_sz)
 {
-	const int tuple_sz = sizeof(struct sd_dif_tuple);
+	const int tuple_sz = sizeof(struct t10_pi_tuple);
 	struct bio *bio;
 	struct scsi_disk *sdkp;
-	struct sd_dif_tuple *sdt;
+	struct t10_pi_tuple *pi;
 	u32 phys, virt;
 
 	sdkp = rq->bio->bi_bdev->bd_disk->private_data;
@@ -334,19 +135,18 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 		virt = bip_get_seed(bip) & 0xffffffff;
 
 		bip_for_each_vec(iv, bip, iter) {
-			sdt = kmap_atomic(iv.bv_page)
-				+ iv.bv_offset;
+			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
 
-			for (j = 0; j < iv.bv_len; j += tuple_sz, sdt++) {
+			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
 
-				if (be32_to_cpu(sdt->ref_tag) == virt)
-					sdt->ref_tag = cpu_to_be32(phys);
+				if (be32_to_cpu(pi->ref_tag) == virt)
+					pi->ref_tag = cpu_to_be32(phys);
 
 				virt++;
 				phys++;
 			}
 
-			kunmap_atomic(sdt);
+			kunmap_atomic(pi);
 		}
 
 		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
@@ -359,10 +159,10 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
  */
 void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 {
-	const int tuple_sz = sizeof(struct sd_dif_tuple);
+	const int tuple_sz = sizeof(struct t10_pi_tuple);
 	struct scsi_disk *sdkp;
 	struct bio *bio;
-	struct sd_dif_tuple *sdt;
+	struct t10_pi_tuple *pi;
 	unsigned int j, sectors, sector_sz;
 	u32 phys, virt;
 
@@ -386,25 +186,24 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 		virt = bip_get_seed(bip) & 0xffffffff;
 
 		bip_for_each_vec(iv, bip, iter) {
-			sdt = kmap_atomic(iv.bv_page)
-				+ iv.bv_offset;
+			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
 
-			for (j = 0; j < iv.bv_len; j += tuple_sz, sdt++) {
+			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
 
 				if (sectors == 0) {
-					kunmap_atomic(sdt);
+					kunmap_atomic(pi);
 					return;
 				}
 
-				if (be32_to_cpu(sdt->ref_tag) == phys)
-					sdt->ref_tag = cpu_to_be32(virt);
+				if (be32_to_cpu(pi->ref_tag) == phys)
+					pi->ref_tag = cpu_to_be32(virt);
 
 				virt++;
 				phys++;
 				sectors--;
 			}
 
-			kunmap_atomic(sdt);
+			kunmap_atomic(pi);
 		}
 	}
 }
diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h
index b3cb71f0d3b0..cf53d0773ce3 100644
--- a/include/linux/crc-t10dif.h
+++ b/include/linux/crc-t10dif.h
@@ -6,7 +6,8 @@
 #define CRC_T10DIF_DIGEST_SIZE 2
 #define CRC_T10DIF_BLOCK_SIZE 1
 
-__u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len);
-__u16 crc_t10dif(unsigned char const *, size_t);
+extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer,
+				size_t len);
+extern __u16 crc_t10dif(unsigned char const *, size_t);
 
 #endif
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
new file mode 100644
index 000000000000..6a8b9942632d
--- /dev/null
+++ b/include/linux/t10-pi.h
@@ -0,0 +1,22 @@
+#ifndef _LINUX_T10_PI_H
+#define _LINUX_T10_PI_H
+
+#include <linux/types.h>
+#include <linux/blkdev.h>
+
+/*
+ * T10 Protection Information tuple.
+ */
+struct t10_pi_tuple {
+	__be16 guard_tag;	/* Checksum */
+	__be16 app_tag;		/* Opaque storage */
+	__be32 ref_tag;		/* Target LBA or indirect LBA */
+};
+
+
+extern struct blk_integrity t10_pi_type1_crc;
+extern struct blk_integrity t10_pi_type1_ip;
+extern struct blk_integrity t10_pi_type3_crc;
+extern struct blk_integrity t10_pi_type3_ip;
+
+#endif
-- 
cgit v1.2.3


From 4d742e6230b5ff157422d91d6ae8d2fc1303eb28 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Fri, 5 Sep 2014 11:28:12 +0200
Subject: clk: rockchip: add binding id for ARMCLK

Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Doug Anderson <dianders@chromium.org>
---
 include/dt-bindings/clock/rk3188-cru-common.h | 1 +
 include/dt-bindings/clock/rk3288-cru.h        | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/rk3188-cru-common.h b/include/dt-bindings/clock/rk3188-cru-common.h
index 750ee60e75fb..6a370503c954 100644
--- a/include/dt-bindings/clock/rk3188-cru-common.h
+++ b/include/dt-bindings/clock/rk3188-cru-common.h
@@ -20,6 +20,7 @@
 #define PLL_GPLL		4
 #define CORE_PERI		5
 #define CORE_L2C		6
+#define ARMCLK			7
 
 /* sclk gates (special clocks) */
 #define SCLK_UART0		64
diff --git a/include/dt-bindings/clock/rk3288-cru.h b/include/dt-bindings/clock/rk3288-cru.h
index ebcb460ea4ad..8f75bf065c1f 100644
--- a/include/dt-bindings/clock/rk3288-cru.h
+++ b/include/dt-bindings/clock/rk3288-cru.h
@@ -19,6 +19,7 @@
 #define PLL_CPLL		3
 #define PLL_GPLL		4
 #define PLL_NPLL		5
+#define ARMCLK			6
 
 /* sclk gates (special clocks) */
 #define SCLK_GPU		64
-- 
cgit v1.2.3


From 20e075585973453515be6615b91901c959e0a573 Mon Sep 17 00:00:00 2001
From: Zhangfei Gao <zhangfei.gao@linaro.org>
Date: Tue, 13 May 2014 20:26:59 +0800
Subject: clk: hix5hd2: add complex clk

Support clk of sata, usb and ethernet

Signed-off-by: Jiancheng Xue <xuejiancheng@huawei.com>
Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Wei Xu <xuwei5@hisilicon.com>
---
 drivers/clk/hisilicon/clk-hix5hd2.c       | 181 ++++++++++++++++++++++++++++++
 include/dt-bindings/clock/hix5hd2-clock.h |   9 ++
 2 files changed, 190 insertions(+)

(limited to 'include')

diff --git a/drivers/clk/hisilicon/clk-hix5hd2.c b/drivers/clk/hisilicon/clk-hix5hd2.c
index e5fcfb4e32ef..da9ca05e6fb7 100644
--- a/drivers/clk/hisilicon/clk-hix5hd2.c
+++ b/drivers/clk/hisilicon/clk-hix5hd2.c
@@ -9,6 +9,8 @@
 
 #include <linux/of_address.h>
 #include <dt-bindings/clock/hix5hd2-clock.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
 #include "clk.h"
 
 static struct hisi_fixed_rate_clock hix5hd2_fixed_rate_clks[] __initdata = {
@@ -79,8 +81,184 @@ static struct hisi_gate_clock hix5hd2_gate_clks[] __initdata = {
 		CLK_SET_RATE_PARENT, 0xa0, 1, 0, },
 	{ HIX5HD2_MMC_CIU_RST, "rst_mmc_ciu", "clk_mmc_ciu",
 		CLK_SET_RATE_PARENT, 0xa0, 4, CLK_GATE_SET_TO_DISABLE, },
+	/* gsf */
+	{ HIX5HD2_FWD_BUS_CLK, "clk_fwd_bus", NULL, 0, 0xcc, 0, 0, },
+	{ HIX5HD2_FWD_SYS_CLK, "clk_fwd_sys", "clk_fwd_bus", 0, 0xcc, 5, 0, },
+	{ HIX5HD2_MAC0_PHY_CLK, "clk_fephy", "clk_fwd_sys",
+		 CLK_SET_RATE_PARENT, 0x120, 0, 0, },
 };
 
+enum hix5hd2_clk_type {
+	TYPE_COMPLEX,
+	TYPE_ETHER,
+};
+
+struct hix5hd2_complex_clock {
+	const char	*name;
+	const char	*parent_name;
+	u32		id;
+	u32		ctrl_reg;
+	u32		ctrl_clk_mask;
+	u32		ctrl_rst_mask;
+	u32		phy_reg;
+	u32		phy_clk_mask;
+	u32		phy_rst_mask;
+	enum hix5hd2_clk_type type;
+};
+
+struct hix5hd2_clk_complex {
+	struct clk_hw	hw;
+	u32		id;
+	void __iomem	*ctrl_reg;
+	u32		ctrl_clk_mask;
+	u32		ctrl_rst_mask;
+	void __iomem	*phy_reg;
+	u32		phy_clk_mask;
+	u32		phy_rst_mask;
+};
+
+static struct hix5hd2_complex_clock hix5hd2_complex_clks[] __initdata = {
+	{"clk_mac0", "clk_fephy", HIX5HD2_MAC0_CLK,
+		0xcc, 0xa, 0x500, 0x120, 0, 0x10, TYPE_ETHER},
+	{"clk_mac1", "clk_fwd_sys", HIX5HD2_MAC1_CLK,
+		0xcc, 0x14, 0xa00, 0x168, 0x2, 0, TYPE_ETHER},
+	{"clk_sata", NULL, HIX5HD2_SATA_CLK,
+		0xa8, 0x1f, 0x300, 0xac, 0x1, 0x0, TYPE_COMPLEX},
+	{"clk_usb", NULL, HIX5HD2_USB_CLK,
+		0xb8, 0xff, 0x3f000, 0xbc, 0x7, 0x3f00, TYPE_COMPLEX},
+};
+
+#define to_complex_clk(_hw) container_of(_hw, struct hix5hd2_clk_complex, hw)
+
+static int clk_ether_prepare(struct clk_hw *hw)
+{
+	struct hix5hd2_clk_complex *clk = to_complex_clk(hw);
+	u32 val;
+
+	val = readl_relaxed(clk->ctrl_reg);
+	val |= clk->ctrl_clk_mask | clk->ctrl_rst_mask;
+	writel_relaxed(val, clk->ctrl_reg);
+	val &= ~(clk->ctrl_rst_mask);
+	writel_relaxed(val, clk->ctrl_reg);
+
+	val = readl_relaxed(clk->phy_reg);
+	val |= clk->phy_clk_mask;
+	val &= ~(clk->phy_rst_mask);
+	writel_relaxed(val, clk->phy_reg);
+	mdelay(10);
+
+	val &= ~(clk->phy_clk_mask);
+	val |= clk->phy_rst_mask;
+	writel_relaxed(val, clk->phy_reg);
+	mdelay(10);
+
+	val |= clk->phy_clk_mask;
+	val &= ~(clk->phy_rst_mask);
+	writel_relaxed(val, clk->phy_reg);
+	mdelay(30);
+	return 0;
+}
+
+static void clk_ether_unprepare(struct clk_hw *hw)
+{
+	struct hix5hd2_clk_complex *clk = to_complex_clk(hw);
+	u32 val;
+
+	val = readl_relaxed(clk->ctrl_reg);
+	val &= ~(clk->ctrl_clk_mask);
+	writel_relaxed(val, clk->ctrl_reg);
+}
+
+static struct clk_ops clk_ether_ops = {
+	.prepare = clk_ether_prepare,
+	.unprepare = clk_ether_unprepare,
+};
+
+static int clk_complex_enable(struct clk_hw *hw)
+{
+	struct hix5hd2_clk_complex *clk = to_complex_clk(hw);
+	u32 val;
+
+	val = readl_relaxed(clk->ctrl_reg);
+	val |= clk->ctrl_clk_mask;
+	val &= ~(clk->ctrl_rst_mask);
+	writel_relaxed(val, clk->ctrl_reg);
+
+	val = readl_relaxed(clk->phy_reg);
+	val |= clk->phy_clk_mask;
+	val &= ~(clk->phy_rst_mask);
+	writel_relaxed(val, clk->phy_reg);
+
+	return 0;
+}
+
+static void clk_complex_disable(struct clk_hw *hw)
+{
+	struct hix5hd2_clk_complex *clk = to_complex_clk(hw);
+	u32 val;
+
+	val = readl_relaxed(clk->ctrl_reg);
+	val |= clk->ctrl_rst_mask;
+	val &= ~(clk->ctrl_clk_mask);
+	writel_relaxed(val, clk->ctrl_reg);
+
+	val = readl_relaxed(clk->phy_reg);
+	val |= clk->phy_rst_mask;
+	val &= ~(clk->phy_clk_mask);
+	writel_relaxed(val, clk->phy_reg);
+}
+
+static struct clk_ops clk_complex_ops = {
+	.enable = clk_complex_enable,
+	.disable = clk_complex_disable,
+};
+
+void __init hix5hd2_clk_register_complex(struct hix5hd2_complex_clock *clks,
+					 int nums, struct hisi_clock_data *data)
+{
+	void __iomem *base = data->base;
+	int i;
+
+	for (i = 0; i < nums; i++) {
+		struct hix5hd2_clk_complex *p_clk;
+		struct clk *clk;
+		struct clk_init_data init;
+
+		p_clk = kzalloc(sizeof(*p_clk), GFP_KERNEL);
+		if (!p_clk)
+			return;
+
+		init.name = clks[i].name;
+		if (clks[i].type == TYPE_ETHER)
+			init.ops = &clk_ether_ops;
+		else
+			init.ops = &clk_complex_ops;
+
+		init.flags = CLK_IS_BASIC;
+		init.parent_names =
+			(clks[i].parent_name ? &clks[i].parent_name : NULL);
+		init.num_parents = (clks[i].parent_name ? 1 : 0);
+
+		p_clk->ctrl_reg = base + clks[i].ctrl_reg;
+		p_clk->ctrl_clk_mask = clks[i].ctrl_clk_mask;
+		p_clk->ctrl_rst_mask = clks[i].ctrl_rst_mask;
+		p_clk->phy_reg = base + clks[i].phy_reg;
+		p_clk->phy_clk_mask = clks[i].phy_clk_mask;
+		p_clk->phy_rst_mask = clks[i].phy_rst_mask;
+		p_clk->hw.init = &init;
+
+		clk = clk_register(NULL, &p_clk->hw);
+		if (IS_ERR(clk)) {
+			kfree(p_clk);
+			pr_err("%s: failed to register clock %s\n",
+			       __func__, clks[i].name);
+			continue;
+		}
+
+		data->clk_data.clks[clks[i].id] = clk;
+	}
+}
+
 static void __init hix5hd2_clk_init(struct device_node *np)
 {
 	struct hisi_clock_data *clk_data;
@@ -96,6 +274,9 @@ static void __init hix5hd2_clk_init(struct device_node *np)
 					clk_data);
 	hisi_clk_register_gate(hix5hd2_gate_clks,
 			ARRAY_SIZE(hix5hd2_gate_clks), clk_data);
+	hix5hd2_clk_register_complex(hix5hd2_complex_clks,
+				     ARRAY_SIZE(hix5hd2_complex_clks),
+				     clk_data);
 }
 
 CLK_OF_DECLARE(hix5hd2_clk, "hisilicon,hix5hd2-clock", hix5hd2_clk_init);
diff --git a/include/dt-bindings/clock/hix5hd2-clock.h b/include/dt-bindings/clock/hix5hd2-clock.h
index aad579a75802..e3286695382d 100644
--- a/include/dt-bindings/clock/hix5hd2-clock.h
+++ b/include/dt-bindings/clock/hix5hd2-clock.h
@@ -53,6 +53,15 @@
 #define HIX5HD2_MMC_CIU_CLK		130
 #define HIX5HD2_MMC_BIU_CLK		131
 #define HIX5HD2_MMC_CIU_RST		132
+#define HIX5HD2_FWD_BUS_CLK		133
+#define HIX5HD2_FWD_SYS_CLK		134
+#define HIX5HD2_MAC0_PHY_CLK		135
+
+/* complex */
+#define HIX5HD2_MAC0_CLK		192
+#define HIX5HD2_MAC1_CLK		193
+#define HIX5HD2_SATA_CLK		194
+#define HIX5HD2_USB_CLK			195
 
 #define HIX5HD2_NR_CLKS			256
 #endif	/* __DTS_HIX5HD2_CLOCK_H */
-- 
cgit v1.2.3


From cc855dd9994cfd179891cf5b966ebc8051d95a9f Mon Sep 17 00:00:00 2001
From: Jiancheng Xue <xuejiancheng@huawei.com>
Date: Wed, 28 May 2014 11:35:32 +0800
Subject: clk: hix5hd2: add sd clk

Signed-off-by: Jiancheng Xue <xuejiancheng@huawei.com>
Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Wei Xu <xuwei5@hisilicon.com>
---
 drivers/clk/hisilicon/clk-hix5hd2.c       | 21 +++++++++++++++------
 include/dt-bindings/clock/hix5hd2-clock.h |  4 ++++
 2 files changed, 19 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/hisilicon/clk-hix5hd2.c b/drivers/clk/hisilicon/clk-hix5hd2.c
index da9ca05e6fb7..13d6ec24af12 100644
--- a/drivers/clk/hisilicon/clk-hix5hd2.c
+++ b/drivers/clk/hisilicon/clk-hix5hd2.c
@@ -50,9 +50,9 @@ static const char *sfc_mux_p[] __initconst = {
 		"24m", "150m", "200m", "100m", "75m", };
 static u32 sfc_mux_table[] = {0, 4, 5, 6, 7};
 
-static const char *sdio1_mux_p[] __initconst = {
+static const char *sdio_mux_p[] __initconst = {
 		"75m", "100m", "50m", "15m", };
-static u32 sdio1_mux_table[] = {0, 1, 2, 3};
+static u32 sdio_mux_table[] = {0, 1, 2, 3};
 
 static const char *fephy_mux_p[] __initconst = { "25m", "125m"};
 static u32 fephy_mux_table[] = {0, 1};
@@ -61,20 +61,29 @@ static u32 fephy_mux_table[] = {0, 1};
 static struct hisi_mux_clock hix5hd2_mux_clks[] __initdata = {
 	{ HIX5HD2_SFC_MUX, "sfc_mux", sfc_mux_p, ARRAY_SIZE(sfc_mux_p),
 		CLK_SET_RATE_PARENT, 0x5c, 8, 3, 0, sfc_mux_table, },
-	{ HIX5HD2_MMC_MUX, "mmc_mux", sdio1_mux_p, ARRAY_SIZE(sdio1_mux_p),
-		CLK_SET_RATE_PARENT, 0xa0, 8, 2, 0, sdio1_mux_table, },
+	{ HIX5HD2_MMC_MUX, "mmc_mux", sdio_mux_p, ARRAY_SIZE(sdio_mux_p),
+		CLK_SET_RATE_PARENT, 0xa0, 8, 2, 0, sdio_mux_table, },
+	{ HIX5HD2_SD_MUX, "sd_mux", sdio_mux_p, ARRAY_SIZE(sdio_mux_p),
+		CLK_SET_RATE_PARENT, 0x9c, 8, 2, 0, sdio_mux_table, },
 	{ HIX5HD2_FEPHY_MUX, "fephy_mux",
 		fephy_mux_p, ARRAY_SIZE(fephy_mux_p),
 		CLK_SET_RATE_PARENT, 0x120, 8, 2, 0, fephy_mux_table, },
 };
 
 static struct hisi_gate_clock hix5hd2_gate_clks[] __initdata = {
-	/*sfc*/
+	/* sfc */
 	{ HIX5HD2_SFC_CLK, "clk_sfc", "sfc_mux",
 		CLK_SET_RATE_PARENT, 0x5c, 0, 0, },
 	{ HIX5HD2_SFC_RST, "rst_sfc", "clk_sfc",
 		CLK_SET_RATE_PARENT, 0x5c, 4, CLK_GATE_SET_TO_DISABLE, },
-	/*sdio1*/
+	/* sdio0 */
+	{ HIX5HD2_SD_BIU_CLK, "clk_sd_biu", "200m",
+		CLK_SET_RATE_PARENT, 0x9c, 0, 0, },
+	{ HIX5HD2_SD_CIU_CLK, "clk_sd_ciu", "sd_mux",
+		CLK_SET_RATE_PARENT, 0x9c, 1, 0, },
+	{ HIX5HD2_SD_CIU_RST, "rst_sd_ciu", "clk_sd_ciu",
+		CLK_SET_RATE_PARENT, 0x9c, 4, CLK_GATE_SET_TO_DISABLE, },
+	/* sdio1 */
 	{ HIX5HD2_MMC_BIU_CLK, "clk_mmc_biu", "200m",
 		CLK_SET_RATE_PARENT, 0xa0, 0, 0, },
 	{ HIX5HD2_MMC_CIU_CLK, "clk_mmc_ciu", "mmc_mux",
diff --git a/include/dt-bindings/clock/hix5hd2-clock.h b/include/dt-bindings/clock/hix5hd2-clock.h
index e3286695382d..5bd4135c9544 100644
--- a/include/dt-bindings/clock/hix5hd2-clock.h
+++ b/include/dt-bindings/clock/hix5hd2-clock.h
@@ -46,6 +46,7 @@
 #define HIX5HD2_SFC_MUX			64
 #define HIX5HD2_MMC_MUX			65
 #define HIX5HD2_FEPHY_MUX		66
+#define HIX5HD2_SD_MUX			67
 
 /* gate clocks */
 #define HIX5HD2_SFC_RST			128
@@ -56,6 +57,9 @@
 #define HIX5HD2_FWD_BUS_CLK		133
 #define HIX5HD2_FWD_SYS_CLK		134
 #define HIX5HD2_MAC0_PHY_CLK		135
+#define HIX5HD2_SD_CIU_CLK		136
+#define HIX5HD2_SD_BIU_CLK		137
+#define HIX5HD2_SD_CIU_RST		138
 
 /* complex */
 #define HIX5HD2_MAC0_CLK		192
-- 
cgit v1.2.3


From 1463fba39c2e95803147e1d6e159ea402d965e6f Mon Sep 17 00:00:00 2001
From: Guoxiong Yan <yanguoxiong@huawei.com>
Date: Tue, 17 Jun 2014 17:04:17 +0800
Subject: clk: hix5hd2: add watchdog0 clocks

hix5hd2 add watchdog0 clocks

Signed-off-by: Guoxiong Yan <yanguoxiong@huawei.com>
Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Wei Xu <xuwei5@hisilicon.com>
---
 drivers/clk/hisilicon/clk-hix5hd2.c       | 5 +++++
 include/dt-bindings/clock/hix5hd2-clock.h | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/drivers/clk/hisilicon/clk-hix5hd2.c b/drivers/clk/hisilicon/clk-hix5hd2.c
index 13d6ec24af12..6e97e54b869c 100644
--- a/drivers/clk/hisilicon/clk-hix5hd2.c
+++ b/drivers/clk/hisilicon/clk-hix5hd2.c
@@ -95,6 +95,11 @@ static struct hisi_gate_clock hix5hd2_gate_clks[] __initdata = {
 	{ HIX5HD2_FWD_SYS_CLK, "clk_fwd_sys", "clk_fwd_bus", 0, 0xcc, 5, 0, },
 	{ HIX5HD2_MAC0_PHY_CLK, "clk_fephy", "clk_fwd_sys",
 		 CLK_SET_RATE_PARENT, 0x120, 0, 0, },
+	/* wdg0 */
+	{ HIX5HD2_WDG0_CLK, "clk_wdg0", "24m",
+		CLK_SET_RATE_PARENT, 0x178, 0, 0, },
+	{ HIX5HD2_WDG0_RST, "rst_wdg0", "clk_wdg0",
+		CLK_SET_RATE_PARENT, 0x178, 4, CLK_GATE_SET_TO_DISABLE, },
 };
 
 enum hix5hd2_clk_type {
diff --git a/include/dt-bindings/clock/hix5hd2-clock.h b/include/dt-bindings/clock/hix5hd2-clock.h
index 5bd4135c9544..b8e3c9deda20 100644
--- a/include/dt-bindings/clock/hix5hd2-clock.h
+++ b/include/dt-bindings/clock/hix5hd2-clock.h
@@ -60,6 +60,8 @@
 #define HIX5HD2_SD_CIU_CLK		136
 #define HIX5HD2_SD_BIU_CLK		137
 #define HIX5HD2_SD_CIU_RST		138
+#define HIX5HD2_WDG0_CLK		139
+#define HIX5HD2_WDG0_RST		140
 
 /* complex */
 #define HIX5HD2_MAC0_CLK		192
-- 
cgit v1.2.3


From 45bcf9c6f299ae77c14c2ae8cea3f8e540fe80d1 Mon Sep 17 00:00:00 2001
From: Wei Yan <sledge.yanwei@huawei.com>
Date: Thu, 7 Aug 2014 09:09:13 +0800
Subject: clk: hix5hd2: add I2C clocks

hix5hd2 add I2C clocks (I2C0~i2C5)

Signed-off-by: Wei Yan <sledge.yanwei@huawei.com>
Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Wei Xu <xuwei5@hisilicon.com>
---
 drivers/clk/hisilicon/clk-hix5hd2.c       | 25 +++++++++++++++++++++++++
 include/dt-bindings/clock/hix5hd2-clock.h | 12 ++++++++++++
 2 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/drivers/clk/hisilicon/clk-hix5hd2.c b/drivers/clk/hisilicon/clk-hix5hd2.c
index 6e97e54b869c..3f369c60fe56 100644
--- a/drivers/clk/hisilicon/clk-hix5hd2.c
+++ b/drivers/clk/hisilicon/clk-hix5hd2.c
@@ -100,6 +100,31 @@ static struct hisi_gate_clock hix5hd2_gate_clks[] __initdata = {
 		CLK_SET_RATE_PARENT, 0x178, 0, 0, },
 	{ HIX5HD2_WDG0_RST, "rst_wdg0", "clk_wdg0",
 		CLK_SET_RATE_PARENT, 0x178, 4, CLK_GATE_SET_TO_DISABLE, },
+	/* I2C */
+	{HIX5HD2_I2C0_CLK, "clk_i2c0", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 4, 0, },
+	{HIX5HD2_I2C0_RST, "rst_i2c0", "clk_i2c0",
+		 CLK_SET_RATE_PARENT, 0x06c, 5, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C1_CLK, "clk_i2c1", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 8, 0, },
+	{HIX5HD2_I2C1_RST, "rst_i2c1", "clk_i2c1",
+		 CLK_SET_RATE_PARENT, 0x06c, 9, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C2_CLK, "clk_i2c2", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 12, 0, },
+	{HIX5HD2_I2C2_RST, "rst_i2c2", "clk_i2c2",
+		 CLK_SET_RATE_PARENT, 0x06c, 13, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C3_CLK, "clk_i2c3", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 16, 0, },
+	{HIX5HD2_I2C3_RST, "rst_i2c3", "clk_i2c3",
+		 CLK_SET_RATE_PARENT, 0x06c, 17, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C4_CLK, "clk_i2c4", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 20, 0, },
+	{HIX5HD2_I2C4_RST, "rst_i2c4", "clk_i2c4",
+		 CLK_SET_RATE_PARENT, 0x06c, 21, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C5_CLK, "clk_i2c5", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 0, 0, },
+	{HIX5HD2_I2C5_RST, "rst_i2c5", "clk_i2c5",
+		 CLK_SET_RATE_PARENT, 0x06c, 1, CLK_GATE_SET_TO_DISABLE, },
 };
 
 enum hix5hd2_clk_type {
diff --git a/include/dt-bindings/clock/hix5hd2-clock.h b/include/dt-bindings/clock/hix5hd2-clock.h
index b8e3c9deda20..fd29c174ba63 100644
--- a/include/dt-bindings/clock/hix5hd2-clock.h
+++ b/include/dt-bindings/clock/hix5hd2-clock.h
@@ -62,6 +62,18 @@
 #define HIX5HD2_SD_CIU_RST		138
 #define HIX5HD2_WDG0_CLK		139
 #define HIX5HD2_WDG0_RST		140
+#define HIX5HD2_I2C0_CLK		141
+#define HIX5HD2_I2C0_RST		142
+#define HIX5HD2_I2C1_CLK		143
+#define HIX5HD2_I2C1_RST		144
+#define HIX5HD2_I2C2_CLK		145
+#define HIX5HD2_I2C2_RST		146
+#define HIX5HD2_I2C3_CLK		147
+#define HIX5HD2_I2C3_RST		148
+#define HIX5HD2_I2C4_CLK		149
+#define HIX5HD2_I2C4_RST		150
+#define HIX5HD2_I2C5_CLK		151
+#define HIX5HD2_I2C5_RST		152
 
 /* complex */
 #define HIX5HD2_MAC0_CLK		192
-- 
cgit v1.2.3


From 7bced397510ab569d31de4c70b39e13355046387 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 30 Dec 2013 12:37:29 -0800
Subject: net_dma: simple removal

Per commit "77873803363c net_dma: mark broken" net_dma is no longer used
and there is no plan to fix it.

This is the mechanical removal of bits in CONFIG_NET_DMA ifdef guards.
Reverting the remainder of the net_dma induced changes is deferred to
subsequent patches.

Marked for stable due to Roman's report of a memory leak in
dma_pin_iovec_pages():

    https://lkml.org/lkml/2014/9/3/177

Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Vinod Koul <vinod.koul@intel.com>
Cc: David Whipple <whipple@securedatainnovations.ch>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: <stable@vger.kernel.org>
Reported-by: Roman Gushchin <klamm@yandex-team.ru>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 Documentation/ABI/removed/net_dma      |   8 +
 Documentation/networking/ip-sysctl.txt |   6 -
 drivers/dma/Kconfig                    |  12 --
 drivers/dma/Makefile                   |   1 -
 drivers/dma/dmaengine.c                | 104 ------------
 drivers/dma/ioat/dma.c                 |   1 -
 drivers/dma/ioat/dma.h                 |   7 -
 drivers/dma/ioat/dma_v2.c              |   1 -
 drivers/dma/ioat/dma_v3.c              |   1 -
 drivers/dma/iovlock.c                  | 280 ---------------------------------
 include/linux/dmaengine.h              |  22 +--
 include/linux/skbuff.h                 |   8 +-
 include/linux/tcp.h                    |   8 -
 include/net/netdma.h                   |  32 ----
 include/net/sock.h                     |  19 +--
 include/net/tcp.h                      |   8 -
 kernel/sysctl_binary.c                 |   1 -
 net/core/Makefile                      |   1 -
 net/core/dev.c                         |  10 --
 net/core/sock.c                        |   6 -
 net/core/user_dma.c                    | 131 ---------------
 net/dccp/proto.c                       |   4 +-
 net/ipv4/sysctl_net_ipv4.c             |   9 --
 net/ipv4/tcp.c                         | 147 ++---------------
 net/ipv4/tcp_input.c                   |  61 -------
 net/ipv4/tcp_ipv4.c                    |  18 +--
 net/ipv6/tcp_ipv6.c                    |  13 +-
 net/llc/af_llc.c                       |  10 +-
 28 files changed, 35 insertions(+), 894 deletions(-)
 create mode 100644 Documentation/ABI/removed/net_dma
 delete mode 100644 drivers/dma/iovlock.c
 delete mode 100644 include/net/netdma.h
 delete mode 100644 net/core/user_dma.c

(limited to 'include')

diff --git a/Documentation/ABI/removed/net_dma b/Documentation/ABI/removed/net_dma
new file mode 100644
index 000000000000..a173aecc2f18
--- /dev/null
+++ b/Documentation/ABI/removed/net_dma
@@ -0,0 +1,8 @@
+What:		tcp_dma_copybreak sysctl
+Date:		Removed in kernel v3.13
+Contact:	Dan Williams <dan.j.williams@intel.com>
+Description:
+	Formerly the lower limit, in bytes, of the size of socket reads
+	that will be offloaded to a DMA copy engine.  Removed due to
+	coherency issues of the cpu potentially touching the buffers
+	while dma is in flight.
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ab42c95f9985..ea8f3b182e70 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -582,12 +582,6 @@ tcp_workaround_signed_windows - BOOLEAN
 	not receive a window scaling option from them.
 	Default: 0
 
-tcp_dma_copybreak - INTEGER
-	Lower limit, in bytes, of the size of socket reads that will be
-	offloaded to a DMA copy engine, if one is present in the system
-	and CONFIG_NET_DMA is enabled.
-	Default: 4096
-
 tcp_thin_linear_timeouts - BOOLEAN
 	Enable dynamic triggering of linear timeouts for thin streams.
 	If set, a check is performed upon retransmission by timeout to
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 605b016bcea4..6b5f37e01a70 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -368,18 +368,6 @@ config DMA_OF
 comment "DMA Clients"
 	depends on DMA_ENGINE
 
-config NET_DMA
-	bool "Network: TCP receive copy offload"
-	depends on DMA_ENGINE && NET
-	default (INTEL_IOATDMA || FSL_DMA)
-	depends on BROKEN
-	help
-	  This enables the use of DMA engines in the network stack to
-	  offload receive copy-to-user operations, freeing CPU cycles.
-
-	  Say Y here if you enabled INTEL_IOATDMA or FSL_DMA, otherwise
-	  say N.
-
 config ASYNC_TX_DMA
 	bool "Async_tx: Offload support for the async_tx api"
 	depends on DMA_ENGINE
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index a029d0f4a1be..0c9dc7549327 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -6,7 +6,6 @@ obj-$(CONFIG_DMA_VIRTUAL_CHANNELS) += virt-dma.o
 obj-$(CONFIG_DMA_ACPI) += acpi-dma.o
 obj-$(CONFIG_DMA_OF) += of-dma.o
 
-obj-$(CONFIG_NET_DMA) += iovlock.o
 obj-$(CONFIG_INTEL_MID_DMAC) += intel_mid_dma.o
 obj-$(CONFIG_DMATEST) += dmatest.o
 obj-$(CONFIG_INTEL_IOATDMA) += ioat/
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index ed610b497518..268de183b519 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1084,110 +1084,6 @@ dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
 }
 EXPORT_SYMBOL(dmaengine_get_unmap_data);
 
-/**
- * dma_async_memcpy_pg_to_pg - offloaded copy from page to page
- * @chan: DMA channel to offload copy to
- * @dest_pg: destination page
- * @dest_off: offset in page to copy to
- * @src_pg: source page
- * @src_off: offset in page to copy from
- * @len: length
- *
- * Both @dest_page/@dest_off and @src_page/@src_off must be mappable to a bus
- * address according to the DMA mapping API rules for streaming mappings.
- * Both @dest_page/@dest_off and @src_page/@src_off must stay memory resident
- * (kernel memory or locked user space pages).
- */
-dma_cookie_t
-dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
-	unsigned int dest_off, struct page *src_pg, unsigned int src_off,
-	size_t len)
-{
-	struct dma_device *dev = chan->device;
-	struct dma_async_tx_descriptor *tx;
-	struct dmaengine_unmap_data *unmap;
-	dma_cookie_t cookie;
-	unsigned long flags;
-
-	unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOWAIT);
-	if (!unmap)
-		return -ENOMEM;
-
-	unmap->to_cnt = 1;
-	unmap->from_cnt = 1;
-	unmap->addr[0] = dma_map_page(dev->dev, src_pg, src_off, len,
-				      DMA_TO_DEVICE);
-	unmap->addr[1] = dma_map_page(dev->dev, dest_pg, dest_off, len,
-				      DMA_FROM_DEVICE);
-	unmap->len = len;
-	flags = DMA_CTRL_ACK;
-	tx = dev->device_prep_dma_memcpy(chan, unmap->addr[1], unmap->addr[0],
-					 len, flags);
-
-	if (!tx) {
-		dmaengine_unmap_put(unmap);
-		return -ENOMEM;
-	}
-
-	dma_set_unmap(tx, unmap);
-	cookie = tx->tx_submit(tx);
-	dmaengine_unmap_put(unmap);
-
-	preempt_disable();
-	__this_cpu_add(chan->local->bytes_transferred, len);
-	__this_cpu_inc(chan->local->memcpy_count);
-	preempt_enable();
-
-	return cookie;
-}
-EXPORT_SYMBOL(dma_async_memcpy_pg_to_pg);
-
-/**
- * dma_async_memcpy_buf_to_buf - offloaded copy between virtual addresses
- * @chan: DMA channel to offload copy to
- * @dest: destination address (virtual)
- * @src: source address (virtual)
- * @len: length
- *
- * Both @dest and @src must be mappable to a bus address according to the
- * DMA mapping API rules for streaming mappings.
- * Both @dest and @src must stay memory resident (kernel memory or locked
- * user space pages).
- */
-dma_cookie_t
-dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
-			    void *src, size_t len)
-{
-	return dma_async_memcpy_pg_to_pg(chan, virt_to_page(dest),
-					 (unsigned long) dest & ~PAGE_MASK,
-					 virt_to_page(src),
-					 (unsigned long) src & ~PAGE_MASK, len);
-}
-EXPORT_SYMBOL(dma_async_memcpy_buf_to_buf);
-
-/**
- * dma_async_memcpy_buf_to_pg - offloaded copy from address to page
- * @chan: DMA channel to offload copy to
- * @page: destination page
- * @offset: offset in page to copy to
- * @kdata: source address (virtual)
- * @len: length
- *
- * Both @page/@offset and @kdata must be mappable to a bus address according
- * to the DMA mapping API rules for streaming mappings.
- * Both @page/@offset and @kdata must stay memory resident (kernel memory or
- * locked user space pages)
- */
-dma_cookie_t
-dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
-			   unsigned int offset, void *kdata, size_t len)
-{
-	return dma_async_memcpy_pg_to_pg(chan, page, offset,
-					 virt_to_page(kdata),
-					 (unsigned long) kdata & ~PAGE_MASK, len);
-}
-EXPORT_SYMBOL(dma_async_memcpy_buf_to_pg);
-
 void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 	struct dma_chan *chan)
 {
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index b76c1485933b..940c1502a8b5 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -1222,7 +1222,6 @@ int ioat1_dma_probe(struct ioatdma_device *device, int dca)
 	err = ioat_probe(device);
 	if (err)
 		return err;
-	ioat_set_tcp_copy_break(4096);
 	err = ioat_register(device);
 	if (err)
 		return err;
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index e982f00a9843..d63f68b1aa35 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -214,13 +214,6 @@ __dump_desc_dbg(struct ioat_chan_common *chan, struct ioat_dma_descriptor *hw,
 #define dump_desc_dbg(c, d) \
 	({ if (d) __dump_desc_dbg(&c->base, d->hw, &d->txd, desc_id(d)); 0; })
 
-static inline void ioat_set_tcp_copy_break(unsigned long copybreak)
-{
-	#ifdef CONFIG_NET_DMA
-	sysctl_tcp_dma_copybreak = copybreak;
-	#endif
-}
-
 static inline struct ioat_chan_common *
 ioat_chan_by_index(struct ioatdma_device *device, int index)
 {
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 2ce9be498608..695483e6be32 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -900,7 +900,6 @@ int ioat2_dma_probe(struct ioatdma_device *device, int dca)
 	err = ioat_probe(device);
 	if (err)
 		return err;
-	ioat_set_tcp_copy_break(2048);
 
 	list_for_each_entry(c, &dma->channels, device_node) {
 		chan = to_chan_common(c);
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index 85971d6e9646..895f869d6c2c 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -1655,7 +1655,6 @@ int ioat3_dma_probe(struct ioatdma_device *device, int dca)
 	err = ioat_probe(device);
 	if (err)
 		return err;
-	ioat_set_tcp_copy_break(262144);
 
 	list_for_each_entry(c, &dma->channels, device_node) {
 		chan = to_chan_common(c);
diff --git a/drivers/dma/iovlock.c b/drivers/dma/iovlock.c
deleted file mode 100644
index bb48a57c2fc1..000000000000
--- a/drivers/dma/iovlock.c
+++ /dev/null
@@ -1,280 +0,0 @@
-/*
- * Copyright(c) 2004 - 2006 Intel Corporation. All rights reserved.
- * Portions based on net/core/datagram.c and copyrighted by their authors.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called COPYING.
- */
-
-/*
- * This code allows the net stack to make use of a DMA engine for
- * skb to iovec copies.
- */
-
-#include <linux/dmaengine.h>
-#include <linux/pagemap.h>
-#include <linux/slab.h>
-#include <net/tcp.h> /* for memcpy_toiovec */
-#include <asm/io.h>
-#include <asm/uaccess.h>
-
-static int num_pages_spanned(struct iovec *iov)
-{
-	return
-	((PAGE_ALIGN((unsigned long)iov->iov_base + iov->iov_len) -
-	((unsigned long)iov->iov_base & PAGE_MASK)) >> PAGE_SHIFT);
-}
-
-/*
- * Pin down all the iovec pages needed for len bytes.
- * Return a struct dma_pinned_list to keep track of pages pinned down.
- *
- * We are allocating a single chunk of memory, and then carving it up into
- * 3 sections, the latter 2 whose size depends on the number of iovecs and the
- * total number of pages, respectively.
- */
-struct dma_pinned_list *dma_pin_iovec_pages(struct iovec *iov, size_t len)
-{
-	struct dma_pinned_list *local_list;
-	struct page **pages;
-	int i;
-	int ret;
-	int nr_iovecs = 0;
-	int iovec_len_used = 0;
-	int iovec_pages_used = 0;
-
-	/* don't pin down non-user-based iovecs */
-	if (segment_eq(get_fs(), KERNEL_DS))
-		return NULL;
-
-	/* determine how many iovecs/pages there are, up front */
-	do {
-		iovec_len_used += iov[nr_iovecs].iov_len;
-		iovec_pages_used += num_pages_spanned(&iov[nr_iovecs]);
-		nr_iovecs++;
-	} while (iovec_len_used < len);
-
-	/* single kmalloc for pinned list, page_list[], and the page arrays */
-	local_list = kmalloc(sizeof(*local_list)
-		+ (nr_iovecs * sizeof (struct dma_page_list))
-		+ (iovec_pages_used * sizeof (struct page*)), GFP_KERNEL);
-	if (!local_list)
-		goto out;
-
-	/* list of pages starts right after the page list array */
-	pages = (struct page **) &local_list->page_list[nr_iovecs];
-
-	local_list->nr_iovecs = 0;
-
-	for (i = 0; i < nr_iovecs; i++) {
-		struct dma_page_list *page_list = &local_list->page_list[i];
-
-		len -= iov[i].iov_len;
-
-		if (!access_ok(VERIFY_WRITE, iov[i].iov_base, iov[i].iov_len))
-			goto unpin;
-
-		page_list->nr_pages = num_pages_spanned(&iov[i]);
-		page_list->base_address = iov[i].iov_base;
-
-		page_list->pages = pages;
-		pages += page_list->nr_pages;
-
-		/* pin pages down */
-		down_read(&current->mm->mmap_sem);
-		ret = get_user_pages(
-			current,
-			current->mm,
-			(unsigned long) iov[i].iov_base,
-			page_list->nr_pages,
-			1,	/* write */
-			0,	/* force */
-			page_list->pages,
-			NULL);
-		up_read(&current->mm->mmap_sem);
-
-		if (ret != page_list->nr_pages)
-			goto unpin;
-
-		local_list->nr_iovecs = i + 1;
-	}
-
-	return local_list;
-
-unpin:
-	dma_unpin_iovec_pages(local_list);
-out:
-	return NULL;
-}
-
-void dma_unpin_iovec_pages(struct dma_pinned_list *pinned_list)
-{
-	int i, j;
-
-	if (!pinned_list)
-		return;
-
-	for (i = 0; i < pinned_list->nr_iovecs; i++) {
-		struct dma_page_list *page_list = &pinned_list->page_list[i];
-		for (j = 0; j < page_list->nr_pages; j++) {
-			set_page_dirty_lock(page_list->pages[j]);
-			page_cache_release(page_list->pages[j]);
-		}
-	}
-
-	kfree(pinned_list);
-}
-
-
-/*
- * We have already pinned down the pages we will be using in the iovecs.
- * Each entry in iov array has corresponding entry in pinned_list->page_list.
- * Using array indexing to keep iov[] and page_list[] in sync.
- * Initial elements in iov array's iov->iov_len will be 0 if already copied into
- *   by another call.
- * iov array length remaining guaranteed to be bigger than len.
- */
-dma_cookie_t dma_memcpy_to_iovec(struct dma_chan *chan, struct iovec *iov,
-	struct dma_pinned_list *pinned_list, unsigned char *kdata, size_t len)
-{
-	int iov_byte_offset;
-	int copy;
-	dma_cookie_t dma_cookie = 0;
-	int iovec_idx;
-	int page_idx;
-
-	if (!chan)
-		return memcpy_toiovec(iov, kdata, len);
-
-	iovec_idx = 0;
-	while (iovec_idx < pinned_list->nr_iovecs) {
-		struct dma_page_list *page_list;
-
-		/* skip already used-up iovecs */
-		while (!iov[iovec_idx].iov_len)
-			iovec_idx++;
-
-		page_list = &pinned_list->page_list[iovec_idx];
-
-		iov_byte_offset = ((unsigned long)iov[iovec_idx].iov_base & ~PAGE_MASK);
-		page_idx = (((unsigned long)iov[iovec_idx].iov_base & PAGE_MASK)
-			 - ((unsigned long)page_list->base_address & PAGE_MASK)) >> PAGE_SHIFT;
-
-		/* break up copies to not cross page boundary */
-		while (iov[iovec_idx].iov_len) {
-			copy = min_t(int, PAGE_SIZE - iov_byte_offset, len);
-			copy = min_t(int, copy, iov[iovec_idx].iov_len);
-
-			dma_cookie = dma_async_memcpy_buf_to_pg(chan,
-					page_list->pages[page_idx],
-					iov_byte_offset,
-					kdata,
-					copy);
-			/* poll for a descriptor slot */
-			if (unlikely(dma_cookie < 0)) {
-				dma_async_issue_pending(chan);
-				continue;
-			}
-
-			len -= copy;
-			iov[iovec_idx].iov_len -= copy;
-			iov[iovec_idx].iov_base += copy;
-
-			if (!len)
-				return dma_cookie;
-
-			kdata += copy;
-			iov_byte_offset = 0;
-			page_idx++;
-		}
-		iovec_idx++;
-	}
-
-	/* really bad if we ever run out of iovecs */
-	BUG();
-	return -EFAULT;
-}
-
-dma_cookie_t dma_memcpy_pg_to_iovec(struct dma_chan *chan, struct iovec *iov,
-	struct dma_pinned_list *pinned_list, struct page *page,
-	unsigned int offset, size_t len)
-{
-	int iov_byte_offset;
-	int copy;
-	dma_cookie_t dma_cookie = 0;
-	int iovec_idx;
-	int page_idx;
-	int err;
-
-	/* this needs as-yet-unimplemented buf-to-buff, so punt. */
-	/* TODO: use dma for this */
-	if (!chan || !pinned_list) {
-		u8 *vaddr = kmap(page);
-		err = memcpy_toiovec(iov, vaddr + offset, len);
-		kunmap(page);
-		return err;
-	}
-
-	iovec_idx = 0;
-	while (iovec_idx < pinned_list->nr_iovecs) {
-		struct dma_page_list *page_list;
-
-		/* skip already used-up iovecs */
-		while (!iov[iovec_idx].iov_len)
-			iovec_idx++;
-
-		page_list = &pinned_list->page_list[iovec_idx];
-
-		iov_byte_offset = ((unsigned long)iov[iovec_idx].iov_base & ~PAGE_MASK);
-		page_idx = (((unsigned long)iov[iovec_idx].iov_base & PAGE_MASK)
-			 - ((unsigned long)page_list->base_address & PAGE_MASK)) >> PAGE_SHIFT;
-
-		/* break up copies to not cross page boundary */
-		while (iov[iovec_idx].iov_len) {
-			copy = min_t(int, PAGE_SIZE - iov_byte_offset, len);
-			copy = min_t(int, copy, iov[iovec_idx].iov_len);
-
-			dma_cookie = dma_async_memcpy_pg_to_pg(chan,
-					page_list->pages[page_idx],
-					iov_byte_offset,
-					page,
-					offset,
-					copy);
-			/* poll for a descriptor slot */
-			if (unlikely(dma_cookie < 0)) {
-				dma_async_issue_pending(chan);
-				continue;
-			}
-
-			len -= copy;
-			iov[iovec_idx].iov_len -= copy;
-			iov[iovec_idx].iov_base += copy;
-
-			if (!len)
-				return dma_cookie;
-
-			offset += copy;
-			iov_byte_offset = 0;
-			page_idx++;
-		}
-		iovec_idx++;
-	}
-
-	/* really bad if we ever run out of iovecs */
-	BUG();
-	return -EFAULT;
-}
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index c5c92d59e531..3e382ecd1927 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -903,18 +903,6 @@ static inline void dmaengine_put(void)
 }
 #endif
 
-#ifdef CONFIG_NET_DMA
-#define net_dmaengine_get()	dmaengine_get()
-#define net_dmaengine_put()	dmaengine_put()
-#else
-static inline void net_dmaengine_get(void)
-{
-}
-static inline void net_dmaengine_put(void)
-{
-}
-#endif
-
 #ifdef CONFIG_ASYNC_TX_DMA
 #define async_dmaengine_get()	dmaengine_get()
 #define async_dmaengine_put()	dmaengine_put()
@@ -936,16 +924,8 @@ async_dma_find_channel(enum dma_transaction_type type)
 	return NULL;
 }
 #endif /* CONFIG_ASYNC_TX_DMA */
-
-dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan,
-	void *dest, void *src, size_t len);
-dma_cookie_t dma_async_memcpy_buf_to_pg(struct dma_chan *chan,
-	struct page *page, unsigned int offset, void *kdata, size_t len);
-dma_cookie_t dma_async_memcpy_pg_to_pg(struct dma_chan *chan,
-	struct page *dest_pg, unsigned int dest_off, struct page *src_pg,
-	unsigned int src_off, size_t len);
 void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
-	struct dma_chan *chan);
+				  struct dma_chan *chan);
 
 static inline void async_tx_ack(struct dma_async_tx_descriptor *tx)
 {
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5e1e6f2d98c2..bdbf7afad6b7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -28,7 +28,6 @@
 #include <linux/textsearch.h>
 #include <net/checksum.h>
 #include <linux/rcupdate.h>
-#include <linux/dmaengine.h>
 #include <linux/hrtimer.h>
 #include <linux/dma-mapping.h>
 #include <linux/netdev_features.h>
@@ -515,11 +514,8 @@ struct sk_buff {
 	/* 6/8 bit hole (depending on ndisc_nodetype presence) */
 	kmemcheck_bitfield_end(flags2);
 
-#if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL
-	union {
-		unsigned int	napi_id;
-		dma_cookie_t	dma_cookie;
-	};
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int	napi_id;
 #endif
 #ifdef CONFIG_NETWORK_SECMARK
 	__u32			secmark;
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4ad0706d40eb..90895b8dc7f2 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -19,7 +19,6 @@
 
 
 #include <linux/skbuff.h>
-#include <linux/dmaengine.h>
 #include <net/sock.h>
 #include <net/inet_connection_sock.h>
 #include <net/inet_timewait_sock.h>
@@ -169,13 +168,6 @@ struct tcp_sock {
 		struct iovec		*iov;
 		int			memory;
 		int			len;
-#ifdef CONFIG_NET_DMA
-		/* members for async copy */
-		struct dma_chan		*dma_chan;
-		int			wakeup;
-		struct dma_pinned_list	*pinned_list;
-		dma_cookie_t		dma_cookie;
-#endif
 	} ucopy;
 
 	u32	snd_wl1;	/* Sequence for window update		*/
diff --git a/include/net/netdma.h b/include/net/netdma.h
deleted file mode 100644
index 8ba8ce284eeb..000000000000
--- a/include/net/netdma.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * Copyright(c) 2004 - 2006 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called COPYING.
- */
-#ifndef NETDMA_H
-#define NETDMA_H
-#ifdef CONFIG_NET_DMA
-#include <linux/dmaengine.h>
-#include <linux/skbuff.h>
-
-int dma_skb_copy_datagram_iovec(struct dma_chan* chan,
-		struct sk_buff *skb, int offset, struct iovec *to,
-		size_t len, struct dma_pinned_list *pinned_list);
-
-#endif /* CONFIG_NET_DMA */
-#endif /* NETDMA_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index b9586a137cad..3353b47f3d40 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -231,7 +231,6 @@ struct cg_proto;
   *	@sk_receive_queue: incoming packets
   *	@sk_wmem_alloc: transmit queue bytes committed
   *	@sk_write_queue: Packet sending queue
-  *	@sk_async_wait_queue: DMA copied packets
   *	@sk_omem_alloc: "o" is "option" or "other"
   *	@sk_wmem_queued: persistent queue size
   *	@sk_forward_alloc: space allocated forward
@@ -354,10 +353,6 @@ struct sock {
 	struct sk_filter __rcu	*sk_filter;
 	struct socket_wq __rcu	*sk_wq;
 
-#ifdef CONFIG_NET_DMA
-	struct sk_buff_head	sk_async_wait_queue;
-#endif
-
 #ifdef CONFIG_XFRM
 	struct xfrm_policy	*sk_policy[2];
 #endif
@@ -2214,27 +2209,15 @@ void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
  * @skb: socket buffer to eat
- * @copied_early: flag indicating whether DMA operations copied this data early
  *
  * This routine must be called with interrupts disabled or with the socket
  * locked so that the sk_buff queue operation is ok.
 */
-#ifdef CONFIG_NET_DMA
-static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, bool copied_early)
-{
-	__skb_unlink(skb, &sk->sk_receive_queue);
-	if (!copied_early)
-		__kfree_skb(skb);
-	else
-		__skb_queue_tail(&sk->sk_async_wait_queue, skb);
-}
-#else
-static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, bool copied_early)
+static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
 	__kfree_skb(skb);
 }
-#endif
 
 static inline
 struct net *sock_net(const struct sock *sk)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 8c4dd63134d4..2c2f24ffa383 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -27,7 +27,6 @@
 #include <linux/cache.h>
 #include <linux/percpu.h>
 #include <linux/skbuff.h>
-#include <linux/dmaengine.h>
 #include <linux/crypto.h>
 #include <linux/cryptohash.h>
 #include <linux/kref.h>
@@ -267,7 +266,6 @@ extern int sysctl_tcp_adv_win_scale;
 extern int sysctl_tcp_tw_reuse;
 extern int sysctl_tcp_frto;
 extern int sysctl_tcp_low_latency;
-extern int sysctl_tcp_dma_copybreak;
 extern int sysctl_tcp_nometrics_save;
 extern int sysctl_tcp_moderate_rcvbuf;
 extern int sysctl_tcp_tso_win_divisor;
@@ -1023,12 +1021,6 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp)
 	tp->ucopy.len = 0;
 	tp->ucopy.memory = 0;
 	skb_queue_head_init(&tp->ucopy.prequeue);
-#ifdef CONFIG_NET_DMA
-	tp->ucopy.dma_chan = NULL;
-	tp->ucopy.wakeup = 0;
-	tp->ucopy.pinned_list = NULL;
-	tp->ucopy.dma_cookie = 0;
-#endif
 }
 
 bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 653cbbd9e7ad..d457005acedf 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -390,7 +390,6 @@ static const struct bin_table bin_net_ipv4_table[] = {
 	{ CTL_INT,	NET_TCP_MTU_PROBING,			"tcp_mtu_probing" },
 	{ CTL_INT,	NET_TCP_BASE_MSS,			"tcp_base_mss" },
 	{ CTL_INT,	NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS,	"tcp_workaround_signed_windows" },
-	{ CTL_INT,	NET_TCP_DMA_COPYBREAK,			"tcp_dma_copybreak" },
 	{ CTL_INT,	NET_TCP_SLOW_START_AFTER_IDLE,		"tcp_slow_start_after_idle" },
 	{ CTL_INT,	NET_CIPSOV4_CACHE_ENABLE,		"cipso_cache_enable" },
 	{ CTL_INT,	NET_CIPSOV4_CACHE_BUCKET_SIZE,		"cipso_cache_bucket_size" },
diff --git a/net/core/Makefile b/net/core/Makefile
index 9628c20acff6..5038f1ea0349 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -16,7 +16,6 @@ obj-y += net-sysfs.o
 obj-$(CONFIG_PROC_FS) += net-procfs.o
 obj-$(CONFIG_NET_PKTGEN) += pktgen.o
 obj-$(CONFIG_NETPOLL) += netpoll.o
-obj-$(CONFIG_NET_DMA) += user_dma.o
 obj-$(CONFIG_FIB_RULES) += fib_rules.o
 obj-$(CONFIG_TRACEPOINTS) += net-traces.o
 obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
diff --git a/net/core/dev.c b/net/core/dev.c
index b1b0c8d4d7df..5e37e9abe8c5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1266,7 +1266,6 @@ static int __dev_open(struct net_device *dev)
 		clear_bit(__LINK_STATE_START, &dev->state);
 	else {
 		dev->flags |= IFF_UP;
-		net_dmaengine_get();
 		dev_set_rx_mode(dev);
 		dev_activate(dev);
 		add_device_randomness(dev->dev_addr, dev->addr_len);
@@ -1342,7 +1341,6 @@ static int __dev_close_many(struct list_head *head)
 			ops->ndo_stop(dev);
 
 		dev->flags &= ~IFF_UP;
-		net_dmaengine_put();
 	}
 
 	return 0;
@@ -4405,14 +4403,6 @@ static void net_rx_action(struct softirq_action *h)
 out:
 	net_rps_action_and_irq_enable(sd);
 
-#ifdef CONFIG_NET_DMA
-	/*
-	 * There may not be any more sk_buffs coming right now, so push
-	 * any pending DMA copies to hardware
-	 */
-	dma_issue_pending_all();
-#endif
-
 	return;
 
 softnet_break:
diff --git a/net/core/sock.c b/net/core/sock.c
index c0fc6bdad1e3..2f143c3b190a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1452,9 +1452,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		atomic_set(&newsk->sk_omem_alloc, 0);
 		skb_queue_head_init(&newsk->sk_receive_queue);
 		skb_queue_head_init(&newsk->sk_write_queue);
-#ifdef CONFIG_NET_DMA
-		skb_queue_head_init(&newsk->sk_async_wait_queue);
-#endif
 
 		spin_lock_init(&newsk->sk_dst_lock);
 		rwlock_init(&newsk->sk_callback_lock);
@@ -2265,9 +2262,6 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	skb_queue_head_init(&sk->sk_receive_queue);
 	skb_queue_head_init(&sk->sk_write_queue);
 	skb_queue_head_init(&sk->sk_error_queue);
-#ifdef CONFIG_NET_DMA
-	skb_queue_head_init(&sk->sk_async_wait_queue);
-#endif
 
 	sk->sk_send_head	=	NULL;
 
diff --git a/net/core/user_dma.c b/net/core/user_dma.c
deleted file mode 100644
index 1b5fefdb8198..000000000000
--- a/net/core/user_dma.c
+++ /dev/null
@@ -1,131 +0,0 @@
-/*
- * Copyright(c) 2004 - 2006 Intel Corporation. All rights reserved.
- * Portions based on net/core/datagram.c and copyrighted by their authors.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called COPYING.
- */
-
-/*
- * This code allows the net stack to make use of a DMA engine for
- * skb to iovec copies.
- */
-
-#include <linux/dmaengine.h>
-#include <linux/socket.h>
-#include <linux/export.h>
-#include <net/tcp.h>
-#include <net/netdma.h>
-
-#define NET_DMA_DEFAULT_COPYBREAK 4096
-
-int sysctl_tcp_dma_copybreak = NET_DMA_DEFAULT_COPYBREAK;
-EXPORT_SYMBOL(sysctl_tcp_dma_copybreak);
-
-/**
- *	dma_skb_copy_datagram_iovec - Copy a datagram to an iovec.
- *	@skb - buffer to copy
- *	@offset - offset in the buffer to start copying from
- *	@iovec - io vector to copy to
- *	@len - amount of data to copy from buffer to iovec
- *	@pinned_list - locked iovec buffer data
- *
- *	Note: the iovec is modified during the copy.
- */
-int dma_skb_copy_datagram_iovec(struct dma_chan *chan,
-			struct sk_buff *skb, int offset, struct iovec *to,
-			size_t len, struct dma_pinned_list *pinned_list)
-{
-	int start = skb_headlen(skb);
-	int i, copy = start - offset;
-	struct sk_buff *frag_iter;
-	dma_cookie_t cookie = 0;
-
-	/* Copy header. */
-	if (copy > 0) {
-		if (copy > len)
-			copy = len;
-		cookie = dma_memcpy_to_iovec(chan, to, pinned_list,
-					    skb->data + offset, copy);
-		if (cookie < 0)
-			goto fault;
-		len -= copy;
-		if (len == 0)
-			goto end;
-		offset += copy;
-	}
-
-	/* Copy paged appendix. Hmm... why does this look so complicated? */
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		int end;
-		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-		WARN_ON(start > offset + len);
-
-		end = start + skb_frag_size(frag);
-		copy = end - offset;
-		if (copy > 0) {
-			struct page *page = skb_frag_page(frag);
-
-			if (copy > len)
-				copy = len;
-
-			cookie = dma_memcpy_pg_to_iovec(chan, to, pinned_list, page,
-					frag->page_offset + offset - start, copy);
-			if (cookie < 0)
-				goto fault;
-			len -= copy;
-			if (len == 0)
-				goto end;
-			offset += copy;
-		}
-		start = end;
-	}
-
-	skb_walk_frags(skb, frag_iter) {
-		int end;
-
-		WARN_ON(start > offset + len);
-
-		end = start + frag_iter->len;
-		copy = end - offset;
-		if (copy > 0) {
-			if (copy > len)
-				copy = len;
-			cookie = dma_skb_copy_datagram_iovec(chan, frag_iter,
-							     offset - start,
-							     to, copy,
-							     pinned_list);
-			if (cookie < 0)
-				goto fault;
-			len -= copy;
-			if (len == 0)
-				goto end;
-			offset += copy;
-		}
-		start = end;
-	}
-
-end:
-	if (!len) {
-		skb->dma_cookie = cookie;
-		return cookie;
-	}
-
-fault:
-	return -EFAULT;
-}
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index eb892b4f4814..f9076f295b13 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -848,7 +848,7 @@ int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		default:
 			dccp_pr_debug("packet_type=%s\n",
 				      dccp_packet_name(dh->dccph_type));
-			sk_eat_skb(sk, skb, false);
+			sk_eat_skb(sk, skb);
 		}
 verify_sock_status:
 		if (sock_flag(sk, SOCK_DONE)) {
@@ -905,7 +905,7 @@ verify_sock_status:
 			len = skb->len;
 	found_fin_ok:
 		if (!(flags & MSG_PEEK))
-			sk_eat_skb(sk, skb, false);
+			sk_eat_skb(sk, skb);
 		break;
 	} while (1);
 out:
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 44eba052b43d..c3d2a48481f1 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -635,15 +635,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-#ifdef CONFIG_NET_DMA
-	{
-		.procname	= "tcp_dma_copybreak",
-		.data		= &sysctl_tcp_dma_copybreak,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-#endif
 	{
 		.procname	= "tcp_slow_start_after_idle",
 		.data		= &sysctl_tcp_slow_start_after_idle,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 97c8f5620c43..28595a364f09 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -274,7 +274,6 @@
 #include <net/tcp.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
-#include <net/netdma.h>
 #include <net/sock.h>
 
 #include <asm/uaccess.h>
@@ -1454,39 +1453,6 @@ static void tcp_prequeue_process(struct sock *sk)
 	tp->ucopy.memory = 0;
 }
 
-#ifdef CONFIG_NET_DMA
-static void tcp_service_net_dma(struct sock *sk, bool wait)
-{
-	dma_cookie_t done, used;
-	dma_cookie_t last_issued;
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (!tp->ucopy.dma_chan)
-		return;
-
-	last_issued = tp->ucopy.dma_cookie;
-	dma_async_issue_pending(tp->ucopy.dma_chan);
-
-	do {
-		if (dma_async_is_tx_complete(tp->ucopy.dma_chan,
-					      last_issued, &done,
-					      &used) == DMA_COMPLETE) {
-			/* Safe to free early-copied skbs now */
-			__skb_queue_purge(&sk->sk_async_wait_queue);
-			break;
-		} else {
-			struct sk_buff *skb;
-			while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
-			       (dma_async_is_complete(skb->dma_cookie, done,
-						      used) == DMA_COMPLETE)) {
-				__skb_dequeue(&sk->sk_async_wait_queue);
-				kfree_skb(skb);
-			}
-		}
-	} while (wait);
-}
-#endif
-
 static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 {
 	struct sk_buff *skb;
@@ -1504,7 +1470,7 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 		 * splitted a fat GRO packet, while we released socket lock
 		 * in skb_splice_bits()
 		 */
-		sk_eat_skb(sk, skb, false);
+		sk_eat_skb(sk, skb);
 	}
 	return NULL;
 }
@@ -1570,11 +1536,11 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 				continue;
 		}
 		if (tcp_hdr(skb)->fin) {
-			sk_eat_skb(sk, skb, false);
+			sk_eat_skb(sk, skb);
 			++seq;
 			break;
 		}
-		sk_eat_skb(sk, skb, false);
+		sk_eat_skb(sk, skb);
 		if (!desc->count)
 			break;
 		tp->copied_seq = seq;
@@ -1612,7 +1578,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	int target;		/* Read at least this many bytes */
 	long timeo;
 	struct task_struct *user_recv = NULL;
-	bool copied_early = false;
 	struct sk_buff *skb;
 	u32 urg_hole = 0;
 
@@ -1655,28 +1620,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 
-#ifdef CONFIG_NET_DMA
-	tp->ucopy.dma_chan = NULL;
-	preempt_disable();
-	skb = skb_peek_tail(&sk->sk_receive_queue);
-	{
-		int available = 0;
-
-		if (skb)
-			available = TCP_SKB_CB(skb)->seq + skb->len - (*seq);
-		if ((available < target) &&
-		    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
-		    !sysctl_tcp_low_latency &&
-		    net_dma_find_channel()) {
-			preempt_enable();
-			tp->ucopy.pinned_list =
-					dma_pin_iovec_pages(msg->msg_iov, len);
-		} else {
-			preempt_enable();
-		}
-	}
-#endif
-
 	do {
 		u32 offset;
 
@@ -1807,16 +1750,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			/* __ Set realtime policy in scheduler __ */
 		}
 
-#ifdef CONFIG_NET_DMA
-		if (tp->ucopy.dma_chan) {
-			if (tp->rcv_wnd == 0 &&
-			    !skb_queue_empty(&sk->sk_async_wait_queue)) {
-				tcp_service_net_dma(sk, true);
-				tcp_cleanup_rbuf(sk, copied);
-			} else
-				dma_async_issue_pending(tp->ucopy.dma_chan);
-		}
-#endif
 		if (copied >= target) {
 			/* Do not sleep, just process backlog. */
 			release_sock(sk);
@@ -1824,11 +1757,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		} else
 			sk_wait_data(sk, &timeo);
 
-#ifdef CONFIG_NET_DMA
-		tcp_service_net_dma(sk, false);  /* Don't block */
-		tp->ucopy.wakeup = 0;
-#endif
-
 		if (user_recv) {
 			int chunk;
 
@@ -1886,43 +1814,13 @@ do_prequeue:
 		}
 
 		if (!(flags & MSG_TRUNC)) {
-#ifdef CONFIG_NET_DMA
-			if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-				tp->ucopy.dma_chan = net_dma_find_channel();
-
-			if (tp->ucopy.dma_chan) {
-				tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
-					tp->ucopy.dma_chan, skb, offset,
-					msg->msg_iov, used,
-					tp->ucopy.pinned_list);
-
-				if (tp->ucopy.dma_cookie < 0) {
-
-					pr_alert("%s: dma_cookie < 0\n",
-						 __func__);
-
-					/* Exception. Bailout! */
-					if (!copied)
-						copied = -EFAULT;
-					break;
-				}
-
-				dma_async_issue_pending(tp->ucopy.dma_chan);
-
-				if ((offset + used) == skb->len)
-					copied_early = true;
-
-			} else
-#endif
-			{
-				err = skb_copy_datagram_iovec(skb, offset,
-						msg->msg_iov, used);
-				if (err) {
-					/* Exception. Bailout! */
-					if (!copied)
-						copied = -EFAULT;
-					break;
-				}
+			err = skb_copy_datagram_iovec(skb, offset,
+						      msg->msg_iov, used);
+			if (err) {
+				/* Exception. Bailout! */
+				if (!copied)
+					copied = -EFAULT;
+				break;
 			}
 		}
 
@@ -1942,19 +1840,15 @@ skip_copy:
 
 		if (tcp_hdr(skb)->fin)
 			goto found_fin_ok;
-		if (!(flags & MSG_PEEK)) {
-			sk_eat_skb(sk, skb, copied_early);
-			copied_early = false;
-		}
+		if (!(flags & MSG_PEEK))
+			sk_eat_skb(sk, skb);
 		continue;
 
 	found_fin_ok:
 		/* Process the FIN. */
 		++*seq;
-		if (!(flags & MSG_PEEK)) {
-			sk_eat_skb(sk, skb, copied_early);
-			copied_early = false;
-		}
+		if (!(flags & MSG_PEEK))
+			sk_eat_skb(sk, skb);
 		break;
 	} while (len > 0);
 
@@ -1977,16 +1871,6 @@ skip_copy:
 		tp->ucopy.len = 0;
 	}
 
-#ifdef CONFIG_NET_DMA
-	tcp_service_net_dma(sk, true);  /* Wait for queue to drain */
-	tp->ucopy.dma_chan = NULL;
-
-	if (tp->ucopy.pinned_list) {
-		dma_unpin_iovec_pages(tp->ucopy.pinned_list);
-		tp->ucopy.pinned_list = NULL;
-	}
-#endif
-
 	/* According to UNIX98, msg_name/msg_namelen are ignored
 	 * on connected socket. I was just happy when found this 8) --ANK
 	 */
@@ -2330,9 +2214,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	__skb_queue_purge(&sk->sk_receive_queue);
 	tcp_write_queue_purge(sk);
 	__skb_queue_purge(&tp->out_of_order_queue);
-#ifdef CONFIG_NET_DMA
-	__skb_queue_purge(&sk->sk_async_wait_queue);
-#endif
 
 	inet->inet_dport = 0;
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eeaac399420d..1342e9851f97 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -73,7 +73,6 @@
 #include <net/inet_common.h>
 #include <linux/ipsec.h>
 #include <asm/unaligned.h>
-#include <net/netdma.h>
 
 int sysctl_tcp_timestamps __read_mostly = 1;
 int sysctl_tcp_window_scaling __read_mostly = 1;
@@ -4970,53 +4969,6 @@ static inline bool tcp_checksum_complete_user(struct sock *sk,
 	       __tcp_checksum_complete_user(sk, skb);
 }
 
-#ifdef CONFIG_NET_DMA
-static bool tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb,
-				  int hlen)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	int chunk = skb->len - hlen;
-	int dma_cookie;
-	bool copied_early = false;
-
-	if (tp->ucopy.wakeup)
-		return false;
-
-	if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-		tp->ucopy.dma_chan = net_dma_find_channel();
-
-	if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) {
-
-		dma_cookie = dma_skb_copy_datagram_iovec(tp->ucopy.dma_chan,
-							 skb, hlen,
-							 tp->ucopy.iov, chunk,
-							 tp->ucopy.pinned_list);
-
-		if (dma_cookie < 0)
-			goto out;
-
-		tp->ucopy.dma_cookie = dma_cookie;
-		copied_early = true;
-
-		tp->ucopy.len -= chunk;
-		tp->copied_seq += chunk;
-		tcp_rcv_space_adjust(sk);
-
-		if ((tp->ucopy.len == 0) ||
-		    (tcp_flag_word(tcp_hdr(skb)) & TCP_FLAG_PSH) ||
-		    (atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1))) {
-			tp->ucopy.wakeup = 1;
-			sk->sk_data_ready(sk, 0);
-		}
-	} else if (chunk > 0) {
-		tp->ucopy.wakeup = 1;
-		sk->sk_data_ready(sk, 0);
-	}
-out:
-	return copied_early;
-}
-#endif /* CONFIG_NET_DMA */
-
 /* Does PAWS and seqno based validation of an incoming segment, flags will
  * play significant role here.
  */
@@ -5201,14 +5153,6 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 
 			if (tp->copied_seq == tp->rcv_nxt &&
 			    len - tcp_header_len <= tp->ucopy.len) {
-#ifdef CONFIG_NET_DMA
-				if (tp->ucopy.task == current &&
-				    sock_owned_by_user(sk) &&
-				    tcp_dma_try_early_copy(sk, skb, tcp_header_len)) {
-					copied_early = 1;
-					eaten = 1;
-				}
-#endif
 				if (tp->ucopy.task == current &&
 				    sock_owned_by_user(sk) && !copied_early) {
 					__set_current_state(TASK_RUNNING);
@@ -5274,11 +5218,6 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			if (!copied_early || tp->rcv_nxt != tp->rcv_wup)
 				__tcp_ack_snd_check(sk, 0);
 no_ack:
-#ifdef CONFIG_NET_DMA
-			if (copied_early)
-				__skb_queue_tail(&sk->sk_async_wait_queue, skb);
-			else
-#endif
 			if (eaten)
 				kfree_skb_partial(skb, fragstolen);
 			sk->sk_data_ready(sk, 0);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3cf976510497..737c2e270ee3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -72,7 +72,6 @@
 #include <net/inet_common.h>
 #include <net/timewait_sock.h>
 #include <net/xfrm.h>
-#include <net/netdma.h>
 #include <net/secure_seq.h>
 #include <net/tcp_memcontrol.h>
 #include <net/busy_poll.h>
@@ -1999,18 +1998,8 @@ process:
 	bh_lock_sock_nested(sk);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
-#ifdef CONFIG_NET_DMA
-		struct tcp_sock *tp = tcp_sk(sk);
-		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-			tp->ucopy.dma_chan = net_dma_find_channel();
-		if (tp->ucopy.dma_chan)
+		if (!tcp_prequeue(sk, skb))
 			ret = tcp_v4_do_rcv(sk, skb);
-		else
-#endif
-		{
-			if (!tcp_prequeue(sk, skb))
-				ret = tcp_v4_do_rcv(sk, skb);
-		}
 	} else if (unlikely(sk_add_backlog(sk, skb,
 					   sk->sk_rcvbuf + sk->sk_sndbuf))) {
 		bh_unlock_sock(sk);
@@ -2169,11 +2158,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	}
 #endif
 
-#ifdef CONFIG_NET_DMA
-	/* Cleans up our sk_async_wait_queue */
-	__skb_queue_purge(&sk->sk_async_wait_queue);
-#endif
-
 	/* Clean prequeue, it must be empty really */
 	__skb_queue_purge(&tp->ucopy.prequeue);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 889079b2ea85..cb21fccf2089 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -59,7 +59,6 @@
 #include <net/snmp.h>
 #include <net/dsfield.h>
 #include <net/timewait_sock.h>
-#include <net/netdma.h>
 #include <net/inet_common.h>
 #include <net/secure_seq.h>
 #include <net/tcp_memcontrol.h>
@@ -1520,18 +1519,8 @@ process:
 	bh_lock_sock_nested(sk);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
-#ifdef CONFIG_NET_DMA
-		struct tcp_sock *tp = tcp_sk(sk);
-		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-			tp->ucopy.dma_chan = net_dma_find_channel();
-		if (tp->ucopy.dma_chan)
+		if (!tcp_prequeue(sk, skb))
 			ret = tcp_v6_do_rcv(sk, skb);
-		else
-#endif
-		{
-			if (!tcp_prequeue(sk, skb))
-				ret = tcp_v6_do_rcv(sk, skb);
-		}
 	} else if (unlikely(sk_add_backlog(sk, skb,
 					   sk->sk_rcvbuf + sk->sk_sndbuf))) {
 		bh_unlock_sock(sk);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 0080d2b0a8ae..bb9cbc17d926 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -839,7 +839,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 		if (!(flags & MSG_PEEK)) {
 			spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags);
-			sk_eat_skb(sk, skb, false);
+			sk_eat_skb(sk, skb);
 			spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags);
 			*seq = 0;
 		}
@@ -861,10 +861,10 @@ copy_uaddr:
 		llc_cmsg_rcv(msg, skb);
 
 	if (!(flags & MSG_PEEK)) {
-			spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags);
-			sk_eat_skb(sk, skb, false);
-			spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags);
-			*seq = 0;
+		spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags);
+		sk_eat_skb(sk, skb);
+		spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags);
+		*seq = 0;
 	}
 
 	goto out;
-- 
cgit v1.2.3


From 3f334078567245429540e6461c81c749fce87f70 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 30 Dec 2013 17:12:07 -0800
Subject: net: make tcp_cleanup_rbuf private

net_dma was the only external user so this can become local to tcp.c
again.

Cc: James Morris <jmorris@namei.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 include/net/tcp.h | 1 -
 net/ipv4/tcp.c    | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2c2f24ffa383..7ffbcbf90a64 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -371,7 +371,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			 const struct tcphdr *th, unsigned int len);
 void tcp_rcv_space_adjust(struct sock *sk);
-void tcp_cleanup_rbuf(struct sock *sk, int copied);
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
 void tcp_twsk_destructor(struct sock *sk);
 ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 28595a364f09..4874a0efd34a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1377,7 +1377,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-void tcp_cleanup_rbuf(struct sock *sk, int copied)
+static void tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
-- 
cgit v1.2.3


From 24a2d43d8886f5a29c3cf108927f630c545a9a38 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 27 Sep 2014 09:50:55 -0700
Subject: ipv4: rename ip_options_echo to __ip_options_echo()

ip_options_echo() assumes struct ip_options is provided in &IPCB(skb)->opt
Lets break this assumption, but provide a helper to not change all call points.

ip_send_unicast_reply() gets a new struct ip_options pointer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h      | 15 ++++++++++++---
 net/ipv4/ip_options.c |  6 ++----
 net/ipv4/ip_output.c  |  8 +++++---
 net/ipv4/tcp_ipv4.c   | 10 ++++++----
 4 files changed, 25 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index fcd9068fb8c3..0bb620702929 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -180,8 +180,10 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
 	return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
 }
 
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
-			   __be32 saddr, const struct ip_reply_arg *arg,
+void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+			   const struct ip_options *sopt,
+			   __be32 daddr, __be32 saddr,
+			   const struct ip_reply_arg *arg,
 			   unsigned int len);
 
 #define IP_INC_STATS(net, field)	SNMP_INC_STATS64((net)->mib.ip_statistics, field)
@@ -511,7 +513,14 @@ int ip_forward(struct sk_buff *skb);
  
 void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
 		      __be32 daddr, struct rtable *rt, int is_frag);
-int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb);
+
+int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb,
+		      const struct ip_options *sopt);
+static inline int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)
+{
+	return __ip_options_echo(dopt, skb, &IPCB(skb)->opt);
+}
+
 void ip_options_fragment(struct sk_buff *skb);
 int ip_options_compile(struct net *net, struct ip_options *opt,
 		       struct sk_buff *skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ad382499bace..5b3d91be2db0 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -87,17 +87,15 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
  * NOTE: dopt cannot point to skb.
  */
 
-int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)
+int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb,
+		      const struct ip_options *sopt)
 {
-	const struct ip_options *sopt;
 	unsigned char *sptr, *dptr;
 	int soffset, doffset;
 	int	optlen;
 
 	memset(dopt, 0, sizeof(struct ip_options));
 
-	sopt = &(IPCB(skb)->opt);
-
 	if (sopt->optlen == 0)
 		return 0;
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 215af2b155cb..c8fa62476461 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1522,8 +1522,10 @@ static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
 	.uc_ttl		= -1,
 };
 
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
-			   __be32 saddr, const struct ip_reply_arg *arg,
+void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+			   const struct ip_options *sopt,
+			   __be32 daddr, __be32 saddr,
+			   const struct ip_reply_arg *arg,
 			   unsigned int len)
 {
 	struct ip_options_data replyopts;
@@ -1534,7 +1536,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	struct sock *sk;
 	struct inet_sock *inet;
 
-	if (ip_options_echo(&replyopts.opt.opt, skb))
+	if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))
 		return;
 
 	ipc.addr = daddr;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3b2e49cb2b61..28ab90382c01 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -681,8 +681,9 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 
 	net = dev_net(skb_dst(skb)->dev);
 	arg.tos = ip_hdr(skb)->tos;
-	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
-			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
+	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
+			      &arg, arg.iov[0].iov_len);
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
@@ -764,8 +765,9 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
-	ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
-			      ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
+	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
+			      &arg, arg.iov[0].iov_len);
 
 	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
 }
-- 
cgit v1.2.3


From a224772db8420ecb7ce91a9ba5d535ee3a50d982 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 27 Sep 2014 09:50:56 -0700
Subject: ipv6: add a struct inet6_skb_parm param to ipv6_opt_accepted()

ipv6_opt_accepted() assumes IP6CB(skb) holds the struct inet6_skb_parm
that it needs. Lets not assume this, as TCP stack might use a different
place.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h    | 3 ++-
 net/dccp/ipv6.c       | 2 +-
 net/ipv6/af_inet6.c   | 4 ++--
 net/ipv6/syncookies.c | 2 +-
 net/ipv6/tcp_ipv6.c   | 5 +++--
 5 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 7e247e9b8765..97f472012438 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -288,7 +288,8 @@ struct ipv6_txoptions *ipv6_renew_options(struct sock *sk,
 struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
 					  struct ipv6_txoptions *opt);
 
-bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb);
+bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
+		       const struct inet6_skb_parm *opt);
 
 static inline bool ipv6_accept_ra(struct inet6_dev *idev)
 {
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 04cb17d4b0ce..ad2acfe1ca61 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -404,7 +404,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 
-	if (ipv6_opt_accepted(sk, skb) ||
+	if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
 		atomic_inc(&skb->users);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e4865a3ebe1d..34f726f59814 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -672,10 +672,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(inet6_sk_rebuild_header);
 
-bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb)
+bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
+		       const struct inet6_skb_parm *opt)
 {
 	const struct ipv6_pinfo *np = inet6_sk(sk);
-	const struct inet6_skb_parm *opt = IP6CB(skb);
 
 	if (np->rxopt.all) {
 		if ((opt->hop && (np->rxopt.bits.hopopts ||
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index c643dc907ce7..9a2838e93cc5 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -203,7 +203,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	ireq->ir_num = ntohs(th->dest);
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
-	if (ipv6_opt_accepted(sk, skb) ||
+	if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
 		atomic_inc(&skb->users);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index de51a88bec6f..9400b4326f22 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -742,7 +742,8 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
 		ireq->ir_iif = inet6_iif(skb);
 
 	if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
-	    (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo ||
+	    (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
+	     np->rxopt.bits.rxinfo ||
 	     np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
 	     np->rxopt.bits.rxohlim || np->repflow)) {
 		atomic_inc(&skb->users);
@@ -1367,7 +1368,7 @@ ipv6_pktoptions:
 			np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
 		if (np->repflow)
 			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
-		if (ipv6_opt_accepted(sk, opt_skb)) {
+		if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
 			skb_set_owner_r(opt_skb, sk);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
 		} else {
-- 
cgit v1.2.3


From 971f10eca186cab238c49daa91f703c5a001b0b1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 27 Sep 2014 09:50:57 -0700
Subject: tcp: better TCP_SKB_CB layout to reduce cache line misses

TCP maintains lists of skb in write queue, and in receive queues
(in order and out of order queues)

Scanning these lists both in input and output path usually requires
access to skb->next, TCP_SKB_CB(skb)->seq, and TCP_SKB_CB(skb)->end_seq

These fields are currently in two different cache lines, meaning we
waste lot of memory bandwidth when these queues are big and flows
have either packet drops or packet reorders.

We can move TCP_SKB_CB(skb)->header at the end of TCP_SKB_CB, because
this header is not used in fast path. This allows TCP to search much faster
in the skb lists.

Even with regular flows, we save one cache line miss in fast path.

Thanks to Christoph Paasch for noticing we need to cleanup
skb->cb[] (IPCB/IP6CB) before entering IP stack in tx path,
and that I forgot IPCB use in tcp_v4_hnd_req() and tcp_v4_save_options().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 12 ++++++------
 net/ipv4/tcp_ipv4.c   | 19 ++++++++++++-------
 net/ipv4/tcp_output.c |  5 +++++
 net/ipv6/tcp_ipv6.c   |  7 +++++++
 4 files changed, 30 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index a4201ef216e8..4dc6641ee990 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -696,12 +696,6 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
  * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately.
  */
 struct tcp_skb_cb {
-	union {
-		struct inet_skb_parm	h4;
-#if IS_ENABLED(CONFIG_IPV6)
-		struct inet6_skb_parm	h6;
-#endif
-	} header;	/* For incoming frames		*/
 	__u32		seq;		/* Starting sequence number	*/
 	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
 	__u32		tcp_tw_isn;	/* isn chosen by tcp_timewait_state_process() */
@@ -720,6 +714,12 @@ struct tcp_skb_cb {
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
 	/* 1 byte hole */
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
+	union {
+		struct inet_skb_parm	h4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct inet6_skb_parm	h6;
+#endif
+	} header;	/* For incoming frames		*/
 };
 
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 28ab90382c01..9ce3eac02957 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -886,18 +886,16 @@ EXPORT_SYMBOL(tcp_syn_flood_action);
  */
 static struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
 {
-	const struct ip_options *opt = &(IPCB(skb)->opt);
+	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	struct ip_options_rcu *dopt = NULL;
 
 	if (opt && opt->optlen) {
 		int opt_size = sizeof(*dopt) + opt->optlen;
 
 		dopt = kmalloc(opt_size, GFP_ATOMIC);
-		if (dopt) {
-			if (ip_options_echo(&dopt->opt, skb)) {
-				kfree(dopt);
-				dopt = NULL;
-			}
+		if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) {
+			kfree(dopt);
+			dopt = NULL;
 		}
 	}
 	return dopt;
@@ -1431,7 +1429,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_SYN_COOKIES
 	if (!th->syn)
-		sk = cookie_v4_check(sk, skb, &(IPCB(skb)->opt));
+		sk = cookie_v4_check(sk, skb, &TCP_SKB_CB(skb)->header.h4.opt);
 #endif
 	return sk;
 }
@@ -1636,6 +1634,13 @@ int tcp_v4_rcv(struct sk_buff *skb)
 
 	th = tcp_hdr(skb);
 	iph = ip_hdr(skb);
+	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+	 * barrier() makes sure compiler wont play fool^Waliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
+		sizeof(struct inet_skb_parm));
+	barrier();
+
 	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff * 4);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f173b1c4f815..a462fb1db896 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -974,6 +974,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	/* Our usage of tstamp should remain private */
 	skb->tstamp.tv64 = 0;
+
+	/* Cleanup our debris for IP stacks */
+	memset(skb->cb, 0, max(sizeof(struct inet_skb_parm),
+			       sizeof(struct inet6_skb_parm)));
+
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
 
 	if (likely(err <= 0))
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9400b4326f22..132bac137aed 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1412,6 +1412,13 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 
 	th = tcp_hdr(skb);
 	hdr = ipv6_hdr(skb);
+	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+	 * barrier() makes sure compiler wont play fool^Waliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb),
+		sizeof(struct inet6_skb_parm));
+	barrier();
+
 	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff*4);
-- 
cgit v1.2.3


From cd7d8498c9a5d510c64db38d9f4f4fbc41790f09 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 24 Sep 2014 04:11:22 -0700
Subject: tcp: change tcp_skb_pcount() location

Our goal is to access no more than one cache line access per skb in
a write or receive queue when doing the various walks.

After recent TCP_SKB_CB() reorganizations, it is almost done.

Last part is tcp_skb_pcount() which currently uses
skb_shinfo(skb)->gso_segs, which is a terrible choice, because it needs
3 cache lines in current kernel (skb->head, skb->end, and
shinfo->gso_segs are all in 3 different cache lines, far from skb->cb)

This very simple patch reuses space currently taken by tcp_tw_isn
only in input path, as tcp_skb_pcount is only needed for skb stored in
write queue.

This considerably speeds up tcp_ack(), granted we avoid shinfo->tx_flags
to get SKBTX_ACK_TSTAMP, which seems possible.

This also speeds up all sack processing in general.

This speeds up tcp_sendmsg() because it no longer has to access/dirty
shinfo.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 23 +++++++++++++++++++++--
 net/ipv4/tcp.c        |  4 ++--
 net/ipv4/tcp_input.c  |  8 ++++----
 net/ipv4/tcp_output.c |  9 ++++++---
 4 files changed, 33 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4dc6641ee990..02a9a2c366bf 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -698,7 +698,16 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
 struct tcp_skb_cb {
 	__u32		seq;		/* Starting sequence number	*/
 	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/
-	__u32		tcp_tw_isn;	/* isn chosen by tcp_timewait_state_process() */
+	union {
+		/* Note : tcp_tw_isn is used in input path only
+		 *	  (isn chosen by tcp_timewait_state_process())
+		 *
+		 * 	  tcp_gso_segs is used in write queue only,
+		 *	  cf tcp_skb_pcount()
+		 */
+		__u32		tcp_tw_isn;
+		__u32		tcp_gso_segs;
+	};
 	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
 
 	__u8		sacked;		/* State flags for SACK/FACK.	*/
@@ -746,7 +755,17 @@ TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb,
  */
 static inline int tcp_skb_pcount(const struct sk_buff *skb)
 {
-	return skb_shinfo(skb)->gso_segs;
+	return TCP_SKB_CB(skb)->tcp_gso_segs;
+}
+
+static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs)
+{
+	TCP_SKB_CB(skb)->tcp_gso_segs = segs;
+}
+
+static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs)
+{
+	TCP_SKB_CB(skb)->tcp_gso_segs += segs;
 }
 
 /* This is valid iff tcp_skb_pcount() > 1. */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 553b01f52f71..87289e51be00 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -963,7 +963,7 @@ new_segment:
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		tp->write_seq += copy;
 		TCP_SKB_CB(skb)->end_seq += copy;
-		skb_shinfo(skb)->gso_segs = 0;
+		tcp_skb_pcount_set(skb, 0);
 
 		if (!copied)
 			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
@@ -1261,7 +1261,7 @@ new_segment:
 
 			tp->write_seq += copy;
 			TCP_SKB_CB(skb)->end_seq += copy;
-			skb_shinfo(skb)->gso_segs = 0;
+			tcp_skb_pcount_set(skb, 0);
 
 			from += copy;
 			copied += copy;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f3f016a15c5a..2c0af90231cf 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1295,9 +1295,9 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	TCP_SKB_CB(prev)->end_seq += shifted;
 	TCP_SKB_CB(skb)->seq += shifted;
 
-	skb_shinfo(prev)->gso_segs += pcount;
-	BUG_ON(skb_shinfo(skb)->gso_segs < pcount);
-	skb_shinfo(skb)->gso_segs -= pcount;
+	tcp_skb_pcount_add(prev, pcount);
+	BUG_ON(tcp_skb_pcount(skb) < pcount);
+	tcp_skb_pcount_add(skb, -pcount);
 
 	/* When we're adding to gso_segs == 1, gso_size will be zero,
 	 * in theory this shouldn't be necessary but as long as DSACK
@@ -1310,7 +1310,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	}
 
 	/* CHECKME: To clear or not to clear? Mimics normal skb currently */
-	if (skb_shinfo(skb)->gso_segs <= 1) {
+	if (tcp_skb_pcount(skb) <= 1) {
 		skb_shinfo(skb)->gso_size = 0;
 		skb_shinfo(skb)->gso_type = 0;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a462fb1db896..4d92703df4c6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -384,7 +384,7 @@ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
 	TCP_SKB_CB(skb)->tcp_flags = flags;
 	TCP_SKB_CB(skb)->sacked = 0;
 
-	shinfo->gso_segs = 1;
+	tcp_skb_pcount_set(skb, 1);
 	shinfo->gso_size = 0;
 	shinfo->gso_type = 0;
 
@@ -972,6 +972,9 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
 			      tcp_skb_pcount(skb));
 
+	/* OK, its time to fill skb_shinfo(skb)->gso_segs */
+	skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb);
+
 	/* Our usage of tstamp should remain private */
 	skb->tstamp.tv64 = 0;
 
@@ -1019,11 +1022,11 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
 		/* Avoid the costly divide in the normal
 		 * non-TSO case.
 		 */
-		shinfo->gso_segs = 1;
+		tcp_skb_pcount_set(skb, 1);
 		shinfo->gso_size = 0;
 		shinfo->gso_type = 0;
 	} else {
-		shinfo->gso_segs = DIV_ROUND_UP(skb->len, mss_now);
+		tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now));
 		shinfo->gso_size = mss_now;
 		shinfo->gso_type = sk->sk_gso_type;
 	}
-- 
cgit v1.2.3


From b2f2af21e37f6d12bd735c27da8942331aa9b3d7 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 24 Sep 2014 17:05:18 -0700
Subject: net: dsa: allow enabling and disable switch ports

Whenever a per-port network device is used/unused, invoke the switch
driver port_enable/port_disable callbacks to allow saving as much power
as possible by disabling unused parts of the switch (RX/TX logic, memory
arrays, PHYs...). We supply a PHY device argument to make sure the
switch driver can act on the PHY device if needed (like putting/taking
the PHY out of deep low power mode).

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  8 ++++++++
 net/dsa/slave.c   | 14 ++++++++++++++
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index d8054fb4a4df..4f664fe0e42c 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -224,6 +224,14 @@ struct dsa_switch_driver {
 	 */
 	int	(*suspend)(struct dsa_switch *ds);
 	int	(*resume)(struct dsa_switch *ds);
+
+	/*
+	 * Port enable/disable
+	 */
+	int	(*port_enable)(struct dsa_switch *ds, int port,
+			       struct phy_device *phy);
+	void	(*port_disable)(struct dsa_switch *ds, int port,
+				struct phy_device *phy);
 };
 
 void register_switch_driver(struct dsa_switch_driver *type);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 4392e983abda..182d30ae6818 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -62,6 +62,7 @@ static int dsa_slave_open(struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct net_device *master = p->parent->dst->master_netdev;
+	struct dsa_switch *ds = p->parent;
 	int err;
 
 	if (!(master->flags & IFF_UP))
@@ -84,11 +85,20 @@ static int dsa_slave_open(struct net_device *dev)
 			goto clear_allmulti;
 	}
 
+	if (ds->drv->port_enable) {
+		err = ds->drv->port_enable(ds, p->port, p->phy);
+		if (err)
+			goto clear_promisc;
+	}
+
 	if (p->phy)
 		phy_start(p->phy);
 
 	return 0;
 
+clear_promisc:
+	if (dev->flags & IFF_PROMISC)
+		dev_set_promiscuity(master, 0);
 clear_allmulti:
 	if (dev->flags & IFF_ALLMULTI)
 		dev_set_allmulti(master, -1);
@@ -103,6 +113,7 @@ static int dsa_slave_close(struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct net_device *master = p->parent->dst->master_netdev;
+	struct dsa_switch *ds = p->parent;
 
 	if (p->phy)
 		phy_stop(p->phy);
@@ -117,6 +128,9 @@ static int dsa_slave_close(struct net_device *dev)
 	if (!ether_addr_equal(dev->dev_addr, master->dev_addr))
 		dev_uc_del(master, dev->dev_addr);
 
+	if (ds->drv->port_disable)
+		ds->drv->port_disable(ds, p->port, p->phy);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 7905288f093ad924004609bb89a7ce1597892726 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 24 Sep 2014 17:05:21 -0700
Subject: net: dsa: allow switches driver to implement get/set EEE

Allow switches driver to query and enable/disable EEE on a per-port
basis by implementing the ethtool_{get,set}_eee settings and delegating
these operations to the switch driver.

set_eee() will need to coordinate with the PHY driver to make sure that
EEE is enabled, the link-partner supports it and the auto-negotiation
result is satisfactory.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  9 +++++++++
 net/dsa/slave.c   | 40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 4f664fe0e42c..58ad8c6492db 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -232,6 +232,15 @@ struct dsa_switch_driver {
 			       struct phy_device *phy);
 	void	(*port_disable)(struct dsa_switch *ds, int port,
 				struct phy_device *phy);
+
+	/*
+	 * EEE setttings
+	 */
+	int	(*set_eee)(struct dsa_switch *ds, int port,
+			   struct phy_device *phydev,
+			   struct ethtool_eee *e);
+	int	(*get_eee)(struct dsa_switch *ds, int port,
+			   struct ethtool_eee *e);
 };
 
 void register_switch_driver(struct dsa_switch_driver *type);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 182d30ae6818..36953c84ff2d 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -342,6 +342,44 @@ static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w)
 	return ret;
 }
 
+static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret;
+
+	if (!ds->drv->set_eee)
+		return -EOPNOTSUPP;
+
+	ret = ds->drv->set_eee(ds, p->port, p->phy, e);
+	if (ret)
+		return ret;
+
+	if (p->phy)
+		ret = phy_ethtool_set_eee(p->phy, e);
+
+	return ret;
+}
+
+static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
+{
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret;
+
+	if (!ds->drv->get_eee)
+		return -EOPNOTSUPP;
+
+	ret = ds->drv->get_eee(ds, p->port, e);
+	if (ret)
+		return ret;
+
+	if (p->phy)
+		ret = phy_ethtool_get_eee(p->phy, e);
+
+	return ret;
+}
+
 static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_settings		= dsa_slave_get_settings,
 	.set_settings		= dsa_slave_set_settings,
@@ -353,6 +391,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_sset_count		= dsa_slave_get_sset_count,
 	.set_wol		= dsa_slave_set_wol,
 	.get_wol		= dsa_slave_get_wol,
+	.set_eee		= dsa_slave_set_eee,
+	.get_eee		= dsa_slave_get_eee,
 };
 
 static const struct net_device_ops dsa_slave_netdev_ops = {
-- 
cgit v1.2.3


From 18d0264f630e200772bf236ac5747c47e908501e Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Sep 2014 10:26:37 -0700
Subject: net_sched: remove the first parameter from tcf_exts_destroy()

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <hadi@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h   | 2 +-
 net/sched/cls_api.c     | 2 +-
 net/sched/cls_basic.c   | 4 ++--
 net/sched/cls_bpf.c     | 4 ++--
 net/sched/cls_cgroup.c  | 6 +++---
 net/sched/cls_flow.c    | 4 ++--
 net/sched/cls_fw.c      | 4 ++--
 net/sched/cls_route.c   | 4 ++--
 net/sched/cls_rsvp.h    | 4 ++--
 net/sched/cls_tcindex.c | 4 ++--
 net/sched/cls_u32.c     | 4 ++--
 11 files changed, 21 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 6da46dcf1049..73f9532ee581 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -137,7 +137,7 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts,
 int tcf_exts_validate(struct net *net, struct tcf_proto *tp,
 		      struct nlattr **tb, struct nlattr *rate_tlv,
 		      struct tcf_exts *exts, bool ovr);
-void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts);
+void tcf_exts_destroy(struct tcf_exts *exts);
 void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
 		     struct tcf_exts *src);
 int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e547efdaba9d..77147c8c4acc 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -496,7 +496,7 @@ out:
 	return skb->len;
 }
 
-void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts)
+void tcf_exts_destroy(struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	tcf_action_destroy(&exts->actions, TCA_ACT_UNBIND);
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 1937298d6775..fe20826a79e7 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -94,7 +94,7 @@ static void basic_delete_filter(struct rcu_head *head)
 	struct tcf_proto *tp = f->tp;
 
 	tcf_unbind_filter(tp, &f->res);
-	tcf_exts_destroy(tp, &f->exts);
+	tcf_exts_destroy(&f->exts);
 	tcf_em_tree_destroy(tp, &f->ematches);
 	kfree(f);
 }
@@ -161,7 +161,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp,
 
 	return 0;
 errout:
-	tcf_exts_destroy(tp, &e);
+	tcf_exts_destroy(&e);
 	return err;
 }
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 4e3f5bfc0b26..4318d067b0a0 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -93,7 +93,7 @@ static int cls_bpf_init(struct tcf_proto *tp)
 static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog)
 {
 	tcf_unbind_filter(tp, &prog->res);
-	tcf_exts_destroy(tp, &prog->exts);
+	tcf_exts_destroy(&prog->exts);
 
 	bpf_prog_destroy(prog->filter);
 
@@ -217,7 +217,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 errout_free:
 	kfree(bpf_ops);
 errout:
-	tcf_exts_destroy(tp, &exts);
+	tcf_exts_destroy(&exts);
 	return ret;
 }
 
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 15c34d4ccd9e..3409f168225f 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -86,7 +86,7 @@ static void cls_cgroup_destroy_rcu(struct rcu_head *root)
 						    struct cls_cgroup_head,
 						    rcu);
 
-	tcf_exts_destroy(head->tp, &head->exts);
+	tcf_exts_destroy(&head->exts);
 	tcf_em_tree_destroy(head->tp, &head->ematches);
 	kfree(head);
 }
@@ -135,7 +135,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 
 	err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &t);
 	if (err < 0) {
-		tcf_exts_destroy(tp, &e);
+		tcf_exts_destroy(&e);
 		goto errout;
 	}
 
@@ -156,7 +156,7 @@ static void cls_cgroup_destroy(struct tcf_proto *tp)
 	struct cls_cgroup_head *head = rtnl_dereference(tp->root);
 
 	if (head) {
-		tcf_exts_destroy(tp, &head->exts);
+		tcf_exts_destroy(&head->exts);
 		tcf_em_tree_destroy(tp, &head->ematches);
 		RCU_INIT_POINTER(tp->root, NULL);
 		kfree_rcu(head, rcu);
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 95736fa479f3..f18d27f7b5f2 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -354,7 +354,7 @@ static void flow_destroy_filter(struct rcu_head *head)
 	struct flow_filter *f = container_of(head, struct flow_filter, rcu);
 
 	del_timer_sync(&f->perturb_timer);
-	tcf_exts_destroy(f->tp, &f->exts);
+	tcf_exts_destroy(&f->exts);
 	tcf_em_tree_destroy(f->tp, &f->ematches);
 	kfree(f);
 }
@@ -533,7 +533,7 @@ err2:
 	tcf_em_tree_destroy(tp, &t);
 	kfree(fnew);
 err1:
-	tcf_exts_destroy(tp, &e);
+	tcf_exts_destroy(&e);
 	return err;
 }
 
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 2650285620ee..da805aeeb65c 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -126,7 +126,7 @@ static void fw_delete_filter(struct rcu_head *head)
 	struct tcf_proto *tp = f->tp;
 
 	tcf_unbind_filter(tp, &f->res);
-	tcf_exts_destroy(tp, &f->exts);
+	tcf_exts_destroy(&f->exts);
 	kfree(f);
 }
 
@@ -223,7 +223,7 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f,
 
 	return 0;
 errout:
-	tcf_exts_destroy(tp, &e);
+	tcf_exts_destroy(&e);
 	return err;
 }
 
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index ba96deacf27c..b665aee661f7 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -272,7 +272,7 @@ route4_delete_filter(struct rcu_head *head)
 	struct tcf_proto *tp = f->tp;
 
 	tcf_unbind_filter(tp, &f->res);
-	tcf_exts_destroy(tp, &f->exts);
+	tcf_exts_destroy(&f->exts);
 	kfree(f);
 }
 
@@ -456,7 +456,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
 
 	return 0;
 errout:
-	tcf_exts_destroy(tp, &e);
+	tcf_exts_destroy(&e);
 	return err;
 }
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index b044c208b133..1c64a09753c4 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -264,7 +264,7 @@ static void
 rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f)
 {
 	tcf_unbind_filter(tp, &f->res);
-	tcf_exts_destroy(tp, &f->exts);
+	tcf_exts_destroy(&f->exts);
 	kfree_rcu(f, rcu);
 }
 
@@ -577,7 +577,7 @@ insert:
 errout:
 	kfree(f);
 errout2:
-	tcf_exts_destroy(tp, &e);
+	tcf_exts_destroy(&e);
 	return err;
 }
 
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 5054fae33a48..e3c6fa3ea3d2 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -169,7 +169,7 @@ found:
 		rcu_assign_pointer(*walk, rtnl_dereference(f->next));
 	}
 	tcf_unbind_filter(tp, &r->res);
-	tcf_exts_destroy(tp, &r->exts);
+	tcf_exts_destroy(&r->exts);
 	if (f)
 		kfree_rcu(f, rcu);
 	return 0;
@@ -401,7 +401,7 @@ errout_alloc:
 		kfree(cp->h);
 errout:
 	kfree(cp);
-	tcf_exts_destroy(tp, &e);
+	tcf_exts_destroy(&e);
 	return err;
 }
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index ef97a646ee94..4be3ebf46d67 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -359,7 +359,7 @@ static int u32_destroy_key(struct tcf_proto *tp,
 			   bool free_pf)
 {
 	tcf_unbind_filter(tp, &n->res);
-	tcf_exts_destroy(tp, &n->exts);
+	tcf_exts_destroy(&n->exts);
 	if (n->ht_down)
 		n->ht_down->refcnt--;
 #ifdef CONFIG_CLS_U32_PERF
@@ -606,7 +606,7 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 
 	return 0;
 errout:
-	tcf_exts_destroy(tp, &e);
+	tcf_exts_destroy(&e);
 	return err;
 }
 
-- 
cgit v1.2.3


From 3d9a0d2f8212879407e58d67f460d8920eb6543d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 25 Sep 2014 23:04:56 -0700
Subject: dql: dql_queued() should write first to reduce bus transactions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While doing high throughput test on a BQL enabled NIC,
I found a very high cost in ndo_start_xmit() when accessing BQL data.

It turned out the problem was caused by compiler trying to be
smart, but involving a bad MESI transaction :

  0.05 │  mov    0xc0(%rax),%edi    // LOAD dql->num_queued
  0.48 │  mov    %edx,0xc8(%rax)    // STORE dql->last_obj_cnt = count
 58.23 │  add    %edx,%edi
  0.58 │  cmp    %edi,0xc4(%rax)
  0.76 │  mov    %edi,0xc0(%rax)    // STORE dql->num_queued += count
  0.72 │  js     bd8

I got an incredible 10 % gain [1] by making sure cpu do not attempt
to get the cache line in Shared mode, but directly requests for
ownership.

New code :
	mov    %edx,0xc8(%rax)  // STORE dql->last_obj_cnt = count
	add    %edx,0xc0(%rax)  // RMW   dql->num_queued += count
	mov    0xc4(%rax),%ecx  // LOAD dql->adj_limit
	mov    0xc0(%rax),%edx  // LOAD dql->num_queued
	cmp    %edx,%ecx

The TX completion was running from another cpu, with high interrupts
rate.

Note that I am using barrier() as a soft hint, as mb() here could be
too heavy cost.

[1] This was a netperf TCP_STREAM with TSO disabled, but GSO enabled.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dynamic_queue_limits.h | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
index 5621547d631b..a4be70398ce1 100644
--- a/include/linux/dynamic_queue_limits.h
+++ b/include/linux/dynamic_queue_limits.h
@@ -73,14 +73,22 @@ static inline void dql_queued(struct dql *dql, unsigned int count)
 {
 	BUG_ON(count > DQL_MAX_OBJECT);
 
-	dql->num_queued += count;
 	dql->last_obj_cnt = count;
+
+	/* We want to force a write first, so that cpu do not attempt
+	 * to get cache line containing last_obj_cnt, num_queued, adj_limit
+	 * in Shared state, but directly does a Request For Ownership
+	 * It is only a hint, we use barrier() only.
+	 */
+	barrier();
+
+	dql->num_queued += count;
 }
 
 /* Returns how many objects can be queued, < 0 indicates over limit. */
 static inline int dql_avail(const struct dql *dql)
 {
-	return dql->adj_limit - dql->num_queued;
+	return ACCESS_ONCE(dql->adj_limit) - ACCESS_ONCE(dql->num_queued);
 }
 
 /* Record number of completed objects and recalculate the limit. */
-- 
cgit v1.2.3


From 55d8694fa82c9b5858ae5a78a210353961f908f9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 26 Sep 2014 22:37:32 +0200
Subject: net: tcp: assign tcp cong_ops when tcp sk is created

Split assignment and initialization from one into two functions.

This is required by followup patches that add Datacenter TCP
(DCTCP) congestion control algorithm - we need to be able to
determine if the connection is moderated by DCTCP before the
3WHS has finished.

As we walk the available congestion control list during the
assignment, we are always guaranteed to have Reno present as
it's fixed compiled-in. Therefore, since we're doing the
early assignment, we don't have a real use for the Reno alias
tcp_init_congestion_ops anymore and can thus remove it.

Actual usage of the congestion control operations are being
made after the 3WHS has finished, in some cases however we
can access get_info() via diag if implemented, therefore we
need to zero out the private area for those modules.

Joint work with Daniel Borkmann and Glenn Judd.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        |  2 +-
 net/ipv4/tcp.c           |  6 ++----
 net/ipv4/tcp_cong.c      | 46 ++++++++++++++++++++++------------------------
 net/ipv4/tcp_minisocks.c |  5 ++---
 4 files changed, 27 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 02a9a2c366bf..f99b0c072ee5 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -824,6 +824,7 @@ struct tcp_congestion_ops {
 int tcp_register_congestion_control(struct tcp_congestion_ops *type);
 void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
 
+void tcp_assign_congestion_control(struct sock *sk);
 void tcp_init_congestion_control(struct sock *sk);
 void tcp_cleanup_congestion_control(struct sock *sk);
 int tcp_set_default_congestion_control(const char *name);
@@ -835,7 +836,6 @@ int tcp_set_congestion_control(struct sock *sk, const char *name);
 int tcp_slow_start(struct tcp_sock *tp, u32 acked);
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
 
-extern struct tcp_congestion_ops tcp_init_congestion_ops;
 u32 tcp_reno_ssthresh(struct sock *sk);
 void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
 extern struct tcp_congestion_ops tcp_reno;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 87289e51be00..cf5e508e1ef5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -405,7 +405,7 @@ void tcp_init_sock(struct sock *sk)
 
 	tp->reordering = sysctl_tcp_reordering;
 	tcp_enable_early_retrans(tp);
-	icsk->icsk_ca_ops = &tcp_init_congestion_ops;
+	tcp_assign_congestion_control(sk);
 
 	tp->tsoffset = 0;
 
@@ -3258,8 +3258,6 @@ void __init tcp_init(void)
 		tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
 
 	tcp_metrics_init();
-
-	tcp_register_congestion_control(&tcp_reno);
-
+	BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
 	tcp_tasklet_init();
 }
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 80248f56c89f..a6c8a5775624 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -74,24 +74,34 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
 EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
 
 /* Assign choice of congestion control. */
-void tcp_init_congestion_control(struct sock *sk)
+void tcp_assign_congestion_control(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_congestion_ops *ca;
 
-	/* if no choice made yet assign the current value set as default */
-	if (icsk->icsk_ca_ops == &tcp_init_congestion_ops) {
-		rcu_read_lock();
-		list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
-			if (try_module_get(ca->owner)) {
-				icsk->icsk_ca_ops = ca;
-				break;
-			}
-
-			/* fallback to next available */
+	rcu_read_lock();
+	list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
+		if (likely(try_module_get(ca->owner))) {
+			icsk->icsk_ca_ops = ca;
+			goto out;
 		}
-		rcu_read_unlock();
+		/* Fallback to next available. The last really
+		 * guaranteed fallback is Reno from this list.
+		 */
 	}
+out:
+	rcu_read_unlock();
+
+	/* Clear out private data before diag gets it and
+	 * the ca has not been initialized.
+	 */
+	if (ca->get_info)
+		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+}
+
+void tcp_init_congestion_control(struct sock *sk)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (icsk->icsk_ca_ops->init)
 		icsk->icsk_ca_ops->init(sk);
@@ -345,15 +355,3 @@ struct tcp_congestion_ops tcp_reno = {
 	.ssthresh	= tcp_reno_ssthresh,
 	.cong_avoid	= tcp_reno_cong_avoid,
 };
-
-/* Initial congestion control used (until SYN)
- * really reno under another name so we can tell difference
- * during tcp_set_default_congestion_control
- */
-struct tcp_congestion_ops tcp_init_congestion_ops  = {
-	.name		= "",
-	.owner		= THIS_MODULE,
-	.ssthresh	= tcp_reno_ssthresh,
-	.cong_avoid	= tcp_reno_cong_avoid,
-};
-EXPORT_SYMBOL_GPL(tcp_init_congestion_ops);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a058f411d3a6..47b73506b77e 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -451,9 +451,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		newtp->snd_cwnd = TCP_INIT_CWND;
 		newtp->snd_cwnd_cnt = 0;
 
-		if (newicsk->icsk_ca_ops != &tcp_init_congestion_ops &&
-		    !try_module_get(newicsk->icsk_ca_ops->owner))
-			newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
+		if (!try_module_get(newicsk->icsk_ca_ops->owner))
+			tcp_assign_congestion_control(newsk);
 
 		tcp_set_ca_state(newsk, TCP_CA_Open);
 		tcp_init_xmit_timers(newsk);
-- 
cgit v1.2.3


From 30e502a34b8b21fae2c789da102bd9f6e99fef83 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 26 Sep 2014 22:37:33 +0200
Subject: net: tcp: add flag for ca to indicate that ECN is required

This patch adds a flag to TCP congestion algorithms that allows
for requesting to mark IPv4/IPv6 sockets with transport as ECN
capable, that is, ECT(0), when required by a congestion algorithm.

It is currently used and needed in DataCenter TCP (DCTCP), as it
requires both peers to assert ECT on all IP packets sent - it
uses ECN feedback (i.e. CE, Congestion Encountered information)
from switches inside the data center to derive feedback to the
end hosts.

Therefore, simply add a new flag to icsk_ca_ops. Note that DCTCP's
algorithm/behaviour slightly diverges from RFC3168, therefore this
is only (!) enabled iff the assigned congestion control ops module
has requested this. By that, we can tightly couple this logic really
only to the provided congestion control ops.

Joint work with Florian Westphal and Glenn Judd.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 61 +++++++++++++++++++++++++++++++++++++--------------
 net/ipv4/tcp_input.c  |  2 +-
 net/ipv4/tcp_output.c | 25 +++++++++++++++------
 3 files changed, 63 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f99b0c072ee5..a12f145cfbc3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -733,23 +733,6 @@ struct tcp_skb_cb {
 
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
 
-/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
- *
- * If we receive a SYN packet with these bits set, it means a network is
- * playing bad games with TOS bits. In order to avoid possible false congestion
- * notifications, we disable TCP ECN negociation.
- */
-static inline void
-TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb,
-		struct net *net)
-{
-	const struct tcphdr *th = tcp_hdr(skb);
-
-	if (net->ipv4.sysctl_tcp_ecn && th->ece && th->cwr &&
-	    INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield))
-		inet_rsk(req)->ecn_ok = 1;
-}
-
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
  */
@@ -791,7 +774,10 @@ enum tcp_ca_event {
 #define TCP_CA_MAX	128
 #define TCP_CA_BUF_MAX	(TCP_CA_NAME_MAX*TCP_CA_MAX)
 
+/* Algorithm can be set on socket without CAP_NET_ADMIN privileges */
 #define TCP_CONG_NON_RESTRICTED 0x1
+/* Requires ECN/ECT set on all packets */
+#define TCP_CONG_NEEDS_ECN	0x2
 
 struct tcp_congestion_ops {
 	struct list_head	list;
@@ -840,6 +826,13 @@ u32 tcp_reno_ssthresh(struct sock *sk);
 void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
 extern struct tcp_congestion_ops tcp_reno;
 
+static inline bool tcp_ca_needs_ecn(const struct sock *sk)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+
+	return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
+}
+
 static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -857,6 +850,40 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
 		icsk->icsk_ca_ops->cwnd_event(sk, event);
 }
 
+/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
+ *
+ * If we receive a SYN packet with these bits set, it means a
+ * network is playing bad games with TOS bits. In order to
+ * avoid possible false congestion notifications, we disable
+ * TCP ECN negociation.
+ *
+ * Exception: tcp_ca wants ECN. This is required for DCTCP
+ * congestion control; it requires setting ECT on all packets,
+ * including SYN. We inverse the test in this case: If our
+ * local socket wants ECN, but peer only set ece/cwr (but not
+ * ECT in IP header) its probably a non-DCTCP aware sender.
+ */
+static inline void
+TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb,
+		       const struct sock *listen_sk)
+{
+	const struct tcphdr *th = tcp_hdr(skb);
+	const struct net *net = sock_net(listen_sk);
+	bool th_ecn = th->ece && th->cwr;
+	bool ect, need_ecn;
+
+	if (!th_ecn)
+		return;
+
+	ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
+	need_ecn = tcp_ca_needs_ecn(listen_sk);
+
+	if (!ect && !need_ecn && net->ipv4.sysctl_tcp_ecn)
+		inet_rsk(req)->ecn_ok = 1;
+	else if (ect && need_ecn)
+		inet_rsk(req)->ecn_ok = 1;
+}
+
 /* These functions determine how the current flow behaves in respect of SACK
  * handling. SACK is negotiated with the peer, and therefore it can vary
  * between different flows.
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5073eefa6fae..fb0fe97e1c54 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5944,7 +5944,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		goto drop_and_free;
 
 	if (!want_cookie || tmp_opt.tstamp_ok)
-		TCP_ECN_create_request(req, skb, sock_net(sk));
+		TCP_ECN_create_request(req, skb, sk);
 
 	if (want_cookie) {
 		isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4d92703df4c6..20e73271d75c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -318,11 +318,15 @@ static u16 tcp_select_window(struct sock *sk)
 }
 
 /* Packet ECN state for a SYN-ACK */
-static inline void TCP_ECN_send_synack(const struct tcp_sock *tp, struct sk_buff *skb)
+static inline void TCP_ECN_send_synack(struct sock *sk, struct sk_buff *skb)
 {
+	const struct tcp_sock *tp = tcp_sk(sk);
+
 	TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR;
 	if (!(tp->ecn_flags & TCP_ECN_OK))
 		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE;
+	else if (tcp_ca_needs_ecn(sk))
+		INET_ECN_xmit(sk);
 }
 
 /* Packet ECN state for a SYN.  */
@@ -331,17 +335,24 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tp->ecn_flags = 0;
-	if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) {
+	if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+	    tcp_ca_needs_ecn(sk)) {
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
 		tp->ecn_flags = TCP_ECN_OK;
+		if (tcp_ca_needs_ecn(sk))
+			INET_ECN_xmit(sk);
 	}
 }
 
 static __inline__ void
-TCP_ECN_make_synack(const struct request_sock *req, struct tcphdr *th)
+TCP_ECN_make_synack(const struct request_sock *req, struct tcphdr *th,
+		    struct sock *sk)
 {
-	if (inet_rsk(req)->ecn_ok)
+	if (inet_rsk(req)->ecn_ok) {
 		th->ece = 1;
+		if (tcp_ca_needs_ecn(sk))
+			INET_ECN_xmit(sk);
+	}
 }
 
 /* Set up ECN state for a packet on a ESTABLISHED socket that is about to
@@ -362,7 +373,7 @@ static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
 				tcp_hdr(skb)->cwr = 1;
 				skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
 			}
-		} else {
+		} else if (!tcp_ca_needs_ecn(sk)) {
 			/* ACK or retransmitted segment: clear ECT|CE */
 			INET_ECN_dontxmit(sk);
 		}
@@ -2789,7 +2800,7 @@ int tcp_send_synack(struct sock *sk)
 		}
 
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK;
-		TCP_ECN_send_synack(tcp_sk(sk), skb);
+		TCP_ECN_send_synack(sk, skb);
 	}
 	return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 }
@@ -2848,7 +2859,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	memset(th, 0, sizeof(struct tcphdr));
 	th->syn = 1;
 	th->ack = 1;
-	TCP_ECN_make_synack(req, th);
+	TCP_ECN_make_synack(req, th, sk);
 	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
 	/* Setting of flags are superfluous here for callers (and ECE is
-- 
cgit v1.2.3


From 7354c8c389d18719dd71cc810da70b0921d66694 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 26 Sep 2014 22:37:34 +0200
Subject: net: tcp: split ack slow/fast events from cwnd_event

The congestion control ops "cwnd_event" currently supports
CA_EVENT_FAST_ACK and CA_EVENT_SLOW_ACK events (among others).
Both FAST and SLOW_ACK are only used by Westwood congestion
control algorithm.

This removes both flags from cwnd_event and adds a new
in_ack_event callback for this. The goal is to be able to
provide more detailed information about ACKs, such as whether
ECE flag was set, or whether the ACK resulted in a window
update.

It is required for DataCenter TCP (DCTCP) congestion control
algorithm as it makes a different choice depending on ECE being
set or not.

Joint work with Daniel Borkmann and Glenn Judd.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h       |  8 ++++++--
 net/ipv4/tcp_input.c    | 12 ++++++++++--
 net/ipv4/tcp_westwood.c | 28 ++++++++++++++++------------
 3 files changed, 32 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index a12f145cfbc3..7ec6a28305c0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -763,8 +763,10 @@ enum tcp_ca_event {
 	CA_EVENT_CWND_RESTART,	/* congestion window restart */
 	CA_EVENT_COMPLETE_CWR,	/* end of congestion recovery */
 	CA_EVENT_LOSS,		/* loss timeout */
-	CA_EVENT_FAST_ACK,	/* in sequence ack */
-	CA_EVENT_SLOW_ACK,	/* other ack */
+};
+
+enum tcp_ca_ack_event_flags {
+	CA_ACK_SLOWPATH = (1 << 0),
 };
 
 /*
@@ -796,6 +798,8 @@ struct tcp_congestion_ops {
 	void (*set_state)(struct sock *sk, u8 new_state);
 	/* call when cwnd event occurs (optional) */
 	void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
+	/* call when ack arrives (optional) */
+	void (*in_ack_event)(struct sock *sk, u32 flags);
 	/* new value of cwnd after loss (optional) */
 	u32  (*undo_cwnd)(struct sock *sk);
 	/* hook for packet ack accounting (optional) */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fb0fe97e1c54..8a38774cc66e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3362,6 +3362,14 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 	}
 }
 
+static inline void tcp_in_ack_event(struct sock *sk, u32 flags)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (icsk->icsk_ca_ops->in_ack_event)
+		icsk->icsk_ca_ops->in_ack_event(sk, flags);
+}
+
 /* This routine deals with incoming acks, but not outgoing ones. */
 static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 {
@@ -3421,7 +3429,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tp->snd_una = ack;
 		flag |= FLAG_WIN_UPDATE;
 
-		tcp_ca_event(sk, CA_EVENT_FAST_ACK);
+		tcp_in_ack_event(sk, 0);
 
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPACKS);
 	} else {
@@ -3439,7 +3447,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
 			flag |= FLAG_ECE;
 
-		tcp_ca_event(sk, CA_EVENT_SLOW_ACK);
+		tcp_in_ack_event(sk, CA_ACK_SLOWPATH);
 	}
 
 	/* We passed data and got it acked, remove any soft error
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index 81911a92356c..bb63fba47d47 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -220,32 +220,35 @@ static u32 tcp_westwood_bw_rttmin(const struct sock *sk)
 	return max_t(u32, (w->bw_est * w->rtt_min) / tp->mss_cache, 2);
 }
 
+static void tcp_westwood_ack(struct sock *sk, u32 ack_flags)
+{
+	if (ack_flags & CA_ACK_SLOWPATH) {
+		struct westwood *w = inet_csk_ca(sk);
+
+		westwood_update_window(sk);
+		w->bk += westwood_acked_count(sk);
+
+		update_rtt_min(w);
+		return;
+	}
+
+	westwood_fast_bw(sk);
+}
+
 static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct westwood *w = inet_csk_ca(sk);
 
 	switch (event) {
-	case CA_EVENT_FAST_ACK:
-		westwood_fast_bw(sk);
-		break;
-
 	case CA_EVENT_COMPLETE_CWR:
 		tp->snd_cwnd = tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk);
 		break;
-
 	case CA_EVENT_LOSS:
 		tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk);
 		/* Update RTT_min when next ack arrives */
 		w->reset_rtt_min = 1;
 		break;
-
-	case CA_EVENT_SLOW_ACK:
-		westwood_update_window(sk);
-		w->bk += westwood_acked_count(sk);
-		update_rtt_min(w);
-		break;
-
 	default:
 		/* don't care */
 		break;
@@ -274,6 +277,7 @@ static struct tcp_congestion_ops tcp_westwood __read_mostly = {
 	.ssthresh	= tcp_reno_ssthresh,
 	.cong_avoid	= tcp_reno_cong_avoid,
 	.cwnd_event	= tcp_westwood_event,
+	.in_ack_event	= tcp_westwood_ack,
 	.get_info	= tcp_westwood_info,
 	.pkts_acked	= tcp_westwood_pkts_acked,
 
-- 
cgit v1.2.3


From 9890092e46b2996bb85f7f973e69424cb5c07bc0 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 26 Sep 2014 22:37:35 +0200
Subject: net: tcp: more detailed ACK events and events for CE marked packets

DataCenter TCP (DCTCP) determines cwnd growth based on ECN information
and ACK properties, e.g. ACK that updates window is treated differently
than DUPACK.

Also DCTCP needs information whether ACK was delayed ACK. Furthermore,
DCTCP also implements a CE state machine that keeps track of CE markings
of incoming packets.

Therefore, extend the congestion control framework to provide these
event types, so that DCTCP can be properly implemented as a normal
congestion algorithm module outside of the core stack.

Joint work with Daniel Borkmann and Glenn Judd.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     |  9 ++++++++-
 net/ipv4/tcp_input.c  | 22 ++++++++++++++++++----
 net/ipv4/tcp_output.c |  4 ++++
 3 files changed, 30 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7ec6a28305c0..1f57c5363492 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -763,10 +763,17 @@ enum tcp_ca_event {
 	CA_EVENT_CWND_RESTART,	/* congestion window restart */
 	CA_EVENT_COMPLETE_CWR,	/* end of congestion recovery */
 	CA_EVENT_LOSS,		/* loss timeout */
+	CA_EVENT_ECN_NO_CE,	/* ECT set, but not CE marked */
+	CA_EVENT_ECN_IS_CE,	/* received CE marked IP packet */
+	CA_EVENT_DELAYED_ACK,	/* Delayed ack is sent */
+	CA_EVENT_NON_DELAYED_ACK,
 };
 
+/* Information about inbound ACK, passed to cong_ops->in_ack_event() */
 enum tcp_ca_ack_event_flags {
-	CA_ACK_SLOWPATH = (1 << 0),
+	CA_ACK_SLOWPATH		= (1 << 0),	/* In slow path processing */
+	CA_ACK_WIN_UPDATE	= (1 << 1),	/* ACK updated window */
+	CA_ACK_ECE		= (1 << 2),	/* ECE bit is set on ack */
 };
 
 /*
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8a38774cc66e..fc133178c787 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -233,14 +233,21 @@ static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *s
 			tcp_enter_quickack_mode((struct sock *)tp);
 		break;
 	case INET_ECN_CE:
+		if (tcp_ca_needs_ecn((struct sock *)tp))
+			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE);
+
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
 			tcp_enter_quickack_mode((struct sock *)tp);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
-		/* fallinto */
+		tp->ecn_flags |= TCP_ECN_SEEN;
+		break;
 	default:
+		if (tcp_ca_needs_ecn((struct sock *)tp))
+			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE);
 		tp->ecn_flags |= TCP_ECN_SEEN;
+		break;
 	}
 }
 
@@ -3429,10 +3436,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tp->snd_una = ack;
 		flag |= FLAG_WIN_UPDATE;
 
-		tcp_in_ack_event(sk, 0);
+		tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
 
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPACKS);
 	} else {
+		u32 ack_ev_flags = CA_ACK_SLOWPATH;
+
 		if (ack_seq != TCP_SKB_CB(skb)->end_seq)
 			flag |= FLAG_DATA;
 		else
@@ -3444,10 +3453,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 			flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
 							&sack_rtt_us);
 
-		if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
+		if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) {
 			flag |= FLAG_ECE;
+			ack_ev_flags |= CA_ACK_ECE;
+		}
+
+		if (flag & FLAG_WIN_UPDATE)
+			ack_ev_flags |= CA_ACK_WIN_UPDATE;
 
-		tcp_in_ack_event(sk, CA_ACK_SLOWPATH);
+		tcp_in_ack_event(sk, ack_ev_flags);
 	}
 
 	/* We passed data and got it acked, remove any soft error
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 20e73271d75c..124f9e4e4594 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3130,6 +3130,8 @@ void tcp_send_delayed_ack(struct sock *sk)
 	int ato = icsk->icsk_ack.ato;
 	unsigned long timeout;
 
+	tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
+
 	if (ato > TCP_DELACK_MIN) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 		int max_ato = HZ / 2;
@@ -3186,6 +3188,8 @@ void tcp_send_ack(struct sock *sk)
 	if (sk->sk_state == TCP_CLOSE)
 		return;
 
+	tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
+
 	/* We are not putting this on the write queue, so
 	 * tcp_transmit_skb() will set the ownership to this
 	 * sock.
-- 
cgit v1.2.3


From e3118e8359bb7c59555aca60c725106e6d78c5ce Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 26 Sep 2014 22:37:36 +0200
Subject: net: tcp: add DCTCP congestion control algorithm

This work adds the DataCenter TCP (DCTCP) congestion control
algorithm [1], which has been first published at SIGCOMM 2010 [2],
resp. follow-up analysis at SIGMETRICS 2011 [3] (and also, more
recently as an informational IETF draft available at [4]).

DCTCP is an enhancement to the TCP congestion control algorithm for
data center networks. Typical data center workloads are i.e.
i) partition/aggregate (queries; bursty, delay sensitive), ii) short
messages e.g. 50KB-1MB (for coordination and control state; delay
sensitive), and iii) large flows e.g. 1MB-100MB (data update;
throughput sensitive). DCTCP has therefore been designed for such
environments to provide/achieve the following three requirements:

  * High burst tolerance (incast due to partition/aggregate)
  * Low latency (short flows, queries)
  * High throughput (continuous data updates, large file
    transfers) with commodity, shallow buffered switches

The basic idea of its design consists of two fundamentals: i) on the
switch side, packets are being marked when its internal queue
length > threshold K (K is chosen so that a large enough headroom
for marked traffic is still available in the switch queue); ii) the
sender/host side maintains a moving average of the fraction of marked
packets, so each RTT, F is being updated as follows:

 F := X / Y, where X is # of marked ACKs, Y is total # of ACKs
 alpha := (1 - g) * alpha + g * F, where g is a smoothing constant

The resulting alpha (iow: probability that switch queue is congested)
is then being used in order to adaptively decrease the congestion
window W:

 W := (1 - (alpha / 2)) * W

The means for receiving marked packets resp. marking them on switch
side in DCTCP is the use of ECN.

RFC3168 describes a mechanism for using Explicit Congestion Notification
from the switch for early detection of congestion, rather than waiting
for segment loss to occur.

However, this method only detects the presence of congestion, not
the *extent*. In the presence of mild congestion, it reduces the TCP
congestion window too aggressively and unnecessarily affects the
throughput of long flows [4].

DCTCP, as mentioned, enhances Explicit Congestion Notification (ECN)
processing to estimate the fraction of bytes that encounter congestion,
rather than simply detecting that some congestion has occurred. DCTCP
then scales the TCP congestion window based on this estimate [4],
thus it can derive multibit feedback from the information present in
the single-bit sequence of marks in its control law. And thus act in
*proportion* to the extent of congestion, not its *presence*.

Switches therefore set the Congestion Experienced (CE) codepoint in
packets when internal queue lengths exceed threshold K. Resulting,
DCTCP delivers the same or better throughput than normal TCP, while
using 90% less buffer space.

It was found in [2] that DCTCP enables the applications to handle 10x
the current background traffic, without impacting foreground traffic.
Moreover, a 10x increase in foreground traffic did not cause any
timeouts, and thus largely eliminates TCP incast collapse problems.

The algorithm itself has already seen deployments in large production
data centers since then.

We did a long-term stress-test and analysis in a data center, short
summary of our TCP incast tests with iperf compared to cubic:

This test measured DCTCP throughput and latency and compared it with
CUBIC throughput and latency for an incast scenario. In this test, 19
senders sent at maximum rate to a single receiver. The receiver simply
ran iperf -s.

The senders ran iperf -c <receiver> -t 30. All senders started
simultaneously (using local clocks synchronized by ntp).

This test was repeated multiple times. Below shows the results from a
single test. Other tests are similar. (DCTCP results were extremely
consistent, CUBIC results show some variance induced by the TCP timeouts
that CUBIC encountered.)

For this test, we report statistics on the number of TCP timeouts,
flow throughput, and traffic latency.

1) Timeouts (total over all flows, and per flow summaries):

            CUBIC            DCTCP
  Total     3227             25
  Mean       169.842          1.316
  Median     183              1
  Max        207              5
  Min        123              0
  Stddev      28.991          1.600

Timeout data is taken by measuring the net change in netstat -s
"other TCP timeouts" reported. As a result, the timeout measurements
above are not restricted to the test traffic, and we believe that it
is likely that all of the "DCTCP timeouts" are actually timeouts for
non-test traffic. We report them nevertheless. CUBIC will also include
some non-test timeouts, but they are drawfed by bona fide test traffic
timeouts for CUBIC. Clearly DCTCP does an excellent job of preventing
TCP timeouts. DCTCP reduces timeouts by at least two orders of
magnitude and may well have eliminated them in this scenario.

2) Throughput (per flow in Mbps):

            CUBIC            DCTCP
  Mean      521.684          521.895
  Median    464              523
  Max       776              527
  Min       403              519
  Stddev    105.891            2.601
  Fairness    0.962            0.999

Throughput data was simply the average throughput for each flow
reported by iperf. By avoiding TCP timeouts, DCTCP is able to
achieve much better per-flow results. In CUBIC, many flows
experience TCP timeouts which makes flow throughput unpredictable and
unfair. DCTCP, on the other hand, provides very clean predictable
throughput without incurring TCP timeouts. Thus, the standard deviation
of CUBIC throughput is dramatically higher than the standard deviation
of DCTCP throughput.

Mean throughput is nearly identical because even though cubic flows
suffer TCP timeouts, other flows will step in and fill the unused
bandwidth. Note that this test is something of a best case scenario
for incast under CUBIC: it allows other flows to fill in for flows
experiencing a timeout. Under situations where the receiver is issuing
requests and then waiting for all flows to complete, flows cannot fill
in for timed out flows and throughput will drop dramatically.

3) Latency (in ms):

            CUBIC            DCTCP
  Mean      4.0088           0.04219
  Median    4.055            0.0395
  Max       4.2              0.085
  Min       3.32             0.028
  Stddev    0.1666           0.01064

Latency for each protocol was computed by running "ping -i 0.2
<receiver>" from a single sender to the receiver during the incast
test. For DCTCP, "ping -Q 0x6 -i 0.2 <receiver>" was used to ensure
that traffic traversed the DCTCP queue and was not dropped when the
queue size was greater than the marking threshold. The summary
statistics above are over all ping metrics measured between the single
sender, receiver pair.

The latency results for this test show a dramatic difference between
CUBIC and DCTCP. CUBIC intentionally overflows the switch buffer
which incurs the maximum queue latency (more buffer memory will lead
to high latency.) DCTCP, on the other hand, deliberately attempts to
keep queue occupancy low. The result is a two orders of magnitude
reduction of latency with DCTCP - even with a switch with relatively
little RAM. Switches with larger amounts of RAM will incur increasing
amounts of latency for CUBIC, but not for DCTCP.

4) Convergence and stability test:

This test measured the time that DCTCP took to fairly redistribute
bandwidth when a new flow commences. It also measured DCTCP's ability
to remain stable at a fair bandwidth distribution. DCTCP is compared
with CUBIC for this test.

At the commencement of this test, a single flow is sending at maximum
rate (near 10 Gbps) to a single receiver. One second after that first
flow commences, a new flow from a distinct server begins sending to
the same receiver as the first flow. After the second flow has sent
data for 10 seconds, the second flow is terminated. The first flow
sends for an additional second. Ideally, the bandwidth would be evenly
shared as soon as the second flow starts, and recover as soon as it
stops.

The results of this test are shown below. Note that the flow bandwidth
for the two flows was measured near the same time, but not
simultaneously.

DCTCP performs nearly perfectly within the measurement limitations
of this test: bandwidth is quickly distributed fairly between the two
flows, remains stable throughout the duration of the test, and
recovers quickly. CUBIC, in contrast, is slow to divide the bandwidth
fairly, and has trouble remaining stable.

  CUBIC                      DCTCP

  Seconds  Flow 1  Flow 2    Seconds  Flow 1  Flow 2
   0       9.93    0          0       9.92    0
   0.5     9.87    0          0.5     9.86    0
   1       8.73    2.25       1       6.46    4.88
   1.5     7.29    2.8        1.5     4.9     4.99
   2       6.96    3.1        2       4.92    4.94
   2.5     6.67    3.34       2.5     4.93    5
   3       6.39    3.57       3       4.92    4.99
   3.5     6.24    3.75       3.5     4.94    4.74
   4       6       3.94       4       5.34    4.71
   4.5     5.88    4.09       4.5     4.99    4.97
   5       5.27    4.98       5       4.83    5.01
   5.5     4.93    5.04       5.5     4.89    4.99
   6       4.9     4.99       6       4.92    5.04
   6.5     4.93    5.1        6.5     4.91    4.97
   7       4.28    5.8        7       4.97    4.97
   7.5     4.62    4.91       7.5     4.99    4.82
   8       5.05    4.45       8       5.16    4.76
   8.5     5.93    4.09       8.5     4.94    4.98
   9       5.73    4.2        9       4.92    5.02
   9.5     5.62    4.32       9.5     4.87    5.03
  10       6.12    3.2       10       4.91    5.01
  10.5     6.91    3.11      10.5     4.87    5.04
  11       8.48    0         11       8.49    4.94
  11.5     9.87    0         11.5     9.9     0

SYN/ACK ECT test:

This test demonstrates the importance of ECT on SYN and SYN-ACK packets
by measuring the connection probability in the presence of competing
flows for a DCTCP connection attempt *without* ECT in the SYN packet.
The test was repeated five times for each number of competing flows.

              Competing Flows  1 |    2 |    4 |    8 |   16
                               ------------------------------
Mean Connection Probability    1 | 0.67 | 0.45 | 0.28 |    0
Median Connection Probability  1 | 0.65 | 0.45 | 0.25 |    0

As the number of competing flows moves beyond 1, the connection
probability drops rapidly.

Enabling DCTCP with this patch requires the following steps:

DCTCP must be running both on the sender and receiver side in your
data center, i.e.:

  sysctl -w net.ipv4.tcp_congestion_control=dctcp

Also, ECN functionality must be enabled on all switches in your
data center for DCTCP to work. The default ECN marking threshold (K)
heuristic on the switch for DCTCP is e.g., 20 packets (30KB) at
1Gbps, and 65 packets (~100KB) at 10Gbps (K > 1/7 * C * RTT, [4]).

In above tests, for each switch port, traffic was segregated into two
queues. For any packet with a DSCP of 0x01 - or equivalently a TOS of
0x04 - the packet was placed into the DCTCP queue. All other packets
were placed into the default drop-tail queue. For the DCTCP queue,
RED/ECN marking was enabled, here, with a marking threshold of 75 KB.
More details however, we refer you to the paper [2] under section 3).

There are no code changes required to applications running in user
space. DCTCP has been implemented in full *isolation* of the rest of
the TCP code as its own congestion control module, so that it can run
without a need to expose code to the core of the TCP stack, and thus
nothing changes for non-DCTCP users.

Changes in the CA framework code are minimal, and DCTCP algorithm
operates on mechanisms that are already available in most Silicon.
The gain (dctcp_shift_g) is currently a fixed constant (1/16) from
the paper, but we leave the option that it can be chosen carefully
to a different value by the user.

In case DCTCP is being used and ECN support on peer site is off,
DCTCP falls back after 3WHS to operate in normal TCP Reno mode.

ss {-4,-6} -t -i diag interface:

  ... dctcp wscale:7,7 rto:203 rtt:2.349/0.026 mss:1448 cwnd:2054
  ssthresh:1102 ce_state 0 alpha 15 ab_ecn 0 ab_tot 735584
  send 10129.2Mbps pacing_rate 20254.1Mbps unacked:1822 retrans:0/15
  reordering:101 rcv_space:29200

  ... dctcp-reno wscale:7,7 rto:201 rtt:0.711/1.327 ato:40 mss:1448
  cwnd:10 ssthresh:1102 fallback_mode send 162.9Mbps pacing_rate
  325.5Mbps rcv_rtt:1.5 rcv_space:29200

More information about DCTCP can be found in [1-4].

  [1] http://simula.stanford.edu/~alizade/Site/DCTCP.html
  [2] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
  [3] http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf
  [4] http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00

Joint work with Florian Westphal and Glenn Judd.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/dctcp.txt |  43 +++++
 include/uapi/linux/inet_diag.h     |  13 +-
 net/ipv4/Kconfig                   |  26 ++-
 net/ipv4/Makefile                  |   1 +
 net/ipv4/tcp_dctcp.c               | 344 +++++++++++++++++++++++++++++++++++++
 net/ipv4/tcp_output.c              |   1 +
 6 files changed, 425 insertions(+), 3 deletions(-)
 create mode 100644 Documentation/networking/dctcp.txt
 create mode 100644 net/ipv4/tcp_dctcp.c

(limited to 'include')

diff --git a/Documentation/networking/dctcp.txt b/Documentation/networking/dctcp.txt
new file mode 100644
index 000000000000..0d5dfbc89ec9
--- /dev/null
+++ b/Documentation/networking/dctcp.txt
@@ -0,0 +1,43 @@
+DCTCP (DataCenter TCP)
+----------------------
+
+DCTCP is an enhancement to the TCP congestion control algorithm for data
+center networks and leverages Explicit Congestion Notification (ECN) in
+the data center network to provide multi-bit feedback to the end hosts.
+
+To enable it on end hosts:
+
+  sysctl -w net.ipv4.tcp_congestion_control=dctcp
+
+All switches in the data center network running DCTCP must support ECN
+marking and be configured for marking when reaching defined switch buffer
+thresholds. The default ECN marking threshold heuristic for DCTCP on
+switches is 20 packets (30KB) at 1Gbps, and 65 packets (~100KB) at 10Gbps,
+but might need further careful tweaking.
+
+For more details, see below documents:
+
+Paper:
+
+The algorithm is further described in detail in the following two
+SIGCOMM/SIGMETRICS papers:
+
+ i) Mohammad Alizadeh, Albert Greenberg, David A. Maltz, Jitendra Padhye,
+    Parveen Patel, Balaji Prabhakar, Sudipta Sengupta, and Murari Sridharan:
+      "Data Center TCP (DCTCP)", Data Center Networks session
+      Proc. ACM SIGCOMM, New Delhi, 2010.
+    http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+    http://www.sigcomm.org/ccr/papers/2010/October/1851275.1851192
+
+ii) Mohammad Alizadeh, Adel Javanmard, and Balaji Prabhakar:
+      "Analysis of DCTCP: Stability, Convergence, and Fairness"
+      Proc. ACM SIGMETRICS, San Jose, 2011.
+    http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf
+
+IETF informational draft:
+
+  http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-00
+
+DCTCP site:
+
+  http://simula.stanford.edu/~alizade/Site/DCTCP.html
diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index bbde90fa5838..d65c0a09efd3 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -110,10 +110,10 @@ enum {
 	INET_DIAG_TCLASS,
 	INET_DIAG_SKMEMINFO,
 	INET_DIAG_SHUTDOWN,
+	INET_DIAG_DCTCPINFO,
 };
 
-#define INET_DIAG_MAX INET_DIAG_SHUTDOWN
-
+#define INET_DIAG_MAX INET_DIAG_DCTCPINFO
 
 /* INET_DIAG_MEM */
 
@@ -133,5 +133,14 @@ struct tcpvegas_info {
 	__u32	tcpv_minrtt;
 };
 
+/* INET_DIAG_DCTCPINFO */
+
+struct tcp_dctcp_info {
+	__u16	dctcp_enabled;
+	__u16	dctcp_ce_state;
+	__u32	dctcp_alpha;
+	__u32	dctcp_ab_ecn;
+	__u32	dctcp_ab_tot;
+};
 
 #endif /* _UAPI_INET_DIAG_H_ */
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 84f710b7472a..69fb37854449 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -570,6 +570,27 @@ config TCP_CONG_ILLINOIS
 	For further details see:
 	  http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
 
+config TCP_CONG_DCTCP
+	tristate "DataCenter TCP (DCTCP)"
+	default n
+	---help---
+	DCTCP leverages Explicit Congestion Notification (ECN) in the network to
+	provide multi-bit feedback to the end hosts. It is designed to provide:
+
+	- High burst tolerance (incast due to partition/aggregate),
+	- Low latency (short flows, queries),
+	- High throughput (continuous data updates, large file transfers) with
+	  commodity, shallow-buffered switches.
+
+	All switches in the data center network running DCTCP must support
+	ECN marking and be configured for marking when reaching defined switch
+	buffer thresholds. The default ECN marking threshold heuristic for
+	DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets
+	(~100KB) at 10Gbps, but might need further careful tweaking.
+
+	For further details see:
+	  http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+
 choice
 	prompt "Default TCP congestion control"
 	default DEFAULT_CUBIC
@@ -598,9 +619,11 @@ choice
 	config DEFAULT_WESTWOOD
 		bool "Westwood" if TCP_CONG_WESTWOOD=y
 
+	config DEFAULT_DCTCP
+		bool "DCTCP" if TCP_CONG_DCTCP=y
+
 	config DEFAULT_RENO
 		bool "Reno"
-
 endchoice
 
 endif
@@ -620,6 +643,7 @@ config DEFAULT_TCP_CONG
 	default "westwood" if DEFAULT_WESTWOOD
 	default "veno" if DEFAULT_VENO
 	default "reno" if DEFAULT_RENO
+	default "dctcp" if DEFAULT_DCTCP
 	default "cubic"
 
 config TCP_MD5SIG
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index d78d404c596f..d8105787c199 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
 obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
 obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
 obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
+obj-$(CONFIG_TCP_CONG_DCTCP) += tcp_dctcp.o
 obj-$(CONFIG_TCP_CONG_WESTWOOD) += tcp_westwood.o
 obj-$(CONFIG_TCP_CONG_HSTCP) += tcp_highspeed.o
 obj-$(CONFIG_TCP_CONG_HYBLA) += tcp_hybla.o
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
new file mode 100644
index 000000000000..b504371af742
--- /dev/null
+++ b/net/ipv4/tcp_dctcp.c
@@ -0,0 +1,344 @@
+/* DataCenter TCP (DCTCP) congestion control.
+ *
+ * http://simula.stanford.edu/~alizade/Site/DCTCP.html
+ *
+ * This is an implementation of DCTCP over Reno, an enhancement to the
+ * TCP congestion control algorithm designed for data centers. DCTCP
+ * leverages Explicit Congestion Notification (ECN) in the network to
+ * provide multi-bit feedback to the end hosts. DCTCP's goal is to meet
+ * the following three data center transport requirements:
+ *
+ *  - High burst tolerance (incast due to partition/aggregate)
+ *  - Low latency (short flows, queries)
+ *  - High throughput (continuous data updates, large file transfers)
+ *    with commodity shallow buffered switches
+ *
+ * The algorithm is described in detail in the following two papers:
+ *
+ * 1) Mohammad Alizadeh, Albert Greenberg, David A. Maltz, Jitendra Padhye,
+ *    Parveen Patel, Balaji Prabhakar, Sudipta Sengupta, and Murari Sridharan:
+ *      "Data Center TCP (DCTCP)", Data Center Networks session
+ *      Proc. ACM SIGCOMM, New Delhi, 2010.
+ *   http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
+ *
+ * 2) Mohammad Alizadeh, Adel Javanmard, and Balaji Prabhakar:
+ *      "Analysis of DCTCP: Stability, Convergence, and Fairness"
+ *      Proc. ACM SIGMETRICS, San Jose, 2011.
+ *   http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf
+ *
+ * Initial prototype from Abdul Kabbani, Masato Yasuda and Mohammad Alizadeh.
+ *
+ * Authors:
+ *
+ *	Daniel Borkmann <dborkman@redhat.com>
+ *	Florian Westphal <fw@strlen.de>
+ *	Glenn Judd <glenn.judd@morganstanley.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <net/tcp.h>
+#include <linux/inet_diag.h>
+
+#define DCTCP_MAX_ALPHA	1024U
+
+struct dctcp {
+	u32 acked_bytes_ecn;
+	u32 acked_bytes_total;
+	u32 prior_snd_una;
+	u32 prior_rcv_nxt;
+	u32 dctcp_alpha;
+	u32 next_seq;
+	u32 ce_state;
+	u32 delayed_ack_reserved;
+};
+
+static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
+module_param(dctcp_shift_g, uint, 0644);
+MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha");
+
+static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
+module_param(dctcp_alpha_on_init, uint, 0644);
+MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
+
+static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
+module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
+MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
+		 "parameter for clamping alpha on loss");
+
+static struct tcp_congestion_ops dctcp_reno;
+
+static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
+{
+	ca->next_seq = tp->snd_nxt;
+
+	ca->acked_bytes_ecn = 0;
+	ca->acked_bytes_total = 0;
+}
+
+static void dctcp_init(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+
+	if ((tp->ecn_flags & TCP_ECN_OK) ||
+	    (sk->sk_state == TCP_LISTEN ||
+	     sk->sk_state == TCP_CLOSE)) {
+		struct dctcp *ca = inet_csk_ca(sk);
+
+		ca->prior_snd_una = tp->snd_una;
+		ca->prior_rcv_nxt = tp->rcv_nxt;
+
+		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
+
+		ca->delayed_ack_reserved = 0;
+		ca->ce_state = 0;
+
+		dctcp_reset(tp, ca);
+		return;
+	}
+
+	/* No ECN support? Fall back to Reno. Also need to clear
+	 * ECT from sk since it is set during 3WHS for DCTCP.
+	 */
+	inet_csk(sk)->icsk_ca_ops = &dctcp_reno;
+	INET_ECN_dontxmit(sk);
+}
+
+static u32 dctcp_ssthresh(struct sock *sk)
+{
+	const struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
+}
+
+/* Minimal DCTP CE state machine:
+ *
+ * S:	0 <- last pkt was non-CE
+ *	1 <- last pkt was CE
+ */
+
+static void dctcp_ce_state_0_to_1(struct sock *sk)
+{
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	/* State has changed from CE=0 to CE=1 and delayed
+	 * ACK has not sent yet.
+	 */
+	if (!ca->ce_state && ca->delayed_ack_reserved) {
+		u32 tmp_rcv_nxt;
+
+		/* Save current rcv_nxt. */
+		tmp_rcv_nxt = tp->rcv_nxt;
+
+		/* Generate previous ack with CE=0. */
+		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+		tp->rcv_nxt = ca->prior_rcv_nxt;
+
+		tcp_send_ack(sk);
+
+		/* Recover current rcv_nxt. */
+		tp->rcv_nxt = tmp_rcv_nxt;
+	}
+
+	ca->prior_rcv_nxt = tp->rcv_nxt;
+	ca->ce_state = 1;
+
+	tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+}
+
+static void dctcp_ce_state_1_to_0(struct sock *sk)
+{
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	/* State has changed from CE=1 to CE=0 and delayed
+	 * ACK has not sent yet.
+	 */
+	if (ca->ce_state && ca->delayed_ack_reserved) {
+		u32 tmp_rcv_nxt;
+
+		/* Save current rcv_nxt. */
+		tmp_rcv_nxt = tp->rcv_nxt;
+
+		/* Generate previous ack with CE=1. */
+		tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+		tp->rcv_nxt = ca->prior_rcv_nxt;
+
+		tcp_send_ack(sk);
+
+		/* Recover current rcv_nxt. */
+		tp->rcv_nxt = tmp_rcv_nxt;
+	}
+
+	ca->prior_rcv_nxt = tp->rcv_nxt;
+	ca->ce_state = 0;
+
+	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+static void dctcp_update_alpha(struct sock *sk, u32 flags)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
+	u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
+
+	/* If ack did not advance snd_una, count dupack as MSS size.
+	 * If ack did update window, do not count it at all.
+	 */
+	if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
+		acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
+	if (acked_bytes) {
+		ca->acked_bytes_total += acked_bytes;
+		ca->prior_snd_una = tp->snd_una;
+
+		if (flags & CA_ACK_ECE)
+			ca->acked_bytes_ecn += acked_bytes;
+	}
+
+	/* Expired RTT */
+	if (!before(tp->snd_una, ca->next_seq)) {
+		/* For avoiding denominator == 1. */
+		if (ca->acked_bytes_total == 0)
+			ca->acked_bytes_total = 1;
+
+		/* alpha = (1 - g) * alpha + g * F */
+		ca->dctcp_alpha = ca->dctcp_alpha -
+				  (ca->dctcp_alpha >> dctcp_shift_g) +
+				  (ca->acked_bytes_ecn << (10U - dctcp_shift_g)) /
+				  ca->acked_bytes_total;
+
+		if (ca->dctcp_alpha > DCTCP_MAX_ALPHA)
+			/* Clamp dctcp_alpha to max. */
+			ca->dctcp_alpha = DCTCP_MAX_ALPHA;
+
+		dctcp_reset(tp, ca);
+	}
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
+		struct dctcp *ca = inet_csk_ca(sk);
+
+		/* If this extension is enabled, we clamp dctcp_alpha to
+		 * max on packet loss; the motivation is that dctcp_alpha
+		 * is an indicator to the extend of congestion and packet
+		 * loss is an indicator of extreme congestion; setting
+		 * this in practice turned out to be beneficial, and
+		 * effectively assumes total congestion which reduces the
+		 * window by half.
+		 */
+		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
+	}
+}
+
+static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
+{
+	struct dctcp *ca = inet_csk_ca(sk);
+
+	switch (ev) {
+	case CA_EVENT_DELAYED_ACK:
+		if (!ca->delayed_ack_reserved)
+			ca->delayed_ack_reserved = 1;
+		break;
+	case CA_EVENT_NON_DELAYED_ACK:
+		if (ca->delayed_ack_reserved)
+			ca->delayed_ack_reserved = 0;
+		break;
+	default:
+		/* Don't care for the rest. */
+		break;
+	}
+}
+
+static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
+{
+	switch (ev) {
+	case CA_EVENT_ECN_IS_CE:
+		dctcp_ce_state_0_to_1(sk);
+		break;
+	case CA_EVENT_ECN_NO_CE:
+		dctcp_ce_state_1_to_0(sk);
+		break;
+	case CA_EVENT_DELAYED_ACK:
+	case CA_EVENT_NON_DELAYED_ACK:
+		dctcp_update_ack_reserved(sk, ev);
+		break;
+	default:
+		/* Don't care for the rest. */
+		break;
+	}
+}
+
+static void dctcp_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
+{
+	const struct dctcp *ca = inet_csk_ca(sk);
+
+	/* Fill it also in case of VEGASINFO due to req struct limits.
+	 * We can still correctly retrieve it later.
+	 */
+	if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) ||
+	    ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
+		struct tcp_dctcp_info info;
+
+		memset(&info, 0, sizeof(info));
+		if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) {
+			info.dctcp_enabled = 1;
+			info.dctcp_ce_state = (u16) ca->ce_state;
+			info.dctcp_alpha = ca->dctcp_alpha;
+			info.dctcp_ab_ecn = ca->acked_bytes_ecn;
+			info.dctcp_ab_tot = ca->acked_bytes_total;
+		}
+
+		nla_put(skb, INET_DIAG_DCTCPINFO, sizeof(info), &info);
+	}
+}
+
+static struct tcp_congestion_ops dctcp __read_mostly = {
+	.init		= dctcp_init,
+	.in_ack_event   = dctcp_update_alpha,
+	.cwnd_event	= dctcp_cwnd_event,
+	.ssthresh	= dctcp_ssthresh,
+	.cong_avoid	= tcp_reno_cong_avoid,
+	.set_state	= dctcp_state,
+	.get_info	= dctcp_get_info,
+	.flags		= TCP_CONG_NEEDS_ECN,
+	.owner		= THIS_MODULE,
+	.name		= "dctcp",
+};
+
+static struct tcp_congestion_ops dctcp_reno __read_mostly = {
+	.ssthresh	= tcp_reno_ssthresh,
+	.cong_avoid	= tcp_reno_cong_avoid,
+	.get_info	= dctcp_get_info,
+	.owner		= THIS_MODULE,
+	.name		= "dctcp-reno",
+};
+
+static int __init dctcp_register(void)
+{
+	BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE);
+	return tcp_register_congestion_control(&dctcp);
+}
+
+static void __exit dctcp_unregister(void)
+{
+	tcp_unregister_congestion_control(&dctcp);
+}
+
+module_init(dctcp_register);
+module_exit(dctcp_unregister);
+
+MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_AUTHOR("Glenn Judd <glenn.judd@morganstanley.com>");
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("DataCenter TCP (DCTCP)");
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 124f9e4e4594..86a0216fcaa1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3211,6 +3211,7 @@ void tcp_send_ack(struct sock *sk)
 	skb_mstamp_get(&buff->skb_mstamp);
 	tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
 }
+EXPORT_SYMBOL_GPL(tcp_send_ack);
 
 /* This routine sends a packet with an out of date sequence
  * number. It assumes the other end will try to ack it.
-- 
cgit v1.2.3


From c08ee14cc6634457948bc5e26584697208baa02a Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Fri, 12 Sep 2014 15:01:57 +0300
Subject: clk: ti: change clock init to use generic of_clk_init

Previously, the TI clock driver initialized all the clocks hierarchically
under each separate clock provider node. Now, each clock that requires
IO access will instead check their parent node to find out which IO range
to use.

This patch allows the TI clock driver to use a few new features provided
by the generic of_clk_init, and also allows registration of clock nodes
outside the clock hierarchy (for example, any external clocks.)

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Cc: Mike Turquette <mturquette@linaro.org>
Cc: Paul Walmsley <paul@pwsan.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Ujfalusi <peter.ujfalusi@ti.com>
Cc: Jyri Sarha <jsarha@ti.com>
Cc: Stefan Assmann <sassmann@kpanic.de>
Acked-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/io.c         | 12 +++++--
 arch/arm/mach-omap2/prm_common.c |  2 --
 drivers/clk/ti/clk.c             | 68 +++++++++++++++++++++++++---------------
 include/linux/clk/ti.h           |  1 +
 4 files changed, 54 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 5d0667c119f6..a1b82a994842 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -734,8 +734,16 @@ int __init omap_clk_init(void)
 	ti_clk_init_features();
 
 	ret = of_prcm_init();
-	if (!ret)
-		ret = omap_clk_soc_init();
+	if (ret)
+		return ret;
+
+	of_clk_init(NULL);
+
+	ti_dt_clk_init_retry_clks();
+
+	ti_dt_clockdomains_setup();
+
+	ret = omap_clk_soc_init();
 
 	return ret;
 }
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 76ca320f007c..3b890807f5e6 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -525,8 +525,6 @@ int __init of_prcm_init(void)
 		memmap_index++;
 	}
 
-	ti_dt_clockdomains_setup();
-
 	return 0;
 }
 
diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c
index b1a6f7144f3f..337abe5909e1 100644
--- a/drivers/clk/ti/clk.c
+++ b/drivers/clk/ti/clk.c
@@ -25,8 +25,8 @@
 #undef pr_fmt
 #define pr_fmt(fmt) "%s: " fmt, __func__
 
-static int ti_dt_clk_memmap_index;
 struct ti_clk_ll_ops *ti_clk_ll_ops;
+static struct device_node *clocks_node_ptr[CLK_MAX_MEMMAPS];
 
 /**
  * ti_dt_clocks_register - register DT alias clocks during boot
@@ -108,9 +108,21 @@ void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index)
 	struct clk_omap_reg *reg;
 	u32 val;
 	u32 tmp;
+	int i;
 
 	reg = (struct clk_omap_reg *)&tmp;
-	reg->index = ti_dt_clk_memmap_index;
+
+	for (i = 0; i < CLK_MAX_MEMMAPS; i++) {
+		if (clocks_node_ptr[i] == node->parent)
+			break;
+	}
+
+	if (i == CLK_MAX_MEMMAPS) {
+		pr_err("clk-provider not found for %s!\n", node->name);
+		return NULL;
+	}
+
+	reg->index = i;
 
 	if (of_property_read_u32_index(node, "reg", index, &val)) {
 		pr_err("%s must have reg[%d]!\n", node->name, index);
@@ -127,20 +139,14 @@ void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index)
  * @parent: master node
  * @index: internal index for clk_reg_ops
  *
- * Initializes a master clock IP block and its child clock nodes.
- * Regmap is provided for accessing the register space for the
- * IP block and all the clocks under it.
+ * Initializes a master clock IP block. This basically sets up the
+ * mapping from clocks node to the memory map index. All the clocks
+ * are then initialized through the common of_clk_init call, and the
+ * clocks will access their memory maps based on the node layout.
  */
 void ti_dt_clk_init_provider(struct device_node *parent, int index)
 {
-	const struct of_device_id *match;
-	struct device_node *np;
 	struct device_node *clocks;
-	of_clk_init_cb_t clk_init_cb;
-	struct clk_init_item *retry;
-	struct clk_init_item *tmp;
-
-	ti_dt_clk_memmap_index = index;
 
 	/* get clocks for this parent */
 	clocks = of_get_child_by_name(parent, "clocks");
@@ -149,19 +155,31 @@ void ti_dt_clk_init_provider(struct device_node *parent, int index)
 		return;
 	}
 
-	for_each_child_of_node(clocks, np) {
-		match = of_match_node(&__clk_of_table, np);
-		if (!match)
-			continue;
-		clk_init_cb = (of_clk_init_cb_t)match->data;
-		pr_debug("%s: initializing: %s\n", __func__, np->name);
-		clk_init_cb(np);
-	}
+	/* add clocks node info */
+	clocks_node_ptr[index] = clocks;
+}
 
-	list_for_each_entry_safe(retry, tmp, &retry_list, link) {
-		pr_debug("retry-init: %s\n", retry->node->name);
-		retry->func(retry->hw, retry->node);
-		list_del(&retry->link);
-		kfree(retry);
+/**
+ * ti_dt_clk_init_retry_clks - init clocks from the retry list
+ *
+ * Initializes any clocks that have failed to initialize before,
+ * reasons being missing parent node(s) during earlier init. This
+ * typically happens only for DPLLs which need to have both of their
+ * parent clocks ready during init.
+ */
+void ti_dt_clk_init_retry_clks(void)
+{
+	struct clk_init_item *retry;
+	struct clk_init_item *tmp;
+	int retries = 5;
+
+	while (!list_empty(&retry_list) && retries) {
+		list_for_each_entry_safe(retry, tmp, &retry_list, link) {
+			pr_debug("retry-init: %s\n", retry->node->name);
+			retry->func(retry->hw, retry->node);
+			list_del(&retry->link);
+			kfree(retry);
+		}
+		retries--;
 	}
 }
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index e8d8a35034a5..f75acbf70e96 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -292,6 +292,7 @@ void omap2xxx_clkt_vps_init(void);
 void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index);
 void ti_dt_clocks_register(struct ti_dt_clk *oclks);
 void ti_dt_clk_init_provider(struct device_node *np, int index);
+void ti_dt_clk_init_retry_clks(void);
 void ti_dt_clockdomains_setup(void);
 int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw,
 		      ti_of_clk_init_cb_t func);
-- 
cgit v1.2.3


From 9363dc4b599949bde338cdaba1cf7cac243e4e97 Mon Sep 17 00:00:00 2001
From: Arturo Borrero <arturo.borrero.glez@gmail.com>
Date: Tue, 23 Sep 2014 13:30:41 +0200
Subject: netfilter: nf_tables: store and dump set policy

We want to know in which cases the user explicitly sets the policy
options. In that case, we also want to dump back the info.

Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 2 ++
 net/netfilter/nf_tables_api.c     | 6 ++++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index c4d86198d3d6..3d7292392fac 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -241,6 +241,7 @@ void nft_unregister_set(struct nft_set_ops *ops);
  * 	@dtype: data type (verdict or numeric type defined by userspace)
  * 	@size: maximum set size
  * 	@nelems: number of elements
+ *	@policy: set parameterization (see enum nft_set_policies)
  * 	@ops: set ops
  * 	@flags: set flags
  * 	@klen: key length
@@ -255,6 +256,7 @@ struct nft_set {
 	u32				dtype;
 	u32				size;
 	u32				nelems;
+	u16				policy;
 	/* runtime data below here */
 	const struct nft_set_ops	*ops ____cacheline_aligned;
 	u16				flags;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a476b9962155..19e79f0d9ad2 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2344,6 +2344,11 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			goto nla_put_failure;
 	}
 
+	if (set->policy != NFT_SET_POL_PERFORMANCE) {
+		if (nla_put_be32(skb, NFTA_SET_POLICY, htonl(set->policy)))
+			goto nla_put_failure;
+	}
+
 	desc = nla_nest_start(skb, NFTA_SET_DESC);
 	if (desc == NULL)
 		goto nla_put_failure;
@@ -2669,6 +2674,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	set->dlen  = desc.dlen;
 	set->flags = flags;
 	set->size  = desc.size;
+	set->policy = policy;
 
 	err = ops->init(set, &desc, nla);
 	if (err < 0)
-- 
cgit v1.2.3


From 3d46e73dfdb840f460e5b06416965d132570ec33 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@free-electrons.com>
Date: Wed, 24 Sep 2014 23:05:50 +0400
Subject: usb: rename phy to usb_phy in HCD

The USB PHY member of the HCD structure is renamed to 'usb_phy' and
modifications are done in all drivers accessing it.
This is in preparation to adding the generic PHY support.

Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
[Sergei: added missing 'drivers/usb/misc/lvstest.c' file, resolved rejects,
updated changelog.]
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/host.c   |  2 +-
 drivers/usb/core/hcd.c        | 20 ++++++++++----------
 drivers/usb/core/hub.c        |  8 ++++----
 drivers/usb/host/ehci-fsl.c   | 16 ++++++++--------
 drivers/usb/host/ehci-hub.c   |  2 +-
 drivers/usb/host/ehci-msm.c   |  4 ++--
 drivers/usb/host/ehci-tegra.c | 16 ++++++++--------
 drivers/usb/host/ohci-omap.c  | 20 ++++++++++----------
 drivers/usb/misc/lvstest.c    |  8 ++++----
 include/linux/usb/hcd.h       |  2 +-
 10 files changed, 49 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index 0d6b24cb2270..ebde7b6ce687 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -59,7 +59,7 @@ static int host_start(struct ci_hdrc *ci)
 	hcd->has_tt = 1;
 
 	hcd->power_budget = ci->platdata->power_budget;
-	hcd->phy = ci->transceiver;
+	hcd->usb_phy = ci->transceiver;
 	hcd->tpl_support = ci->platdata->tpl_support;
 
 	ehci = hcd_to_ehci(hcd);
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index bcb96ff207ba..2c56252b9ff8 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2629,7 +2629,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	int retval;
 	struct usb_device *rhdev;
 
-	if (IS_ENABLED(CONFIG_USB_PHY) && !hcd->phy) {
+	if (IS_ENABLED(CONFIG_USB_PHY) && !hcd->usb_phy) {
 		struct usb_phy *phy = usb_get_phy_dev(hcd->self.controller, 0);
 
 		if (IS_ERR(phy)) {
@@ -2642,7 +2642,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 				usb_put_phy(phy);
 				return retval;
 			}
-			hcd->phy = phy;
+			hcd->usb_phy = phy;
 			hcd->remove_phy = 1;
 		}
 	}
@@ -2790,10 +2790,10 @@ err_allocate_root_hub:
 err_register_bus:
 	hcd_buffer_destroy(hcd);
 err_remove_phy:
-	if (hcd->remove_phy && hcd->phy) {
-		usb_phy_shutdown(hcd->phy);
-		usb_put_phy(hcd->phy);
-		hcd->phy = NULL;
+	if (hcd->remove_phy && hcd->usb_phy) {
+		usb_phy_shutdown(hcd->usb_phy);
+		usb_put_phy(hcd->usb_phy);
+		hcd->usb_phy = NULL;
 	}
 	return retval;
 }
@@ -2866,10 +2866,10 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 
 	usb_deregister_bus(&hcd->self);
 	hcd_buffer_destroy(hcd);
-	if (hcd->remove_phy && hcd->phy) {
-		usb_phy_shutdown(hcd->phy);
-		usb_put_phy(hcd->phy);
-		hcd->phy = NULL;
+	if (hcd->remove_phy && hcd->usb_phy) {
+		usb_phy_shutdown(hcd->usb_phy);
+		usb_put_phy(hcd->usb_phy);
+		hcd->usb_phy = NULL;
 	}
 
 	usb_put_invalidate_rhdev(hcd);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 1d21b2c21f9b..11e80ac31324 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4468,8 +4468,8 @@ hub_port_init (struct usb_hub *hub, struct usb_device *udev, int port1,
 	if (retval)
 		goto fail;
 
-	if (hcd->phy && !hdev->parent)
-		usb_phy_notify_connect(hcd->phy, udev->speed);
+	if (hcd->usb_phy && !hdev->parent)
+		usb_phy_notify_connect(hcd->usb_phy, udev->speed);
 
 	/*
 	 * Some superspeed devices have finished the link training process
@@ -4627,9 +4627,9 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 
 	/* Disconnect any existing devices under this port */
 	if (udev) {
-		if (hcd->phy && !hdev->parent &&
+		if (hcd->usb_phy && !hdev->parent &&
 				!(portstatus & USB_PORT_STAT_CONNECTION))
-			usb_phy_notify_disconnect(hcd->phy, udev->speed);
+			usb_phy_notify_disconnect(hcd->usb_phy, udev->speed);
 		usb_disconnect(&port_dev->child);
 	}
 
diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
index 3d84b6a41dae..2d2ae8db439e 100644
--- a/drivers/usb/host/ehci-fsl.c
+++ b/drivers/usb/host/ehci-fsl.c
@@ -136,15 +136,15 @@ static int usb_hcd_fsl_probe(const struct hc_driver *driver,
 	if (pdata->operating_mode == FSL_USB2_DR_OTG) {
 		struct ehci_hcd *ehci = hcd_to_ehci(hcd);
 
-		hcd->phy = usb_get_phy(USB_PHY_TYPE_USB2);
+		hcd->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
 		dev_dbg(&pdev->dev, "hcd=0x%p  ehci=0x%p, phy=0x%p\n",
-			hcd, ehci, hcd->phy);
+			hcd, ehci, hcd->usb_phy);
 
-		if (!IS_ERR_OR_NULL(hcd->phy)) {
-			retval = otg_set_host(hcd->phy->otg,
+		if (!IS_ERR_OR_NULL(hcd->usb_phy)) {
+			retval = otg_set_host(hcd->usb_phy->otg,
 					      &ehci_to_hcd(ehci)->self);
 			if (retval) {
-				usb_put_phy(hcd->phy);
+				usb_put_phy(hcd->usb_phy);
 				goto err2;
 			}
 		} else {
@@ -181,9 +181,9 @@ static void usb_hcd_fsl_remove(struct usb_hcd *hcd,
 {
 	struct fsl_usb2_platform_data *pdata = dev_get_platdata(&pdev->dev);
 
-	if (!IS_ERR_OR_NULL(hcd->phy)) {
-		otg_set_host(hcd->phy->otg, NULL);
-		usb_put_phy(hcd->phy);
+	if (!IS_ERR_OR_NULL(hcd->usb_phy)) {
+		otg_set_host(hcd->usb_phy->otg, NULL);
+		usb_put_phy(hcd->usb_phy);
 	}
 
 	usb_remove_hcd(hcd);
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 7ccb3ccf8e86..5728829cf6ef 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -922,7 +922,7 @@ int ehci_hub_control(
 #ifdef CONFIG_USB_OTG
 			if ((hcd->self.otg_port == (wIndex + 1))
 			    && hcd->self.b_hnp_enable) {
-				otg_start_hnp(hcd->phy->otg);
+				otg_start_hnp(hcd->usb_phy->otg);
 				break;
 			}
 #endif
diff --git a/drivers/usb/host/ehci-msm.c b/drivers/usb/host/ehci-msm.c
index 934b39d5e44a..9dc2118ae808 100644
--- a/drivers/usb/host/ehci-msm.c
+++ b/drivers/usb/host/ehci-msm.c
@@ -124,7 +124,7 @@ static int ehci_msm_probe(struct platform_device *pdev)
 		goto put_hcd;
 	}
 
-	hcd->phy = phy;
+	hcd->usb_phy = phy;
 	device_init_wakeup(&pdev->dev, 1);
 	/*
 	 * OTG device parent of HCD takes care of putting
@@ -151,7 +151,7 @@ static int ehci_msm_remove(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
 
-	otg_set_host(hcd->phy->otg, NULL);
+	otg_set_host(hcd->usb_phy->otg, NULL);
 
 	/* FIXME: need to call usb_remove_hcd() here? */
 
diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
index 7aafb05e7a40..aaa01971efe9 100644
--- a/drivers/usb/host/ehci-tegra.c
+++ b/drivers/usb/host/ehci-tegra.c
@@ -206,7 +206,7 @@ static int tegra_ehci_hub_control(
 		if (tegra->port_resuming && !(temp & PORT_SUSPEND)) {
 			/* Resume completed, re-enable disconnect detection */
 			tegra->port_resuming = 0;
-			tegra_usb_phy_postresume(hcd->phy);
+			tegra_usb_phy_postresume(hcd->usb_phy);
 		}
 	}
 
@@ -259,7 +259,7 @@ static int tegra_ehci_hub_control(
 			goto done;
 
 		/* Disable disconnect detection during port resume */
-		tegra_usb_phy_preresume(hcd->phy);
+		tegra_usb_phy_preresume(hcd->usb_phy);
 
 		ehci->reset_done[wIndex-1] = jiffies + msecs_to_jiffies(25);
 
@@ -454,7 +454,7 @@ static int tegra_ehci_probe(struct platform_device *pdev)
 		err = PTR_ERR(u_phy);
 		goto cleanup_clk_en;
 	}
-	hcd->phy = u_phy;
+	hcd->usb_phy = u_phy;
 
 	tegra->needs_double_reset = of_property_read_bool(pdev->dev.of_node,
 		"nvidia,needs-double-reset");
@@ -475,7 +475,7 @@ static int tegra_ehci_probe(struct platform_device *pdev)
 	ehci->caps = hcd->regs + 0x100;
 	ehci->has_hostpc = soc_config->has_hostpc;
 
-	err = usb_phy_init(hcd->phy);
+	err = usb_phy_init(hcd->usb_phy);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to initialize phy\n");
 		goto cleanup_clk_en;
@@ -490,7 +490,7 @@ static int tegra_ehci_probe(struct platform_device *pdev)
 	}
 	u_phy->otg->host = hcd_to_bus(hcd);
 
-	err = usb_phy_set_suspend(hcd->phy, 0);
+	err = usb_phy_set_suspend(hcd->usb_phy, 0);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to power on the phy\n");
 		goto cleanup_phy;
@@ -517,7 +517,7 @@ static int tegra_ehci_probe(struct platform_device *pdev)
 cleanup_otg_set_host:
 	otg_set_host(u_phy->otg, NULL);
 cleanup_phy:
-	usb_phy_shutdown(hcd->phy);
+	usb_phy_shutdown(hcd->usb_phy);
 cleanup_clk_en:
 	clk_disable_unprepare(tegra->clk);
 cleanup_hcd_create:
@@ -531,9 +531,9 @@ static int tegra_ehci_remove(struct platform_device *pdev)
 	struct tegra_ehci_hcd *tegra =
 		(struct tegra_ehci_hcd *)hcd_to_ehci(hcd)->priv;
 
-	otg_set_host(hcd->phy->otg, NULL);
+	otg_set_host(hcd->usb_phy->otg, NULL);
 
-	usb_phy_shutdown(hcd->phy);
+	usb_phy_shutdown(hcd->usb_phy);
 	usb_remove_hcd(hcd);
 
 	clk_disable_unprepare(tegra->clk);
diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c
index de9428362503..0231606d47c2 100644
--- a/drivers/usb/host/ohci-omap.c
+++ b/drivers/usb/host/ohci-omap.c
@@ -180,10 +180,10 @@ static void start_hnp(struct ohci_hcd *ohci)
 	unsigned long	flags;
 	u32 l;
 
-	otg_start_hnp(hcd->phy->otg);
+	otg_start_hnp(hcd->usb_phy->otg);
 
 	local_irq_save(flags);
-	hcd->phy->state = OTG_STATE_A_SUSPEND;
+	hcd->usb_phy->state = OTG_STATE_A_SUSPEND;
 	writel (RH_PS_PSS, &ohci->regs->roothub.portstatus [port]);
 	l = omap_readl(OTG_CTRL);
 	l &= ~OTG_A_BUSREQ;
@@ -220,14 +220,14 @@ static int ohci_omap_reset(struct usb_hcd *hcd)
 
 #ifdef	CONFIG_USB_OTG
 	if (need_transceiver) {
-		hcd->phy = usb_get_phy(USB_PHY_TYPE_USB2);
-		if (!IS_ERR_OR_NULL(hcd->phy)) {
-			int	status = otg_set_host(hcd->phy->otg,
+		hcd->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
+		if (!IS_ERR_OR_NULL(hcd->usb_phy)) {
+			int	status = otg_set_host(hcd->usb_phy->otg,
 						&ohci_to_hcd(ohci)->self);
 			dev_dbg(hcd->self.controller, "init %s phy, status %d\n",
-					hcd->phy->label, status);
+					hcd->usb_phy->label, status);
 			if (status) {
-				usb_put_phy(hcd->phy);
+				usb_put_phy(hcd->usb_phy);
 				return status;
 			}
 		} else {
@@ -399,9 +399,9 @@ usb_hcd_omap_remove (struct usb_hcd *hcd, struct platform_device *pdev)
 	dev_dbg(hcd->self.controller, "stopping USB Controller\n");
 	usb_remove_hcd(hcd);
 	omap_ohci_clock_power(0);
-	if (!IS_ERR_OR_NULL(hcd->phy)) {
-		(void) otg_set_host(hcd->phy->otg, 0);
-		usb_put_phy(hcd->phy);
+	if (!IS_ERR_OR_NULL(hcd->usb_phy)) {
+		(void) otg_set_host(hcd->usb_phy->otg, 0);
+		usb_put_phy(hcd->usb_phy);
 	}
 	if (machine_is_omap_osk())
 		gpio_free(9);
diff --git a/drivers/usb/misc/lvstest.c b/drivers/usb/misc/lvstest.c
index 7d589c156fb1..62cb8cd08403 100644
--- a/drivers/usb/misc/lvstest.c
+++ b/drivers/usb/misc/lvstest.c
@@ -333,13 +333,13 @@ static void lvs_rh_work(struct work_struct *work)
 					USB_PORT_STAT_CONNECTION) {
 				lvs->present = true;
 				lvs->portnum = i;
-				if (hcd->phy)
-					usb_phy_notify_connect(hcd->phy,
+				if (hcd->usb_phy)
+					usb_phy_notify_connect(hcd->usb_phy,
 							USB_SPEED_SUPER);
 			} else {
 				lvs->present = false;
-				if (hcd->phy)
-					usb_phy_notify_disconnect(hcd->phy,
+				if (hcd->usb_phy)
+					usb_phy_notify_disconnect(hcd->usb_phy,
 							USB_SPEED_SUPER);
 			}
 			break;
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index a48c89e96988..788059a108e5 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -106,7 +106,7 @@ struct usb_hcd {
 	 * OTG and some Host controllers need software interaction with phys;
 	 * other external phys should be software-transparent
 	 */
-	struct usb_phy	*phy;
+	struct usb_phy		*usb_phy;
 
 	/* Flags that need to be manipulated atomically because they can
 	 * change while the host controller is running.  Always use
-- 
cgit v1.2.3


From 0043325495222139daa0696db736f67658dc7770 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Wed, 24 Sep 2014 23:09:44 +0400
Subject: usb: hcd: add generic PHY support

Add the generic PHY support, analogous to the USB PHY support. Intended it to be
used with the PCI EHCI/OHCI drivers and the xHCI platform driver.

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c  | 42 ++++++++++++++++++++++++++++++++++++++++--
 include/linux/usb/hcd.h |  1 +
 2 files changed, 41 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 2c56252b9ff8..b84fb141e122 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -42,6 +42,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/types.h>
 
+#include <linux/phy/phy.h>
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
 #include <linux/usb/phy.h>
@@ -2647,6 +2648,29 @@ int usb_add_hcd(struct usb_hcd *hcd,
 		}
 	}
 
+	if (IS_ENABLED(CONFIG_GENERIC_PHY)) {
+		struct phy *phy = phy_get(hcd->self.controller, "usb");
+
+		if (IS_ERR(phy)) {
+			retval = PTR_ERR(phy);
+			if (retval == -EPROBE_DEFER)
+				goto err_phy;
+		} else {
+			retval = phy_init(phy);
+			if (retval) {
+				phy_put(phy);
+				goto err_phy;
+			}
+			retval = phy_power_on(phy);
+			if (retval) {
+				phy_exit(phy);
+				phy_put(phy);
+				goto err_phy;
+			}
+			hcd->phy = phy;
+		}
+	}
+
 	dev_info(hcd->self.controller, "%s\n", hcd->product_desc);
 
 	/* Keep old behaviour if authorized_default is not in [0, 1]. */
@@ -2662,7 +2686,7 @@ int usb_add_hcd(struct usb_hcd *hcd,
 	 */
 	if ((retval = hcd_buffer_create(hcd)) != 0) {
 		dev_dbg(hcd->self.controller, "pool alloc failed\n");
-		goto err_remove_phy;
+		goto err_create_buf;
 	}
 
 	if ((retval = usb_register_bus(&hcd->self)) < 0)
@@ -2789,7 +2813,14 @@ err_allocate_root_hub:
 	usb_deregister_bus(&hcd->self);
 err_register_bus:
 	hcd_buffer_destroy(hcd);
-err_remove_phy:
+err_create_buf:
+	if (IS_ENABLED(CONFIG_GENERIC_PHY) && hcd->phy) {
+		phy_power_off(hcd->phy);
+		phy_exit(hcd->phy);
+		phy_put(hcd->phy);
+		hcd->phy = NULL;
+	}
+err_phy:
 	if (hcd->remove_phy && hcd->usb_phy) {
 		usb_phy_shutdown(hcd->usb_phy);
 		usb_put_phy(hcd->usb_phy);
@@ -2866,6 +2897,13 @@ void usb_remove_hcd(struct usb_hcd *hcd)
 
 	usb_deregister_bus(&hcd->self);
 	hcd_buffer_destroy(hcd);
+
+	if (IS_ENABLED(CONFIG_GENERIC_PHY) && hcd->phy) {
+		phy_power_off(hcd->phy);
+		phy_exit(hcd->phy);
+		phy_put(hcd->phy);
+		hcd->phy = NULL;
+	}
 	if (hcd->remove_phy && hcd->usb_phy) {
 		usb_phy_shutdown(hcd->usb_phy);
 		usb_put_phy(hcd->usb_phy);
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 788059a108e5..cd96a2bc3388 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -107,6 +107,7 @@ struct usb_hcd {
 	 * other external phys should be software-transparent
 	 */
 	struct usb_phy		*usb_phy;
+	struct phy		*phy;
 
 	/* Flags that need to be manipulated atomically because they can
 	 * change while the host controller is running.  Always use
-- 
cgit v1.2.3


From 1f180359f42fc6fda4600175c63f2a84f444cc92 Mon Sep 17 00:00:00 2001
From: Tomas Winkler <tomas.winkler@intel.com>
Date: Mon, 29 Sep 2014 16:31:46 +0300
Subject: mei: remove include to pci header from mei module files

Remove inclusion of linux/pci.h in mei layer
however we need to include the headers that before
got included implicitly from linux/pci.h.

Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/amthif.c    | 2 +-
 drivers/misc/mei/bus.c       | 1 -
 drivers/misc/mei/client.c    | 2 +-
 drivers/misc/mei/debugfs.c   | 1 -
 drivers/misc/mei/hbm.c       | 5 +++--
 drivers/misc/mei/init.c      | 1 -
 drivers/misc/mei/interrupt.c | 2 +-
 drivers/misc/mei/main.c      | 2 +-
 drivers/misc/mei/nfc.c       | 3 ++-
 drivers/misc/mei/wd.c        | 1 -
 include/linux/mei_cl_bus.h   | 1 +
 11 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c
index 5d47d1b36ccf..d9b0e761fcd2 100644
--- a/drivers/misc/mei/amthif.c
+++ b/drivers/misc/mei/amthif.c
@@ -20,7 +20,6 @@
 #include <linux/types.h>
 #include <linux/fcntl.h>
 #include <linux/aio.h>
-#include <linux/pci.h>
 #include <linux/ioctl.h>
 #include <linux/cdev.h>
 #include <linux/list.h>
@@ -29,6 +28,7 @@
 #include <linux/uuid.h>
 #include <linux/jiffies.h>
 #include <linux/uaccess.h>
+#include <linux/slab.h>
 
 #include <linux/mei.h>
 
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 4cc1a66187be..4d20d60ca38d 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -22,7 +22,6 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/interrupt.h>
-#include <linux/pci.h>
 #include <linux/mei_cl_bus.h>
 
 #include "mei_dev.h"
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index bfc3ad24db9c..04a196429e55 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -14,10 +14,10 @@
  *
  */
 
-#include <linux/pci.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 #include <linux/pm_runtime.h>
 
 #include <linux/mei.h>
diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c
index e14a7db9a669..aca7847da69f 100644
--- a/drivers/misc/mei/debugfs.c
+++ b/drivers/misc/mei/debugfs.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/device.h>
 #include <linux/debugfs.h>
-#include <linux/pci.h>
 
 #include <linux/mei.h>
 
diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c
index 209650bccf57..c874fdd44ce1 100644
--- a/drivers/misc/mei/hbm.c
+++ b/drivers/misc/mei/hbm.c
@@ -15,11 +15,12 @@
  */
 
 #include <linux/export.h>
-#include <linux/pci.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
-#include <linux/mei.h>
 #include <linux/pm_runtime.h>
+#include <linux/slab.h>
+
+#include <linux/mei.h>
 
 #include "mei_dev.h"
 #include "hbm.h"
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index dd233fd43178..76ef8ffa42c1 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/export.h>
-#include <linux/pci.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/delay.h>
diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c
index 8dac76901130..8844e1772793 100644
--- a/drivers/misc/mei/interrupt.c
+++ b/drivers/misc/mei/interrupt.c
@@ -16,11 +16,11 @@
 
 
 #include <linux/export.h>
-#include <linux/pci.h>
 #include <linux/kthread.h>
 #include <linux/interrupt.h>
 #include <linux/fs.h>
 #include <linux/jiffies.h>
+#include <linux/slab.h>
 
 #include <linux/mei.h>
 
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 4d738c881878..d31f271f6516 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -17,12 +17,12 @@
 #include <linux/moduleparam.h>
 #include <linux/kernel.h>
 #include <linux/device.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
 #include <linux/aio.h>
-#include <linux/pci.h>
 #include <linux/poll.h>
 #include <linux/init.h>
 #include <linux/ioctl.h>
diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c
index 9f32fd6eaccf..5b369f4c47de 100644
--- a/drivers/misc/mei/nfc.c
+++ b/drivers/misc/mei/nfc.c
@@ -19,7 +19,8 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/device.h>
-#include <linux/pci.h>
+#include <linux/slab.h>
+
 #include <linux/mei_cl_bus.h>
 
 #include "mei_dev.h"
diff --git a/drivers/misc/mei/wd.c b/drivers/misc/mei/wd.c
index d28511b78eaa..626b4c13993b 100644
--- a/drivers/misc/mei/wd.c
+++ b/drivers/misc/mei/wd.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/device.h>
-#include <linux/pci.h>
 #include <linux/sched.h>
 #include <linux/watchdog.h>
 
diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h
index d14af7b722ef..164aad1f9f12 100644
--- a/include/linux/mei_cl_bus.h
+++ b/include/linux/mei_cl_bus.h
@@ -3,6 +3,7 @@
 
 #include <linux/device.h>
 #include <linux/uuid.h>
+#include <linux/mod_devicetable.h>
 
 struct mei_cl_device;
 
-- 
cgit v1.2.3


From c02607aad2f9ed478eb288bcec1c00cd9df38b3c Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Mon, 29 Sep 2014 10:05:06 -0600
Subject: iommu: introduce domain attribute for nesting IOMMUs

Some IOMMUs, such as the ARM SMMU, support two stages of translation.
The idea behind such a scheme is to allow a guest operating system to
use the IOMMU for DMA mappings in the first stage of translation, with
the hypervisor then installing mappings in the second stage to provide
isolation of the DMA to the physical range assigned to that virtual
machine.

In order to allow IOMMU domains to be used for second-stage translation,
this patch adds a new iommu_attr (IOMMU_ATTR_NESTING) for setting
second-stage domains prior to device attach. The attribute can also be
queried to see if a domain is actually making use of nesting.

Acked-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/linux/iommu.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 20f9a527922a..7b02bcc85b9e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -80,6 +80,7 @@ enum iommu_attr {
 	DOMAIN_ATTR_FSL_PAMU_STASH,
 	DOMAIN_ATTR_FSL_PAMU_ENABLE,
 	DOMAIN_ATTR_FSL_PAMUV1,
+	DOMAIN_ATTR_NESTING,	/* two stages of translation */
 	DOMAIN_ATTR_MAX,
 };
 
-- 
cgit v1.2.3


From f5c9ecebaf2a2c9381973798e389cc019dd983e0 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Mon, 29 Sep 2014 10:06:19 -0600
Subject: vfio/iommu_type1: add new VFIO_TYPE1_NESTING_IOMMU IOMMU type

VFIO allows devices to be safely handed off to userspace by putting
them behind an IOMMU configured to ensure DMA and interrupt isolation.
This enables userspace KVM clients, such as kvmtool and qemu, to further
map the device into a virtual machine.

With IOMMUs such as the ARM SMMU, it is then possible to provide SMMU
translation services to the guest operating system, which are nested
with the existing translation installed by VFIO. However, enabling this
feature means that the IOMMU driver must be informed that the VFIO domain
is being created for the purposes of nested translation.

This patch adds a new IOMMU type (VFIO_TYPE1_NESTING_IOMMU) to the VFIO
type-1 driver. The new IOMMU type acts identically to the
VFIO_TYPE1v2_IOMMU type, but additionally sets the DOMAIN_ATTR_NESTING
attribute on its IOMMU domains.

Cc: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 30 +++++++++++++++++++++++++-----
 include/uapi/linux/vfio.h       |  3 +++
 2 files changed, 28 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 0734fbe5b651..583ccdb2c58f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -57,7 +57,8 @@ struct vfio_iommu {
 	struct list_head	domain_list;
 	struct mutex		lock;
 	struct rb_root		dma_list;
-	bool v2;
+	bool			v2;
+	bool			nesting;
 };
 
 struct vfio_domain {
@@ -705,6 +706,15 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 		goto out_free;
 	}
 
+	if (iommu->nesting) {
+		int attr = 1;
+
+		ret = iommu_domain_set_attr(domain->domain, DOMAIN_ATTR_NESTING,
+					    &attr);
+		if (ret)
+			goto out_domain;
+	}
+
 	ret = iommu_attach_group(domain->domain, iommu_group);
 	if (ret)
 		goto out_domain;
@@ -819,17 +829,26 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 {
 	struct vfio_iommu *iommu;
 
-	if (arg != VFIO_TYPE1_IOMMU && arg != VFIO_TYPE1v2_IOMMU)
-		return ERR_PTR(-EINVAL);
-
 	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
 		return ERR_PTR(-ENOMEM);
 
+	switch (arg) {
+	case VFIO_TYPE1_IOMMU:
+		break;
+	case VFIO_TYPE1_NESTING_IOMMU:
+		iommu->nesting = true;
+	case VFIO_TYPE1v2_IOMMU:
+		iommu->v2 = true;
+		break;
+	default:
+		kfree(iommu);
+		return ERR_PTR(-EINVAL);
+	}
+
 	INIT_LIST_HEAD(&iommu->domain_list);
 	iommu->dma_list = RB_ROOT;
 	mutex_init(&iommu->lock);
-	iommu->v2 = (arg == VFIO_TYPE1v2_IOMMU);
 
 	return iommu;
 }
@@ -885,6 +904,7 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		switch (arg) {
 		case VFIO_TYPE1_IOMMU:
 		case VFIO_TYPE1v2_IOMMU:
+		case VFIO_TYPE1_NESTING_IOMMU:
 			return 1;
 		case VFIO_DMA_CC_IOMMU:
 			if (!iommu)
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 6612974c64bf..29715d27548f 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -33,6 +33,9 @@
 /* Check if EEH is supported */
 #define VFIO_EEH			5
 
+/* Two-stage IOMMU */
+#define VFIO_TYPE1_NESTING_IOMMU	6	/* Implies v2 */
+
 /*
  * The IOCTL interface is designed for extensibility by embedding the
  * structure length (argsz) and flags into structures passed between
-- 
cgit v1.2.3


From b1937227316417aa7568d01e6fa1f272e98fb890 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 28 Sep 2014 22:18:47 -0700
Subject: net: reorganize sk_buff for faster __copy_skb_header()

With proliferation of bit fields in sk_buff, __copy_skb_header() became
quite expensive, showing as the most expensive function in a GSO
workload.

__copy_skb_header() performance is also critical for non GSO TCP
operations, as it is used from skb_clone()

This patch carefully moves all the fields that were not copied in a
separate zone : cloned, nohdr, fclone, peeked, head_frag, xmit_more

Then I moved all other fields and all other copied fields in a section
delimited by headers_start[0]/headers_end[0] section so that we
can use a single memcpy() call, inlined by compiler using long
word load/stores.

I also tried to make all copies in the natural orders of sk_buff,
to help hardware prefetching.

I made sure sk_buff size did not change.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 133 ++++++++++++++++++++++++++-----------------------
 net/core/skbuff.c      |  80 ++++++++++++++---------------
 2 files changed, 113 insertions(+), 100 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 8eaa62400fca..b6cced304b26 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -527,27 +527,41 @@ struct sk_buff {
 	char			cb[48] __aligned(8);
 
 	unsigned long		_skb_refdst;
+	void			(*destructor)(struct sk_buff *skb);
 #ifdef CONFIG_XFRM
 	struct	sec_path	*sp;
+#endif
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	struct nf_conntrack	*nfct;
+#endif
+#ifdef CONFIG_BRIDGE_NETFILTER
+	struct nf_bridge_info	*nf_bridge;
 #endif
 	unsigned int		len,
 				data_len;
 	__u16			mac_len,
 				hdr_len;
-	union {
-		__wsum		csum;
-		struct {
-			__u16	csum_start;
-			__u16	csum_offset;
-		};
-	};
-	__u32			priority;
+
+	/* Following fields are _not_ copied in __copy_skb_header()
+	 * Note that queue_mapping is here mostly to fill a hole.
+	 */
 	kmemcheck_bitfield_begin(flags1);
-	__u8			ignore_df:1,
-				cloned:1,
-				ip_summed:2,
+	__u16			queue_mapping;
+	__u8			cloned:1,
 				nohdr:1,
-				nfctinfo:3;
+				fclone:2,
+				peeked:1,
+				head_frag:1,
+				xmit_more:1;
+	/* one bit hole */
+	kmemcheck_bitfield_end(flags1);
+
+
+
+	/* fields enclosed in headers_start/headers_end are copied
+	 * using a single memcpy() in __copy_skb_header()
+	 */
+	__u32			headers_start[0];
 
 /* if you move pkt_type around you also must adapt those constants */
 #ifdef __BIG_ENDIAN_BITFIELD
@@ -558,58 +572,53 @@ struct sk_buff {
 #define PKT_TYPE_OFFSET()	offsetof(struct sk_buff, __pkt_type_offset)
 
 	__u8			__pkt_type_offset[0];
-	__u8			pkt_type:3,
-				fclone:2,
-				ipvs_property:1,
-				peeked:1,
-				nf_trace:1;
-	kmemcheck_bitfield_end(flags1);
-	__be16			protocol;
-
-	void			(*destructor)(struct sk_buff *skb);
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-	struct nf_conntrack	*nfct;
-#endif
-#ifdef CONFIG_BRIDGE_NETFILTER
-	struct nf_bridge_info	*nf_bridge;
-#endif
-
-	int			skb_iif;
-
-	__u32			hash;
-
-	__be16			vlan_proto;
-	__u16			vlan_tci;
-
-#ifdef CONFIG_NET_SCHED
-	__u16			tc_index;	/* traffic control index */
-#ifdef CONFIG_NET_CLS_ACT
-	__u16			tc_verd;	/* traffic control verdict */
-#endif
-#endif
-
-	__u16			queue_mapping;
-	kmemcheck_bitfield_begin(flags2);
-	__u8			xmit_more:1;
-#ifdef CONFIG_IPV6_NDISC_NODETYPE
-	__u8			ndisc_nodetype:2;
-#endif
+	__u8			pkt_type:3;
 	__u8			pfmemalloc:1;
+	__u8			ignore_df:1;
+	__u8			nfctinfo:3;
+
+	__u8			nf_trace:1;
+	__u8			ip_summed:2;
 	__u8			ooo_okay:1;
 	__u8			l4_hash:1;
 	__u8			sw_hash:1;
 	__u8			wifi_acked_valid:1;
 	__u8			wifi_acked:1;
+
 	__u8			no_fcs:1;
-	__u8			head_frag:1;
 	/* Indicates the inner headers are valid in the skbuff. */
 	__u8			encapsulation:1;
 	__u8			encap_hdr_csum:1;
 	__u8			csum_valid:1;
 	__u8			csum_complete_sw:1;
-	/* 1/3 bit hole (depending on ndisc_nodetype presence) */
-	kmemcheck_bitfield_end(flags2);
+	__u8			csum_level:2;
+	__u8			csum_bad:1;
 
+#ifdef CONFIG_IPV6_NDISC_NODETYPE
+	__u8			ndisc_nodetype:2;
+#endif
+	__u8			ipvs_property:1;
+	/* 5 or 7 bit hole */
+
+#ifdef CONFIG_NET_SCHED
+	__u16			tc_index;	/* traffic control index */
+#ifdef CONFIG_NET_CLS_ACT
+	__u16			tc_verd;	/* traffic control verdict */
+#endif
+#endif
+
+	union {
+		__wsum		csum;
+		struct {
+			__u16	csum_start;
+			__u16	csum_offset;
+		};
+	};
+	__u32			priority;
+	int			skb_iif;
+	__u32			hash;
+	__be16			vlan_proto;
+	__u16			vlan_tci;
 #if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL
 	union {
 		unsigned int	napi_id;
@@ -625,19 +634,18 @@ struct sk_buff {
 		__u32		reserved_tailroom;
 	};
 
-	kmemcheck_bitfield_begin(flags3);
-	__u8			csum_level:2;
-	__u8			csum_bad:1;
-	/* 13 bit hole */
-	kmemcheck_bitfield_end(flags3);
-
 	__be16			inner_protocol;
 	__u16			inner_transport_header;
 	__u16			inner_network_header;
 	__u16			inner_mac_header;
+
+	__be16			protocol;
 	__u16			transport_header;
 	__u16			network_header;
 	__u16			mac_header;
+
+	__u32			headers_end[0];
+
 	/* These elements must be at the end, see alloc_skb() for details.  */
 	sk_buff_data_t		tail;
 	sk_buff_data_t		end;
@@ -3040,19 +3048,22 @@ static inline void nf_reset_trace(struct sk_buff *skb)
 }
 
 /* Note: This doesn't put any conntrack and bridge info in dst. */
-static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
+static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src,
+			     bool copy)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	dst->nfct = src->nfct;
 	nf_conntrack_get(src->nfct);
-	dst->nfctinfo = src->nfctinfo;
+	if (copy)
+		dst->nfctinfo = src->nfctinfo;
 #endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	dst->nf_bridge  = src->nf_bridge;
 	nf_bridge_get(src->nf_bridge);
 #endif
 #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
-	dst->nf_trace = src->nf_trace;
+	if (copy)
+		dst->nf_trace = src->nf_trace;
 #endif
 }
 
@@ -3064,7 +3075,7 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(dst->nf_bridge);
 #endif
-	__nf_copy(dst, src);
+	__nf_copy(dst, src, true);
 }
 
 #ifdef CONFIG_NETWORK_SECMARK
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d4fdc649112c..4be570a4ab21 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -261,7 +261,6 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 		atomic_t *fclone_ref = (atomic_t *) (child + 1);
 
 		kmemcheck_annotate_bitfield(child, flags1);
-		kmemcheck_annotate_bitfield(child, flags2);
 		skb->fclone = SKB_FCLONE_ORIG;
 		atomic_set(fclone_ref, 1);
 
@@ -675,57 +674,61 @@ void consume_skb(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(consume_skb);
 
+/* Make sure a field is enclosed inside headers_start/headers_end section */
+#define CHECK_SKB_FIELD(field) \
+	BUILD_BUG_ON(offsetof(struct sk_buff, field) <		\
+		     offsetof(struct sk_buff, headers_start));	\
+	BUILD_BUG_ON(offsetof(struct sk_buff, field) >		\
+		     offsetof(struct sk_buff, headers_end));	\
+
 static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 {
 	new->tstamp		= old->tstamp;
+	/* We do not copy old->sk */
 	new->dev		= old->dev;
-	new->transport_header	= old->transport_header;
-	new->network_header	= old->network_header;
-	new->mac_header		= old->mac_header;
-	new->inner_protocol	= old->inner_protocol;
-	new->inner_transport_header = old->inner_transport_header;
-	new->inner_network_header = old->inner_network_header;
-	new->inner_mac_header = old->inner_mac_header;
+	memcpy(new->cb, old->cb, sizeof(old->cb));
 	skb_dst_copy(new, old);
-	skb_copy_hash(new, old);
-	new->ooo_okay		= old->ooo_okay;
-	new->no_fcs		= old->no_fcs;
-	new->encapsulation	= old->encapsulation;
-	new->encap_hdr_csum	= old->encap_hdr_csum;
-	new->csum_valid		= old->csum_valid;
-	new->csum_complete_sw	= old->csum_complete_sw;
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
 #endif
-	memcpy(new->cb, old->cb, sizeof(old->cb));
-	new->csum		= old->csum;
-	new->ignore_df		= old->ignore_df;
-	new->pkt_type		= old->pkt_type;
-	new->ip_summed		= old->ip_summed;
-	skb_copy_queue_mapping(new, old);
-	new->priority		= old->priority;
-#if IS_ENABLED(CONFIG_IP_VS)
-	new->ipvs_property	= old->ipvs_property;
+	__nf_copy(new, old, false);
+
+	/* Note : this field could be in headers_start/headers_end section
+	 * It is not yet because we do not want to have a 16 bit hole
+	 */
+	new->queue_mapping = old->queue_mapping;
+
+	memcpy(&new->headers_start, &old->headers_start,
+	       offsetof(struct sk_buff, headers_end) -
+	       offsetof(struct sk_buff, headers_start));
+	CHECK_SKB_FIELD(protocol);
+	CHECK_SKB_FIELD(csum);
+	CHECK_SKB_FIELD(hash);
+	CHECK_SKB_FIELD(priority);
+	CHECK_SKB_FIELD(skb_iif);
+	CHECK_SKB_FIELD(vlan_proto);
+	CHECK_SKB_FIELD(vlan_tci);
+	CHECK_SKB_FIELD(transport_header);
+	CHECK_SKB_FIELD(network_header);
+	CHECK_SKB_FIELD(mac_header);
+	CHECK_SKB_FIELD(inner_protocol);
+	CHECK_SKB_FIELD(inner_transport_header);
+	CHECK_SKB_FIELD(inner_network_header);
+	CHECK_SKB_FIELD(inner_mac_header);
+	CHECK_SKB_FIELD(mark);
+#ifdef CONFIG_NETWORK_SECMARK
+	CHECK_SKB_FIELD(secmark);
+#endif
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	CHECK_SKB_FIELD(napi_id);
 #endif
-	new->pfmemalloc		= old->pfmemalloc;
-	new->protocol		= old->protocol;
-	new->mark		= old->mark;
-	new->skb_iif		= old->skb_iif;
-	__nf_copy(new, old);
 #ifdef CONFIG_NET_SCHED
-	new->tc_index		= old->tc_index;
+	CHECK_SKB_FIELD(tc_index);
 #ifdef CONFIG_NET_CLS_ACT
-	new->tc_verd		= old->tc_verd;
+	CHECK_SKB_FIELD(tc_verd);
 #endif
 #endif
-	new->vlan_proto		= old->vlan_proto;
-	new->vlan_tci		= old->vlan_tci;
-
-	skb_copy_secmark(new, old);
 
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	new->napi_id	= old->napi_id;
-#endif
 }
 
 /*
@@ -876,7 +879,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 			return NULL;
 
 		kmemcheck_annotate_bitfield(n, flags1);
-		kmemcheck_annotate_bitfield(n, flags2);
 		n->fclone = SKB_FCLONE_UNAVAILABLE;
 	}
 
-- 
cgit v1.2.3


From 0bd2ac3dae74ee25c5ea171cb572731c7a89c248 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 29 Sep 2014 11:40:42 +0200
Subject: ASoC: Remove CODEC pointer from snd_soc_dapm_context

The only remaining user of the CODEC pointer in the DAPM struct is to
initialize the CODEC pointer in the widget struct. The later is scheduled
for removal, but has still a few users left. For now use
dapm->component->codec to initialize it.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h | 1 -
 sound/soc/soc-core.c     | 1 -
 sound/soc/soc-dapm.c     | 2 +-
 3 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index aac04ff84eea..d60c61b4b341 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -593,7 +593,6 @@ struct snd_soc_dapm_context {
 
 	struct device *dev; /* from parent - for debug */
 	struct snd_soc_component *component; /* parent component */
-	struct snd_soc_codec *codec; /* parent codec */
 	struct snd_soc_card *card; /* parent card */
 
 	/* used during DAPM updates */
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 052f59c1917f..8d45eec141a9 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -4351,7 +4351,6 @@ int snd_soc_register_codec(struct device *dev,
 	if (codec_drv->read)
 		codec->component.read = snd_soc_codec_drv_read;
 	codec->component.ignore_pmdown_time = codec_drv->ignore_pmdown_time;
-	codec->dapm.codec = codec;
 	codec->dapm.idle_bias_off = codec_drv->idle_bias_off;
 	if (codec_drv->seq_notifier)
 		codec->dapm.seq_notifier = codec_drv->seq_notifier;
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 8348352dc2c6..1f1e9657481a 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3107,7 +3107,7 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
 	}
 
 	w->dapm = dapm;
-	w->codec = dapm->codec;
+	w->codec = dapm->component->codec;
 	INIT_LIST_HEAD(&w->sources);
 	INIT_LIST_HEAD(&w->sinks);
 	INIT_LIST_HEAD(&w->list);
-- 
cgit v1.2.3


From 87a15a8090c0e5284c0e53528d9defa5d9237866 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Fri, 26 Sep 2014 13:58:26 -0400
Subject: NFSD: Add generic v4.2 infrastructure

It's cleaner to introduce everything at once and have the server reply
with "not supported" than it would be to introduce extra operations when
implementing a specific one in the middle of the list.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4xdr.c    | 28 ++++++++++++++++++++++++++++
 include/linux/nfs4.h | 18 ++++++++++++++++--
 2 files changed, 44 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index e771a1a7c6f1..0311baebd7d3 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1586,6 +1586,20 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_WANT_DELEGATION]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_DESTROY_CLIENTID]	= (nfsd4_dec)nfsd4_decode_destroy_clientid,
 	[OP_RECLAIM_COMPLETE]	= (nfsd4_dec)nfsd4_decode_reclaim_complete,
+
+	/* new operations for NFSv4.2 */
+	[OP_ALLOCATE]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_COPY]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_COPY_NOTIFY]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_DEALLOCATE]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_IO_ADVISE]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_LAYOUTERROR]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_LAYOUTSTATS]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_OFFLOAD_CANCEL]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_OFFLOAD_STATUS]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_READ_PLUS]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_SEEK]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_WRITE_SAME]		= (nfsd4_dec)nfsd4_decode_notsupp,
 };
 
 static inline bool
@@ -3823,6 +3837,20 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_WANT_DELEGATION]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_DESTROY_CLIENTID]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_RECLAIM_COMPLETE]	= (nfsd4_enc)nfsd4_encode_noop,
+
+	/* NFSv4.2 operations */
+	[OP_ALLOCATE]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_COPY]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_COPY_NOTIFY]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_DEALLOCATE]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_IO_ADVISE]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_LAYOUTERROR]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_LAYOUTSTATS]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_OFFLOAD_CANCEL]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_OFFLOAD_STATUS]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_READ_PLUS]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_SEEK]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_WRITE_SAME]		= (nfsd4_enc)nfsd4_encode_noop,
 };
 
 /*
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 79b2a0f5c318..cf38224c4fa0 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -110,6 +110,20 @@ enum nfs_opnum4 {
 	OP_DESTROY_CLIENTID = 57,
 	OP_RECLAIM_COMPLETE = 58,
 
+	/* nfs42 */
+	OP_ALLOCATE = 59,
+	OP_COPY = 60,
+	OP_COPY_NOTIFY = 61,
+	OP_DEALLOCATE = 62,
+	OP_IO_ADVISE = 63,
+	OP_LAYOUTERROR = 64,
+	OP_LAYOUTSTATS = 65,
+	OP_OFFLOAD_CANCEL = 66,
+	OP_OFFLOAD_STATUS = 67,
+	OP_READ_PLUS = 68,
+	OP_SEEK = 69,
+	OP_WRITE_SAME = 70,
+
 	OP_ILLEGAL = 10044,
 };
 
@@ -117,10 +131,10 @@ enum nfs_opnum4 {
 Needs to be updated if more operations are defined in future.*/
 
 #define FIRST_NFS4_OP	OP_ACCESS
-#define LAST_NFS4_OP 	OP_RECLAIM_COMPLETE
+#define LAST_NFS4_OP 	OP_WRITE_SAME
 #define LAST_NFS40_OP	OP_RELEASE_LOCKOWNER
 #define LAST_NFS41_OP	OP_RECLAIM_COMPLETE
-#define LAST_NFS42_OP	OP_RECLAIM_COMPLETE
+#define LAST_NFS42_OP	OP_WRITE_SAME
 
 enum nfsstat4 {
 	NFS4_OK = 0,
-- 
cgit v1.2.3


From 24bab491220faa446d945624086d838af41d616c Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Fri, 26 Sep 2014 13:58:27 -0400
Subject: NFSD: Implement SEEK

This patch adds server support for the NFS v4.2 operation SEEK, which
returns the position of the next hole or data segment in a file.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4proc.c   | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfsd/nfs4xdr.c    | 36 ++++++++++++++++++++++++++++++++++--
 fs/nfsd/xdr4.h       | 14 ++++++++++++++
 include/linux/nfs4.h |  5 +++++
 4 files changed, 102 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 5e0dc528a0e8..cdeb3cfd6f32 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1013,6 +1013,49 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status;
 }
 
+static __be32
+nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		struct nfsd4_seek *seek)
+{
+	int whence;
+	__be32 status;
+	struct file *file;
+
+	status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate,
+					    &seek->seek_stateid,
+					    RD_STATE, &file);
+	if (status) {
+		dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
+		return status;
+	}
+
+	switch (seek->seek_whence) {
+	case NFS4_CONTENT_DATA:
+		whence = SEEK_DATA;
+		break;
+	case NFS4_CONTENT_HOLE:
+		whence = SEEK_HOLE;
+		break;
+	default:
+		status = nfserr_union_notsupp;
+		goto out;
+	}
+
+	/*
+	 * Note:  This call does change file->f_pos, but nothing in NFSD
+	 *        should ever file->f_pos.
+	 */
+	seek->seek_pos = vfs_llseek(file, seek->seek_offset, whence);
+	if (seek->seek_pos < 0)
+		status = nfserrno(seek->seek_pos);
+	else if (seek->seek_pos >= i_size_read(file_inode(file)))
+		seek->seek_eof = true;
+
+out:
+	fput(file);
+	return status;
+}
+
 /* This routine never returns NFS_OK!  If there are no other errors, it
  * will return NFSERR_SAME or NFSERR_NOT_SAME depending on whether the
  * attributes matched.  VERIFY is implemented by mapping NFSERR_SAME
@@ -1881,6 +1924,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+
+	/* NFSv4.2 operations */
+	[OP_SEEK] = {
+		.op_func = (nfsd4op_func)nfsd4_seek,
+		.op_name = "OP_SEEK",
+	},
 };
 
 int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0311baebd7d3..7ec646380005 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1513,6 +1513,22 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	DECODE_TAIL;
 }
 
+static __be32
+nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
+{
+	DECODE_HEAD;
+
+	status = nfsd4_decode_stateid(argp, &seek->seek_stateid);
+	if (status)
+		return status;
+
+	READ_BUF(8 + 4);
+	p = xdr_decode_hyper(p, &seek->seek_offset);
+	seek->seek_whence = be32_to_cpup(p);
+
+	DECODE_TAIL;
+}
+
 static __be32
 nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p)
 {
@@ -1598,7 +1614,7 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_OFFLOAD_CANCEL]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_OFFLOAD_STATUS]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_READ_PLUS]		= (nfsd4_dec)nfsd4_decode_notsupp,
-	[OP_SEEK]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_SEEK]		= (nfsd4_dec)nfsd4_decode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_dec)nfsd4_decode_notsupp,
 };
 
@@ -3765,6 +3781,22 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
 	return nfserr;
 }
 
+static __be32
+nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
+		  struct nfsd4_seek *seek)
+{
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(&resp->xdr, 4 + 8);
+	*p++ = cpu_to_be32(seek->seek_eof);
+	p = xdr_encode_hyper(p, seek->seek_pos);
+
+	return nfserr;
+}
+
 static __be32
 nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p)
 {
@@ -3849,7 +3881,7 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_OFFLOAD_CANCEL]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_OFFLOAD_STATUS]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_READ_PLUS]		= (nfsd4_enc)nfsd4_encode_noop,
-	[OP_SEEK]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_SEEK]		= (nfsd4_enc)nfsd4_encode_seek,
 	[OP_WRITE_SAME]		= (nfsd4_enc)nfsd4_encode_noop,
 };
 
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 465e7799742a..5720e9457f33 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -428,6 +428,17 @@ struct nfsd4_reclaim_complete {
 	u32 rca_one_fs;
 };
 
+struct nfsd4_seek {
+	/* request */
+	stateid_t	seek_stateid;
+	loff_t		seek_offset;
+	u32		seek_whence;
+
+	/* response */
+	u32		seek_eof;
+	loff_t		seek_pos;
+};
+
 struct nfsd4_op {
 	int					opnum;
 	__be32					status;
@@ -473,6 +484,9 @@ struct nfsd4_op {
 		struct nfsd4_reclaim_complete	reclaim_complete;
 		struct nfsd4_test_stateid	test_stateid;
 		struct nfsd4_free_stateid	free_stateid;
+
+		/* NFSv4.2 */
+		struct nfsd4_seek		seek;
 	} u;
 	struct nfs4_replay *			replay;
 };
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index cf38224c4fa0..026b0c042c40 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -550,4 +550,9 @@ struct nfs4_deviceid {
 	char data[NFS4_DEVICEID4_SIZE];
 };
 
+enum data_content4 {
+	NFS4_CONTENT_DATA		= 0,
+	NFS4_CONTENT_HOLE		= 1,
+};
+
 #endif
-- 
cgit v1.2.3


From 8c14f9c70327a6fb75534c4c61d7ea9c82ccf78f Mon Sep 17 00:00:00 2001
From: Michael Grzeschik <m.grzeschik@pengutronix.de>
Date: Mon, 29 Sep 2014 11:55:36 +0200
Subject: ARCNET: add com20020 PCI IDs with metadata

This patch adds metadata for the com20020 to prepare for devices with
multiple io address areas with multi card interfaces.

Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/arcnet/com20020-pci.c | 216 ++++++++++++++++++++++++++++++++------
 include/linux/com20020.h          |  16 +++
 2 files changed, 197 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index 7bb292e59559..f9e55527739d 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -63,6 +63,8 @@ MODULE_LICENSE("GPL");
 
 static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct com20020_pci_channel_map *cm;
+	struct com20020_pci_card_info *ci;
 	struct net_device *dev;
 	struct arcnet_local *lp;
 	int ioaddr, err;
@@ -75,19 +77,15 @@ static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *i
 
 	dev->netdev_ops = &com20020_netdev_ops;
 
+	ci = (struct com20020_pci_card_info *)id->driver_data;
+
 	lp = netdev_priv(dev);
 
 	pci_set_drvdata(pdev, dev);
 
-	// SOHARD needs PCI base addr 4
-	if (pdev->vendor==0x10B5) {
-		BUGMSG(D_NORMAL, "SOHARD\n");
-		ioaddr = pci_resource_start(pdev, 4);
-	}
-	else {
-		BUGMSG(D_NORMAL, "Contemporary Controls\n");
-		ioaddr = pci_resource_start(pdev, 2);
-	}
+	cm = &ci->chan_map_tbl[0];
+	BUGMSG(D_NORMAL, "%s Controls\n", ci->name);
+	ioaddr = pci_resource_start(pdev, cm->bar);
 
 	if (!request_region(ioaddr, ARCNET_TOTAL_SIZE, "com20020-pci")) {
 		BUGMSG(D_INIT, "IO region %xh-%xh already allocated.\n",
@@ -105,7 +103,7 @@ static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *i
 	dev->irq = pdev->irq;
 	dev->dev_addr[0] = node;
 	lp->card_name = "PCI COM20020";
-	lp->card_flags = id->driver_data;
+	lp->card_flags = ci->flags;
 	lp->backplane = backplane;
 	lp->clockp = clockp & 7;
 	lp->clockm = clockm & 3;
@@ -144,32 +142,180 @@ static void com20020pci_remove(struct pci_dev *pdev)
 	free_netdev(dev);
 }
 
+static struct com20020_pci_card_info card_info_10mbit = {
+	.name = "ARC-PCI",
+	.devcount = 1,
+	.chan_map_tbl = {
+		{ 2, 0x00, 0x08 },
+	},
+	.flags = ARC_CAN_10MBIT,
+};
+
+static struct com20020_pci_card_info card_info_5mbit = {
+	.name = "ARC-PCI",
+	.devcount = 1,
+	.chan_map_tbl = {
+		{ 2, 0x00, 0x08 },
+	},
+	.flags = ARC_IS_5MBIT,
+};
+
+static struct com20020_pci_card_info card_info_sohard = {
+	.name = "PLX-PCI",
+	.devcount = 1,
+	/* SOHARD needs PCI base addr 4 */
+	.chan_map_tbl = {
+		{4, 0x00, 0x08},
+	},
+	.flags = ARC_CAN_10MBIT,
+};
+
 static const struct pci_device_id com20020pci_id_table[] = {
-	{ 0x1571, 0xa001, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
-	{ 0x1571, 0xa002, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
-	{ 0x1571, 0xa003, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
-	{ 0x1571, 0xa004, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
-	{ 0x1571, 0xa005, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
-	{ 0x1571, 0xa006, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
-	{ 0x1571, 0xa007, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
-	{ 0x1571, 0xa008, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
-	{ 0x1571, 0xa009, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_IS_5MBIT },
-	{ 0x1571, 0xa00a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_IS_5MBIT },
-	{ 0x1571, 0xa00b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_IS_5MBIT },
-	{ 0x1571, 0xa00c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_IS_5MBIT },
-	{ 0x1571, 0xa00d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_IS_5MBIT },
-	{ 0x1571, 0xa00e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_IS_5MBIT },
-	{ 0x1571, 0xa201, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
-	{ 0x1571, 0xa202, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
-	{ 0x1571, 0xa203, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
-	{ 0x1571, 0xa204, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
-	{ 0x1571, 0xa205, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
-	{ 0x1571, 0xa206, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
-	{ 0x10B5, 0x9030, 0x10B5,     0x2978,     0, 0, ARC_CAN_10MBIT },
-	{ 0x10B5, 0x9050, 0x10B5,     0x2273,     0, 0, ARC_CAN_10MBIT },
-	{ 0x14BA, 0x6000, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
-	{ 0x10B5, 0x2200, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ARC_CAN_10MBIT },
-	{0,}
+	{
+		0x1571, 0xa001,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		0,
+	},
+	{
+		0x1571, 0xa002,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		0,
+	},
+	{
+		0x1571, 0xa003,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		0
+	},
+	{
+		0x1571, 0xa004,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		0,
+	},
+	{
+		0x1571, 0xa005,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		0
+	},
+	{
+		0x1571, 0xa006,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		0
+	},
+	{
+		0x1571, 0xa007,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		0
+	},
+	{
+		0x1571, 0xa008,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		0
+	},
+	{
+		0x1571, 0xa009,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_5mbit
+	},
+	{
+		0x1571, 0xa00a,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_5mbit
+	},
+	{
+		0x1571, 0xa00b,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_5mbit
+	},
+	{
+		0x1571, 0xa00c,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_5mbit
+	},
+	{
+		0x1571, 0xa00d,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_5mbit
+	},
+	{
+		0x1571, 0xa00e,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_5mbit
+	},
+	{
+		0x1571, 0xa201,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_10mbit
+	},
+	{
+		0x1571, 0xa202,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_10mbit
+	},
+	{
+		0x1571, 0xa203,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_10mbit
+	},
+	{
+		0x1571, 0xa204,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_10mbit
+	},
+	{
+		0x1571, 0xa205,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_10mbit
+	},
+	{
+		0x1571, 0xa206,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_10mbit
+	},
+	{
+		0x10B5, 0x9030,
+		0x10B5, 0x2978,
+		0, 0,
+		(kernel_ulong_t)&card_info_sohard
+	},
+	{
+		0x10B5, 0x9050,
+		0x10B5, 0x2273,
+		0, 0,
+		(kernel_ulong_t)&card_info_sohard
+	},
+	{
+		0x14BA, 0x6000,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_10mbit
+	},
+	{
+		0x10B5, 0x2200,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0,
+		(kernel_ulong_t)&card_info_10mbit
+	},
+	{ 0, }
 };
 
 MODULE_DEVICE_TABLE(pci, com20020pci_id_table);
diff --git a/include/linux/com20020.h b/include/linux/com20020.h
index 5dcfb944b6ce..6a1ceca61e7f 100644
--- a/include/linux/com20020.h
+++ b/include/linux/com20020.h
@@ -41,6 +41,22 @@ extern const struct net_device_ops com20020_netdev_ops;
 #define BUS_ALIGN  1
 #endif
 
+#define PLX_PCI_MAX_CARDS 1
+
+struct com20020_pci_channel_map {
+	u32 bar;
+	u32 offset;
+	u32 size;               /* 0x00 - auto, e.g. length of entire bar */
+};
+
+struct com20020_pci_card_info {
+	const char *name;
+	int devcount;
+
+	struct com20020_pci_channel_map chan_map_tbl[PLX_PCI_MAX_CARDS];
+
+	unsigned int flags;
+};
 
 #define _INTMASK  (ioaddr+BUS_ALIGN*0)	/* writable */
 #define _STATUS   (ioaddr+BUS_ALIGN*0)	/* readable */
-- 
cgit v1.2.3


From c51da42a6346c0c747e70a4f5ae873da1150a784 Mon Sep 17 00:00:00 2001
From: Michael Grzeschik <m.grzeschik@pengutronix.de>
Date: Mon, 29 Sep 2014 11:55:37 +0200
Subject: ARCNET: add support for multi interfaces on com20020

The com20020-pci driver is currently designed to instance
one netdev with one pci device. This patch adds support to
instance many cards with one pci device, depending on the device
data in the private data.

Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/arcnet/com20020-pci.c | 149 ++++++++++++++++++++++++--------------
 drivers/net/arcnet/com20020_cs.c  |   4 -
 include/linux/com20020.h          |  15 +++-
 3 files changed, 109 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index f9e55527739d..fe87576bae3c 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -38,6 +38,7 @@
 #include <linux/pci.h>
 #include <linux/arcdevice.h>
 #include <linux/com20020.h>
+#include <linux/list.h>
 
 #include <asm/io.h>
 
@@ -61,85 +62,125 @@ module_param(clockp, int, 0);
 module_param(clockm, int, 0);
 MODULE_LICENSE("GPL");
 
+static void com20020pci_remove(struct pci_dev *pdev);
+
 static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	struct com20020_pci_channel_map *cm;
 	struct com20020_pci_card_info *ci;
 	struct net_device *dev;
 	struct arcnet_local *lp;
-	int ioaddr, err;
+	struct com20020_priv *priv;
+	int i, ioaddr, ret;
+	struct resource *r;
 
 	if (pci_enable_device(pdev))
 		return -EIO;
-	dev = alloc_arcdev(device);
-	if (!dev)
-		return -ENOMEM;
-
-	dev->netdev_ops = &com20020_netdev_ops;
 
+	priv = devm_kzalloc(&pdev->dev, sizeof(struct com20020_priv),
+			    GFP_KERNEL);
 	ci = (struct com20020_pci_card_info *)id->driver_data;
+	priv->ci = ci;
 
-	lp = netdev_priv(dev);
+	INIT_LIST_HEAD(&priv->list_dev);
 
-	pci_set_drvdata(pdev, dev);
 
-	cm = &ci->chan_map_tbl[0];
-	BUGMSG(D_NORMAL, "%s Controls\n", ci->name);
-	ioaddr = pci_resource_start(pdev, cm->bar);
+	for (i = 0; i < ci->devcount; i++) {
+		struct com20020_pci_channel_map *cm = &ci->chan_map_tbl[i];
+		struct com20020_dev *card;
 
-	if (!request_region(ioaddr, ARCNET_TOTAL_SIZE, "com20020-pci")) {
-		BUGMSG(D_INIT, "IO region %xh-%xh already allocated.\n",
-		       ioaddr, ioaddr + ARCNET_TOTAL_SIZE - 1);
-		err = -EBUSY;
-		goto out_dev;
-	}
+		dev = alloc_arcdev(device);
+		if (!dev) {
+			ret = -ENOMEM;
+			goto out_port;
+		}
 
-	// Dummy access after Reset
-	// ARCNET controller needs this access to detect bustype
-	outb(0x00,ioaddr+1);
-	inb(ioaddr+1);
-
-	dev->base_addr = ioaddr;
-	dev->irq = pdev->irq;
-	dev->dev_addr[0] = node;
-	lp->card_name = "PCI COM20020";
-	lp->card_flags = ci->flags;
-	lp->backplane = backplane;
-	lp->clockp = clockp & 7;
-	lp->clockm = clockm & 3;
-	lp->timeout = timeout;
-	lp->hw.owner = THIS_MODULE;
-
-	if (ASTATUS() == 0xFF) {
-		BUGMSG(D_NORMAL, "IO address %Xh was reported by PCI BIOS, "
-		       "but seems empty!\n", ioaddr);
-		err = -EIO;
-		goto out_port;
-	}
-	if (com20020_check(dev)) {
-		err = -EIO;
-		goto out_port;
+		dev->netdev_ops = &com20020_netdev_ops;
+
+		lp = netdev_priv(dev);
+
+		BUGMSG(D_NORMAL, "%s Controls\n", ci->name);
+		ioaddr = pci_resource_start(pdev, cm->bar) + cm->offset;
+
+		r = devm_request_region(&pdev->dev, ioaddr, cm->size,
+					"com20020-pci");
+		if (!r) {
+			pr_err("IO region %xh-%xh already allocated.\n",
+			       ioaddr, ioaddr + cm->size - 1);
+			ret = -EBUSY;
+			goto out_port;
+		}
+
+		/* Dummy access after Reset
+		 * ARCNET controller needs
+		 * this access to detect bustype
+		 */
+		outb(0x00, ioaddr + 1);
+		inb(ioaddr + 1);
+
+		dev->base_addr = ioaddr;
+		dev->dev_addr[0] = node;
+		dev->irq = pdev->irq;
+		lp->card_name = "PCI COM20020";
+		lp->card_flags = ci->flags;
+		lp->backplane = backplane;
+		lp->clockp = clockp & 7;
+		lp->clockm = clockm & 3;
+		lp->timeout = timeout;
+		lp->hw.owner = THIS_MODULE;
+
+		if (ASTATUS() == 0xFF) {
+			pr_err("IO address %Xh is empty!\n", ioaddr);
+			ret = -EIO;
+			goto out_port;
+		}
+		if (com20020_check(dev)) {
+			ret = -EIO;
+			goto out_port;
+		}
+
+		card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev),
+				    GFP_KERNEL);
+		if (!card) {
+			pr_err("%s out of memory!\n", __func__);
+			return -ENOMEM;
+		}
+
+		card->index = i;
+		card->pci_priv = priv;
+		card->dev = dev;
+
+		dev_set_drvdata(&dev->dev, card);
+
+		ret = com20020_found(dev, IRQF_SHARED);
+		if (ret)
+			goto out_port;
+
+		list_add(&card->list, &priv->list_dev);
 	}
 
-	if ((err = com20020_found(dev, IRQF_SHARED)) != 0)
-	        goto out_port;
+	pci_set_drvdata(pdev, priv);
 
 	return 0;
 
 out_port:
-	release_region(ioaddr, ARCNET_TOTAL_SIZE);
-out_dev:
-	free_netdev(dev);
-	return err;
+	com20020pci_remove(pdev);
+	return ret;
 }
 
 static void com20020pci_remove(struct pci_dev *pdev)
 {
-	struct net_device *dev = pci_get_drvdata(pdev);
-	unregister_netdev(dev);
-	free_irq(dev->irq, dev);
-	release_region(dev->base_addr, ARCNET_TOTAL_SIZE);
-	free_netdev(dev);
+	struct com20020_dev *card, *tmpcard;
+	struct com20020_priv *priv;
+
+	priv = pci_get_drvdata(pdev);
+
+	list_for_each_entry_safe(card, tmpcard, &priv->list_dev, list) {
+		struct net_device *dev = card->dev;
+
+		unregister_netdev(dev);
+		free_irq(dev->irq, dev);
+		free_netdev(dev);
+	}
 }
 
 static struct com20020_pci_card_info card_info_10mbit = {
diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c
index 1a790a20210d..057d9582132a 100644
--- a/drivers/net/arcnet/com20020_cs.c
+++ b/drivers/net/arcnet/com20020_cs.c
@@ -112,10 +112,6 @@ static void com20020_detach(struct pcmcia_device *p_dev);
 
 /*====================================================================*/
 
-struct com20020_dev {
-    struct net_device       *dev;
-};
-
 static int com20020_probe(struct pcmcia_device *p_dev)
 {
     struct com20020_dev *info;
diff --git a/include/linux/com20020.h b/include/linux/com20020.h
index 6a1ceca61e7f..85898995b234 100644
--- a/include/linux/com20020.h
+++ b/include/linux/com20020.h
@@ -41,7 +41,7 @@ extern const struct net_device_ops com20020_netdev_ops;
 #define BUS_ALIGN  1
 #endif
 
-#define PLX_PCI_MAX_CARDS 1
+#define PLX_PCI_MAX_CARDS 2
 
 struct com20020_pci_channel_map {
 	u32 bar;
@@ -58,6 +58,19 @@ struct com20020_pci_card_info {
 	unsigned int flags;
 };
 
+struct com20020_priv {
+	struct com20020_pci_card_info *ci;
+	struct list_head list_dev;
+};
+
+struct com20020_dev {
+	struct list_head list;
+	struct net_device *dev;
+
+	struct com20020_priv *pci_priv;
+	int index;
+};
+
 #define _INTMASK  (ioaddr+BUS_ALIGN*0)	/* writable */
 #define _STATUS   (ioaddr+BUS_ALIGN*0)	/* readable */
 #define _COMMAND  (ioaddr+BUS_ALIGN*1)	/* standard arcnet commands */
-- 
cgit v1.2.3


From d82bd1229885d550d03926cfa937703f6caa3cc0 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 29 Sep 2014 13:08:29 +0200
Subject: tcp: move TCP_ECN_create_request out of header

After Octavian Purdilas tcp ipv4/ipv6 unification work this helper only
has a single callsite.

While at it, convert name to lowercase, suggested by Stephen.

Suggested-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    | 34 ----------------------------------
 net/ipv4/tcp_input.c | 36 +++++++++++++++++++++++++++++++++++-
 2 files changed, 35 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 1f57c5363492..545a79aa4212 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -861,40 +861,6 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
 		icsk->icsk_ca_ops->cwnd_event(sk, event);
 }
 
-/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
- *
- * If we receive a SYN packet with these bits set, it means a
- * network is playing bad games with TOS bits. In order to
- * avoid possible false congestion notifications, we disable
- * TCP ECN negociation.
- *
- * Exception: tcp_ca wants ECN. This is required for DCTCP
- * congestion control; it requires setting ECT on all packets,
- * including SYN. We inverse the test in this case: If our
- * local socket wants ECN, but peer only set ece/cwr (but not
- * ECT in IP header) its probably a non-DCTCP aware sender.
- */
-static inline void
-TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb,
-		       const struct sock *listen_sk)
-{
-	const struct tcphdr *th = tcp_hdr(skb);
-	const struct net *net = sock_net(listen_sk);
-	bool th_ecn = th->ece && th->cwr;
-	bool ect, need_ecn;
-
-	if (!th_ecn)
-		return;
-
-	ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
-	need_ecn = tcp_ca_needs_ecn(listen_sk);
-
-	if (!ect && !need_ecn && net->ipv4.sysctl_tcp_ecn)
-		inet_rsk(req)->ecn_ok = 1;
-	else if (ect && need_ecn)
-		inet_rsk(req)->ecn_ok = 1;
-}
-
 /* These functions determine how the current flow behaves in respect of SACK
  * handling. SACK is negotiated with the peer, and therefore it can vary
  * between different flows.
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fc133178c787..174181e28ef3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5906,6 +5906,40 @@ static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
 #endif
 }
 
+/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
+ *
+ * If we receive a SYN packet with these bits set, it means a
+ * network is playing bad games with TOS bits. In order to
+ * avoid possible false congestion notifications, we disable
+ * TCP ECN negociation.
+ *
+ * Exception: tcp_ca wants ECN. This is required for DCTCP
+ * congestion control; it requires setting ECT on all packets,
+ * including SYN. We inverse the test in this case: If our
+ * local socket wants ECN, but peer only set ece/cwr (but not
+ * ECT in IP header) its probably a non-DCTCP aware sender.
+ */
+static void tcp_ecn_create_request(struct request_sock *req,
+				   const struct sk_buff *skb,
+				   const struct sock *listen_sk)
+{
+	const struct tcphdr *th = tcp_hdr(skb);
+	const struct net *net = sock_net(listen_sk);
+	bool th_ecn = th->ece && th->cwr;
+	bool ect, need_ecn;
+
+	if (!th_ecn)
+		return;
+
+	ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
+	need_ecn = tcp_ca_needs_ecn(listen_sk);
+
+	if (!ect && !need_ecn && net->ipv4.sysctl_tcp_ecn)
+		inet_rsk(req)->ecn_ok = 1;
+	else if (ect && need_ecn)
+		inet_rsk(req)->ecn_ok = 1;
+}
+
 int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		     const struct tcp_request_sock_ops *af_ops,
 		     struct sock *sk, struct sk_buff *skb)
@@ -5966,7 +6000,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		goto drop_and_free;
 
 	if (!want_cookie || tmp_opt.tstamp_ok)
-		TCP_ECN_create_request(req, skb, sk);
+		tcp_ecn_create_request(req, skb, sk);
 
 	if (want_cookie) {
 		isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
-- 
cgit v1.2.3


From 6f67c380056ceaf5844f18d3a5d769d233247849 Mon Sep 17 00:00:00 2001
From: Anatol Pomozov <anatol.pomozov@gmail.com>
Date: Fri, 26 Sep 2014 09:57:27 -0700
Subject: ASoC: rt5677: Add dts properties for input/output differential
 configuration

Signed-off-by: Anatol Pomozov <anatol.pomozov@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/rt5677.txt |  9 +++++++++
 include/sound/rt5677.h                             |  5 ++++-
 sound/soc/codecs/rt5677.c                          | 23 ++++++++++++++++++++++
 3 files changed, 36 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/sound/rt5677.txt b/Documentation/devicetree/bindings/sound/rt5677.txt
index bd28df604b7b..0701b834fc73 100644
--- a/Documentation/devicetree/bindings/sound/rt5677.txt
+++ b/Documentation/devicetree/bindings/sound/rt5677.txt
@@ -19,6 +19,14 @@ Optional properties:
 
 - realtek,pow-ldo2-gpio : The GPIO that controls the CODEC's POW_LDO2 pin.
 
+- realtek,in1-differential
+- realtek,in2-differential
+- realtek,lout1-differential
+- realtek,lout2-differential
+- realtek,lout3-differential
+  Boolean. Indicate MIC1/2 input and LOUT1/2/3 outputs are differential,
+  rather than single-ended.
+
 Pins on the device (for linking into audio routes):
 
   * IN1P
@@ -47,4 +55,5 @@ rt5677 {
 
 	realtek,pow-ldo2-gpio =
 		<&gpio TEGRA_GPIO(V, 3) GPIO_ACTIVE_HIGH>;
+	realtek,in1-differential = "true";
 };
diff --git a/include/sound/rt5677.h b/include/sound/rt5677.h
index a676717f74f4..082670e3a353 100644
--- a/include/sound/rt5677.h
+++ b/include/sound/rt5677.h
@@ -19,9 +19,12 @@ enum rt5677_dmic2_clk {
 
 
 struct rt5677_platform_data {
-	/* IN1 IN2 can optionally be differential */
+	/* IN1/IN2/LOUT1/LOUT2/LOUT3 can optionally be differential */
 	bool in1_diff;
 	bool in2_diff;
+	bool lout1_diff;
+	bool lout2_diff;
+	bool lout3_diff;
 	/* DMIC2 clock source selection */
 	enum rt5677_dmic2_clk dmic2_clk_pin;
 };
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index d2c6abf38ad2..97dff7172fb6 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -3569,6 +3569,17 @@ MODULE_DEVICE_TABLE(i2c, rt5677_i2c_id);
 
 static int rt5677_parse_dt(struct rt5677_priv *rt5677, struct device_node *np)
 {
+	rt5677->pdata.in1_diff = of_property_read_bool(np,
+					"realtek,in1-differential");
+	rt5677->pdata.in2_diff = of_property_read_bool(np,
+					"realtek,in2-differential");
+	rt5677->pdata.lout1_diff = of_property_read_bool(np,
+					"realtek,lout1-differential");
+	rt5677->pdata.lout2_diff = of_property_read_bool(np,
+					"realtek,lout2-differential");
+	rt5677->pdata.lout3_diff = of_property_read_bool(np,
+					"realtek,lout3-differential");
+
 	rt5677->pow_ldo2 = of_get_named_gpio(np,
 					"realtek,pow-ldo2-gpio", 0);
 
@@ -3660,6 +3671,18 @@ static int rt5677_i2c_probe(struct i2c_client *i2c,
 		regmap_update_bits(rt5677->regmap, RT5677_IN1,
 					RT5677_IN_DF2, RT5677_IN_DF2);
 
+	if (rt5677->pdata.lout1_diff)
+		regmap_update_bits(rt5677->regmap, RT5677_LOUT1,
+					RT5677_LOUT1_L_DF, RT5677_LOUT1_L_DF);
+
+	if (rt5677->pdata.lout2_diff)
+		regmap_update_bits(rt5677->regmap, RT5677_LOUT1,
+					RT5677_LOUT2_L_DF, RT5677_LOUT2_L_DF);
+
+	if (rt5677->pdata.lout3_diff)
+		regmap_update_bits(rt5677->regmap, RT5677_LOUT1,
+					RT5677_LOUT3_L_DF, RT5677_LOUT3_L_DF);
+
 	if (rt5677->pdata.dmic2_clk_pin == RT5677_DMIC_CLK2) {
 		regmap_update_bits(rt5677->regmap, RT5677_GEN_CTRL2,
 					RT5677_GPIO5_FUNC_MASK,
-- 
cgit v1.2.3


From 79cf79abce71eb7dbc40e2f3121048ca5405cb47 Mon Sep 17 00:00:00 2001
From: Michael Braun <michael-dev@fami-braun.de>
Date: Thu, 25 Sep 2014 16:31:08 +0200
Subject: macvlan: add source mode

This patch adds a new mode of operation to macvlan, called "source".
It allows one to set a list of allowed mac address, which is used
to match against source mac address from received frames on underlying
interface.
This enables creating mac based VLAN associations, instead of standard
port or tag based. The feature is useful to deploy 802.1x mac based
behavior, where drivers of underlying interfaces doesn't allows that.

Configuration is done through the netlink interface using e.g.:
 ip link add link eth0 name macvlan0 type macvlan mode source
 ip link add link eth0 name macvlan1 type macvlan mode source
 ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11
 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22
 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33
 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33
 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44

This allows clients with MAC addresses 00:11:11:11:11:11,
00:22:22:22:22:22 to be part of only VLAN associated with macvlan0
interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN
associated with macvlan1 interface. And client with MAC address
00:33:33:33:33:33 to be associated with both VLANs.

Based on work of Stefan Gula <steweg@gmail.com>

v8: last version of Stefan Gula for Kernel 3.2.1
v9: rework onto linux-next 2014-03-12 by Michael Braun
    add MACADDR_SET command, enable to configure mac for source mode
    while creating interface
v10:
  - reduce indention level
  - rename source_list to source_entry
  - use aligned 64bit ether address
  - use hash_64 instead of addr[5]
v11:
  - rebase for 3.14 / linux-next 20.04.2014
v12
  - rebase for linux-next 2014-09-25

Signed-off-by: Michael Braun <michael-dev@fami-braun.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c        | 304 ++++++++++++++++++++++++++++++++++++++++++-
 include/linux/if_macvlan.h   |   1 +
 include/uapi/linux/if_link.h |  12 ++
 3 files changed, 314 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 726edabff26b..e8a453f1b458 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -35,7 +35,8 @@
 #include <net/xfrm.h>
 #include <linux/netpoll.h>
 
-#define MACVLAN_HASH_SIZE	(1 << BITS_PER_BYTE)
+#define MACVLAN_HASH_BITS	8
+#define MACVLAN_HASH_SIZE	(1<<MACVLAN_HASH_BITS)
 #define MACVLAN_BC_QUEUE_LEN	1000
 
 struct macvlan_port {
@@ -47,6 +48,14 @@ struct macvlan_port {
 	struct work_struct	bc_work;
 	bool 			passthru;
 	int			count;
+	struct hlist_head	vlan_source_hash[MACVLAN_HASH_SIZE];
+};
+
+struct macvlan_source_entry {
+	struct hlist_node	hlist;
+	struct macvlan_dev	*vlan;
+	unsigned char		addr[6+2] __aligned(sizeof(u16));
+	struct rcu_head		rcu;
 };
 
 struct macvlan_skb_cb {
@@ -57,6 +66,20 @@ struct macvlan_skb_cb {
 
 static void macvlan_port_destroy(struct net_device *dev);
 
+/* Hash Ethernet address */
+static u32 macvlan_eth_hash(const unsigned char *addr)
+{
+	u64 value = get_unaligned((u64 *)addr);
+
+	/* only want 6 bytes */
+#ifdef __BIG_ENDIAN
+	value >>= 16;
+#else
+	value <<= 16;
+#endif
+	return hash_64(value, MACVLAN_HASH_BITS);
+}
+
 static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev)
 {
 	return rcu_dereference(dev->rx_handler_data);
@@ -73,20 +96,68 @@ static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port,
 					       const unsigned char *addr)
 {
 	struct macvlan_dev *vlan;
+	u32 idx = macvlan_eth_hash(addr);
 
-	hlist_for_each_entry_rcu(vlan, &port->vlan_hash[addr[5]], hlist) {
+	hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist) {
 		if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr))
 			return vlan;
 	}
 	return NULL;
 }
 
+static struct macvlan_source_entry *macvlan_hash_lookup_source(
+	const struct macvlan_dev *vlan,
+	const unsigned char *addr)
+{
+	struct macvlan_source_entry *entry;
+	u32 idx = macvlan_eth_hash(addr);
+	struct hlist_head *h = &vlan->port->vlan_source_hash[idx];
+
+	hlist_for_each_entry_rcu(entry, h, hlist) {
+		if (ether_addr_equal_64bits(entry->addr, addr) &&
+		    entry->vlan == vlan)
+			return entry;
+	}
+	return NULL;
+}
+
+static int macvlan_hash_add_source(struct macvlan_dev *vlan,
+				   const unsigned char *addr)
+{
+	struct macvlan_port *port = vlan->port;
+	struct macvlan_source_entry *entry;
+	struct hlist_head *h;
+
+	entry = macvlan_hash_lookup_source(vlan, addr);
+	if (entry)
+		return 0;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	ether_addr_copy(entry->addr, addr);
+	entry->vlan = vlan;
+	h = &port->vlan_source_hash[macvlan_eth_hash(addr)];
+	hlist_add_head_rcu(&entry->hlist, h);
+	vlan->macaddr_count++;
+
+	return 0;
+}
+
 static void macvlan_hash_add(struct macvlan_dev *vlan)
 {
 	struct macvlan_port *port = vlan->port;
 	const unsigned char *addr = vlan->dev->dev_addr;
+	u32 idx = macvlan_eth_hash(addr);
 
-	hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[addr[5]]);
+	hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[idx]);
+}
+
+static void macvlan_hash_del_source(struct macvlan_source_entry *entry)
+{
+	hlist_del_rcu(&entry->hlist);
+	kfree_rcu(entry, rcu);
 }
 
 static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync)
@@ -267,6 +338,65 @@ err:
 	atomic_long_inc(&skb->dev->rx_dropped);
 }
 
+static void macvlan_flush_sources(struct macvlan_port *port,
+				  struct macvlan_dev *vlan)
+{
+	int i;
+
+	for (i = 0; i < MACVLAN_HASH_SIZE; i++) {
+		struct hlist_node *h, *n;
+
+		hlist_for_each_safe(h, n, &port->vlan_source_hash[i]) {
+			struct macvlan_source_entry *entry;
+
+			entry = hlist_entry(h, struct macvlan_source_entry,
+					    hlist);
+			if (entry->vlan == vlan)
+				macvlan_hash_del_source(entry);
+		}
+	}
+	vlan->macaddr_count = 0;
+}
+
+static void macvlan_forward_source_one(struct sk_buff *skb,
+				       struct macvlan_dev *vlan)
+{
+	struct sk_buff *nskb;
+	struct net_device *dev;
+	int len;
+	int ret;
+
+	dev = vlan->dev;
+	if (unlikely(!(dev->flags & IFF_UP)))
+		return;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return;
+
+	len = nskb->len + ETH_HLEN;
+	nskb->dev = dev;
+	nskb->pkt_type = PACKET_HOST;
+
+	ret = netif_rx(nskb);
+	macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, 0);
+}
+
+static void macvlan_forward_source(struct sk_buff *skb,
+				   struct macvlan_port *port,
+				   const unsigned char *addr)
+{
+	struct macvlan_source_entry *entry;
+	u32 idx = macvlan_eth_hash(addr);
+	struct hlist_head *h = &port->vlan_source_hash[idx];
+
+	hlist_for_each_entry_rcu(entry, h, hlist) {
+		if (ether_addr_equal_64bits(entry->addr, addr))
+			if (entry->vlan->dev->flags & IFF_UP)
+				macvlan_forward_source_one(skb, entry->vlan);
+	}
+}
+
 /* called under rcu_read_lock() from netif_receive_skb */
 static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 {
@@ -285,6 +415,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 		if (!skb)
 			return RX_HANDLER_CONSUMED;
 		eth = eth_hdr(skb);
+		macvlan_forward_source(skb, port, eth->h_source);
 		src = macvlan_hash_lookup(port, eth->h_source);
 		if (src && src->mode != MACVLAN_MODE_VEPA &&
 		    src->mode != MACVLAN_MODE_BRIDGE) {
@@ -301,6 +432,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 		return RX_HANDLER_PASS;
 	}
 
+	macvlan_forward_source(skb, port, eth->h_source);
 	if (port->passthru)
 		vlan = list_first_or_null_rcu(&port->vlans,
 					      struct macvlan_dev, list);
@@ -667,6 +799,7 @@ static void macvlan_uninit(struct net_device *dev)
 
 	free_percpu(vlan->pcpu_stats);
 
+	macvlan_flush_sources(port, vlan);
 	port->count -= 1;
 	if (!port->count)
 		macvlan_port_destroy(port->dev);
@@ -925,6 +1058,8 @@ static int macvlan_port_create(struct net_device *dev)
 	INIT_LIST_HEAD(&port->vlans);
 	for (i = 0; i < MACVLAN_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&port->vlan_hash[i]);
+	for (i = 0; i < MACVLAN_HASH_SIZE; i++)
+		INIT_HLIST_HEAD(&port->vlan_source_hash[i]);
 
 	skb_queue_head_init(&port->bc_queue);
 	INIT_WORK(&port->bc_work, macvlan_process_broadcast);
@@ -966,11 +1101,102 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[])
 		case MACVLAN_MODE_VEPA:
 		case MACVLAN_MODE_BRIDGE:
 		case MACVLAN_MODE_PASSTHRU:
+		case MACVLAN_MODE_SOURCE:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
+		switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) {
+		case MACVLAN_MACADDR_ADD:
+		case MACVLAN_MACADDR_DEL:
+		case MACVLAN_MACADDR_FLUSH:
+		case MACVLAN_MACADDR_SET:
 			break;
 		default:
 			return -EINVAL;
 		}
 	}
+
+	if (data && data[IFLA_MACVLAN_MACADDR]) {
+		if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN)
+			return -EINVAL;
+
+		if (!is_valid_ether_addr(nla_data(data[IFLA_MACVLAN_MACADDR])))
+			return -EADDRNOTAVAIL;
+	}
+
+	if (data && data[IFLA_MACVLAN_MACADDR_COUNT])
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * reconfigure list of remote source mac address
+ * (only for macvlan devices in source mode)
+ * Note regarding alignment: all netlink data is aligned to 4 Byte, which
+ * suffices for both ether_addr_copy and ether_addr_equal_64bits usage.
+ */
+static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode,
+				      struct nlattr *data[])
+{
+	char *addr = NULL;
+	int ret, rem, len;
+	struct nlattr *nla, *head;
+	struct macvlan_source_entry *entry;
+
+	if (data[IFLA_MACVLAN_MACADDR])
+		addr = nla_data(data[IFLA_MACVLAN_MACADDR]);
+
+	if (mode == MACVLAN_MACADDR_ADD) {
+		if (!addr)
+			return -EINVAL;
+
+		return macvlan_hash_add_source(vlan, addr);
+
+	} else if (mode == MACVLAN_MACADDR_DEL) {
+		if (!addr)
+			return -EINVAL;
+
+		entry = macvlan_hash_lookup_source(vlan, addr);
+		if (entry) {
+			macvlan_hash_del_source(entry);
+			vlan->macaddr_count--;
+		}
+	} else if (mode == MACVLAN_MACADDR_FLUSH) {
+		macvlan_flush_sources(vlan->port, vlan);
+	} else if (mode == MACVLAN_MACADDR_SET) {
+		macvlan_flush_sources(vlan->port, vlan);
+
+		if (addr) {
+			ret = macvlan_hash_add_source(vlan, addr);
+			if (ret)
+				return ret;
+		}
+
+		if (!data || !data[IFLA_MACVLAN_MACADDR_DATA])
+			return 0;
+
+		head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]);
+		len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]);
+
+		nla_for_each_attr(nla, head, len, rem) {
+			if (nla_type(nla) != IFLA_MACVLAN_MACADDR ||
+			    nla_len(nla) != ETH_ALEN)
+				continue;
+
+			addr = nla_data(nla);
+			ret = macvlan_hash_add_source(vlan, addr);
+			if (ret)
+				return ret;
+		}
+	} else {
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -981,6 +1207,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 	struct macvlan_port *port;
 	struct net_device *lowerdev;
 	int err;
+	int macmode;
 
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
@@ -1034,6 +1261,15 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 		eth_hw_addr_inherit(dev, lowerdev);
 	}
 
+	if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
+		if (vlan->mode != MACVLAN_MODE_SOURCE)
+			return -EINVAL;
+		macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]);
+		err = macvlan_changelink_sources(vlan, macmode, data);
+		if (err)
+			return err;
+	}
+
 	port->count += 1;
 	err = register_netdevice(dev);
 	if (err < 0)
@@ -1070,6 +1306,8 @@ void macvlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 
+	if (vlan->mode == MACVLAN_MODE_SOURCE)
+		macvlan_flush_sources(vlan->port, vlan);
 	list_del_rcu(&vlan->list);
 	unregister_netdevice_queue(dev, head);
 	netdev_upper_dev_unlink(vlan->lowerdev, dev);
@@ -1082,6 +1320,8 @@ static int macvlan_changelink(struct net_device *dev,
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	enum macvlan_mode mode;
 	bool set_mode = false;
+	enum macvlan_macaddr_mode macmode;
+	int ret;
 
 	/* Validate mode, but don't set yet: setting flags may fail. */
 	if (data && data[IFLA_MACVLAN_MODE]) {
@@ -1091,6 +1331,9 @@ static int macvlan_changelink(struct net_device *dev,
 		if ((mode == MACVLAN_MODE_PASSTHRU) !=
 		    (vlan->mode == MACVLAN_MODE_PASSTHRU))
 			return -EINVAL;
+		if (vlan->mode == MACVLAN_MODE_SOURCE &&
+		    vlan->mode != mode)
+			macvlan_flush_sources(vlan->port, vlan);
 	}
 
 	if (data && data[IFLA_MACVLAN_FLAGS]) {
@@ -1110,26 +1353,77 @@ static int macvlan_changelink(struct net_device *dev,
 	}
 	if (set_mode)
 		vlan->mode = mode;
+	if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
+		if (vlan->mode != MACVLAN_MODE_SOURCE)
+			return -EINVAL;
+		macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]);
+		ret = macvlan_changelink_sources(vlan, macmode, data);
+		if (ret)
+			return ret;
+	}
 	return 0;
 }
 
+static size_t macvlan_get_size_mac(const struct macvlan_dev *vlan)
+{
+	if (vlan->macaddr_count == 0)
+		return 0;
+	return nla_total_size(0) /* IFLA_MACVLAN_MACADDR_DATA */
+		+ vlan->macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN);
+}
+
 static size_t macvlan_get_size(const struct net_device *dev)
 {
+	struct macvlan_dev *vlan = netdev_priv(dev);
+
 	return (0
 		+ nla_total_size(4) /* IFLA_MACVLAN_MODE */
 		+ nla_total_size(2) /* IFLA_MACVLAN_FLAGS */
+		+ nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */
+		+ macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */
 		);
 }
 
+static int macvlan_fill_info_macaddr(struct sk_buff *skb,
+				     const struct macvlan_dev *vlan,
+				     const int i)
+{
+	struct hlist_head *h = &vlan->port->vlan_source_hash[i];
+	struct macvlan_source_entry *entry;
+
+	hlist_for_each_entry_rcu(entry, h, hlist) {
+		if (entry->vlan != vlan)
+			continue;
+		if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr))
+			return 1;
+	}
+	return 0;
+}
+
 static int macvlan_fill_info(struct sk_buff *skb,
 				const struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
+	int i;
+	struct nlattr *nest;
 
 	if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode))
 		goto nla_put_failure;
 	if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags))
 		goto nla_put_failure;
+	if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count))
+		goto nla_put_failure;
+	if (vlan->macaddr_count > 0) {
+		nest = nla_nest_start(skb, IFLA_MACVLAN_MACADDR_DATA);
+		if (nest == NULL)
+			goto nla_put_failure;
+
+		for (i = 0; i < MACVLAN_HASH_SIZE; i++) {
+			if (macvlan_fill_info_macaddr(skb, vlan, i))
+				goto nla_put_failure;
+		}
+		nla_nest_end(skb, nest);
+	}
 	return 0;
 
 nla_put_failure:
@@ -1139,6 +1433,10 @@ nla_put_failure:
 static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = {
 	[IFLA_MACVLAN_MODE]  = { .type = NLA_U32 },
 	[IFLA_MACVLAN_FLAGS] = { .type = NLA_U16 },
+	[IFLA_MACVLAN_MACADDR_MODE] = { .type = NLA_U32 },
+	[IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+	[IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED },
+	[IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 },
 };
 
 int macvlan_link_register(struct rtnl_link_ops *ops)
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 6b2c7cf352a5..6f6929ea8a0c 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -60,6 +60,7 @@ struct macvlan_dev {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll		*netpoll;
 #endif
+	unsigned int		macaddr_count;
 };
 
 static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index c80f95f6ee78..0bdb77e16875 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -303,6 +303,10 @@ enum {
 	IFLA_MACVLAN_UNSPEC,
 	IFLA_MACVLAN_MODE,
 	IFLA_MACVLAN_FLAGS,
+	IFLA_MACVLAN_MACADDR_MODE,
+	IFLA_MACVLAN_MACADDR,
+	IFLA_MACVLAN_MACADDR_DATA,
+	IFLA_MACVLAN_MACADDR_COUNT,
 	__IFLA_MACVLAN_MAX,
 };
 
@@ -313,6 +317,14 @@ enum macvlan_mode {
 	MACVLAN_MODE_VEPA    = 2, /* talk to other ports through ext bridge */
 	MACVLAN_MODE_BRIDGE  = 4, /* talk to bridge ports directly */
 	MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */
+	MACVLAN_MODE_SOURCE  = 16,/* use source MAC address list to assign */
+};
+
+enum macvlan_macaddr_mode {
+	MACVLAN_MACADDR_ADD,
+	MACVLAN_MACADDR_DEL,
+	MACVLAN_MACADDR_FLUSH,
+	MACVLAN_MACADDR_SET,
 };
 
 #define MACVLAN_FLAG_NOPROMISC	1
-- 
cgit v1.2.3


From 4bcfda09936da647b0a3b49d5dcb3c6c6ebb0395 Mon Sep 17 00:00:00 2001
From: "Tan, Raymond" <raymond.tan@intel.com>
Date: Wed, 3 Sep 2014 10:41:38 +0800
Subject: i2c: designware: add support of platform data to set I2C mode

Use the platform data to set the clk_freq when there is no DT configuration
available. The clk_freq in turn will determine the I2C speed mode.

In Quark, there is currently no other configuration mechanism other than
board files.

Signed-off-by: Raymond Tan <raymond.tan@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Hock Leong Kweh <hock.leong.kweh@intel.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/busses/i2c-designware-platdrv.c  |  6 ++++++
 include/linux/platform_data/i2c-designware.h | 21 +++++++++++++++++++++
 2 files changed, 27 insertions(+)
 create mode 100644 include/linux/platform_data/i2c-designware.h

(limited to 'include')

diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 8193e8eea764..4d6a6b94e2fa 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -41,6 +41,7 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
+#include <linux/platform_data/i2c-designware.h>
 #include "i2c-designware-core.h"
 
 static struct i2c_algorithm i2c_dw_algo = {
@@ -122,6 +123,7 @@ static int dw_i2c_probe(struct platform_device *pdev)
 	struct dw_i2c_dev *dev;
 	struct i2c_adapter *adap;
 	struct resource *mem;
+	struct dw_i2c_platform_data *pdata;
 	int irq, r;
 	u32 clk_freq;
 
@@ -182,6 +184,10 @@ static int dw_i2c_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "Only 100kHz and 400kHz supported");
 			return -EINVAL;
 		}
+	} else {
+		pdata = dev_get_platdata(&pdev->dev);
+		if (pdata)
+			clk_freq = pdata->i2c_scl_freq;
 	}
 
 	dev->functionality =
diff --git a/include/linux/platform_data/i2c-designware.h b/include/linux/platform_data/i2c-designware.h
new file mode 100644
index 000000000000..7a61fb27c25b
--- /dev/null
+++ b/include/linux/platform_data/i2c-designware.h
@@ -0,0 +1,21 @@
+/*
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef I2C_DESIGNWARE_H
+#define I2C_DESIGNWARE_H
+
+struct dw_i2c_platform_data {
+	unsigned int i2c_scl_freq;
+};
+
+#endif
-- 
cgit v1.2.3


From f48c767ce8951e30eb716b8ef69142d21aacbd1d Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 29 Sep 2014 13:58:47 +0200
Subject: PM / Domains: Move dev_pm_domain_attach|detach() to pm_domain.h

The commit 46420dd73b80 (PM / Domains: Add APIs to attach/detach a PM
domain for a device) started using errno values in pm.h header file.
It also failed to include the header for these, thus it caused
compiler errors.

Instead of including the errno header to pm.h, let's move the functions
to pm_domain.h, since it's a better match.

Fixes: 46420dd73b80 (PM / Domains: Add APIs to attach/detach a PM domain for a device)
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Wolfram Sang <wsa@the-dreams.de>
Acked-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/amba/bus.c          |  1 +
 drivers/base/platform.c     |  1 +
 drivers/i2c/i2c-core.c      |  1 +
 drivers/mmc/core/sdio_bus.c |  1 +
 drivers/spi/spi.c           |  1 +
 include/linux/pm.h          | 11 -----------
 include/linux/pm_domain.h   | 11 +++++++++++
 7 files changed, 16 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 8f5239377f91..47bbdc1b5be3 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -15,6 +15,7 @@
 #include <linux/io.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/amba/bus.h>
 #include <linux/sizes.h>
 
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 904be3dc0908..b2afc29403f9 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -21,6 +21,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/idr.h>
 #include <linux/acpi.h>
 #include <linux/clk/clk-conf.h>
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 3cd8f11f1b5f..e61a6c5c3372 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -48,6 +48,7 @@
 #include <linux/irqflags.h>
 #include <linux/rwsem.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/acpi.h>
 #include <linux/jump_label.h>
 #include <asm/uaccess.h>
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 1df0fc63c17c..65cf7a7e05ea 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/acpi.h>
 
 #include <linux/mmc/card.h>
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 72a0beb1fafa..3907f1493e7d 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -35,6 +35,7 @@
 #include <linux/spi/spi.h>
 #include <linux/of_gpio.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/export.h>
 #include <linux/sched/rt.h>
 #include <linux/delay.h>
diff --git a/include/linux/pm.h b/include/linux/pm.h
index c4cbf485a5d6..1022ba1eb4de 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -622,17 +622,6 @@ struct dev_pm_domain {
 	void (*detach)(struct device *dev, bool power_off);
 };
 
-#ifdef CONFIG_PM
-extern int dev_pm_domain_attach(struct device *dev, bool power_on);
-extern void dev_pm_domain_detach(struct device *dev, bool power_off);
-#else
-static inline int dev_pm_domain_attach(struct device *dev, bool power_on)
-{
-	return -ENODEV;
-}
-static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
-#endif
-
 /*
  * The PM_EVENT_ messages are also used by drivers implementing the legacy
  * suspend framework, based on the ->suspend() and ->resume() callbacks common
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index ed4f4a79c528..900474317afc 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -301,4 +301,15 @@ static inline int of_genpd_add_provider_onecell(struct device_node *np,
 	return __of_genpd_add_provider(np, __of_genpd_xlate_onecell, data);
 }
 
+#ifdef CONFIG_PM
+extern int dev_pm_domain_attach(struct device *dev, bool power_on);
+extern void dev_pm_domain_detach(struct device *dev, bool power_off);
+#else
+static inline int dev_pm_domain_attach(struct device *dev, bool power_on)
+{
+	return -ENODEV;
+}
+static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
+#endif
+
 #endif /* _LINUX_PM_DOMAIN_H */
-- 
cgit v1.2.3


From baeb7ef34952f523a129e5d1369aa42ecbe7f8c9 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 29 Sep 2014 10:21:03 +0200
Subject: tty: serial: 8250: use 32bit variable for rpm_tx_active

The kbuild test robot wrote me:
|  make.cross ARCH=powerpc
|>> ERROR: ".__xchg_called_with_bad_pointer" [drivers/tty/serial/8250/8250.ko] undefined!

The generic implementation of xchg() on arm and x86 works for variables of
size one bye (char). According to the report powerpc does not support
xchg() for one byte sized variables and looking further it seems also to
be the same case for sparc and tile (or for 10 out of 26 architectures
which provide a custom implementation).
For that reason I increase the size of the variable from one to four
bytes to get it work on powerpc (and the others).

Reported-By: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/serial_8250.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index c267412a3ef4..3df10d5f154b 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -84,7 +84,7 @@ struct uart_8250_port {
 	unsigned char		mcr_mask;	/* mask of user bits */
 	unsigned char		mcr_force;	/* mask of forced bits */
 	unsigned char		cur_iotype;	/* Running I/O type */
-	unsigned char		rpm_tx_active;
+	unsigned int		rpm_tx_active;
 
 	/*
 	 * Some bits in registers are cleared on a read, so they must
-- 
cgit v1.2.3


From 22e0f8b9322cb1a48b1357e8f4ae6f5a9eca8cfa Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 28 Sep 2014 11:52:56 -0700
Subject: net: sched: make bstats per cpu and estimator RCU safe

In order to run qdisc's without locking statistics and estimators
need to be handled correctly.

To resolve bstats make the statistics per cpu. And because this is
only needed for qdiscs that are running without locks which is not
the case for most qdiscs in the near future only create percpu
stats when qdiscs set the TCQ_F_CPUSTATS flag.

Next because estimators use the bstats to calculate packets per
second and bytes per second the estimator code paths are updated
to use the per cpu statistics.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gen_stats.h    | 11 ++++++++++
 include/net/sch_generic.h  | 22 ++++++++++++++++++-
 net/core/gen_estimator.c   | 29 +++++++++++++++----------
 net/core/gen_stats.c       | 53 +++++++++++++++++++++++++++++++++++++++++-----
 net/netfilter/xt_RATEEST.c |  2 +-
 net/sched/act_api.c        |  5 +++--
 net/sched/act_police.c     |  2 +-
 net/sched/sch_api.c        | 29 +++++++++++++++++++------
 net/sched/sch_atm.c        |  2 +-
 net/sched/sch_cbq.c        |  7 +++---
 net/sched/sch_drr.c        |  7 +++---
 net/sched/sch_generic.c    |  3 +++
 net/sched/sch_hfsc.c       | 13 +++++++-----
 net/sched/sch_htb.c        | 12 +++++++----
 net/sched/sch_mq.c         |  2 +-
 net/sched/sch_mqprio.c     |  4 ++--
 net/sched/sch_multiq.c     |  2 +-
 net/sched/sch_prio.c       |  2 +-
 net/sched/sch_qfq.c        |  8 ++++---
 19 files changed, 164 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index ea4271dceff0..ce3c1281f2a0 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -6,6 +6,11 @@
 #include <linux/rtnetlink.h>
 #include <linux/pkt_sched.h>
 
+struct gnet_stats_basic_cpu {
+	struct gnet_stats_basic_packed bstats;
+	struct u64_stats_sync syncp;
+};
+
 struct gnet_dump {
 	spinlock_t *      lock;
 	struct sk_buff *  skb;
@@ -27,7 +32,11 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
 				 spinlock_t *lock, struct gnet_dump *d);
 
 int gnet_stats_copy_basic(struct gnet_dump *d,
+			  struct gnet_stats_basic_cpu __percpu *cpu,
 			  struct gnet_stats_basic_packed *b);
+void __gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+			     struct gnet_stats_basic_cpu __percpu *cpu,
+			     struct gnet_stats_basic_packed *b);
 int gnet_stats_copy_rate_est(struct gnet_dump *d,
 			     const struct gnet_stats_basic_packed *b,
 			     struct gnet_stats_rate_est64 *r);
@@ -37,11 +46,13 @@ int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
 int gnet_stats_finish_copy(struct gnet_dump *d);
 
 int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
+		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct gnet_stats_rate_est64 *rate_est,
 		      spinlock_t *stats_lock, struct nlattr *opt);
 void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
 			struct gnet_stats_rate_est64 *rate_est);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
+			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct gnet_stats_rate_est64 *rate_est,
 			  spinlock_t *stats_lock, struct nlattr *opt);
 bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e65b8e0752af..4b9351120fd8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -6,6 +6,7 @@
 #include <linux/rcupdate.h>
 #include <linux/pkt_sched.h>
 #include <linux/pkt_cls.h>
+#include <linux/percpu.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 
@@ -58,6 +59,7 @@ struct Qdisc {
 				      * multiqueue device.
 				      */
 #define TCQ_F_WARN_NONWC	(1 << 16)
+#define TCQ_F_CPUSTATS		0x20 /* run using percpu statistics */
 	u32			limit;
 	const struct Qdisc_ops	*ops;
 	struct qdisc_size_table	__rcu *stab;
@@ -83,7 +85,10 @@ struct Qdisc {
 	 */
 	unsigned long		state;
 	struct sk_buff_head	q;
-	struct gnet_stats_basic_packed bstats;
+	union {
+		struct gnet_stats_basic_packed bstats;
+		struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	} __packed;
 	unsigned int		__state;
 	struct gnet_stats_queue	qstats;
 	struct rcu_head		rcu_head;
@@ -487,6 +492,10 @@ static inline int qdisc_enqueue_root(struct sk_buff *skb, struct Qdisc *sch)
 	return qdisc_enqueue(skb, sch) & NET_XMIT_MASK;
 }
 
+static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
+{
+	return q->flags & TCQ_F_CPUSTATS;
+}
 
 static inline void bstats_update(struct gnet_stats_basic_packed *bstats,
 				 const struct sk_buff *skb)
@@ -495,6 +504,17 @@ static inline void bstats_update(struct gnet_stats_basic_packed *bstats,
 	bstats->packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
 }
 
+static inline void qdisc_bstats_update_cpu(struct Qdisc *sch,
+					   const struct sk_buff *skb)
+{
+	struct gnet_stats_basic_cpu *bstats =
+				this_cpu_ptr(sch->cpu_bstats);
+
+	u64_stats_update_begin(&bstats->syncp);
+	bstats_update(&bstats->bstats, skb);
+	u64_stats_update_end(&bstats->syncp);
+}
+
 static inline void qdisc_bstats_update(struct Qdisc *sch,
 				       const struct sk_buff *skb)
 {
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 9d33dfffca19..9dfb88a933e7 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -91,6 +91,8 @@ struct gen_estimator
 	u32			avpps;
 	struct rcu_head		e_rcu;
 	struct rb_node		node;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct rcu_head		head;
 };
 
 struct gen_estimator_head
@@ -115,9 +117,8 @@ static void est_timer(unsigned long arg)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(e, &elist[idx].list, list) {
-		u64 nbytes;
+		struct gnet_stats_basic_packed b = {0};
 		u64 brate;
-		u32 npackets;
 		u32 rate;
 
 		spin_lock(e->stats_lock);
@@ -125,15 +126,15 @@ static void est_timer(unsigned long arg)
 		if (e->bstats == NULL)
 			goto skip;
 
-		nbytes = e->bstats->bytes;
-		npackets = e->bstats->packets;
-		brate = (nbytes - e->last_bytes)<<(7 - idx);
-		e->last_bytes = nbytes;
+		__gnet_stats_copy_basic(&b, e->cpu_bstats, e->bstats);
+
+		brate = (b.bytes - e->last_bytes)<<(7 - idx);
+		e->last_bytes = b.bytes;
 		e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log);
 		e->rate_est->bps = (e->avbps+0xF)>>5;
 
-		rate = (npackets - e->last_packets)<<(12 - idx);
-		e->last_packets = npackets;
+		rate = (b.packets - e->last_packets)<<(12 - idx);
+		e->last_packets = b.packets;
 		e->avpps += (rate >> e->ewma_log) - (e->avpps >> e->ewma_log);
 		e->rate_est->pps = (e->avpps+0x1FF)>>10;
 skip:
@@ -203,12 +204,14 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats
  *
  */
 int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
+		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct gnet_stats_rate_est64 *rate_est,
 		      spinlock_t *stats_lock,
 		      struct nlattr *opt)
 {
 	struct gen_estimator *est;
 	struct gnet_estimator *parm = nla_data(opt);
+	struct gnet_stats_basic_packed b = {0};
 	int idx;
 
 	if (nla_len(opt) < sizeof(*parm))
@@ -221,15 +224,18 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 	if (est == NULL)
 		return -ENOBUFS;
 
+	__gnet_stats_copy_basic(&b, cpu_bstats, bstats);
+
 	idx = parm->interval + 2;
 	est->bstats = bstats;
 	est->rate_est = rate_est;
 	est->stats_lock = stats_lock;
 	est->ewma_log = parm->ewma_log;
-	est->last_bytes = bstats->bytes;
+	est->last_bytes = b.bytes;
 	est->avbps = rate_est->bps<<5;
-	est->last_packets = bstats->packets;
+	est->last_packets = b.packets;
 	est->avpps = rate_est->pps<<10;
+	est->cpu_bstats = cpu_bstats;
 
 	spin_lock_bh(&est_tree_lock);
 	if (!elist[idx].timer.function) {
@@ -290,11 +296,12 @@ EXPORT_SYMBOL(gen_kill_estimator);
  * Returns 0 on success or a negative error code.
  */
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
+			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct gnet_stats_rate_est64 *rate_est,
 			  spinlock_t *stats_lock, struct nlattr *opt)
 {
 	gen_kill_estimator(bstats, rate_est);
-	return gen_new_estimator(bstats, rate_est, stats_lock, opt);
+	return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, opt);
 }
 EXPORT_SYMBOL(gen_replace_estimator);
 
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 2ddbce4cce14..5ff8e80fe0bb 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -97,6 +97,43 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock,
 }
 EXPORT_SYMBOL(gnet_stats_start_copy);
 
+static void
+__gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats,
+			    struct gnet_stats_basic_cpu __percpu *cpu)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct gnet_stats_basic_cpu *bcpu = per_cpu_ptr(cpu, i);
+		unsigned int start;
+		__u64 bytes;
+		__u32 packets;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&bcpu->syncp);
+			bytes = bcpu->bstats.bytes;
+			packets = bcpu->bstats.packets;
+		} while (u64_stats_fetch_retry_irq(&bcpu->syncp, start));
+
+		bstats->bytes += bcpu->bstats.bytes;
+		bstats->packets += bcpu->bstats.packets;
+	}
+}
+
+void
+__gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+			struct gnet_stats_basic_cpu __percpu *cpu,
+			struct gnet_stats_basic_packed *b)
+{
+	if (cpu) {
+		__gnet_stats_copy_basic_cpu(bstats, cpu);
+	} else {
+		bstats->bytes = b->bytes;
+		bstats->packets = b->packets;
+	}
+}
+EXPORT_SYMBOL(__gnet_stats_copy_basic);
+
 /**
  * gnet_stats_copy_basic - copy basic statistics into statistic TLV
  * @d: dumping handle
@@ -109,19 +146,25 @@ EXPORT_SYMBOL(gnet_stats_start_copy);
  * if the room in the socket buffer was not sufficient.
  */
 int
-gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b)
+gnet_stats_copy_basic(struct gnet_dump *d,
+		      struct gnet_stats_basic_cpu __percpu *cpu,
+		      struct gnet_stats_basic_packed *b)
 {
+	struct gnet_stats_basic_packed bstats = {0};
+
+	__gnet_stats_copy_basic(&bstats, cpu, b);
+
 	if (d->compat_tc_stats) {
-		d->tc_stats.bytes = b->bytes;
-		d->tc_stats.packets = b->packets;
+		d->tc_stats.bytes = bstats.bytes;
+		d->tc_stats.packets = bstats.packets;
 	}
 
 	if (d->tail) {
 		struct gnet_stats_basic sb;
 
 		memset(&sb, 0, sizeof(sb));
-		sb.bytes = b->bytes;
-		sb.packets = b->packets;
+		sb.bytes = bstats.bytes;
+		sb.packets = bstats.packets;
 		return gnet_stats_copy(d, TCA_STATS_BASIC, &sb, sizeof(sb));
 	}
 	return 0;
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 370adf622cef..604df6fae6fc 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -136,7 +136,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 	cfg.est.interval	= info->interval;
 	cfg.est.ewma_log	= info->ewma_log;
 
-	ret = gen_new_estimator(&est->bstats, &est->rstats,
+	ret = gen_new_estimator(&est->bstats, NULL, &est->rstats,
 				&est->lock, &cfg.opt);
 	if (ret < 0)
 		goto err2;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 648778aef1a2..eca4cf9ece2f 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -252,7 +252,8 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
 	p->tcfc_tm.install = jiffies;
 	p->tcfc_tm.lastuse = jiffies;
 	if (est) {
-		int err = gen_new_estimator(&p->tcfc_bstats, &p->tcfc_rate_est,
+		int err = gen_new_estimator(&p->tcfc_bstats, NULL,
+					    &p->tcfc_rate_est,
 					    &p->tcfc_lock, est);
 		if (err) {
 			kfree(p);
@@ -619,7 +620,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 	if (err < 0)
 		goto errout;
 
-	if (gnet_stats_copy_basic(&d, &p->tcfc_bstats) < 0 ||
+	if (gnet_stats_copy_basic(&d, NULL, &p->tcfc_bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
 				     &p->tcfc_rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, &p->tcfc_qstats) < 0)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index f32bcb094915..69791ca77a05 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -178,7 +178,7 @@ override:
 
 	spin_lock_bh(&police->tcf_lock);
 	if (est) {
-		err = gen_replace_estimator(&police->tcf_bstats,
+		err = gen_replace_estimator(&police->tcf_bstats, NULL,
 					    &police->tcf_rate_est,
 					    &police->tcf_lock, est);
 		if (err)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 15e7beee266c..a95e3b48fa51 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -942,6 +942,13 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 	sch->handle = handle;
 
 	if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) {
+		if (qdisc_is_percpu_stats(sch)) {
+			sch->cpu_bstats =
+				alloc_percpu(struct gnet_stats_basic_cpu);
+			if (!sch->cpu_bstats)
+				goto err_out4;
+		}
+
 		if (tca[TCA_STAB]) {
 			stab = qdisc_get_stab(tca[TCA_STAB]);
 			if (IS_ERR(stab)) {
@@ -964,8 +971,11 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 			else
 				root_lock = qdisc_lock(sch);
 
-			err = gen_new_estimator(&sch->bstats, &sch->rate_est,
-						root_lock, tca[TCA_RATE]);
+			err = gen_new_estimator(&sch->bstats,
+						sch->cpu_bstats,
+						&sch->rate_est,
+						root_lock,
+						tca[TCA_RATE]);
 			if (err)
 				goto err_out4;
 		}
@@ -984,6 +994,7 @@ err_out:
 	return NULL;
 
 err_out4:
+	free_percpu(sch->cpu_bstats);
 	/*
 	 * Any broken qdiscs that would require a ops->reset() here?
 	 * The qdisc was never in action so it shouldn't be necessary.
@@ -1022,9 +1033,11 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
 		   because change can't be undone. */
 		if (sch->flags & TCQ_F_MQROOT)
 			goto out;
-		gen_replace_estimator(&sch->bstats, &sch->rate_est,
-					    qdisc_root_sleeping_lock(sch),
-					    tca[TCA_RATE]);
+		gen_replace_estimator(&sch->bstats,
+				      sch->cpu_bstats,
+				      &sch->rate_est,
+				      qdisc_root_sleeping_lock(sch),
+				      tca[TCA_RATE]);
 	}
 out:
 	return 0;
@@ -1299,6 +1312,7 @@ graft:
 static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 			 u32 portid, u32 seq, u16 flags, int event)
 {
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL;
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
 	unsigned char *b = skb_tail_pointer(skb);
@@ -1334,7 +1348,10 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 	if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0)
 		goto nla_put_failure;
 
-	if (gnet_stats_copy_basic(&d, &q->bstats) < 0 ||
+	if (qdisc_is_percpu_stats(q))
+		cpu_bstats = q->cpu_bstats;
+
+	if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, &q->qstats) < 0)
 		goto nla_put_failure;
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index c398f9c3dbdd..01017663e5d8 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -639,7 +639,7 @@ atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	flow->qstats.qlen = flow->q->q.qlen;
 
-	if (gnet_stats_copy_basic(d, &flow->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &flow->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, &flow->qstats) < 0)
 		return -1;
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index d2cd981ba60d..22a3a029a911 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1601,7 +1601,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	if (cl->undertime != PSCHED_PASTPERFECT)
 		cl->xstats.undertime = cl->undertime - q->now;
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
 		return -1;
@@ -1759,7 +1759,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 		}
 
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
 						    qdisc_root_sleeping_lock(sch),
 						    tca[TCA_RATE]);
 			if (err) {
@@ -1852,7 +1853,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 		goto failure;
 
 	if (tca[TCA_RATE]) {
-		err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
 					qdisc_root_sleeping_lock(sch),
 					tca[TCA_RATE]);
 		if (err) {
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index d8b5ccfd248a..7a6243c5d270 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -88,7 +88,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 
 	if (cl != NULL) {
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
 						    qdisc_root_sleeping_lock(sch),
 						    tca[TCA_RATE]);
 			if (err)
@@ -116,7 +117,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		cl->qdisc = &noop_qdisc;
 
 	if (tca[TCA_RATE]) {
-		err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+		err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
 					    qdisc_root_sleeping_lock(sch),
 					    tca[TCA_RATE]);
 		if (err) {
@@ -282,7 +283,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 		cl->qdisc->qstats.qlen = cl->qdisc->q.qlen;
 	}
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
 		return -1;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 11b28f651ad1..7c8e5d73d433 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -632,6 +632,9 @@ static void qdisc_rcu_free(struct rcu_head *head)
 {
 	struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
 
+	if (qdisc_is_percpu_stats(qdisc))
+		free_percpu(qdisc->cpu_bstats);
+
 	kfree((char *) qdisc - qdisc->padded);
 }
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 04b0de4c68b5..209b966b2eed 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1014,9 +1014,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		cur_time = psched_get_time();
 
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
-					      qdisc_root_sleeping_lock(sch),
-					      tca[TCA_RATE]);
+			spinlock_t *lock = qdisc_root_sleeping_lock(sch);
+
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
+						    lock,
+						    tca[TCA_RATE]);
 			if (err)
 				return err;
 		}
@@ -1063,7 +1066,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		return -ENOBUFS;
 
 	if (tca[TCA_RATE]) {
-		err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
 					qdisc_root_sleeping_lock(sch),
 					tca[TCA_RATE]);
 		if (err) {
@@ -1374,7 +1377,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	xstats.work    = cl->cl_total;
 	xstats.rtwork  = cl->cl_cumul;
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
 		return -1;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 063e953d9848..0256dee69bd6 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1144,7 +1144,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
 	cl->xstats.tokens = PSCHED_NS2TICKS(cl->tokens);
 	cl->xstats.ctokens = PSCHED_NS2TICKS(cl->ctokens);
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
 		return -1;
@@ -1402,7 +1402,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			goto failure;
 
 		if (htb_rate_est || tca[TCA_RATE]) {
-			err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+			err = gen_new_estimator(&cl->bstats, NULL,
+						&cl->rate_est,
 						qdisc_root_sleeping_lock(sch),
 						tca[TCA_RATE] ? : &est.nla);
 			if (err) {
@@ -1464,8 +1465,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			parent->children++;
 	} else {
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
-						    qdisc_root_sleeping_lock(sch),
+			spinlock_t *lock = qdisc_root_sleeping_lock(sch);
+
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
+						    lock,
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index a8b2864a696b..d3a27fb607af 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -201,7 +201,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	sch = dev_queue->qdisc_sleeping;
 	sch->qstats.qlen = sch->q.qlen;
-	if (gnet_stats_copy_basic(d, &sch->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, &sch->qstats) < 0)
 		return -1;
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 37e7d25d21f1..8917372fddc6 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -355,7 +355,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		}
 		/* Reclaim root sleeping lock before completing stats */
 		spin_lock_bh(d->lock);
-		if (gnet_stats_copy_basic(d, &bstats) < 0 ||
+		if (gnet_stats_copy_basic(d, NULL, &bstats) < 0 ||
 		    gnet_stats_copy_queue(d, &qstats) < 0)
 			return -1;
 	} else {
@@ -363,7 +363,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 		sch = dev_queue->qdisc_sleeping;
 		sch->qstats.qlen = sch->q.qlen;
-		if (gnet_stats_copy_basic(d, &sch->bstats) < 0 ||
+		if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
 		    gnet_stats_copy_queue(d, &sch->qstats) < 0)
 			return -1;
 	}
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index c0466c1840f3..4adbf7fefc09 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -361,7 +361,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	cl_q->qstats.qlen = cl_q->q.qlen;
-	if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
 		return -1;
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 03ef99e52a5c..68a8f25e30c3 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -325,7 +325,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	cl_q->qstats.qlen = cl_q->q.qlen;
-	if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
 		return -1;
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 602ea01a4ddd..d59f8574540a 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -459,7 +459,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 
 	if (cl != NULL) { /* modify existing class */
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
 						    qdisc_root_sleeping_lock(sch),
 						    tca[TCA_RATE]);
 			if (err)
@@ -484,7 +485,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		cl->qdisc = &noop_qdisc;
 
 	if (tca[TCA_RATE]) {
-		err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+		err = gen_new_estimator(&cl->bstats, NULL,
+					&cl->rate_est,
 					qdisc_root_sleeping_lock(sch),
 					tca[TCA_RATE]);
 		if (err)
@@ -667,7 +669,7 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	xstats.weight = cl->agg->class_weight;
 	xstats.lmax = cl->agg->lmax;
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
 		return -1;
-- 
cgit v1.2.3


From 25331d6ce42bcf4b34b6705fce4da15c3fabe62f Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 28 Sep 2014 11:53:29 -0700
Subject: net: sched: implement qstat helper routines

This adds helpers to manipulate qstats logic and replaces locations
that touch the counters directly. This simplifies future patches
to push qstats onto per cpu counters.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 39 +++++++++++++++++++++++++++++++++------
 net/sched/sch_api.c       |  2 +-
 net/sched/sch_atm.c       |  2 +-
 net/sched/sch_cbq.c       | 10 +++++-----
 net/sched/sch_choke.c     | 14 +++++++-------
 net/sched/sch_codel.c     |  2 +-
 net/sched/sch_drr.c       |  4 ++--
 net/sched/sch_dsmark.c    |  2 +-
 net/sched/sch_fifo.c      |  2 +-
 net/sched/sch_fq.c        |  4 ++--
 net/sched/sch_fq_codel.c  |  8 ++++----
 net/sched/sch_gred.c      |  4 ++--
 net/sched/sch_hfsc.c      |  8 ++++----
 net/sched/sch_hhf.c       |  8 ++++----
 net/sched/sch_htb.c       |  6 +++---
 net/sched/sch_ingress.c   |  2 +-
 net/sched/sch_multiq.c    |  4 ++--
 net/sched/sch_netem.c     | 15 +++++++--------
 net/sched/sch_pie.c       |  2 +-
 net/sched/sch_prio.c      |  4 ++--
 net/sched/sch_qfq.c       |  4 ++--
 net/sched/sch_red.c       |  8 ++++----
 net/sched/sch_sfb.c       | 10 +++++-----
 net/sched/sch_sfq.c       | 17 +++++++++--------
 net/sched/sch_tbf.c       |  8 ++++----
 25 files changed, 108 insertions(+), 81 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 4b9351120fd8..23a0f0fc83d8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -521,11 +521,38 @@ static inline void qdisc_bstats_update(struct Qdisc *sch,
 	bstats_update(&sch->bstats, skb);
 }
 
+static inline void qdisc_qstats_backlog_dec(struct Qdisc *sch,
+					    const struct sk_buff *skb)
+{
+	sch->qstats.backlog -= qdisc_pkt_len(skb);
+}
+
+static inline void qdisc_qstats_backlog_inc(struct Qdisc *sch,
+					    const struct sk_buff *skb)
+{
+	sch->qstats.backlog += qdisc_pkt_len(skb);
+}
+
+static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count)
+{
+	sch->qstats.drops += count;
+}
+
+static inline void qdisc_qstats_drop(struct Qdisc *sch)
+{
+	sch->qstats.drops++;
+}
+
+static inline void qdisc_qstats_overlimit(struct Qdisc *sch)
+{
+	sch->qstats.overlimits++;
+}
+
 static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch,
 				       struct sk_buff_head *list)
 {
 	__skb_queue_tail(list, skb);
-	sch->qstats.backlog += qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_inc(sch, skb);
 
 	return NET_XMIT_SUCCESS;
 }
@@ -541,7 +568,7 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct Qdisc *sch,
 	struct sk_buff *skb = __skb_dequeue(list);
 
 	if (likely(skb != NULL)) {
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_bstats_update(sch, skb);
 	}
 
@@ -560,7 +587,7 @@ static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch,
 
 	if (likely(skb != NULL)) {
 		unsigned int len = qdisc_pkt_len(skb);
-		sch->qstats.backlog -= len;
+		qdisc_qstats_backlog_dec(sch, skb);
 		kfree_skb(skb);
 		return len;
 	}
@@ -579,7 +606,7 @@ static inline struct sk_buff *__qdisc_dequeue_tail(struct Qdisc *sch,
 	struct sk_buff *skb = __skb_dequeue_tail(list);
 
 	if (likely(skb != NULL))
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 
 	return skb;
 }
@@ -661,14 +688,14 @@ static inline unsigned int qdisc_queue_drop(struct Qdisc *sch)
 static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
 {
 	kfree_skb(skb);
-	sch->qstats.drops++;
+	qdisc_qstats_drop(sch);
 
 	return NET_XMIT_DROP;
 }
 
 static inline int qdisc_reshape_fail(struct sk_buff *skb, struct Qdisc *sch)
 {
-	sch->qstats.drops++;
+	qdisc_qstats_drop(sch);
 
 #ifdef CONFIG_NET_CLS_ACT
 	if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch))
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index a95e3b48fa51..2862bc61a358 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -763,7 +763,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 			cops->put(sch, cl);
 		}
 		sch->q.qlen -= n;
-		sch->qstats.drops += drops;
+		__qdisc_qstats_drop(sch, drops);
 	}
 }
 EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 01017663e5d8..040212cab988 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -417,7 +417,7 @@ done:
 	if (ret != NET_XMIT_SUCCESS) {
 drop: __maybe_unused
 		if (net_xmit_drop_count(ret)) {
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 			if (flow)
 				flow->qstats.drops++;
 		}
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 22a3a029a911..60432c3d3cd4 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -377,7 +377,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 #endif
 	if (cl == NULL) {
 		if (ret & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return ret;
 	}
@@ -395,7 +395,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 
 	if (net_xmit_drop_count(ret)) {
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 		cbq_mark_toplevel(q, cl);
 		cl->qstats.drops++;
 	}
@@ -650,11 +650,11 @@ static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child)
 			return 0;
 		}
 		if (net_xmit_drop_count(ret))
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		return 0;
 	}
 
-	sch->qstats.drops++;
+	qdisc_qstats_drop(sch);
 	return -1;
 }
 #endif
@@ -995,7 +995,7 @@ cbq_dequeue(struct Qdisc *sch)
 	 */
 
 	if (sch->q.qlen) {
-		sch->qstats.overlimits++;
+		qdisc_qstats_overlimit(sch);
 		if (q->wd_expires)
 			qdisc_watchdog_schedule(&q->watchdog,
 						now + q->wd_expires);
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 8abc2625c3a1..c009eb9045ce 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -127,7 +127,7 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 	if (idx == q->tail)
 		choke_zap_tail_holes(q);
 
-	sch->qstats.backlog -= qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_drop(skb, sch);
 	qdisc_tree_decrease_qlen(sch, 1);
 	--sch->q.qlen;
@@ -302,7 +302,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		if (q->vars.qavg > p->qth_max) {
 			q->vars.qcount = -1;
 
-			sch->qstats.overlimits++;
+			qdisc_qstats_overlimit(sch);
 			if (use_harddrop(q) || !use_ecn(q) ||
 			    !INET_ECN_set_ce(skb)) {
 				q->stats.forced_drop++;
@@ -315,7 +315,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 				q->vars.qcount = 0;
 				q->vars.qR = red_random(p);
 
-				sch->qstats.overlimits++;
+				qdisc_qstats_overlimit(sch);
 				if (!use_ecn(q) || !INET_ECN_set_ce(skb)) {
 					q->stats.prob_drop++;
 					goto congestion_drop;
@@ -332,7 +332,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		q->tab[q->tail] = skb;
 		q->tail = (q->tail + 1) & q->tab_mask;
 		++sch->q.qlen;
-		sch->qstats.backlog += qdisc_pkt_len(skb);
+		qdisc_qstats_backlog_inc(sch, skb);
 		return NET_XMIT_SUCCESS;
 	}
 
@@ -345,7 +345,7 @@ congestion_drop:
 
 other_drop:
 	if (ret & __NET_XMIT_BYPASS)
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 	kfree_skb(skb);
 	return ret;
 }
@@ -365,7 +365,7 @@ static struct sk_buff *choke_dequeue(struct Qdisc *sch)
 	q->tab[q->head] = NULL;
 	choke_zap_head_holes(q);
 	--sch->q.qlen;
-	sch->qstats.backlog -= qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	qdisc_bstats_update(sch, skb);
 
 	return skb;
@@ -460,7 +460,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 					ntab[tail++] = skb;
 					continue;
 				}
-				sch->qstats.backlog -= qdisc_pkt_len(skb);
+				qdisc_qstats_backlog_dec(sch, skb);
 				--sch->q.qlen;
 				qdisc_drop(skb, sch);
 			}
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 2f9ab17db85a..de28f8e968e8 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -149,7 +149,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
 	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 7a6243c5d270..907b12fd6825 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -360,7 +360,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	cl = drr_classify(skb, sch, &err);
 	if (cl == NULL) {
 		if (err & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return err;
 	}
@@ -369,7 +369,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		}
 		return err;
 	}
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 485e456c8139..227114f27f94 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -258,7 +258,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	err = qdisc_enqueue(skb, p->q);
 	if (err != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(err))
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		return err;
 	}
 
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index e15a9eb29087..2e2398cfc694 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -42,7 +42,7 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	/* queue full, remove one skb to fulfill the limit */
 	__qdisc_queue_drop_head(sch, &sch->q);
-	sch->qstats.drops++;
+	qdisc_qstats_drop(sch);
 	qdisc_enqueue_tail(skb, sch);
 
 	return NET_XMIT_CN;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index e12f997e1b4c..c9b9fcb53206 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -290,7 +290,7 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow)
 		flow->head = skb->next;
 		skb->next = NULL;
 		flow->qlen--;
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 	}
 	return skb;
@@ -371,7 +371,7 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	f->qlen++;
 	if (skb_is_retransmit(skb))
 		q->stat_tcp_retrans++;
-	sch->qstats.backlog += qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_inc(sch, skb);
 	if (fq_flow_is_detached(f)) {
 		fq_flow_add_tail(&q->new_flows, f);
 		if (time_after(jiffies, f->age + q->flow_refill_delay))
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 105cf5557630..9270e1b2f25d 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -164,8 +164,8 @@ static unsigned int fq_codel_drop(struct Qdisc *sch)
 	q->backlogs[idx] -= len;
 	kfree_skb(skb);
 	sch->q.qlen--;
-	sch->qstats.drops++;
-	sch->qstats.backlog -= len;
+	qdisc_qstats_drop(sch);
+	qdisc_qstats_backlog_dec(sch, skb);
 	flow->dropped++;
 	return idx;
 }
@@ -180,7 +180,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	idx = fq_codel_classify(skb, sch, &ret);
 	if (idx == 0) {
 		if (ret & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return ret;
 	}
@@ -190,7 +190,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	flow = &q->flows[idx];
 	flow_queue_add(flow, skb);
 	q->backlogs[idx] += qdisc_pkt_len(skb);
-	sch->qstats.backlog += qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_inc(sch, skb);
 
 	if (list_empty(&flow->flowchain)) {
 		list_add_tail(&flow->flowchain, &q->new_flows);
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 12cbc09157fc..a4ca4517cdc8 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -209,7 +209,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		break;
 
 	case RED_PROB_MARK:
-		sch->qstats.overlimits++;
+		qdisc_qstats_overlimit(sch);
 		if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) {
 			q->stats.prob_drop++;
 			goto congestion_drop;
@@ -219,7 +219,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		break;
 
 	case RED_HARD_MARK:
-		sch->qstats.overlimits++;
+		qdisc_qstats_overlimit(sch);
 		if (gred_use_harddrop(t) || !gred_use_ecn(t) ||
 		    !INET_ECN_set_ce(skb)) {
 			q->stats.forced_drop++;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 209b966b2eed..ad278251d811 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1591,7 +1591,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	cl = hfsc_classify(skb, sch, &err);
 	if (cl == NULL) {
 		if (err & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return err;
 	}
@@ -1600,7 +1600,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		}
 		return err;
 	}
@@ -1643,7 +1643,7 @@ hfsc_dequeue(struct Qdisc *sch)
 		 */
 		cl = vttree_get_minvt(&q->root, cur_time);
 		if (cl == NULL) {
-			sch->qstats.overlimits++;
+			qdisc_qstats_overlimit(sch);
 			hfsc_schedule_watchdog(sch);
 			return NULL;
 		}
@@ -1698,7 +1698,7 @@ hfsc_drop(struct Qdisc *sch)
 				list_move_tail(&cl->dlist, &q->droplist);
 			}
 			cl->qstats.drops++;
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 			sch->q.qlen--;
 			return len;
 		}
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index d85b6812a7d4..15d3aabfe250 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -376,8 +376,8 @@ static unsigned int hhf_drop(struct Qdisc *sch)
 		struct sk_buff *skb = dequeue_head(bucket);
 
 		sch->q.qlen--;
-		sch->qstats.drops++;
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_qstats_drop(sch);
+		qdisc_qstats_backlog_dec(sch, skb);
 		kfree_skb(skb);
 	}
 
@@ -395,7 +395,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	bucket = &q->buckets[idx];
 	bucket_add(bucket, skb);
-	sch->qstats.backlog += qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_inc(sch, skb);
 
 	if (list_empty(&bucket->bucketchain)) {
 		unsigned int weight;
@@ -457,7 +457,7 @@ begin:
 	if (bucket->head) {
 		skb = dequeue_head(bucket);
 		sch->q.qlen--;
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 	}
 
 	if (!skb) {
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 0256dee69bd6..c40ab7a98c50 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -586,13 +586,13 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 #ifdef CONFIG_NET_CLS_ACT
 	} else if (!cl) {
 		if (ret & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return ret;
 #endif
 	} else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q)) != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(ret)) {
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 			cl->qstats.drops++;
 		}
 		return ret;
@@ -925,7 +925,7 @@ ok:
 				goto ok;
 		}
 	}
-	sch->qstats.overlimits++;
+	qdisc_qstats_overlimit(sch);
 	if (likely(next_event > q->now)) {
 		if (!test_bit(__QDISC_STATE_DEACTIVATED,
 			      &qdisc_root_sleeping(q->watchdog.qdisc)->state)) {
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index b351125f3849..eb5b8445fef9 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -69,7 +69,7 @@ static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	switch (result) {
 	case TC_ACT_SHOT:
 		result = TC_ACT_SHOT;
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 		break;
 	case TC_ACT_STOLEN:
 	case TC_ACT_QUEUED:
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 4adbf7fefc09..7f4e1d8504b0 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -75,7 +75,7 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (qdisc == NULL) {
 
 		if (ret & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return ret;
 	}
@@ -87,7 +87,7 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_SUCCESS;
 	}
 	if (net_xmit_drop_count(ret))
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 	return ret;
 }
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 111d70fddaea..b34331967e02 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -429,12 +429,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	/* Drop packet? */
 	if (loss_event(q)) {
 		if (q->ecn && INET_ECN_set_ce(skb))
-			sch->qstats.drops++; /* mark packet */
+			qdisc_qstats_drop(sch); /* mark packet */
 		else
 			--count;
 	}
 	if (count == 0) {
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	}
@@ -478,7 +478,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (unlikely(skb_queue_len(&sch->q) >= sch->limit))
 		return qdisc_reshape_fail(skb, sch);
 
-	sch->qstats.backlog += qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_inc(sch, skb);
 
 	cb = netem_skb_cb(skb);
 	if (q->gap == 0 ||		/* not doing reordering */
@@ -549,15 +549,14 @@ static unsigned int netem_drop(struct Qdisc *sch)
 			sch->q.qlen--;
 			skb->next = NULL;
 			skb->prev = NULL;
-			len = qdisc_pkt_len(skb);
-			sch->qstats.backlog -= len;
+			qdisc_qstats_backlog_dec(sch, skb);
 			kfree_skb(skb);
 		}
 	}
 	if (!len && q->qdisc && q->qdisc->ops->drop)
 	    len = q->qdisc->ops->drop(q->qdisc);
 	if (len)
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 
 	return len;
 }
@@ -575,7 +574,7 @@ tfifo_dequeue:
 	skb = __skb_dequeue(&sch->q);
 	if (skb) {
 deliver:
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_unthrottled(sch);
 		qdisc_bstats_update(sch, skb);
 		return skb;
@@ -610,7 +609,7 @@ deliver:
 
 				if (unlikely(err != NET_XMIT_SUCCESS)) {
 					if (net_xmit_drop_count(err)) {
-						sch->qstats.drops++;
+						qdisc_qstats_drop(sch);
 						qdisc_tree_decrease_qlen(sch, 1);
 					}
 				}
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index fefeeb73f15f..33d7a98a7a97 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -232,7 +232,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
-		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
 	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 68a8f25e30c3..b411e78a02fc 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -77,7 +77,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (qdisc == NULL) {
 
 		if (ret & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return ret;
 	}
@@ -89,7 +89,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_SUCCESS;
 	}
 	if (net_xmit_drop_count(ret))
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 	return ret;
 }
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index d59f8574540a..3fb26555c79b 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1229,7 +1229,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	cl = qfq_classify(skb, sch, &err);
 	if (cl == NULL) {
 		if (err & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return err;
 	}
@@ -1249,7 +1249,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		pr_debug("qfq_enqueue: enqueue failed %d\n", err);
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		}
 		return err;
 	}
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 633e32defdcc..6c0534cc7758 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -74,7 +74,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		break;
 
 	case RED_PROB_MARK:
-		sch->qstats.overlimits++;
+		qdisc_qstats_overlimit(sch);
 		if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) {
 			q->stats.prob_drop++;
 			goto congestion_drop;
@@ -84,7 +84,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		break;
 
 	case RED_HARD_MARK:
-		sch->qstats.overlimits++;
+		qdisc_qstats_overlimit(sch);
 		if (red_use_harddrop(q) || !red_use_ecn(q) ||
 		    !INET_ECN_set_ce(skb)) {
 			q->stats.forced_drop++;
@@ -100,7 +100,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		sch->q.qlen++;
 	} else if (net_xmit_drop_count(ret)) {
 		q->stats.pdrop++;
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 	}
 	return ret;
 
@@ -142,7 +142,7 @@ static unsigned int red_drop(struct Qdisc *sch)
 
 	if (child->ops->drop && (len = child->ops->drop(child)) > 0) {
 		q->stats.other++;
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 		sch->q.qlen--;
 		return len;
 	}
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 1562fb2b3f46..5819dd82630d 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -290,7 +290,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	struct flow_keys keys;
 
 	if (unlikely(sch->q.qlen >= q->limit)) {
-		sch->qstats.overlimits++;
+		qdisc_qstats_overlimit(sch);
 		q->stats.queuedrop++;
 		goto drop;
 	}
@@ -348,7 +348,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	sfb_skb_cb(skb)->hashes[slot] = 0;
 
 	if (unlikely(minqlen >= q->max)) {
-		sch->qstats.overlimits++;
+		qdisc_qstats_overlimit(sch);
 		q->stats.bucketdrop++;
 		goto drop;
 	}
@@ -376,7 +376,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			}
 		}
 		if (sfb_rate_limit(skb, q)) {
-			sch->qstats.overlimits++;
+			qdisc_qstats_overlimit(sch);
 			q->stats.penaltydrop++;
 			goto drop;
 		}
@@ -411,7 +411,7 @@ enqueue:
 		increment_qlen(skb, q);
 	} else if (net_xmit_drop_count(ret)) {
 		q->stats.childdrop++;
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 	}
 	return ret;
 
@@ -420,7 +420,7 @@ drop:
 	return NET_XMIT_CN;
 other_drop:
 	if (ret & __NET_XMIT_BYPASS)
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 	kfree_skb(skb);
 	return ret;
 }
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 80c36bd54abc..158dfa641d18 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -331,8 +331,8 @@ drop:
 		sfq_dec(q, x);
 		kfree_skb(skb);
 		sch->q.qlen--;
-		sch->qstats.drops++;
-		sch->qstats.backlog -= len;
+		qdisc_qstats_drop(sch);
+		qdisc_qstats_backlog_dec(sch, skb);
 		return len;
 	}
 
@@ -379,7 +379,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	hash = sfq_classify(skb, sch, &ret);
 	if (hash == 0) {
 		if (ret & __NET_XMIT_BYPASS)
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		kfree_skb(skb);
 		return ret;
 	}
@@ -409,7 +409,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			break;
 
 		case RED_PROB_MARK:
-			sch->qstats.overlimits++;
+			qdisc_qstats_overlimit(sch);
 			if (sfq_prob_mark(q)) {
 				/* We know we have at least one packet in queue */
 				if (sfq_headdrop(q) &&
@@ -426,7 +426,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			goto congestion_drop;
 
 		case RED_HARD_MARK:
-			sch->qstats.overlimits++;
+			qdisc_qstats_overlimit(sch);
 			if (sfq_hard_mark(q)) {
 				/* We know we have at least one packet in queue */
 				if (sfq_headdrop(q) &&
@@ -461,7 +461,7 @@ congestion_drop:
 	}
 
 enqueue:
-	sch->qstats.backlog += qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_inc(sch, skb);
 	slot->backlog += qdisc_pkt_len(skb);
 	slot_queue_add(slot, skb);
 	sfq_inc(q, x);
@@ -520,7 +520,7 @@ next_slot:
 	sfq_dec(q, a);
 	qdisc_bstats_update(sch, skb);
 	sch->q.qlen--;
-	sch->qstats.backlog -= qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	slot->backlog -= qdisc_pkt_len(skb);
 	/* Is the slot empty? */
 	if (slot->qlen == 0) {
@@ -586,7 +586,8 @@ static void sfq_rehash(struct Qdisc *sch)
 		if (x == SFQ_EMPTY_SLOT) {
 			x = q->dep[0].next; /* get a free slot */
 			if (x >= SFQ_MAX_FLOWS) {
-drop:				sch->qstats.backlog -= qdisc_pkt_len(skb);
+drop:
+				qdisc_qstats_backlog_dec(sch, skb);
 				kfree_skb(skb);
 				dropped++;
 				continue;
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 0c39b754083b..77edffe329c4 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -175,7 +175,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 		ret = qdisc_enqueue(segs, q->qdisc);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
-				sch->qstats.drops++;
+				qdisc_qstats_drop(sch);
 		} else {
 			nb++;
 		}
@@ -201,7 +201,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	ret = qdisc_enqueue(skb, q->qdisc);
 	if (ret != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(ret))
-			sch->qstats.drops++;
+			qdisc_qstats_drop(sch);
 		return ret;
 	}
 
@@ -216,7 +216,7 @@ static unsigned int tbf_drop(struct Qdisc *sch)
 
 	if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) {
 		sch->q.qlen--;
-		sch->qstats.drops++;
+		qdisc_qstats_drop(sch);
 	}
 	return len;
 }
@@ -281,7 +281,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 		   (cf. CSZ, HPFQ, HFSC)
 		 */
 
-		sch->qstats.overlimits++;
+		qdisc_qstats_overlimit(sch);
 	}
 	return NULL;
 }
-- 
cgit v1.2.3


From 6401585366326fc0ecbc372ec60d1a15cd8be2f5 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 28 Sep 2014 11:53:57 -0700
Subject: net: sched: restrict use of qstats qlen

This removes the use of qstats->qlen variable from the classifiers
and makes it an explicit argument to gnet_stats_copy_queue().

The qlen represents the qdisc queue length and is packed into
the qstats at the last moment before passnig to user space. By
handling it explicitely we avoid, in the percpu stats case, having
to figure out which per_cpu variable to put it in.

It would probably be best to remove it from qstats completely
but qstats is a user space ABI and can't be broken. A future
patch could make an internal only qstats structure that would
avoid having to allocate an additional u32 variable on the
Qdisc struct. This would make the qstats struct 128bits instead
of 128+32.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gen_stats.h  | 3 ++-
 net/core/gen_stats.c     | 6 +++++-
 net/sched/act_api.c      | 4 +++-
 net/sched/sch_api.c      | 5 +++--
 net/sched/sch_atm.c      | 4 +---
 net/sched/sch_cbq.c      | 3 +--
 net/sched/sch_drr.c      | 7 +++----
 net/sched/sch_fq_codel.c | 2 +-
 net/sched/sch_hfsc.c     | 3 +--
 net/sched/sch_htb.c      | 5 +++--
 net/sched/sch_mq.c       | 4 +---
 net/sched/sch_mqprio.c   | 9 ++++-----
 net/sched/sch_multiq.c   | 3 +--
 net/sched/sch_prio.c     | 3 +--
 net/sched/sch_qfq.c      | 3 +--
 net/sched/sch_sfq.c      | 2 +-
 16 files changed, 32 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index ce3c1281f2a0..de9b3dd5750e 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -40,7 +40,8 @@ void __gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
 int gnet_stats_copy_rate_est(struct gnet_dump *d,
 			     const struct gnet_stats_basic_packed *b,
 			     struct gnet_stats_rate_est64 *r);
-int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q);
+int gnet_stats_copy_queue(struct gnet_dump *d,
+			  struct gnet_stats_queue *q, __u32 len);
 int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
 
 int gnet_stats_finish_copy(struct gnet_dump *d);
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 5ff8e80fe0bb..ad3ecb6ba835 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -219,6 +219,7 @@ EXPORT_SYMBOL(gnet_stats_copy_rate_est);
  * gnet_stats_copy_queue - copy queue statistics into statistics TLV
  * @d: dumping handle
  * @q: queue statistics
+ * @qlen: queue length statistics
  *
  * Appends the queue statistics to the top level TLV created by
  * gnet_stats_start_copy().
@@ -227,8 +228,11 @@ EXPORT_SYMBOL(gnet_stats_copy_rate_est);
  * if the room in the socket buffer was not sufficient.
  */
 int
-gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q)
+gnet_stats_copy_queue(struct gnet_dump *d,
+		      struct gnet_stats_queue *q, __u32 qlen)
 {
+	q->qlen = qlen;
+
 	if (d->compat_tc_stats) {
 		d->tc_stats.drops = q->drops;
 		d->tc_stats.qlen = q->qlen;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index eca4cf9ece2f..2e134093b8ec 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -623,7 +623,9 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 	if (gnet_stats_copy_basic(&d, NULL, &p->tcfc_bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
 				     &p->tcfc_rate_est) < 0 ||
-	    gnet_stats_copy_queue(&d, &p->tcfc_qstats) < 0)
+	    gnet_stats_copy_queue(&d,
+				  &p->tcfc_qstats,
+				  p->tcfc_qstats.qlen) < 0)
 		goto errout;
 
 	if (gnet_stats_finish_copy(&d) < 0)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 2862bc61a358..ca00ea8e84dc 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1318,6 +1318,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 	unsigned char *b = skb_tail_pointer(skb);
 	struct gnet_dump d;
 	struct qdisc_size_table *stab;
+	__u32 qlen;
 
 	cond_resched();
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
@@ -1335,7 +1336,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 		goto nla_put_failure;
 	if (q->ops->dump && q->ops->dump(q, skb) < 0)
 		goto nla_put_failure;
-	q->qstats.qlen = q->q.qlen;
+	qlen = q->q.qlen;
 
 	stab = rtnl_dereference(q->stab);
 	if (stab && qdisc_dump_stab(skb, stab) < 0)
@@ -1353,7 +1354,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 
 	if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
-	    gnet_stats_copy_queue(&d, &q->qstats) < 0)
+	    gnet_stats_copy_queue(&d, &q->qstats, qlen) < 0)
 		goto nla_put_failure;
 
 	if (gnet_stats_finish_copy(&d) < 0)
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 040212cab988..c145eb6279cc 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -637,10 +637,8 @@ atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 {
 	struct atm_flow_data *flow = (struct atm_flow_data *)arg;
 
-	flow->qstats.qlen = flow->q->q.qlen;
-
 	if (gnet_stats_copy_basic(d, NULL, &flow->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, &flow->qstats) < 0)
+	    gnet_stats_copy_queue(d, &flow->qstats, flow->q->q.qlen) < 0)
 		return -1;
 
 	return 0;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 60432c3d3cd4..c610081ffba5 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1594,7 +1594,6 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
 
-	cl->qstats.qlen = cl->q->q.qlen;
 	cl->xstats.avgidle = cl->avgidle;
 	cl->xstats.undertime = 0;
 
@@ -1603,7 +1602,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
+	    gnet_stats_copy_queue(d, &cl->qstats, cl->q->q.qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats));
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 907b12fd6825..5835a93905b1 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -275,17 +275,16 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 				struct gnet_dump *d)
 {
 	struct drr_class *cl = (struct drr_class *)arg;
+	__u32 qlen = cl->qdisc->q.qlen;
 	struct tc_drr_stats xstats;
 
 	memset(&xstats, 0, sizeof(xstats));
-	if (cl->qdisc->q.qlen) {
+	if (qlen)
 		xstats.deficit = cl->deficit;
-		cl->qdisc->qstats.qlen = cl->qdisc->q.qlen;
-	}
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
+	    gnet_stats_copy_queue(d, &cl->qdisc->qstats, qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 9270e1b2f25d..226d73597539 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -550,7 +550,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		qs.backlog = q->backlogs[idx];
 		qs.drops = flow->dropped;
 	}
-	if (gnet_stats_copy_queue(d, &qs) < 0)
+	if (gnet_stats_copy_queue(d, &qs, 0) < 0)
 		return -1;
 	if (idx < q->flows_cnt)
 		return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index ad278251d811..d364acb2ad07 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1370,7 +1370,6 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	struct hfsc_class *cl = (struct hfsc_class *)arg;
 	struct tc_hfsc_stats xstats;
 
-	cl->qstats.qlen = cl->qdisc->q.qlen;
 	cl->qstats.backlog = cl->qdisc->qstats.backlog;
 	xstats.level   = cl->level;
 	xstats.period  = cl->cl_vtperiod;
@@ -1379,7 +1378,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
+	    gnet_stats_copy_queue(d, &cl->qstats, cl->qdisc->q.qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index c40ab7a98c50..3a691fd88f99 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1138,15 +1138,16 @@ static int
 htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
 {
 	struct htb_class *cl = (struct htb_class *)arg;
+	__u32 qlen = 0;
 
 	if (!cl->level && cl->un.leaf.q)
-		cl->qstats.qlen = cl->un.leaf.q->q.qlen;
+		qlen = cl->un.leaf.q->q.qlen;
 	cl->xstats.tokens = PSCHED_NS2TICKS(cl->tokens);
 	cl->xstats.ctokens = PSCHED_NS2TICKS(cl->ctokens);
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
+	    gnet_stats_copy_queue(d, &cl->qstats, qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats));
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index d3a27fb607af..6416a6942062 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -112,7 +112,6 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
 		sch->q.qlen		+= qdisc->q.qlen;
 		sch->bstats.bytes	+= qdisc->bstats.bytes;
 		sch->bstats.packets	+= qdisc->bstats.packets;
-		sch->qstats.qlen	+= qdisc->qstats.qlen;
 		sch->qstats.backlog	+= qdisc->qstats.backlog;
 		sch->qstats.drops	+= qdisc->qstats.drops;
 		sch->qstats.requeues	+= qdisc->qstats.requeues;
@@ -200,9 +199,8 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
 
 	sch = dev_queue->qdisc_sleeping;
-	sch->qstats.qlen = sch->q.qlen;
 	if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, &sch->qstats) < 0)
+	    gnet_stats_copy_queue(d, &sch->qstats, sch->q.qlen) < 0)
 		return -1;
 	return 0;
 }
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 8917372fddc6..03dbeb5e8181 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -236,7 +236,6 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 		sch->q.qlen		+= qdisc->q.qlen;
 		sch->bstats.bytes	+= qdisc->bstats.bytes;
 		sch->bstats.packets	+= qdisc->bstats.packets;
-		sch->qstats.qlen	+= qdisc->qstats.qlen;
 		sch->qstats.backlog	+= qdisc->qstats.backlog;
 		sch->qstats.drops	+= qdisc->qstats.drops;
 		sch->qstats.requeues	+= qdisc->qstats.requeues;
@@ -327,6 +326,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	if (cl <= netdev_get_num_tc(dev)) {
 		int i;
+		__u32 qlen = 0;
 		struct Qdisc *qdisc;
 		struct gnet_stats_queue qstats = {0};
 		struct gnet_stats_basic_packed bstats = {0};
@@ -344,9 +344,9 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 			qdisc = rtnl_dereference(q->qdisc);
 			spin_lock_bh(qdisc_lock(qdisc));
+			qlen		  += qdisc->q.qlen;
 			bstats.bytes      += qdisc->bstats.bytes;
 			bstats.packets    += qdisc->bstats.packets;
-			qstats.qlen       += qdisc->qstats.qlen;
 			qstats.backlog    += qdisc->qstats.backlog;
 			qstats.drops      += qdisc->qstats.drops;
 			qstats.requeues   += qdisc->qstats.requeues;
@@ -356,15 +356,14 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		/* Reclaim root sleeping lock before completing stats */
 		spin_lock_bh(d->lock);
 		if (gnet_stats_copy_basic(d, NULL, &bstats) < 0 ||
-		    gnet_stats_copy_queue(d, &qstats) < 0)
+		    gnet_stats_copy_queue(d, &qstats, qlen) < 0)
 			return -1;
 	} else {
 		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
 
 		sch = dev_queue->qdisc_sleeping;
-		sch->qstats.qlen = sch->q.qlen;
 		if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
-		    gnet_stats_copy_queue(d, &sch->qstats) < 0)
+		    gnet_stats_copy_queue(d, &sch->qstats, sch->q.qlen) < 0)
 			return -1;
 	}
 	return 0;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 7f4e1d8504b0..53357b368bff 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -360,9 +360,8 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct Qdisc *cl_q;
 
 	cl_q = q->queues[cl - 1];
-	cl_q->qstats.qlen = cl_q->q.qlen;
 	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
+	    gnet_stats_copy_queue(d, &cl_q->qstats, cl_q->q.qlen) < 0)
 		return -1;
 
 	return 0;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index b411e78a02fc..4644f55242d2 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -324,9 +324,8 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct Qdisc *cl_q;
 
 	cl_q = q->queues[cl - 1];
-	cl_q->qstats.qlen = cl_q->q.qlen;
 	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
+	    gnet_stats_copy_queue(d, &cl_q->qstats, cl_q->q.qlen) < 0)
 		return -1;
 
 	return 0;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 3fb26555c79b..66df9d9e301a 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -664,14 +664,13 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	struct tc_qfq_stats xstats;
 
 	memset(&xstats, 0, sizeof(xstats));
-	cl->qdisc->qstats.qlen = cl->qdisc->q.qlen;
 
 	xstats.weight = cl->agg->class_weight;
 	xstats.lmax = cl->agg->lmax;
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
+	    gnet_stats_copy_queue(d, &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 158dfa641d18..d4afcbc1c6f7 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -871,7 +871,7 @@ static int sfq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		qs.qlen = slot->qlen;
 		qs.backlog = slot->backlog;
 	}
-	if (gnet_stats_copy_queue(d, &qs) < 0)
+	if (gnet_stats_copy_queue(d, &qs, qs.qlen) < 0)
 		return -1;
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
 }
-- 
cgit v1.2.3


From b0ab6f92752b9f9d8da980506e9df3bd9dcd7ed3 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 28 Sep 2014 11:54:24 -0700
Subject: net: sched: enable per cpu qstats

After previous patches to simplify qstats the qstats can be
made per cpu with a packed union in Qdisc struct.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gen_stats.h   |  3 ++-
 include/net/sch_generic.h | 12 ++++++++++-
 net/core/gen_stats.c      | 55 +++++++++++++++++++++++++++++++++++++++++------
 net/sched/act_api.c       |  2 +-
 net/sched/sch_api.c       | 12 +++++++++--
 net/sched/sch_atm.c       |  2 +-
 net/sched/sch_cbq.c       |  2 +-
 net/sched/sch_drr.c       |  2 +-
 net/sched/sch_fq_codel.c  |  2 +-
 net/sched/sch_hfsc.c      |  2 +-
 net/sched/sch_htb.c       |  2 +-
 net/sched/sch_mq.c        |  2 +-
 net/sched/sch_mqprio.c    |  5 +++--
 net/sched/sch_multiq.c    |  2 +-
 net/sched/sch_prio.c      |  2 +-
 net/sched/sch_qfq.c       |  3 ++-
 net/sched/sch_sfq.c       |  2 +-
 17 files changed, 87 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index de9b3dd5750e..cbafa3768d48 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -41,7 +41,8 @@ int gnet_stats_copy_rate_est(struct gnet_dump *d,
 			     const struct gnet_stats_basic_packed *b,
 			     struct gnet_stats_rate_est64 *r);
 int gnet_stats_copy_queue(struct gnet_dump *d,
-			  struct gnet_stats_queue *q, __u32 len);
+			  struct gnet_stats_queue __percpu *cpu_q,
+			  struct gnet_stats_queue *q, __u32 qlen);
 int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
 
 int gnet_stats_finish_copy(struct gnet_dump *d);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 23a0f0fc83d8..f12669819d1a 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -90,7 +90,10 @@ struct Qdisc {
 		struct gnet_stats_basic_cpu __percpu *cpu_bstats;
 	} __packed;
 	unsigned int		__state;
-	struct gnet_stats_queue	qstats;
+	union {
+		struct gnet_stats_queue	qstats;
+		struct gnet_stats_queue	__percpu *cpu_qstats;
+	} __packed;
 	struct rcu_head		rcu_head;
 	int			padded;
 	atomic_t		refcnt;
@@ -543,6 +546,13 @@ static inline void qdisc_qstats_drop(struct Qdisc *sch)
 	sch->qstats.drops++;
 }
 
+static inline void qdisc_qstats_drop_cpu(struct Qdisc *sch)
+{
+	struct gnet_stats_queue *qstats = this_cpu_ptr(sch->cpu_qstats);
+
+	qstats->drops++;
+}
+
 static inline void qdisc_qstats_overlimit(struct Qdisc *sch)
 {
 	sch->qstats.overlimits++;
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index ad3ecb6ba835..14681b97a4f3 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -215,33 +215,74 @@ gnet_stats_copy_rate_est(struct gnet_dump *d,
 }
 EXPORT_SYMBOL(gnet_stats_copy_rate_est);
 
+static void
+__gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats,
+			    const struct gnet_stats_queue __percpu *q)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i);
+
+		qstats->qlen = 0;
+		qstats->backlog += qcpu->backlog;
+		qstats->drops += qcpu->drops;
+		qstats->requeues += qcpu->requeues;
+		qstats->overlimits += qcpu->overlimits;
+	}
+}
+
+static void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats,
+				    const struct gnet_stats_queue __percpu *cpu,
+				    const struct gnet_stats_queue *q,
+				    __u32 qlen)
+{
+	if (cpu) {
+		__gnet_stats_copy_queue_cpu(qstats, cpu);
+	} else {
+		qstats->qlen = q->qlen;
+		qstats->backlog = q->backlog;
+		qstats->drops = q->drops;
+		qstats->requeues = q->requeues;
+		qstats->overlimits = q->overlimits;
+	}
+
+	qstats->qlen = qlen;
+}
+
 /**
  * gnet_stats_copy_queue - copy queue statistics into statistics TLV
  * @d: dumping handle
+ * @cpu_q: per cpu queue statistics
  * @q: queue statistics
  * @qlen: queue length statistics
  *
  * Appends the queue statistics to the top level TLV created by
- * gnet_stats_start_copy().
+ * gnet_stats_start_copy(). Using per cpu queue statistics if
+ * they are available.
  *
  * Returns 0 on success or -1 with the statistic lock released
  * if the room in the socket buffer was not sufficient.
  */
 int
 gnet_stats_copy_queue(struct gnet_dump *d,
+		      struct gnet_stats_queue __percpu *cpu_q,
 		      struct gnet_stats_queue *q, __u32 qlen)
 {
-	q->qlen = qlen;
+	struct gnet_stats_queue qstats = {0};
+
+	__gnet_stats_copy_queue(&qstats, cpu_q, q, qlen);
 
 	if (d->compat_tc_stats) {
-		d->tc_stats.drops = q->drops;
-		d->tc_stats.qlen = q->qlen;
-		d->tc_stats.backlog = q->backlog;
-		d->tc_stats.overlimits = q->overlimits;
+		d->tc_stats.drops = qstats.drops;
+		d->tc_stats.qlen = qstats.qlen;
+		d->tc_stats.backlog = qstats.backlog;
+		d->tc_stats.overlimits = qstats.overlimits;
 	}
 
 	if (d->tail)
-		return gnet_stats_copy(d, TCA_STATS_QUEUE, q, sizeof(*q));
+		return gnet_stats_copy(d, TCA_STATS_QUEUE,
+				       &qstats, sizeof(qstats));
 
 	return 0;
 }
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 2e134093b8ec..3d43e4979f27 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -623,7 +623,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 	if (gnet_stats_copy_basic(&d, NULL, &p->tcfc_bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
 				     &p->tcfc_rate_est) < 0 ||
-	    gnet_stats_copy_queue(&d,
+	    gnet_stats_copy_queue(&d, NULL,
 				  &p->tcfc_qstats,
 				  p->tcfc_qstats.qlen) < 0)
 		goto errout;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ca00ea8e84dc..aa8329508dba 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -947,6 +947,10 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 				alloc_percpu(struct gnet_stats_basic_cpu);
 			if (!sch->cpu_bstats)
 				goto err_out4;
+
+			sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
+			if (!sch->cpu_qstats)
+				goto err_out4;
 		}
 
 		if (tca[TCA_STAB]) {
@@ -995,6 +999,7 @@ err_out:
 
 err_out4:
 	free_percpu(sch->cpu_bstats);
+	free_percpu(sch->cpu_qstats);
 	/*
 	 * Any broken qdiscs that would require a ops->reset() here?
 	 * The qdisc was never in action so it shouldn't be necessary.
@@ -1313,6 +1318,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 			 u32 portid, u32 seq, u16 flags, int event)
 {
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL;
+	struct gnet_stats_queue __percpu *cpu_qstats = NULL;
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
 	unsigned char *b = skb_tail_pointer(skb);
@@ -1349,12 +1355,14 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 	if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0)
 		goto nla_put_failure;
 
-	if (qdisc_is_percpu_stats(q))
+	if (qdisc_is_percpu_stats(q)) {
 		cpu_bstats = q->cpu_bstats;
+		cpu_qstats = q->cpu_qstats;
+	}
 
 	if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
-	    gnet_stats_copy_queue(&d, &q->qstats, qlen) < 0)
+	    gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0)
 		goto nla_put_failure;
 
 	if (gnet_stats_finish_copy(&d) < 0)
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index c145eb6279cc..e3e2cc5fd068 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -638,7 +638,7 @@ atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	struct atm_flow_data *flow = (struct atm_flow_data *)arg;
 
 	if (gnet_stats_copy_basic(d, NULL, &flow->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, &flow->qstats, flow->q->q.qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0)
 		return -1;
 
 	return 0;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index c610081ffba5..beeb75f80fdb 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1602,7 +1602,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qstats, cl->q->q.qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats));
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 5835a93905b1..338706092c27 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -284,7 +284,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qdisc->qstats, qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 226d73597539..b9ca32ebc1de 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -550,7 +550,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		qs.backlog = q->backlogs[idx];
 		qs.drops = flow->dropped;
 	}
-	if (gnet_stats_copy_queue(d, &qs, 0) < 0)
+	if (gnet_stats_copy_queue(d, NULL, &qs, 0) < 0)
 		return -1;
 	if (idx < q->flows_cnt)
 		return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index d364acb2ad07..e6c7416d0332 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1378,7 +1378,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qstats, cl->qdisc->q.qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->qdisc->q.qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 3a691fd88f99..f1acb0f60dc3 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1147,7 +1147,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qstats, qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats));
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 6416a6942062..f3cbaecd283a 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -200,7 +200,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	sch = dev_queue->qdisc_sleeping;
 	if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, &sch->qstats, sch->q.qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0)
 		return -1;
 	return 0;
 }
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 03dbeb5e8181..3811a745452c 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -356,14 +356,15 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		/* Reclaim root sleeping lock before completing stats */
 		spin_lock_bh(d->lock);
 		if (gnet_stats_copy_basic(d, NULL, &bstats) < 0 ||
-		    gnet_stats_copy_queue(d, &qstats, qlen) < 0)
+		    gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0)
 			return -1;
 	} else {
 		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
 
 		sch = dev_queue->qdisc_sleeping;
 		if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
-		    gnet_stats_copy_queue(d, &sch->qstats, sch->q.qlen) < 0)
+		    gnet_stats_copy_queue(d, NULL,
+					  &sch->qstats, sch->q.qlen) < 0)
 			return -1;
 	}
 	return 0;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 53357b368bff..42dd218871e0 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -361,7 +361,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, &cl_q->qstats, cl_q->q.qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
 		return -1;
 
 	return 0;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 4644f55242d2..8e5cd34aaa74 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -325,7 +325,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, &cl_q->qstats, cl_q->q.qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
 		return -1;
 
 	return 0;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 66df9d9e301a..3ec7e88a43ca 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -670,7 +670,8 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL,
+				  &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index d4afcbc1c6f7..b877140beda5 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -871,7 +871,7 @@ static int sfq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		qs.qlen = slot->qlen;
 		qs.backlog = slot->backlog;
 	}
-	if (gnet_stats_copy_queue(d, &qs, qs.qlen) < 0)
+	if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0)
 		return -1;
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
 }
-- 
cgit v1.2.3


From d8e0a86f9713689e35dc14f7184e85a13a2a9f4e Mon Sep 17 00:00:00 2001
From: Doug Anderson <dianders@chromium.org>
Date: Mon, 23 Jun 2014 14:20:06 -0700
Subject: i2c: cros_ec: Remove EC_I2C_FLAG_10BIT

In <https://lkml.org/lkml/2014/6/10/265> pointed out that the 10-bit
flag in the cros_ec_tunnel was useless.  It went into a 16-bit flags
field but was defined at (1 << 16).

Since we have no 10-bit i2c devices on the other side of the tunnel on
any known devices this was never a problem.  Until we do it makes
sense to remove this code.  On the EC side the code to handle this
flag was removed in <https://chromium-review.googlesource.com/204162>.

Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Doug Anderson <dianders@chromium.org>
Reviewed-by: Simon Glass <sjg@chromium.org>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/busses/i2c-cros-ec-tunnel.c | 6 ++++--
 include/linux/mfd/cros_ec_commands.h    | 3 ---
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
index 0403ec1dc3b5..fc89c13b1632 100644
--- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c
+++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
@@ -94,7 +94,7 @@ static int ec_i2c_construct_message(u8 *buf, const struct i2c_msg i2c_msgs[],
 		msg->addr_flags = i2c_msg->addr;
 
 		if (i2c_msg->flags & I2C_M_TEN)
-			msg->addr_flags |= EC_I2C_FLAG_10BIT;
+			return -EINVAL;
 
 		if (i2c_msg->flags & I2C_M_RD) {
 			msg->addr_flags |= EC_I2C_FLAG_READ;
@@ -218,7 +218,9 @@ static int ec_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg i2c_msgs[],
 		}
 	}
 
-	ec_i2c_construct_message(request, i2c_msgs, num, bus_num);
+	result = ec_i2c_construct_message(request, i2c_msgs, num, bus_num);
+	if (result)
+		goto exit;
 
 	msg.version = 0;
 	msg.command = EC_CMD_I2C_PASSTHRU;
diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h
index 7853a6410d14..a49cd41feea7 100644
--- a/include/linux/mfd/cros_ec_commands.h
+++ b/include/linux/mfd/cros_ec_commands.h
@@ -1928,9 +1928,6 @@ struct ec_response_power_info {
 
 #define EC_CMD_I2C_PASSTHRU 0x9e
 
-/* Slave address is 10 (not 7) bit */
-#define EC_I2C_FLAG_10BIT	(1 << 16)
-
 /* Read data; if not present, message is a write */
 #define EC_I2C_FLAG_READ	(1 << 15)
 
-- 
cgit v1.2.3


From b5e9c1a25fcf8a0d664606251a53b5caa6a19d08 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Date: Thu, 9 Jan 2014 11:03:14 +0100
Subject: drm: Pass dma-buf as argument to gem_prime_import_sg_table

Allows importing dma_reservation_objects from a dma-buf.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
---
 drivers/gpu/drm/drm_gem_cma_helper.c    | 7 ++++---
 drivers/gpu/drm/drm_prime.c             | 2 +-
 drivers/gpu/drm/msm/msm_drv.h           | 2 +-
 drivers/gpu/drm/msm/msm_gem_prime.c     | 5 +++--
 drivers/gpu/drm/nouveau/nouveau_gem.h   | 2 +-
 drivers/gpu/drm/nouveau/nouveau_prime.c | 5 +++--
 drivers/gpu/drm/qxl/qxl_drv.h           | 2 +-
 drivers/gpu/drm/qxl/qxl_prime.c         | 2 +-
 drivers/gpu/drm/radeon/radeon_drv.c     | 2 +-
 drivers/gpu/drm/radeon/radeon_prime.c   | 5 +++--
 include/drm/drmP.h                      | 4 +++-
 include/drm/drm_gem_cma_helper.h        | 3 ++-
 12 files changed, 24 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index e467e67af6e7..0316310e2cc4 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -316,7 +316,8 @@ out:
 EXPORT_SYMBOL_GPL(drm_gem_cma_prime_get_sg_table);
 
 struct drm_gem_object *
-drm_gem_cma_prime_import_sg_table(struct drm_device *dev, size_t size,
+drm_gem_cma_prime_import_sg_table(struct drm_device *dev,
+				  struct dma_buf_attachment *attach,
 				  struct sg_table *sgt)
 {
 	struct drm_gem_cma_object *cma_obj;
@@ -325,14 +326,14 @@ drm_gem_cma_prime_import_sg_table(struct drm_device *dev, size_t size,
 		return ERR_PTR(-EINVAL);
 
 	/* Create a CMA GEM buffer. */
-	cma_obj = __drm_gem_cma_create(dev, size);
+	cma_obj = __drm_gem_cma_create(dev, attach->dmabuf->size);
 	if (IS_ERR(cma_obj))
 		return ERR_CAST(cma_obj);
 
 	cma_obj->paddr = sg_dma_address(sgt->sgl);
 	cma_obj->sgt = sgt;
 
-	DRM_DEBUG_PRIME("dma_addr = %pad, size = %zu\n", &cma_obj->paddr, size);
+	DRM_DEBUG_PRIME("dma_addr = %pad, size = %zu\n", &cma_obj->paddr, attach->dmabuf->size);
 
 	return &cma_obj->base;
 }
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 7826de9da276..78ca30808422 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -525,7 +525,7 @@ struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev,
 		goto fail_detach;
 	}
 
-	obj = dev->driver->gem_prime_import_sg_table(dev, dma_buf->size, sgt);
+	obj = dev->driver->gem_prime_import_sg_table(dev, attach, sgt);
 	if (IS_ERR(obj)) {
 		ret = PTR_ERR(obj);
 		goto fail_unmap;
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index afaafd42dee7..67f9d0a2332c 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -171,7 +171,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj);
 void *msm_gem_prime_vmap(struct drm_gem_object *obj);
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
-		size_t size, struct sg_table *sg);
+		struct dma_buf_attachment *attach, struct sg_table *sg);
 int msm_gem_prime_pin(struct drm_gem_object *obj);
 void msm_gem_prime_unpin(struct drm_gem_object *obj);
 void *msm_gem_vaddr_locked(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index d48f9fc5129b..ad772fe36115 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -18,6 +18,7 @@
 #include "msm_drv.h"
 #include "msm_gem.h"
 
+#include <linux/dma-buf.h>
 
 struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
@@ -37,9 +38,9 @@ void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 }
 
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
-		size_t size, struct sg_table *sg)
+		struct dma_buf_attachment *attach, struct sg_table *sg)
 {
-	return msm_gem_import(dev, size, sg);
+	return msm_gem_import(dev, attach->dmabuf->size, sg);
 }
 
 int msm_gem_prime_pin(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.h b/drivers/gpu/drm/nouveau/nouveau_gem.h
index ddab762d81fe..e4049faca780 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.h
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.h
@@ -39,7 +39,7 @@ struct reservation_object *nouveau_gem_prime_res_obj(struct drm_gem_object *);
 extern void nouveau_gem_prime_unpin(struct drm_gem_object *);
 extern struct sg_table *nouveau_gem_prime_get_sg_table(struct drm_gem_object *);
 extern struct drm_gem_object *nouveau_gem_prime_import_sg_table(
-	struct drm_device *, size_t size, struct sg_table *);
+	struct drm_device *, struct dma_buf_attachment *, struct sg_table *);
 extern void *nouveau_gem_prime_vmap(struct drm_gem_object *);
 extern void nouveau_gem_prime_vunmap(struct drm_gem_object *, void *);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c
index 1f51008e4d26..2215cdba587d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_prime.c
+++ b/drivers/gpu/drm/nouveau/nouveau_prime.c
@@ -23,6 +23,7 @@
  */
 
 #include <drm/drmP.h>
+#include <linux/dma-buf.h>
 
 #include "nouveau_drm.h"
 #include "nouveau_gem.h"
@@ -56,7 +57,7 @@ void nouveau_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 }
 
 struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev,
-							 size_t size,
+							 struct dma_buf_attachment *attach,
 							 struct sg_table *sg)
 {
 	struct nouveau_bo *nvbo;
@@ -65,7 +66,7 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev,
 
 	flags = TTM_PL_FLAG_TT;
 
-	ret = nouveau_bo_new(dev, size, 0, flags, 0, 0,
+	ret = nouveau_bo_new(dev, attach->dmabuf->size, 0, flags, 0, 0,
 			     sg, &nvbo);
 	if (ret)
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index ff0772728eb0..7c6cafe21f5f 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -537,7 +537,7 @@ int qxl_gem_prime_pin(struct drm_gem_object *obj);
 void qxl_gem_prime_unpin(struct drm_gem_object *obj);
 struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *qxl_gem_prime_import_sg_table(
-	struct drm_device *dev, size_t size,
+	struct drm_device *dev, struct dma_buf_attachment *attach,
 	struct sg_table *sgt);
 void *qxl_gem_prime_vmap(struct drm_gem_object *obj);
 void qxl_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c
index ba0689c728e8..3d031b50a8fd 100644
--- a/drivers/gpu/drm/qxl/qxl_prime.c
+++ b/drivers/gpu/drm/qxl/qxl_prime.c
@@ -46,7 +46,7 @@ struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj)
 }
 
 struct drm_gem_object *qxl_gem_prime_import_sg_table(
-	struct drm_device *dev, size_t size,
+	struct drm_device *dev, struct dma_buf_attachment *attach,
 	struct sg_table *table)
 {
 	WARN_ONCE(1, "not implemented");
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index de108427a197..69c6a835bcd5 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -135,7 +135,7 @@ int radeon_mode_dumb_create(struct drm_file *file_priv,
 			    struct drm_mode_create_dumb *args);
 struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev,
-							size_t size,
+							struct dma_buf_attachment *,
 							struct sg_table *sg);
 int radeon_gem_prime_pin(struct drm_gem_object *obj);
 void radeon_gem_prime_unpin(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c
index d5414d42e44b..171daf7fc483 100644
--- a/drivers/gpu/drm/radeon/radeon_prime.c
+++ b/drivers/gpu/drm/radeon/radeon_prime.c
@@ -27,6 +27,7 @@
 
 #include "radeon.h"
 #include <drm/radeon_drm.h>
+#include <linux/dma-buf.h>
 
 struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
@@ -57,14 +58,14 @@ void radeon_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 }
 
 struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev,
-							size_t size,
+							struct dma_buf_attachment *attach,
 							struct sg_table *sg)
 {
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_bo *bo;
 	int ret;
 
-	ret = radeon_bo_create(rdev, size, PAGE_SIZE, false,
+	ret = radeon_bo_create(rdev, attach->dmabuf->size, PAGE_SIZE, false,
 			       RADEON_GEM_DOMAIN_GTT, 0, sg, &bo);
 	if (ret)
 		return ERR_PTR(ret);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index d2c2b7f3a4e2..53ed87698a74 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -87,6 +87,7 @@ struct drm_gem_object;
 struct device_node;
 struct videomode;
 struct reservation_object;
+struct dma_buf_attachment;
 
 /*
  * 4 debug categories are defined:
@@ -570,7 +571,8 @@ struct drm_driver {
 				struct drm_gem_object *obj);
 	struct sg_table *(*gem_prime_get_sg_table)(struct drm_gem_object *obj);
 	struct drm_gem_object *(*gem_prime_import_sg_table)(
-				struct drm_device *dev, size_t size,
+				struct drm_device *dev,
+				struct dma_buf_attachment *attach,
 				struct sg_table *sgt);
 	void *(*gem_prime_vmap)(struct drm_gem_object *obj);
 	void (*gem_prime_vunmap)(struct drm_gem_object *obj, void *vaddr);
diff --git a/include/drm/drm_gem_cma_helper.h b/include/drm/drm_gem_cma_helper.h
index 42f11f3a8d39..2ff35f3de9c5 100644
--- a/include/drm/drm_gem_cma_helper.h
+++ b/include/drm/drm_gem_cma_helper.h
@@ -45,7 +45,8 @@ void drm_gem_cma_describe(struct drm_gem_cma_object *obj, struct seq_file *m);
 
 struct sg_table *drm_gem_cma_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *
-drm_gem_cma_prime_import_sg_table(struct drm_device *dev, size_t size,
+drm_gem_cma_prime_import_sg_table(struct drm_device *dev,
+				  struct dma_buf_attachment *attach,
 				  struct sg_table *sgt);
 int drm_gem_cma_prime_mmap(struct drm_gem_object *obj,
 			   struct vm_area_struct *vma);
-- 
cgit v1.2.3


From f4f4e3e3e9f3bde110067b9e4487cb267d90055a Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Date: Thu, 9 Jan 2014 11:03:15 +0100
Subject: drm/ttm: add reservation_object as argument to ttm_bo_init

This allows importing reservation objects from dma-bufs.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
---
 drivers/gpu/drm/ast/ast_ttm.c            |  2 +-
 drivers/gpu/drm/bochs/bochs_mm.c         |  2 +-
 drivers/gpu/drm/cirrus/cirrus_ttm.c      |  2 +-
 drivers/gpu/drm/mgag200/mgag200_ttm.c    |  2 +-
 drivers/gpu/drm/nouveau/nouveau_bo.c     |  2 +-
 drivers/gpu/drm/qxl/qxl_object.c         |  2 +-
 drivers/gpu/drm/radeon/radeon_object.c   |  2 +-
 drivers/gpu/drm/ttm/ttm_bo.c             | 24 ++++++++++++++++++------
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c |  2 +-
 include/drm/ttm/ttm_bo_api.h             |  2 ++
 10 files changed, 28 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index c65d432f42c4..08f82eae6939 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -339,7 +339,7 @@ int ast_bo_create(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&ast->ttm.bdev, &astbo->bo, size,
 			  ttm_bo_type_device, &astbo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size,
-			  NULL, ast_bo_ttm_destroy);
+			  NULL, NULL, ast_bo_ttm_destroy);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
index 324f5a09a0a1..66286ff518d4 100644
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ b/drivers/gpu/drm/bochs/bochs_mm.c
@@ -377,7 +377,7 @@ static int bochs_bo_create(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&bochs->ttm.bdev, &bochsbo->bo, size,
 			  ttm_bo_type_device, &bochsbo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size,
-			  NULL, bochs_bo_ttm_destroy);
+			  NULL, NULL, bochs_bo_ttm_destroy);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index d3c615f9b183..dfffd528517a 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -343,7 +343,7 @@ int cirrus_bo_create(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&cirrus->ttm.bdev, &cirrusbo->bo, size,
 			  ttm_bo_type_device, &cirrusbo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size,
-			  NULL, cirrus_bo_ttm_destroy);
+			  NULL, NULL, cirrus_bo_ttm_destroy);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 8ac70626df6c..d16964ea0ed4 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -339,7 +339,7 @@ int mgag200_bo_create(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&mdev->ttm.bdev, &mgabo->bo, size,
 			  ttm_bo_type_device, &mgabo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size,
-			  NULL, mgag200_bo_ttm_destroy);
+			  NULL, NULL, mgag200_bo_ttm_destroy);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 049f5de90928..7034cacaa4a1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -230,7 +230,7 @@ nouveau_bo_new(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&drm->ttm.bdev, &nvbo->bo, size,
 			  type, &nvbo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size, sg,
-			  nouveau_bo_del_ttm);
+			  NULL, nouveau_bo_del_ttm);
 	if (ret) {
 		/* ttm will call nouveau_bo_del_ttm if it fails.. */
 		return ret;
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index 69c104c3240f..cdeaf08fdc74 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -110,7 +110,7 @@ int qxl_bo_create(struct qxl_device *qdev,
 
 	r = ttm_bo_init(&qdev->mman.bdev, &bo->tbo, size, type,
 			&bo->placement, 0, !kernel, NULL, size,
-			NULL, &qxl_ttm_bo_destroy);
+			NULL, NULL, &qxl_ttm_bo_destroy);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
 			dev_err(qdev->dev,
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 8abee5fa93bd..0e82f0223fd4 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -216,7 +216,7 @@ int radeon_bo_create(struct radeon_device *rdev,
 	down_read(&rdev->pm.mclk_lock);
 	r = ttm_bo_init(&rdev->mman.bdev, &bo->tbo, size, type,
 			&bo->placement, page_align, !kernel, NULL,
-			acc_size, sg, &radeon_ttm_bo_destroy);
+			acc_size, sg, NULL, &radeon_ttm_bo_destroy);
 	up_read(&rdev->pm.mclk_lock);
 	if (unlikely(r != 0)) {
 		return r;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index a11969acfea5..8f5cec67c47d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1068,6 +1068,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 		struct file *persistent_swap_storage,
 		size_t acc_size,
 		struct sg_table *sg,
+		struct reservation_object *resv,
 		void (*destroy) (struct ttm_buffer_object *))
 {
 	int ret = 0;
@@ -1121,8 +1122,13 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	bo->persistent_swap_storage = persistent_swap_storage;
 	bo->acc_size = acc_size;
 	bo->sg = sg;
-	bo->resv = &bo->ttm_resv;
-	reservation_object_init(bo->resv);
+	if (resv) {
+		bo->resv = resv;
+		lockdep_assert_held(&bo->resv->lock.base);
+	} else {
+		bo->resv = &bo->ttm_resv;
+		reservation_object_init(&bo->ttm_resv);
+	}
 	atomic_inc(&bo->glob->bo_count);
 	drm_vma_node_reset(&bo->vma_node);
 
@@ -1135,13 +1141,19 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 		ret = drm_vma_offset_add(&bdev->vma_manager, &bo->vma_node,
 					 bo->mem.num_pages);
 
-	locked = ww_mutex_trylock(&bo->resv->lock);
-	WARN_ON(!locked);
+	/* passed reservation objects should already be locked,
+	 * since otherwise lockdep will be angered in radeon.
+	 */
+	if (!resv) {
+		locked = ww_mutex_trylock(&bo->resv->lock);
+		WARN_ON(!locked);
+	}
 
 	if (likely(!ret))
 		ret = ttm_bo_validate(bo, placement, interruptible, false);
 
-	ttm_bo_unreserve(bo);
+	if (!resv)
+		ttm_bo_unreserve(bo);
 
 	if (unlikely(ret))
 		ttm_bo_unref(&bo);
@@ -1199,7 +1211,7 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 	acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
 	ret = ttm_bo_init(bdev, bo, size, type, placement, page_alignment,
 			  interruptible, persistent_swap_storage, acc_size,
-			  NULL, NULL);
+			  NULL, NULL, NULL);
 	if (likely(ret == 0))
 		*p_bo = bo;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 26584316cb78..026de7cea0f6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -430,7 +430,7 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv,
 	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
 			  ttm_bo_type_device, placement,
 			  0, interruptible,
-			  NULL, acc_size, NULL, bo_free);
+			  NULL, acc_size, NULL, NULL, bo_free);
 	return ret;
 }
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 70b44917c368..0ccf7f267ff9 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -460,6 +460,7 @@ size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev,
  * point to the shmem object backing a GEM object if TTM is used to back a
  * GEM user interface.
  * @acc_size: Accounted size for this object.
+ * @resv: Pointer to a reservation_object, or NULL to let ttm allocate one.
  * @destroy: Destroy function. Use NULL for kfree().
  *
  * This function initializes a pre-allocated struct ttm_buffer_object.
@@ -487,6 +488,7 @@ extern int ttm_bo_init(struct ttm_bo_device *bdev,
 			struct file *persistent_swap_storage,
 			size_t acc_size,
 			struct sg_table *sg,
+			struct reservation_object *resv,
 			void (*destroy) (struct ttm_buffer_object *));
 
 /**
-- 
cgit v1.2.3


From 8e4a5da69c39788fabc9e7cf178eb62b6077c96b Mon Sep 17 00:00:00 2001
From: Sebastian Herbszt <herbszt@gmx.de>
Date: Sat, 20 Sep 2014 13:37:55 +0200
Subject: scsi: fix comment in struct Scsi_Host definition

Commit 1abf635 (scsi: use 64-bit value for 'max_luns') changed the order
of Scsi_Host members. Update the comment to reflect this.

Signed-off-by: Sebastian Herbszt <herbszt@gmx.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/scsi/scsi_host.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index d0f69a3210df..5e362489ee88 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -606,7 +606,7 @@ struct Scsi_Host {
 	/*
 	 * These three parameters can be used to allow for wide scsi,
 	 * and for host adapters that support multiple busses
-	 * The first two should be set to 1 more than the actual max id
+	 * The last two should be set to 1 more than the actual max id
 	 * or lun (e.g. 8 for SCSI parallel systems).
 	 */
 	unsigned int max_channel;
-- 
cgit v1.2.3


From 112eeaa7f87bbd2925e919486bb504f8954fa675 Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Mon, 29 Sep 2014 15:29:20 +0100
Subject: asm-generic/io.h: Fix ioport_map() for !CONFIG_GENERIC_IOMAP

The !CONFIG_GENERIC_IOMAP version of ioport_map() is wrong.  It returns a
mapped, i.e., virtual, address that can start from zero and completely
ignores the PCI_IOBASE and IO_SPACE_LIMIT that most architectures that use
!CONFIG_GENERIC_MAP define.

Tested-by: Tanmay Inamdar <tinamdar@apm.com>
Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
---
 include/asm-generic/io.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 975e1cc75edb..b8fdc57a7335 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -331,7 +331,7 @@ static inline void iounmap(void __iomem *addr)
 #ifndef CONFIG_GENERIC_IOMAP
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
-	return (void __iomem *) port;
+	return PCI_IOBASE + (port & IO_SPACE_LIMIT);
 }
 
 static inline void ioport_unmap(void __iomem *p)
-- 
cgit v1.2.3


From 41f8bba7f5552d033583777dede2df7c36e7853d Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Mon, 29 Sep 2014 15:29:21 +0100
Subject: of/pci: Add pci_register_io_range() and pci_pio_to_address()

Some architectures do not have a simple view of the PCI I/O space and
instead use a range of CPU addresses that map to bus addresses.  For some
architectures these ranges will be expressed by OF bindings in a device
tree file.

This patch introduces a pci_register_io_range() helper function with a
generic implementation that can be used by such architectures to keep track
of the I/O ranges described by the PCI bindings.  If the PCI_IOBASE macro
is not defined, that signals lack of support for PCI and we return an
error.

In order to retrieve the CPU address associated with an I/O port, a new
helper function pci_pio_to_address() is introduced.  This will search in
the list of ranges registered with pci_register_io_range() and return the
CPU address that corresponds to the given port.

[arnd: add dummy !CONFIG_OF pci_pio_to_address() to fix build errors]
Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Rob Herring <robh@kernel.org>
CC: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/address.c       | 109 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/of_address.h |   7 +++
 2 files changed, 116 insertions(+)

(limited to 'include')

diff --git a/drivers/of/address.c b/drivers/of/address.c
index e3718250d66e..758d4f04d4aa 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -5,6 +5,8 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/pci_regs.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 
 /* Max address size we deal with */
@@ -601,12 +603,119 @@ const __be32 *of_get_address(struct device_node *dev, int index, u64 *size,
 }
 EXPORT_SYMBOL(of_get_address);
 
+#ifdef PCI_IOBASE
+struct io_range {
+	struct list_head list;
+	phys_addr_t start;
+	resource_size_t size;
+};
+
+static LIST_HEAD(io_range_list);
+static DEFINE_SPINLOCK(io_range_lock);
+#endif
+
+/*
+ * Record the PCI IO range (expressed as CPU physical address + size).
+ * Return a negative value if an error has occured, zero otherwise
+ */
+int __weak pci_register_io_range(phys_addr_t addr, resource_size_t size)
+{
+	int err = 0;
+
+#ifdef PCI_IOBASE
+	struct io_range *range;
+	resource_size_t allocated_size = 0;
+
+	/* check if the range hasn't been previously recorded */
+	spin_lock(&io_range_lock);
+	list_for_each_entry(range, &io_range_list, list) {
+		if (addr >= range->start && addr + size <= range->start + size) {
+			/* range already registered, bail out */
+			goto end_register;
+		}
+		allocated_size += range->size;
+	}
+
+	/* range not registed yet, check for available space */
+	if (allocated_size + size - 1 > IO_SPACE_LIMIT) {
+		/* if it's too big check if 64K space can be reserved */
+		if (allocated_size + SZ_64K - 1 > IO_SPACE_LIMIT) {
+			err = -E2BIG;
+			goto end_register;
+		}
+
+		size = SZ_64K;
+		pr_warn("Requested IO range too big, new size set to 64K\n");
+	}
+
+	/* add the range to the list */
+	range = kzalloc(sizeof(*range), GFP_KERNEL);
+	if (!range) {
+		err = -ENOMEM;
+		goto end_register;
+	}
+
+	range->start = addr;
+	range->size = size;
+
+	list_add_tail(&range->list, &io_range_list);
+
+end_register:
+	spin_unlock(&io_range_lock);
+#endif
+
+	return err;
+}
+
+phys_addr_t pci_pio_to_address(unsigned long pio)
+{
+	phys_addr_t address = (phys_addr_t)OF_BAD_ADDR;
+
+#ifdef PCI_IOBASE
+	struct io_range *range;
+	resource_size_t allocated_size = 0;
+
+	if (pio > IO_SPACE_LIMIT)
+		return address;
+
+	spin_lock(&io_range_lock);
+	list_for_each_entry(range, &io_range_list, list) {
+		if (pio >= allocated_size && pio < allocated_size + range->size) {
+			address = range->start + pio - allocated_size;
+			break;
+		}
+		allocated_size += range->size;
+	}
+	spin_unlock(&io_range_lock);
+#endif
+
+	return address;
+}
+
 unsigned long __weak pci_address_to_pio(phys_addr_t address)
 {
+#ifdef PCI_IOBASE
+	struct io_range *res;
+	resource_size_t offset = 0;
+	unsigned long addr = -1;
+
+	spin_lock(&io_range_lock);
+	list_for_each_entry(res, &io_range_list, list) {
+		if (address >= res->start && address < res->start + res->size) {
+			addr = res->start - address + offset;
+			break;
+		}
+		offset += res->size;
+	}
+	spin_unlock(&io_range_lock);
+
+	return addr;
+#else
 	if (address > IO_SPACE_LIMIT)
 		return (unsigned long)-1;
 
 	return (unsigned long) address;
+#endif
 }
 
 static int __of_address_to_resource(struct device_node *dev,
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index fb7b7221e063..497a04356ff8 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -55,7 +55,9 @@ extern void __iomem *of_iomap(struct device_node *device, int index);
 extern const __be32 *of_get_address(struct device_node *dev, int index,
 			   u64 *size, unsigned int *flags);
 
+extern int pci_register_io_range(phys_addr_t addr, resource_size_t size);
 extern unsigned long pci_address_to_pio(phys_addr_t addr);
+extern phys_addr_t pci_pio_to_address(unsigned long pio);
 
 extern int of_pci_range_parser_init(struct of_pci_range_parser *parser,
 			struct device_node *node);
@@ -80,6 +82,11 @@ static inline const __be32 *of_get_address(struct device_node *dev, int index,
 	return NULL;
 }
 
+static inline phys_addr_t pci_pio_to_address(unsigned long pio)
+{
+	return 0;
+}
+
 static inline int of_pci_range_parser_init(struct of_pci_range_parser *parser,
 			struct device_node *node)
 {
-- 
cgit v1.2.3


From 2101e533f41a90b25bee17ce969734e26eb0eb55 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Fri, 26 Sep 2014 00:09:19 +0200
Subject: bcma: register bcma as device tree driver

This driver is used by the bcm53xx ARM SoC code. Now it is possible to
give the address of the chipcommon core in device tree and bcma will
search for all the other cores.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 Documentation/devicetree/bindings/bus/bcma.txt | 20 +++++++
 drivers/bcma/bcma_private.h                    | 14 +++++
 drivers/bcma/host_soc.c                        | 81 ++++++++++++++++++++++++++
 drivers/bcma/main.c                            | 52 ++++++++++++++++-
 include/linux/bcma/bcma.h                      |  2 +
 5 files changed, 168 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/devicetree/bindings/bus/bcma.txt

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/bus/bcma.txt b/Documentation/devicetree/bindings/bus/bcma.txt
new file mode 100644
index 000000000000..e9070c161172
--- /dev/null
+++ b/Documentation/devicetree/bindings/bus/bcma.txt
@@ -0,0 +1,20 @@
+Driver for ARM AXI Bus with Broadcom Plugins (bcma)
+
+Required properties:
+
+- compatible : brcm,bus-axi
+
+- reg : iomem address range of chipcommon core
+
+The cores on the AXI bus are automatically detected by bcma with the
+memory ranges they are using and they get registered afterwards.
+
+Example:
+
+	axi@18000000 {
+		compatible = "brcm,bus-axi";
+		reg = <0x18000000 0x1000>;
+		ranges = <0x00000000 0x18000000 0x00100000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+	};
diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index b40be43c6f31..b6412b2d748d 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -88,6 +88,20 @@ extern int __init bcma_host_pci_init(void);
 extern void __exit bcma_host_pci_exit(void);
 #endif /* CONFIG_BCMA_HOST_PCI */
 
+/* host_soc.c */
+#if defined(CONFIG_BCMA_HOST_SOC) && defined(CONFIG_OF)
+extern int __init bcma_host_soc_register_driver(void);
+extern void __exit bcma_host_soc_unregister_driver(void);
+#else
+static inline int __init bcma_host_soc_register_driver(void)
+{
+	return 0;
+}
+static inline void __exit bcma_host_soc_unregister_driver(void)
+{
+}
+#endif /* CONFIG_BCMA_HOST_SOC && CONFIG_OF */
+
 /* driver_pci.c */
 u32 bcma_pcie_read(struct bcma_drv_pci *pc, u32 address);
 
diff --git a/drivers/bcma/host_soc.c b/drivers/bcma/host_soc.c
index 718e054dd727..335cbcfd945b 100644
--- a/drivers/bcma/host_soc.c
+++ b/drivers/bcma/host_soc.c
@@ -7,6 +7,9 @@
 
 #include "bcma_private.h"
 #include "scan.h"
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
 #include <linux/bcma/bcma.h>
 #include <linux/bcma/bcma_soc.h>
 
@@ -176,6 +179,7 @@ int __init bcma_host_soc_register(struct bcma_soc *soc)
 	/* Host specific */
 	bus->hosttype = BCMA_HOSTTYPE_SOC;
 	bus->ops = &bcma_host_soc_ops;
+	bus->host_pdev = NULL;
 
 	/* Initialize struct, detect chip */
 	bcma_init_bus(bus);
@@ -195,3 +199,80 @@ int __init bcma_host_soc_init(struct bcma_soc *soc)
 
 	return err;
 }
+
+#ifdef CONFIG_OF
+static int bcma_host_soc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct bcma_bus *bus;
+	int err;
+
+	/* Alloc */
+	bus = devm_kzalloc(dev, sizeof(*bus), GFP_KERNEL);
+	if (!bus)
+		return -ENOMEM;
+
+	/* Map MMIO */
+	bus->mmio = of_iomap(np, 0);
+	if (!bus->mmio)
+		return -ENOMEM;
+
+	/* Host specific */
+	bus->hosttype = BCMA_HOSTTYPE_SOC;
+	bus->ops = &bcma_host_soc_ops;
+	bus->host_pdev = pdev;
+
+	/* Initialize struct, detect chip */
+	bcma_init_bus(bus);
+
+	/* Register */
+	err = bcma_bus_register(bus);
+	if (err)
+		goto err_unmap_mmio;
+
+	platform_set_drvdata(pdev, bus);
+
+	return err;
+
+err_unmap_mmio:
+	iounmap(bus->mmio);
+	return err;
+}
+
+static int bcma_host_soc_remove(struct platform_device *pdev)
+{
+	struct bcma_bus *bus = platform_get_drvdata(pdev);
+
+	bcma_bus_unregister(bus);
+	iounmap(bus->mmio);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static const struct of_device_id bcma_host_soc_of_match[] = {
+	{ .compatible = "brcm,bus-axi", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, bcma_host_soc_of_match);
+
+static struct platform_driver bcma_host_soc_driver = {
+	.driver = {
+		.name = "bcma-host-soc",
+		.of_match_table = bcma_host_soc_of_match,
+	},
+	.probe		= bcma_host_soc_probe,
+	.remove		= bcma_host_soc_remove,
+};
+
+int __init bcma_host_soc_register_driver(void)
+{
+	return platform_driver_register(&bcma_host_soc_driver);
+}
+
+void __exit bcma_host_soc_unregister_driver(void)
+{
+	platform_driver_unregister(&bcma_host_soc_driver);
+}
+#endif /* CONFIG_OF */
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index c421403cab43..d1656c2f70af 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -10,6 +10,7 @@
 #include <linux/platform_device.h>
 #include <linux/bcma/bcma.h>
 #include <linux/slab.h>
+#include <linux/of_address.h>
 
 MODULE_DESCRIPTION("Broadcom's specific AMBA driver");
 MODULE_LICENSE("GPL");
@@ -131,6 +132,43 @@ static bool bcma_is_core_needed_early(u16 core_id)
 	return false;
 }
 
+#ifdef CONFIG_OF
+static struct device_node *bcma_of_find_child_device(struct platform_device *parent,
+						     struct bcma_device *core)
+{
+	struct device_node *node;
+	u64 size;
+	const __be32 *reg;
+
+	if (!parent || !parent->dev.of_node)
+		return NULL;
+
+	for_each_child_of_node(parent->dev.of_node, node) {
+		reg = of_get_address(node, 0, &size, NULL);
+		if (!reg)
+			continue;
+		if (of_translate_address(node, reg) == core->addr)
+			return node;
+	}
+	return NULL;
+}
+
+static void bcma_of_fill_device(struct platform_device *parent,
+				struct bcma_device *core)
+{
+	struct device_node *node;
+
+	node = bcma_of_find_child_device(parent, core);
+	if (node)
+		core->dev.of_node = node;
+}
+#else
+static void bcma_of_fill_device(struct platform_device *parent,
+				struct bcma_device *core)
+{
+}
+#endif /* CONFIG_OF */
+
 static void bcma_register_core(struct bcma_bus *bus, struct bcma_device *core)
 {
 	int err;
@@ -147,7 +185,13 @@ static void bcma_register_core(struct bcma_bus *bus, struct bcma_device *core)
 		break;
 	case BCMA_HOSTTYPE_SOC:
 		core->dev.dma_mask = &core->dev.coherent_dma_mask;
-		core->dma_dev = &core->dev;
+		if (bus->host_pdev) {
+			core->dma_dev = &bus->host_pdev->dev;
+			core->dev.parent = &bus->host_pdev->dev;
+			bcma_of_fill_device(bus->host_pdev, core);
+		} else {
+			core->dma_dev = &core->dev;
+		}
 		break;
 	case BCMA_HOSTTYPE_SDIO:
 		break;
@@ -528,6 +572,11 @@ static int __init bcma_modinit(void)
 	if (err)
 		return err;
 
+	err = bcma_host_soc_register_driver();
+	if (err) {
+		pr_err("SoC host initialization failed\n");
+		err = 0;
+	}
 #ifdef CONFIG_BCMA_HOST_PCI
 	err = bcma_host_pci_init();
 	if (err) {
@@ -545,6 +594,7 @@ static void __exit bcma_modexit(void)
 #ifdef CONFIG_BCMA_HOST_PCI
 	bcma_host_pci_exit();
 #endif
+	bcma_host_soc_unregister_driver();
 	bus_unregister(&bcma_bus_type);
 }
 module_exit(bcma_modexit)
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index 634597917670..729f48e6b20b 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -323,6 +323,8 @@ struct bcma_bus {
 		struct pci_dev *host_pci;
 		/* Pointer to the SDIO device (only for BCMA_HOSTTYPE_SDIO) */
 		struct sdio_func *host_sdio;
+		/* Pointer to platform device (only for BCMA_HOSTTYPE_SOC) */
+		struct platform_device *host_pdev;
 	};
 
 	struct bcma_chipinfo chipinfo;
-- 
cgit v1.2.3


From 705f1c869d577c8055736dd02501f26a2507dd5b Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sun, 28 Sep 2014 00:46:06 +0200
Subject: ipv6: remove rt6i_genid

Eric Dumazet noticed that all no-nonexthop or no-gateway routes which
are already marked DST_HOST (e.g. input routes routes) will always be
invalidated during sk_dst_check. Thus per-socket dst caching absolutely
had no effect and early demuxing had no effect.

Thus this patch removes rt6i_genid: fn_sernum already gets modified during
add operations, so we only must ensure we mutate fn_sernum during ipv6
address remove operations. This is a fairly cost extensive operations,
but address removal should not happen that often. Also our mtu update
functions do the same and we heard no complains so far. xfrm policy
changes also cause a call into fib6_flush_trees. Also plug a hole in
rt6_info (no cacheline changes).

I verified via tracing that this change has effect.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: YOSHIFUJI Hideaki <hideaki@yoshifuji.org>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h       |  5 +----
 include/net/net_namespace.h | 20 +++-----------------
 net/ipv6/addrconf.c         |  3 ++-
 net/ipv6/addrconf_core.c    |  7 +++++++
 net/ipv6/ip6_fib.c          | 20 ++++++++++++++++++++
 net/ipv6/route.c            |  4 ----
 6 files changed, 33 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 9bcb220bd4ad..cf485f9aa563 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -114,16 +114,13 @@ struct rt6_info {
 	u32				rt6i_flags;
 	struct rt6key			rt6i_src;
 	struct rt6key			rt6i_prefsrc;
-	u32				rt6i_metric;
 
 	struct inet6_dev		*rt6i_idev;
 	unsigned long			_rt6i_peer;
 
-	u32				rt6i_genid;
-
+	u32				rt6i_metric;
 	/* more non-fragment space at head required */
 	unsigned short			rt6i_nfheader_len;
-
 	u8				rt6i_protocol;
 };
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 361d26077196..e0d64667a4b3 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -352,26 +352,12 @@ static inline void rt_genid_bump_ipv4(struct net *net)
 	atomic_inc(&net->ipv4.rt_genid);
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
-static inline int rt_genid_ipv6(struct net *net)
-{
-	return atomic_read(&net->ipv6.rt_genid);
-}
-
-static inline void rt_genid_bump_ipv6(struct net *net)
-{
-	atomic_inc(&net->ipv6.rt_genid);
-}
-#else
-static inline int rt_genid_ipv6(struct net *net)
-{
-	return 0;
-}
-
+extern void (*__fib6_flush_trees)(struct net *net);
 static inline void rt_genid_bump_ipv6(struct net *net)
 {
+	if (__fib6_flush_trees)
+		__fib6_flush_trees(net);
 }
-#endif
 
 #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
 static inline struct netns_ieee802154_lowpan *
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3342ee64f2e3..3e118dfddd02 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4780,10 +4780,11 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 
 		if (ip6_del_rt(ifp->rt))
 			dst_free(&ifp->rt->dst);
+
+		rt_genid_bump_ipv6(net);
 		break;
 	}
 	atomic_inc(&net->ipv6.dev_addr_genid);
-	rt_genid_bump_ipv6(net);
 }
 
 static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index e6960457f625..98cc4cd570e2 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -8,6 +8,13 @@
 #include <net/addrconf.h>
 #include <net/ip.h>
 
+/* if ipv6 module registers this function is used by xfrm to force all
+ * sockets to relookup their nodes - this is fairly expensive, be
+ * careful
+ */
+void (*__fib6_flush_trees)(struct net *);
+EXPORT_SYMBOL(__fib6_flush_trees);
+
 #define IPV6_ADDR_SCOPE_TYPE(scope)	((scope) << 16)
 
 static inline unsigned int ipv6_addr_scope2type(unsigned int scope)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 76b7f5ee8f4c..97b9fa8de377 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1605,6 +1605,24 @@ static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
 	fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL);
 }
 
+static int fib6_update_sernum(struct rt6_info *rt, void *arg)
+{
+	__u32 sernum = *(__u32 *)arg;
+
+	if (rt->rt6i_node &&
+	    rt->rt6i_node->fn_sernum != sernum)
+		rt->rt6i_node->fn_sernum = sernum;
+
+	return 0;
+}
+
+static void fib6_flush_trees(struct net *net)
+{
+	__u32 new_sernum = fib6_new_sernum();
+
+	fib6_clean_all(net, fib6_update_sernum, &new_sernum);
+}
+
 /*
  *	Garbage collection
  */
@@ -1788,6 +1806,8 @@ int __init fib6_init(void)
 			      NULL);
 	if (ret)
 		goto out_unregister_subsys;
+
+	__fib6_flush_trees = fib6_flush_trees;
 out:
 	return ret;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f23fbd28a501..bafde82324c5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -314,7 +314,6 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
 
 		memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
 		rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
-		rt->rt6i_genid = rt_genid_ipv6(net);
 		INIT_LIST_HEAD(&rt->rt6i_siblings);
 	}
 	return rt;
@@ -1098,9 +1097,6 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 	 * DST_OBSOLETE_FORCE_CHK which forces validation calls down
 	 * into this function always.
 	 */
-	if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev)))
-		return NULL;
-
 	if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
 		return NULL;
 
-- 
cgit v1.2.3


From e0fa975d85b2ec300b3d69f08bc4933f79316651 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 30 Sep 2014 02:25:42 +0200
Subject: ACPICA: Introduce acpi_enable_all_wakeup_gpes()

Add a routine for host OSes to enable all wakeup GPEs and disable
all of the non-wakeup ones at the same time.

It will be used for the handling of GPE wakeup from suspend-to-idle
in Linux.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/evxfgpe.c | 32 ++++++++++++++++++++++++++++++++
 include/acpi/acpixf.h         |  1 +
 2 files changed, 33 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index 0cf159cc6e6d..56710a03c9b0 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -596,6 +596,38 @@ acpi_status acpi_enable_all_runtime_gpes(void)
 
 ACPI_EXPORT_SYMBOL(acpi_enable_all_runtime_gpes)
 
+/******************************************************************************
+ *
+ * FUNCTION:    acpi_enable_all_wakeup_gpes
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Enable all "wakeup" GPEs and disable all of the other GPEs, in
+ *              all GPE blocks.
+ *
+ ******************************************************************************/
+
+acpi_status acpi_enable_all_wakeup_gpes(void)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_enable_all_wakeup_gpes);
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	status = acpi_hw_enable_all_wakeup_gpes();
+	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
+
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_enable_all_wakeup_gpes)
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_install_gpe_block
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index dc9d037d3055..9fc1d71c82bc 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -692,6 +692,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 						     *event_status))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))
 
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_get_gpe_device(u32 gpe_index,
-- 
cgit v1.2.3


From 2a8a8ce651d3a88fdf83e2ed15633c8d19292108 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 30 Sep 2014 02:21:34 +0200
Subject: PM / sleep: Export dpm_suspend_late/noirq() and
 dpm_resume_early/noirq()

Subsequent change sets will add platform-related operations between
dpm_suspend_late() and dpm_suspend_noirq() as well as between
dpm_resume_noirq() and dpm_resume_early() in suspend_enter(), so
export these functions for suspend_enter() to be able to call them
separately and split the invocations of dpm_suspend_end() and
dpm_resume_start() in there accordingly.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/main.c |  8 ++++----
 include/linux/pm.h        |  4 ++++
 kernel/power/suspend.c    | 14 +++++++++++---
 3 files changed, 19 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index b67d9aef9fe4..44973196d3fd 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -540,7 +540,7 @@ static void async_resume_noirq(void *data, async_cookie_t cookie)
  * Call the "noirq" resume handlers for all devices in dpm_noirq_list and
  * enable device drivers to receive interrupts.
  */
-static void dpm_resume_noirq(pm_message_t state)
+void dpm_resume_noirq(pm_message_t state)
 {
 	struct device *dev;
 	ktime_t starttime = ktime_get();
@@ -662,7 +662,7 @@ static void async_resume_early(void *data, async_cookie_t cookie)
  * dpm_resume_early - Execute "early resume" callbacks for all devices.
  * @state: PM transition of the system being carried out.
  */
-static void dpm_resume_early(pm_message_t state)
+void dpm_resume_early(pm_message_t state)
 {
 	struct device *dev;
 	ktime_t starttime = ktime_get();
@@ -1093,7 +1093,7 @@ static int device_suspend_noirq(struct device *dev)
  * Prevent device drivers from receiving interrupts and call the "noirq" suspend
  * handlers for all non-sysdev devices.
  */
-static int dpm_suspend_noirq(pm_message_t state)
+int dpm_suspend_noirq(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	int error = 0;
@@ -1232,7 +1232,7 @@ static int device_suspend_late(struct device *dev)
  * dpm_suspend_late - Execute "late suspend" callbacks for all devices.
  * @state: PM transition of the system being carried out.
  */
-static int dpm_suspend_late(pm_message_t state)
+int dpm_suspend_late(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	int error = 0;
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 72c0fe098a27..e1c00b7ee913 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -679,12 +679,16 @@ struct dev_pm_domain {
 extern void device_pm_lock(void);
 extern void dpm_resume_start(pm_message_t state);
 extern void dpm_resume_end(pm_message_t state);
+extern void dpm_resume_noirq(pm_message_t state);
+extern void dpm_resume_early(pm_message_t state);
 extern void dpm_resume(pm_message_t state);
 extern void dpm_complete(pm_message_t state);
 
 extern void device_pm_unlock(void);
 extern int dpm_suspend_end(pm_message_t state);
 extern int dpm_suspend_start(pm_message_t state);
+extern int dpm_suspend_noirq(pm_message_t state);
+extern int dpm_suspend_late(pm_message_t state);
 extern int dpm_suspend(pm_message_t state);
 extern int dpm_prepare(pm_message_t state);
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index e837dd6783c6..58ae98b7dc2b 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -265,11 +265,16 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	if (error)
 		goto Platform_finish;
 
-	error = dpm_suspend_end(PMSG_SUSPEND);
+	error = dpm_suspend_late(PMSG_SUSPEND);
 	if (error) {
-		printk(KERN_ERR "PM: Some devices failed to power down\n");
+		printk(KERN_ERR "PM: late suspend of devices failed\n");
 		goto Platform_finish;
 	}
+	error = dpm_suspend_noirq(PMSG_SUSPEND);
+	if (error) {
+		printk(KERN_ERR "PM: noirq suspend of devices failed\n");
+		goto Devices_early_resume;
+	}
 	error = platform_suspend_prepare_late(state);
 	if (error)
 		goto Platform_wake;
@@ -319,7 +324,10 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 
  Platform_wake:
 	platform_suspend_wake(state);
-	dpm_resume_start(PMSG_RESUME);
+	dpm_resume_noirq(PMSG_RESUME);
+
+ Devices_early_resume:
+	dpm_resume_early(PMSG_RESUME);
 
  Platform_finish:
 	platform_suspend_finish(state);
-- 
cgit v1.2.3


From a8d46b9e4e487301affe84fa53de40b890898604 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 30 Sep 2014 02:29:01 +0200
Subject: ACPI / sleep: Rework the handling of ACPI GPE wakeup from
 suspend-to-idle

The ACPI GPE wakeup from suspend-to-idle is currently based on using
the IRQF_NO_SUSPEND flag for the ACPI SCI, but that is problematic
for a couple of reasons.  First, in principle the ACPI SCI may be
shared and IRQF_NO_SUSPEND does not really work well with shared
interrupts.  Second, it may require the ACPI subsystem to special-case
the handling of device notifications depending on whether or not
they are received during suspend-to-idle in some places which would
lead to fragile code.  Finally, it's better the handle ACPI wakeup
interrupts consistently with wakeup interrupts from other sources.

For this reason, remove the IRQF_NO_SUSPEND flag from the ACPI SCI
and use enable_irq_wake()/disable_irq_wake() with it instead, which
requires two additional platform hooks to be added to struct
platform_freeze_ops.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/osl.c      |  2 +-
 drivers/acpi/sleep.c    | 16 ++++++++++++++++
 include/linux/suspend.h |  2 ++
 kernel/power/suspend.c  | 21 ++++++++++++++++++++-
 4 files changed, 39 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 3abe9b223ba7..5ca29b5af8d1 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -825,7 +825,7 @@ acpi_os_install_interrupt_handler(u32 gsi, acpi_osd_handler handler,
 
 	acpi_irq_handler = handler;
 	acpi_irq_context = context;
-	if (request_irq(irq, acpi_irq, IRQF_SHARED | IRQF_NO_SUSPEND, "acpi", acpi_irq)) {
+	if (request_irq(irq, acpi_irq, IRQF_SHARED, "acpi", acpi_irq)) {
 		printk(KERN_ERR PREFIX "SCI (IRQ%d) allocation failed\n", irq);
 		acpi_irq_handler = NULL;
 		return AE_NOT_ACQUIRED;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 54da4a3fe65e..05a31b573fc3 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -14,6 +14,7 @@
 #include <linux/irq.h>
 #include <linux/dmi.h>
 #include <linux/device.h>
+#include <linux/interrupt.h>
 #include <linux/suspend.h>
 #include <linux/reboot.h>
 #include <linux/acpi.h>
@@ -626,6 +627,19 @@ static int acpi_freeze_begin(void)
 	return 0;
 }
 
+static int acpi_freeze_prepare(void)
+{
+	acpi_enable_all_wakeup_gpes();
+	enable_irq_wake(acpi_gbl_FADT.sci_interrupt);
+	return 0;
+}
+
+static void acpi_freeze_restore(void)
+{
+	disable_irq_wake(acpi_gbl_FADT.sci_interrupt);
+	acpi_enable_all_runtime_gpes();
+}
+
 static void acpi_freeze_end(void)
 {
 	acpi_scan_lock_release();
@@ -633,6 +647,8 @@ static void acpi_freeze_end(void)
 
 static const struct platform_freeze_ops acpi_freeze_ops = {
 	.begin = acpi_freeze_begin,
+	.prepare = acpi_freeze_prepare,
+	.restore = acpi_freeze_restore,
 	.end = acpi_freeze_end,
 };
 
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 06a9910827c2..3388c1b6f7d8 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -189,6 +189,8 @@ struct platform_suspend_ops {
 
 struct platform_freeze_ops {
 	int (*begin)(void);
+	int (*prepare)(void);
+	void (*restore)(void);
 	void (*end)(void);
 };
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index a25e768d92b5..4ca9a33ff620 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -144,6 +144,12 @@ static int platform_suspend_prepare(suspend_state_t state)
 		suspend_ops->prepare() : 0;
 }
 
+static int platform_suspend_prepare_late(suspend_state_t state)
+{
+	return state == PM_SUSPEND_FREEZE && freeze_ops->prepare ?
+		freeze_ops->prepare() : 0;
+}
+
 static int platform_suspend_prepare_noirq(suspend_state_t state)
 {
 	return state != PM_SUSPEND_FREEZE && suspend_ops->prepare_late ?
@@ -156,6 +162,12 @@ static void platform_resume_noirq(suspend_state_t state)
 		suspend_ops->wake();
 }
 
+static void platform_resume_early(suspend_state_t state)
+{
+	if (state == PM_SUSPEND_FREEZE && freeze_ops->restore)
+		freeze_ops->restore();
+}
+
 static void platform_resume_finish(suspend_state_t state)
 {
 	if (state != PM_SUSPEND_FREEZE && suspend_ops->finish)
@@ -270,10 +282,14 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 		printk(KERN_ERR "PM: late suspend of devices failed\n");
 		goto Platform_finish;
 	}
+	error = platform_suspend_prepare_late(state);
+	if (error)
+		goto Devices_early_resume;
+
 	error = dpm_suspend_noirq(PMSG_SUSPEND);
 	if (error) {
 		printk(KERN_ERR "PM: noirq suspend of devices failed\n");
-		goto Devices_early_resume;
+		goto Platform_early_resume;
 	}
 	error = platform_suspend_prepare_noirq(state);
 	if (error)
@@ -326,6 +342,9 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	platform_resume_noirq(state);
 	dpm_resume_noirq(PMSG_RESUME);
 
+ Platform_early_resume:
+	platform_resume_early(state);
+
  Devices_early_resume:
 	dpm_resume_early(PMSG_RESUME);
 
-- 
cgit v1.2.3


From 83bbde1cc0ec9d156b9271e29ffe0dc89c687feb Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Mon, 29 Sep 2014 15:29:24 +0100
Subject: of/pci: Move of_pci_range_to_resource() to of/address.c

We need to enhance of_pci_range_to_resources() enough that it won't make
sense for it to be inline anymore.  Move it to drivers/of/address.c, under
#ifdef CONFIG_PCI.

of_address.h previously implemented of_pci_range_to_resources()
unconditionally, regardless of any config options.  The implementation in
address.c is defined only when CONFIG_OF_ADDRESS=y and CONFIG_PCI=y,
so add a dummy version to avoid build errors when CONFIG_OF or
CONFIG_OF_ADDRESS is not defined.

[bhelgaas: drop extra detail from changelog, move def under CONFIG_PCI,
add dummy of_pci_range_to_resource() for build errors (from Arnd)]
Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Grant Likely <grant.likely@linaro.org>
CC: Rob Herring <robh+dt@kernel.org>
CC: Arnd Bergmann <arnd@arndb.de>
CC: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/of/address.c       |  9 +++++++++
 include/linux/of_address.h | 20 +++++++++-----------
 2 files changed, 18 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/of/address.c b/drivers/of/address.c
index 758d4f04d4aa..327a57410797 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -295,6 +295,15 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser,
 }
 EXPORT_SYMBOL_GPL(of_pci_range_parser_one);
 
+void of_pci_range_to_resource(struct of_pci_range *range,
+			      struct device_node *np, struct resource *res)
+{
+	res->flags = range->flags;
+	res->start = range->cpu_addr;
+	res->end = range->cpu_addr + range->size - 1;
+	res->parent = res->child = res->sibling = NULL;
+	res->name = np->full_name;
+}
 #endif /* CONFIG_PCI */
 
 /*
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index 497a04356ff8..a38e1c846c23 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -23,17 +23,6 @@ struct of_pci_range {
 #define for_each_of_pci_range(parser, range) \
 	for (; of_pci_range_parser_one(parser, range);)
 
-static inline void of_pci_range_to_resource(struct of_pci_range *range,
-					    struct device_node *np,
-					    struct resource *res)
-{
-	res->flags = range->flags;
-	res->start = range->cpu_addr;
-	res->end = range->cpu_addr + range->size - 1;
-	res->parent = res->child = res->sibling = NULL;
-	res->name = np->full_name;
-}
-
 /* Translate a DMA address from device space to CPU space */
 extern u64 of_translate_dma_address(struct device_node *dev,
 				    const __be32 *in_addr);
@@ -145,6 +134,9 @@ extern const __be32 *of_get_pci_address(struct device_node *dev, int bar_no,
 			       u64 *size, unsigned int *flags);
 extern int of_pci_address_to_resource(struct device_node *dev, int bar,
 				      struct resource *r);
+extern void of_pci_range_to_resource(struct of_pci_range *range,
+				     struct device_node *np,
+				     struct resource *res);
 #else /* CONFIG_OF_ADDRESS && CONFIG_PCI */
 static inline int of_pci_address_to_resource(struct device_node *dev, int bar,
 				             struct resource *r)
@@ -157,6 +149,12 @@ static inline const __be32 *of_get_pci_address(struct device_node *dev,
 {
 	return NULL;
 }
+static inline void of_pci_range_to_resource(struct of_pci_range *range,
+					    struct device_node *np,
+					    struct resource *res)
+{
+	return -ENOSYS;
+}
 #endif /* CONFIG_OF_ADDRESS && CONFIG_PCI */
 
 #endif /* __OF_ADDRESS_H */
-- 
cgit v1.2.3


From bda003036684b9779fca2b3d457621eaff9bcd0a Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Wed, 30 Jul 2014 22:50:59 +0200
Subject: clk: add pxa clocks infrastructure

Add a the common code used by all PXA variants.

This is the first step in the transition from architecture defined
clocks (in arch/arm/mach-pxa) towards clock framework. The goal is to
have the same features (and not all the features) of the existing
clocks, and enable the transition of PXA to device-tree.

All PXA rely on a "CKEN" type clock, which :
 - has a gate (bit in CKEN register)
 - is generated from a PLL, generally divided
 - has an alternate low power clock

Each variant will specialize the CKEN clock :
 - pxa25x have no low power clock
 - pxa27x in low power use always the 13 MHz ring oscillator
 - pxa3xx in low power have specific dividers for each clock

The device-tree provides a list of CLK_* (ex: CLK_USB or CLK_I2C) to get
a handle on the clock. While pxa-clock.h will describe all the clocks of
all the variants, each variant will only use a subset of it.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 drivers/clk/Makefile                  |   1 +
 drivers/clk/pxa/Makefile              |   1 +
 drivers/clk/pxa/clk-pxa.c             |  97 ++++++++++++++++++++++++++++++
 drivers/clk/pxa/clk-pxa.h             | 107 ++++++++++++++++++++++++++++++++++
 include/dt-bindings/clock/pxa-clock.h |  77 ++++++++++++++++++++++++
 5 files changed, 283 insertions(+)
 create mode 100644 drivers/clk/pxa/Makefile
 create mode 100644 drivers/clk/pxa/clk-pxa.c
 create mode 100644 drivers/clk/pxa/clk-pxa.h
 create mode 100644 include/dt-bindings/clock/pxa-clock.h

(limited to 'include')

diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index f537a0b1f798..7891e4edaa07 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_ARCH_MMP)			+= mmp/
 endif
 obj-$(CONFIG_PLAT_ORION)		+= mvebu/
 obj-$(CONFIG_ARCH_MXS)			+= mxs/
+obj-$(CONFIG_ARCH_PXA)			+= pxa/
 obj-$(CONFIG_COMMON_CLK_QCOM)		+= qcom/
 obj-$(CONFIG_ARCH_ROCKCHIP)		+= rockchip/
 obj-$(CONFIG_COMMON_CLK_SAMSUNG)	+= samsung/
diff --git a/drivers/clk/pxa/Makefile b/drivers/clk/pxa/Makefile
new file mode 100644
index 000000000000..cb2bd8ff53da
--- /dev/null
+++ b/drivers/clk/pxa/Makefile
@@ -0,0 +1 @@
+obj-y				+= clk-pxa.o
diff --git a/drivers/clk/pxa/clk-pxa.c b/drivers/clk/pxa/clk-pxa.c
new file mode 100644
index 000000000000..ef3c05389c0a
--- /dev/null
+++ b/drivers/clk/pxa/clk-pxa.c
@@ -0,0 +1,97 @@
+/*
+ * Marvell PXA family clocks
+ *
+ * Copyright (C) 2014 Robert Jarzmik
+ *
+ * Common clock code for PXA clocks ("CKEN" type clocks + DT)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ */
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/of.h>
+
+#include <dt-bindings/clock/pxa-clock.h>
+#include "clk-pxa.h"
+
+DEFINE_SPINLOCK(lock);
+
+static struct clk *pxa_clocks[CLK_MAX];
+static struct clk_onecell_data onecell_data = {
+	.clks = pxa_clocks,
+	.clk_num = CLK_MAX,
+};
+
+#define to_pxa_clk(_hw) container_of(_hw, struct pxa_clk_cken, hw)
+
+static unsigned long cken_recalc_rate(struct clk_hw *hw,
+				      unsigned long parent_rate)
+{
+	struct pxa_clk_cken *pclk = to_pxa_clk(hw);
+	struct clk_fixed_factor *fix;
+
+	if (!pclk->is_in_low_power || pclk->is_in_low_power())
+		fix = &pclk->lp;
+	else
+		fix = &pclk->hp;
+	fix->hw.clk = hw->clk;
+	return clk_fixed_factor_ops.recalc_rate(&fix->hw, parent_rate);
+}
+
+static struct clk_ops cken_rate_ops = {
+	.recalc_rate = cken_recalc_rate,
+};
+
+static u8 cken_get_parent(struct clk_hw *hw)
+{
+	struct pxa_clk_cken *pclk = to_pxa_clk(hw);
+
+	if (!pclk->is_in_low_power)
+		return 0;
+	return pclk->is_in_low_power() ? 0 : 1;
+}
+
+static struct clk_ops cken_mux_ops = {
+	.get_parent = cken_get_parent,
+	.set_parent = dummy_clk_set_parent,
+};
+
+void __init clkdev_pxa_register(int ckid, const char *con_id,
+				const char *dev_id, struct clk *clk)
+{
+	if (!IS_ERR(clk) && (ckid != CLK_NONE))
+		pxa_clocks[ckid] = clk;
+	if (!IS_ERR(clk))
+		clk_register_clkdev(clk, con_id, dev_id);
+}
+
+int __init clk_pxa_cken_init(struct pxa_clk_cken *clks, int nb_clks)
+{
+	int i;
+	struct pxa_clk_cken *pclk;
+	struct clk *clk;
+
+	for (i = 0; i < nb_clks; i++) {
+		pclk = clks + i;
+		pclk->gate.lock = &lock;
+		clk = clk_register_composite(NULL, pclk->name,
+					     pclk->parent_names, 2,
+					     &pclk->hw, &cken_mux_ops,
+					     &pclk->hw, &cken_rate_ops,
+					     &pclk->gate.hw, &clk_gate_ops,
+					     pclk->flags);
+		clkdev_pxa_register(pclk->ckid, pclk->con_id, pclk->dev_id,
+				    clk);
+	}
+	return 0;
+}
+
+static void __init pxa_dt_clocks_init(struct device_node *np)
+{
+	of_clk_add_provider(np, of_clk_src_onecell_get, &onecell_data);
+}
+CLK_OF_DECLARE(pxa_clks, "marvell,pxa-clocks", pxa_dt_clocks_init);
diff --git a/drivers/clk/pxa/clk-pxa.h b/drivers/clk/pxa/clk-pxa.h
new file mode 100644
index 000000000000..5fe219d06b49
--- /dev/null
+++ b/drivers/clk/pxa/clk-pxa.h
@@ -0,0 +1,107 @@
+/*
+ * Marvell PXA family clocks
+ *
+ * Copyright (C) 2014 Robert Jarzmik
+ *
+ * Common clock code for PXA clocks ("CKEN" type clocks + DT)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ */
+#ifndef _CLK_PXA_
+#define _CLK_PXA_
+
+#define PARENTS(name) \
+	static const char *name ## _parents[] __initconst
+#define MUX_RO_RATE_RO_OPS(name, clk_name)			\
+	static struct clk_hw name ## _mux_hw;			\
+	static struct clk_hw name ## _rate_hw;			\
+	static struct clk_ops name ## _mux_ops = {		\
+		.get_parent = name ## _get_parent,		\
+		.set_parent = dummy_clk_set_parent,		\
+	};							\
+	static struct clk_ops name ## _rate_ops = {		\
+		.recalc_rate = name ## _get_rate,		\
+	};							\
+	static struct clk *clk_register_ ## name(void)		\
+	{							\
+		return clk_register_composite(NULL, clk_name,	\
+			name ## _parents,			\
+			ARRAY_SIZE(name ## _parents),		\
+			&name ## _mux_hw, &name ## _mux_ops,	\
+			&name ## _rate_hw, &name ## _rate_ops,	\
+			NULL, NULL, CLK_GET_RATE_NOCACHE);	\
+	}
+
+#define RATE_RO_OPS(name, clk_name)			\
+	static struct clk_hw name ## _rate_hw;			\
+	static struct clk_ops name ## _rate_ops = {		\
+		.recalc_rate = name ## _get_rate,		\
+	};							\
+	static struct clk *clk_register_ ## name(void)		\
+	{							\
+		return clk_register_composite(NULL, clk_name,	\
+			name ## _parents,			\
+			ARRAY_SIZE(name ## _parents),		\
+			NULL, NULL,				\
+			&name ## _rate_hw, &name ## _rate_ops,	\
+			NULL, NULL, CLK_GET_RATE_NOCACHE);	\
+	}
+
+/*
+ * CKEN clock type
+ * This clock takes it source from 2 possible parents :
+ *  - a low power parent
+ *  - a normal parent
+ *
+ *  +------------+     +-----------+
+ *  |  Low Power | --- | x mult_lp |
+ *  |    Clock   |     | / div_lp  |\
+ *  +------------+     +-----------+ \+-----+   +-----------+
+ *                                    | Mux |---| CKEN gate |
+ *  +------------+     +-----------+ /+-----+   +-----------+
+ *  | High Power |     | x mult_hp |/
+ *  |    Clock   | --- | / div_hp  |
+ *  +------------+     +-----------+
+ */
+struct pxa_clk_cken {
+	struct clk_hw hw;
+	int ckid;
+	const char *name;
+	const char *dev_id;
+	const char *con_id;
+	const char **parent_names;
+	struct clk_fixed_factor lp;
+	struct clk_fixed_factor hp;
+	struct clk_gate gate;
+	bool (*is_in_low_power)(void);
+	const unsigned long flags;
+};
+
+#define PXA_CKEN(_dev_id, _con_id, _name, parents, _mult_lp, _div_lp,	\
+		 _mult_hp, _div_hp, is_lp, _cken_reg, _cken_bit, flag)	\
+	{ .ckid = CLK_ ## _name, .name = #_name,			\
+	  .dev_id = _dev_id, .con_id = _con_id,	.parent_names = parents,\
+	  .lp = { .mult = _mult_lp, .div = _div_lp },			\
+	  .hp = { .mult = _mult_hp, .div = _div_hp },			\
+	  .is_in_low_power = is_lp,					\
+	  .gate = { .reg = (void __iomem *)_cken_reg, .bit_idx = _cken_bit }, \
+	  .flags = flag,						\
+	}
+#define PXA_CKEN_1RATE(dev_id, con_id, name, parents, cken_reg,		\
+			    cken_bit, flag)				\
+	PXA_CKEN(dev_id, con_id, name, parents, 1, 1, 1, 1,		\
+		 NULL, cken_reg, cken_bit, flag)
+
+static int dummy_clk_set_parent(struct clk_hw *hw, u8 index)
+{
+	return 0;
+}
+
+extern void clkdev_pxa_register(int ckid, const char *con_id,
+				const char *dev_id, struct clk *clk);
+extern int clk_pxa_cken_init(struct pxa_clk_cken *clks, int nb_clks);
+
+#endif
diff --git a/include/dt-bindings/clock/pxa-clock.h b/include/dt-bindings/clock/pxa-clock.h
new file mode 100644
index 000000000000..e65803b1dc7e
--- /dev/null
+++ b/include/dt-bindings/clock/pxa-clock.h
@@ -0,0 +1,77 @@
+/*
+ * Inspired by original work from pxa2xx-regs.h by Nicolas Pitre
+ * Copyright (C) 2014 Robert Jarzmik
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_PXA2XX_H__
+#define __DT_BINDINGS_CLOCK_PXA2XX_H__
+
+#define CLK_NONE 0
+#define CLK_1WIRE 1
+#define CLK_AC97 2
+#define CLK_AC97CONF 3
+#define CLK_ASSP 4
+#define CLK_BOOT 5
+#define CLK_BTUART 6
+#define CLK_CAMERA 7
+#define CLK_CIR 8
+#define CLK_CORE 9
+#define CLK_DMC 10
+#define CLK_FFUART 11
+#define CLK_FICP 12
+#define CLK_GPIO 13
+#define CLK_HSIO2 14
+#define CLK_HWUART 15
+#define CLK_I2C 16
+#define CLK_I2S 17
+#define CLK_IM 18
+#define CLK_INC 19
+#define CLK_ISC 20
+#define CLK_KEYPAD 21
+#define CLK_LCD 22
+#define CLK_MEMC 23
+#define CLK_MEMSTK 24
+#define CLK_MINI_IM 25
+#define CLK_MINI_LCD 26
+#define CLK_MMC 27
+#define CLK_MMC1 28
+#define CLK_MMC2 29
+#define CLK_MMC3 30
+#define CLK_MSL 31
+#define CLK_MSL0 32
+#define CLK_MVED 33
+#define CLK_NAND 34
+#define CLK_NSSP 35
+#define CLK_OSTIMER 36
+#define CLK_PWM0 37
+#define CLK_PWM1 38
+#define CLK_PWM2 39
+#define CLK_PWM3 40
+#define CLK_PWRI2C 41
+#define CLK_PXA300_GCU 42
+#define CLK_PXA320_GCU 43
+#define CLK_SMC 44
+#define CLK_SSP 45
+#define CLK_SSP1 46
+#define CLK_SSP2 47
+#define CLK_SSP3 48
+#define CLK_SSP4 49
+#define CLK_STUART 50
+#define CLK_TOUCH 51
+#define CLK_TPM 52
+#define CLK_UDC 53
+#define CLK_USB 54
+#define CLK_USB2 55
+#define CLK_USBH 56
+#define CLK_USBHOST 57
+#define CLK_USIM 58
+#define CLK_USIM1 59
+#define CLK_USMI0 60
+#define CLK_MAX 61
+
+#endif
-- 
cgit v1.2.3


From 1c6dcbe5ceff81c2cf8d929646af675cd59fe7c0 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@netapp.com>
Date: Fri, 26 Sep 2014 13:58:48 -0400
Subject: NFS: Implement SEEK

The SEEK operation is used when an application makes an lseek call with
either the SEEK_HOLE or SEEK_DATA flags set.  I fall back on
nfs_file_llseek() if the server does not have SEEK support.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/Makefile           |  1 +
 fs/nfs/inode.c            |  2 +
 fs/nfs/nfs42.h            | 14 +++++++
 fs/nfs/nfs42proc.c        | 69 +++++++++++++++++++++++++++++++++
 fs/nfs/nfs42xdr.c         | 98 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4_fs.h          |  3 ++
 fs/nfs/nfs4file.c         | 25 ++++++++++++
 fs/nfs/nfs4proc.c         |  4 +-
 fs/nfs/nfs4xdr.c          |  7 ++++
 include/linux/nfs4.h      |  3 ++
 include/linux/nfs_fs_sb.h |  1 +
 include/linux/nfs_xdr.h   | 19 +++++++++
 12 files changed, 244 insertions(+), 2 deletions(-)
 create mode 100644 fs/nfs/nfs42.h
 create mode 100644 fs/nfs/nfs42proc.c
 create mode 100644 fs/nfs/nfs42xdr.c

(limited to 'include')

diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 4782e0840dcc..04cb830fa09f 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -28,6 +28,7 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
 nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
+nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
 obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 577a36f0a510..56d073ede3c7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -716,6 +716,7 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
 	kfree(new);
 	return res;
 }
+EXPORT_SYMBOL_GPL(nfs_get_lock_context);
 
 void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
 {
@@ -728,6 +729,7 @@ void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
 	spin_unlock(&inode->i_lock);
 	kfree(l_ctx);
 }
+EXPORT_SYMBOL_GPL(nfs_put_lock_context);
 
 /**
  * nfs_close_context - Common close_context() routine NFSv2/v3
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
new file mode 100644
index 000000000000..d10333a197bf
--- /dev/null
+++ b/fs/nfs/nfs42.h
@@ -0,0 +1,14 @@
+/*
+ * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
+ */
+
+#ifndef __LINUX_FS_NFS_NFS4_2_H
+#define __LINUX_FS_NFS_NFS4_2_H
+
+/* nfs4.2proc.c */
+loff_t nfs42_proc_llseek(struct file *, loff_t, int);
+
+/* nfs4.2xdr.h */
+extern struct rpc_procinfo nfs4_2_procedures[];
+
+#endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
new file mode 100644
index 000000000000..0886f1db5917
--- /dev/null
+++ b/fs/nfs/nfs42proc.c
@@ -0,0 +1,69 @@
+/*
+ * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
+ */
+#include <linux/fs.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/nfs.h>
+#include <linux/nfs3.h>
+#include <linux/nfs4.h>
+#include <linux/nfs_xdr.h>
+#include <linux/nfs_fs.h>
+#include "nfs4_fs.h"
+#include "nfs42.h"
+
+static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
+				fmode_t fmode)
+{
+	struct nfs_open_context *open;
+	struct nfs_lock_context *lock;
+	int ret;
+
+	open = get_nfs_open_context(nfs_file_open_context(file));
+	lock = nfs_get_lock_context(open);
+	if (IS_ERR(lock)) {
+		put_nfs_open_context(open);
+		return PTR_ERR(lock);
+	}
+
+	ret = nfs4_set_rw_stateid(dst, open, lock, fmode);
+
+	nfs_put_lock_context(lock);
+	put_nfs_open_context(open);
+	return ret;
+}
+
+loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+{
+	struct inode *inode = file_inode(filep);
+	struct nfs42_seek_args args = {
+		.sa_fh		= NFS_FH(inode),
+		.sa_offset	= offset,
+		.sa_what	= (whence == SEEK_HOLE) ?
+					NFS4_CONTENT_HOLE : NFS4_CONTENT_DATA,
+	};
+	struct nfs42_seek_res res;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SEEK],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	struct nfs_server *server = NFS_SERVER(inode);
+	int status;
+
+	if (!(server->caps & NFS_CAP_SEEK))
+		return -ENOTSUPP;
+
+	status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ);
+	if (status)
+		return status;
+
+	nfs_wb_all(inode);
+	status = nfs4_call_sync(server->client, server, &msg,
+				&args.seq_args, &res.seq_res, 0);
+	if (status == -ENOTSUPP)
+		server->caps &= ~NFS_CAP_SEEK;
+	if (status)
+		return status;
+
+	return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
+}
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
new file mode 100644
index 000000000000..c90469b604b8
--- /dev/null
+++ b/fs/nfs/nfs42xdr.c
@@ -0,0 +1,98 @@
+/*
+ * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
+ */
+#ifndef __LINUX_FS_NFS_NFS4_2XDR_H
+#define __LINUX_FS_NFS_NFS4_2XDR_H
+
+#define encode_seek_maxsz		(op_encode_hdr_maxsz + \
+					 encode_stateid_maxsz + \
+					 2 /* offset */ + \
+					 1 /* whence */)
+#define decode_seek_maxsz		(op_decode_hdr_maxsz + \
+					 1 /* eof */ + \
+					 1 /* whence */ + \
+					 2 /* offset */ + \
+					 2 /* length */)
+
+#define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_seek_maxsz)
+#define NFS4_dec_seek_sz		(compound_decode_hdr_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_seek_maxsz)
+
+
+static void encode_seek(struct xdr_stream *xdr,
+			struct nfs42_seek_args *args,
+			struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_SEEK, decode_seek_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->sa_stateid);
+	encode_uint64(xdr, args->sa_offset);
+	encode_uint32(xdr, args->sa_what);
+}
+
+/*
+ * Encode SEEK request
+ */
+static void nfs4_xdr_enc_seek(struct rpc_rqst *req,
+			      struct xdr_stream *xdr,
+			      struct nfs42_seek_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->sa_fh, &hdr);
+	encode_seek(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
+{
+	int status;
+	__be32 *p;
+
+	status = decode_op_hdr(xdr, OP_SEEK);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4 + 8);
+	if (unlikely(!p))
+		goto out_overflow;
+
+	res->sr_eof = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &res->sr_offset);
+	return 0;
+
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
+/*
+ * Decode SEEK request
+ */
+static int nfs4_xdr_dec_seek(struct rpc_rqst *rqstp,
+			     struct xdr_stream *xdr,
+			     struct nfs42_seek_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_seek(xdr, res);
+out:
+	return status;
+}
+#endif /* __LINUX_FS_NFS_NFS4_2XDR_H */
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 92193eddb41d..b6b518d18aa7 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -227,6 +227,9 @@ int nfs4_replace_transport(struct nfs_server *server,
 				const struct nfs4_fs_locations *locations);
 
 /* nfs4proc.c */
+extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *,
+			  struct rpc_message *, struct nfs4_sequence_args *,
+			  struct nfs4_sequence_res *, int);
 extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
 extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *, bool);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index a816f0627a6c..4dffa3a64731 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -8,6 +8,10 @@
 #include "fscache.h"
 #include "pnfs.h"
 
+#ifdef CONFIG_NFS_V4_2
+#include "nfs42.h"
+#endif
+
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
 static int
@@ -115,8 +119,29 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	return ret;
 }
 
+#ifdef CONFIG_NFS_V4_2
+static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
+{
+	loff_t ret;
+
+	switch (whence) {
+	case SEEK_HOLE:
+	case SEEK_DATA:
+		ret = nfs42_proc_llseek(filep, offset, whence);
+		if (ret != -ENOTSUPP)
+			return ret;
+	default:
+		return nfs_file_llseek(filep, offset, whence);
+	}
+}
+#endif /* CONFIG_NFS_V4_2 */
+
 const struct file_operations nfs4_file_operations = {
+#ifdef CONFIG_NFS_V4_2
+	.llseek		= nfs4_file_llseek,
+#else
 	.llseek		= nfs_file_llseek,
+#endif
 	.read		= new_sync_read,
 	.write		= new_sync_write,
 	.read_iter	= nfs_file_read,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7dd8aca31c29..f3a59f1fb498 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -875,7 +875,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
 	return ret;
 }
 
-static
 int nfs4_call_sync(struct rpc_clnt *clnt,
 		   struct nfs_server *server,
 		   struct rpc_message *msg,
@@ -8429,7 +8428,8 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
-		| NFS_CAP_ATOMIC_OPEN_V1,
+		| NFS_CAP_ATOMIC_OPEN_V1
+		| NFS_CAP_SEEK,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e13b59d8d9aa..949e8717118c 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7427,6 +7427,10 @@ nfs4_stat_to_errno(int stat)
 	return -stat;
 }
 
+#ifdef CONFIG_NFS_V4_2
+#include "nfs42xdr.c"
+#endif /* CONFIG_NFS_V4_2 */
+
 #define PROC(proc, argtype, restype)				\
 [NFSPROC4_CLNT_##proc] = {					\
 	.p_proc   = NFSPROC4_COMPOUND,				\
@@ -7495,6 +7499,9 @@ struct rpc_procinfo	nfs4_procedures[] = {
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
 	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),
 #endif /* CONFIG_NFS_V4_1 */
+#ifdef CONFIG_NFS_V4_2
+	PROC(SEEK,		enc_seek,		dec_seek),
+#endif /* CONFIG_NFS_V4_2 */
 };
 
 const struct rpc_version nfs_version4 = {
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 026b0c042c40..356acc2846fd 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -487,6 +487,9 @@ enum {
 	NFSPROC4_CLNT_GETDEVICELIST,
 	NFSPROC4_CLNT_BIND_CONN_TO_SESSION,
 	NFSPROC4_CLNT_DESTROY_CLIENTID,
+
+	/* nfs42 */
+	NFSPROC4_CLNT_SEEK,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 922be2e050f5..a32ba0d7a98f 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -230,5 +230,6 @@ struct nfs_server {
 #define NFS_CAP_STATEID_NFSV41	(1U << 16)
 #define NFS_CAP_ATOMIC_OPEN_V1	(1U << 17)
 #define NFS_CAP_SECURITY_LABEL	(1U << 18)
+#define NFS_CAP_SEEK		(1U << 19)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0040629894df..0051b1ad2b37 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1239,6 +1239,25 @@ struct pnfs_ds_commit_info {
 
 #endif /* CONFIG_NFS_V4_1 */
 
+#ifdef CONFIG_NFS_V4_2
+struct nfs42_seek_args {
+	struct nfs4_sequence_args	seq_args;
+
+	struct nfs_fh			*sa_fh;
+	nfs4_stateid			sa_stateid;
+	u64				sa_offset;
+	u32				sa_what;
+};
+
+struct nfs42_seek_res {
+	struct nfs4_sequence_res	seq_res;
+	unsigned int			status;
+
+	u32	sr_eof;
+	u64	sr_offset;
+};
+#endif
+
 struct nfs_page;
 
 #define NFS_PAGEVEC_SIZE	(8U)
-- 
cgit v1.2.3


From e1c00e10e92c04aa637126db2e59b092bd4878f8 Mon Sep 17 00:00:00 2001
From: Majd Dibbiny <majd@mellanox.com>
Date: Tue, 30 Sep 2014 12:03:48 +0300
Subject: net/mlx4_core: New init and exit flow for mlx4_core

In the new flow, we separate the pci initialization and teardown
from the initialization and teardown of the other resources.

__mlx4_init_one handles the pci resources initialization. It then
calls mlx4_load_one to initialize the remainder of the resources.

When removing a device, mlx4_remove_one is invoked. However, now
mlx4_remove_one calls mlx4_unload_one to free all the resources except the pci
resources. When mlx4_unload_one returns, mlx4_remove_one then frees the
pci resources.

The above separation will allow us to implement 'reset flow' in the future.
It will also enable more EQs for VFs and is a pre-step to the modern API to
enable/disable SRIOV.

Also added nvfs; an integer array of size MLX4_MAX_PORTS + 1; to the mlx4_dev
struct. This new field is used to avoid parsing the num_vfs module parameter
each time the mlx4_restart_one is called.

Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 393 +++++++++++++++++-------------
 include/linux/mlx4/device.h               |   1 +
 2 files changed, 220 insertions(+), 174 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 4e9857b409f3..f6c32a947185 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2259,116 +2259,18 @@ static void mlx4_free_ownership(struct mlx4_dev *dev)
 	iounmap(owner);
 }
 
-static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
+static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
+			 int total_vfs, int *nvfs, struct mlx4_priv *priv)
 {
-	struct mlx4_priv *priv;
 	struct mlx4_dev *dev;
+	unsigned sum = 0;
 	int err;
 	int port;
-	int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0};
-	int prb_vf[MLX4_MAX_PORTS + 1] = {0, 0, 0};
-	const int param_map[MLX4_MAX_PORTS + 1][MLX4_MAX_PORTS + 1] = {
-		{2, 0, 0}, {0, 1, 2}, {0, 1, 2} };
-	unsigned total_vfs = 0;
-	int sriov_initialized = 0;
-	unsigned int i;
+	int i;
 	int existing_vfs = 0;
 
-	pr_info(DRV_NAME ": Initializing %s\n", pci_name(pdev));
-
-	err = pci_enable_device(pdev);
-	if (err) {
-		dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n");
-		return err;
-	}
-
-	/* Due to requirement that all VFs and the PF are *guaranteed* 2 MACS
-	 * per port, we must limit the number of VFs to 63 (since their are
-	 * 128 MACs)
-	 */
-	for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && i < num_vfs_argc;
-	     total_vfs += nvfs[param_map[num_vfs_argc - 1][i]], i++) {
-		nvfs[param_map[num_vfs_argc - 1][i]] = num_vfs[i];
-		if (nvfs[i] < 0) {
-			dev_err(&pdev->dev, "num_vfs module parameter cannot be negative\n");
-			return -EINVAL;
-		}
-	}
-	for (i = 0; i < sizeof(prb_vf)/sizeof(prb_vf[0]) && i < probe_vfs_argc;
-	     i++) {
-		prb_vf[param_map[probe_vfs_argc - 1][i]] = probe_vf[i];
-		if (prb_vf[i] < 0 || prb_vf[i] > nvfs[i]) {
-			dev_err(&pdev->dev, "probe_vf module parameter cannot be negative or greater than num_vfs\n");
-			return -EINVAL;
-		}
-	}
-	if (total_vfs >= MLX4_MAX_NUM_VF) {
-		dev_err(&pdev->dev,
-			"Requested more VF's (%d) than allowed (%d)\n",
-			total_vfs, MLX4_MAX_NUM_VF - 1);
-		return -EINVAL;
-	}
-
-	for (i = 0; i < MLX4_MAX_PORTS; i++) {
-		if (nvfs[i] + nvfs[2] >= MLX4_MAX_NUM_VF_P_PORT) {
-			dev_err(&pdev->dev,
-				"Requested more VF's (%d) for port (%d) than allowed (%d)\n",
-				nvfs[i] + nvfs[2], i + 1,
-				MLX4_MAX_NUM_VF_P_PORT - 1);
-			return -EINVAL;
-		}
-	}
-
-
-	/*
-	 * Check for BARs.
-	 */
-	if (!(pci_dev_data & MLX4_PCI_DEV_IS_VF) &&
-	    !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
-		dev_err(&pdev->dev, "Missing DCS, aborting (driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n",
-			pci_dev_data, pci_resource_flags(pdev, 0));
-		err = -ENODEV;
-		goto err_disable_pdev;
-	}
-	if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) {
-		dev_err(&pdev->dev, "Missing UAR, aborting\n");
-		err = -ENODEV;
-		goto err_disable_pdev;
-	}
-
-	err = pci_request_regions(pdev, DRV_NAME);
-	if (err) {
-		dev_err(&pdev->dev, "Couldn't get PCI resources, aborting\n");
-		goto err_disable_pdev;
-	}
-
-	pci_set_master(pdev);
+	dev = &priv->dev;
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err) {
-		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n");
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (err) {
-			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n");
-			goto err_release_regions;
-		}
-	}
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err) {
-		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit consistent PCI DMA mask\n");
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (err) {
-			dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, aborting\n");
-			goto err_release_regions;
-		}
-	}
-
-	/* Allow large DMA segments, up to the firmware limit of 1 GB */
-	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
-
-	dev       = pci_get_drvdata(pdev);
-	priv      = mlx4_priv(dev);
-	dev->pdev = pdev;
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
 
@@ -2382,28 +2284,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 
 	dev->rev_id = pdev->revision;
 	dev->numa_node = dev_to_node(&pdev->dev);
+
 	/* Detect if this device is a virtual function */
 	if (pci_dev_data & MLX4_PCI_DEV_IS_VF) {
-		/* When acting as pf, we normally skip vfs unless explicitly
-		 * requested to probe them. */
-		if (total_vfs) {
-			unsigned vfs_offset = 0;
-			for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) &&
-				     vfs_offset + nvfs[i] < extended_func_num(pdev);
-			     vfs_offset += nvfs[i], i++)
-				;
-			if (i == sizeof(nvfs)/sizeof(nvfs[0])) {
-				err = -ENODEV;
-				goto err_free_dev;
-			}
-			if ((extended_func_num(pdev) - vfs_offset)
-			    > prb_vf[i]) {
-				mlx4_warn(dev, "Skipping virtual function:%d\n",
-					  extended_func_num(pdev));
-				err = -ENODEV;
-				goto err_free_dev;
-			}
-		}
 		mlx4_warn(dev, "Detected virtual function - running in slave mode\n");
 		dev->flags |= MLX4_FLAG_SLAVE;
 	} else {
@@ -2413,11 +2296,10 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 		err = mlx4_get_ownership(dev);
 		if (err) {
 			if (err < 0)
-				goto err_free_dev;
+				return err;
 			else {
 				mlx4_warn(dev, "Multiple PFs not yet supported - Skipping PF\n");
-				err = -EINVAL;
-				goto err_free_dev;
+				return -EINVAL;
 			}
 		}
 
@@ -2429,7 +2311,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 				GFP_KERNEL);
 			if (NULL == dev->dev_vfs) {
 				mlx4_err(dev, "Failed to allocate memory for VFs\n");
-				err = 0;
+				err = -ENOMEM;
+				goto err_free_own;
 			} else {
 				atomic_inc(&pf_loading);
 				existing_vfs = pci_num_vf(pdev);
@@ -2445,13 +2328,11 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 					mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d)\n",
 						 err);
 					atomic_dec(&pf_loading);
-					err = 0;
 				} else {
 					mlx4_warn(dev, "Running in master mode\n");
 					dev->flags |= MLX4_FLAG_SRIOV |
 						MLX4_FLAG_MASTER;
 					dev->num_vfs = total_vfs;
-					sriov_initialized = 1;
 				}
 			}
 		}
@@ -2467,7 +2348,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 		err = mlx4_reset(dev);
 		if (err) {
 			mlx4_err(dev, "Failed to reset HCA, aborting\n");
-			goto err_rel_own;
+			goto err_sriov;
 		}
 	}
 
@@ -2517,34 +2398,46 @@ slave_start:
 	/* In master functions, the communication channel must be initialized
 	 * after obtaining its address from fw */
 	if (mlx4_is_master(dev)) {
-		unsigned sum = 0;
-		err = mlx4_multi_func_init(dev);
-		if (err) {
-			mlx4_err(dev, "Failed to init master mfunc interface, aborting\n");
+		int ib_ports = 0;
+
+		mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+			ib_ports++;
+
+		if (ib_ports &&
+		    (num_vfs_argc > 1 || probe_vfs_argc > 1)) {
+			mlx4_err(dev,
+				 "Invalid syntax of num_vfs/probe_vfs with IB port - single port VFs syntax is only supported when all ports are configured as ethernet\n");
+			err = -EINVAL;
+			goto err_close;
+		}
+		if (dev->caps.num_ports < 2 &&
+		    num_vfs_argc > 1) {
+			err = -EINVAL;
+			mlx4_err(dev,
+				 "Error: Trying to configure VFs on port 2, but HCA has only %d physical ports\n",
+				 dev->caps.num_ports);
 			goto err_close;
 		}
-		if (sriov_initialized) {
-			int ib_ports = 0;
-			mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
-				ib_ports++;
+		memcpy(dev->nvfs, nvfs, sizeof(dev->nvfs));
 
-			if (ib_ports &&
-			    (num_vfs_argc > 1 || probe_vfs_argc > 1)) {
-				mlx4_err(dev,
-					 "Invalid syntax of num_vfs/probe_vfs with IB port - single port VFs syntax is only supported when all ports are configured as ethernet\n");
-				err = -EINVAL;
-				goto err_master_mfunc;
-			}
-			for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]); i++) {
-				unsigned j;
-				for (j = 0; j < nvfs[i]; ++sum, ++j) {
-					dev->dev_vfs[sum].min_port =
-						i < 2 ? i + 1 : 1;
-					dev->dev_vfs[sum].n_ports = i < 2 ? 1 :
-						dev->caps.num_ports;
-				}
+		for (i = 0; i < sizeof(dev->nvfs)/sizeof(dev->nvfs[0]); i++) {
+			unsigned j;
+
+			for (j = 0; j < dev->nvfs[i]; ++sum, ++j) {
+				dev->dev_vfs[sum].min_port = i < 2 ? i + 1 : 1;
+				dev->dev_vfs[sum].n_ports = i < 2 ? 1 :
+					dev->caps.num_ports;
 			}
 		}
+
+		/* In master functions, the communication channel
+		 * must be initialized after obtaining its address from fw
+		 */
+		err = mlx4_multi_func_init(dev);
+		if (err) {
+			mlx4_err(dev, "Failed to init master mfunc interface, aborting.\n");
+			goto err_close;
+		}
 	}
 
 	err = mlx4_alloc_eq_table(dev);
@@ -2565,7 +2458,7 @@ slave_start:
 	if (!mlx4_is_slave(dev)) {
 		err = mlx4_init_steering(dev);
 		if (err)
-			goto err_free_eq;
+			goto err_disable_msix;
 	}
 
 	err = mlx4_setup_hca(dev);
@@ -2625,6 +2518,10 @@ err_steer:
 	if (!mlx4_is_slave(dev))
 		mlx4_clear_steering(dev);
 
+err_disable_msix:
+	if (dev->flags & MLX4_FLAG_MSI_X)
+		pci_disable_msix(pdev);
+
 err_free_eq:
 	mlx4_free_eq_table(dev);
 
@@ -2641,9 +2538,6 @@ err_master_mfunc:
 	}
 
 err_close:
-	if (dev->flags & MLX4_FLAG_MSI_X)
-		pci_disable_msix(pdev);
-
 	mlx4_close_hca(dev);
 
 err_mfunc:
@@ -2657,17 +2551,151 @@ err_sriov:
 	if (dev->flags & MLX4_FLAG_SRIOV && !existing_vfs)
 		pci_disable_sriov(pdev);
 
-err_rel_own:
-	if (!mlx4_is_slave(dev))
-		mlx4_free_ownership(dev);
-
 	if (mlx4_is_master(dev) && dev->num_vfs)
 		atomic_dec(&pf_loading);
 
 	kfree(priv->dev.dev_vfs);
 
-err_free_dev:
-	kfree(priv);
+err_free_own:
+	if (!mlx4_is_slave(dev))
+		mlx4_free_ownership(dev);
+
+	return err;
+}
+
+static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
+			   struct mlx4_priv *priv)
+{
+	int err;
+	int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0};
+	int prb_vf[MLX4_MAX_PORTS + 1] = {0, 0, 0};
+	const int param_map[MLX4_MAX_PORTS + 1][MLX4_MAX_PORTS + 1] = {
+		{2, 0, 0}, {0, 1, 2}, {0, 1, 2} };
+	unsigned total_vfs = 0;
+	unsigned int i;
+
+	pr_info(DRV_NAME ": Initializing %s\n", pci_name(pdev));
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n");
+		return err;
+	}
+
+	/* Due to requirement that all VFs and the PF are *guaranteed* 2 MACS
+	 * per port, we must limit the number of VFs to 63 (since their are
+	 * 128 MACs)
+	 */
+	for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && i < num_vfs_argc;
+	     total_vfs += nvfs[param_map[num_vfs_argc - 1][i]], i++) {
+		nvfs[param_map[num_vfs_argc - 1][i]] = num_vfs[i];
+		if (nvfs[i] < 0) {
+			dev_err(&pdev->dev, "num_vfs module parameter cannot be negative\n");
+			err = -EINVAL;
+			goto err_disable_pdev;
+		}
+	}
+	for (i = 0; i < sizeof(prb_vf)/sizeof(prb_vf[0]) && i < probe_vfs_argc;
+	     i++) {
+		prb_vf[param_map[probe_vfs_argc - 1][i]] = probe_vf[i];
+		if (prb_vf[i] < 0 || prb_vf[i] > nvfs[i]) {
+			dev_err(&pdev->dev, "probe_vf module parameter cannot be negative or greater than num_vfs\n");
+			err = -EINVAL;
+			goto err_disable_pdev;
+		}
+	}
+	if (total_vfs >= MLX4_MAX_NUM_VF) {
+		dev_err(&pdev->dev,
+			"Requested more VF's (%d) than allowed (%d)\n",
+			total_vfs, MLX4_MAX_NUM_VF - 1);
+		err = -EINVAL;
+		goto err_disable_pdev;
+	}
+
+	for (i = 0; i < MLX4_MAX_PORTS; i++) {
+		if (nvfs[i] + nvfs[2] >= MLX4_MAX_NUM_VF_P_PORT) {
+			dev_err(&pdev->dev,
+				"Requested more VF's (%d) for port (%d) than allowed (%d)\n",
+				nvfs[i] + nvfs[2], i + 1,
+				MLX4_MAX_NUM_VF_P_PORT - 1);
+			err = -EINVAL;
+			goto err_disable_pdev;
+		}
+	}
+
+	/* Check for BARs. */
+	if (!(pci_dev_data & MLX4_PCI_DEV_IS_VF) &&
+	    !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
+		dev_err(&pdev->dev, "Missing DCS, aborting (driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n",
+			pci_dev_data, pci_resource_flags(pdev, 0));
+		err = -ENODEV;
+		goto err_disable_pdev;
+	}
+	if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) {
+		dev_err(&pdev->dev, "Missing UAR, aborting\n");
+		err = -ENODEV;
+		goto err_disable_pdev;
+	}
+
+	err = pci_request_regions(pdev, DRV_NAME);
+	if (err) {
+		dev_err(&pdev->dev, "Couldn't get PCI resources, aborting\n");
+		goto err_disable_pdev;
+	}
+
+	pci_set_master(pdev);
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n");
+		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n");
+			goto err_release_regions;
+		}
+	}
+	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit consistent PCI DMA mask\n");
+		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, aborting\n");
+			goto err_release_regions;
+		}
+	}
+
+	/* Allow large DMA segments, up to the firmware limit of 1 GB */
+	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
+	/* Detect if this device is a virtual function */
+	if (pci_dev_data & MLX4_PCI_DEV_IS_VF) {
+		/* When acting as pf, we normally skip vfs unless explicitly
+		 * requested to probe them.
+		 */
+		if (total_vfs) {
+			unsigned vfs_offset = 0;
+
+			for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) &&
+			     vfs_offset + nvfs[i] < extended_func_num(pdev);
+			     vfs_offset += nvfs[i], i++)
+				;
+			if (i == sizeof(nvfs)/sizeof(nvfs[0])) {
+				err = -ENODEV;
+				goto err_release_regions;
+			}
+			if ((extended_func_num(pdev) - vfs_offset)
+			    > prb_vf[i]) {
+				dev_warn(&pdev->dev, "Skipping virtual function:%d\n",
+					 extended_func_num(pdev));
+				err = -ENODEV;
+				goto err_release_regions;
+			}
+		}
+	}
+
+	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv);
+	if (err)
+		goto err_release_regions;
+	return 0;
 
 err_release_regions:
 	pci_release_regions(pdev);
@@ -2682,6 +2710,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct mlx4_priv *priv;
 	struct mlx4_dev *dev;
+	int ret;
 
 	printk_once(KERN_INFO "%s", mlx4_version);
 
@@ -2690,13 +2719,18 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	dev       = &priv->dev;
+	dev->pdev = pdev;
 	pci_set_drvdata(pdev, dev);
 	priv->pci_dev_data = id->driver_data;
 
-	return __mlx4_init_one(pdev, id->driver_data);
+	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
+	if (ret)
+		kfree(priv);
+
+	return ret;
 }
 
-static void __mlx4_remove_one(struct pci_dev *pdev)
+static void mlx4_unload_one(struct pci_dev *pdev)
 {
 	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2775,8 +2809,6 @@ static void __mlx4_remove_one(struct pci_dev *pdev)
 	kfree(dev->caps.qp1_proxy);
 	kfree(dev->dev_vfs);
 
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
 	memset(priv, 0, sizeof(*priv));
 	priv->pci_dev_data = pci_dev_data;
 	priv->removed = 1;
@@ -2787,7 +2819,9 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
-	__mlx4_remove_one(pdev);
+	mlx4_unload_one(pdev);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
 	kfree(priv);
 	pci_set_drvdata(pdev, NULL);
 }
@@ -2796,11 +2830,22 @@ int mlx4_restart_one(struct pci_dev *pdev)
 {
 	struct mlx4_dev	 *dev  = pci_get_drvdata(pdev);
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	int		  pci_dev_data;
+	int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0};
+	int pci_dev_data, err, total_vfs;
 
 	pci_dev_data = priv->pci_dev_data;
-	__mlx4_remove_one(pdev);
-	return __mlx4_init_one(pdev, pci_dev_data);
+	total_vfs = dev->num_vfs;
+	memcpy(nvfs, dev->nvfs, sizeof(dev->nvfs));
+
+	mlx4_unload_one(pdev);
+	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv);
+	if (err) {
+		mlx4_err(dev, "%s: ERROR: mlx4_load_one failed, pci_name=%s, err=%d\n",
+			 __func__, pci_name(pdev), err);
+		return err;
+	}
+
+	return err;
 }
 
 static const struct pci_device_id mlx4_pci_table[] = {
@@ -2854,7 +2899,7 @@ MODULE_DEVICE_TABLE(pci, mlx4_pci_table);
 static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
 					      pci_channel_state_t state)
 {
-	__mlx4_remove_one(pdev);
+	mlx4_unload_one(pdev);
 
 	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
@@ -2866,7 +2911,7 @@ static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int               ret;
 
-	ret = __mlx4_init_one(pdev, priv->pci_dev_data);
+	ret = __mlx4_init_one(pdev, priv->pci_dev_data, priv);
 
 	return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
@@ -2880,7 +2925,7 @@ static struct pci_driver mlx4_driver = {
 	.name		= DRV_NAME,
 	.id_table	= mlx4_pci_table,
 	.probe		= mlx4_init_one,
-	.shutdown	= __mlx4_remove_one,
+	.shutdown	= mlx4_unload_one,
 	.remove		= mlx4_remove_one,
 	.err_handler    = &mlx4_err_handler,
 };
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 03b5608a4329..b2f8ab9a57c4 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -707,6 +707,7 @@ struct mlx4_dev {
 	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
 	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
 	struct mlx4_vf_dev     *dev_vfs;
+	int                     nvfs[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_eqe {
-- 
cgit v1.2.3


From a12a601ed163578084a48708ae376805f79a1ccf Mon Sep 17 00:00:00 2001
From: Li RongQing <roy.qing.li@gmail.com>
Date: Tue, 30 Sep 2014 09:49:55 +0800
Subject: tcp: Change tcp_slow_start function to return void

No caller uses the return value, so make this function return void.

Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   | 2 +-
 net/ipv4/tcp_cong.c | 4 +---
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 545a79aa4212..ba2f9d03076b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -830,7 +830,7 @@ void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
 int tcp_set_congestion_control(struct sock *sk, const char *name);
-int tcp_slow_start(struct tcp_sock *tp, u32 acked);
+void tcp_slow_start(struct tcp_sock *tp, u32 acked);
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
 
 u32 tcp_reno_ssthresh(struct sock *sk);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index a6c8a5775624..b1c5970d47a1 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -291,15 +291,13 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
  * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
  * returns the leftover acks to adjust cwnd in congestion avoidance mode.
  */
-int tcp_slow_start(struct tcp_sock *tp, u32 acked)
+void tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
 	u32 cwnd = tp->snd_cwnd + acked;
 
 	if (cwnd > tp->snd_ssthresh)
 		cwnd = tp->snd_ssthresh + 1;
-	acked -= cwnd - tp->snd_cwnd;
 	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
-	return acked;
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
-- 
cgit v1.2.3


From c611529e7cd3465ec0eada0f44200e8420c38908 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Sep 2014 19:20:08 -0400
Subject: sd: Honor block layer integrity handling flags

A set of flags introduced in the block layer enable better control over
how protection information is handled. These flags are useful for both
error injection and data recovery purposes. Checking can be enabled and
disabled for controller and disk, and the guard tag format is now a
per-I/O property.

Update sd_protect_op to communicate the relevant information to the
low-level device driver via a set of flags in scsi_cmnd.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/scsi/sd.c        | 73 ++++++++++++++++++++++++++++--------------------
 drivers/scsi/sd.h        | 66 +++++++++++++++++++++++++++++++++++++++++--
 drivers/scsi/sd_dif.c    | 23 ++++++---------
 include/linux/bio.h      | 33 ++++++++++++++++------
 include/scsi/scsi_cmnd.h | 36 +++++++++++++++++-------
 5 files changed, 166 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 2c2041ca4b70..9f7099f4b537 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -610,29 +610,44 @@ static void scsi_disk_put(struct scsi_disk *sdkp)
 	mutex_unlock(&sd_ref_mutex);
 }
 
-static void sd_prot_op(struct scsi_cmnd *scmd, unsigned int dif)
-{
-	unsigned int prot_op = SCSI_PROT_NORMAL;
-	unsigned int dix = scsi_prot_sg_count(scmd);
-
-	if (scmd->sc_data_direction == DMA_FROM_DEVICE) {
-		if (dif && dix)
-			prot_op = SCSI_PROT_READ_PASS;
-		else if (dif && !dix)
-			prot_op = SCSI_PROT_READ_STRIP;
-		else if (!dif && dix)
-			prot_op = SCSI_PROT_READ_INSERT;
-	} else {
-		if (dif && dix)
-			prot_op = SCSI_PROT_WRITE_PASS;
-		else if (dif && !dix)
-			prot_op = SCSI_PROT_WRITE_INSERT;
-		else if (!dif && dix)
-			prot_op = SCSI_PROT_WRITE_STRIP;
+
+
+static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd,
+					   unsigned int dix, unsigned int dif)
+{
+	struct bio *bio = scmd->request->bio;
+	unsigned int prot_op = sd_prot_op(rq_data_dir(scmd->request), dix, dif);
+	unsigned int protect = 0;
+
+	if (dix) {				/* DIX Type 0, 1, 2, 3 */
+		if (bio_integrity_flagged(bio, BIP_IP_CHECKSUM))
+			scmd->prot_flags |= SCSI_PROT_IP_CHECKSUM;
+
+		if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
+			scmd->prot_flags |= SCSI_PROT_GUARD_CHECK;
+	}
+
+	if (dif != SD_DIF_TYPE3_PROTECTION) {	/* DIX/DIF Type 0, 1, 2 */
+		scmd->prot_flags |= SCSI_PROT_REF_INCREMENT;
+
+		if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
+			scmd->prot_flags |= SCSI_PROT_REF_CHECK;
+	}
+
+	if (dif) {				/* DIX/DIF Type 1, 2, 3 */
+		scmd->prot_flags |= SCSI_PROT_TRANSFER_PI;
+
+		if (bio_integrity_flagged(bio, BIP_DISK_NOCHECK))
+			protect = 3 << 5;	/* Disable target PI checking */
+		else
+			protect = 1 << 5;	/* Enable target PI checking */
 	}
 
 	scsi_set_prot_op(scmd, prot_op);
 	scsi_set_prot_type(scmd, dif);
+	scmd->prot_flags &= sd_prot_flag_mask(prot_op);
+
+	return protect;
 }
 
 static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
@@ -893,7 +908,8 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	sector_t block = blk_rq_pos(rq);
 	sector_t threshold;
 	unsigned int this_count = blk_rq_sectors(rq);
-	int ret, host_dif;
+	unsigned int dif, dix;
+	int ret;
 	unsigned char protect;
 
 	ret = scsi_init_io(SCpnt, GFP_ATOMIC);
@@ -995,7 +1011,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 		SCpnt->cmnd[0] = WRITE_6;
 
 		if (blk_integrity_rq(rq))
-			sd_dif_prepare(rq, block, sdp->sector_size);
+			sd_dif_prepare(SCpnt);
 
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
@@ -1010,14 +1026,15 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 					"writing" : "reading", this_count,
 					blk_rq_sectors(rq)));
 
-	/* Set RDPROTECT/WRPROTECT if disk is formatted with DIF */
-	host_dif = scsi_host_dif_capable(sdp->host, sdkp->protection_type);
-	if (host_dif)
-		protect = 1 << 5;
+	dix = scsi_prot_sg_count(SCpnt);
+	dif = scsi_host_dif_capable(SCpnt->device->host, sdkp->protection_type);
+
+	if (dif || dix)
+		protect = sd_setup_protect_cmnd(SCpnt, dix, dif);
 	else
 		protect = 0;
 
-	if (host_dif == SD_DIF_TYPE2_PROTECTION) {
+	if (protect && sdkp->protection_type == SD_DIF_TYPE2_PROTECTION) {
 		SCpnt->cmnd = mempool_alloc(sd_cdb_pool, GFP_ATOMIC);
 
 		if (unlikely(SCpnt->cmnd == NULL)) {
@@ -1102,10 +1119,6 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	}
 	SCpnt->sdb.length = this_count * sdp->sector_size;
 
-	/* If DIF or DIX is enabled, tell HBA how to handle request */
-	if (host_dif || scsi_prot_sg_count(SCpnt))
-		sd_prot_op(SCpnt, host_dif);
-
 	/*
 	 * We shouldn't disconnect in the middle of a sector, so with a dumb
 	 * host adapter, it's safe to assume that we can at least transfer
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 4c3ab8377fd3..467377884b63 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -166,6 +166,68 @@ enum sd_dif_target_protection_types {
 	SD_DIF_TYPE3_PROTECTION = 0x3,
 };
 
+/*
+ * Look up the DIX operation based on whether the command is read or
+ * write and whether dix and dif are enabled.
+ */
+static inline unsigned int sd_prot_op(bool write, bool dix, bool dif)
+{
+	/* Lookup table: bit 2 (write), bit 1 (dix), bit 0 (dif) */
+	const unsigned int ops[] = {	/* wrt dix dif */
+		SCSI_PROT_NORMAL,	/*  0	0   0  */
+		SCSI_PROT_READ_STRIP,	/*  0	0   1  */
+		SCSI_PROT_READ_INSERT,	/*  0	1   0  */
+		SCSI_PROT_READ_PASS,	/*  0	1   1  */
+		SCSI_PROT_NORMAL,	/*  1	0   0  */
+		SCSI_PROT_WRITE_INSERT, /*  1	0   1  */
+		SCSI_PROT_WRITE_STRIP,	/*  1	1   0  */
+		SCSI_PROT_WRITE_PASS,	/*  1	1   1  */
+	};
+
+	return ops[write << 2 | dix << 1 | dif];
+}
+
+/*
+ * Returns a mask of the protection flags that are valid for a given DIX
+ * operation.
+ */
+static inline unsigned int sd_prot_flag_mask(unsigned int prot_op)
+{
+	const unsigned int flag_mask[] = {
+		[SCSI_PROT_NORMAL]		= 0,
+
+		[SCSI_PROT_READ_STRIP]		= SCSI_PROT_TRANSFER_PI |
+						  SCSI_PROT_GUARD_CHECK |
+						  SCSI_PROT_REF_CHECK |
+						  SCSI_PROT_REF_INCREMENT,
+
+		[SCSI_PROT_READ_INSERT]		= SCSI_PROT_REF_INCREMENT |
+						  SCSI_PROT_IP_CHECKSUM,
+
+		[SCSI_PROT_READ_PASS]		= SCSI_PROT_TRANSFER_PI |
+						  SCSI_PROT_GUARD_CHECK |
+						  SCSI_PROT_REF_CHECK |
+						  SCSI_PROT_REF_INCREMENT |
+						  SCSI_PROT_IP_CHECKSUM,
+
+		[SCSI_PROT_WRITE_INSERT]	= SCSI_PROT_TRANSFER_PI |
+						  SCSI_PROT_REF_INCREMENT,
+
+		[SCSI_PROT_WRITE_STRIP]		= SCSI_PROT_GUARD_CHECK |
+						  SCSI_PROT_REF_CHECK |
+						  SCSI_PROT_REF_INCREMENT |
+						  SCSI_PROT_IP_CHECKSUM,
+
+		[SCSI_PROT_WRITE_PASS]		= SCSI_PROT_TRANSFER_PI |
+						  SCSI_PROT_GUARD_CHECK |
+						  SCSI_PROT_REF_CHECK |
+						  SCSI_PROT_REF_INCREMENT |
+						  SCSI_PROT_IP_CHECKSUM,
+	};
+
+	return flag_mask[prot_op];
+}
+
 /*
  * Data Integrity Field tuple.
  */
@@ -178,7 +240,7 @@ struct sd_dif_tuple {
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 
 extern void sd_dif_config_host(struct scsi_disk *);
-extern void sd_dif_prepare(struct request *rq, sector_t, unsigned int);
+extern void sd_dif_prepare(struct scsi_cmnd *scmd);
 extern void sd_dif_complete(struct scsi_cmnd *, unsigned int);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
@@ -186,7 +248,7 @@ extern void sd_dif_complete(struct scsi_cmnd *, unsigned int);
 static inline void sd_dif_config_host(struct scsi_disk *disk)
 {
 }
-static inline int sd_dif_prepare(struct request *rq, sector_t s, unsigned int a)
+static inline int sd_dif_prepare(struct scsi_cmnd *scmd)
 {
 	return 0;
 }
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index b7eaeadc18f9..14c7d42a11c2 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -106,8 +106,7 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
  *
  * Type 3 does not have a reference tag so no remapping is required.
  */
-void sd_dif_prepare(struct request *rq, sector_t hw_sector,
-		    unsigned int sector_sz)
+void sd_dif_prepare(struct scsi_cmnd *scmd)
 {
 	const int tuple_sz = sizeof(struct t10_pi_tuple);
 	struct bio *bio;
@@ -115,14 +114,14 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 	struct t10_pi_tuple *pi;
 	u32 phys, virt;
 
-	sdkp = rq->bio->bi_bdev->bd_disk->private_data;
+	sdkp = scsi_disk(scmd->request->rq_disk);
 
 	if (sdkp->protection_type == SD_DIF_TYPE3_PROTECTION)
 		return;
 
-	phys = hw_sector & 0xffffffff;
+	phys = scsi_prot_ref_tag(scmd);
 
-	__rq_for_each_bio(bio, rq) {
+	__rq_for_each_bio(bio, scmd->request) {
 		struct bio_integrity_payload *bip = bio_integrity(bio);
 		struct bio_vec iv;
 		struct bvec_iter iter;
@@ -163,7 +162,7 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 	struct scsi_disk *sdkp;
 	struct bio *bio;
 	struct t10_pi_tuple *pi;
-	unsigned int j, sectors, sector_sz;
+	unsigned int j, intervals;
 	u32 phys, virt;
 
 	sdkp = scsi_disk(scmd->request->rq_disk);
@@ -171,12 +170,8 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 	if (sdkp->protection_type == SD_DIF_TYPE3_PROTECTION || good_bytes == 0)
 		return;
 
-	sector_sz = scmd->device->sector_size;
-	sectors = good_bytes / sector_sz;
-
-	phys = blk_rq_pos(scmd->request) & 0xffffffff;
-	if (sector_sz == 4096)
-		phys >>= 3;
+	intervals = good_bytes / scsi_prot_interval(scmd);
+	phys = scsi_prot_ref_tag(scmd);
 
 	__rq_for_each_bio(bio, scmd->request) {
 		struct bio_integrity_payload *bip = bio_integrity(bio);
@@ -190,7 +185,7 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 
 			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
 
-				if (sectors == 0) {
+				if (intervals == 0) {
 					kunmap_atomic(pi);
 					return;
 				}
@@ -200,7 +195,7 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 
 				virt++;
 				phys++;
-				sectors--;
+				intervals--;
 			}
 
 			kunmap_atomic(pi);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 14bff3fe56d4..ce6b75964b71 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -292,6 +292,14 @@ static inline unsigned bio_segments(struct bio *bio)
  */
 #define bio_get(bio)	atomic_inc(&(bio)->bi_cnt)
 
+enum bip_flags {
+	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
+	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
+	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
+	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
+	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
+};
+
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
 static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
@@ -323,13 +331,15 @@ struct bio_integrity_payload {
 	struct bio_vec		bip_inline_vecs[0];/* embedded bvec array */
 };
 
-enum bip_flags {
-	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
-	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
-	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
-	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
-	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
-};
+static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
+{
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+
+	if (bip)
+		return bip->bip_flags & flag;
+
+	return false;
+}
 
 static inline sector_t bip_get_seed(struct bio_integrity_payload *bip)
 {
@@ -701,9 +711,9 @@ extern void bio_integrity_init(void);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
-static inline int bio_integrity(struct bio *bio)
+static inline void *bio_integrity(struct bio *bio)
 {
-	return 0;
+	return NULL;
 }
 
 static inline bool bio_integrity_enabled(struct bio *bio)
@@ -754,6 +764,11 @@ static inline void bio_integrity_init(void)
 	return;
 }
 
+static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
+{
+	return false;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 #endif /* CONFIG_BLOCK */
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 73f349044941..522a5f27f553 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -10,9 +10,10 @@
 #include <scsi/scsi_device.h>
 
 struct Scsi_Host;
-struct scsi_device;
 struct scsi_driver;
 
+#include <scsi/scsi_device.h>
+
 /*
  * MAX_COMMAND_SIZE is:
  * The longest fixed-length SCSI CDB as per the SCSI standard.
@@ -81,6 +82,7 @@ struct scsi_cmnd {
 
 	unsigned char prot_op;
 	unsigned char prot_type;
+	unsigned char prot_flags;
 
 	unsigned short cmd_len;
 	enum dma_data_direction sc_data_direction;
@@ -252,6 +254,14 @@ static inline unsigned char scsi_get_prot_op(struct scsi_cmnd *scmd)
 	return scmd->prot_op;
 }
 
+enum scsi_prot_flags {
+	SCSI_PROT_TRANSFER_PI		= 1 << 0,
+	SCSI_PROT_GUARD_CHECK		= 1 << 1,
+	SCSI_PROT_REF_CHECK		= 1 << 2,
+	SCSI_PROT_REF_INCREMENT		= 1 << 3,
+	SCSI_PROT_IP_CHECKSUM		= 1 << 4,
+};
+
 /*
  * The controller usually does not know anything about the target it
  * is communicating with.  However, when DIX is enabled the controller
@@ -280,6 +290,17 @@ static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd)
 	return blk_rq_pos(scmd->request);
 }
 
+static inline unsigned int scsi_prot_interval(struct scsi_cmnd *scmd)
+{
+	return scmd->device->sector_size;
+}
+
+static inline u32 scsi_prot_ref_tag(struct scsi_cmnd *scmd)
+{
+	return blk_rq_pos(scmd->request) >>
+		(ilog2(scsi_prot_interval(scmd)) - 9) & 0xffffffff;
+}
+
 static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd)
 {
 	return cmd->prot_sdb ? cmd->prot_sdb->table.nents : 0;
@@ -316,17 +337,12 @@ static inline void set_driver_byte(struct scsi_cmnd *cmd, char status)
 static inline unsigned scsi_transfer_length(struct scsi_cmnd *scmd)
 {
 	unsigned int xfer_len = scsi_out(scmd)->length;
-	unsigned int prot_op = scsi_get_prot_op(scmd);
-	unsigned int sector_size = scmd->device->sector_size;
+	unsigned int prot_interval = scsi_prot_interval(scmd);
 
-	switch (prot_op) {
-	case SCSI_PROT_NORMAL:
-	case SCSI_PROT_WRITE_STRIP:
-	case SCSI_PROT_READ_INSERT:
-		return xfer_len;
-	}
+	if (scmd->prot_flags & SCSI_PROT_TRANSFER_PI)
+		xfer_len += (xfer_len >> ilog2(prot_interval)) * 8;
 
-	return xfer_len + (xfer_len >> ilog2(sector_size)) * 8;
+	return xfer_len;
 }
 
 #endif /* _SCSI_SCSI_CMND_H */
-- 
cgit v1.2.3


From 75ab4cb8301adb3a02a96c5c03c837ed941f1bc5 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Sat, 20 Sep 2014 21:57:51 -0700
Subject: f2fs: introduce cp_control structure

This patch add a new data structure to control checkpoint parameters.
Currently, it presents the reason of checkpoint such as is_umount and normal
sync.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c        | 16 ++++++++--------
 fs/f2fs/f2fs.h              | 11 ++++++++++-
 fs/f2fs/gc.c                |  7 +++++--
 fs/f2fs/recovery.c          |  5 ++++-
 fs/f2fs/super.c             | 13 ++++++++++---
 include/trace/events/f2fs.h | 15 ++++++++++-----
 6 files changed, 47 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index b4a813345de2..efc530cb74a9 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -826,7 +826,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 	finish_wait(&sbi->cp_wait, &wait);
 }
 
-static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
@@ -894,7 +894,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
 			orphan_blocks);
 
-	if (is_umount) {
+	if (cpc->reason == CP_UMOUNT) {
 		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
 		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
 				cp_payload_blks + data_sum_blocks +
@@ -948,7 +948,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 
 	write_data_summaries(sbi, start_blk);
 	start_blk += data_sum_blocks;
-	if (is_umount) {
+	if (cpc->reason == CP_UMOUNT) {
 		write_node_summaries(sbi, start_blk);
 		start_blk += NR_CURSEG_NODE_TYPE;
 	}
@@ -988,12 +988,12 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 /*
  * We guarantee that this checkpoint procedure will not fail.
  */
-void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned long long ckpt_ver;
 
-	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops");
+	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
 
 	mutex_lock(&sbi->cp_mutex);
 
@@ -1004,7 +1004,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	if (block_operations(sbi))
 		goto out;
 
-	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops");
+	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
 
 	f2fs_submit_merged_bio(sbi, DATA, WRITE);
 	f2fs_submit_merged_bio(sbi, NODE, WRITE);
@@ -1023,13 +1023,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	flush_sit_entries(sbi);
 
 	/* unlock all the fs_lock[] in do_checkpoint() */
-	do_checkpoint(sbi, is_umount);
+	do_checkpoint(sbi, cpc);
 
 	unblock_operations(sbi);
 	stat_inc_cp_count(sbi->stat_info);
 out:
 	mutex_unlock(&sbi->cp_mutex);
-	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint");
+	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
 }
 
 void init_ino_entry_info(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 3b70b0137191..529892418862 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -96,6 +96,15 @@ enum {
 	SIT_BITMAP
 };
 
+enum {
+	CP_UMOUNT,
+	CP_SYNC,
+};
+
+struct cp_control {
+	int reason;
+};
+
 /*
  * For CP/NAT/SIT/SSA readahead
  */
@@ -1314,7 +1323,7 @@ void update_dirty_page(struct inode *, struct page *);
 void add_dirty_dir_inode(struct inode *);
 void remove_dirty_dir_inode(struct inode *);
 void sync_dirty_dir_inodes(struct f2fs_sb_info *);
-void write_checkpoint(struct f2fs_sb_info *, bool);
+void write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
 void init_ino_entry_info(struct f2fs_sb_info *);
 int __init create_checkpoint_caches(void);
 void destroy_checkpoint_caches(void);
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 7bf8392d555f..e88fcf65aa7f 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -694,6 +694,9 @@ int f2fs_gc(struct f2fs_sb_info *sbi)
 	int gc_type = BG_GC;
 	int nfree = 0;
 	int ret = -1;
+	struct cp_control cpc = {
+		.reason = CP_SYNC,
+	};
 
 	INIT_LIST_HEAD(&ilist);
 gc_more:
@@ -704,7 +707,7 @@ gc_more:
 
 	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) {
 		gc_type = FG_GC;
-		write_checkpoint(sbi, false);
+		write_checkpoint(sbi, &cpc);
 	}
 
 	if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
@@ -729,7 +732,7 @@ gc_more:
 		goto gc_more;
 
 	if (gc_type == FG_GC)
-		write_checkpoint(sbi, false);
+		write_checkpoint(sbi, &cpc);
 stop:
 	mutex_unlock(&sbi->gc_mutex);
 
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 39c4ff69990e..947b92273d08 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -542,8 +542,11 @@ out:
 		set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
 		mutex_unlock(&sbi->cp_mutex);
 	} else if (need_writecp) {
+		struct cp_control cpc = {
+			.reason = CP_SYNC,
+		};
 		mutex_unlock(&sbi->cp_mutex);
-		write_checkpoint(sbi, false);
+		write_checkpoint(sbi, &cpc);
 	} else {
 		mutex_unlock(&sbi->cp_mutex);
 	}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 7a91a381dced..128c42000fa3 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -434,8 +434,12 @@ static void f2fs_put_super(struct super_block *sb)
 	stop_gc_thread(sbi);
 
 	/* We don't need to do checkpoint when it's clean */
-	if (sbi->s_dirty)
-		write_checkpoint(sbi, true);
+	if (sbi->s_dirty) {
+		struct cp_control cpc = {
+			.reason = CP_UMOUNT,
+		};
+		write_checkpoint(sbi, &cpc);
+	}
 
 	/*
 	 * normally superblock is clean, so we need to release this.
@@ -466,8 +470,11 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 	trace_f2fs_sync_fs(sb, sync);
 
 	if (sync) {
+		struct cp_control cpc = {
+			.reason = CP_SYNC,
+		};
 		mutex_lock(&sbi->gc_mutex);
-		write_checkpoint(sbi, false);
+		write_checkpoint(sbi, &cpc);
 		mutex_unlock(&sbi->gc_mutex);
 	} else {
 		f2fs_balance_fs(sbi);
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index d06d44363fea..66eaace9c07e 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -69,6 +69,11 @@
 		{ GC_GREEDY,	"Greedy" },				\
 		{ GC_CB,	"Cost-Benefit" })
 
+#define show_cpreason(type)						\
+	__print_symbolic(type,						\
+		{ CP_UMOUNT,	"Umount" },				\
+		{ CP_SYNC,	"Sync" })
+
 struct victim_sel_policy;
 
 DECLARE_EVENT_CLASS(f2fs__inode,
@@ -944,25 +949,25 @@ TRACE_EVENT(f2fs_submit_page_mbio,
 
 TRACE_EVENT(f2fs_write_checkpoint,
 
-	TP_PROTO(struct super_block *sb, bool is_umount, char *msg),
+	TP_PROTO(struct super_block *sb, int reason, char *msg),
 
-	TP_ARGS(sb, is_umount, msg),
+	TP_ARGS(sb, reason, msg),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
-		__field(bool,	is_umount)
+		__field(int,	reason)
 		__field(char *,	msg)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
-		__entry->is_umount	= is_umount;
+		__entry->reason		= reason;
 		__entry->msg		= msg;
 	),
 
 	TP_printk("dev = (%d,%d), checkpoint for %s, state = %s",
 		show_dev(__entry),
-		__entry->is_umount ? "clean umount" : "consistency",
+		show_cpreason(__entry->reason),
 		__entry->msg)
 );
 
-- 
cgit v1.2.3


From 4b2fecc84655055a6a1fe9151786992ac04b56ce Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Sat, 20 Sep 2014 22:06:39 -0700
Subject: f2fs: introduce FITRIM in f2fs_ioctl

This patch introduces FITRIM in f2fs_ioctl.
In this case, f2fs will issue small discards and prefree discards as many as
possible for the given area.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c        |   4 +-
 fs/f2fs/f2fs.h              |   9 +++-
 fs/f2fs/file.c              |  29 ++++++++++++
 fs/f2fs/segment.c           | 104 +++++++++++++++++++++++++++++++++++++++-----
 fs/f2fs/super.c             |   1 +
 include/trace/events/f2fs.h |   3 +-
 6 files changed, 136 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index efc530cb74a9..4abf0ba01525 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -997,7 +997,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	mutex_lock(&sbi->cp_mutex);
 
-	if (!sbi->s_dirty)
+	if (!sbi->s_dirty && cpc->reason != CP_DISCARD)
 		goto out;
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto out;
@@ -1020,7 +1020,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* write cached NAT/SIT entries to NAT/SIT area */
 	flush_nat_entries(sbi);
-	flush_sit_entries(sbi);
+	flush_sit_entries(sbi, cpc);
 
 	/* unlock all the fs_lock[] in do_checkpoint() */
 	do_checkpoint(sbi, cpc);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 529892418862..7b1e1d20a9c1 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -99,10 +99,15 @@ enum {
 enum {
 	CP_UMOUNT,
 	CP_SYNC,
+	CP_DISCARD,
 };
 
 struct cp_control {
 	int reason;
+	__u64 trim_start;
+	__u64 trim_end;
+	__u64 trim_minlen;
+	__u64 trimmed;
 };
 
 /*
@@ -1276,9 +1281,11 @@ void destroy_flush_cmd_control(struct f2fs_sb_info *);
 void invalidate_blocks(struct f2fs_sb_info *, block_t);
 void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
 void clear_prefree_segments(struct f2fs_sb_info *);
+void release_discard_addrs(struct f2fs_sb_info *);
 void discard_next_dnode(struct f2fs_sb_info *, block_t);
 int npages_for_summary_flush(struct f2fs_sb_info *);
 void allocate_new_segments(struct f2fs_sb_info *);
+int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
 struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
 void write_meta_page(struct f2fs_sb_info *, struct page *);
 void write_node_page(struct f2fs_sb_info *, struct page *,
@@ -1295,7 +1302,7 @@ void write_data_summaries(struct f2fs_sb_info *, block_t);
 void write_node_summaries(struct f2fs_sb_info *, block_t);
 int lookup_journal_in_cursum(struct f2fs_summary_block *,
 					int, unsigned int, int);
-void flush_sit_entries(struct f2fs_sb_info *);
+void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
 int build_segment_manager(struct f2fs_sb_info *);
 void destroy_segment_manager(struct f2fs_sb_info *);
 int __init create_segment_manager_caches(void);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ac8c6804097f..11842076d960 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -860,6 +860,35 @@ out:
 		mnt_drop_write_file(filp);
 		return ret;
 	}
+	case FITRIM:
+	{
+		struct super_block *sb = inode->i_sb;
+		struct request_queue *q = bdev_get_queue(sb->s_bdev);
+		struct fstrim_range range;
+		int ret = 0;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (!blk_queue_discard(q))
+			return -EOPNOTSUPP;
+
+		if (copy_from_user(&range, (struct fstrim_range __user *)arg,
+					sizeof(range)))
+			return -EFAULT;
+
+		range.minlen = max((unsigned int)range.minlen,
+				   q->limits.discard_granularity);
+		ret = f2fs_trim_fs(F2FS_SB(sb), &range);
+		if (ret < 0)
+			return ret;
+
+		if (copy_to_user((struct fstrim_range __user *)arg, &range,
+					sizeof(range)))
+			return -EFAULT;
+
+		return 0;
+	}
 	default:
 		return -ENOTTY;
 	}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 3125a3d35245..fc87da189884 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -386,22 +386,48 @@ void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
 	}
 }
 
-static void add_discard_addrs(struct f2fs_sb_info *sbi,
-			unsigned int segno, struct seg_entry *se)
+static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct list_head *head = &SM_I(sbi)->discard_list;
 	struct discard_entry *new;
 	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
 	int max_blocks = sbi->blocks_per_seg;
+	struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
 	unsigned long dmap[entries];
 	unsigned int start = 0, end = -1;
+	bool force = (cpc->reason == CP_DISCARD);
 	int i;
 
-	if (!test_opt(sbi, DISCARD))
+	if (!force && !test_opt(sbi, DISCARD))
 		return;
 
+	if (force && !se->valid_blocks) {
+		struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+		/*
+		 * if this segment is registered in the prefree list, then
+		 * we should skip adding a discard candidate, and let the
+		 * checkpoint do that later.
+		 */
+		mutex_lock(&dirty_i->seglist_lock);
+		if (test_bit(cpc->trim_start, dirty_i->dirty_segmap[PRE])) {
+			mutex_unlock(&dirty_i->seglist_lock);
+			cpc->trimmed += sbi->blocks_per_seg;
+			return;
+		}
+		mutex_unlock(&dirty_i->seglist_lock);
+
+		new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
+		INIT_LIST_HEAD(&new->list);
+		new->blkaddr = START_BLOCK(sbi, cpc->trim_start);
+		new->len = sbi->blocks_per_seg;
+		list_add_tail(&new->list, head);
+		SM_I(sbi)->nr_discards += sbi->blocks_per_seg;
+		cpc->trimmed += sbi->blocks_per_seg;
+		return;
+	}
+
 	/* zero block will be discarded through the prefree list */
 	if (!se->valid_blocks || se->valid_blocks == max_blocks)
 		return;
@@ -410,23 +436,39 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi,
 	for (i = 0; i < entries; i++)
 		dmap[i] = (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
 
-	while (SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
+	while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
 		start = __find_rev_next_bit(dmap, max_blocks, end + 1);
 		if (start >= max_blocks)
 			break;
 
 		end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
 
+		if (end - start < cpc->trim_minlen)
+			continue;
+
 		new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
 		INIT_LIST_HEAD(&new->list);
-		new->blkaddr = START_BLOCK(sbi, segno) + start;
+		new->blkaddr = START_BLOCK(sbi, cpc->trim_start) + start;
 		new->len = end - start;
+		cpc->trimmed += end - start;
 
 		list_add_tail(&new->list, head);
 		SM_I(sbi)->nr_discards += end - start;
 	}
 }
 
+void release_discard_addrs(struct f2fs_sb_info *sbi)
+{
+	struct list_head *head = &(SM_I(sbi)->discard_list);
+	struct discard_entry *entry, *this;
+
+	/* drop caches */
+	list_for_each_entry_safe(entry, this, head, list) {
+		list_del(&entry->list);
+		kmem_cache_free(discard_entry_slab, entry);
+	}
+}
+
 /*
  * Should call clear_prefree_segments after checkpoint is done.
  */
@@ -897,6 +939,41 @@ static const struct segment_allocation default_salloc_ops = {
 	.allocate_segment = allocate_segment_by_default,
 };
 
+int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
+{
+	block_t start_addr = SM_I(sbi)->main_blkaddr;
+	__u64 start = range->start >> sbi->log_blocksize;
+	__u64 end = start + (range->len >> sbi->log_blocksize) - 1;
+	__u64 segment = 1 << (sbi->log_blocksize + sbi->log_blocks_per_seg);
+	unsigned int start_segno, end_segno;
+	struct cp_control cpc;
+
+	if (range->minlen > segment ||
+			start >= SM_I(sbi)->seg0_blkaddr + TOTAL_BLKS(sbi) ||
+			range->len < sbi->blocksize)
+		return -EINVAL;
+
+	if (end <= start_addr)
+		goto out;
+
+	/* start/end segment number in main_area */
+	start_segno = (start <= start_addr) ? 0 : GET_SEGNO(sbi, start);
+	end_segno = (end >= SM_I(sbi)->seg0_blkaddr + TOTAL_BLKS(sbi)) ?
+				TOTAL_SEGS(sbi) - 1 : GET_SEGNO(sbi, end);
+
+	cpc.reason = CP_DISCARD;
+	cpc.trim_start = start_segno;
+	cpc.trim_end = end_segno;
+	cpc.trim_minlen = range->minlen >> sbi->log_blocksize;
+	cpc.trimmed = 0;
+
+	/* do checkpoint to issue discard commands safely */
+	write_checkpoint(sbi, &cpc);
+out:
+	range->len = cpc.trimmed << sbi->log_blocksize;
+	return 0;
+}
+
 static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -1524,7 +1601,7 @@ static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
  * CP calls this function, which flushes SIT entries including sit_journal,
  * and moves prefree segs to free segs.
  */
-void flush_sit_entries(struct f2fs_sb_info *sbi)
+void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
@@ -1534,6 +1611,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi)
 	struct list_head *head = &SM_I(sbi)->sit_entry_set;
 	unsigned long nsegs = TOTAL_SEGS(sbi);
 	bool to_journal = true;
+	struct seg_entry *se;
 
 	mutex_lock(&curseg->curseg_mutex);
 	mutex_lock(&sit_i->sentry_lock);
@@ -1580,11 +1658,14 @@ void flush_sit_entries(struct f2fs_sb_info *sbi)
 		/* flush dirty sit entries in region of current sit set */
 		for_each_set_bit_from(segno, bitmap, end) {
 			int offset, sit_offset;
-			struct seg_entry *se = get_seg_entry(sbi, segno);
+
+			se = get_seg_entry(sbi, segno);
 
 			/* add discard candidates */
-			if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards)
-				add_discard_addrs(sbi, segno, se);
+			if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards) {
+				cpc->trim_start = segno;
+				add_discard_addrs(sbi, cpc);
+			}
 
 			if (to_journal) {
 				offset = lookup_journal_in_cursum(sum,
@@ -1614,8 +1695,11 @@ void flush_sit_entries(struct f2fs_sb_info *sbi)
 
 	f2fs_bug_on(sbi, !list_empty(head));
 	f2fs_bug_on(sbi, sit_i->dirty_sentries);
-
 out:
+	if (cpc->reason == CP_DISCARD) {
+		for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++)
+			add_discard_addrs(sbi, cpc);
+	}
 	mutex_unlock(&sit_i->sentry_lock);
 	mutex_unlock(&curseg->curseg_mutex);
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 128c42000fa3..bb6b568d6ad4 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -446,6 +446,7 @@ static void f2fs_put_super(struct super_block *sb)
 	 * In addition, EIO will skip do checkpoint, we need this as well.
 	 */
 	release_dirty_inode(sbi);
+	release_discard_addrs(sbi);
 
 	iput(sbi->node_inode);
 	iput(sbi->meta_inode);
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 66eaace9c07e..bbc4de9baef7 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -72,7 +72,8 @@
 #define show_cpreason(type)						\
 	__print_symbolic(type,						\
 		{ CP_UMOUNT,	"Umount" },				\
-		{ CP_SYNC,	"Sync" })
+		{ CP_SYNC,	"Sync" },				\
+		{ CP_DISCARD,	"Discard" })
 
 struct victim_sel_policy;
 
-- 
cgit v1.2.3


From 0b0b0893d49b34201a6c4416b1a707b580b91e3d Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Mon, 29 Sep 2014 15:29:25 +0100
Subject: of/pci: Fix the conversion of IO ranges into IO resources

The ranges property for a host bridge controller in DT describes the
mapping between the PCI bus address and the CPU physical address.  The
resources framework however expects that the IO resources start at a pseudo
"port" address 0 (zero) and have a maximum size of IO_SPACE_LIMIT.  The
conversion from PCI ranges to resources failed to take that into account,
returning a CPU physical address instead of a port number.

Also fix all the drivers that depend on the old behaviour by fetching the
CPU physical address based on the port number where it is being needed.

Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
CC: Grant Likely <grant.likely@linaro.org>
CC: Rob Herring <robh+dt@kernel.org>
CC: Arnd Bergmann <arnd@arndb.de>
CC: Thierry Reding <thierry.reding@gmail.com>
CC: Simon Horman <horms@verge.net.au>
CC: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm/mach-integrator/pci_v3.c | 23 ++++++++++----------
 drivers/of/address.c              | 44 +++++++++++++++++++++++++++++++++++----
 drivers/pci/host/pci-tegra.c      | 10 ++++++---
 drivers/pci/host/pcie-rcar.c      | 21 +++++++++++++------
 include/linux/of_address.h        | 12 +++++------
 5 files changed, 80 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index 05e1f73a1e8d..c186a17c2cff 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -660,6 +660,7 @@ static void __init pci_v3_preinit(void)
 {
 	unsigned long flags;
 	unsigned int temp;
+	phys_addr_t io_address = pci_pio_to_address(io_mem.start);
 
 	pcibios_min_mem = 0x00100000;
 
@@ -701,7 +702,7 @@ static void __init pci_v3_preinit(void)
 	/*
 	 * Setup window 2 - PCI IO
 	 */
-	v3_writel(V3_LB_BASE2, v3_addr_to_lb_base2(io_mem.start) |
+	v3_writel(V3_LB_BASE2, v3_addr_to_lb_base2(io_address) |
 			V3_LB_BASE_ENABLE);
 	v3_writew(V3_LB_MAP2, v3_addr_to_lb_map2(0));
 
@@ -742,6 +743,7 @@ static void __init pci_v3_preinit(void)
 static void __init pci_v3_postinit(void)
 {
 	unsigned int pci_cmd;
+	phys_addr_t io_address = pci_pio_to_address(io_mem.start);
 
 	pci_cmd = PCI_COMMAND_MEMORY |
 		  PCI_COMMAND_MASTER | PCI_COMMAND_INVALIDATE;
@@ -758,7 +760,7 @@ static void __init pci_v3_postinit(void)
 		       "interrupt: %d\n", ret);
 #endif
 
-	register_isa_ports(non_mem.start, io_mem.start, 0);
+	register_isa_ports(non_mem.start, io_address, 0);
 }
 
 /*
@@ -867,33 +869,32 @@ static int __init pci_v3_probe(struct platform_device *pdev)
 
 	for_each_of_pci_range(&parser, &range) {
 		if (!range.flags) {
-			of_pci_range_to_resource(&range, np, &conf_mem);
+			ret = of_pci_range_to_resource(&range, np, &conf_mem);
 			conf_mem.name = "PCIv3 config";
 		}
 		if (range.flags & IORESOURCE_IO) {
-			of_pci_range_to_resource(&range, np, &io_mem);
+			ret = of_pci_range_to_resource(&range, np, &io_mem);
 			io_mem.name = "PCIv3 I/O";
 		}
 		if ((range.flags & IORESOURCE_MEM) &&
 			!(range.flags & IORESOURCE_PREFETCH)) {
 			non_mem_pci = range.pci_addr;
 			non_mem_pci_sz = range.size;
-			of_pci_range_to_resource(&range, np, &non_mem);
+			ret = of_pci_range_to_resource(&range, np, &non_mem);
 			non_mem.name = "PCIv3 non-prefetched mem";
 		}
 		if ((range.flags & IORESOURCE_MEM) &&
 			(range.flags & IORESOURCE_PREFETCH)) {
 			pre_mem_pci = range.pci_addr;
 			pre_mem_pci_sz = range.size;
-			of_pci_range_to_resource(&range, np, &pre_mem);
+			ret = of_pci_range_to_resource(&range, np, &pre_mem);
 			pre_mem.name = "PCIv3 prefetched mem";
 		}
-	}
 
-	if (!conf_mem.start || !io_mem.start ||
-	    !non_mem.start || !pre_mem.start) {
-		dev_err(&pdev->dev, "missing ranges in device node\n");
-		return -EINVAL;
+		if (ret < 0) {
+			dev_err(&pdev->dev, "missing ranges in device node\n");
+			return ret;
+		}
 	}
 
 	pci_v3.map_irq = of_irq_parse_and_map_pci;
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 327a57410797..afdb78299f61 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -295,14 +295,50 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser,
 }
 EXPORT_SYMBOL_GPL(of_pci_range_parser_one);
 
-void of_pci_range_to_resource(struct of_pci_range *range,
-			      struct device_node *np, struct resource *res)
+/*
+ * of_pci_range_to_resource - Create a resource from an of_pci_range
+ * @range:	the PCI range that describes the resource
+ * @np:		device node where the range belongs to
+ * @res:	pointer to a valid resource that will be updated to
+ *              reflect the values contained in the range.
+ *
+ * Returns EINVAL if the range cannot be converted to resource.
+ *
+ * Note that if the range is an IO range, the resource will be converted
+ * using pci_address_to_pio() which can fail if it is called too early or
+ * if the range cannot be matched to any host bridge IO space (our case here).
+ * To guard against that we try to register the IO range first.
+ * If that fails we know that pci_address_to_pio() will do too.
+ */
+int of_pci_range_to_resource(struct of_pci_range *range,
+			     struct device_node *np, struct resource *res)
 {
+	int err;
 	res->flags = range->flags;
-	res->start = range->cpu_addr;
-	res->end = range->cpu_addr + range->size - 1;
 	res->parent = res->child = res->sibling = NULL;
 	res->name = np->full_name;
+
+	if (res->flags & IORESOURCE_IO) {
+		unsigned long port;
+		err = pci_register_io_range(range->cpu_addr, range->size);
+		if (err)
+			goto invalid_range;
+		port = pci_address_to_pio(range->cpu_addr);
+		if (port == (unsigned long)-1) {
+			err = -EINVAL;
+			goto invalid_range;
+		}
+		res->start = port;
+	} else {
+		res->start = range->cpu_addr;
+	}
+	res->end = res->start + range->size - 1;
+	return 0;
+
+invalid_range:
+	res->start = (resource_size_t)OF_BAD_ADDR;
+	res->end = (resource_size_t)OF_BAD_ADDR;
+	return err;
 }
 #endif /* CONFIG_PCI */
 
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 0fb0fdb223d5..946935db62b6 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -626,13 +626,14 @@ DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_relax_enable);
 static int tegra_pcie_setup(int nr, struct pci_sys_data *sys)
 {
 	struct tegra_pcie *pcie = sys_to_pcie(sys);
+	phys_addr_t io_start = pci_pio_to_address(pcie->io.start);
 
 	pci_add_resource_offset(&sys->resources, &pcie->mem, sys->mem_offset);
 	pci_add_resource_offset(&sys->resources, &pcie->prefetch,
 				sys->mem_offset);
 	pci_add_resource(&sys->resources, &pcie->busn);
 
-	pci_ioremap_io(nr * SZ_64K, pcie->io.start);
+	pci_ioremap_io(nr * SZ_64K, io_start);
 
 	return 1;
 }
@@ -737,6 +738,7 @@ static irqreturn_t tegra_pcie_isr(int irq, void *arg)
 static void tegra_pcie_setup_translations(struct tegra_pcie *pcie)
 {
 	u32 fpci_bar, size, axi_address;
+	phys_addr_t io_start = pci_pio_to_address(pcie->io.start);
 
 	/* Bar 0: type 1 extended configuration space */
 	fpci_bar = 0xfe100000;
@@ -749,7 +751,7 @@ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie)
 	/* Bar 1: downstream IO bar */
 	fpci_bar = 0xfdfc0000;
 	size = resource_size(&pcie->io);
-	axi_address = pcie->io.start;
+	axi_address = io_start;
 	afi_writel(pcie, axi_address, AFI_AXI_BAR1_START);
 	afi_writel(pcie, size >> 12, AFI_AXI_BAR1_SZ);
 	afi_writel(pcie, fpci_bar, AFI_FPCI_BAR1);
@@ -1520,7 +1522,9 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 	}
 
 	for_each_of_pci_range(&parser, &range) {
-		of_pci_range_to_resource(&range, np, &res);
+		err = of_pci_range_to_resource(&range, np, &res);
+		if (err < 0)
+			return err;
 
 		switch (res.flags & IORESOURCE_TYPE_BITS) {
 		case IORESOURCE_IO:
diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c
index 4884ee5e07d4..61158e03ab5f 100644
--- a/drivers/pci/host/pcie-rcar.c
+++ b/drivers/pci/host/pcie-rcar.c
@@ -323,6 +323,7 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie)
 
 	/* Setup PCIe address space mappings for each resource */
 	resource_size_t size;
+	resource_size_t res_start;
 	u32 mask;
 
 	rcar_pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win));
@@ -335,8 +336,13 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie)
 	mask = (roundup_pow_of_two(size) / SZ_128) - 1;
 	rcar_pci_write_reg(pcie, mask << 7, PCIEPAMR(win));
 
-	rcar_pci_write_reg(pcie, upper_32_bits(res->start), PCIEPARH(win));
-	rcar_pci_write_reg(pcie, lower_32_bits(res->start), PCIEPARL(win));
+	if (res->flags & IORESOURCE_IO)
+		res_start = pci_pio_to_address(res->start);
+	else
+		res_start = res->start;
+
+	rcar_pci_write_reg(pcie, upper_32_bits(res_start), PCIEPARH(win));
+	rcar_pci_write_reg(pcie, lower_32_bits(res_start), PCIEPARL(win));
 
 	/* First resource is for IO */
 	mask = PAR_ENABLE;
@@ -363,9 +369,10 @@ static int rcar_pcie_setup(int nr, struct pci_sys_data *sys)
 
 		rcar_pcie_setup_window(i, pcie);
 
-		if (res->flags & IORESOURCE_IO)
-			pci_ioremap_io(nr * SZ_64K, res->start);
-		else
+		if (res->flags & IORESOURCE_IO) {
+			phys_addr_t io_start = pci_pio_to_address(res->start);
+			pci_ioremap_io(nr * SZ_64K, io_start);
+		} else
 			pci_add_resource(&sys->resources, res);
 	}
 	pci_add_resource(&sys->resources, &pcie->busn);
@@ -935,8 +942,10 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 	}
 
 	for_each_of_pci_range(&parser, &range) {
-		of_pci_range_to_resource(&range, pdev->dev.of_node,
+		err = of_pci_range_to_resource(&range, pdev->dev.of_node,
 						&pcie->res[win++]);
+		if (err < 0)
+			return err;
 
 		if (win > RCAR_PCI_MAX_RESOURCES)
 			break;
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index a38e1c846c23..8cb14eb393d6 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -134,9 +134,9 @@ extern const __be32 *of_get_pci_address(struct device_node *dev, int bar_no,
 			       u64 *size, unsigned int *flags);
 extern int of_pci_address_to_resource(struct device_node *dev, int bar,
 				      struct resource *r);
-extern void of_pci_range_to_resource(struct of_pci_range *range,
-				     struct device_node *np,
-				     struct resource *res);
+extern int of_pci_range_to_resource(struct of_pci_range *range,
+				    struct device_node *np,
+				    struct resource *res);
 #else /* CONFIG_OF_ADDRESS && CONFIG_PCI */
 static inline int of_pci_address_to_resource(struct device_node *dev, int bar,
 				             struct resource *r)
@@ -149,9 +149,9 @@ static inline const __be32 *of_get_pci_address(struct device_node *dev,
 {
 	return NULL;
 }
-static inline void of_pci_range_to_resource(struct of_pci_range *range,
-					    struct device_node *np,
-					    struct resource *res)
+static inline int of_pci_range_to_resource(struct of_pci_range *range,
+					   struct device_node *np,
+					   struct resource *res)
 {
 	return -ENOSYS;
 }
-- 
cgit v1.2.3


From 670ba0c8883b576d0aec28bd7a838358a4be1406 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 29 Sep 2014 15:29:26 +0100
Subject: PCI: Add generic domain handling

The handling of PCI domains (or PCI segments in ACPI speak) is usually a
straightforward affair but its implementation is currently left to the
architectural code, with pci_domain_nr(b) querying the value of the domain
associated with bus b.

This patch introduces CONFIG_PCI_DOMAINS_GENERIC as an option that can be
selected if an architecture wants a simple implementation where the value
of the domain associated with a bus is stored in struct pci_bus.

The architectures that select CONFIG_PCI_DOMAINS_GENERIC will then have to
implement pci_bus_assign_domain_nr() as a way of setting the domain number
associated with a root bus.  All child buses except the root bus will
inherit the domain_nr value from their parent.

Signed-off-by: Catalin Marinas <Catalin.Marinas@arm.com>
[Renamed pci_set_domain_nr() to pci_bus_assign_domain_nr()]
Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Arnd Bergmann <arnd@arndb.de>
---
 drivers/pci/probe.c | 11 ++++++++---
 include/linux/pci.h | 21 +++++++++++++++++++++
 2 files changed, 29 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index e3cf8a2e6292..636d1c9156a9 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -485,7 +485,7 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	}
 }
 
-static struct pci_bus *pci_alloc_bus(void)
+static struct pci_bus *pci_alloc_bus(struct pci_bus *parent)
 {
 	struct pci_bus *b;
 
@@ -500,6 +500,10 @@ static struct pci_bus *pci_alloc_bus(void)
 	INIT_LIST_HEAD(&b->resources);
 	b->max_bus_speed = PCI_SPEED_UNKNOWN;
 	b->cur_bus_speed = PCI_SPEED_UNKNOWN;
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+	if (parent)
+		b->domain_nr = parent->domain_nr;
+#endif
 	return b;
 }
 
@@ -671,7 +675,7 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 	/*
 	 * Allocate a new bus, and inherit stuff from the parent..
 	 */
-	child = pci_alloc_bus();
+	child = pci_alloc_bus(parent);
 	if (!child)
 		return NULL;
 
@@ -1761,13 +1765,14 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 	char bus_addr[64];
 	char *fmt;
 
-	b = pci_alloc_bus();
+	b = pci_alloc_bus(NULL);
 	if (!b)
 		return NULL;
 
 	b->sysdata = sysdata;
 	b->ops = ops;
 	b->number = b->busn_res.start = bus;
+	pci_bus_assign_domain_nr(b, parent);
 	b2 = pci_find_bus(pci_domain_nr(b), bus);
 	if (b2) {
 		/* If we already got to this bus through a different bridge, ignore it */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 61978a460841..a494e5d775c3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -456,6 +456,9 @@ struct pci_bus {
 	unsigned char	primary;	/* number of primary bridge */
 	unsigned char	max_bus_speed;	/* enum pci_bus_speed */
 	unsigned char	cur_bus_speed;	/* enum pci_bus_speed */
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+	int		domain_nr;
+#endif
 
 	char		name[48];
 
@@ -1288,6 +1291,24 @@ static inline int pci_domain_nr(struct pci_bus *bus) { return 0; }
 static inline int pci_proc_domain(struct pci_bus *bus) { return 0; }
 #endif /* CONFIG_PCI_DOMAINS */
 
+/*
+ * Generic implementation for PCI domain support. If your
+ * architecture does not need custom management of PCI
+ * domains then this implementation will be used
+ */
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+static inline int pci_domain_nr(struct pci_bus *bus)
+{
+	return bus->domain_nr;
+}
+void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent);
+#else
+static inline void pci_bus_assign_domain_nr(struct pci_bus *bus,
+					struct device *parent)
+{
+}
+#endif
+
 /* some architectures require additional setup to direct VGA traffic */
 typedef int (*arch_set_vga_state_t)(struct pci_dev *pdev, bool decode,
 		      unsigned int command_bits, u32 flags);
-- 
cgit v1.2.3


From 41e5c0f81d3e676d671d96a0a1fafb27abfbd9d7 Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Mon, 29 Sep 2014 15:29:27 +0100
Subject: of/pci: Add pci_get_new_domain_nr() and of_get_pci_domain_nr()

Add pci_get_new_domain_nr() to allocate a new domain number and
of_get_pci_domain_nr() to retrieve the PCI domain number of a given device
from DT.  Host bridge drivers or architecture-specific code can choose to
implement their PCI domain number policy using these two functions.

Using of_get_pci_domain_nr() guarantees a stable PCI domain number on every
boot provided that all host bridge controllers are assigned a number in the
device tree using "linux,pci-domain" property.  Mixing use of
pci_get_new_domain_nr() and of_get_pci_domain_nr() is not recommended as it
can lead to potentially conflicting domain numbers being assigned to root
buses behind different host bridges.

Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Arnd Bergmann <arnd@arndb.de>
CC: Grant Likely <grant.likely@linaro.org>
CC: Rob Herring <robh+dt@kernel.org>
CC: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/of/of_pci.c    | 25 +++++++++++++++++++++++++
 drivers/pci/pci.c      |  9 +++++++++
 include/linux/of_pci.h |  7 +++++++
 include/linux/pci.h    |  3 +++
 4 files changed, 44 insertions(+)

(limited to 'include')

diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index 848199633798..82d172fa145a 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -89,6 +89,31 @@ int of_pci_parse_bus_range(struct device_node *node, struct resource *res)
 }
 EXPORT_SYMBOL_GPL(of_pci_parse_bus_range);
 
+/**
+ * This function will try to obtain the host bridge domain number by
+ * finding a property called "linux,pci-domain" of the given device node.
+ *
+ * @node: device tree node with the domain information
+ *
+ * Returns the associated domain number from DT in the range [0-0xffff], or
+ * a negative value if the required property is not found.
+ */
+int of_get_pci_domain_nr(struct device_node *node)
+{
+	const __be32 *value;
+	int len;
+	u16 domain;
+
+	value = of_get_property(node, "linux,pci-domain", &len);
+	if (!value || len < sizeof(*value))
+		return -EINVAL;
+
+	domain = (u16)be32_to_cpup(value);
+
+	return domain;
+}
+EXPORT_SYMBOL_GPL(of_get_pci_domain_nr);
+
 #ifdef CONFIG_PCI_MSI
 
 static LIST_HEAD(of_pci_msi_chip_list);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 2c9ac70254e2..d36f35ff6c5d 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4406,6 +4406,15 @@ static void pci_no_domains(void)
 #endif
 }
 
+#ifdef CONFIG_PCI_DOMAINS
+static atomic_t __domain_nr = ATOMIC_INIT(-1);
+
+int pci_get_new_domain_nr(void)
+{
+	return atomic_inc_return(&__domain_nr);
+}
+#endif
+
 /**
  * pci_ext_cfg_avail - can we access extended PCI config space?
  *
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index dde3a4a0fa5d..71062e9602f5 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -15,6 +15,7 @@ struct device_node *of_pci_find_child_device(struct device_node *parent,
 int of_pci_get_devfn(struct device_node *np);
 int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin);
 int of_pci_parse_bus_range(struct device_node *node, struct resource *res);
+int of_get_pci_domain_nr(struct device_node *node);
 #else
 static inline int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq)
 {
@@ -43,6 +44,12 @@ of_pci_parse_bus_range(struct device_node *node, struct resource *res)
 {
 	return -EINVAL;
 }
+
+static inline int
+of_get_pci_domain_nr(struct device_node *node)
+{
+	return -1;
+}
 #endif
 
 #if defined(CONFIG_OF) && defined(CONFIG_PCI_MSI)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index a494e5d775c3..150da2d644e7 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1285,10 +1285,12 @@ void pci_cfg_access_unlock(struct pci_dev *dev);
  */
 #ifdef CONFIG_PCI_DOMAINS
 extern int pci_domains_supported;
+int pci_get_new_domain_nr(void);
 #else
 enum { pci_domains_supported = 0 };
 static inline int pci_domain_nr(struct pci_bus *bus) { return 0; }
 static inline int pci_proc_domain(struct pci_bus *bus) { return 0; }
+static inline int pci_get_new_domain_nr(void) { return -ENOSYS; }
 #endif /* CONFIG_PCI_DOMAINS */
 
 /*
@@ -1417,6 +1419,7 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus,
 
 static inline int pci_domain_nr(struct pci_bus *bus) { return 0; }
 static inline struct pci_dev *pci_dev_get(struct pci_dev *dev) { return NULL; }
+static inline int pci_get_new_domain_nr(void) { return -ENOSYS; }
 
 #define dev_is_pci(d) (false)
 #define dev_is_pf(d) (false)
-- 
cgit v1.2.3


From cbe4097f8ae699ebbdaf8c95ecab38d47e0bd5da Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Mon, 29 Sep 2014 15:29:28 +0100
Subject: of/pci: Add support for parsing PCI host bridge resources from DT

Provide a function to parse the PCI DT ranges that can be used to create a
pci_host_bridge structure together with its associated bus.

Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com>
[make io_base parameter optional]
Signed-off-by: Robert Richter <rrichter@cavium.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Arnd Bergmann <arnd@arndb.de>
CC: Grant Likely <grant.likely@linaro.org>
CC: Rob Herring <robh+dt@kernel.org>
CC: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/of/of_pci.c    | 117 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/of_pci.h |   6 +++
 2 files changed, 123 insertions(+)

(limited to 'include')

diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index 82d172fa145a..8882b467be95 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -1,7 +1,9 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_pci.h>
+#include <linux/slab.h>
 
 static inline int __of_pci_pci_compare(struct device_node *node,
 				       unsigned int data)
@@ -114,6 +116,121 @@ int of_get_pci_domain_nr(struct device_node *node)
 }
 EXPORT_SYMBOL_GPL(of_get_pci_domain_nr);
 
+#if defined(CONFIG_OF_ADDRESS)
+/**
+ * of_pci_get_host_bridge_resources - Parse PCI host bridge resources from DT
+ * @dev: device node of the host bridge having the range property
+ * @busno: bus number associated with the bridge root bus
+ * @bus_max: maximum number of buses for this bridge
+ * @resources: list where the range of resources will be added after DT parsing
+ * @io_base: pointer to a variable that will contain on return the physical
+ * address for the start of the I/O range. Can be NULL if the caller doesn't
+ * expect IO ranges to be present in the device tree.
+ *
+ * It is the caller's job to free the @resources list.
+ *
+ * This function will parse the "ranges" property of a PCI host bridge device
+ * node and setup the resource mapping based on its content. It is expected
+ * that the property conforms with the Power ePAPR document.
+ *
+ * It returns zero if the range parsing has been successful or a standard error
+ * value if it failed.
+ */
+int of_pci_get_host_bridge_resources(struct device_node *dev,
+			unsigned char busno, unsigned char bus_max,
+			struct list_head *resources, resource_size_t *io_base)
+{
+	struct resource *res;
+	struct resource *bus_range;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
+	char range_type[4];
+	int err;
+
+	if (io_base)
+		*io_base = (resource_size_t)OF_BAD_ADDR;
+
+	bus_range = kzalloc(sizeof(*bus_range), GFP_KERNEL);
+	if (!bus_range)
+		return -ENOMEM;
+
+	pr_info("PCI host bridge %s ranges:\n", dev->full_name);
+
+	err = of_pci_parse_bus_range(dev, bus_range);
+	if (err) {
+		bus_range->start = busno;
+		bus_range->end = bus_max;
+		bus_range->flags = IORESOURCE_BUS;
+		pr_info("  No bus range found for %s, using %pR\n",
+			dev->full_name, bus_range);
+	} else {
+		if (bus_range->end > bus_range->start + bus_max)
+			bus_range->end = bus_range->start + bus_max;
+	}
+	pci_add_resource(resources, bus_range);
+
+	/* Check for ranges property */
+	err = of_pci_range_parser_init(&parser, dev);
+	if (err)
+		goto parse_failed;
+
+	pr_debug("Parsing ranges property...\n");
+	for_each_of_pci_range(&parser, &range) {
+		/* Read next ranges element */
+		if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_IO)
+			snprintf(range_type, 4, " IO");
+		else if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_MEM)
+			snprintf(range_type, 4, "MEM");
+		else
+			snprintf(range_type, 4, "err");
+		pr_info("  %s %#010llx..%#010llx -> %#010llx\n", range_type,
+			range.cpu_addr, range.cpu_addr + range.size - 1,
+			range.pci_addr);
+
+		/*
+		 * If we failed translation or got a zero-sized region
+		 * then skip this range
+		 */
+		if (range.cpu_addr == OF_BAD_ADDR || range.size == 0)
+			continue;
+
+		res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+		if (!res) {
+			err = -ENOMEM;
+			goto parse_failed;
+		}
+
+		err = of_pci_range_to_resource(&range, dev, res);
+		if (err)
+			goto conversion_failed;
+
+		if (resource_type(res) == IORESOURCE_IO) {
+			if (!io_base) {
+				pr_err("I/O range found for %s. Please provide an io_base pointer to save CPU base address\n",
+					dev->full_name);
+				err = -EINVAL;
+				goto conversion_failed;
+			}
+			if (*io_base != (resource_size_t)OF_BAD_ADDR)
+				pr_warn("More than one I/O resource converted for %s. CPU base address for old range lost!\n",
+					dev->full_name);
+			*io_base = range.cpu_addr;
+		}
+
+		pci_add_resource_offset(resources, res,	res->start - range.pci_addr);
+	}
+
+	return 0;
+
+conversion_failed:
+	kfree(res);
+parse_failed:
+	pci_free_resource_list(resources);
+	return err;
+}
+EXPORT_SYMBOL_GPL(of_pci_get_host_bridge_resources);
+#endif /* CONFIG_OF_ADDRESS */
+
 #ifdef CONFIG_PCI_MSI
 
 static LIST_HEAD(of_pci_msi_chip_list);
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index 71062e9602f5..1fd207e7a847 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -52,6 +52,12 @@ of_get_pci_domain_nr(struct device_node *node)
 }
 #endif
 
+#if defined(CONFIG_OF_ADDRESS)
+int of_pci_get_host_bridge_resources(struct device_node *dev,
+			unsigned char busno, unsigned char bus_max,
+			struct list_head *resources, resource_size_t *io_base);
+#endif
+
 #if defined(CONFIG_OF) && defined(CONFIG_PCI_MSI)
 int of_pci_msi_chip_add(struct msi_chip *chip);
 void of_pci_msi_chip_remove(struct msi_chip *chip);
-- 
cgit v1.2.3


From 8b921acfeffdb0b45085da862fc301a2d25ed2cf Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Mon, 29 Sep 2014 15:29:30 +0100
Subject: PCI: Add pci_remap_iospace() to map bus I/O resources

Add pci_remap_iospace() to map bus I/O resources into the CPU virtual
address space.  Architectures with special needs may provide their own
version, but most should be able to use this one.

This function is useful for PCI host bridge drivers that need to map the
PCI I/O resources into virtual memory space.

[bhelgaas: phys_addr description, drop temporary "err" variable]
Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
CC: Arnd Bergmann <arnd@arndb.de>
---
 drivers/pci/pci.c             | 31 +++++++++++++++++++++++++++++++
 include/asm-generic/pgtable.h |  4 ++++
 include/linux/pci.h           |  3 +++
 3 files changed, 38 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index d36f35ff6c5d..6e994fc077f4 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2704,6 +2704,37 @@ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name)
 }
 EXPORT_SYMBOL(pci_request_regions_exclusive);
 
+/**
+ *	pci_remap_iospace - Remap the memory mapped I/O space
+ *	@res: Resource describing the I/O space
+ *	@phys_addr: physical address of range to be mapped
+ *
+ *	Remap the memory mapped I/O space described by the @res
+ *	and the CPU physical address @phys_addr into virtual address space.
+ *	Only architectures that have memory mapped IO functions defined
+ *	(and the PCI_IOBASE value defined) should call this function.
+ */
+int __weak pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
+{
+#if defined(PCI_IOBASE) && defined(CONFIG_MMU)
+	unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start;
+
+	if (!(res->flags & IORESOURCE_IO))
+		return -EINVAL;
+
+	if (res->end > IO_SPACE_LIMIT)
+		return -EINVAL;
+
+	return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr,
+				  pgprot_device(PAGE_KERNEL));
+#else
+	/* this architecture does not have memory mapped I/O space,
+	   so this function should never be called */
+	WARN_ONCE(1, "This architecture does not support memory mapped I/O\n");
+	return -ENODEV;
+#endif
+}
+
 static void __pci_set_master(struct pci_dev *dev, bool enable)
 {
 	u16 old_cmd, cmd;
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 53b2acc38213..977e545a64c3 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -249,6 +249,10 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #define pgprot_writecombine pgprot_noncached
 #endif
 
+#ifndef pgprot_device
+#define pgprot_device pgprot_noncached
+#endif
+
 /*
  * When walking page tables, get the address of the next boundary,
  * or the end address of the range if that comes earlier.  Although no
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 150da2d644e7..b4995fdfffb1 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1100,6 +1100,9 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus,
 						  resource_size_t),
 			void *alignf_data);
 
+
+int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
+
 static inline dma_addr_t pci_bus_address(struct pci_dev *pdev, int bar)
 {
 	struct pci_bus_region region;
-- 
cgit v1.2.3


From 7704ac937345d4b502062952657027234aa86a37 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Tue, 23 Sep 2014 12:08:08 -0400
Subject: HID: wacom: implement generic HID handling for pen generic devices

ISDv4 and v5 are plain HID devices. We can directly implement a generic
HID parsing/handling and remove the need to manually add those PID in
the list of supported devices.

This patch implements the pen support only. The finger part will come in
a later patch.

To be properly notified of an .event() and a .report(), we need to force
hid-core to go through the HID parsing. By default, wacom.ko binds only
hidraw, so the hid parsing is not done by hid-core. When a true HID device
is there, we add the flag HID_CLAIMED_DRIVER to hid->claimed which will
force hid-core to parse the incoming reports.
(Note that this can be easily backported by directly setting the .claimed
flag to HID_CLAIMED_DRIVER even if hid-core does not support
HID_CONNECT_DRIVER)

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Acked-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c  |   3 +
 drivers/hid/wacom.h     |   6 ++
 drivers/hid/wacom_sys.c |  12 +++-
 drivers/hid/wacom_wac.c | 179 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/hid/wacom_wac.h |   8 +++
 include/linux/hid.h     |   2 +
 6 files changed, 208 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 12b6e67d9de0..583344dba3c6 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1591,6 +1591,9 @@ int hid_connect(struct hid_device *hdev, unsigned int connect_mask)
 	if ((connect_mask & HID_CONNECT_HIDRAW) && !hidraw_connect(hdev))
 		hdev->claimed |= HID_CLAIMED_HIDRAW;
 
+	if (connect_mask & HID_CONNECT_DRIVER)
+		hdev->claimed |= HID_CLAIMED_DRIVER;
+
 	/* Drivers with the ->raw_event callback set are not required to connect
 	 * to any other listener. */
 	if (!hdev->claimed && !hdev->driver->raw_event) {
diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h
index 64bc1b296d91..0cc53440543a 100644
--- a/drivers/hid/wacom.h
+++ b/drivers/hid/wacom.h
@@ -89,6 +89,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
+#include <linux/hid.h>
 #include <linux/usb/input.h>
 #include <linux/power_supply.h>
 #include <asm/unaligned.h>
@@ -143,4 +144,9 @@ int wacom_setup_input_capabilities(struct input_dev *input_dev,
 				   struct wacom_wac *wacom_wac);
 int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 				       struct wacom_wac *wacom_wac);
+void wacom_wac_usage_mapping(struct hid_device *hdev,
+		struct hid_field *field, struct hid_usage *usage);
+int wacom_wac_event(struct hid_device *hdev, struct hid_field *field,
+		struct hid_usage *usage, __s32 value);
+void wacom_wac_report(struct hid_device *hdev, struct hid_report *report);
 #endif
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 21ac2baa21be..dd288b2fbfe8 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -13,7 +13,6 @@
 
 #include "wacom_wac.h"
 #include "wacom.h"
-#include <linux/hid.h>
 
 #define WAC_MSG_RETRIES		5
 
@@ -215,6 +214,9 @@ static void wacom_usage_mapping(struct hid_device *hdev,
 			features->pressure_max = field->logical_maximum;
 		break;
 	}
+
+	if (features->type == HID_GENERIC)
+		wacom_wac_usage_mapping(hdev, field, usage);
 }
 
 static void wacom_parse_hid(struct hid_device *hdev,
@@ -1318,6 +1320,7 @@ static int wacom_probe(struct hid_device *hdev,
 	struct wacom_wac *wacom_wac;
 	struct wacom_features *features;
 	int error;
+	unsigned int connect_mask = HID_CONNECT_HIDRAW;
 
 	if (!id->driver_data)
 		return -EINVAL;
@@ -1451,8 +1454,11 @@ static int wacom_probe(struct hid_device *hdev,
 	/* Note that if query fails it is not a hard failure */
 	wacom_query_tablet_data(hdev, features);
 
+	if (features->type == HID_GENERIC)
+		connect_mask |= HID_CONNECT_DRIVER;
+
 	/* Regular HID work starts now */
-	error = hid_hw_start(hdev, HID_CONNECT_HIDRAW);
+	error = hid_hw_start(hdev, connect_mask);
 	if (error) {
 		hid_err(hdev, "hw start failed\n");
 		goto fail_hw_start;
@@ -1532,6 +1538,8 @@ static struct hid_driver wacom_driver = {
 	.id_table =	wacom_ids,
 	.probe =	wacom_probe,
 	.remove =	wacom_remove,
+	.event =	wacom_wac_event,
+	.report =	wacom_wac_report,
 #ifdef CONFIG_PM
 	.resume =	wacom_resume,
 	.reset_resume =	wacom_reset_resume,
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index b8180e40534d..e77d46d85a11 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -1248,6 +1248,176 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 	return 0;
 }
 
+static void wacom_map_usage(struct wacom *wacom, struct hid_usage *usage,
+		struct hid_field *field, __u8 type, __u16 code, int fuzz)
+{
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct input_dev *input = wacom_wac->input;
+	int fmin = field->logical_minimum;
+	int fmax = field->logical_maximum;
+
+	usage->type = type;
+	usage->code = code;
+
+	set_bit(type, input->evbit);
+
+	switch (type) {
+	case EV_ABS:
+		input_set_abs_params(input, code, fmin, fmax, fuzz, 0);
+		input_abs_set_res(input, code,
+				  hidinput_calc_abs_res(field, code));
+		break;
+	case EV_KEY:
+		input_set_capability(input, EV_KEY, code);
+		break;
+	case EV_MSC:
+		input_set_capability(input, EV_MSC, code);
+		break;
+	}
+}
+
+static void wacom_wac_pen_usage_mapping(struct hid_device *hdev,
+		struct hid_field *field, struct hid_usage *usage)
+{
+	struct wacom *wacom = hid_get_drvdata(hdev);
+
+	switch (usage->hid) {
+	case HID_GD_X:
+		wacom_map_usage(wacom, usage, field, EV_ABS, ABS_X, 4);
+		break;
+	case HID_GD_Y:
+		wacom_map_usage(wacom, usage, field, EV_ABS, ABS_Y, 4);
+		break;
+	case HID_DG_TIPPRESSURE:
+		wacom_map_usage(wacom, usage, field, EV_ABS, ABS_PRESSURE, 0);
+		break;
+	case HID_DG_INRANGE:
+		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_TOOL_PEN, 0);
+		break;
+	case HID_DG_INVERT:
+		wacom_map_usage(wacom, usage, field, EV_KEY,
+				BTN_TOOL_RUBBER, 0);
+		break;
+	case HID_DG_ERASER:
+	case HID_DG_TIPSWITCH:
+		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_TOUCH, 0);
+		break;
+	case HID_DG_BARRELSWITCH:
+		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_STYLUS, 0);
+		break;
+	case HID_DG_BARRELSWITCH2:
+		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_STYLUS2, 0);
+		break;
+	case HID_DG_TOOLSERIALNUMBER:
+		wacom_map_usage(wacom, usage, field, EV_MSC, MSC_SERIAL, 0);
+		break;
+	}
+}
+
+static int wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field,
+		struct hid_usage *usage, __s32 value)
+{
+	struct wacom *wacom = hid_get_drvdata(hdev);
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct input_dev *input = wacom_wac->input;
+
+	/* checking which Tool / tip switch to send */
+	switch (usage->hid) {
+	case HID_DG_INRANGE:
+		wacom_wac->hid_data.inrange_state = value;
+		return 0;
+	case HID_DG_INVERT:
+		wacom_wac->hid_data.invert_state = value;
+		return 0;
+	case HID_DG_ERASER:
+	case HID_DG_TIPSWITCH:
+		wacom_wac->hid_data.tipswitch |= value;
+		return 0;
+	}
+
+	/* send pen events only when touch is up or forced out */
+	if (!usage->type || wacom_wac->shared->touch_down)
+		return 0;
+
+	input_event(input, usage->type, usage->code, value);
+
+	return 0;
+}
+
+static void wacom_wac_pen_report(struct hid_device *hdev,
+		struct hid_report *report)
+{
+	struct wacom *wacom = hid_get_drvdata(hdev);
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct input_dev *input = wacom_wac->input;
+	bool prox = wacom_wac->hid_data.inrange_state;
+
+	if (!wacom_wac->shared->stylus_in_proximity) /* first in prox */
+		/* Going into proximity select tool */
+		wacom_wac->tool[0] = wacom_wac->hid_data.invert_state ?
+						BTN_TOOL_RUBBER : BTN_TOOL_PEN;
+
+	/* keep pen state for touch events */
+	wacom_wac->shared->stylus_in_proximity = prox;
+
+	/* send pen events only when touch is up or forced out */
+	if (!wacom_wac->shared->touch_down) {
+		input_report_key(input, BTN_TOUCH,
+				wacom_wac->hid_data.tipswitch);
+		input_report_key(input, wacom_wac->tool[0], prox);
+
+		wacom_wac->hid_data.tipswitch = false;
+
+		input_sync(input);
+	}
+}
+
+#define WACOM_PEN_FIELD(f)	(((f)->logical == HID_DG_STYLUS) || \
+				 ((f)->physical == HID_DG_STYLUS))
+#define WACOM_FINGER_FIELD(f)	(((f)->logical == HID_DG_FINGER) || \
+				 ((f)->physical == HID_DG_FINGER))
+
+void wacom_wac_usage_mapping(struct hid_device *hdev,
+		struct hid_field *field, struct hid_usage *usage)
+{
+	struct wacom *wacom = hid_get_drvdata(hdev);
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct input_dev *input = wacom_wac->input;
+
+	/* currently, only direct devices have proper hid report descriptors */
+	__set_bit(INPUT_PROP_DIRECT, input->propbit);
+
+	if (WACOM_PEN_FIELD(field))
+		return wacom_wac_pen_usage_mapping(hdev, field, usage);
+}
+
+int wacom_wac_event(struct hid_device *hdev, struct hid_field *field,
+		struct hid_usage *usage, __s32 value)
+{
+	struct wacom *wacom = hid_get_drvdata(hdev);
+
+	if (wacom->wacom_wac.features.type != HID_GENERIC)
+		return 0;
+
+	if (WACOM_PEN_FIELD(field))
+		return wacom_wac_pen_event(hdev, field, usage, value);
+
+	return 0;
+}
+
+void wacom_wac_report(struct hid_device *hdev, struct hid_report *report)
+{
+	struct wacom *wacom = hid_get_drvdata(hdev);
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct hid_field *field = report->field[0];
+
+	if (wacom_wac->features.type != HID_GENERIC)
+		return;
+
+	if (WACOM_PEN_FIELD(field))
+		return wacom_wac_pen_report(hdev, report);
+}
+
 static int wacom_bpt_touch(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
@@ -1746,6 +1916,10 @@ int wacom_setup_input_capabilities(struct input_dev *input_dev,
 
 	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
 
+	if (features->type == HID_GENERIC)
+		/* setup has already been done */
+		return 0;
+
 	__set_bit(BTN_TOUCH, input_dev->keybit);
 	__set_bit(ABS_MISC, input_dev->absbit);
 
@@ -2585,6 +2759,9 @@ static const struct wacom_features wacom_features_0x30C =
 	  .oVid = USB_VENDOR_ID_WACOM, .oPid = 0x30A, .touch_max = 10,
 	  .check_for_hid_type = true, .hid_type = HID_TYPE_USBNONE };
 
+static const struct wacom_features wacom_features_HID_ANY_ID =
+	{ "Wacom HID", .type = HID_GENERIC };
+
 #define USB_DEVICE_WACOM(prod)						\
 	HID_DEVICE(BUS_USB, HID_GROUP_WACOM, USB_VENDOR_ID_WACOM, prod),\
 	.driver_data = (kernel_ulong_t)&wacom_features_##prod
@@ -2729,6 +2906,8 @@ const struct hid_device_id wacom_ids[] = {
 	{ USB_DEVICE_WACOM(0x4004) },
 	{ USB_DEVICE_WACOM(0x5000) },
 	{ USB_DEVICE_WACOM(0x5002) },
+
+	{ USB_DEVICE_WACOM(HID_ANY_ID) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, wacom_ids);
diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
index 72f9ca8e5cd4..f472eac292d5 100644
--- a/drivers/hid/wacom_wac.h
+++ b/drivers/hid/wacom_wac.h
@@ -113,6 +113,7 @@ enum {
 	MTSCREEN,
 	MTTPC,
 	MTTPC_B,
+	HID_GENERIC,
 	MAX_TYPE
 };
 
@@ -154,6 +155,12 @@ struct wacom_shared {
 	struct input_dev *touch_input;
 };
 
+struct hid_data {
+	bool inrange_state;
+	bool invert_state;
+	bool tipswitch;
+};
+
 struct wacom_wac {
 	char name[WACOM_NAME_MAX];
 	char pad_name[WACOM_NAME_MAX];
@@ -175,6 +182,7 @@ struct wacom_wac {
 	int ps_connected;
 	u8 bt_features;
 	u8 bt_high_speed;
+	struct hid_data hid_data;
 };
 
 #endif
diff --git a/include/linux/hid.h b/include/linux/hid.h
index f53c4a9cca1d..3dcd00496064 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -265,6 +265,7 @@ struct hid_item {
 #define HID_CONNECT_HIDDEV		0x08
 #define HID_CONNECT_HIDDEV_FORCE	0x10
 #define HID_CONNECT_FF			0x20
+#define HID_CONNECT_DRIVER		0x40
 #define HID_CONNECT_DEFAULT	(HID_CONNECT_HIDINPUT|HID_CONNECT_HIDRAW| \
 		HID_CONNECT_HIDDEV|HID_CONNECT_FF)
 
@@ -440,6 +441,7 @@ struct hid_output_fifo {
 #define HID_CLAIMED_INPUT	1
 #define HID_CLAIMED_HIDDEV	2
 #define HID_CLAIMED_HIDRAW	4
+#define HID_CLAIMED_DRIVER	8
 
 #define HID_STAT_ADDED		1
 #define HID_STAT_PARSED		2
-- 
cgit v1.2.3


From 45341ca3fcacc8720c425e757a627ef81b65b1ee Mon Sep 17 00:00:00 2001
From: Subhash Jadavani <subhashj@codeaurora.org>
Date: Thu, 25 Sep 2014 15:32:19 +0300
Subject: scsi: fix the type for well known LUs

Some devices may respond with wrong type for well-known logical units.
This patch forces well-known type for devices which doesn't report it
correct.

Signed-off-by: Subhash Jadavani <subhashj@codeaurora.org>
Signed-off-by: Sujit Reddy Thumma <sthumma@codeaurora.org>
Signed-off-by: Dolev Raviv <draviv@codeaurora.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/scsi_scan.c | 13 +++++++++++++
 include/scsi/scsi.h      |  1 +
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index f84c40188478..dde0c542e0b1 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -815,6 +815,19 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	} else {
 		sdev->type = (inq_result[0] & 0x1f);
 		sdev->removable = (inq_result[1] & 0x80) >> 7;
+
+		/*
+		 * some devices may respond with wrong type for
+		 * well-known logical units. Force well-known type
+		 * to enumerate them correctly.
+		 */
+		if (scsi_is_wlun(sdev->lun) && sdev->type != TYPE_WLUN) {
+			sdev_printk(KERN_WARNING, sdev,
+				"%s: correcting incorrect peripheral device type 0x%x for W-LUN 0x%16xhN\n",
+				__func__, sdev->type, (unsigned int)sdev->lun);
+			sdev->type = TYPE_WLUN;
+		}
+
 	}
 
 	if (sdev->type == TYPE_RBC || sdev->type == TYPE_ROM) {
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 261e708010da..d17178e6fcdd 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -333,6 +333,7 @@ static inline int scsi_status_is_good(int status)
 #define TYPE_RBC	    0x0e
 #define TYPE_OSD            0x11
 #define TYPE_ZBC            0x14
+#define TYPE_WLUN           0x1e    /* well-known logical unit */
 #define TYPE_NO_LUN         0x7f
 
 /* SCSI protocols; these are taken from SPC-3 section 7.5 */
-- 
cgit v1.2.3


From ad975ebad4c3ce8dcc7d0bb4db26ea5aca4cfc99 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@redhat.com>
Date: Tue, 23 Sep 2014 12:39:54 -0600
Subject: PCI/MSI: Remove arch_msi_check_device()

No architectures implement arch_msi_check_device() or the struct msi_chip
.check_device() method, so remove them.

Remove the "type" parameter to pci_msi_check_device() because it was only
used to call arch_msi_check_device() and is no longer needed.

[bhelgaas: changelog, split to separate patch]
Signed-off-by: Alexander Gordeev <agordeev@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/msi.c   | 21 +++------------------
 include/linux/msi.h |  3 ---
 2 files changed, 3 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 5a40516444f3..db21b77a03a5 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -56,16 +56,6 @@ void __weak arch_teardown_msi_irq(unsigned int irq)
 	chip->teardown_irq(chip, irq);
 }
 
-int __weak arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
-{
-	struct msi_chip *chip = dev->bus->msi;
-
-	if (!chip || !chip->check_device)
-		return 0;
-
-	return chip->check_device(chip, dev, nvec, type);
-}
-
 int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	struct msi_desc *entry;
@@ -815,10 +805,9 @@ out_free:
  * to determine if MSI/-X are supported for the device. If MSI/-X is
  * supported return 0, else return an error code.
  **/
-static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type)
+static int pci_msi_check_device(struct pci_dev *dev, int nvec)
 {
 	struct pci_bus *bus;
-	int ret;
 
 	/* MSI must be globally enabled and supported by the device */
 	if (!pci_msi_enable || !dev || dev->no_msi)
@@ -843,10 +832,6 @@ static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type)
 		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
 			return -EINVAL;
 
-	ret = arch_msi_check_device(dev, nvec, type);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 
@@ -952,7 +937,7 @@ int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
 	if (!entries || !dev->msix_cap || dev->current_state != PCI_D0)
 		return -EINVAL;
 
-	status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSIX);
+	status = pci_msi_check_device(dev, nvec);
 	if (status)
 		return status;
 
@@ -1086,7 +1071,7 @@ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
 		nvec = maxvec;
 
 	do {
-		rc = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI);
+		rc = pci_msi_check_device(dev, nvec);
 		if (rc < 0) {
 			return rc;
 		} else if (rc > 0) {
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 8103f32f6d87..dbf7cc932444 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -60,7 +60,6 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc);
 void arch_teardown_msi_irq(unsigned int irq);
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
 void arch_teardown_msi_irqs(struct pci_dev *dev);
-int arch_msi_check_device(struct pci_dev* dev, int nvec, int type);
 void arch_restore_msi_irqs(struct pci_dev *dev);
 
 void default_teardown_msi_irqs(struct pci_dev *dev);
@@ -77,8 +76,6 @@ struct msi_chip {
 	int (*setup_irq)(struct msi_chip *chip, struct pci_dev *dev,
 			 struct msi_desc *desc);
 	void (*teardown_irq)(struct msi_chip *chip, unsigned int irq);
-	int (*check_device)(struct msi_chip *chip, struct pci_dev *dev,
-			    int nvec, int type);
 };
 
 #endif /* LINUX_MSI_H */
-- 
cgit v1.2.3


From 81052769e48609525c452d8f078a5786b673e178 Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Tue, 23 Sep 2014 13:27:22 +0800
Subject: PCI/MSI: Remove unused kobject from struct msi_desc

After commit 1c51b50c2995 ("PCI/MSI: Export MSI mode using attributes, not
kobjects"), the kobject in struct msi_desc is unused.

Remove the unused struct kobject from struct msi_desc.

[bhelgaas: changelog]
Fixes: 1c51b50c2995 ("PCI/MSI: Export MSI mode using attributes, not kobjects")
Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/msi.c   | 11 -----------
 include/linux/msi.h |  2 --
 2 files changed, 13 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 5f1e5dc994cf..97d6ef67a3c8 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -374,17 +374,6 @@ static void free_msi_irqs(struct pci_dev *dev)
 				iounmap(entry->mask_base);
 		}
 
-		/*
-		 * Its possible that we get into this path
-		 * When populate_msi_sysfs fails, which means the entries
-		 * were not registered with sysfs.  In that case don't
-		 * unregister them.
-		 */
-		if (entry->kobj.parent) {
-			kobject_del(&entry->kobj);
-			kobject_put(&entry->kobj);
-		}
-
 		list_del(&entry->list);
 		kfree(entry);
 	}
diff --git a/include/linux/msi.h b/include/linux/msi.h
index dbf7cc932444..5a91c2d58ffd 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -47,8 +47,6 @@ struct msi_desc {
 
 	/* Last set MSI message */
 	struct msi_msg msg;
-
-	struct kobject kobj;
 };
 
 /*
-- 
cgit v1.2.3


From 48c3c38f003c25d50a09d3da558667c5ecd530aa Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Tue, 23 Sep 2014 11:02:42 -0600
Subject: PCI/MSI: Remove "pos" from the struct msi_desc msi_attrib

"msi_attrib.pos" is only used for MSI (not MSI-X), and we already cache the
MSI capability offset in "dev->msi_cap".

Remove "pos" from the struct msi_attrib and use "dev->msi_cap" directly.

[bhelgaas: changelog, fix whitespace]
Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/mips/pci/msi-octeon.c         | 6 ++----
 drivers/pci/host/pcie-designware.c | 5 ++---
 drivers/pci/msi.c                  | 2 --
 include/linux/msi.h                | 1 -
 4 files changed, 4 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index ab0c5d14c6f7..63bbe07a1ccd 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -73,8 +73,7 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 	 * wants.  Most devices only want 1, which will give
 	 * configured_private_bits and request_private_bits equal 0.
 	 */
-	pci_read_config_word(dev, desc->msi_attrib.pos + PCI_MSI_FLAGS,
-			     &control);
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
 
 	/*
 	 * If the number of private bits has been configured then use
@@ -176,8 +175,7 @@ msi_irq_allocated:
 	/* Update the number of IRQs the device has available to it */
 	control &= ~PCI_MSI_FLAGS_QSIZE;
 	control |= request_private_bits << 4;
-	pci_write_config_word(dev, desc->msi_attrib.pos + PCI_MSI_FLAGS,
-			      control);
+	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
 
 	irq_set_msi_desc(irq, desc);
 	write_msi_msg(irq, &msg);
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 52bd3a143563..fa2fa459ed90 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -355,9 +355,8 @@ static int dw_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
 		return -EINVAL;
 	}
 
-	pci_read_config_word(pdev, desc->msi_attrib.pos+PCI_MSI_FLAGS,
-				&msg_ctr);
-	msgvec = (msg_ctr&PCI_MSI_FLAGS_QSIZE) >> 4;
+	pci_read_config_word(pdev, pdev->msi_cap + PCI_MSI_FLAGS, &msg_ctr);
+	msgvec = (msg_ctr & PCI_MSI_FLAGS_QSIZE) >> 4;
 	if (msgvec == 0)
 		msgvec = (msg_ctr & PCI_MSI_FLAGS_QMASK) >> 1;
 	if (msgvec > 5)
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 97d6ef67a3c8..40699a2041b5 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -574,7 +574,6 @@ static struct msi_desc *msi_setup_entry(struct pci_dev *dev)
 	entry->msi_attrib.entry_nr	= 0;
 	entry->msi_attrib.maskbit	= !!(control & PCI_MSI_FLAGS_MASKBIT);
 	entry->msi_attrib.default_irq	= dev->irq;	/* Save IOAPIC IRQ */
-	entry->msi_attrib.pos		= dev->msi_cap;
 	entry->msi_attrib.multi_cap	= (control & PCI_MSI_FLAGS_QMASK) >> 1;
 
 	if (control & PCI_MSI_FLAGS_64BIT)
@@ -678,7 +677,6 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 		entry->msi_attrib.is_64		= 1;
 		entry->msi_attrib.entry_nr	= entries[i].entry;
 		entry->msi_attrib.default_irq	= dev->irq;
-		entry->msi_attrib.pos		= dev->msix_cap;
 		entry->mask_base		= base;
 
 		list_add_tail(&entry->list, &dev->msi_list);
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 5a91c2d58ffd..44f4746d033b 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -29,7 +29,6 @@ struct msi_desc {
 		__u8	multi_cap : 3;	/* log2 num of messages supported */
 		__u8	maskbit	: 1;	/* mask-pending bit supported ? */
 		__u8	is_64	: 1;	/* Address size: 0=32bit 1=64bit */
-		__u8	pos;		/* Location of the msi capability */
 		__u16	entry_nr;	/* specific enabled entry */
 		unsigned default_irq;	/* default pre-assigned irq */
 	} msi_attrib;
-- 
cgit v1.2.3


From f3fa1bbd836a7d6efb2abd506ed8e24096f39062 Mon Sep 17 00:00:00 2001
From: Oder Chiou <oder_chiou@realtek.com>
Date: Fri, 19 Sep 2014 19:15:45 +0800
Subject: ASoC: rt5645: Add headset detect function

Add headset detect function

Signed-off-by: Oder Chiou <oder_chiou@realtek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/rt5645.h    |  3 ++
 sound/soc/codecs/rt5645.c | 99 +++++++++++++++++++++++++++++++++++++++++++++++
 sound/soc/codecs/rt5645.h |  5 +++
 3 files changed, 107 insertions(+)

(limited to 'include')

diff --git a/include/sound/rt5645.h b/include/sound/rt5645.h
index 1de744c242f6..a5352712194b 100644
--- a/include/sound/rt5645.h
+++ b/include/sound/rt5645.h
@@ -20,6 +20,9 @@ struct rt5645_platform_data {
 	/* 0 = IN2N; 1 = GPIO5; 2 = GPIO11 */
 	unsigned int dmic2_data_pin;
 	/* 0 = IN2P; 1 = GPIO6; 2 = GPIO10; 3 = GPIO12 */
+
+	unsigned int hp_det_gpio;
+	bool gpio_hp_det_active_high;
 };
 
 #endif
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index a7762d0a623e..3fb83bf09768 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -17,6 +17,7 @@
 #include <linux/i2c.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
+#include <linux/gpio.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -2103,6 +2104,77 @@ static int rt5645_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
+static int rt5645_jack_detect(struct snd_soc_codec *codec,
+	struct snd_soc_jack *jack)
+{
+	struct rt5645_priv *rt5645 = snd_soc_codec_get_drvdata(codec);
+	int gpio_state, jack_type = 0;
+	unsigned int val;
+
+	gpio_state = gpio_get_value(rt5645->pdata.hp_det_gpio);
+
+	dev_dbg(codec->dev, "gpio = %d(%d)\n", rt5645->pdata.hp_det_gpio,
+		gpio_state);
+
+	if ((rt5645->pdata.gpio_hp_det_active_high && gpio_state) ||
+		(!rt5645->pdata.gpio_hp_det_active_high && !gpio_state)) {
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "micbias1");
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "micbias2");
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "LDO2");
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "Mic Det Power");
+		snd_soc_dapm_sync(&codec->dapm);
+
+		snd_soc_write(codec, RT5645_IN1_CTRL1, 0x0006);
+		snd_soc_write(codec, RT5645_JD_CTRL3, 0x00b0);
+
+		snd_soc_update_bits(codec, RT5645_IN1_CTRL2,
+			RT5645_CBJ_MN_JD, 0);
+		snd_soc_update_bits(codec, RT5645_IN1_CTRL2,
+			RT5645_CBJ_MN_JD, RT5645_CBJ_MN_JD);
+
+		msleep(400);
+		val = snd_soc_read(codec, RT5645_IN1_CTRL3) & 0x7;
+		dev_dbg(codec->dev, "val = %d\n", val);
+
+		if (val == 1 || val == 2)
+			jack_type = SND_JACK_HEADSET;
+		else
+			jack_type = SND_JACK_HEADPHONE;
+
+		snd_soc_dapm_disable_pin(&codec->dapm, "micbias1");
+		snd_soc_dapm_disable_pin(&codec->dapm, "micbias2");
+		snd_soc_dapm_disable_pin(&codec->dapm, "LDO2");
+		snd_soc_dapm_disable_pin(&codec->dapm, "Mic Det Power");
+		snd_soc_dapm_sync(&codec->dapm);
+	}
+
+	snd_soc_jack_report(rt5645->jack, jack_type, SND_JACK_HEADSET);
+
+	return 0;
+}
+
+int rt5645_set_jack_detect(struct snd_soc_codec *codec,
+	struct snd_soc_jack *jack)
+{
+	struct rt5645_priv *rt5645 = snd_soc_codec_get_drvdata(codec);
+
+	rt5645->jack = jack;
+
+	rt5645_jack_detect(codec, rt5645->jack);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rt5645_set_jack_detect);
+
+static irqreturn_t rt5645_irq(int irq, void *data)
+{
+	struct rt5645_priv *rt5645 = data;
+
+	rt5645_jack_detect(rt5645->codec, rt5645->jack);
+
+	return IRQ_HANDLED;
+}
+
 static int rt5645_probe(struct snd_soc_codec *codec)
 {
 	struct rt5645_priv *rt5645 = snd_soc_codec_get_drvdata(codec);
@@ -2250,6 +2322,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c,
 	if (rt5645 == NULL)
 		return -ENOMEM;
 
+	rt5645->i2c = i2c;
 	i2c_set_clientdata(i2c, rt5645);
 
 	if (pdata)
@@ -2345,12 +2418,38 @@ static int rt5645_i2c_probe(struct i2c_client *i2c,
 
 	}
 
+	if (rt5645->i2c->irq) {
+		ret = request_threaded_irq(rt5645->i2c->irq, NULL, rt5645_irq,
+			IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+			| IRQF_ONESHOT, "rt5645", rt5645);
+		if (ret)
+			dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret);
+	}
+
+	if (gpio_is_valid(rt5645->pdata.hp_det_gpio)) {
+		ret = gpio_request(rt5645->pdata.hp_det_gpio, "rt5645");
+		if (ret)
+			dev_err(&i2c->dev, "Fail gpio_request hp_det_gpio\n");
+
+		ret = gpio_direction_input(rt5645->pdata.hp_det_gpio);
+		if (ret)
+			dev_err(&i2c->dev, "Fail gpio_direction hp_det_gpio\n");
+	}
+
 	return snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5645,
 				      rt5645_dai, ARRAY_SIZE(rt5645_dai));
 }
 
 static int rt5645_i2c_remove(struct i2c_client *i2c)
 {
+	struct rt5645_priv *rt5645 = i2c_get_clientdata(i2c);
+
+	if (i2c->irq)
+		free_irq(i2c->irq, rt5645);
+
+	if (gpio_is_valid(rt5645->pdata.hp_det_gpio))
+		gpio_free(rt5645->pdata.hp_det_gpio);
+
 	snd_soc_unregister_codec(&i2c->dev);
 
 	return 0;
diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h
index 355b7e9eefab..50c62c5668ea 100644
--- a/sound/soc/codecs/rt5645.h
+++ b/sound/soc/codecs/rt5645.h
@@ -2166,6 +2166,8 @@ struct rt5645_priv {
 	struct snd_soc_codec *codec;
 	struct rt5645_platform_data pdata;
 	struct regmap *regmap;
+	struct i2c_client *i2c;
+	struct snd_soc_jack *jack;
 
 	int sysclk;
 	int sysclk_src;
@@ -2178,4 +2180,7 @@ struct rt5645_priv {
 	int pll_out;
 };
 
+int rt5645_set_jack_detect(struct snd_soc_codec *codec,
+	struct snd_soc_jack *jack);
+
 #endif /* __RT5645_H__ */
-- 
cgit v1.2.3


From d0bf4a9e92b9a93ffeeacbd7b6cb83e0ee3dc2ef Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 29 Sep 2014 13:29:15 -0700
Subject: net: cleanup and document skb fclone layout

Lets use a proper structure to clearly document and implement
skb fast clones.

Then, we might experiment more easily alternative layouts.

This patch adds a new skb_fclone_busy() helper, used by tcp and xfrm,
to stop leaking of implementation details.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 25 +++++++++++++++++++++++++
 net/core/skbuff.c      | 41 ++++++++++++++++++++---------------------
 net/ipv4/tcp_output.c  |  5 +----
 net/xfrm/xfrm_policy.c |  4 +---
 4 files changed, 47 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 262efdbc346b..d8f7d74d5a4d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -781,6 +781,31 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 				     int *errcode,
 				     gfp_t gfp_mask);
 
+/* Layout of fast clones : [skb1][skb2][fclone_ref] */
+struct sk_buff_fclones {
+	struct sk_buff	skb1;
+
+	struct sk_buff	skb2;
+
+	atomic_t	fclone_ref;
+};
+
+/**
+ *	skb_fclone_busy - check if fclone is busy
+ *	@skb: buffer
+ *
+ * Returns true is skb is a fast clone, and its clone is not freed.
+ */
+static inline bool skb_fclone_busy(const struct sk_buff *skb)
+{
+	const struct sk_buff_fclones *fclones;
+
+	fclones = container_of(skb, struct sk_buff_fclones, skb1);
+
+	return skb->fclone == SKB_FCLONE_ORIG &&
+	       fclones->skb2.fclone == SKB_FCLONE_CLONE;
+}
+
 static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 					       gfp_t priority)
 {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4be570a4ab21..a8cebb40699c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -257,15 +257,16 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	kmemcheck_annotate_variable(shinfo->destructor_arg);
 
 	if (flags & SKB_ALLOC_FCLONE) {
-		struct sk_buff *child = skb + 1;
-		atomic_t *fclone_ref = (atomic_t *) (child + 1);
+		struct sk_buff_fclones *fclones;
 
-		kmemcheck_annotate_bitfield(child, flags1);
+		fclones = container_of(skb, struct sk_buff_fclones, skb1);
+
+		kmemcheck_annotate_bitfield(&fclones->skb2, flags1);
 		skb->fclone = SKB_FCLONE_ORIG;
-		atomic_set(fclone_ref, 1);
+		atomic_set(&fclones->fclone_ref, 1);
 
-		child->fclone = SKB_FCLONE_UNAVAILABLE;
-		child->pfmemalloc = pfmemalloc;
+		fclones->skb2.fclone = SKB_FCLONE_UNAVAILABLE;
+		fclones->skb2.pfmemalloc = pfmemalloc;
 	}
 out:
 	return skb;
@@ -524,8 +525,7 @@ static void skb_release_data(struct sk_buff *skb)
  */
 static void kfree_skbmem(struct sk_buff *skb)
 {
-	struct sk_buff *other;
-	atomic_t *fclone_ref;
+	struct sk_buff_fclones *fclones;
 
 	switch (skb->fclone) {
 	case SKB_FCLONE_UNAVAILABLE:
@@ -533,22 +533,21 @@ static void kfree_skbmem(struct sk_buff *skb)
 		break;
 
 	case SKB_FCLONE_ORIG:
-		fclone_ref = (atomic_t *) (skb + 2);
-		if (atomic_dec_and_test(fclone_ref))
-			kmem_cache_free(skbuff_fclone_cache, skb);
+		fclones = container_of(skb, struct sk_buff_fclones, skb1);
+		if (atomic_dec_and_test(&fclones->fclone_ref))
+			kmem_cache_free(skbuff_fclone_cache, fclones);
 		break;
 
 	case SKB_FCLONE_CLONE:
-		fclone_ref = (atomic_t *) (skb + 1);
-		other = skb - 1;
+		fclones = container_of(skb, struct sk_buff_fclones, skb2);
 
 		/* The clone portion is available for
 		 * fast-cloning again.
 		 */
 		skb->fclone = SKB_FCLONE_UNAVAILABLE;
 
-		if (atomic_dec_and_test(fclone_ref))
-			kmem_cache_free(skbuff_fclone_cache, other);
+		if (atomic_dec_and_test(&fclones->fclone_ref))
+			kmem_cache_free(skbuff_fclone_cache, fclones);
 		break;
 	}
 }
@@ -859,17 +858,18 @@ EXPORT_SYMBOL_GPL(skb_copy_ubufs);
 
 struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 {
-	struct sk_buff *n;
+	struct sk_buff_fclones *fclones = container_of(skb,
+						       struct sk_buff_fclones,
+						       skb1);
+	struct sk_buff *n = &fclones->skb2;
 
 	if (skb_orphan_frags(skb, gfp_mask))
 		return NULL;
 
-	n = skb + 1;
 	if (skb->fclone == SKB_FCLONE_ORIG &&
 	    n->fclone == SKB_FCLONE_UNAVAILABLE) {
-		atomic_t *fclone_ref = (atomic_t *) (n + 1);
 		n->fclone = SKB_FCLONE_CLONE;
-		atomic_inc(fclone_ref);
+		atomic_inc(&fclones->fclone_ref);
 	} else {
 		if (skb_pfmemalloc(skb))
 			gfp_mask |= __GFP_MEMALLOC;
@@ -3240,8 +3240,7 @@ void __init skb_init(void)
 					      SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 					      NULL);
 	skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
-						(2*sizeof(struct sk_buff)) +
-						sizeof(atomic_t),
+						sizeof(struct sk_buff_fclones),
 						0,
 						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 						NULL);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ee567e9e98c3..8d4eac793700 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2110,10 +2110,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 static bool skb_still_in_host_queue(const struct sock *sk,
 				    const struct sk_buff *skb)
 {
-	const struct sk_buff *fclone = skb + 1;
-
-	if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
-		     fclone->fclone == SKB_FCLONE_CLONE)) {
+	if (unlikely(skb_fclone_busy(skb))) {
 		NET_INC_STATS_BH(sock_net(sk),
 				 LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
 		return true;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f623dca6ce30..4c4e457e7888 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1961,10 +1961,8 @@ static int xdst_queue_output(struct sock *sk, struct sk_buff *skb)
 	struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
 	struct xfrm_policy *pol = xdst->pols[0];
 	struct xfrm_policy_queue *pq = &pol->polq;
-	const struct sk_buff *fclone = skb + 1;
 
-	if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
-		     fclone->fclone == SKB_FCLONE_CLONE)) {
+	if (unlikely(skb_fclone_busy(skb))) {
 		kfree_skb(skb);
 		return 0;
 	}
-- 
cgit v1.2.3


From 8bce6d7d0d1ede22af334ee241841e9278365278 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Mon, 29 Sep 2014 20:22:29 -0700
Subject: udp: Generalize skb_udp_segment

skb_udp_segment is the function called from udp4_ufo_fragment to
segment a UDP tunnel packet. This function currently assumes
segmentation is transparent Ethernet bridging (i.e. VXLAN
encapsulation). This patch generalizes the function to
operate on either Ethertype or IP protocol.

The inner_protocol field must be set to the protocol of the inner
header. This can now be either an Ethertype or an IP protocol
(in a union). A new flag in the skbuff indicates which type is
effective. skb_set_inner_protocol and skb_set_inner_ipproto
helper functions were added to set the inner_protocol. These
functions are called from the point where the tunnel encapsulation
is occuring.

When skb_udp_tunnel_segment is called, the function to segment the
inner packet is selected based on the inner IP or Ethertype. In the
case of an IP protocol encapsulation, the function is derived from
inet[6]_offloads. In the case of Ethertype, skb->protocol is
set to the inner_protocol and skb_mac_gso_segment is called. (GRE
currently does this, but it might be possible to lookup the protocol
in offload_base and call the appropriate segmenation function
directly).

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 26 +++++++++++++++++++++++--
 include/net/udp.h      |  3 ++-
 net/ipv4/udp_offload.c | 51 +++++++++++++++++++++++++++++++++++++++++++++-----
 net/ipv6/udp_offload.c |  2 +-
 4 files changed, 73 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d8f7d74d5a4d..7c5036d11feb 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -596,7 +596,8 @@ struct sk_buff {
 	__u8			ndisc_nodetype:2;
 #endif
 	__u8			ipvs_property:1;
-	/* 5 or 7 bit hole */
+	__u8			inner_protocol_type:1;
+	/* 4 or 6 bit hole */
 
 #ifdef CONFIG_NET_SCHED
 	__u16			tc_index;	/* traffic control index */
@@ -632,7 +633,11 @@ struct sk_buff {
 		__u32		reserved_tailroom;
 	};
 
-	__be16			inner_protocol;
+	union {
+		__be16		inner_protocol;
+		__u8		inner_ipproto;
+	};
+
 	__u16			inner_transport_header;
 	__u16			inner_network_header;
 	__u16			inner_mac_header;
@@ -1762,6 +1767,23 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+#define ENCAP_TYPE_ETHER	0
+#define ENCAP_TYPE_IPPROTO	1
+
+static inline void skb_set_inner_protocol(struct sk_buff *skb,
+					  __be16 protocol)
+{
+	skb->inner_protocol = protocol;
+	skb->inner_protocol_type = ENCAP_TYPE_ETHER;
+}
+
+static inline void skb_set_inner_ipproto(struct sk_buff *skb,
+					 __u8 ipproto)
+{
+	skb->inner_ipproto = ipproto;
+	skb->inner_protocol_type = ENCAP_TYPE_IPPROTO;
+}
+
 static inline void skb_reset_inner_headers(struct sk_buff *skb)
 {
 	skb->inner_mac_header = skb->mac_header;
diff --git a/include/net/udp.h b/include/net/udp.h
index 16f4e80f0519..07f9b70962f6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -239,7 +239,8 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 int udp_disconnect(struct sock *sk, int flags);
 unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait);
 struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
-				       netdev_features_t features);
+				       netdev_features_t features,
+				       bool is_ipv6);
 int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 		       char __user *optval, int __user *optlen);
 int udp_lib_setsockopt(struct sock *sk, int level, int optname,
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 19ebe6a39ddc..8c35f2c939ee 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -25,8 +25,11 @@ struct udp_offload_priv {
 	struct udp_offload_priv __rcu *next;
 };
 
-struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
-				       netdev_features_t features)
+static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
+	netdev_features_t features,
+	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
+					     netdev_features_t features),
+	__be16 new_protocol)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	u16 mac_offset = skb->mac_header;
@@ -48,7 +51,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, skb_inner_network_offset(skb));
 	skb->mac_len = skb_inner_network_offset(skb);
-	skb->protocol = htons(ETH_P_TEB);
+	skb->protocol = new_protocol;
 
 	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
 	if (need_csum)
@@ -56,7 +59,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 
 	/* segment inner packet. */
 	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
-	segs = skb_mac_gso_segment(skb, enc_features);
+	segs = gso_inner_segment(skb, enc_features);
 	if (IS_ERR_OR_NULL(segs)) {
 		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
 				     mac_len);
@@ -101,6 +104,44 @@ out:
 	return segs;
 }
 
+struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
+				       netdev_features_t features,
+				       bool is_ipv6)
+{
+	__be16 protocol = skb->protocol;
+	const struct net_offload **offloads;
+	const struct net_offload *ops;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
+					     netdev_features_t features);
+
+	rcu_read_lock();
+
+	switch (skb->inner_protocol_type) {
+	case ENCAP_TYPE_ETHER:
+		protocol = skb->inner_protocol;
+		gso_inner_segment = skb_mac_gso_segment;
+		break;
+	case ENCAP_TYPE_IPPROTO:
+		offloads = is_ipv6 ? inet6_offloads : inet_offloads;
+		ops = rcu_dereference(offloads[skb->inner_ipproto]);
+		if (!ops || !ops->callbacks.gso_segment)
+			goto out_unlock;
+		gso_inner_segment = ops->callbacks.gso_segment;
+		break;
+	default:
+		goto out_unlock;
+	}
+
+	segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment,
+					protocol);
+
+out_unlock:
+	rcu_read_unlock();
+
+	return segs;
+}
+
 static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 					 netdev_features_t features)
 {
@@ -113,7 +154,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	if (skb->encapsulation &&
 	    (skb_shinfo(skb)->gso_type &
 	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
-		segs = skb_udp_tunnel_segment(skb, features);
+		segs = skb_udp_tunnel_segment(skb, features, false);
 		goto out;
 	}
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 212ebfc7973f..8f96988c1db2 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -58,7 +58,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 
 	if (skb->encapsulation && skb_shinfo(skb)->gso_type &
 	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
-		segs = skb_udp_tunnel_segment(skb, features);
+		segs = skb_udp_tunnel_segment(skb, features, true);
 	else {
 		const struct ipv6hdr *ipv6h;
 		struct udphdr *uh;
-- 
cgit v1.2.3


From a0efb80ce3abacfd22a4284c3730924fc2f1f077 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 30 Sep 2014 16:07:24 -0700
Subject: net_sched: avoid calling tcf_unbind_filter() in call_rcu callback

This fixes the following crash:

[   63.976822] general protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[   63.980094] CPU: 1 PID: 15 Comm: ksoftirqd/1 Not tainted 3.17.0-rc6+ #648
[   63.980094] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[   63.980094] task: ffff880117dea690 ti: ffff880117dfc000 task.ti: ffff880117dfc000
[   63.980094] RIP: 0010:[<ffffffff817e6d07>]  [<ffffffff817e6d07>] u32_destroy_key+0x27/0x6d
[   63.980094] RSP: 0018:ffff880117dffcc0  EFLAGS: 00010202
[   63.980094] RAX: ffff880117dea690 RBX: ffff8800d02e0820 RCX: 0000000000000000
[   63.980094] RDX: 0000000000000001 RSI: 0000000000000002 RDI: 6b6b6b6b6b6b6b6b
[   63.980094] RBP: ffff880117dffcd0 R08: 0000000000000000 R09: 0000000000000000
[   63.980094] R10: 00006c0900006ba8 R11: 00006ba100006b9d R12: 0000000000000001
[   63.980094] R13: ffff8800d02e0898 R14: ffffffff817e6d4d R15: ffff880117387a30
[   63.980094] FS:  0000000000000000(0000) GS:ffff88011a800000(0000) knlGS:0000000000000000
[   63.980094] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[   63.980094] CR2: 00007f07e6732fed CR3: 000000011665b000 CR4: 00000000000006e0
[   63.980094] Stack:
[   63.980094]  ffff88011a9cd300 ffffffff82051ac0 ffff880117dffce0 ffffffff817e6d68
[   63.980094]  ffff880117dffd70 ffffffff810cb4c7 ffffffff810cb3cd ffff880117dfffd8
[   63.980094]  ffff880117dea690 ffff880117dea690 ffff880117dfffd8 000000000000000a
[   63.980094] Call Trace:
[   63.980094]  [<ffffffff817e6d68>] u32_delete_key_freepf_rcu+0x1b/0x1d
[   63.980094]  [<ffffffff810cb4c7>] rcu_process_callbacks+0x3bb/0x691
[   63.980094]  [<ffffffff810cb3cd>] ? rcu_process_callbacks+0x2c1/0x691
[   63.980094]  [<ffffffff817e6d4d>] ? u32_destroy_key+0x6d/0x6d
[   63.980094]  [<ffffffff810780a4>] __do_softirq+0x142/0x323
[   63.980094]  [<ffffffff810782a8>] run_ksoftirqd+0x23/0x53
[   63.980094]  [<ffffffff81092126>] smpboot_thread_fn+0x203/0x221
[   63.980094]  [<ffffffff81091f23>] ? smpboot_unpark_thread+0x33/0x33
[   63.980094]  [<ffffffff8108e44d>] kthread+0xc9/0xd1
[   63.980094]  [<ffffffff819e00ea>] ? do_wait_for_common+0xf8/0x125
[   63.980094]  [<ffffffff8108e384>] ? __kthread_parkme+0x61/0x61
[   63.980094]  [<ffffffff819e43ec>] ret_from_fork+0x7c/0xb0
[   63.980094]  [<ffffffff8108e384>] ? __kthread_parkme+0x61/0x61

tp could be freed in call_rcu callback too, the order is not guaranteed.

John Fastabend says:

====================
Its worth noting why this is safe. Any running schedulers will either
read the valid class field or it will be zeroed.

All schedulers today when the class is 0 do a lookup using the
same call used by the tcf_exts_bind(). So even if we have a running
classifier hit the null class pointer it will do a lookup and get
to the same result. This is particularly fragile at the moment because
the only way to verify this is to audit the schedulers call sites.
====================

Cc: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h |  6 +-----
 net/sched/cls_u32.c   | 10 ++++++----
 2 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 73f9532ee581..ef44ad9a6426 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -20,11 +20,7 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops);
 static inline unsigned long
 __cls_set_class(unsigned long *clp, unsigned long cl)
 {
-	unsigned long old_cl;
- 
-	old_cl = *clp;
-	*clp = cl;
-	return old_cl;
+	return xchg(clp, cl);
 }
 
 static inline unsigned long
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 4be3ebf46d67..0472909bb014 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -358,7 +358,6 @@ static int u32_destroy_key(struct tcf_proto *tp,
 			   struct tc_u_knode *n,
 			   bool free_pf)
 {
-	tcf_unbind_filter(tp, &n->res);
 	tcf_exts_destroy(&n->exts);
 	if (n->ht_down)
 		n->ht_down->refcnt--;
@@ -416,6 +415,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 			if (pkp == key) {
 				RCU_INIT_POINTER(*kp, key->next);
 
+				tcf_unbind_filter(tp, &key->res);
 				call_rcu(&key->rcu, u32_delete_key_freepf_rcu);
 				return 0;
 			}
@@ -425,7 +425,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 	return 0;
 }
 
-static void u32_clear_hnode(struct tc_u_hnode *ht)
+static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
 {
 	struct tc_u_knode *n;
 	unsigned int h;
@@ -434,6 +434,7 @@ static void u32_clear_hnode(struct tc_u_hnode *ht)
 		while ((n = rtnl_dereference(ht->ht[h])) != NULL) {
 			RCU_INIT_POINTER(ht->ht[h],
 					 rtnl_dereference(n->next));
+			tcf_unbind_filter(tp, &n->res);
 			call_rcu(&n->rcu, u32_delete_key_freepf_rcu);
 		}
 	}
@@ -447,7 +448,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
 
 	WARN_ON(ht->refcnt);
 
-	u32_clear_hnode(ht);
+	u32_clear_hnode(tp, ht);
 
 	hn = &tp_c->hlist;
 	for (phn = rtnl_dereference(*hn);
@@ -482,7 +483,7 @@ static void u32_destroy(struct tcf_proto *tp)
 		     ht;
 		     ht = rtnl_dereference(ht->next)) {
 			ht->refcnt--;
-			u32_clear_hnode(ht);
+			u32_clear_hnode(tp, ht);
 		}
 
 		while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) {
@@ -731,6 +732,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		}
 
 		u32_replace_knode(tp, tp_c, new);
+		tcf_unbind_filter(tp, &n->res);
 		call_rcu(&n->rcu, u32_delete_key_rcu);
 		return 0;
 	}
-- 
cgit v1.2.3


From d068b02cfdfc27f5962ec82ec5568b706f599edc Mon Sep 17 00:00:00 2001
From: Petri Gynther <pgynther@google.com>
Date: Wed, 1 Oct 2014 11:58:02 -0700
Subject: net: phy: add BCM7425 and BCM7429 PHYs

Signed-off-by: Petri Gynther <pgynther@google.com>
Acked-by: Florian Fainelli <f.fainelli@gmai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 28 ++++++++++++++++++++++++++++
 include/linux/brcmphy.h   |  2 ++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index daae69950925..1d211d369039 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -350,6 +350,32 @@ static struct phy_driver bcm7xxx_driver[] = {
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7439, "Broadcom BCM7439"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7445, "Broadcom BCM7445"),
 {
+	.phy_id         = PHY_ID_BCM7425,
+	.phy_id_mask    = 0xfffffff0,
+	.name           = "Broadcom BCM7425",
+	.features       = PHY_GBIT_FEATURES |
+			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+	.flags          = 0,
+	.config_init    = bcm7xxx_config_init,
+	.config_aneg    = genphy_config_aneg,
+	.read_status    = genphy_read_status,
+	.suspend        = bcm7xxx_suspend,
+	.resume         = bcm7xxx_config_init,
+	.driver         = { .owner = THIS_MODULE },
+}, {
+	.phy_id         = PHY_ID_BCM7429,
+	.phy_id_mask    = 0xfffffff0,
+	.name           = "Broadcom BCM7429",
+	.features       = PHY_GBIT_FEATURES |
+			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+	.flags          = PHY_IS_INTERNAL,
+	.config_init    = bcm7xxx_config_init,
+	.config_aneg    = genphy_config_aneg,
+	.read_status    = genphy_read_status,
+	.suspend        = bcm7xxx_suspend,
+	.resume         = bcm7xxx_config_init,
+	.driver         = { .owner = THIS_MODULE },
+}, {
 	.phy_id		= PHY_BCM_OUI_4,
 	.phy_id_mask	= 0xffff0000,
 	.name		= "Broadcom BCM7XXX 40nm",
@@ -381,6 +407,8 @@ static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
 	{ PHY_ID_BCM7250, 0xfffffff0, },
 	{ PHY_ID_BCM7364, 0xfffffff0, },
 	{ PHY_ID_BCM7366, 0xfffffff0, },
+	{ PHY_ID_BCM7425, 0xfffffff0, },
+	{ PHY_ID_BCM7429, 0xfffffff0, },
 	{ PHY_ID_BCM7439, 0xfffffff0, },
 	{ PHY_ID_BCM7445, 0xfffffff0, },
 	{ PHY_BCM_OUI_4, 0xffff0000 },
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 3f626fe48c9a..7ccd928cc1f2 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -16,6 +16,8 @@
 #define PHY_ID_BCM7250			0xae025280
 #define PHY_ID_BCM7364			0xae025260
 #define PHY_ID_BCM7366			0x600d8490
+#define PHY_ID_BCM7425			0x03625e60
+#define PHY_ID_BCM7429			0x600d8730
 #define PHY_ID_BCM7439			0x600d8480
 #define PHY_ID_BCM7445			0x600d8510
 
-- 
cgit v1.2.3


From 599bad38cf7163123af7c9efea0fcf228bc74fe1 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Tue, 30 Sep 2014 13:02:02 +0200
Subject: driver core: Add BUS_NOTIFY_REMOVED_DEVICE event

This event closes an important gap in the bus notifiers.
There is already the BUS_NOTIFY_DEL_DEVICE event, but that
is sent when the device is still bound to its device driver.

This is too early for the IOMMU code to destroy any mappings
for the device, as they might still be in use by the driver.

The new BUS_NOTIFY_REMOVED_DEVICE event introduced with this
patch closes this gap as it is sent when the device is
already unbound from its device driver and almost completly
removed from the driver core.

With this event the IOMMU code can safely destroy any
mappings and other data structures when a device is removed.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: Jerry Hoemann <jerry.hoemann@hp.com>
---
 drivers/base/core.c    |  3 +++
 include/linux/device.h | 11 ++++++-----
 2 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 20da3ad1696b..7b270a2e6ed5 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1211,6 +1211,9 @@ void device_del(struct device *dev)
 	 */
 	if (platform_notify_remove)
 		platform_notify_remove(dev);
+	if (dev->bus)
+		blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
+					     BUS_NOTIFY_REMOVED_DEVICE, dev);
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
 	cleanup_device_parent(dev);
 	kobject_del(&dev->kobj);
diff --git a/include/linux/device.h b/include/linux/device.h
index 43d183aeb25b..d0d5c5db509d 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -181,13 +181,14 @@ extern int bus_unregister_notifier(struct bus_type *bus,
  * with the device lock held in the core, so be careful.
  */
 #define BUS_NOTIFY_ADD_DEVICE		0x00000001 /* device added */
-#define BUS_NOTIFY_DEL_DEVICE		0x00000002 /* device removed */
-#define BUS_NOTIFY_BIND_DRIVER		0x00000003 /* driver about to be
+#define BUS_NOTIFY_DEL_DEVICE		0x00000002 /* device to be removed */
+#define BUS_NOTIFY_REMOVED_DEVICE	0x00000003 /* device removed */
+#define BUS_NOTIFY_BIND_DRIVER		0x00000004 /* driver about to be
 						      bound */
-#define BUS_NOTIFY_BOUND_DRIVER		0x00000004 /* driver bound to device */
-#define BUS_NOTIFY_UNBIND_DRIVER	0x00000005 /* driver about to be
+#define BUS_NOTIFY_BOUND_DRIVER		0x00000005 /* driver bound to device */
+#define BUS_NOTIFY_UNBIND_DRIVER	0x00000006 /* driver about to be
 						      unbound */
-#define BUS_NOTIFY_UNBOUND_DRIVER	0x00000006 /* driver is unbound
+#define BUS_NOTIFY_UNBOUND_DRIVER	0x00000007 /* driver is unbound
 						      from the device */
 
 extern struct kset *bus_get_kset(struct bus_type *bus);
-- 
cgit v1.2.3


From 89168b48991537bec2573b3b6a8841df74465b12 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 2 Oct 2014 09:08:46 +0200
Subject: mmc: core: restore detect line inversion semantics

commit 98e90de99a0c43bd434da814c882c4332441871e
"mmc: host: switch OF parser to use gpio descriptors"
switched the semantic behaviour of card detect and read
only flags such that the inversion capability flag would
only be set if inversion was explicitly specified in the
device tree, in the hopes that no-one was using double
inversion.

It turns out that the XOR:ing between the explicit
inversion was indeed in use, so we need to restore the
old semantics where both ways of inversion are checked
and the end result XOR:ed.

Reported-by: Javier Martinez Canillas <javier@dowhile0.org>
Tested-by: Javier Martinez Canillas <javier@dowhile0.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/host.c       | 32 ++++++++++++++++++++++++++++----
 drivers/mmc/core/slot-gpio.c  | 14 ++++++++++++--
 drivers/mmc/host/mmci.c       |  4 ++--
 drivers/mmc/host/sdhci-acpi.c |  2 +-
 include/linux/mmc/slot-gpio.h |  4 ++--
 5 files changed, 45 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 31969436d77c..03c53b72a2d6 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -311,6 +311,7 @@ int mmc_of_parse(struct mmc_host *host)
 	struct device_node *np;
 	u32 bus_width;
 	int len, ret;
+	bool cap_invert, gpio_invert;
 
 	if (!host->parent || !host->parent->of_node)
 		return 0;
@@ -359,12 +360,15 @@ int mmc_of_parse(struct mmc_host *host)
 		host->caps |= MMC_CAP_NONREMOVABLE;
 	} else {
 		if (of_property_read_bool(np, "cd-inverted"))
-			host->caps2 |= MMC_CAP2_CD_ACTIVE_HIGH;
+			cap_invert = true;
+		else
+			cap_invert = false;
 
 		if (of_find_property(np, "broken-cd", &len))
 			host->caps |= MMC_CAP_NEEDS_POLL;
 
-		ret = mmc_gpiod_request_cd(host, "cd", 0, false, 0);
+		ret = mmc_gpiod_request_cd(host, "cd", 0, true,
+					   0, &gpio_invert);
 		if (ret) {
 			if (ret == -EPROBE_DEFER)
 				return ret;
@@ -375,13 +379,29 @@ int mmc_of_parse(struct mmc_host *host)
 			}
 		} else
 			dev_info(host->parent, "Got CD GPIO\n");
+
+		/*
+		 * There are two ways to flag that the CD line is inverted:
+		 * through the cd-inverted flag and by the GPIO line itself
+		 * being inverted from the GPIO subsystem. This is a leftover
+		 * from the times when the GPIO subsystem did not make it
+		 * possible to flag a line as inverted.
+		 *
+		 * If the capability on the host AND the GPIO line are
+		 * both inverted, the end result is that the CD line is
+		 * not inverted.
+		 */
+		if (cap_invert ^ gpio_invert)
+			host->caps2 |= MMC_CAP2_CD_ACTIVE_HIGH;
 	}
 
 	/* Parse Write Protection */
 	if (of_property_read_bool(np, "wp-inverted"))
-		host->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
+		cap_invert = true;
+	else
+		cap_invert = false;
 
-	ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0);
+	ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0, &gpio_invert);
 	if (ret) {
 		if (ret == -EPROBE_DEFER)
 			goto out;
@@ -393,6 +413,10 @@ int mmc_of_parse(struct mmc_host *host)
 	} else
 		dev_info(host->parent, "Got WP GPIO\n");
 
+	/* See the comment on CD inversion above */
+	if (cap_invert ^ gpio_invert)
+		host->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
+
 	if (of_find_property(np, "cap-sd-highspeed", &len))
 		host->caps |= MMC_CAP_SD_HIGHSPEED;
 	if (of_find_property(np, "cap-mmc-highspeed", &len))
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 38f76555d4bf..69bbf2adb329 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -281,6 +281,8 @@ EXPORT_SYMBOL(mmc_gpio_free_cd);
  * @idx: index of the GPIO to obtain in the consumer
  * @override_active_level: ignore %GPIO_ACTIVE_LOW flag
  * @debounce: debounce time in microseconds
+ * @gpio_invert: will return whether the GPIO line is inverted or not, set
+ * to NULL to ignore
  *
  * Use this function in place of mmc_gpio_request_cd() to use the GPIO
  * descriptor API.  Note that it is paired with mmc_gpiod_free_cd() not
@@ -291,7 +293,7 @@ EXPORT_SYMBOL(mmc_gpio_free_cd);
  */
 int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
-			 unsigned int debounce)
+			 unsigned int debounce, bool *gpio_invert)
 {
 	struct mmc_gpio *ctx;
 	struct gpio_desc *desc;
@@ -316,6 +318,9 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 			return ret;
 	}
 
+	if (gpio_invert)
+		*gpio_invert = !gpiod_is_active_low(desc);
+
 	ctx->override_cd_active_level = override_active_level;
 	ctx->cd_gpio = desc;
 
@@ -330,6 +335,8 @@ EXPORT_SYMBOL(mmc_gpiod_request_cd);
  * @idx: index of the GPIO to obtain in the consumer
  * @override_active_level: ignore %GPIO_ACTIVE_LOW flag
  * @debounce: debounce time in microseconds
+ * @gpio_invert: will return whether the GPIO line is inverted or not,
+ * set to NULL to ignore
  *
  * Use this function in place of mmc_gpio_request_ro() to use the GPIO
  * descriptor API.  Note that it is paired with mmc_gpiod_free_ro() not
@@ -339,7 +346,7 @@ EXPORT_SYMBOL(mmc_gpiod_request_cd);
  */
 int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
-			 unsigned int debounce)
+			 unsigned int debounce, bool *gpio_invert)
 {
 	struct mmc_gpio *ctx;
 	struct gpio_desc *desc;
@@ -364,6 +371,9 @@ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 			return ret;
 	}
 
+	if (gpio_invert)
+		*gpio_invert = !gpiod_is_active_low(desc);
+
 	ctx->override_ro_active_level = override_active_level;
 	ctx->ro_gpio = desc;
 
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index c9dafed550f2..43af791e2e45 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1682,7 +1682,7 @@ static int mmci_probe(struct amba_device *dev,
 	 * silently of these do not exist and proceed to try platform data
 	 */
 	if (!np) {
-		ret = mmc_gpiod_request_cd(mmc, "cd", 0, false, 0);
+		ret = mmc_gpiod_request_cd(mmc, "cd", 0, false, 0, NULL);
 		if (ret < 0) {
 			if (ret == -EPROBE_DEFER)
 				goto clk_disable;
@@ -1693,7 +1693,7 @@ static int mmci_probe(struct amba_device *dev,
 			}
 		}
 
-		ret = mmc_gpiod_request_ro(mmc, "wp", 0, false, 0);
+		ret = mmc_gpiod_request_ro(mmc, "wp", 0, false, 0, NULL);
 		if (ret < 0) {
 			if (ret == -EPROBE_DEFER)
 				goto clk_disable;
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 3483c089baa7..327bc24ec8ce 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -352,7 +352,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	if (sdhci_acpi_flag(c, SDHCI_ACPI_SD_CD)) {
 		bool v = sdhci_acpi_flag(c, SDHCI_ACPI_SD_CD_OVERRIDE_LEVEL);
 
-		if (mmc_gpiod_request_cd(host->mmc, NULL, 0, v, 0)) {
+		if (mmc_gpiod_request_cd(host->mmc, NULL, 0, v, 0, NULL)) {
 			dev_warn(dev, "failed to setup card detect gpio\n");
 			c->use_runtime_pm = false;
 		}
diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h
index a0d0442c15bf..e56fa24c9322 100644
--- a/include/linux/mmc/slot-gpio.h
+++ b/include/linux/mmc/slot-gpio.h
@@ -24,10 +24,10 @@ void mmc_gpio_free_cd(struct mmc_host *host);
 
 int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
-			 unsigned int debounce);
+			 unsigned int debounce, bool *gpio_invert);
 int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
-			 unsigned int debounce);
+			 unsigned int debounce, bool *gpio_invert);
 void mmc_gpiod_free_cd(struct mmc_host *host);
 void mmc_gpiod_request_cd_irq(struct mmc_host *host);
 
-- 
cgit v1.2.3


From 57384592c43375d2c9a14d82aebbdc95fdda9e9d Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Thu, 2 Oct 2014 11:50:25 +0200
Subject: iommu/vt-d: Store bus information in RMRR PCI device path

This will be used later to match broken RMRR entries.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/dmar.c | 1 +
 include/linux/dmar.h | 8 +++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 8ed55b0a1ce4..68da1ab0f2cd 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -155,6 +155,7 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
 	if (event == BUS_NOTIFY_ADD_DEVICE) {
 		for (tmp = dev; tmp; tmp = tmp->bus->self) {
 			level--;
+			info->path[level].bus = tmp->bus->number;
 			info->path[level].device = PCI_SLOT(tmp->devfn);
 			info->path[level].function = PCI_FUNC(tmp->devfn);
 			if (pci_is_root_bus(tmp->bus))
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 1deece46a0ca..593fff99e6bf 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -56,13 +56,19 @@ struct dmar_drhd_unit {
 	struct intel_iommu *iommu;
 };
 
+struct dmar_pci_path {
+	u8 bus;
+	u8 device;
+	u8 function;
+};
+
 struct dmar_pci_notify_info {
 	struct pci_dev			*dev;
 	unsigned long			event;
 	int				bus;
 	u16				seg;
 	u16				level;
-	struct acpi_dmar_pci_path	path[];
+	struct dmar_pci_path		path[];
 }  __attribute__((packed));
 
 extern struct rw_semaphore dmar_global_lock;
-- 
cgit v1.2.3


From 51b0a5d8c21a91801bbef9bcc8639dc0b206c6cd Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 26 Sep 2014 14:35:14 +0200
Subject: netfilter: nft_reject: introduce icmp code abstraction for inet and
 bridge

This patch introduces the NFT_REJECT_ICMPX_UNREACH type which provides
an abstraction to the ICMP and ICMPv6 codes that you can use from the
inet and bridge tables, they are:

* NFT_REJECT_ICMPX_NO_ROUTE: no route to host - network unreachable
* NFT_REJECT_ICMPX_PORT_UNREACH: port unreachable
* NFT_REJECT_ICMPX_HOST_UNREACH: host unreachable
* NFT_REJECT_ICMPX_ADMIN_PROHIBITED: administratevely prohibited

You can still use the specific codes when restricting the rule to match
the corresponding layer 3 protocol.

I decided to not overload the existing NFT_REJECT_ICMP_UNREACH to have
different semantics depending on the table family and to allow the user
to specify ICMP family specific codes if they restrict it to the
corresponding family.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv4/nf_reject.h   |  1 +
 include/net/netfilter/nft_reject.h       |  9 +--
 include/uapi/linux/netfilter/nf_tables.h | 21 +++++++
 net/bridge/netfilter/nft_reject_bridge.c | 95 ++++++++++++++++++++++++++++++--
 net/ipv4/netfilter/nft_reject_ipv4.c     |  1 -
 net/netfilter/nft_reject.c               | 37 +++++++++++++
 net/netfilter/nft_reject_inet.c          | 94 +++++++++++++++++++++++++++++--
 7 files changed, 241 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h
index f713b5a31d62..8ce06385a552 100644
--- a/include/net/netfilter/ipv4/nf_reject.h
+++ b/include/net/netfilter/ipv4/nf_reject.h
@@ -5,6 +5,7 @@
 #include <net/tcp.h>
 #include <net/route.h>
 #include <net/dst.h>
+#include <net/icmp.h>
 
 static inline void nf_send_unreach(struct sk_buff *skb_in, int code)
 {
diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h
index 36b0da2d55bb..60fa1530006b 100644
--- a/include/net/netfilter/nft_reject.h
+++ b/include/net/netfilter/nft_reject.h
@@ -14,12 +14,7 @@ int nft_reject_init(const struct nft_ctx *ctx,
 
 int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr);
 
-void nft_reject_ipv4_eval(const struct nft_expr *expr,
-			  struct nft_data data[NFT_REG_MAX + 1],
-			  const struct nft_pktinfo *pkt);
-
-void nft_reject_ipv6_eval(const struct nft_expr *expr,
-			  struct nft_data data[NFT_REG_MAX + 1],
-			  const struct nft_pktinfo *pkt);
+int nft_reject_icmp_code(u8 code);
+int nft_reject_icmpv6_code(u8 code);
 
 #endif
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index b72ccfeaf865..c26df6787fb0 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -749,12 +749,33 @@ enum nft_queue_attributes {
  *
  * @NFT_REJECT_ICMP_UNREACH: reject using ICMP unreachable
  * @NFT_REJECT_TCP_RST: reject using TCP RST
+ * @NFT_REJECT_ICMPX_UNREACH: abstracted ICMP unreachable for bridge and inet
  */
 enum nft_reject_types {
 	NFT_REJECT_ICMP_UNREACH,
 	NFT_REJECT_TCP_RST,
+	NFT_REJECT_ICMPX_UNREACH,
 };
 
+/**
+ * enum nft_reject_code - Generic reject codes for IPv4/IPv6
+ *
+ * @NFT_REJECT_ICMPX_NO_ROUTE: no route to host / network unreachable
+ * @NFT_REJECT_ICMPX_PORT_UNREACH: port unreachable
+ * @NFT_REJECT_ICMPX_HOST_UNREACH: host unreachable
+ * @NFT_REJECT_ICMPX_ADMIN_PROHIBITED: administratively prohibited
+ *
+ * These codes are mapped to real ICMP and ICMPv6 codes.
+ */
+enum nft_reject_inet_code {
+	NFT_REJECT_ICMPX_NO_ROUTE	= 0,
+	NFT_REJECT_ICMPX_PORT_UNREACH,
+	NFT_REJECT_ICMPX_HOST_UNREACH,
+	NFT_REJECT_ICMPX_ADMIN_PROHIBITED,
+	__NFT_REJECT_ICMPX_MAX
+};
+#define NFT_REJECT_ICMPX_MAX	(__NFT_REJECT_ICMPX_MAX + 1)
+
 /**
  * enum nft_reject_attributes - nf_tables reject expression netlink attributes
  *
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index ee3ffe93e14e..a76479535df2 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -14,21 +14,106 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
 
 static void nft_reject_bridge_eval(const struct nft_expr *expr,
 				 struct nft_data data[NFT_REG_MAX + 1],
 				 const struct nft_pktinfo *pkt)
 {
+	struct nft_reject *priv = nft_expr_priv(expr);
+	struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
+
 	switch (eth_hdr(pkt->skb)->h_proto) {
 	case htons(ETH_P_IP):
-		return nft_reject_ipv4_eval(expr, data, pkt);
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nf_send_unreach(pkt->skb, priv->icmp_code);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nf_send_reset(pkt->skb, pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nf_send_unreach(pkt->skb,
+					nft_reject_icmp_code(priv->icmp_code));
+			break;
+		}
+		break;
 	case htons(ETH_P_IPV6):
-		return nft_reject_ipv6_eval(expr, data, pkt);
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nf_send_unreach6(net, pkt->skb, priv->icmp_code,
+					 pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nf_send_unreach6(net, pkt->skb,
+					 nft_reject_icmpv6_code(priv->icmp_code),
+					 pkt->ops->hooknum);
+			break;
+		}
+		break;
 	default:
 		/* No explicit way to reject this protocol, drop it. */
-		data[NFT_REG_VERDICT].verdict = NF_DROP;
 		break;
 	}
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+
+static int nft_reject_bridge_init(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr,
+				  const struct nlattr * const tb[])
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+	int icmp_code;
+
+	if (tb[NFTA_REJECT_TYPE] == NULL)
+		return -EINVAL;
+
+	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
+		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
+			return -EINVAL;
+
+		icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+		if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
+		    icmp_code > NFT_REJECT_ICMPX_MAX)
+			return -EINVAL;
+
+		priv->icmp_code = icmp_code;
+		break;
+	case NFT_REJECT_TCP_RST:
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int nft_reject_bridge_dump(struct sk_buff *skb,
+				  const struct nft_expr *expr)
+{
+	const struct nft_reject *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
+		goto nla_put_failure;
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
+		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
+			goto nla_put_failure;
+		break;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -1;
 }
 
 static struct nft_expr_type nft_reject_bridge_type;
@@ -36,8 +121,8 @@ static const struct nft_expr_ops nft_reject_bridge_ops = {
 	.type		= &nft_reject_bridge_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
 	.eval		= nft_reject_bridge_eval,
-	.init		= nft_reject_init,
-	.dump		= nft_reject_dump,
+	.init		= nft_reject_bridge_init,
+	.dump		= nft_reject_bridge_dump,
 };
 
 static struct nft_expr_type nft_reject_bridge_type __read_mostly = {
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index e79718a382f2..ed33299c56d1 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -16,7 +16,6 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
-#include <net/icmp.h>
 #include <net/netfilter/ipv4/nf_reject.h>
 #include <net/netfilter/nft_reject.h>
 
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index f3448c296446..ec8a456092a7 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -17,6 +17,8 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_reject.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
 
 const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
 	[NFTA_REJECT_TYPE]		= { .type = NLA_U32 },
@@ -70,5 +72,40 @@ nla_put_failure:
 }
 EXPORT_SYMBOL_GPL(nft_reject_dump);
 
+static u8 icmp_code_v4[NFT_REJECT_ICMPX_MAX] = {
+	[NFT_REJECT_ICMPX_NO_ROUTE]		= ICMP_NET_UNREACH,
+	[NFT_REJECT_ICMPX_PORT_UNREACH]		= ICMP_PORT_UNREACH,
+	[NFT_REJECT_ICMPX_HOST_UNREACH]		= ICMP_HOST_UNREACH,
+	[NFT_REJECT_ICMPX_ADMIN_PROHIBITED]	= ICMP_PKT_FILTERED,
+};
+
+int nft_reject_icmp_code(u8 code)
+{
+	if (code > NFT_REJECT_ICMPX_MAX)
+		return -EINVAL;
+
+	return icmp_code_v4[code];
+}
+
+EXPORT_SYMBOL_GPL(nft_reject_icmp_code);
+
+
+static u8 icmp_code_v6[NFT_REJECT_ICMPX_MAX] = {
+	[NFT_REJECT_ICMPX_NO_ROUTE]		= ICMPV6_NOROUTE,
+	[NFT_REJECT_ICMPX_PORT_UNREACH]		= ICMPV6_PORT_UNREACH,
+	[NFT_REJECT_ICMPX_HOST_UNREACH]		= ICMPV6_ADDR_UNREACH,
+	[NFT_REJECT_ICMPX_ADMIN_PROHIBITED]	= ICMPV6_ADM_PROHIBITED,
+};
+
+int nft_reject_icmpv6_code(u8 code)
+{
+	if (code > NFT_REJECT_ICMPX_MAX)
+		return -EINVAL;
+
+	return icmp_code_v6[code];
+}
+
+EXPORT_SYMBOL_GPL(nft_reject_icmpv6_code);
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index b718a52a4654..7b5f9d58680a 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -14,17 +14,103 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
 
 static void nft_reject_inet_eval(const struct nft_expr *expr,
 				 struct nft_data data[NFT_REG_MAX + 1],
 				 const struct nft_pktinfo *pkt)
 {
+	struct nft_reject *priv = nft_expr_priv(expr);
+	struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
+
 	switch (pkt->ops->pf) {
 	case NFPROTO_IPV4:
-		return nft_reject_ipv4_eval(expr, data, pkt);
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nf_send_unreach(pkt->skb, priv->icmp_code);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nf_send_reset(pkt->skb, pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nf_send_unreach(pkt->skb,
+					nft_reject_icmp_code(priv->icmp_code));
+			break;
+		}
+		break;
 	case NFPROTO_IPV6:
-		return nft_reject_ipv6_eval(expr, data, pkt);
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nf_send_unreach6(net, pkt->skb, priv->icmp_code,
+					 pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nf_send_unreach6(net, pkt->skb,
+					 nft_reject_icmpv6_code(priv->icmp_code),
+					 pkt->ops->hooknum);
+			break;
+		}
+		break;
+	}
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+
+static int nft_reject_inet_init(const struct nft_ctx *ctx,
+				const struct nft_expr *expr,
+				const struct nlattr * const tb[])
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+	int icmp_code;
+
+	if (tb[NFTA_REJECT_TYPE] == NULL)
+		return -EINVAL;
+
+	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
+		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
+			return -EINVAL;
+
+		icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+		if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
+		    icmp_code > NFT_REJECT_ICMPX_MAX)
+			return -EINVAL;
+
+		priv->icmp_code = icmp_code;
+		break;
+	case NFT_REJECT_TCP_RST:
+		break;
+	default:
+		return -EINVAL;
 	}
+	return 0;
+}
+
+static int nft_reject_inet_dump(struct sk_buff *skb,
+				const struct nft_expr *expr)
+{
+	const struct nft_reject *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
+		goto nla_put_failure;
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
+		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
+			goto nla_put_failure;
+		break;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -1;
 }
 
 static struct nft_expr_type nft_reject_inet_type;
@@ -32,8 +118,8 @@ static const struct nft_expr_ops nft_reject_inet_ops = {
 	.type		= &nft_reject_inet_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
 	.eval		= nft_reject_inet_eval,
-	.init		= nft_reject_init,
-	.dump		= nft_reject_dump,
+	.init		= nft_reject_inet_init,
+	.dump		= nft_reject_inet_dump,
 };
 
 static struct nft_expr_type nft_reject_inet_type __read_mostly = {
-- 
cgit v1.2.3


From c8d7b98bec43faaa6583c3135030be5eb4693acb Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 26 Sep 2014 14:35:15 +0200
Subject: netfilter: move nf_send_resetX() code to nf_reject_ipvX modules

Move nf_send_reset() and nf_send_reset6() to nf_reject_ipv4 and
nf_reject_ipv6 respectively. This code is shared by x_tables and
nf_tables.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv4/nf_reject.h | 118 +-----------------------
 net/ipv4/netfilter/Kconfig             |   6 ++
 net/ipv4/netfilter/Makefile            |   3 +
 net/ipv4/netfilter/nf_reject_ipv4.c    | 127 +++++++++++++++++++++++++
 net/ipv6/netfilter/Kconfig             |   6 ++
 net/ipv6/netfilter/Makefile            |   3 +
 net/ipv6/netfilter/nf_reject_ipv6.c    | 163 +++++++++++++++++++++++++++++++++
 7 files changed, 309 insertions(+), 117 deletions(-)
 create mode 100644 net/ipv4/netfilter/nf_reject_ipv4.c
 create mode 100644 net/ipv6/netfilter/nf_reject_ipv6.c

(limited to 'include')

diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h
index 8ce06385a552..e8427193c777 100644
--- a/include/net/netfilter/ipv4/nf_reject.h
+++ b/include/net/netfilter/ipv4/nf_reject.h
@@ -1,10 +1,6 @@
 #ifndef _IPV4_NF_REJECT_H
 #define _IPV4_NF_REJECT_H
 
-#include <net/ip.h>
-#include <net/tcp.h>
-#include <net/route.h>
-#include <net/dst.h>
 #include <net/icmp.h>
 
 static inline void nf_send_unreach(struct sk_buff *skb_in, int code)
@@ -12,118 +8,6 @@ static inline void nf_send_unreach(struct sk_buff *skb_in, int code)
 	icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
 }
 
-/* Send RST reply */
-static void nf_send_reset(struct sk_buff *oldskb, int hook)
-{
-	struct sk_buff *nskb;
-	const struct iphdr *oiph;
-	struct iphdr *niph;
-	const struct tcphdr *oth;
-	struct tcphdr _otcph, *tcph;
-
-	/* IP header checks: fragment. */
-	if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
-		return;
-
-	oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
-				 sizeof(_otcph), &_otcph);
-	if (oth == NULL)
-		return;
-
-	/* No RST for RST. */
-	if (oth->rst)
-		return;
-
-	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
-		return;
-
-	/* Check checksum */
-	if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
-		return;
-	oiph = ip_hdr(oldskb);
-
-	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
-			 LL_MAX_HEADER, GFP_ATOMIC);
-	if (!nskb)
-		return;
-
-	skb_reserve(nskb, LL_MAX_HEADER);
-
-	skb_reset_network_header(nskb);
-	niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
-	niph->version	= 4;
-	niph->ihl	= sizeof(struct iphdr) / 4;
-	niph->tos	= 0;
-	niph->id	= 0;
-	niph->frag_off	= htons(IP_DF);
-	niph->protocol	= IPPROTO_TCP;
-	niph->check	= 0;
-	niph->saddr	= oiph->daddr;
-	niph->daddr	= oiph->saddr;
-
-	skb_reset_transport_header(nskb);
-	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
-	memset(tcph, 0, sizeof(*tcph));
-	tcph->source	= oth->dest;
-	tcph->dest	= oth->source;
-	tcph->doff	= sizeof(struct tcphdr) / 4;
-
-	if (oth->ack)
-		tcph->seq = oth->ack_seq;
-	else {
-		tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
-				      oldskb->len - ip_hdrlen(oldskb) -
-				      (oth->doff << 2));
-		tcph->ack = 1;
-	}
-
-	tcph->rst	= 1;
-	tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
-				    niph->daddr, 0);
-	nskb->ip_summed = CHECKSUM_PARTIAL;
-	nskb->csum_start = (unsigned char *)tcph - nskb->head;
-	nskb->csum_offset = offsetof(struct tcphdr, check);
-
-	/* ip_route_me_harder expects skb->dst to be set */
-	skb_dst_set_noref(nskb, skb_dst(oldskb));
-
-	nskb->protocol = htons(ETH_P_IP);
-	if (ip_route_me_harder(nskb, RTN_UNSPEC))
-		goto free_nskb;
-
-	niph->ttl	= ip4_dst_hoplimit(skb_dst(nskb));
-
-	/* "Never happens" */
-	if (nskb->len > dst_mtu(skb_dst(nskb)))
-		goto free_nskb;
-
-	nf_ct_attach(nskb, oldskb);
-
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	/* If we use ip_local_out for bridged traffic, the MAC source on
-	 * the RST will be ours, instead of the destination's.  This confuses
-	 * some routers/firewalls, and they drop the packet.  So we need to
-	 * build the eth header using the original destination's MAC as the
-	 * source, and send the RST packet directly.
-	 */
-	if (oldskb->nf_bridge) {
-		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
-		niph->tot_len = htons(nskb->len);
-		ip_send_check(niph);
-		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
-				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
-			goto free_nskb;
-		dev_queue_xmit(nskb);
-	} else
-#endif
-		ip_local_out(nskb);
-
-	return;
-
- free_nskb:
-	kfree_skb(nskb);
-}
-
+void nf_send_reset(struct sk_buff *oldskb, int hook);
 
 #endif /* _IPV4_NF_REJECT_H */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 345242a79db6..4c019d5c3f57 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -61,8 +61,13 @@ config NFT_CHAIN_ROUTE_IPV4
 	  fields such as the source, destination, type of service and
 	  the packet mark.
 
+config NF_REJECT_IPV4
+	tristate "IPv4 packet rejection"
+	default m if NETFILTER_ADVANCED=n
+
 config NFT_REJECT_IPV4
 	depends on NF_TABLES_IPV4
+	select NF_REJECT_IPV4
 	default NFT_REJECT
 	tristate
 
@@ -208,6 +213,7 @@ config IP_NF_FILTER
 config IP_NF_TARGET_REJECT
 	tristate "REJECT target support"
 	depends on IP_NF_FILTER
+	select NF_REJECT_IPV4
 	default m if NETFILTER_ADVANCED=n
 	help
 	  The REJECT target allows a filtering rule to specify that an ICMP
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 14488cc5fd2c..f4cef5af0969 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -23,6 +23,9 @@ obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o
 obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o
 obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o
 
+# reject
+obj-$(CONFIG_NF_REJECT_IPV4) += nf_reject_ipv4.o
+
 # NAT helpers (nf_conntrack)
 obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
new file mode 100644
index 000000000000..b023b4eb1a96
--- /dev/null
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -0,0 +1,127 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <net/ip.h>
+#include <net/tcp.h>
+#include <net/route.h>
+#include <net/dst.h>
+#include <linux/netfilter_ipv4.h>
+
+/* Send RST reply */
+void nf_send_reset(struct sk_buff *oldskb, int hook)
+{
+	struct sk_buff *nskb;
+	const struct iphdr *oiph;
+	struct iphdr *niph;
+	const struct tcphdr *oth;
+	struct tcphdr _otcph, *tcph;
+
+	/* IP header checks: fragment. */
+	if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
+		return;
+
+	oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
+				 sizeof(_otcph), &_otcph);
+	if (oth == NULL)
+		return;
+
+	/* No RST for RST. */
+	if (oth->rst)
+		return;
+
+	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
+		return;
+
+	/* Check checksum */
+	if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
+		return;
+	oiph = ip_hdr(oldskb);
+
+	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
+			 LL_MAX_HEADER, GFP_ATOMIC);
+	if (!nskb)
+		return;
+
+	skb_reserve(nskb, LL_MAX_HEADER);
+
+	skb_reset_network_header(nskb);
+	niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
+	niph->version	= 4;
+	niph->ihl	= sizeof(struct iphdr) / 4;
+	niph->tos	= 0;
+	niph->id	= 0;
+	niph->frag_off	= htons(IP_DF);
+	niph->protocol	= IPPROTO_TCP;
+	niph->check	= 0;
+	niph->saddr	= oiph->daddr;
+	niph->daddr	= oiph->saddr;
+
+	skb_reset_transport_header(nskb);
+	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
+	memset(tcph, 0, sizeof(*tcph));
+	tcph->source	= oth->dest;
+	tcph->dest	= oth->source;
+	tcph->doff	= sizeof(struct tcphdr) / 4;
+
+	if (oth->ack)
+		tcph->seq = oth->ack_seq;
+	else {
+		tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
+				      oldskb->len - ip_hdrlen(oldskb) -
+				      (oth->doff << 2));
+		tcph->ack = 1;
+	}
+
+	tcph->rst	= 1;
+	tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
+				    niph->daddr, 0);
+	nskb->ip_summed = CHECKSUM_PARTIAL;
+	nskb->csum_start = (unsigned char *)tcph - nskb->head;
+	nskb->csum_offset = offsetof(struct tcphdr, check);
+
+	/* ip_route_me_harder expects skb->dst to be set */
+	skb_dst_set_noref(nskb, skb_dst(oldskb));
+
+	nskb->protocol = htons(ETH_P_IP);
+	if (ip_route_me_harder(nskb, RTN_UNSPEC))
+		goto free_nskb;
+
+	niph->ttl	= ip4_dst_hoplimit(skb_dst(nskb));
+
+	/* "Never happens" */
+	if (nskb->len > dst_mtu(skb_dst(nskb)))
+		goto free_nskb;
+
+	nf_ct_attach(nskb, oldskb);
+
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	/* If we use ip_local_out for bridged traffic, the MAC source on
+	 * the RST will be ours, instead of the destination's.  This confuses
+	 * some routers/firewalls, and they drop the packet.  So we need to
+	 * build the eth header using the original destination's MAC as the
+	 * source, and send the RST packet directly.
+	 */
+	if (oldskb->nf_bridge) {
+		struct ethhdr *oeth = eth_hdr(oldskb);
+		nskb->dev = oldskb->nf_bridge->physindev;
+		niph->tot_len = htons(nskb->len);
+		ip_send_check(niph);
+		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
+				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
+			goto free_nskb;
+		dev_queue_xmit(nskb);
+	} else
+#endif
+		ip_local_out(nskb);
+
+	return;
+
+ free_nskb:
+	kfree_skb(nskb);
+}
+EXPORT_SYMBOL_GPL(nf_send_reset);
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index bb1a40db7be1..6af874fc187f 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -40,8 +40,13 @@ config NFT_CHAIN_ROUTE_IPV6
 	  fields such as the source, destination, flowlabel, hop-limit and
 	  the packet mark.
 
+config NF_REJECT_IPV6
+	tristate "IPv6 packet rejection"
+	default m if NETFILTER_ADVANCED=n
+
 config NFT_REJECT_IPV6
 	depends on NF_TABLES_IPV6
+	select NF_REJECT_IPV6
 	default NFT_REJECT
 	tristate
 
@@ -208,6 +213,7 @@ config IP6_NF_FILTER
 config IP6_NF_TARGET_REJECT
 	tristate "REJECT target support"
 	depends on IP6_NF_FILTER
+	select NF_REJECT_IPV6
 	default m if NETFILTER_ADVANCED=n
 	help
 	  The REJECT target allows a filtering rule to specify that an ICMPv6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 0f7e5b3f328d..fbb25f01143c 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -27,6 +27,9 @@ obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
 # logging
 obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o
 
+# reject
+obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o
+
 # nf_tables
 obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
new file mode 100644
index 000000000000..5f5f0438d74d
--- /dev/null
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -0,0 +1,163 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_checksum.h>
+#include <linux/netfilter_ipv6.h>
+
+void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
+{
+	struct sk_buff *nskb;
+	struct tcphdr otcph, *tcph;
+	unsigned int otcplen, hh_len;
+	int tcphoff, needs_ack;
+	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
+	struct ipv6hdr *ip6h;
+#define DEFAULT_TOS_VALUE	0x0U
+	const __u8 tclass = DEFAULT_TOS_VALUE;
+	struct dst_entry *dst = NULL;
+	u8 proto;
+	__be16 frag_off;
+	struct flowi6 fl6;
+
+	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
+	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
+		pr_debug("addr is not unicast.\n");
+		return;
+	}
+
+	proto = oip6h->nexthdr;
+	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
+
+	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
+		pr_debug("Cannot get TCP header.\n");
+		return;
+	}
+
+	otcplen = oldskb->len - tcphoff;
+
+	/* IP header checks: fragment, too short. */
+	if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
+		pr_debug("proto(%d) != IPPROTO_TCP, "
+			 "or too short. otcplen = %d\n",
+			 proto, otcplen);
+		return;
+	}
+
+	if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
+		BUG();
+
+	/* No RST for RST. */
+	if (otcph.rst) {
+		pr_debug("RST is set\n");
+		return;
+	}
+
+	/* Check checksum. */
+	if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) {
+		pr_debug("TCP checksum is invalid\n");
+		return;
+	}
+
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_TCP;
+	fl6.saddr = oip6h->daddr;
+	fl6.daddr = oip6h->saddr;
+	fl6.fl6_sport = otcph.dest;
+	fl6.fl6_dport = otcph.source;
+	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
+	dst = ip6_route_output(net, NULL, &fl6);
+	if (dst == NULL || dst->error) {
+		dst_release(dst);
+		return;
+	}
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+	if (IS_ERR(dst))
+		return;
+
+	hh_len = (dst->dev->hard_header_len + 15)&~15;
+	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
+			 + sizeof(struct tcphdr) + dst->trailer_len,
+			 GFP_ATOMIC);
+
+	if (!nskb) {
+		net_dbg_ratelimited("cannot alloc skb\n");
+		dst_release(dst);
+		return;
+	}
+
+	skb_dst_set(nskb, dst);
+
+	skb_reserve(nskb, hh_len + dst->header_len);
+
+	skb_put(nskb, sizeof(struct ipv6hdr));
+	skb_reset_network_header(nskb);
+	ip6h = ipv6_hdr(nskb);
+	ip6_flow_hdr(ip6h, tclass, 0);
+	ip6h->hop_limit = ip6_dst_hoplimit(dst);
+	ip6h->nexthdr = IPPROTO_TCP;
+	ip6h->saddr = oip6h->daddr;
+	ip6h->daddr = oip6h->saddr;
+
+	skb_reset_transport_header(nskb);
+	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
+	/* Truncate to length (no data) */
+	tcph->doff = sizeof(struct tcphdr)/4;
+	tcph->source = otcph.dest;
+	tcph->dest = otcph.source;
+
+	if (otcph.ack) {
+		needs_ack = 0;
+		tcph->seq = otcph.ack_seq;
+		tcph->ack_seq = 0;
+	} else {
+		needs_ack = 1;
+		tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
+				      + otcplen - (otcph.doff<<2));
+		tcph->seq = 0;
+	}
+
+	/* Reset flags */
+	((u_int8_t *)tcph)[13] = 0;
+	tcph->rst = 1;
+	tcph->ack = needs_ack;
+	tcph->window = 0;
+	tcph->urg_ptr = 0;
+	tcph->check = 0;
+
+	/* Adjust TCP checksum */
+	tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
+				      &ipv6_hdr(nskb)->daddr,
+				      sizeof(struct tcphdr), IPPROTO_TCP,
+				      csum_partial(tcph,
+						   sizeof(struct tcphdr), 0));
+
+	nf_ct_attach(nskb, oldskb);
+
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+	/* If we use ip6_local_out for bridged traffic, the MAC source on
+	 * the RST will be ours, instead of the destination's.  This confuses
+	 * some routers/firewalls, and they drop the packet.  So we need to
+	 * build the eth header using the original destination's MAC as the
+	 * source, and send the RST packet directly.
+	 */
+	if (oldskb->nf_bridge) {
+		struct ethhdr *oeth = eth_hdr(oldskb);
+		nskb->dev = oldskb->nf_bridge->physindev;
+		nskb->protocol = htons(ETH_P_IPV6);
+		ip6h->payload_len = htons(sizeof(struct tcphdr));
+		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
+				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
+			return;
+		dev_queue_xmit(nskb);
+	} else
+#endif
+		ip6_local_out(nskb);
+}
+EXPORT_SYMBOL_GPL(nf_send_reset6);
-- 
cgit v1.2.3


From 4b7fd5d97ee6e599247b4a55122ca6ba80c8148d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 2 Oct 2014 11:13:21 +0200
Subject: netfilter: explicit module dependency between br_netfilter and
 physdev

You can use physdev to match the physical interface enslaved to the
bridge device. This information is stored in skb->nf_bridge and it is
set up by br_netfilter. So, this is only available when iptables is
used from the bridge netfilter path.

Since 34666d4 ("netfilter: bridge: move br_netfilter out of the core"),
the br_netfilter code is modular. To reduce the impact of this change,
we can autoload the br_netfilter if the physdev match is used since
we assume that the users need br_netfilter in place.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/br_netfilter.h | 6 ++++++
 net/bridge/br_netfilter.c            | 5 +++++
 net/netfilter/xt_physdev.c           | 3 +++
 3 files changed, 14 insertions(+)
 create mode 100644 include/net/netfilter/br_netfilter.h

(limited to 'include')

diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h
new file mode 100644
index 000000000000..2aa6048a55c1
--- /dev/null
+++ b/include/net/netfilter/br_netfilter.h
@@ -0,0 +1,6 @@
+#ifndef _BR_NETFILTER_H_
+#define _BR_NETFILTER_H_
+
+void br_netfilter_enable(void);
+
+#endif /* _BR_NETFILTER_H_ */
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 97e43937aaca..fa1270cc5086 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -856,6 +856,11 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops,
 	return NF_ACCEPT;
 }
 
+void br_netfilter_enable(void)
+{
+}
+EXPORT_SYMBOL_GPL(br_netfilter_enable);
+
 /* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because
  * br_dev_queue_push_xmit is called afterwards */
 static struct nf_hook_ops br_nf_ops[] __read_mostly = {
diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c
index d7ca16b8b8df..f440f57a452f 100644
--- a/net/netfilter/xt_physdev.c
+++ b/net/netfilter/xt_physdev.c
@@ -13,6 +13,7 @@
 #include <linux/netfilter_bridge.h>
 #include <linux/netfilter/xt_physdev.h>
 #include <linux/netfilter/x_tables.h>
+#include <net/netfilter/br_netfilter.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>");
@@ -87,6 +88,8 @@ static int physdev_mt_check(const struct xt_mtchk_param *par)
 {
 	const struct xt_physdev_info *info = par->matchinfo;
 
+	br_netfilter_enable();
+
 	if (!(info->bitmask & XT_PHYSDEV_OP_MASK) ||
 	    info->bitmask & ~XT_PHYSDEV_OP_MASK)
 		return -EINVAL;
-- 
cgit v1.2.3


From 07dcc686fa8f6667dec4696804cdb43a90267b9a Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Tue, 30 Sep 2014 10:50:06 +0900
Subject: ipvs: Clean up comment style in ip_vs.h

* Consistently use the multi-line comment style for networking code:

  /* This
   * That
   * The other thing
   */

* Use single-line comment style for comments with only one line of text.

* In general follow the leading '*' of each line of a comment with a
  single space and then text.

* Add missing line break between functions, remove double line break,
  align comments to previous lines whenever possible.

Reported-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/ip_vs.h | 214 ++++++++++++++++++----------------------------------
 1 file changed, 75 insertions(+), 139 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 576d7f0bed5d..615b20b58545 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1,6 +1,5 @@
-/*
- *      IP Virtual Server
- *      data structure and functionality definitions
+/* IP Virtual Server
+ * data structure and functionality definitions
  */
 
 #ifndef _NET_IP_VS_H
@@ -12,7 +11,7 @@
 
 #include <linux/list.h>                 /* for struct list_head */
 #include <linux/spinlock.h>             /* for struct rwlock_t */
-#include <linux/atomic.h>                 /* for struct atomic_t */
+#include <linux/atomic.h>               /* for struct atomic_t */
 #include <linux/compiler.h>
 #include <linux/timer.h>
 #include <linux/bug.h>
@@ -30,15 +29,13 @@
 #endif
 #include <net/net_namespace.h>		/* Netw namespace */
 
-/*
- * Generic access of ipvs struct
- */
+/* Generic access of ipvs struct */
 static inline struct netns_ipvs *net_ipvs(struct net* net)
 {
 	return net->ipvs;
 }
-/*
- * Get net ptr from skb in traffic cases
+
+/* Get net ptr from skb in traffic cases
  * use skb_sknet when call is from userland (ioctl or netlink)
  */
 static inline struct net *skb_net(const struct sk_buff *skb)
@@ -90,8 +87,8 @@ static inline struct net *skb_sknet(const struct sk_buff *skb)
 	return &init_net;
 #endif
 }
-/*
- * This one needed for single_open_net since net is stored directly in
+
+/* This one needed for single_open_net since net is stored directly in
  * private not as a struct i.e. seq_file_net can't be used.
  */
 static inline struct net *seq_file_single_net(struct seq_file *seq)
@@ -108,7 +105,7 @@ extern int ip_vs_conn_tab_size;
 
 struct ip_vs_iphdr {
 	__u32 len;	/* IPv4 simply where L4 starts
-			   IPv6 where L4 Transport Header starts */
+			 * IPv6 where L4 Transport Header starts */
 	__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
 	__s16 protocol;
 	__s32 flags;
@@ -304,16 +301,11 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
 #define LeaveFunction(level)   do {} while (0)
 #endif
 
-
-/*
- *      The port number of FTP service (in network order).
- */
+/* The port number of FTP service (in network order). */
 #define FTPPORT  cpu_to_be16(21)
 #define FTPDATA  cpu_to_be16(20)
 
-/*
- *      TCP State Values
- */
+/* TCP State Values */
 enum {
 	IP_VS_TCP_S_NONE = 0,
 	IP_VS_TCP_S_ESTABLISHED,
@@ -329,25 +321,19 @@ enum {
 	IP_VS_TCP_S_LAST
 };
 
-/*
- *	UDP State Values
- */
+/* UDP State Values */
 enum {
 	IP_VS_UDP_S_NORMAL,
 	IP_VS_UDP_S_LAST,
 };
 
-/*
- *	ICMP State Values
- */
+/* ICMP State Values */
 enum {
 	IP_VS_ICMP_S_NORMAL,
 	IP_VS_ICMP_S_LAST,
 };
 
-/*
- *	SCTP State Values
- */
+/* SCTP State Values */
 enum ip_vs_sctp_states {
 	IP_VS_SCTP_S_NONE,
 	IP_VS_SCTP_S_INIT1,
@@ -366,21 +352,18 @@ enum ip_vs_sctp_states {
 	IP_VS_SCTP_S_LAST
 };
 
-/*
- *	Delta sequence info structure
- *	Each ip_vs_conn has 2 (output AND input seq. changes).
- *      Only used in the VS/NAT.
+/* Delta sequence info structure
+ * Each ip_vs_conn has 2 (output AND input seq. changes).
+ * Only used in the VS/NAT.
  */
 struct ip_vs_seq {
 	__u32			init_seq;	/* Add delta from this seq */
 	__u32			delta;		/* Delta in sequence numbers */
 	__u32			previous_delta;	/* Delta in sequence numbers
-						   before last resized pkt */
+						 * before last resized pkt */
 };
 
-/*
- * counters per cpu
- */
+/* counters per cpu */
 struct ip_vs_counters {
 	__u32		conns;		/* connections scheduled */
 	__u32		inpkts;		/* incoming packets */
@@ -388,17 +371,13 @@ struct ip_vs_counters {
 	__u64		inbytes;	/* incoming bytes */
 	__u64		outbytes;	/* outgoing bytes */
 };
-/*
- * Stats per cpu
- */
+/* Stats per cpu */
 struct ip_vs_cpu_stats {
 	struct ip_vs_counters   ustats;
 	struct u64_stats_sync   syncp;
 };
 
-/*
- *	IPVS statistics objects
- */
+/* IPVS statistics objects */
 struct ip_vs_estimator {
 	struct list_head	list;
 
@@ -491,9 +470,7 @@ struct ip_vs_protocol {
 	void (*timeout_change)(struct ip_vs_proto_data *pd, int flags);
 };
 
-/*
- * protocol data per netns
- */
+/* protocol data per netns */
 struct ip_vs_proto_data {
 	struct ip_vs_proto_data	*next;
 	struct ip_vs_protocol	*pp;
@@ -520,9 +497,7 @@ struct ip_vs_conn_param {
 	__u8				pe_data_len;
 };
 
-/*
- *	IP_VS structure allocated for each dynamically scheduled connection
- */
+/* IP_VS structure allocated for each dynamically scheduled connection */
 struct ip_vs_conn {
 	struct hlist_node	c_list;         /* hashed list heads */
 	/* Protocol, addresses and port numbers */
@@ -561,17 +536,18 @@ struct ip_vs_conn {
 	struct ip_vs_dest       *dest;          /* real server */
 	atomic_t                in_pkts;        /* incoming packet counter */
 
-	/* packet transmitter for different forwarding methods.  If it
-	   mangles the packet, it must return NF_DROP or better NF_STOLEN,
-	   otherwise this must be changed to a sk_buff **.
-	   NF_ACCEPT can be returned when destination is local.
+	/* Packet transmitter for different forwarding methods.  If it
+	 * mangles the packet, it must return NF_DROP or better NF_STOLEN,
+	 * otherwise this must be changed to a sk_buff **.
+	 * NF_ACCEPT can be returned when destination is local.
 	 */
 	int (*packet_xmit)(struct sk_buff *skb, struct ip_vs_conn *cp,
 			   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 
 	/* Note: we can group the following members into a structure,
-	   in order to save more space, and the following members are
-	   only used in VS/NAT anyway */
+	 * in order to save more space, and the following members are
+	 * only used in VS/NAT anyway
+	 */
 	struct ip_vs_app        *app;           /* bound ip_vs_app object */
 	void                    *app_data;      /* Application private data */
 	struct ip_vs_seq        in_seq;         /* incoming seq. struct */
@@ -584,9 +560,7 @@ struct ip_vs_conn {
 	struct rcu_head		rcu_head;
 };
 
-/*
- *  To save some memory in conn table when name space is disabled.
- */
+/* To save some memory in conn table when name space is disabled. */
 static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp)
 {
 #ifdef CONFIG_NET_NS
@@ -595,6 +569,7 @@ static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp)
 	return &init_net;
 #endif
 }
+
 static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net)
 {
 #ifdef CONFIG_NET_NS
@@ -612,13 +587,12 @@ static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp,
 #endif
 }
 
-/*
- *	Extended internal versions of struct ip_vs_service_user and
- *	ip_vs_dest_user for IPv6 support.
+/* Extended internal versions of struct ip_vs_service_user and ip_vs_dest_user
+ * for IPv6 support.
  *
- *	We need these to conveniently pass around service and destination
- *	options, but unfortunately, we also need to keep the old definitions to
- *	maintain userspace backwards compatibility for the setsockopt interface.
+ * We need these to conveniently pass around service and destination
+ * options, but unfortunately, we also need to keep the old definitions to
+ * maintain userspace backwards compatibility for the setsockopt interface.
  */
 struct ip_vs_service_user_kern {
 	/* virtual service addresses */
@@ -656,8 +630,8 @@ struct ip_vs_dest_user_kern {
 
 
 /*
- *	The information about the virtual service offered to the net
- *	and the forwarding entries
+ * The information about the virtual service offered to the net and the
+ * forwarding entries.
  */
 struct ip_vs_service {
 	struct hlist_node	s_list;   /* for normal service table */
@@ -697,9 +671,8 @@ struct ip_vs_dest_dst {
 	struct rcu_head		rcu_head;
 };
 
-/*
- *	The real server destination forwarding entry
- *	with ip address, port number, and so on.
+/* The real server destination forwarding entry with ip address, port number,
+ * and so on.
  */
 struct ip_vs_dest {
 	struct list_head	n_list;   /* for the dests in the service */
@@ -738,10 +711,7 @@ struct ip_vs_dest {
 	unsigned int		in_rs_table:1;	/* we are in rs_table */
 };
 
-
-/*
- *	The scheduler object
- */
+/* The scheduler object */
 struct ip_vs_scheduler {
 	struct list_head	n_list;		/* d-linked list head */
 	char			*name;		/* scheduler name */
@@ -781,9 +751,7 @@ struct ip_vs_pe {
 	int (*show_pe_data)(const struct ip_vs_conn *cp, char *buf);
 };
 
-/*
- *	The application module object (a.k.a. app incarnation)
- */
+/* The application module object (a.k.a. app incarnation) */
 struct ip_vs_app {
 	struct list_head	a_list;		/* member in app list */
 	int			type;		/* IP_VS_APP_TYPE_xxx */
@@ -799,16 +767,14 @@ struct ip_vs_app {
 	atomic_t		usecnt;		/* usage counter */
 	struct rcu_head		rcu_head;
 
-	/*
-	 * output hook: Process packet in inout direction, diff set for TCP.
+	/* output hook: Process packet in inout direction, diff set for TCP.
 	 * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
 	 *	   2=Mangled but checksum was not updated
 	 */
 	int (*pkt_out)(struct ip_vs_app *, struct ip_vs_conn *,
 		       struct sk_buff *, int *diff);
 
-	/*
-	 * input hook: Process packet in outin direction, diff set for TCP.
+	/* input hook: Process packet in outin direction, diff set for TCP.
 	 * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
 	 *	   2=Mangled but checksum was not updated
 	 */
@@ -867,9 +833,7 @@ struct ipvs_master_sync_state {
 struct netns_ipvs {
 	int			gen;		/* Generation */
 	int			enable;		/* enable like nf_hooks do */
-	/*
-	 *	Hash table: for real service lookups
-	 */
+	/* Hash table: for real service lookups */
 	#define IP_VS_RTAB_BITS 4
 	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
 	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
@@ -903,7 +867,7 @@ struct netns_ipvs {
 	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
 #endif
 	/* ip_vs_conn */
-	atomic_t		conn_count;      /*  connection counter */
+	atomic_t		conn_count;      /* connection counter */
 
 	/* ip_vs_ctl */
 	struct ip_vs_stats		tot_stats;  /* Statistics & est. */
@@ -990,9 +954,9 @@ struct netns_ipvs {
 	char			backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
 	/* net name space ptr */
 	struct net		*net;            /* Needed by timer routines */
-	/* Number of heterogeneous destinations, needed because
-	 * heterogeneous are not supported when synchronization is
-	 * enabled */
+	/* Number of heterogeneous destinations, needed becaus heterogeneous
+	 * are not supported when synchronization is enabled.
+	 */
 	unsigned int		mixed_address_family_dests;
 };
 
@@ -1147,9 +1111,8 @@ static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
 
 #endif
 
-/*
- *      IPVS core functions
- *      (from ip_vs_core.c)
+/* IPVS core functions
+ * (from ip_vs_core.c)
  */
 const char *ip_vs_proto_name(unsigned int proto);
 void ip_vs_init_hash_table(struct list_head *table, int rows);
@@ -1157,11 +1120,9 @@ void ip_vs_init_hash_table(struct list_head *table, int rows);
 
 #define IP_VS_APP_TYPE_FTP	1
 
-/*
- *     ip_vs_conn handling functions
- *     (from ip_vs_conn.c)
+/* ip_vs_conn handling functions
+ * (from ip_vs_conn.c)
  */
-
 enum {
 	IP_VS_DIR_INPUT = 0,
 	IP_VS_DIR_OUTPUT,
@@ -1292,9 +1253,7 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
 	atomic_inc(&ctl_cp->n_control);
 }
 
-/*
- * IPVS netns init & cleanup functions
- */
+/* IPVS netns init & cleanup functions */
 int ip_vs_estimator_net_init(struct net *net);
 int ip_vs_control_net_init(struct net *net);
 int ip_vs_protocol_net_init(struct net *net);
@@ -1309,9 +1268,8 @@ void ip_vs_estimator_net_cleanup(struct net *net);
 void ip_vs_sync_net_cleanup(struct net *net);
 void ip_vs_service_net_cleanup(struct net *net);
 
-/*
- *      IPVS application functions
- *      (from ip_vs_app.c)
+/* IPVS application functions
+ * (from ip_vs_app.c)
  */
 #define IP_VS_APP_MAX_PORTS  8
 struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app);
@@ -1331,9 +1289,7 @@ int unregister_ip_vs_pe(struct ip_vs_pe *pe);
 struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
 struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name);
 
-/*
- * Use a #define to avoid all of module.h just for these trivial ops
- */
+/* Use a #define to avoid all of module.h just for these trivial ops */
 #define ip_vs_pe_get(pe)			\
 	if (pe && pe->module)			\
 		__module_get(pe->module);
@@ -1342,9 +1298,7 @@ struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name);
 	if (pe && pe->module)			\
 		module_put(pe->module);
 
-/*
- *	IPVS protocol functions (from ip_vs_proto.c)
- */
+/* IPVS protocol functions (from ip_vs_proto.c) */
 int ip_vs_protocol_init(void);
 void ip_vs_protocol_cleanup(void);
 void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
@@ -1362,9 +1316,8 @@ extern struct ip_vs_protocol ip_vs_protocol_esp;
 extern struct ip_vs_protocol ip_vs_protocol_ah;
 extern struct ip_vs_protocol ip_vs_protocol_sctp;
 
-/*
- *      Registering/unregistering scheduler functions
- *      (from ip_vs_sched.c)
+/* Registering/unregistering scheduler functions
+ * (from ip_vs_sched.c)
  */
 int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
 int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
@@ -1383,10 +1336,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 
 void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
 
-
-/*
- *      IPVS control data and functions (from ip_vs_ctl.c)
- */
+/* IPVS control data and functions (from ip_vs_ctl.c) */
 extern struct ip_vs_stats ip_vs_stats;
 extern int sysctl_ip_vs_sync_ver;
 
@@ -1427,26 +1377,21 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
 		kfree(dest);
 }
 
-/*
- *      IPVS sync daemon data and function prototypes
- *      (from ip_vs_sync.c)
+/* IPVS sync daemon data and function prototypes
+ * (from ip_vs_sync.c)
  */
 int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid);
 int stop_sync_thread(struct net *net, int state);
 void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts);
 
-/*
- *      IPVS rate estimator prototypes (from ip_vs_est.c)
- */
+/* IPVS rate estimator prototypes (from ip_vs_est.c) */
 void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats);
 void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats);
 void ip_vs_zero_estimator(struct ip_vs_stats *stats);
 void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
 			  struct ip_vs_stats *stats);
 
-/*
- *	Various IPVS packet transmitters (from ip_vs_xmit.c)
- */
+/* Various IPVS packet transmitters (from ip_vs_xmit.c) */
 int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		    struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
@@ -1477,12 +1422,10 @@ int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 #endif
 
 #ifdef CONFIG_SYSCTL
-/*
- *	This is a simple mechanism to ignore packets when
- *	we are loaded. Just set ip_vs_drop_rate to 'n' and
- *	we start to drop 1/rate of the packets
+/* This is a simple mechanism to ignore packets when
+ * we are loaded. Just set ip_vs_drop_rate to 'n' and
+ * we start to drop 1/rate of the packets
  */
-
 static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 {
 	if (!ipvs->drop_rate)
@@ -1496,9 +1439,7 @@ static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
 static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; }
 #endif
 
-/*
- *      ip_vs_fwd_tag returns the forwarding tag of the connection
- */
+/* ip_vs_fwd_tag returns the forwarding tag of the connection */
 #define IP_VS_FWD_METHOD(cp)  (cp->flags & IP_VS_CONN_F_FWD_MASK)
 
 static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp)
@@ -1557,9 +1498,7 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
 	return csum_partial(diff, sizeof(diff), oldsum);
 }
 
-/*
- * Forget current conntrack (unconfirmed) and attach notrack entry
- */
+/* Forget current conntrack (unconfirmed) and attach notrack entry */
 static inline void ip_vs_notrack(struct sk_buff *skb)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
@@ -1576,9 +1515,8 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
 }
 
 #ifdef CONFIG_IP_VS_NFCT
-/*
- *      Netfilter connection tracking
- *      (from ip_vs_nfct.c)
+/* Netfilter connection tracking
+ * (from ip_vs_nfct.c)
  */
 static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 {
@@ -1617,14 +1555,12 @@ static inline int ip_vs_confirm_conntrack(struct sk_buff *skb)
 static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 {
 }
-/* CONFIG_IP_VS_NFCT */
-#endif
+#endif /* CONFIG_IP_VS_NFCT */
 
 static inline int
 ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
 {
-	/*
-	 * We think the overhead of processing active connections is 256
+	/* We think the overhead of processing active connections is 256
 	 * times higher than that of inactive connections in average. (This
 	 * 256 times might not be accurate, we will change it later) We
 	 * use the following formula to estimate the overhead now:
-- 
cgit v1.2.3


From 5dc0158a27f65e7efaa6e3cc496d93b4c4c65d19 Mon Sep 17 00:00:00 2001
From: "Subhransu S. Prusty" <subhransu.s.prusty@intel.com>
Date: Fri, 19 Sep 2014 16:46:05 +0530
Subject: ASoC: Export dapm_kcontrol_get_value

The DSP driver needs to know widget control value in its event handler for
widgets like mixers. This is required in the subsequent patches

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h | 1 +
 sound/soc/soc-dapm.c     | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index aac04ff84eea..6ae0a1952ad7 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -432,6 +432,7 @@ int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
 int snd_soc_dapm_ignore_suspend(struct snd_soc_dapm_context *dapm,
 				const char *pin);
 void snd_soc_dapm_auto_nc_pins(struct snd_soc_card *card);
+unsigned int dapm_kcontrol_get_value(const struct snd_kcontrol *kcontrol);
 
 /* Mostly internal - should not normally be used */
 void dapm_mark_io_dirty(struct snd_soc_dapm_context *dapm);
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 8348352dc2c6..08c79f09034f 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -326,12 +326,13 @@ static struct list_head *dapm_kcontrol_get_path_list(
 	list_for_each_entry(path, dapm_kcontrol_get_path_list(kcontrol), \
 		list_kcontrol)
 
-static unsigned int dapm_kcontrol_get_value(const struct snd_kcontrol *kcontrol)
+unsigned int dapm_kcontrol_get_value(const struct snd_kcontrol *kcontrol)
 {
 	struct dapm_kcontrol_data *data = snd_kcontrol_chip(kcontrol);
 
 	return data->value;
 }
+EXPORT_SYMBOL_GPL(dapm_kcontrol_get_value);
 
 static bool dapm_kcontrol_set_value(const struct snd_kcontrol *kcontrol,
 	unsigned int value)
-- 
cgit v1.2.3


From dba4b74d2da8798626e2b702ad3f452671e335f7 Mon Sep 17 00:00:00 2001
From: Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
Date: Wed, 1 Oct 2014 15:05:25 +0300
Subject: wil6210: atomic I/O for the card memory

Introduce netdev IOCTLs, to be used by the debug tools.

Allows to read/write single dword value or
memory block, aligned to dword
Different address modes supported:
- BAR offset
- Firmware "linker" address
- target's AHB bus

Signed-off-by: Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 MAINTAINERS                                |   1 +
 drivers/net/wireless/ath/wil6210/Makefile  |   1 +
 drivers/net/wireless/ath/wil6210/ioctl.c   | 173 +++++++++++++++++++++++++++++
 drivers/net/wireless/ath/wil6210/netdev.c  |  12 ++
 drivers/net/wireless/ath/wil6210/wil6210.h |   2 +
 include/uapi/linux/wil6210_uapi.h          |  87 +++++++++++++++
 6 files changed, 276 insertions(+)
 create mode 100644 drivers/net/wireless/ath/wil6210/ioctl.c
 create mode 100644 include/uapi/linux/wil6210_uapi.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 482888d80431..66de6b2923d4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1611,6 +1611,7 @@ L:	wil6210@qca.qualcomm.com
 S:	Supported
 W:	http://wireless.kernel.org/en/users/Drivers/wil6210
 F:	drivers/net/wireless/ath/wil6210/
+F:	include/uapi/linux/wil6210_uapi.h
 
 CARL9170 LINUX COMMUNITY WIRELESS DRIVER
 M:	Christian Lamparter <chunkeey@googlemail.com>
diff --git a/drivers/net/wireless/ath/wil6210/Makefile b/drivers/net/wireless/ath/wil6210/Makefile
index 05f29a6b1ba8..8ad4b5f97e04 100644
--- a/drivers/net/wireless/ath/wil6210/Makefile
+++ b/drivers/net/wireless/ath/wil6210/Makefile
@@ -10,6 +10,7 @@ wil6210-y += interrupt.o
 wil6210-y += txrx.o
 wil6210-y += debug.o
 wil6210-y += rx_reorder.o
+wil6210-y += ioctl.o
 wil6210-y += fw.o
 wil6210-$(CONFIG_WIL6210_TRACING) += trace.o
 wil6210-y += wil_platform.o
diff --git a/drivers/net/wireless/ath/wil6210/ioctl.c b/drivers/net/wireless/ath/wil6210/ioctl.c
new file mode 100644
index 000000000000..e9c0673819c6
--- /dev/null
+++ b/drivers/net/wireless/ath/wil6210/ioctl.c
@@ -0,0 +1,173 @@
+/*
+ * Copyright (c) 2014 Qualcomm Atheros, Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/uaccess.h>
+
+#include "wil6210.h"
+#include <uapi/linux/wil6210_uapi.h>
+
+#define wil_hex_dump_ioctl(prefix_str, buf, len) \
+	print_hex_dump_debug("DBG[IOC ]" prefix_str, \
+			     DUMP_PREFIX_OFFSET, 16, 1, buf, len, true)
+#define wil_dbg_ioctl(wil, fmt, arg...) wil_dbg(wil, "DBG[IOC ]" fmt, ##arg)
+
+static void __iomem *wil_ioc_addr(struct wil6210_priv *wil, uint32_t addr,
+				  uint32_t size, enum wil_memio_op op)
+{
+	void __iomem *a;
+	u32 off;
+
+	switch (op & wil_mmio_addr_mask) {
+	case wil_mmio_addr_linker:
+		a = wmi_buffer(wil, cpu_to_le32(addr));
+		break;
+	case wil_mmio_addr_ahb:
+		a = wmi_addr(wil, addr);
+		break;
+	case wil_mmio_addr_bar:
+		a = wmi_addr(wil, addr + WIL6210_FW_HOST_OFF);
+		break;
+	default:
+		wil_err(wil, "Unsupported address mode, op = 0x%08x\n", op);
+		return NULL;
+	}
+
+	off = a - wil->csr;
+	if (size >= WIL6210_MEM_SIZE - off) {
+		wil_err(wil, "Requested block does not fit into memory: "
+			"off = 0x%08x size = 0x%08x\n", off, size);
+		return NULL;
+	}
+
+	return a;
+}
+
+static int wil_ioc_memio_dword(struct wil6210_priv *wil, void __user *data)
+{
+	struct wil_memio io;
+	void __iomem *a;
+	bool need_copy = false;
+
+	if (copy_from_user(&io, data, sizeof(io)))
+		return -EFAULT;
+
+	wil_dbg_ioctl(wil, "IO: addr = 0x%08x val = 0x%08x op = 0x%08x\n",
+		      io.addr, io.val, io.op);
+
+	a = wil_ioc_addr(wil, io.addr, sizeof(u32), io.op);
+	if (!a) {
+		wil_err(wil, "invalid address 0x%08x, op = 0x%08x\n", io.addr,
+			io.op);
+		return -EINVAL;
+	}
+	/* operation */
+	switch (io.op & wil_mmio_op_mask) {
+	case wil_mmio_read:
+		io.val = ioread32(a);
+		need_copy = true;
+		break;
+	case wil_mmio_write:
+		iowrite32(io.val, a);
+		wmb(); /* make sure write propagated to HW */
+		break;
+	default:
+		wil_err(wil, "Unsupported operation, op = 0x%08x\n", io.op);
+		return -EINVAL;
+	}
+
+	if (need_copy) {
+		wil_dbg_ioctl(wil, "IO done: addr = 0x%08x"
+			      " val = 0x%08x op = 0x%08x\n",
+			      io.addr, io.val, io.op);
+		if (copy_to_user(data, &io, sizeof(io)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int wil_ioc_memio_block(struct wil6210_priv *wil, void __user *data)
+{
+	struct wil_memio_block io;
+	void *block;
+	void __iomem *a;
+	int rc = 0;
+
+	if (copy_from_user(&io, data, sizeof(io)))
+		return -EFAULT;
+
+	wil_dbg_ioctl(wil, "IO: addr = 0x%08x size = 0x%08x op = 0x%08x\n",
+		      io.addr, io.size, io.op);
+
+	/* size */
+	if (io.size % 4) {
+		wil_err(wil, "size is not multiple of 4:  0x%08x\n", io.size);
+		return -EINVAL;
+	}
+
+	a = wil_ioc_addr(wil, io.addr, io.size, io.op);
+	if (!a) {
+		wil_err(wil, "invalid address 0x%08x, op = 0x%08x\n", io.addr,
+			io.op);
+		return -EINVAL;
+	}
+
+	block = kmalloc(io.size, GFP_USER);
+	if (!block)
+		return -ENOMEM;
+
+	/* operation */
+	switch (io.op & wil_mmio_op_mask) {
+	case wil_mmio_read:
+		wil_memcpy_fromio_32(block, a, io.size);
+		wil_hex_dump_ioctl("Read  ", block, io.size);
+		if (copy_to_user(io.block, block, io.size)) {
+			rc = -EFAULT;
+			goto out_free;
+		}
+		break;
+	case wil_mmio_write:
+		if (copy_from_user(block, io.block, io.size)) {
+			rc = -EFAULT;
+			goto out_free;
+		}
+		wil_memcpy_toio_32(a, block, io.size);
+		wmb(); /* make sure write propagated to HW */
+		wil_hex_dump_ioctl("Write ", block, io.size);
+		break;
+	default:
+		wil_err(wil, "Unsupported operation, op = 0x%08x\n", io.op);
+		rc = -EINVAL;
+		break;
+	}
+
+out_free:
+	kfree(block);
+	return rc;
+}
+
+int wil_ioctl(struct wil6210_priv *wil, void __user *data, int cmd)
+{
+	switch (cmd) {
+	case WIL_IOCTL_MEMIO:
+		return wil_ioc_memio_dword(wil, data);
+	case WIL_IOCTL_MEMIO_BLOCK:
+		return wil_ioc_memio_block(wil, data);
+	default:
+		wil_dbg_ioctl(wil, "Unsupported IOCTL 0x%04x\n", cmd);
+		return -ENOIOCTLCMD;
+	}
+}
diff --git a/drivers/net/wireless/ath/wil6210/netdev.c b/drivers/net/wireless/ath/wil6210/netdev.c
index c3f0ddfaa5da..239965106c05 100644
--- a/drivers/net/wireless/ath/wil6210/netdev.c
+++ b/drivers/net/wireless/ath/wil6210/netdev.c
@@ -52,6 +52,17 @@ static int wil_change_mtu(struct net_device *ndev, int new_mtu)
 	return 0;
 }
 
+static int wil_do_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
+{
+	struct wil6210_priv *wil = ndev_to_wil(ndev);
+
+	int ret = wil_ioctl(wil, ifr->ifr_data, cmd);
+
+	wil_dbg_misc(wil, "ioctl(0x%04x) -> %d\n", cmd, ret);
+
+	return ret;
+}
+
 static const struct net_device_ops wil_netdev_ops = {
 	.ndo_open		= wil_open,
 	.ndo_stop		= wil_stop,
@@ -59,6 +70,7 @@ static const struct net_device_ops wil_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= wil_change_mtu,
+	.ndo_do_ioctl		= wil_do_ioctl,
 };
 
 static int wil6210_netdev_poll_rx(struct napi_struct *napi, int budget)
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 2991609885f7..61cceca155a2 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -595,5 +595,7 @@ void wil6210_unmask_irq_rx(struct wil6210_priv *wil);
 
 int wil_iftype_nl2wmi(enum nl80211_iftype type);
 
+int wil_ioctl(struct wil6210_priv *wil, void __user *data, int cmd);
 int wil_request_firmware(struct wil6210_priv *wil, const char *name);
+
 #endif /* __WIL6210_H__ */
diff --git a/include/uapi/linux/wil6210_uapi.h b/include/uapi/linux/wil6210_uapi.h
new file mode 100644
index 000000000000..6a3cddd156c4
--- /dev/null
+++ b/include/uapi/linux/wil6210_uapi.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (c) 2014 Qualcomm Atheros, Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __WIL6210_UAPI_H__
+#define __WIL6210_UAPI_H__
+
+#if !defined(__KERNEL__)
+#define __user
+#endif
+
+#include <linux/sockios.h>
+
+/* Numbers SIOCDEVPRIVATE and SIOCDEVPRIVATE + 1
+ * are used by Android devices to implement PNO (preferred network offload).
+ * Albeit it is temporary solution, use different numbers to avoid conflicts
+ */
+
+/**
+ * Perform 32-bit I/O operation to the card memory
+ *
+ * User code should arrange data in memory like this:
+ *
+ *	struct wil_memio io;
+ *	struct ifreq ifr = {
+ *		.ifr_data = &io,
+ *	};
+ */
+#define WIL_IOCTL_MEMIO (SIOCDEVPRIVATE + 2)
+
+/**
+ * Perform block I/O operation to the card memory
+ *
+ * User code should arrange data in memory like this:
+ *
+ *	void *buf;
+ *	struct wil_memio_block io = {
+ *		.block = buf,
+ *	};
+ *	struct ifreq ifr = {
+ *		.ifr_data = &io,
+ *	};
+ */
+#define WIL_IOCTL_MEMIO_BLOCK (SIOCDEVPRIVATE + 3)
+
+/**
+ * operation to perform
+ *
+ * @wil_mmio_op_mask - bits defining operation,
+ * @wil_mmio_addr_mask - bits defining addressing mode
+ */
+enum wil_memio_op {
+	wil_mmio_read = 0,
+	wil_mmio_write = 1,
+	wil_mmio_op_mask = 0xff,
+	wil_mmio_addr_linker = 0 << 8,
+	wil_mmio_addr_ahb = 1 << 8,
+	wil_mmio_addr_bar = 2 << 8,
+	wil_mmio_addr_mask = 0xff00,
+};
+
+struct wil_memio {
+	uint32_t op; /* enum wil_memio_op */
+	uint32_t addr; /* should be 32-bit aligned */
+	uint32_t val;
+};
+
+struct wil_memio_block {
+	uint32_t op; /* enum wil_memio_op */
+	uint32_t addr; /* should be 32-bit aligned */
+	uint32_t size; /* should be multiple of 4 */
+	void __user *block; /* block address */
+};
+
+#endif /* __WIL6210_UAPI_H__ */
-- 
cgit v1.2.3


From 562c85cadb065e33ec9f651b8d41cdfd3054a5d0 Mon Sep 17 00:00:00 2001
From: Yalin Wang <Yalin.Wang@sonymobile.com>
Date: Fri, 26 Sep 2014 03:30:59 +0100
Subject: ARM: 8168/1: extend __init_end to a page align address

This patch changes the __init_end address to a
page align address, so that free_initmem() can
free the whole .init section, because if the end
address is not page aligned, it will round down to
a page align address, then the tail unligned page
will not be freed.

Signed-off-by: wang <yalin.wang2010@gmail.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/kernel/vmlinux.lds.S     | 2 +-
 arch/arm64/kernel/vmlinux.lds.S   | 2 +-
 include/asm-generic/vmlinux.lds.h | 2 ++
 3 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 6f57cb94367f..8e95aa47457a 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -219,8 +219,8 @@ SECTIONS
 	__data_loc = ALIGN(4);		/* location in binary */
 	. = PAGE_OFFSET + TEXT_OFFSET;
 #else
-	__init_end = .;
 	. = ALIGN(THREAD_SIZE);
+	__init_end = .;
 	__data_loc = .;
 #endif
 
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 97f0c0429dfa..edf8715ba39b 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -97,9 +97,9 @@ SECTIONS
 
 	PERCPU_SECTION(64)
 
+	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
 
-	. = ALIGN(PAGE_SIZE);
 	_data = .;
 	_sdata = .;
 	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 5ba0360663a7..aa70cbda327c 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -40,6 +40,8 @@
  * }
  *
  * [__init_begin, __init_end] is the init section that may be freed after init
+ * 	// __init_begin and __init_end should be page aligned, so that we can
+ *	// free the whole .init memory
  * [_stext, _etext] is the text section
  * [_sdata, _edata] is the data section
  *
-- 
cgit v1.2.3


From 347abad981c1ef815ea5ba861adba6a8c6aa1580 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Tue, 30 Sep 2014 15:59:47 -0400
Subject: sched, time: Fix build error with 64 bit cputime_t on 32 bit systems

On 32 bit systems cmpxchg cannot handle 64 bit values, so
some additional magic is required to allow a 32 bit system
with CONFIG_VIRT_CPU_ACCOUNTING_GEN=y enabled to build.

Make sure the correct cmpxchg function is used when doing
an atomic swap of a cputime_t.

Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: umgwanakikbuti@gmail.com
Cc: fweisbec@gmail.com
Cc: srao@redhat.com
Cc: lwoodman@redhat.com
Cc: atheurer@redhat.com
Cc: oleg@redhat.com
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linux390@de.ibm.com
Cc: linux-arch@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Link: http://lkml.kernel.org/r/20140930155947.070cdb1f@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/include/asm/cputime.h    |  2 ++
 arch/s390/include/asm/cputime.h       |  2 ++
 include/asm-generic/cputime_jiffies.h |  2 ++
 include/asm-generic/cputime_nsecs.h   |  2 ++
 kernel/sched/cputime.c                | 29 +++++++++++++++++++----------
 5 files changed, 27 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 607559ab271f..6c840ceab820 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -32,6 +32,8 @@ static inline void setup_cputime_one_jiffy(void) { }
 typedef u64 __nocast cputime_t;
 typedef u64 __nocast cputime64_t;
 
+#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
+
 #ifdef __KERNEL__
 
 /*
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index f65bd3634519..3001887f94b7 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -18,6 +18,8 @@
 typedef unsigned long long __nocast cputime_t;
 typedef unsigned long long __nocast cputime64_t;
 
+#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
+
 static inline unsigned long __div(unsigned long long n, unsigned long base)
 {
 #ifndef CONFIG_64BIT
diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h
index d5cb78f53986..fe386fc6e85e 100644
--- a/include/asm-generic/cputime_jiffies.h
+++ b/include/asm-generic/cputime_jiffies.h
@@ -3,6 +3,8 @@
 
 typedef unsigned long __nocast cputime_t;
 
+#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
+
 #define cputime_one_jiffy		jiffies_to_cputime(1)
 #define cputime_to_jiffies(__ct)	(__force unsigned long)(__ct)
 #define cputime_to_scaled(__ct)		(__ct)
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
index 4e817606c549..0419485891f2 100644
--- a/include/asm-generic/cputime_nsecs.h
+++ b/include/asm-generic/cputime_nsecs.h
@@ -21,6 +21,8 @@
 typedef u64 __nocast cputime_t;
 typedef u64 __nocast cputime64_t;
 
+#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
+
 #define cputime_one_jiffy		jiffies_to_cputime(1)
 
 #define cputime_div(__ct, divisor)  div_u64((__force u64)__ct, divisor)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 64492dff8a81..8394b1ee600c 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -554,6 +554,23 @@ drop_precision:
 	return (__force cputime_t) scaled;
 }
 
+/*
+ * Atomically advance counter to the new value. Interrupts, vcpu
+ * scheduling, and scaling inaccuracies can cause cputime_advance
+ * to be occasionally called with a new value smaller than counter.
+ * Let's enforce atomicity.
+ *
+ * Normally a caller will only go through this loop once, or not
+ * at all in case a previous caller updated counter the same jiffy.
+ */
+static void cputime_advance(cputime_t *counter, cputime_t new)
+{
+	cputime_t old;
+
+	while (new > (old = ACCESS_ONCE(*counter)))
+		cmpxchg_cputime(counter, old, new);
+}
+
 /*
  * Adjust tick based cputime random precision against scheduler
  * runtime accounting.
@@ -599,16 +616,8 @@ static void cputime_adjust(struct task_cputime *curr,
 		utime = rtime - stime;
 	}
 
-	/*
-	 * If the tick based count grows faster than the scheduler one,
-	 * the result of the scaling may go backward.
-	 * Let's enforce monotonicity.
-	 * Atomic exchange protects against concurrent cputime_adjust().
-	 */
-	while (stime > (rtime = ACCESS_ONCE(prev->stime)))
-		cmpxchg(&prev->stime, rtime, stime);
-	while (utime > (rtime = ACCESS_ONCE(prev->utime)))
-		cmpxchg(&prev->utime, rtime, utime);
+	cputime_advance(&prev->stime, stime);
+	cputime_advance(&prev->utime, utime);
 
 out:
 	*ut = prev->utime;
-- 
cgit v1.2.3


From 2291059c852706c6f5ffb400366042b7625066cd Mon Sep 17 00:00:00 2001
From: Pranith Kumar <bobby.prani@gmail.com>
Date: Tue, 23 Sep 2014 10:29:50 -0400
Subject: locking,arch: Use ACCESS_ONCE() instead of cast to volatile in
 atomic_read()

Use the much more reader friendly ACCESS_ONCE() instead of the cast to volatile.
This is purely a stylistic change.

Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Acked-by: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/1411482607-20948-1-git-send-email-bobby.prani@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/atomic.h    | 4 ++--
 arch/arm/include/asm/atomic.h      | 2 +-
 arch/arm64/include/asm/atomic.h    | 4 ++--
 arch/avr32/include/asm/atomic.h    | 2 +-
 arch/cris/include/asm/atomic.h     | 2 +-
 arch/frv/include/asm/atomic.h      | 2 +-
 arch/ia64/include/asm/atomic.h     | 4 ++--
 arch/m32r/include/asm/atomic.h     | 2 +-
 arch/m68k/include/asm/atomic.h     | 2 +-
 arch/mips/include/asm/atomic.h     | 4 ++--
 arch/parisc/include/asm/atomic.h   | 4 ++--
 arch/sh/include/asm/atomic.h       | 2 +-
 arch/sparc/include/asm/atomic_32.h | 2 +-
 arch/sparc/include/asm/atomic_64.h | 4 ++--
 arch/x86/include/asm/atomic.h      | 2 +-
 arch/x86/include/asm/atomic64_64.h | 2 +-
 arch/xtensa/include/asm/atomic.h   | 2 +-
 include/asm-generic/atomic.h       | 2 +-
 18 files changed, 24 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 6fbb53a13049..8f8eafbedd7c 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -17,8 +17,8 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 
 #define atomic_set(v,i)		((v)->counter = (i))
 #define atomic64_set(v,i)	((v)->counter = (i))
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 832f1cdfcd6a..e22c11970b7b 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -27,7 +27,7 @@
  * strex/ldrex monitor on some implementations. The reason we can use it for
  * atomic_set() is the clrex or dummy strex done on every exception return.
  */
-#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))
 
 #if __LINUX_ARM_ARCH__ >= 6
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index b83c325e587f..7047051ded40 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -35,7 +35,7 @@
  * strex/ldrex monitor on some implementations. The reason we can use it for
  * atomic_set() is the clrex or dummy strex done on every exception return.
  */
-#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))
 
 /*
@@ -139,7 +139,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
  */
 #define ATOMIC64_INIT(i) { (i) }
 
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic64_set(v,i)	(((v)->counter) = (i))
 
 #define ATOMIC64_OP(op, asm_op)						\
diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h
index 83e980a4e483..2d07ce1c5327 100644
--- a/arch/avr32/include/asm/atomic.h
+++ b/arch/avr32/include/asm/atomic.h
@@ -19,7 +19,7 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = i)
 
 #define ATOMIC_OP_RETURN(op, asm_op, asm_con)				\
diff --git a/arch/cris/include/asm/atomic.h b/arch/cris/include/asm/atomic.h
index 0033f9dfea24..279766a70664 100644
--- a/arch/cris/include/asm/atomic.h
+++ b/arch/cris/include/asm/atomic.h
@@ -17,7 +17,7 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-#define atomic_read(v) (*(volatile int *)&(v)->counter)
+#define atomic_read(v) ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i) (((v)->counter) = (i))
 
 /* These should be written in asm but we do it in C for now. */
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index f6c3a1690101..102190a61d65 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -31,7 +31,7 @@
  */
 
 #define ATOMIC_INIT(i)		{ (i) }
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = (i))
 
 #ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 42919a831c6c..0bf03501fe5c 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -21,8 +21,8 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 
 #define atomic_set(v,i)		(((v)->counter) = (i))
 #define atomic64_set(v,i)	(((v)->counter) = (i))
diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h
index 3946b2c8d971..31bb74adba08 100644
--- a/arch/m32r/include/asm/atomic.h
+++ b/arch/m32r/include/asm/atomic.h
@@ -28,7 +28,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 
 /**
  * atomic_set - set atomic variable
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 663d4ba2462c..e85f047fb072 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -17,7 +17,7 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = i)
 
 /*
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index f3ee721fe61d..6dd6bfc607e9 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -29,7 +29,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 
 /*
  * atomic_set - set atomic variable
@@ -306,7 +306,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
  * @v: pointer of type atomic64_t
  *
  */
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 
 /*
  * atomic64_set - set atomic variable
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 219750bb4ae7..226f8ca993f6 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -67,7 +67,7 @@ static __inline__ void atomic_set(atomic_t *v, int i)
 
 static __inline__ int atomic_read(const atomic_t *v)
 {
-	return (*(volatile int *)&(v)->counter);
+	return ACCESS_ONCE((v)->counter);
 }
 
 /* exported interface */
@@ -204,7 +204,7 @@ atomic64_set(atomic64_t *v, s64 i)
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
-	return (*(volatile long *)&(v)->counter);
+	return ACCESS_ONCE((v)->counter);
 }
 
 #define atomic64_inc(v)		(atomic64_add(   1,(v)))
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index f57b8a6743b3..05b9f74ce2d5 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -14,7 +14,7 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i)		((v)->counter = (i))
 
 #if defined(CONFIG_GUSA_RB)
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 7b024f02a7ce..765c1776ec9f 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -26,7 +26,7 @@ int atomic_cmpxchg(atomic_t *, int, int);
 int __atomic_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
-#define atomic_read(v)          (*(volatile int *)&(v)->counter)
+#define atomic_read(v)          ACCESS_ONCE((v)->counter)
 
 #define atomic_add(i, v)	((void)atomic_add_return( (int)(i), (v)))
 #define atomic_sub(i, v)	((void)atomic_add_return(-(int)(i), (v)))
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 7e4ca1e73cd9..4082749913ce 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -14,8 +14,8 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 
 #define atomic_set(v, i)	(((v)->counter) = i)
 #define atomic64_set(v, i)	(((v)->counter) = i)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index bf20c817ed34..5e5cd123fdfb 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -24,7 +24,7 @@
  */
 static inline int atomic_read(const atomic_t *v)
 {
-	return (*(volatile int *)&(v)->counter);
+	return ACCESS_ONCE((v)->counter);
 }
 
 /**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 46e9052bbd28..f8d273e18516 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -18,7 +18,7 @@
  */
 static inline long atomic64_read(const atomic64_t *v)
 {
-	return (*(volatile long *)&(v)->counter);
+	return ACCESS_ONCE((v)->counter);
 }
 
 /**
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index 626676660b80..00b7d46b35b8 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -47,7 +47,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 
 /**
  * atomic_set - set atomic variable
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 56d4d36e1531..1973ad2b13f4 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -126,7 +126,7 @@ ATOMIC_OP(or, |)
  * Atomically reads the value of @v.
  */
 #ifndef atomic_read
-#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 #endif
 
 /**
-- 
cgit v1.2.3


From 8acd91e8620836a56ff62028ed28ba629f2881a0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 30 Sep 2014 15:26:00 +0200
Subject: locking/lockdep: Revert qrwlock recusive stuff

Commit f0bab73cb539 ("locking/lockdep: Restrict the use of recursive
read_lock() with qrwlock") changed lockdep to try and conform to the
qrwlock semantics which differ from the traditional rwlock semantics.

In particular qrwlock is fair outside of interrupt context, but in
interrupt context readers will ignore all fairness.

The problem modeling this is that read and write side have different
lock state (interrupts) semantics but we only have a single
representation of these. Therefore lockdep will get confused, thinking
the lock can cause interrupt lock inversions.

So revert it for now; the old rwlock semantics were already imperfectly
modeled and the qrwlock extra won't fit either.

If we want to properly fix this, I think we need to resurrect the work
by Gautham did a few years ago that split the read and write state of
locks:

   http://lwn.net/Articles/332801/

FWIW the locking selftest that would've failed (and was reported by
Borislav earlier) is something like:

  RL(X1);	/* IRQ-ON */
  LOCK(A);
  UNLOCK(A);
  RU(X1);

  IRQ_ENTER();
  RL(X1);	/* IN-IRQ */
  RU(X1);
  IRQ_EXIT();

At which point it would report that because A is an IRQ-unsafe lock we
can suffer the following inversion:

	CPU0		CPU1

	lock(A)
			lock(X1)
			lock(A)
	<IRQ>
	 lock(X1)

And this is 'wrong' because X1 can recurse (assuming the above lock are
in fact read-lock) but lockdep doesn't know about this.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: ego@linux.vnet.ibm.com
Cc: bp@alien8.de
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20140930132600.GA7444@worktop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/lockdep.h  | 10 +--------
 kernel/locking/lockdep.c |  6 ------
 lib/locking-selftest.c   | 56 ++++++------------------------------------------
 3 files changed, 8 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index b5a84b62fb84..f388481201cd 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -478,24 +478,16 @@ static inline void print_irqtrace_events(struct task_struct *curr)
  * on the per lock-class debug mode:
  */
 
-/*
- * Read states in the 2-bit held_lock:read field:
- *  0: Exclusive lock
- *  1: Shareable lock, cannot be recursively called
- *  2: Shareable lock, can be recursively called
- *  3: Shareable lock, cannot be recursively called except in interrupt context
- */
 #define lock_acquire_exclusive(l, s, t, n, i)		lock_acquire(l, s, t, 0, 1, n, i)
 #define lock_acquire_shared(l, s, t, n, i)		lock_acquire(l, s, t, 1, 1, n, i)
 #define lock_acquire_shared_recursive(l, s, t, n, i)	lock_acquire(l, s, t, 2, 1, n, i)
-#define lock_acquire_shared_irecursive(l, s, t, n, i)	lock_acquire(l, s, t, 3, 1, n, i)
 
 #define spin_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define spin_acquire_nest(l, s, t, n, i)	lock_acquire_exclusive(l, s, t, n, i)
 #define spin_release(l, n, i)			lock_release(l, n, i)
 
 #define rwlock_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
-#define rwlock_acquire_read(l, s, t, i)		lock_acquire_shared_irecursive(l, s, t, NULL, i)
+#define rwlock_acquire_read(l, s, t, i)		lock_acquire_shared_recursive(l, s, t, NULL, i)
 #define rwlock_release(l, n, i)			lock_release(l, n, i)
 
 #define seqcount_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 420ba685c4e5..88d0d4420ad2 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3597,12 +3597,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	/*
-	 * An interrupt recursive read in interrupt context can be considered
-	 * to be the same as a recursive read from checking perspective.
-	 */
-	if ((read == 3) && in_interrupt())
-		read = 2;
 	current->lockdep_recursion = 1;
 	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 	__lock_acquire(lock, subclass, trylock, read, check,
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 62af709b2083..872a15a2a637 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -267,46 +267,19 @@ GENERATE_TESTCASE(AA_rsem)
 #undef E
 
 /*
- * Special-case for read-locking, they are not allowed to
- * recurse on the same lock class except under interrupt context:
+ * Special-case for read-locking, they are
+ * allowed to recurse on the same lock class:
  */
 static void rlock_AA1(void)
 {
 	RL(X1);
-	RL(X1); // this one should fail
+	RL(X1); // this one should NOT fail
 }
 
 static void rlock_AA1B(void)
 {
 	RL(X1);
-	RL(X2); // this one should fail
-}
-
-static void rlock_AHA1(void)
-{
-	RL(X1);
-	HARDIRQ_ENTER();
-	RL(X1);	// this one should NOT fail
-	HARDIRQ_EXIT();
-}
-
-static void rlock_AHA1B(void)
-{
-	RL(X1);
-	HARDIRQ_ENTER();
-	RL(X2);	// this one should NOT fail
-	HARDIRQ_EXIT();
-}
-
-static void rlock_ASAHA1(void)
-{
-	RL(X1);
-	SOFTIRQ_ENTER();
-	RL(X1);	// this one should NOT fail
-	HARDIRQ_ENTER();
-	RL(X1);	// this one should NOT fail
-	HARDIRQ_EXIT();
-	SOFTIRQ_EXIT();
+	RL(X2); // this one should NOT fail
 }
 
 static void rsem_AA1(void)
@@ -1096,7 +1069,7 @@ static inline void print_testname(const char *testname)
 	print_testname(desc);					\
 	dotest(name##_spin, FAILURE, LOCKTYPE_SPIN);		\
 	dotest(name##_wlock, FAILURE, LOCKTYPE_RWLOCK);		\
-	dotest(name##_rlock, FAILURE, LOCKTYPE_RWLOCK);		\
+	dotest(name##_rlock, SUCCESS, LOCKTYPE_RWLOCK);		\
 	dotest(name##_mutex, FAILURE, LOCKTYPE_MUTEX);		\
 	dotest(name##_wsem, FAILURE, LOCKTYPE_RWSEM);		\
 	dotest(name##_rsem, FAILURE, LOCKTYPE_RWSEM);		\
@@ -1857,14 +1830,14 @@ void locking_selftest(void)
 	printk("  --------------------------------------------------------------------------\n");
 	print_testname("recursive read-lock");
 	printk("             |");
-	dotest(rlock_AA1, FAILURE, LOCKTYPE_RWLOCK);
+	dotest(rlock_AA1, SUCCESS, LOCKTYPE_RWLOCK);
 	printk("             |");
 	dotest(rsem_AA1, FAILURE, LOCKTYPE_RWSEM);
 	printk("\n");
 
 	print_testname("recursive read-lock #2");
 	printk("             |");
-	dotest(rlock_AA1B, FAILURE, LOCKTYPE_RWLOCK);
+	dotest(rlock_AA1B, SUCCESS, LOCKTYPE_RWLOCK);
 	printk("             |");
 	dotest(rsem_AA1B, FAILURE, LOCKTYPE_RWSEM);
 	printk("\n");
@@ -1883,21 +1856,6 @@ void locking_selftest(void)
 	dotest(rsem_AA3, FAILURE, LOCKTYPE_RWSEM);
 	printk("\n");
 
-	print_testname("recursive rlock with interrupt");
-	printk("             |");
-	dotest(rlock_AHA1, SUCCESS, LOCKTYPE_RWLOCK);
-	printk("\n");
-
-	print_testname("recursive rlock with interrupt #2");
-	printk("             |");
-	dotest(rlock_AHA1B, SUCCESS, LOCKTYPE_RWLOCK);
-	printk("\n");
-
-	print_testname("recursive rlock with interrupt #3");
-	printk("             |");
-	dotest(rlock_ASAHA1, SUCCESS, LOCKTYPE_RWLOCK);
-	printk("\n");
-
 	printk("  --------------------------------------------------------------------------\n");
 
 	/*
-- 
cgit v1.2.3


From bca9b6855888d978d6e5399b0a8a8ed9a11e9236 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Wed, 17 Sep 2014 06:12:35 +0200
Subject: xen: sync some headers with xen tree

To be able to use an initially unmapped initrd with xen the following
header files must be synced to a newer version from the xen tree:

include/xen/interface/elfnote.h
include/xen/interface/xen.h

As the KEXEC and DUMPCORE related ELFNOTES are not relevant for the
kernel they are omitted from elfnote.h.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 include/xen/interface/elfnote.h |  48 ++++++-
 include/xen/interface/xen.h     | 272 ++++++++++++++++++++++++++++++++++++----
 2 files changed, 294 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h
index 6f4eae328ca7..f90b03454659 100644
--- a/include/xen/interface/elfnote.h
+++ b/include/xen/interface/elfnote.h
@@ -3,6 +3,24 @@
  *
  * Definitions used for the Xen ELF notes.
  *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
  * Copyright (c) 2006, Ian Campbell, XenSource Ltd.
  */
 
@@ -18,12 +36,13 @@
  *
  * LEGACY indicated the fields in the legacy __xen_guest string which
  * this a note type replaces.
+ *
+ * String values (for non-legacy) are NULL terminated ASCII, also known
+ * as ASCIZ type.
  */
 
 /*
  * NAME=VALUE pair (string).
- *
- * LEGACY: FEATURES and PAE
  */
 #define XEN_ELFNOTE_INFO           0
 
@@ -137,9 +156,29 @@
 
 /*
  * Whether or not the guest supports cooperative suspend cancellation.
+ * This is a numeric value.
+ *
+ * Default is 0
  */
 #define XEN_ELFNOTE_SUSPEND_CANCEL 14
 
+/*
+ * The (non-default) location the initial phys-to-machine map should be
+ * placed at by the hypervisor (Dom0) or the tools (DomU).
+ * The kernel must be prepared for this mapping to be established using
+ * large pages, despite such otherwise not being available to guests.
+ * The kernel must also be able to handle the page table pages used for
+ * this mapping not being accessible through the initial mapping.
+ * (Only x86-64 supports this at present.)
+ */
+#define XEN_ELFNOTE_INIT_P2M      15
+
+/*
+ * Whether or not the guest can deal with being passed an initrd not
+ * mapped through its initial page tables.
+ */
+#define XEN_ELFNOTE_MOD_START_PFN 16
+
 /*
  * The features supported by this kernel (numeric).
  *
@@ -153,6 +192,11 @@
  */
 #define XEN_ELFNOTE_SUPPORTED_FEATURES 17
 
+/*
+ * The number of the highest elfnote defined.
+ */
+#define XEN_ELFNOTE_MAX XEN_ELFNOTE_SUPPORTED_FEATURES
+
 #endif /* __XEN_PUBLIC_ELFNOTE_H__ */
 
 /*
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index de082130ba4b..f68719f405af 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -3,6 +3,24 @@
  *
  * Guest OS interface to Xen.
  *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
  * Copyright (c) 2004, K A Fraser
  */
 
@@ -73,13 +91,23 @@
  * VIRTUAL INTERRUPTS
  *
  * Virtual interrupts that a guest OS may receive from Xen.
+ * In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a
+ * global VIRQ. The former can be bound once per VCPU and cannot be re-bound.
+ * The latter can be allocated only once per guest: they must initially be
+ * allocated to VCPU0 but can subsequently be re-bound.
  */
-#define VIRQ_TIMER      0  /* Timebase update, and/or requested timeout.  */
-#define VIRQ_DEBUG      1  /* Request guest to dump debug info.           */
-#define VIRQ_CONSOLE    2  /* (DOM0) Bytes received on emergency console. */
-#define VIRQ_DOM_EXC    3  /* (DOM0) Exceptional event for some domain.   */
-#define VIRQ_DEBUGGER   6  /* (DOM0) A domain has paused for debugging.   */
-#define VIRQ_PCPU_STATE 9  /* (DOM0) PCPU state changed                   */
+#define VIRQ_TIMER      0  /* V. Timebase update, and/or requested timeout.  */
+#define VIRQ_DEBUG      1  /* V. Request guest to dump debug info.           */
+#define VIRQ_CONSOLE    2  /* G. (DOM0) Bytes received on emergency console. */
+#define VIRQ_DOM_EXC    3  /* G. (DOM0) Exceptional event for some domain.   */
+#define VIRQ_TBUF       4  /* G. (DOM0) Trace buffer has records available.  */
+#define VIRQ_DEBUGGER   6  /* G. (DOM0) A domain has paused for debugging.   */
+#define VIRQ_XENOPROF   7  /* V. XenOprofile interrupt: new sample available */
+#define VIRQ_CON_RING   8  /* G. (DOM0) Bytes received on console            */
+#define VIRQ_PCPU_STATE 9  /* G. (DOM0) PCPU state changed                   */
+#define VIRQ_MEM_EVENT  10 /* G. (DOM0) A memory event has occured           */
+#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient                     */
+#define VIRQ_ENOMEM     12 /* G. (DOM0) Low on heap memory       */
 
 /* Architecture-specific VIRQ definitions. */
 #define VIRQ_ARCH_0    16
@@ -92,24 +120,68 @@
 #define VIRQ_ARCH_7    23
 
 #define NR_VIRQS       24
+
 /*
- * MMU-UPDATE REQUESTS
- *
- * HYPERVISOR_mmu_update() accepts a list of (ptr, val) pairs.
- * A foreigndom (FD) can be specified (or DOMID_SELF for none).
- * Where the FD has some effect, it is described below.
- * ptr[1:0] specifies the appropriate MMU_* command.
+ * enum neg_errnoval HYPERVISOR_mmu_update(const struct mmu_update reqs[],
+ *                                         unsigned count, unsigned *done_out,
+ *                                         unsigned foreigndom)
+ * @reqs is an array of mmu_update_t structures ((ptr, val) pairs).
+ * @count is the length of the above array.
+ * @pdone is an output parameter indicating number of completed operations
+ * @foreigndom[15:0]: FD, the expected owner of data pages referenced in this
+ *                    hypercall invocation. Can be DOMID_SELF.
+ * @foreigndom[31:16]: PFD, the expected owner of pagetable pages referenced
+ *                     in this hypercall invocation. The value of this field
+ *                     (x) encodes the PFD as follows:
+ *                     x == 0 => PFD == DOMID_SELF
+ *                     x != 0 => PFD == x - 1
  *
+ * Sub-commands: ptr[1:0] specifies the appropriate MMU_* command.
+ * -------------
  * ptr[1:0] == MMU_NORMAL_PT_UPDATE:
- * Updates an entry in a page table. If updating an L1 table, and the new
- * table entry is valid/present, the mapped frame must belong to the FD, if
- * an FD has been specified. If attempting to map an I/O page then the
- * caller assumes the privilege of the FD.
+ * Updates an entry in a page table belonging to PFD. If updating an L1 table,
+ * and the new table entry is valid/present, the mapped frame must belong to
+ * FD. If attempting to map an I/O page then the caller assumes the privilege
+ * of the FD.
  * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller.
  * FD == DOMID_XEN: Map restricted areas of Xen's heap space.
  * ptr[:2]  -- Machine address of the page-table entry to modify.
  * val      -- Value to write.
  *
+ * There also certain implicit requirements when using this hypercall. The
+ * pages that make up a pagetable must be mapped read-only in the guest.
+ * This prevents uncontrolled guest updates to the pagetable. Xen strictly
+ * enforces this, and will disallow any pagetable update which will end up
+ * mapping pagetable page RW, and will disallow using any writable page as a
+ * pagetable. In practice it means that when constructing a page table for a
+ * process, thread, etc, we MUST be very dilligient in following these rules:
+ *  1). Start with top-level page (PGD or in Xen language: L4). Fill out
+ *      the entries.
+ *  2). Keep on going, filling out the upper (PUD or L3), and middle (PMD
+ *      or L2).
+ *  3). Start filling out the PTE table (L1) with the PTE entries. Once
+ *      done, make sure to set each of those entries to RO (so writeable bit
+ *      is unset). Once that has been completed, set the PMD (L2) for this
+ *      PTE table as RO.
+ *  4). When completed with all of the PMD (L2) entries, and all of them have
+ *      been set to RO, make sure to set RO the PUD (L3). Do the same
+ *      operation on PGD (L4) pagetable entries that have a PUD (L3) entry.
+ *  5). Now before you can use those pages (so setting the cr3), you MUST also
+ *      pin them so that the hypervisor can verify the entries. This is done
+ *      via the HYPERVISOR_mmuext_op(MMUEXT_PIN_L4_TABLE, guest physical frame
+ *      number of the PGD (L4)). And this point the HYPERVISOR_mmuext_op(
+ *      MMUEXT_NEW_BASEPTR, guest physical frame number of the PGD (L4)) can be
+ *      issued.
+ * For 32-bit guests, the L4 is not used (as there is less pagetables), so
+ * instead use L3.
+ * At this point the pagetables can be modified using the MMU_NORMAL_PT_UPDATE
+ * hypercall. Also if so desired the OS can also try to write to the PTE
+ * and be trapped by the hypervisor (as the PTE entry is RO).
+ *
+ * To deallocate the pages, the operations are the reverse of the steps
+ * mentioned above. The argument is MMUEXT_UNPIN_TABLE for all levels and the
+ * pagetable MUST not be in use (meaning that the cr3 is not set to it).
+ *
  * ptr[1:0] == MMU_MACHPHYS_UPDATE:
  * Updates an entry in the machine->pseudo-physical mapping table.
  * ptr[:2]  -- Machine address within the frame whose mapping to modify.
@@ -119,6 +191,72 @@
  * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD:
  * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed
  * with those in @val.
+ *
+ * @val is usually the machine frame number along with some attributes.
+ * The attributes by default follow the architecture defined bits. Meaning that
+ * if this is a X86_64 machine and four page table layout is used, the layout
+ * of val is:
+ *  - 63 if set means No execute (NX)
+ *  - 46-13 the machine frame number
+ *  - 12 available for guest
+ *  - 11 available for guest
+ *  - 10 available for guest
+ *  - 9 available for guest
+ *  - 8 global
+ *  - 7 PAT (PSE is disabled, must use hypercall to make 4MB or 2MB pages)
+ *  - 6 dirty
+ *  - 5 accessed
+ *  - 4 page cached disabled
+ *  - 3 page write through
+ *  - 2 userspace accessible
+ *  - 1 writeable
+ *  - 0 present
+ *
+ *  The one bits that does not fit with the default layout is the PAGE_PSE
+ *  also called PAGE_PAT). The MMUEXT_[UN]MARK_SUPER arguments to the
+ *  HYPERVISOR_mmuext_op serve as mechanism to set a pagetable to be 4MB
+ *  (or 2MB) instead of using the PAGE_PSE bit.
+ *
+ *  The reason that the PAGE_PSE (bit 7) is not being utilized is due to Xen
+ *  using it as the Page Attribute Table (PAT) bit - for details on it please
+ *  refer to Intel SDM 10.12. The PAT allows to set the caching attributes of
+ *  pages instead of using MTRRs.
+ *
+ *  The PAT MSR is as follows (it is a 64-bit value, each entry is 8 bits):
+ *                    PAT4                 PAT0
+ *  +-----+-----+----+----+----+-----+----+----+
+ *  | UC  | UC- | WC | WB | UC | UC- | WC | WB |  <= Linux
+ *  +-----+-----+----+----+----+-----+----+----+
+ *  | UC  | UC- | WT | WB | UC | UC- | WT | WB |  <= BIOS (default when machine boots)
+ *  +-----+-----+----+----+----+-----+----+----+
+ *  | rsv | rsv | WP | WC | UC | UC- | WT | WB |  <= Xen
+ *  +-----+-----+----+----+----+-----+----+----+
+ *
+ *  The lookup of this index table translates to looking up
+ *  Bit 7, Bit 4, and Bit 3 of val entry:
+ *
+ *  PAT/PSE (bit 7) ... PCD (bit 4) .. PWT (bit 3).
+ *
+ *  If all bits are off, then we are using PAT0. If bit 3 turned on,
+ *  then we are using PAT1, if bit 3 and bit 4, then PAT2..
+ *
+ *  As you can see, the Linux PAT1 translates to PAT4 under Xen. Which means
+ *  that if a guest that follows Linux's PAT setup and would like to set Write
+ *  Combined on pages it MUST use PAT4 entry. Meaning that Bit 7 (PAGE_PAT) is
+ *  set. For example, under Linux it only uses PAT0, PAT1, and PAT2 for the
+ *  caching as:
+ *
+ *   WB = none (so PAT0)
+ *   WC = PWT (bit 3 on)
+ *   UC = PWT | PCD (bit 3 and 4 are on).
+ *
+ * To make it work with Xen, it needs to translate the WC bit as so:
+ *
+ *  PWT (so bit 3 on) --> PAT (so bit 7 is on) and clear bit 3
+ *
+ * And to translate back it would:
+ *
+ * PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7.
  */
 #define MMU_NORMAL_PT_UPDATE      0 /* checked '*ptr = val'. ptr is MA.       */
 #define MMU_MACHPHYS_UPDATE       1 /* ptr = MA of frame to modify entry for  */
@@ -127,7 +265,12 @@
 /*
  * MMU EXTENDED OPERATIONS
  *
- * HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures.
+ * enum neg_errnoval HYPERVISOR_mmuext_op(mmuext_op_t uops[],
+ *                                        unsigned int count,
+ *                                        unsigned int *pdone,
+ *                                        unsigned int foreigndom)
+ */
+/* HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures.
  * A foreigndom (FD) can be specified (or DOMID_SELF for none).
  * Where the FD has some effect, it is described below.
  *
@@ -164,9 +307,23 @@
  * cmd: MMUEXT_FLUSH_CACHE
  * No additional arguments. Writes back and flushes cache contents.
  *
+ * cmd: MMUEXT_FLUSH_CACHE_GLOBAL
+ * No additional arguments. Writes back and flushes cache contents
+ * on all CPUs in the system.
+ *
  * cmd: MMUEXT_SET_LDT
  * linear_addr: Linear address of LDT base (NB. must be page-aligned).
  * nr_ents: Number of entries in LDT.
+ *
+ * cmd: MMUEXT_CLEAR_PAGE
+ * mfn: Machine frame number to be cleared.
+ *
+ * cmd: MMUEXT_COPY_PAGE
+ * mfn: Machine frame number of the destination page.
+ * src_mfn: Machine frame number of the source page.
+ *
+ * cmd: MMUEXT_[UN]MARK_SUPER
+ * mfn: Machine frame number of head of superpage to be [un]marked.
  */
 #define MMUEXT_PIN_L1_TABLE      0
 #define MMUEXT_PIN_L2_TABLE      1
@@ -183,12 +340,18 @@
 #define MMUEXT_FLUSH_CACHE      12
 #define MMUEXT_SET_LDT          13
 #define MMUEXT_NEW_USER_BASEPTR 15
+#define MMUEXT_CLEAR_PAGE       16
+#define MMUEXT_COPY_PAGE        17
+#define MMUEXT_FLUSH_CACHE_GLOBAL 18
+#define MMUEXT_MARK_SUPER       19
+#define MMUEXT_UNMARK_SUPER     20
 
 #ifndef __ASSEMBLY__
 struct mmuext_op {
 	unsigned int cmd;
 	union {
-		/* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR */
+		/* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR
+		 * CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */
 		xen_pfn_t mfn;
 		/* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */
 		unsigned long linear_addr;
@@ -198,6 +361,8 @@ struct mmuext_op {
 		unsigned int nr_ents;
 		/* TLB_FLUSH_MULTI, INVLPG_MULTI */
 		void *vcpumask;
+		/* COPY_PAGE */
+		xen_pfn_t src_mfn;
 	} arg2;
 };
 DEFINE_GUEST_HANDLE_STRUCT(mmuext_op);
@@ -225,10 +390,23 @@ DEFINE_GUEST_HANDLE_STRUCT(mmuext_op);
  */
 #define VMASST_CMD_enable                0
 #define VMASST_CMD_disable               1
+
+/* x86/32 guests: simulate full 4GB segment limits. */
 #define VMASST_TYPE_4gb_segments         0
+
+/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */
 #define VMASST_TYPE_4gb_segments_notify  1
+
+/*
+ * x86 guests: support writes to bottom-level PTEs.
+ * NB1. Page-directory entries cannot be written.
+ * NB2. Guest must continue to remove all writable mappings of PTEs.
+ */
 #define VMASST_TYPE_writable_pagetables  2
+
+/* x86/PAE guests: support PDPTs above 4GB. */
 #define VMASST_TYPE_pae_extended_cr3     3
+
 #define MAX_VMASST_TYPE 3
 
 #ifndef __ASSEMBLY__
@@ -260,6 +438,15 @@ typedef uint16_t domid_t;
  */
 #define DOMID_XEN  (0x7FF2U)
 
+/* DOMID_COW is used as the owner of sharable pages */
+#define DOMID_COW  (0x7FF3U)
+
+/* DOMID_INVALID is used to identify pages with unknown owner. */
+#define DOMID_INVALID (0x7FF4U)
+
+/* Idle domain. */
+#define DOMID_IDLE (0x7FFFU)
+
 /*
  * Send an array of these to HYPERVISOR_mmu_update().
  * NB. The fields are natural pointer/address size for this architecture.
@@ -272,7 +459,9 @@ DEFINE_GUEST_HANDLE_STRUCT(mmu_update);
 
 /*
  * Send an array of these to HYPERVISOR_multicall().
- * NB. The fields are natural register size for this architecture.
+ * NB. The fields are logically the natural register size for this
+ * architecture. In cases where xen_ulong_t is larger than this then
+ * any unused bits in the upper portion must be zero.
  */
 struct multicall_entry {
     xen_ulong_t op;
@@ -442,8 +631,48 @@ struct start_info {
 	unsigned long mod_start;    /* VIRTUAL address of pre-loaded module.  */
 	unsigned long mod_len;      /* Size (bytes) of pre-loaded module.     */
 	int8_t cmd_line[MAX_GUEST_CMDLINE];
+	/* The pfn range here covers both page table and p->m table frames.   */
+	unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table.    */
+	unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table.  */
 };
 
+/* These flags are passed in the 'flags' field of start_info_t. */
+#define SIF_PRIVILEGED    (1<<0)  /* Is the domain privileged? */
+#define SIF_INITDOMAIN    (1<<1)  /* Is this the initial control domain? */
+#define SIF_MULTIBOOT_MOD (1<<2)  /* Is mod_start a multiboot module? */
+#define SIF_MOD_START_PFN (1<<3)  /* Is mod_start a PFN? */
+#define SIF_PM_MASK       (0xFF<<8) /* reserve 1 byte for xen-pm options */
+
+/*
+ * A multiboot module is a package containing modules very similar to a
+ * multiboot module array. The only differences are:
+ * - the array of module descriptors is by convention simply at the beginning
+ *   of the multiboot module,
+ * - addresses in the module descriptors are based on the beginning of the
+ *   multiboot module,
+ * - the number of modules is determined by a termination descriptor that has
+ *   mod_start == 0.
+ *
+ * This permits to both build it statically and reference it in a configuration
+ * file, and let the PV guest easily rebase the addresses to virtual addresses
+ * and at the same time count the number of modules.
+ */
+struct xen_multiboot_mod_list {
+	/* Address of first byte of the module */
+	uint32_t mod_start;
+	/* Address of last byte of the module (inclusive) */
+	uint32_t mod_end;
+	/* Address of zero-terminated command line */
+	uint32_t cmdline;
+	/* Unused, must be zero */
+	uint32_t pad;
+};
+/*
+ * The console structure in start_info.console.dom0
+ *
+ * This structure includes a variety of information required to
+ * have a working VGA/VESA console.
+ */
 struct dom0_vga_console_info {
 	uint8_t video_type;
 #define XEN_VGATYPE_TEXT_MODE_3 0x03
@@ -484,11 +713,6 @@ struct dom0_vga_console_info {
 	} u;
 };
 
-/* These flags are passed in the 'flags' field of start_info_t. */
-#define SIF_PRIVILEGED    (1<<0)  /* Is the domain privileged? */
-#define SIF_INITDOMAIN    (1<<1)  /* Is this the initial control domain? */
-#define SIF_PM_MASK       (0xFF<<8) /* reserve 1 byte for xen-pm options */
-
 typedef uint64_t cpumap_t;
 
 typedef uint8_t xen_domain_handle_t[16];
-- 
cgit v1.2.3


From 615413979487a1e25a3b76abbaa316280ca19d26 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 24 Sep 2014 10:27:27 +0300
Subject: mmc: sdhci: Add quirk for always getting TC with stop cmd

Add a quirk for a host controller that always sets
a Transfer Complete interrupt status for the stop
command even when a busy response is not indicated.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 8 ++++++--
 include/linux/mmc/sdhci.h | 2 ++
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index cbd433712756..a932f70bcc51 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2225,7 +2225,7 @@ static void sdhci_tuning_timer(unsigned long data)
  *                                                                           *
 \*****************************************************************************/
 
-static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask)
+static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
 {
 	BUG_ON(intmask == 0);
 
@@ -2272,6 +2272,9 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask)
 
 		/* The controller does not support the end-of-busy IRQ,
 		 * fall through and take the SDHCI_INT_RESPONSE */
+	} else if ((host->quirks2 & SDHCI_QUIRK2_STOP_WITH_TC) &&
+		   host->cmd->opcode == MMC_STOP_TRANSMISSION && !host->data) {
+		*mask &= ~SDHCI_INT_DATA_END;
 	}
 
 	if (intmask & SDHCI_INT_RESPONSE)
@@ -2481,7 +2484,8 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 		}
 
 		if (intmask & SDHCI_INT_CMD_MASK)
-			sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK);
+			sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK,
+				      &intmask);
 
 		if (intmask & SDHCI_INT_DATA_MASK)
 			sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK);
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 0aa85ca0c788..dba793e3a331 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -98,6 +98,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK2_BROKEN_HS200			(1<<6)
 /* Controller does not support DDR50 */
 #define SDHCI_QUIRK2_BROKEN_DDR50			(1<<7)
+/* Stop command (CMD12) can set Transfer Complete when not using MMC_RSP_BUSY */
+#define SDHCI_QUIRK2_STOP_WITH_TC			(1<<8)
 
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
-- 
cgit v1.2.3


From f39cb1797ec1094b196d3dab44a7ca6060813d38 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 2 Oct 2014 21:12:34 +0200
Subject: PM / Domains: Rename cpu_data to cpuidle_data

The "cpu_data" are defined for some archs and thus conflicting with the
"cpu_data" member in the struct gpd_cpu_data. This causes a compiler
error for those archs.

Let's fix it by rename the member to cpuidle_data. In this context it
also seems appropriate to rename the struct to gpd_cpuidle_data to
better reflect its use.

Fixes: f48c767ce895 (PM / Domains: Move dev_pm_domain_attach|detach() to pm_domain.h)
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 54 ++++++++++++++++++++++-----------------------
 include/linux/pm_domain.h   |  4 ++--
 2 files changed, 29 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 18cc68d058d6..40bc2f4072cc 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -142,13 +142,13 @@ static void genpd_recalc_cpu_exit_latency(struct generic_pm_domain *genpd)
 {
 	s64 usecs64;
 
-	if (!genpd->cpu_data)
+	if (!genpd->cpuidle_data)
 		return;
 
 	usecs64 = genpd->power_on_latency_ns;
 	do_div(usecs64, NSEC_PER_USEC);
-	usecs64 += genpd->cpu_data->saved_exit_latency;
-	genpd->cpu_data->idle_state->exit_latency = usecs64;
+	usecs64 += genpd->cpuidle_data->saved_exit_latency;
+	genpd->cpuidle_data->idle_state->exit_latency = usecs64;
 }
 
 /**
@@ -188,9 +188,9 @@ static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
 		return 0;
 	}
 
-	if (genpd->cpu_data) {
+	if (genpd->cpuidle_data) {
 		cpuidle_pause_and_lock();
-		genpd->cpu_data->idle_state->disabled = true;
+		genpd->cpuidle_data->idle_state->disabled = true;
 		cpuidle_resume_and_unlock();
 		goto out;
 	}
@@ -513,17 +513,17 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		}
 	}
 
-	if (genpd->cpu_data) {
+	if (genpd->cpuidle_data) {
 		/*
-		 * If cpu_data is set, cpuidle should turn the domain off when
-		 * the CPU in it is idle.  In that case we don't decrement the
-		 * subdomain counts of the master domains, so that power is not
-		 * removed from the current domain prematurely as a result of
-		 * cutting off the masters' power.
+		 * If cpuidle_data is set, cpuidle should turn the domain off
+		 * when the CPU in it is idle.  In that case we don't decrement
+		 * the subdomain counts of the master domains, so that power is
+		 * not removed from the current domain prematurely as a result
+		 * of cutting off the masters' power.
 		 */
 		genpd->status = GPD_STATE_POWER_OFF;
 		cpuidle_pause_and_lock();
-		genpd->cpu_data->idle_state->disabled = false;
+		genpd->cpuidle_data->idle_state->disabled = false;
 		cpuidle_resume_and_unlock();
 		goto out;
 	}
@@ -1698,7 +1698,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 {
 	struct cpuidle_driver *cpuidle_drv;
-	struct gpd_cpu_data *cpu_data;
+	struct gpd_cpuidle_data *cpuidle_data;
 	struct cpuidle_state *idle_state;
 	int ret = 0;
 
@@ -1707,12 +1707,12 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 
 	genpd_acquire_lock(genpd);
 
-	if (genpd->cpu_data) {
+	if (genpd->cpuidle_data) {
 		ret = -EEXIST;
 		goto out;
 	}
-	cpu_data = kzalloc(sizeof(*cpu_data), GFP_KERNEL);
-	if (!cpu_data) {
+	cpuidle_data = kzalloc(sizeof(*cpuidle_data), GFP_KERNEL);
+	if (!cpuidle_data) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1730,9 +1730,9 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 		ret = -EAGAIN;
 		goto err;
 	}
-	cpu_data->idle_state = idle_state;
-	cpu_data->saved_exit_latency = idle_state->exit_latency;
-	genpd->cpu_data = cpu_data;
+	cpuidle_data->idle_state = idle_state;
+	cpuidle_data->saved_exit_latency = idle_state->exit_latency;
+	genpd->cpuidle_data = cpuidle_data;
 	genpd_recalc_cpu_exit_latency(genpd);
 
  out:
@@ -1743,7 +1743,7 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 	cpuidle_driver_unref();
 
  err_drv:
-	kfree(cpu_data);
+	kfree(cpuidle_data);
 	goto out;
 }
 
@@ -1766,7 +1766,7 @@ int pm_genpd_name_attach_cpuidle(const char *name, int state)
  */
 int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
 {
-	struct gpd_cpu_data *cpu_data;
+	struct gpd_cpuidle_data *cpuidle_data;
 	struct cpuidle_state *idle_state;
 	int ret = 0;
 
@@ -1775,20 +1775,20 @@ int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
 
 	genpd_acquire_lock(genpd);
 
-	cpu_data = genpd->cpu_data;
-	if (!cpu_data) {
+	cpuidle_data = genpd->cpuidle_data;
+	if (!cpuidle_data) {
 		ret = -ENODEV;
 		goto out;
 	}
-	idle_state = cpu_data->idle_state;
+	idle_state = cpuidle_data->idle_state;
 	if (!idle_state->disabled) {
 		ret = -EAGAIN;
 		goto out;
 	}
-	idle_state->exit_latency = cpu_data->saved_exit_latency;
+	idle_state->exit_latency = cpuidle_data->saved_exit_latency;
 	cpuidle_driver_unref();
-	genpd->cpu_data = NULL;
-	kfree(cpu_data);
+	genpd->cpuidle_data = NULL;
+	kfree(cpuidle_data);
 
  out:
 	genpd_release_lock(genpd);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 900474317afc..73e938b7e937 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -38,7 +38,7 @@ struct gpd_dev_ops {
 	bool (*active_wakeup)(struct device *dev);
 };
 
-struct gpd_cpu_data {
+struct gpd_cpuidle_data {
 	unsigned int saved_exit_latency;
 	struct cpuidle_state *idle_state;
 };
@@ -71,7 +71,7 @@ struct generic_pm_domain {
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
 	bool max_off_time_changed;
 	bool cached_power_down_ok;
-	struct gpd_cpu_data *cpu_data;
+	struct gpd_cpuidle_data *cpuidle_data;
 	void (*attach_dev)(struct device *dev);
 	void (*detach_dev)(struct device *dev);
 };
-- 
cgit v1.2.3


From 5772e9a3463b264cee5a4e73ef586ad482d7ba48 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Wed, 1 Oct 2014 22:35:59 +0200
Subject: qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE

Based on DaveM's recent API work on dev_hard_start_xmit(), that allows
sending/processing an entire skb list.

This patch implements qdisc bulk dequeue, by allowing multiple packets
to be dequeued in dequeue_skb().

The optimization principle for this is two fold, (1) to amortize
locking cost and (2) avoid expensive tailptr update for notifying HW.
 (1) Several packets are dequeued while holding the qdisc root_lock,
amortizing locking cost over several packet.  The dequeued SKB list is
processed under the TXQ lock in dev_hard_start_xmit(), thus also
amortizing the cost of the TXQ lock.
 (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more
API to delay HW tailptr update, which also reduces the cost per
packet.

One restriction of the new API is that every SKB must belong to the
same TXQ.  This patch takes the easy way out, by restricting bulk
dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the
qdisc only have attached a single TXQ.

Some detail about the flow; dev_hard_start_xmit() will process the skb
list, and transmit packets individually towards the driver (see
xmit_one()).  In case the driver stops midway in the list, the
remaining skb list is returned by dev_hard_start_xmit().  In
sch_direct_xmit() this returned list is requeued by dev_requeue_skb().

To avoid overshooting the HW limits, which results in requeuing, the
patch limits the amount of bytes dequeued, based on the drivers BQL
limits.  In-effect bulking will only happen for BQL enabled drivers.

Small amounts for extra HoL blocking (2x MTU/0.24ms) were
measured at 100Mbit/s, with bulking 8 packets, but the
oscillating nature of the measurement indicate something, like
sched latency might be causing this effect. More comparisons
show, that this oscillation goes away occationally. Thus, we
disregard this artifact completely and remove any "magic" bulking
limit.

For now, as a conservative approach, stop bulking when seeing TSO and
segmented GSO packets.  They already benefit from bulking on their own.
A followup patch add this, to allow easier bisect-ability for finding
regressions.

Jointed work with Hannes, Daniel and Florian.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 16 ++++++++++++++++
 net/sched/sch_generic.c   | 46 ++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 60 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f12669819d1a..d17ed6fb2f70 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -7,6 +7,7 @@
 #include <linux/pkt_sched.h>
 #include <linux/pkt_cls.h>
 #include <linux/percpu.h>
+#include <linux/dynamic_queue_limits.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 
@@ -119,6 +120,21 @@ static inline void qdisc_run_end(struct Qdisc *qdisc)
 	qdisc->__state &= ~__QDISC___STATE_RUNNING;
 }
 
+static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
+{
+	return qdisc->flags & TCQ_F_ONETXQUEUE;
+}
+
+static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
+{
+#ifdef CONFIG_BQL
+	/* Non-BQL migrated drivers will return 0, too. */
+	return dql_avail(&txq->dql);
+#else
+	return 0;
+#endif
+}
+
 static inline bool qdisc_is_throttled(const struct Qdisc *qdisc)
 {
 	return test_bit(__QDISC_STATE_THROTTLED, &qdisc->state) ? true : false;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7c8e5d73d433..c2e87e63b832 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -56,6 +56,41 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 	return 0;
 }
 
+static struct sk_buff *try_bulk_dequeue_skb(struct Qdisc *q,
+					    struct sk_buff *head_skb,
+					    int bytelimit)
+{
+	struct sk_buff *skb, *tail_skb = head_skb;
+
+	while (bytelimit > 0) {
+		/* For now, don't bulk dequeue GSO (or GSO segmented) pkts */
+		if (tail_skb->next || skb_is_gso(tail_skb))
+			break;
+
+		skb = q->dequeue(q);
+		if (!skb)
+			break;
+
+		bytelimit -= skb->len; /* covers GSO len */
+		skb = validate_xmit_skb(skb, qdisc_dev(q));
+		if (!skb)
+			break;
+
+		/* "skb" can be a skb list after validate call above
+		 * (GSO segmented), but it is okay to append it to
+		 * current tail_skb->next, because next round will exit
+		 * in-case "tail_skb->next" is a skb list.
+		 */
+		tail_skb->next = skb;
+		tail_skb = skb;
+	}
+
+	return head_skb;
+}
+
+/* Note that dequeue_skb can possibly return a SKB list (via skb->next).
+ * A requeued skb (via q->gso_skb) can also be a SKB list.
+ */
 static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 {
 	struct sk_buff *skb = q->gso_skb;
@@ -70,10 +105,17 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 		} else
 			skb = NULL;
 	} else {
-		if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq)) {
+		if (!(q->flags & TCQ_F_ONETXQUEUE) ||
+		    !netif_xmit_frozen_or_stopped(txq)) {
+			int bytelimit = qdisc_avail_bulklimit(txq);
+
 			skb = q->dequeue(q);
-			if (skb)
+			if (skb) {
+				bytelimit -= skb->len;
 				skb = validate_xmit_skb(skb, qdisc_dev(q));
+			}
+			if (skb && qdisc_may_bulk(q))
+				skb = try_bulk_dequeue_skb(q, skb, bytelimit);
 		}
 	}
 
-- 
cgit v1.2.3


From d8f429e1669b9709f5b669aac9d734dbe0640891 Mon Sep 17 00:00:00 2001
From: Junichi Nomura <j-nomura@ce.jp.nec.com>
Date: Fri, 3 Oct 2014 17:27:12 -0400
Subject: block: add bioset_create_nobvec()

Users of bio_clone_fast() do not want bios with their own bvecs.
Allocating a bvec mempool as part of the bioset intended for such users
is a waste of memory.

bioset_create_nobvec() creates a bioset that doesn't have the bvec
mempool.

Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/bio.c         | 61 ++++++++++++++++++++++++++++++++++++++---------------
 include/linux/bio.h |  1 +
 2 files changed, 45 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/block/bio.c b/block/bio.c
index 3e6331d25d90..3e6e1986a5b2 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -428,6 +428,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		front_pad = 0;
 		inline_vecs = nr_iovecs;
 	} else {
+		/* should not use nobvec bioset for nr_iovecs > 0 */
+		if (WARN_ON_ONCE(!bs->bvec_pool && nr_iovecs > 0))
+			return NULL;
 		/*
 		 * generic_make_request() converts recursion to iteration; this
 		 * means if we're running beneath it, any bios we allocate and
@@ -1900,20 +1903,9 @@ void bioset_free(struct bio_set *bs)
 }
 EXPORT_SYMBOL(bioset_free);
 
-/**
- * bioset_create  - Create a bio_set
- * @pool_size:	Number of bio and bio_vecs to cache in the mempool
- * @front_pad:	Number of bytes to allocate in front of the returned bio
- *
- * Description:
- *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
- *    to ask for a number of bytes to be allocated in front of the bio.
- *    Front pad allocation is useful for embedding the bio inside
- *    another structure, to avoid allocating extra data to go with the bio.
- *    Note that the bio must be embedded at the END of that structure always,
- *    or things will break badly.
- */
-struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
+static struct bio_set *__bioset_create(unsigned int pool_size,
+				       unsigned int front_pad,
+				       bool create_bvec_pool)
 {
 	unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
 	struct bio_set *bs;
@@ -1938,9 +1930,11 @@ struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
 	if (!bs->bio_pool)
 		goto bad;
 
-	bs->bvec_pool = biovec_create_pool(pool_size);
-	if (!bs->bvec_pool)
-		goto bad;
+	if (create_bvec_pool) {
+		bs->bvec_pool = biovec_create_pool(pool_size);
+		if (!bs->bvec_pool)
+			goto bad;
+	}
 
 	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
 	if (!bs->rescue_workqueue)
@@ -1951,8 +1945,41 @@ bad:
 	bioset_free(bs);
 	return NULL;
 }
+
+/**
+ * bioset_create  - Create a bio_set
+ * @pool_size:	Number of bio and bio_vecs to cache in the mempool
+ * @front_pad:	Number of bytes to allocate in front of the returned bio
+ *
+ * Description:
+ *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
+ *    to ask for a number of bytes to be allocated in front of the bio.
+ *    Front pad allocation is useful for embedding the bio inside
+ *    another structure, to avoid allocating extra data to go with the bio.
+ *    Note that the bio must be embedded at the END of that structure always,
+ *    or things will break badly.
+ */
+struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
+{
+	return __bioset_create(pool_size, front_pad, true);
+}
 EXPORT_SYMBOL(bioset_create);
 
+/**
+ * bioset_create_nobvec  - Create a bio_set without bio_vec mempool
+ * @pool_size:	Number of bio to cache in the mempool
+ * @front_pad:	Number of bytes to allocate in front of the returned bio
+ *
+ * Description:
+ *    Same functionality as bioset_create() except that mempool is not
+ *    created for bio_vecs. Saving some memory for bio_clone_fast() users.
+ */
+struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_pad)
+{
+	return __bioset_create(pool_size, front_pad, false);
+}
+EXPORT_SYMBOL(bioset_create_nobvec);
+
 #ifdef CONFIG_BLK_CGROUP
 /**
  * bio_associate_current - associate a bio with %current
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ce6b75964b71..7347f486ceca 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -378,6 +378,7 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors,
 }
 
 extern struct bio_set *bioset_create(unsigned int, unsigned int);
+extern struct bio_set *bioset_create_nobvec(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
 extern mempool_t *biovec_create_pool(int pool_entries);
 
-- 
cgit v1.2.3


From 906d201530f2c52aeb4eee31895c71cdccf1e9a0 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 24 Sep 2014 11:17:56 -0700
Subject: dynamic_debug: change __dynamic_<foo>_dbg return types to void

The return value is not used by callers of these functions
so change the functions to return void.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/dynamic_debug.h | 12 +++++------
 lib/dynamic_debug.c           | 50 +++++++++++++++++--------------------------
 2 files changed, 26 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 2fe93b26b42f..4f1bbc68cd1b 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -42,7 +42,7 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 #if defined(CONFIG_DYNAMIC_DEBUG)
 extern int ddebug_remove_module(const char *mod_name);
 extern __printf(2, 3)
-int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...);
+void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...);
 
 extern int ddebug_dyndbg_module_param_cb(char *param, char *val,
 					const char *modname);
@@ -50,15 +50,15 @@ extern int ddebug_dyndbg_module_param_cb(char *param, char *val,
 struct device;
 
 extern __printf(3, 4)
-int __dynamic_dev_dbg(struct _ddebug *descriptor, const struct device *dev,
-		      const char *fmt, ...);
+void __dynamic_dev_dbg(struct _ddebug *descriptor, const struct device *dev,
+		       const char *fmt, ...);
 
 struct net_device;
 
 extern __printf(3, 4)
-int __dynamic_netdev_dbg(struct _ddebug *descriptor,
-			 const struct net_device *dev,
-			 const char *fmt, ...);
+void __dynamic_netdev_dbg(struct _ddebug *descriptor,
+			  const struct net_device *dev,
+			  const char *fmt, ...);
 
 #define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt)		\
 	static struct _ddebug  __aligned(8)			\
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index c9afbe2c445a..31fe79e31ab8 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -537,10 +537,9 @@ static char *dynamic_emit_prefix(const struct _ddebug *desc, char *buf)
 	return buf;
 }
 
-int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...)
+void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...)
 {
 	va_list args;
-	int res;
 	struct va_format vaf;
 	char buf[PREFIX_SIZE];
 
@@ -552,21 +551,17 @@ int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...)
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	res = printk(KERN_DEBUG "%s%pV",
-		     dynamic_emit_prefix(descriptor, buf), &vaf);
+	printk(KERN_DEBUG "%s%pV", dynamic_emit_prefix(descriptor, buf), &vaf);
 
 	va_end(args);
-
-	return res;
 }
 EXPORT_SYMBOL(__dynamic_pr_debug);
 
-int __dynamic_dev_dbg(struct _ddebug *descriptor,
+void __dynamic_dev_dbg(struct _ddebug *descriptor,
 		      const struct device *dev, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int res;
 
 	BUG_ON(!descriptor);
 	BUG_ON(!fmt);
@@ -577,30 +572,27 @@ int __dynamic_dev_dbg(struct _ddebug *descriptor,
 	vaf.va = &args;
 
 	if (!dev) {
-		res = printk(KERN_DEBUG "(NULL device *): %pV", &vaf);
+		printk(KERN_DEBUG "(NULL device *): %pV", &vaf);
 	} else {
 		char buf[PREFIX_SIZE];
 
-		res = dev_printk_emit(7, dev, "%s%s %s: %pV",
-				      dynamic_emit_prefix(descriptor, buf),
-				      dev_driver_string(dev), dev_name(dev),
-				      &vaf);
+		dev_printk_emit(7, dev, "%s%s %s: %pV",
+				dynamic_emit_prefix(descriptor, buf),
+				dev_driver_string(dev), dev_name(dev),
+				&vaf);
 	}
 
 	va_end(args);
-
-	return res;
 }
 EXPORT_SYMBOL(__dynamic_dev_dbg);
 
 #ifdef CONFIG_NET
 
-int __dynamic_netdev_dbg(struct _ddebug *descriptor,
-			 const struct net_device *dev, const char *fmt, ...)
+void __dynamic_netdev_dbg(struct _ddebug *descriptor,
+			  const struct net_device *dev, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int res;
 
 	BUG_ON(!descriptor);
 	BUG_ON(!fmt);
@@ -613,23 +605,21 @@ int __dynamic_netdev_dbg(struct _ddebug *descriptor,
 	if (dev && dev->dev.parent) {
 		char buf[PREFIX_SIZE];
 
-		res = dev_printk_emit(7, dev->dev.parent,
-				      "%s%s %s %s%s: %pV",
-				      dynamic_emit_prefix(descriptor, buf),
-				      dev_driver_string(dev->dev.parent),
-				      dev_name(dev->dev.parent),
-				      netdev_name(dev), netdev_reg_state(dev),
-				      &vaf);
+		dev_printk_emit(7, dev->dev.parent,
+				"%s%s %s %s%s: %pV",
+				dynamic_emit_prefix(descriptor, buf),
+				dev_driver_string(dev->dev.parent),
+				dev_name(dev->dev.parent),
+				netdev_name(dev), netdev_reg_state(dev),
+				&vaf);
 	} else if (dev) {
-		res = printk(KERN_DEBUG "%s%s: %pV", netdev_name(dev),
-			     netdev_reg_state(dev), &vaf);
+		printk(KERN_DEBUG "%s%s: %pV", netdev_name(dev),
+		       netdev_reg_state(dev), &vaf);
 	} else {
-		res = printk(KERN_DEBUG "(NULL net_device): %pV", &vaf);
+		printk(KERN_DEBUG "(NULL net_device): %pV", &vaf);
 	}
 
 	va_end(args);
-
-	return res;
 }
 EXPORT_SYMBOL(__dynamic_netdev_dbg);
 
-- 
cgit v1.2.3


From 55a93b3ea780908b7d1b3a8cf1976223a9268d78 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Oct 2014 15:31:07 -0700
Subject: qdisc: validate skb without holding lock

Validation of skb can be pretty expensive :

GSO segmentation and/or checksum computations.

We can do this without holding qdisc lock, so that other cpus
can queue additional packets.

Trick is that requeued packets were already validated, so we carry
a boolean so that sch_direct_xmit() can validate a fresh skb list,
or directly use an old one.

Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads
host.

Turning TSO on or off had no effect on throughput, only few more cpu
cycles. Lock contention on qdisc lock disappeared.

Same if disabling TX checksum offload.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 +-
 include/net/pkt_sched.h   |  2 +-
 net/core/dev.c            | 29 +++++++++++++++++++---
 net/sched/sch_generic.c   | 61 ++++++++++++++++++++++-------------------------
 4 files changed, 56 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9b7fbacb6296..910fb17ad148 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2821,7 +2821,7 @@ int dev_set_mac_address(struct net_device *, struct sockaddr *);
 int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_port_id *ppid);
-struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev);
+struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 				    struct netdev_queue *txq, int *ret);
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 8bbe626e9ece..e4b3c828c1c2 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -99,7 +99,7 @@ void qdisc_put_stab(struct qdisc_size_table *tab);
 void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc);
 int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 		    struct net_device *dev, struct netdev_queue *txq,
-		    spinlock_t *root_lock);
+		    spinlock_t *root_lock, bool validate);
 
 void __qdisc_run(struct Qdisc *q);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index e55c546717d4..1a90530f83ff 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2655,7 +2655,7 @@ struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t featur
 	return skb;
 }
 
-struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
+static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
 {
 	netdev_features_t features;
 
@@ -2720,6 +2720,30 @@ out_null:
 	return NULL;
 }
 
+struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev)
+{
+	struct sk_buff *next, *head = NULL, *tail;
+
+	while (skb) {
+		next = skb->next;
+		skb->next = NULL;
+		skb = validate_xmit_skb(skb, dev);
+		if (skb) {
+			struct sk_buff *end = skb;
+
+			while (end->next)
+				end = end->next;
+			if (!head)
+				head = skb;
+			else
+				tail->next = skb;
+			tail = end;
+		}
+		skb = next;
+	}
+	return head;
+}
+
 static void qdisc_pkt_len_init(struct sk_buff *skb)
 {
 	const struct skb_shared_info *shinfo = skb_shinfo(skb);
@@ -2786,8 +2810,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 		qdisc_bstats_update(q, skb);
 
-		skb = validate_xmit_skb(skb, dev);
-		if (skb && sch_direct_xmit(skb, q, dev, txq, root_lock)) {
+		if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) {
 			if (unlikely(contended)) {
 				spin_unlock(&q->busylock);
 				contended = false;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 797ebef73642..2b349a4de3c8 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -56,40 +56,34 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 	return 0;
 }
 
-static struct sk_buff *try_bulk_dequeue_skb(struct Qdisc *q,
-					    struct sk_buff *head_skb,
-					    int bytelimit)
+static void try_bulk_dequeue_skb(struct Qdisc *q,
+				 struct sk_buff *skb,
+				 const struct netdev_queue *txq)
 {
-	struct sk_buff *skb, *tail_skb = head_skb;
+	int bytelimit = qdisc_avail_bulklimit(txq) - skb->len;
 
 	while (bytelimit > 0) {
-		skb = q->dequeue(q);
-		if (!skb)
-			break;
+		struct sk_buff *nskb = q->dequeue(q);
 
-		bytelimit -= skb->len; /* covers GSO len */
-		skb = validate_xmit_skb(skb, qdisc_dev(q));
-		if (!skb)
+		if (!nskb)
 			break;
 
-		while (tail_skb->next) /* GSO list goto tail */
-			tail_skb = tail_skb->next;
-
-		tail_skb->next = skb;
-		tail_skb = skb;
+		bytelimit -= nskb->len; /* covers GSO len */
+		skb->next = nskb;
+		skb = nskb;
 	}
-
-	return head_skb;
+	skb->next = NULL;
 }
 
 /* Note that dequeue_skb can possibly return a SKB list (via skb->next).
  * A requeued skb (via q->gso_skb) can also be a SKB list.
  */
-static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
+static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate)
 {
 	struct sk_buff *skb = q->gso_skb;
 	const struct netdev_queue *txq = q->dev_queue;
 
+	*validate = true;
 	if (unlikely(skb)) {
 		/* check the reason of requeuing without tx lock first */
 		txq = skb_get_tx_queue(txq->dev, skb);
@@ -98,21 +92,16 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 			q->q.qlen--;
 		} else
 			skb = NULL;
+		/* skb in gso_skb were already validated */
+		*validate = false;
 	} else {
 		if (!(q->flags & TCQ_F_ONETXQUEUE) ||
 		    !netif_xmit_frozen_or_stopped(txq)) {
-			int bytelimit = qdisc_avail_bulklimit(txq);
-
 			skb = q->dequeue(q);
-			if (skb) {
-				bytelimit -= skb->len;
-				skb = validate_xmit_skb(skb, qdisc_dev(q));
-			}
 			if (skb && qdisc_may_bulk(q))
-				skb = try_bulk_dequeue_skb(q, skb, bytelimit);
+				try_bulk_dequeue_skb(q, skb, txq);
 		}
 	}
-
 	return skb;
 }
 
@@ -156,19 +145,24 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb,
  */
 int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 		    struct net_device *dev, struct netdev_queue *txq,
-		    spinlock_t *root_lock)
+		    spinlock_t *root_lock, bool validate)
 {
 	int ret = NETDEV_TX_BUSY;
 
 	/* And release qdisc */
 	spin_unlock(root_lock);
 
-	HARD_TX_LOCK(dev, txq, smp_processor_id());
-	if (!netif_xmit_frozen_or_stopped(txq))
-		skb = dev_hard_start_xmit(skb, dev, txq, &ret);
+	/* Note that we validate skb (GSO, checksum, ...) outside of locks */
+	if (validate)
+		skb = validate_xmit_skb_list(skb, dev);
 
-	HARD_TX_UNLOCK(dev, txq);
+	if (skb) {
+		HARD_TX_LOCK(dev, txq, smp_processor_id());
+		if (!netif_xmit_frozen_or_stopped(txq))
+			skb = dev_hard_start_xmit(skb, dev, txq, &ret);
 
+		HARD_TX_UNLOCK(dev, txq);
+	}
 	spin_lock(root_lock);
 
 	if (dev_xmit_complete(ret)) {
@@ -217,9 +211,10 @@ static inline int qdisc_restart(struct Qdisc *q)
 	struct net_device *dev;
 	spinlock_t *root_lock;
 	struct sk_buff *skb;
+	bool validate;
 
 	/* Dequeue packet */
-	skb = dequeue_skb(q);
+	skb = dequeue_skb(q, &validate);
 	if (unlikely(!skb))
 		return 0;
 
@@ -229,7 +224,7 @@ static inline int qdisc_restart(struct Qdisc *q)
 	dev = qdisc_dev(q);
 	txq = skb_get_tx_queue(dev, skb);
 
-	return sch_direct_xmit(skb, q, dev, txq, root_lock);
+	return sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
 }
 
 void __qdisc_run(struct Qdisc *q)
-- 
cgit v1.2.3


From c7a08ac7ee68b9af0d5af99c7b34b574cac4d144 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Thu, 2 Oct 2014 12:19:42 +0300
Subject: net/mlx5_core: Update device capabilities handling

Rearrange struct mlx5_caps so it has a "gen" field to represent the current
capabilities configured for the device. Max capabilities can also be queried
from the device. Also update capabilities struct to contain more fields as per
the latest revision if firmware specification.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx5/cq.c                |   8 +-
 drivers/infiniband/hw/mlx5/mad.c               |   2 +-
 drivers/infiniband/hw/mlx5/main.c              |  83 ++++++----
 drivers/infiniband/hw/mlx5/qp.c                |  72 +++++---
 drivers/infiniband/hw/mlx5/srq.c               |   6 +-
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c  |  24 ++-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fw.c   |  81 +--------
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 219 +++++++++++++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/uar.c  |   4 +-
 include/linux/mlx5/device.h                    |  24 ++-
 include/linux/mlx5/driver.h                    |  28 +++-
 12 files changed, 331 insertions(+), 222 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index e4056279166d..10cfce5119a9 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -752,7 +752,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
 		return ERR_PTR(-EINVAL);
 
 	entries = roundup_pow_of_two(entries + 1);
-	if (entries > dev->mdev->caps.max_cqes)
+	if (entries > dev->mdev->caps.gen.max_cqes)
 		return ERR_PTR(-EINVAL);
 
 	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
@@ -919,7 +919,7 @@ int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
 	int err;
 	u32 fsel;
 
-	if (!(dev->mdev->caps.flags & MLX5_DEV_CAP_FLAG_CQ_MODER))
+	if (!(dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_CQ_MODER))
 		return -ENOSYS;
 
 	in = kzalloc(sizeof(*in), GFP_KERNEL);
@@ -1074,7 +1074,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 	int uninitialized_var(cqe_size);
 	unsigned long flags;
 
-	if (!(dev->mdev->caps.flags & MLX5_DEV_CAP_FLAG_RESIZE_CQ)) {
+	if (!(dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_RESIZE_CQ)) {
 		pr_info("Firmware does not support resize CQ\n");
 		return -ENOSYS;
 	}
@@ -1083,7 +1083,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 		return -EINVAL;
 
 	entries = roundup_pow_of_two(entries + 1);
-	if (entries > dev->mdev->caps.max_cqes + 1)
+	if (entries > dev->mdev->caps.gen.max_cqes + 1)
 		return -EINVAL;
 
 	if (entries == ibcq->cqe + 1)
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index b514bbb5610f..657af9a1167c 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -129,7 +129,7 @@ int mlx5_query_ext_port_caps(struct mlx5_ib_dev *dev, u8 port)
 
 	packet_error = be16_to_cpu(out_mad->status);
 
-	dev->mdev->caps.ext_port_cap[port - 1] = (!err && !packet_error) ?
+	dev->mdev->caps.gen.ext_port_cap[port - 1] = (!err && !packet_error) ?
 		MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO : 0;
 
 out:
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d8907b20522a..f3114d1132fb 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -157,11 +157,13 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct ib_smp *in_mad  = NULL;
 	struct ib_smp *out_mad = NULL;
+	struct mlx5_general_caps *gen;
 	int err = -ENOMEM;
 	int max_rq_sg;
 	int max_sq_sg;
 	u64 flags;
 
+	gen = &dev->mdev->caps.gen;
 	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
 	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
 	if (!in_mad || !out_mad)
@@ -183,7 +185,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		IB_DEVICE_PORT_ACTIVE_EVENT		|
 		IB_DEVICE_SYS_IMAGE_GUID		|
 		IB_DEVICE_RC_RNR_NAK_GEN;
-	flags = dev->mdev->caps.flags;
+	flags = gen->flags;
 	if (flags & MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR)
 		props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
 	if (flags & MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR)
@@ -213,30 +215,31 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	memcpy(&props->sys_image_guid, out_mad->data +	4, 8);
 
 	props->max_mr_size	   = ~0ull;
-	props->page_size_cap	   = dev->mdev->caps.min_page_sz;
-	props->max_qp		   = 1 << dev->mdev->caps.log_max_qp;
-	props->max_qp_wr	   = dev->mdev->caps.max_wqes;
-	max_rq_sg = dev->mdev->caps.max_rq_desc_sz / sizeof(struct mlx5_wqe_data_seg);
-	max_sq_sg = (dev->mdev->caps.max_sq_desc_sz - sizeof(struct mlx5_wqe_ctrl_seg)) /
+	props->page_size_cap	   = gen->min_page_sz;
+	props->max_qp		   = 1 << gen->log_max_qp;
+	props->max_qp_wr	   = gen->max_wqes;
+	max_rq_sg = gen->max_rq_desc_sz / sizeof(struct mlx5_wqe_data_seg);
+	max_sq_sg = (gen->max_sq_desc_sz - sizeof(struct mlx5_wqe_ctrl_seg)) /
 		sizeof(struct mlx5_wqe_data_seg);
 	props->max_sge = min(max_rq_sg, max_sq_sg);
-	props->max_cq		   = 1 << dev->mdev->caps.log_max_cq;
-	props->max_cqe		   = dev->mdev->caps.max_cqes - 1;
-	props->max_mr		   = 1 << dev->mdev->caps.log_max_mkey;
-	props->max_pd		   = 1 << dev->mdev->caps.log_max_pd;
-	props->max_qp_rd_atom	   = dev->mdev->caps.max_ra_req_qp;
-	props->max_qp_init_rd_atom = dev->mdev->caps.max_ra_res_qp;
+	props->max_cq		   = 1 << gen->log_max_cq;
+	props->max_cqe		   = gen->max_cqes - 1;
+	props->max_mr		   = 1 << gen->log_max_mkey;
+	props->max_pd		   = 1 << gen->log_max_pd;
+	props->max_qp_rd_atom	   = 1 << gen->log_max_ra_req_qp;
+	props->max_qp_init_rd_atom = 1 << gen->log_max_ra_res_qp;
+	props->max_srq		   = 1 << gen->log_max_srq;
+	props->max_srq_wr	   = gen->max_srq_wqes - 1;
+	props->local_ca_ack_delay  = gen->local_ca_ack_delay;
 	props->max_res_rd_atom	   = props->max_qp_rd_atom * props->max_qp;
-	props->max_srq		   = 1 << dev->mdev->caps.log_max_srq;
-	props->max_srq_wr	   = dev->mdev->caps.max_srq_wqes - 1;
 	props->max_srq_sge	   = max_rq_sg - 1;
 	props->max_fast_reg_page_list_len = (unsigned int)-1;
-	props->local_ca_ack_delay  = dev->mdev->caps.local_ca_ack_delay;
+	props->local_ca_ack_delay  = gen->local_ca_ack_delay;
 	props->atomic_cap	   = IB_ATOMIC_NONE;
 	props->masked_atomic_cap   = IB_ATOMIC_NONE;
 	props->max_pkeys	   = be16_to_cpup((__be16 *)(out_mad->data + 28));
-	props->max_mcast_grp	   = 1 << dev->mdev->caps.log_max_mcg;
-	props->max_mcast_qp_attach = dev->mdev->caps.max_qp_mcg;
+	props->max_mcast_grp	   = 1 << gen->log_max_mcg;
+	props->max_mcast_qp_attach = gen->max_qp_mcg;
 	props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
 					   props->max_mcast_grp;
 	props->max_map_per_fmr = INT_MAX; /* no limit in ConnectIB */
@@ -254,10 +257,12 @@ int mlx5_ib_query_port(struct ib_device *ibdev, u8 port,
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct ib_smp *in_mad  = NULL;
 	struct ib_smp *out_mad = NULL;
+	struct mlx5_general_caps *gen;
 	int ext_active_speed;
 	int err = -ENOMEM;
 
-	if (port < 1 || port > dev->mdev->caps.num_ports) {
+	gen = &dev->mdev->caps.gen;
+	if (port < 1 || port > gen->num_ports) {
 		mlx5_ib_warn(dev, "invalid port number %d\n", port);
 		return -EINVAL;
 	}
@@ -288,8 +293,8 @@ int mlx5_ib_query_port(struct ib_device *ibdev, u8 port,
 	props->phys_state	= out_mad->data[33] >> 4;
 	props->port_cap_flags	= be32_to_cpup((__be32 *)(out_mad->data + 20));
 	props->gid_tbl_len	= out_mad->data[50];
-	props->max_msg_sz	= 1 << to_mdev(ibdev)->mdev->caps.log_max_msg;
-	props->pkey_tbl_len	= to_mdev(ibdev)->mdev->caps.port[port - 1].pkey_table_len;
+	props->max_msg_sz	= 1 << gen->log_max_msg;
+	props->pkey_tbl_len	= gen->port[port - 1].pkey_table_len;
 	props->bad_pkey_cntr	= be16_to_cpup((__be16 *)(out_mad->data + 46));
 	props->qkey_viol_cntr	= be16_to_cpup((__be16 *)(out_mad->data + 48));
 	props->active_width	= out_mad->data[31] & 0xf;
@@ -316,7 +321,7 @@ int mlx5_ib_query_port(struct ib_device *ibdev, u8 port,
 
 	/* If reported active speed is QDR, check if is FDR-10 */
 	if (props->active_speed == 4) {
-		if (dev->mdev->caps.ext_port_cap[port - 1] &
+		if (gen->ext_port_cap[port - 1] &
 		    MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO) {
 			init_query_mad(in_mad);
 			in_mad->attr_id = MLX5_ATTR_EXTENDED_PORT_INFO;
@@ -470,6 +475,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	struct mlx5_ib_alloc_ucontext_req_v2 req;
 	struct mlx5_ib_alloc_ucontext_resp resp;
 	struct mlx5_ib_ucontext *context;
+	struct mlx5_general_caps *gen;
 	struct mlx5_uuar_info *uuari;
 	struct mlx5_uar *uars;
 	int gross_uuars;
@@ -480,6 +486,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	int i;
 	size_t reqlen;
 
+	gen = &dev->mdev->caps.gen;
 	if (!dev->ib_active)
 		return ERR_PTR(-EAGAIN);
 
@@ -512,14 +519,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 
 	num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
 	gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
-	resp.qp_tab_size      = 1 << dev->mdev->caps.log_max_qp;
-	resp.bf_reg_size      = dev->mdev->caps.bf_reg_size;
+	resp.qp_tab_size      = 1 << gen->log_max_qp;
+	resp.bf_reg_size      = gen->bf_reg_size;
 	resp.cache_line_size  = L1_CACHE_BYTES;
-	resp.max_sq_desc_sz = dev->mdev->caps.max_sq_desc_sz;
-	resp.max_rq_desc_sz = dev->mdev->caps.max_rq_desc_sz;
-	resp.max_send_wqebb = dev->mdev->caps.max_wqes;
-	resp.max_recv_wr = dev->mdev->caps.max_wqes;
-	resp.max_srq_recv_wr = dev->mdev->caps.max_srq_wqes;
+	resp.max_sq_desc_sz = gen->max_sq_desc_sz;
+	resp.max_rq_desc_sz = gen->max_rq_desc_sz;
+	resp.max_send_wqebb = gen->max_wqes;
+	resp.max_recv_wr = gen->max_wqes;
+	resp.max_srq_recv_wr = gen->max_srq_wqes;
 
 	context = kzalloc(sizeof(*context), GFP_KERNEL);
 	if (!context)
@@ -565,7 +572,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	mutex_init(&context->db_page_mutex);
 
 	resp.tot_uuars = req.total_num_uuars;
-	resp.num_ports = dev->mdev->caps.num_ports;
+	resp.num_ports = gen->num_ports;
 	err = ib_copy_to_udata(udata, &resp,
 			       sizeof(resp) - sizeof(resp.reserved));
 	if (err)
@@ -967,9 +974,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 
 static void get_ext_port_caps(struct mlx5_ib_dev *dev)
 {
+	struct mlx5_general_caps *gen;
 	int port;
 
-	for (port = 1; port <= dev->mdev->caps.num_ports; port++)
+	gen = &dev->mdev->caps.gen;
+	for (port = 1; port <= gen->num_ports; port++)
 		mlx5_query_ext_port_caps(dev, port);
 }
 
@@ -977,9 +986,11 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 {
 	struct ib_device_attr *dprops = NULL;
 	struct ib_port_attr *pprops = NULL;
+	struct mlx5_general_caps *gen;
 	int err = 0;
 	int port;
 
+	gen = &dev->mdev->caps.gen;
 	pprops = kmalloc(sizeof(*pprops), GFP_KERNEL);
 	if (!pprops)
 		goto out;
@@ -994,14 +1005,14 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 		goto out;
 	}
 
-	for (port = 1; port <= dev->mdev->caps.num_ports; port++) {
+	for (port = 1; port <= gen->num_ports; port++) {
 		err = mlx5_ib_query_port(&dev->ib_dev, port, pprops);
 		if (err) {
 			mlx5_ib_warn(dev, "query_port %d failed %d\n", port, err);
 			break;
 		}
-		dev->mdev->caps.port[port - 1].pkey_table_len = dprops->max_pkeys;
-		dev->mdev->caps.port[port - 1].gid_table_len = pprops->gid_tbl_len;
+		gen->port[port - 1].pkey_table_len = dprops->max_pkeys;
+		gen->port[port - 1].gid_table_len = pprops->gid_tbl_len;
 		mlx5_ib_dbg(dev, "pkey_table_len %d, gid_table_len %d\n",
 			    dprops->max_pkeys, pprops->gid_tbl_len);
 	}
@@ -1279,8 +1290,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX);
 	dev->ib_dev.owner		= THIS_MODULE;
 	dev->ib_dev.node_type		= RDMA_NODE_IB_CA;
-	dev->ib_dev.local_dma_lkey	= mdev->caps.reserved_lkey;
-	dev->num_ports		= mdev->caps.num_ports;
+	dev->ib_dev.local_dma_lkey	= mdev->caps.gen.reserved_lkey;
+	dev->num_ports		= mdev->caps.gen.num_ports;
 	dev->ib_dev.phys_port_cnt     = dev->num_ports;
 	dev->ib_dev.num_comp_vectors	= dev->num_comp_vectors;
 	dev->ib_dev.dma_device	= &mdev->pdev->dev;
@@ -1355,7 +1366,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->ib_dev.free_fast_reg_page_list  = mlx5_ib_free_fast_reg_page_list;
 	dev->ib_dev.check_mr_status	= mlx5_ib_check_mr_status;
 
-	if (mdev->caps.flags & MLX5_DEV_CAP_FLAG_XRC) {
+	if (mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_XRC) {
 		dev->ib_dev.alloc_xrcd = mlx5_ib_alloc_xrcd;
 		dev->ib_dev.dealloc_xrcd = mlx5_ib_dealloc_xrcd;
 		dev->ib_dev.uverbs_cmd_mask |=
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 8c574b63d77b..dbfe498870c1 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -158,11 +158,13 @@ static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type)
 static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
 		       int has_rq, struct mlx5_ib_qp *qp, struct mlx5_ib_create_qp *ucmd)
 {
+	struct mlx5_general_caps *gen;
 	int wqe_size;
 	int wq_size;
 
+	gen = &dev->mdev->caps.gen;
 	/* Sanity check RQ size before proceeding */
-	if (cap->max_recv_wr  > dev->mdev->caps.max_wqes)
+	if (cap->max_recv_wr  > gen->max_wqes)
 		return -EINVAL;
 
 	if (!has_rq) {
@@ -182,10 +184,10 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
 			wq_size = roundup_pow_of_two(cap->max_recv_wr) * wqe_size;
 			wq_size = max_t(int, wq_size, MLX5_SEND_WQE_BB);
 			qp->rq.wqe_cnt = wq_size / wqe_size;
-			if (wqe_size > dev->mdev->caps.max_rq_desc_sz) {
+			if (wqe_size > gen->max_rq_desc_sz) {
 				mlx5_ib_dbg(dev, "wqe_size %d, max %d\n",
 					    wqe_size,
-					    dev->mdev->caps.max_rq_desc_sz);
+					    gen->max_rq_desc_sz);
 				return -EINVAL;
 			}
 			qp->rq.wqe_shift = ilog2(wqe_size);
@@ -266,9 +268,11 @@ static int calc_send_wqe(struct ib_qp_init_attr *attr)
 static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 			struct mlx5_ib_qp *qp)
 {
+	struct mlx5_general_caps *gen;
 	int wqe_size;
 	int wq_size;
 
+	gen = &dev->mdev->caps.gen;
 	if (!attr->cap.max_send_wr)
 		return 0;
 
@@ -277,9 +281,9 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 	if (wqe_size < 0)
 		return wqe_size;
 
-	if (wqe_size > dev->mdev->caps.max_sq_desc_sz) {
+	if (wqe_size > gen->max_sq_desc_sz) {
 		mlx5_ib_dbg(dev, "wqe_size(%d) > max_sq_desc_sz(%d)\n",
-			    wqe_size, dev->mdev->caps.max_sq_desc_sz);
+			    wqe_size, gen->max_sq_desc_sz);
 		return -EINVAL;
 	}
 
@@ -292,9 +296,9 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 
 	wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size);
 	qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB;
-	if (qp->sq.wqe_cnt > dev->mdev->caps.max_wqes) {
+	if (qp->sq.wqe_cnt > gen->max_wqes) {
 		mlx5_ib_dbg(dev, "wqe count(%d) exceeds limits(%d)\n",
-			    qp->sq.wqe_cnt, dev->mdev->caps.max_wqes);
+			    qp->sq.wqe_cnt, gen->max_wqes);
 		return -ENOMEM;
 	}
 	qp->sq.wqe_shift = ilog2(MLX5_SEND_WQE_BB);
@@ -309,11 +313,13 @@ static int set_user_buf_size(struct mlx5_ib_dev *dev,
 			    struct mlx5_ib_qp *qp,
 			    struct mlx5_ib_create_qp *ucmd)
 {
+	struct mlx5_general_caps *gen;
 	int desc_sz = 1 << qp->sq.wqe_shift;
 
-	if (desc_sz > dev->mdev->caps.max_sq_desc_sz) {
+	gen = &dev->mdev->caps.gen;
+	if (desc_sz > gen->max_sq_desc_sz) {
 		mlx5_ib_warn(dev, "desc_sz %d, max_sq_desc_sz %d\n",
-			     desc_sz, dev->mdev->caps.max_sq_desc_sz);
+			     desc_sz, gen->max_sq_desc_sz);
 		return -EINVAL;
 	}
 
@@ -325,9 +331,9 @@ static int set_user_buf_size(struct mlx5_ib_dev *dev,
 
 	qp->sq.wqe_cnt = ucmd->sq_wqe_count;
 
-	if (qp->sq.wqe_cnt > dev->mdev->caps.max_wqes) {
+	if (qp->sq.wqe_cnt > gen->max_wqes) {
 		mlx5_ib_warn(dev, "wqe_cnt %d, max_wqes %d\n",
-			     qp->sq.wqe_cnt, dev->mdev->caps.max_wqes);
+			     qp->sq.wqe_cnt, gen->max_wqes);
 		return -EINVAL;
 	}
 
@@ -803,16 +809,18 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	struct mlx5_ib_resources *devr = &dev->devr;
 	struct mlx5_ib_create_qp_resp resp;
 	struct mlx5_create_qp_mbox_in *in;
+	struct mlx5_general_caps *gen;
 	struct mlx5_ib_create_qp ucmd;
 	int inlen = sizeof(*in);
 	int err;
 
+	gen = &dev->mdev->caps.gen;
 	mutex_init(&qp->mutex);
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
 
 	if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK) {
-		if (!(dev->mdev->caps.flags & MLX5_DEV_CAP_FLAG_BLOCK_MCAST)) {
+		if (!(gen->flags & MLX5_DEV_CAP_FLAG_BLOCK_MCAST)) {
 			mlx5_ib_dbg(dev, "block multicast loopback isn't supported\n");
 			return -EINVAL;
 		} else {
@@ -851,9 +859,9 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 				mlx5_ib_dbg(dev, "invalid rq params\n");
 				return -EINVAL;
 			}
-			if (ucmd.sq_wqe_count > dev->mdev->caps.max_wqes) {
+			if (ucmd.sq_wqe_count > gen->max_wqes) {
 				mlx5_ib_dbg(dev, "requested sq_wqe_count (%d) > max allowed (%d)\n",
-					    ucmd.sq_wqe_count, dev->mdev->caps.max_wqes);
+					    ucmd.sq_wqe_count, gen->max_wqes);
 				return -EINVAL;
 			}
 			err = create_user_qp(dev, pd, qp, udata, &in, &resp, &inlen);
@@ -1144,6 +1152,7 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
 				struct ib_qp_init_attr *init_attr,
 				struct ib_udata *udata)
 {
+	struct mlx5_general_caps *gen;
 	struct mlx5_ib_dev *dev;
 	struct mlx5_ib_qp *qp;
 	u16 xrcdn = 0;
@@ -1161,11 +1170,12 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
 		}
 		dev = to_mdev(to_mxrcd(init_attr->xrcd)->ibxrcd.device);
 	}
+	gen = &dev->mdev->caps.gen;
 
 	switch (init_attr->qp_type) {
 	case IB_QPT_XRC_TGT:
 	case IB_QPT_XRC_INI:
-		if (!(dev->mdev->caps.flags & MLX5_DEV_CAP_FLAG_XRC)) {
+		if (!(gen->flags & MLX5_DEV_CAP_FLAG_XRC)) {
 			mlx5_ib_dbg(dev, "XRC not supported\n");
 			return ERR_PTR(-ENOSYS);
 		}
@@ -1272,6 +1282,9 @@ enum {
 
 static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
 {
+	struct mlx5_general_caps *gen;
+
+	gen = &dev->mdev->caps.gen;
 	if (rate == IB_RATE_PORT_CURRENT) {
 		return 0;
 	} else if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_300_GBPS) {
@@ -1279,7 +1292,7 @@ static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
 	} else {
 		while (rate != IB_RATE_2_5_GBPS &&
 		       !(1 << (rate + MLX5_STAT_RATE_OFFSET) &
-			 dev->mdev->caps.stat_rate_support))
+			 gen->stat_rate_support))
 			--rate;
 	}
 
@@ -1290,8 +1303,10 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, const struct ib_ah_attr *ah,
 			 struct mlx5_qp_path *path, u8 port, int attr_mask,
 			 u32 path_flags, const struct ib_qp_attr *attr)
 {
+	struct mlx5_general_caps *gen;
 	int err;
 
+	gen = &dev->mdev->caps.gen;
 	path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
 	path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 : 0;
 
@@ -1318,9 +1333,9 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, const struct ib_ah_attr *ah,
 	path->port = port;
 
 	if (ah->ah_flags & IB_AH_GRH) {
-		if (ah->grh.sgid_index >= dev->mdev->caps.port[port - 1].gid_table_len) {
+		if (ah->grh.sgid_index >= gen->port[port - 1].gid_table_len) {
 			pr_err(KERN_ERR "sgid_index (%u) too large. max is %d\n",
-			       ah->grh.sgid_index, dev->mdev->caps.port[port - 1].gid_table_len);
+			       ah->grh.sgid_index, gen->port[port - 1].gid_table_len);
 			return -EINVAL;
 		}
 
@@ -1492,6 +1507,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
 	struct mlx5_ib_cq *send_cq, *recv_cq;
 	struct mlx5_qp_context *context;
+	struct mlx5_general_caps *gen;
 	struct mlx5_modify_qp_mbox_in *in;
 	struct mlx5_ib_pd *pd;
 	enum mlx5_qp_state mlx5_cur, mlx5_new;
@@ -1500,6 +1516,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	int mlx5_st;
 	int err;
 
+	gen = &dev->mdev->caps.gen;
 	in = kzalloc(sizeof(*in), GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -1539,7 +1556,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 			err = -EINVAL;
 			goto out;
 		}
-		context->mtu_msgmax = (attr->path_mtu << 5) | dev->mdev->caps.log_max_msg;
+		context->mtu_msgmax = (attr->path_mtu << 5) | gen->log_max_msg;
 	}
 
 	if (attr_mask & IB_QP_DEST_QPN)
@@ -1685,9 +1702,11 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
 	enum ib_qp_state cur_state, new_state;
+	struct mlx5_general_caps *gen;
 	int err = -EINVAL;
 	int port;
 
+	gen = &dev->mdev->caps.gen;
 	mutex_lock(&qp->mutex);
 
 	cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
@@ -1699,21 +1718,21 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		goto out;
 
 	if ((attr_mask & IB_QP_PORT) &&
-	    (attr->port_num == 0 || attr->port_num > dev->mdev->caps.num_ports))
+	    (attr->port_num == 0 || attr->port_num > gen->num_ports))
 		goto out;
 
 	if (attr_mask & IB_QP_PKEY_INDEX) {
 		port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
-		if (attr->pkey_index >= dev->mdev->caps.port[port - 1].pkey_table_len)
+		if (attr->pkey_index >= gen->port[port - 1].pkey_table_len)
 			goto out;
 	}
 
 	if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
-	    attr->max_rd_atomic > dev->mdev->caps.max_ra_res_qp)
+	    attr->max_rd_atomic > (1 << gen->log_max_ra_res_qp))
 		goto out;
 
 	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
-	    attr->max_dest_rd_atomic > dev->mdev->caps.max_ra_req_qp)
+	    attr->max_dest_rd_atomic > (1 << gen->log_max_ra_req_qp))
 		goto out;
 
 	if (cur_state == new_state && cur_state == IB_QPS_RESET) {
@@ -2893,7 +2912,8 @@ static void to_ib_ah_attr(struct mlx5_ib_dev *ibdev, struct ib_ah_attr *ib_ah_at
 	memset(ib_ah_attr, 0, sizeof(*ib_ah_attr));
 	ib_ah_attr->port_num	  = path->port;
 
-	if (ib_ah_attr->port_num == 0 || ib_ah_attr->port_num > dev->caps.num_ports)
+	if (ib_ah_attr->port_num == 0 ||
+	    ib_ah_attr->port_num > dev->caps.gen.num_ports)
 		return;
 
 	ib_ah_attr->sl = path->sl & 0xf;
@@ -3011,10 +3031,12 @@ struct ib_xrcd *mlx5_ib_alloc_xrcd(struct ib_device *ibdev,
 					  struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_general_caps *gen;
 	struct mlx5_ib_xrcd *xrcd;
 	int err;
 
-	if (!(dev->mdev->caps.flags & MLX5_DEV_CAP_FLAG_XRC))
+	gen = &dev->mdev->caps.gen;
+	if (!(gen->flags & MLX5_DEV_CAP_FLAG_XRC))
 		return ERR_PTR(-ENOSYS);
 
 	xrcd = kmalloc(sizeof(*xrcd), GFP_KERNEL);
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 70bd131ba646..97cc1baaa8e3 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -238,6 +238,7 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 				  struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+	struct mlx5_general_caps *gen;
 	struct mlx5_ib_srq *srq;
 	int desc_size;
 	int buf_size;
@@ -247,11 +248,12 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 	int is_xrc;
 	u32 flgs, xrcdn;
 
+	gen = &dev->mdev->caps.gen;
 	/* Sanity check SRQ size before proceeding */
-	if (init_attr->attr.max_wr >= dev->mdev->caps.max_srq_wqes) {
+	if (init_attr->attr.max_wr >= gen->max_srq_wqes) {
 		mlx5_ib_dbg(dev, "max_wr %d, cap %d\n",
 			    init_attr->attr.max_wr,
-			    dev->mdev->caps.max_srq_wqes);
+			    gen->max_srq_wqes);
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 65a7da69e2ac..6eb0f85cf872 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1538,16 +1538,9 @@ static const char *cmd_status_str(u8 status)
 	}
 }
 
-int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr)
+static int cmd_status_to_err(u8 status)
 {
-	if (!hdr->status)
-		return 0;
-
-	pr_warn("command failed, status %s(0x%x), syndrome 0x%x\n",
-		cmd_status_str(hdr->status), hdr->status,
-		be32_to_cpu(hdr->syndrome));
-
-	switch (hdr->status) {
+	switch (status) {
 	case MLX5_CMD_STAT_OK:				return 0;
 	case MLX5_CMD_STAT_INT_ERR:			return -EIO;
 	case MLX5_CMD_STAT_BAD_OP_ERR:			return -EINVAL;
@@ -1567,3 +1560,16 @@ int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr)
 	default:					return -EIO;
 	}
 }
+
+/* this will be available till all the commands use set/get macros */
+int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr)
+{
+	if (!hdr->status)
+		return 0;
+
+	pr_warn("command failed, status %s(0x%x), syndrome 0x%x\n",
+		cmd_status_str(hdr->status), hdr->status,
+		be32_to_cpu(hdr->syndrome));
+
+	return cmd_status_to_err(hdr->status);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 4e8bd0b34bb0..11b9b840ad4d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -468,7 +468,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 
 	err = mlx5_create_map_eq(dev, &table->pages_eq,
 				 MLX5_EQ_VEC_PAGES,
-				 dev->caps.max_vf + 1,
+				 dev->caps.gen.max_vf + 1,
 				 1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq",
 				 &dev->priv.uuari.uars[0]);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index f012658b6a92..087c4c797deb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -64,86 +64,9 @@ out_out:
 	return err;
 }
 
-int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev,
-			   struct mlx5_caps *caps)
+int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev, struct mlx5_caps *caps)
 {
-	struct mlx5_cmd_query_hca_cap_mbox_out *out;
-	struct mlx5_cmd_query_hca_cap_mbox_in in;
-	struct mlx5_query_special_ctxs_mbox_out ctx_out;
-	struct mlx5_query_special_ctxs_mbox_in ctx_in;
-	int err;
-	u16 t16;
-
-	out = kzalloc(sizeof(*out), GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
-	memset(&in, 0, sizeof(in));
-	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_HCA_CAP);
-	in.hdr.opmod  = cpu_to_be16(0x1);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, sizeof(*out));
-	if (err)
-		goto out_out;
-
-	if (out->hdr.status) {
-		err = mlx5_cmd_status_to_err(&out->hdr);
-		goto out_out;
-	}
-
-
-	caps->log_max_eq = out->hca_cap.log_max_eq & 0xf;
-	caps->max_cqes = 1 << out->hca_cap.log_max_cq_sz;
-	caps->max_wqes = 1 << out->hca_cap.log_max_qp_sz;
-	caps->max_sq_desc_sz = be16_to_cpu(out->hca_cap.max_desc_sz_sq);
-	caps->max_rq_desc_sz = be16_to_cpu(out->hca_cap.max_desc_sz_rq);
-	caps->flags = be64_to_cpu(out->hca_cap.flags);
-	caps->stat_rate_support = be16_to_cpu(out->hca_cap.stat_rate_support);
-	caps->log_max_msg = out->hca_cap.log_max_msg & 0x1f;
-	caps->num_ports = out->hca_cap.num_ports & 0xf;
-	caps->log_max_cq = out->hca_cap.log_max_cq & 0x1f;
-	if (caps->num_ports > MLX5_MAX_PORTS) {
-		mlx5_core_err(dev, "device has %d ports while the driver supports max %d ports\n",
-			      caps->num_ports, MLX5_MAX_PORTS);
-		err = -EINVAL;
-		goto out_out;
-	}
-	caps->log_max_qp = out->hca_cap.log_max_qp & 0x1f;
-	caps->log_max_mkey = out->hca_cap.log_max_mkey & 0x3f;
-	caps->log_max_pd = out->hca_cap.log_max_pd & 0x1f;
-	caps->log_max_srq = out->hca_cap.log_max_srqs & 0x1f;
-	caps->local_ca_ack_delay = out->hca_cap.local_ca_ack_delay & 0x1f;
-	caps->log_max_mcg = out->hca_cap.log_max_mcg;
-	caps->max_qp_mcg = be32_to_cpu(out->hca_cap.max_qp_mcg) & 0xffffff;
-	caps->max_ra_res_qp = 1 << (out->hca_cap.log_max_ra_res_qp & 0x3f);
-	caps->max_ra_req_qp = 1 << (out->hca_cap.log_max_ra_req_qp & 0x3f);
-	caps->max_srq_wqes = 1 << out->hca_cap.log_max_srq_sz;
-	t16 = be16_to_cpu(out->hca_cap.bf_log_bf_reg_size);
-	if (t16 & 0x8000) {
-		caps->bf_reg_size = 1 << (t16 & 0x1f);
-		caps->bf_regs_per_page = MLX5_BF_REGS_PER_PAGE;
-	} else {
-		caps->bf_reg_size = 0;
-		caps->bf_regs_per_page = 0;
-	}
-	caps->min_page_sz = ~(u32)((1 << out->hca_cap.log_pg_sz) - 1);
-
-	memset(&ctx_in, 0, sizeof(ctx_in));
-	memset(&ctx_out, 0, sizeof(ctx_out));
-	ctx_in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
-	err = mlx5_cmd_exec(dev, &ctx_in, sizeof(ctx_in),
-				 &ctx_out, sizeof(ctx_out));
-	if (err)
-		goto out_out;
-
-	if (ctx_out.hdr.status)
-		err = mlx5_cmd_status_to_err(&ctx_out.hdr);
-
-	caps->reserved_lkey = be32_to_cpu(ctx_out.reserved_lkey);
-
-out_out:
-	kfree(out);
-
-	return err;
+	return mlx5_core_get_caps(dev, caps, HCA_CAP_OPMOD_GET_CUR);
 }
 
 int mlx5_cmd_init_hca(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f2716cc1f51d..d9f74618befa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -207,11 +207,11 @@ static void release_bar(struct pci_dev *pdev)
 static int mlx5_enable_msix(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	int num_eqs = 1 << dev->caps.log_max_eq;
+	int num_eqs = 1 << dev->caps.gen.log_max_eq;
 	int nvec;
 	int i;
 
-	nvec = dev->caps.num_ports * num_online_cpus() + MLX5_EQ_VEC_COMP_BASE;
+	nvec = dev->caps.gen.num_ports * num_online_cpus() + MLX5_EQ_VEC_COMP_BASE;
 	nvec = min_t(int, nvec, num_eqs);
 	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
 		return -ENOMEM;
@@ -250,13 +250,34 @@ struct mlx5_reg_host_endianess {
 #define CAP_MASK(pos, size) ((u64)((1 << (size)) - 1) << (pos))
 
 enum {
-	MLX5_CAP_BITS_RW_MASK	= CAP_MASK(MLX5_CAP_OFF_CMDIF_CSUM, 2) |
-				  CAP_MASK(MLX5_CAP_OFF_DCT, 1),
+	MLX5_CAP_BITS_RW_MASK = CAP_MASK(MLX5_CAP_OFF_CMDIF_CSUM, 2) |
+				MLX5_DEV_CAP_FLAG_DCT,
 };
 
+static u16 to_fw_pkey_sz(u32 size)
+{
+	switch (size) {
+	case 128:
+		return 0;
+	case 256:
+		return 1;
+	case 512:
+		return 2;
+	case 1024:
+		return 3;
+	case 2048:
+		return 4;
+	case 4096:
+		return 5;
+	default:
+		pr_warn("invalid pkey table size %d\n", size);
+		return 0;
+	}
+}
+
 /* selectively copy writable fields clearing any reserved area
  */
-static void copy_rw_fields(struct mlx5_hca_cap *to, struct mlx5_hca_cap *from)
+static void copy_rw_fields(struct mlx5_hca_cap *to, struct mlx5_general_caps *from)
 {
 	u64 v64;
 
@@ -265,76 +286,172 @@ static void copy_rw_fields(struct mlx5_hca_cap *to, struct mlx5_hca_cap *from)
 	to->log_max_ra_res_dc = from->log_max_ra_res_dc & 0x3f;
 	to->log_max_ra_req_qp = from->log_max_ra_req_qp & 0x3f;
 	to->log_max_ra_res_qp = from->log_max_ra_res_qp & 0x3f;
-	to->log_max_atomic_size_qp = from->log_max_atomic_size_qp;
-	to->log_max_atomic_size_dc = from->log_max_atomic_size_dc;
-	v64 = be64_to_cpu(from->flags) & MLX5_CAP_BITS_RW_MASK;
+	to->pkey_table_size = cpu_to_be16(to_fw_pkey_sz(from->pkey_table_size));
+	v64 = from->flags & MLX5_CAP_BITS_RW_MASK;
 	to->flags = cpu_to_be64(v64);
 }
 
-enum {
-	HCA_CAP_OPMOD_GET_MAX	= 0,
-	HCA_CAP_OPMOD_GET_CUR	= 1,
-};
+static u16 get_pkey_table_size(int pkey)
+{
+	if (pkey > MLX5_MAX_LOG_PKEY_TABLE)
+		return 0;
 
-static int handle_hca_cap(struct mlx5_core_dev *dev)
+	return MLX5_MIN_PKEY_TABLE_SIZE << pkey;
+}
+
+static void fw2drv_caps(struct mlx5_caps *caps,
+			struct mlx5_cmd_query_hca_cap_mbox_out *out)
 {
-	struct mlx5_cmd_query_hca_cap_mbox_out *query_out = NULL;
-	struct mlx5_cmd_set_hca_cap_mbox_in *set_ctx = NULL;
-	struct mlx5_cmd_query_hca_cap_mbox_in query_ctx;
-	struct mlx5_cmd_set_hca_cap_mbox_out set_out;
-	u64 flags;
+	struct mlx5_general_caps *gen = &caps->gen;
+	u16 t16;
+
+	gen->max_srq_wqes = 1 << out->hca_cap.log_max_srq_sz;
+	gen->max_wqes = 1 << out->hca_cap.log_max_qp_sz;
+	gen->log_max_qp = out->hca_cap.log_max_qp & 0x1f;
+	gen->log_max_strq = out->hca_cap.log_max_strq_sz;
+	gen->log_max_srq = out->hca_cap.log_max_srqs & 0x1f;
+	gen->max_cqes = 1 << out->hca_cap.log_max_cq_sz;
+	gen->log_max_cq = out->hca_cap.log_max_cq & 0x1f;
+	gen->max_eqes = out->hca_cap.log_max_eq_sz;
+	gen->log_max_mkey = out->hca_cap.log_max_mkey & 0x3f;
+	gen->log_max_eq = out->hca_cap.log_max_eq & 0xf;
+	gen->max_indirection = out->hca_cap.max_indirection;
+	gen->log_max_mrw_sz = out->hca_cap.log_max_mrw_sz;
+	gen->log_max_bsf_list_size = 0;
+	gen->log_max_klm_list_size = 0;
+	gen->log_max_ra_req_dc = out->hca_cap.log_max_ra_req_dc;
+	gen->log_max_ra_res_dc = out->hca_cap.log_max_ra_res_dc;
+	gen->log_max_ra_req_qp = out->hca_cap.log_max_ra_req_qp;
+	gen->log_max_ra_res_qp = out->hca_cap.log_max_ra_res_qp;
+	gen->max_qp_counters = be16_to_cpu(out->hca_cap.max_qp_count);
+	gen->pkey_table_size = get_pkey_table_size(be16_to_cpu(out->hca_cap.pkey_table_size));
+	gen->local_ca_ack_delay = out->hca_cap.local_ca_ack_delay & 0x1f;
+	gen->num_ports = out->hca_cap.num_ports & 0xf;
+	gen->log_max_msg = out->hca_cap.log_max_msg & 0x1f;
+	gen->stat_rate_support = be16_to_cpu(out->hca_cap.stat_rate_support);
+	gen->flags = be64_to_cpu(out->hca_cap.flags);
+	pr_debug("flags = 0x%llx\n", gen->flags);
+	gen->uar_sz = out->hca_cap.uar_sz;
+	gen->min_log_pg_sz = out->hca_cap.log_pg_sz;
+
+	t16 = be16_to_cpu(out->hca_cap.bf_log_bf_reg_size);
+	if (t16 & 0x8000) {
+		gen->bf_reg_size = 1 << (t16 & 0x1f);
+		gen->bf_regs_per_page = MLX5_BF_REGS_PER_PAGE;
+	} else {
+		gen->bf_reg_size = 0;
+		gen->bf_regs_per_page = 0;
+	}
+	gen->max_sq_desc_sz = be16_to_cpu(out->hca_cap.max_desc_sz_sq);
+	gen->max_rq_desc_sz = be16_to_cpu(out->hca_cap.max_desc_sz_rq);
+	gen->max_qp_mcg = be32_to_cpu(out->hca_cap.max_qp_mcg) & 0xffffff;
+	gen->log_max_pd = out->hca_cap.log_max_pd & 0x1f;
+	gen->log_max_xrcd = out->hca_cap.log_max_xrcd;
+	gen->log_uar_page_sz = be16_to_cpu(out->hca_cap.log_uar_page_sz);
+}
+
+static const char *caps_opmod_str(u16 opmod)
+{
+	switch (opmod) {
+	case HCA_CAP_OPMOD_GET_MAX:
+		return "GET_MAX";
+	case HCA_CAP_OPMOD_GET_CUR:
+		return "GET_CUR";
+	default:
+		return "Invalid";
+	}
+}
+
+int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps,
+		       u16 opmod)
+{
+	struct mlx5_cmd_query_hca_cap_mbox_out *out;
+	struct mlx5_cmd_query_hca_cap_mbox_in in;
 	int err;
 
-	memset(&query_ctx, 0, sizeof(query_ctx));
-	query_out = kzalloc(sizeof(*query_out), GFP_KERNEL);
-	if (!query_out)
+	memset(&in, 0, sizeof(in));
+	out = kzalloc(sizeof(*out), GFP_KERNEL);
+	if (!out)
 		return -ENOMEM;
 
-	set_ctx = kzalloc(sizeof(*set_ctx), GFP_KERNEL);
-	if (!set_ctx) {
-		err = -ENOMEM;
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_HCA_CAP);
+	in.hdr.opmod  = cpu_to_be16(opmod);
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, sizeof(*out));
+
+	err = mlx5_cmd_status_to_err(&out->hdr);
+	if (err) {
+		mlx5_core_warn(dev, "query max hca cap failed, %d\n", err);
 		goto query_ex;
 	}
+	mlx5_core_dbg(dev, "%s\n", caps_opmod_str(opmod));
+	fw2drv_caps(caps, out);
 
-	query_ctx.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_HCA_CAP);
-	query_ctx.hdr.opmod  = cpu_to_be16(HCA_CAP_OPMOD_GET_CUR);
-	err = mlx5_cmd_exec(dev, &query_ctx, sizeof(query_ctx),
-				 query_out, sizeof(*query_out));
+query_ex:
+	kfree(out);
+	return err;
+}
+
+static int set_caps(struct mlx5_core_dev *dev,
+		    struct mlx5_cmd_set_hca_cap_mbox_in *in)
+{
+	struct mlx5_cmd_set_hca_cap_mbox_out out;
+	int err;
+
+	memset(&out, 0, sizeof(out));
+
+	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_SET_HCA_CAP);
+	err = mlx5_cmd_exec(dev, in, sizeof(*in), &out, sizeof(out));
 	if (err)
-		goto query_ex;
+		return err;
 
-	err = mlx5_cmd_status_to_err(&query_out->hdr);
-	if (err) {
-		mlx5_core_warn(dev, "query hca cap failed, %d\n", err);
+	err = mlx5_cmd_status_to_err(&out.hdr);
+
+	return err;
+}
+
+static int handle_hca_cap(struct mlx5_core_dev *dev)
+{
+	struct mlx5_cmd_set_hca_cap_mbox_in *set_ctx = NULL;
+	struct mlx5_profile *prof = dev->profile;
+	struct mlx5_caps *cur_caps = NULL;
+	struct mlx5_caps *max_caps = NULL;
+	int err = -ENOMEM;
+
+	set_ctx = kzalloc(sizeof(*set_ctx), GFP_KERNEL);
+	if (!set_ctx)
 		goto query_ex;
-	}
 
-	copy_rw_fields(&set_ctx->hca_cap, &query_out->hca_cap);
+	max_caps = kzalloc(sizeof(*max_caps), GFP_KERNEL);
+	if (!max_caps)
+		goto query_ex;
 
-	if (dev->profile && dev->profile->mask & MLX5_PROF_MASK_QP_SIZE)
-		set_ctx->hca_cap.log_max_qp = dev->profile->log_max_qp;
+	cur_caps = kzalloc(sizeof(*cur_caps), GFP_KERNEL);
+	if (!cur_caps)
+		goto query_ex;
 
-	flags = be64_to_cpu(query_out->hca_cap.flags);
-	/* disable checksum */
-	flags &= ~MLX5_DEV_CAP_FLAG_CMDIF_CSUM;
-
-	set_ctx->hca_cap.flags = cpu_to_be64(flags);
-	memset(&set_out, 0, sizeof(set_out));
-	set_ctx->hca_cap.log_uar_page_sz = cpu_to_be16(PAGE_SHIFT - 12);
-	set_ctx->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_SET_HCA_CAP);
-	err = mlx5_cmd_exec(dev, set_ctx, sizeof(*set_ctx),
-				 &set_out, sizeof(set_out));
-	if (err) {
-		mlx5_core_warn(dev, "set hca cap failed, %d\n", err);
+	err = mlx5_core_get_caps(dev, max_caps, HCA_CAP_OPMOD_GET_MAX);
+	if (err)
 		goto query_ex;
-	}
 
-	err = mlx5_cmd_status_to_err(&set_out.hdr);
+	err = mlx5_core_get_caps(dev, cur_caps, HCA_CAP_OPMOD_GET_CUR);
 	if (err)
 		goto query_ex;
 
+	/* we limit the size of the pkey table to 128 entries for now */
+	cur_caps->gen.pkey_table_size = 128;
+
+	if (prof->mask & MLX5_PROF_MASK_QP_SIZE)
+		cur_caps->gen.log_max_qp = prof->log_max_qp;
+
+	/* disable checksum */
+	cur_caps->gen.flags &= ~MLX5_DEV_CAP_FLAG_CMDIF_CSUM;
+
+	copy_rw_fields(&set_ctx->hca_cap, &cur_caps->gen);
+	err = set_caps(dev, set_ctx);
+
 query_ex:
-	kfree(query_out);
+	kfree(cur_caps);
+	kfree(max_caps);
 	kfree(set_ctx);
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 68f5d9c77c7b..0a6348cefc01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -174,11 +174,11 @@ int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari)
 	for (i = 0; i < tot_uuars; i++) {
 		bf = &uuari->bfs[i];
 
-		bf->buf_size = dev->caps.bf_reg_size / 2;
+		bf->buf_size = dev->caps.gen.bf_reg_size / 2;
 		bf->uar = &uuari->uars[i / MLX5_BF_REGS_PER_PAGE];
 		bf->regreg = uuari->uars[i / MLX5_BF_REGS_PER_PAGE].map;
 		bf->reg = NULL; /* Add WC support */
-		bf->offset = (i % MLX5_BF_REGS_PER_PAGE) * dev->caps.bf_reg_size +
+		bf->offset = (i % MLX5_BF_REGS_PER_PAGE) * dev->caps.gen.bf_reg_size +
 			MLX5_BF_OFFSET;
 		bf->need_lock = need_uuar_lock(i);
 		spin_lock_init(&bf->lock);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 334947151dfc..dce01fd854a8 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -70,6 +70,11 @@ enum {
 	MLX5_INLINE_SEG = 0x80000000,
 };
 
+enum {
+	MLX5_MIN_PKEY_TABLE_SIZE = 128,
+	MLX5_MAX_LOG_PKEY_TABLE  = 5,
+};
+
 enum {
 	MLX5_PERM_LOCAL_READ	= 1 << 2,
 	MLX5_PERM_LOCAL_WRITE	= 1 << 3,
@@ -184,10 +189,10 @@ enum {
 	MLX5_DEV_CAP_FLAG_CQ_MODER	= 1LL << 29,
 	MLX5_DEV_CAP_FLAG_RESIZE_CQ	= 1LL << 30,
 	MLX5_DEV_CAP_FLAG_RESIZE_SRQ	= 1LL << 32,
+	MLX5_DEV_CAP_FLAG_DCT		= 1LL << 37,
 	MLX5_DEV_CAP_FLAG_REMOTE_FENCE	= 1LL << 38,
 	MLX5_DEV_CAP_FLAG_TLP_HINTS	= 1LL << 39,
 	MLX5_DEV_CAP_FLAG_SIG_HAND_OVER	= 1LL << 40,
-	MLX5_DEV_CAP_FLAG_DCT		= 1LL << 41,
 	MLX5_DEV_CAP_FLAG_CMDIF_CSUM	= 3LL << 46,
 };
 
@@ -243,10 +248,14 @@ enum {
 };
 
 enum {
-	MLX5_CAP_OFF_DCT		= 41,
 	MLX5_CAP_OFF_CMDIF_CSUM		= 46,
 };
 
+enum {
+	HCA_CAP_OPMOD_GET_MAX	= 0,
+	HCA_CAP_OPMOD_GET_CUR	= 1,
+};
+
 struct mlx5_inbox_hdr {
 	__be16		opcode;
 	u8		rsvd[4];
@@ -303,9 +312,10 @@ struct mlx5_hca_cap {
 	u8	log_max_ra_req_qp;
 	u8	rsvd10;
 	u8	log_max_ra_res_qp;
-	u8	rsvd11[4];
+	u8	pad_cap;
+	u8	rsvd11[3];
 	__be16	max_qp_count;
-	__be16	rsvd12;
+	__be16	pkey_table_size;
 	u8	rsvd13;
 	u8	local_ca_ack_delay;
 	u8	rsvd14;
@@ -335,11 +345,7 @@ struct mlx5_hca_cap {
 	u8	log_max_xrcd;
 	u8	rsvd25[42];
 	__be16  log_uar_page_sz;
-	u8	rsvd26[28];
-	u8	log_max_atomic_size_qp;
-	u8	rsvd27[2];
-	u8	log_max_atomic_size_dc;
-	u8	rsvd28[76];
+	u8	rsvd26[108];
 };
 
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index b88e9b46d957..45a2add747e0 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -335,23 +335,30 @@ struct mlx5_port_caps {
 	int	pkey_table_len;
 };
 
-struct mlx5_caps {
+struct mlx5_general_caps {
 	u8	log_max_eq;
 	u8	log_max_cq;
 	u8	log_max_qp;
 	u8	log_max_mkey;
 	u8	log_max_pd;
 	u8	log_max_srq;
+	u8	log_max_strq;
+	u8	log_max_mrw_sz;
+	u8	log_max_bsf_list_size;
+	u8	log_max_klm_list_size;
 	u32	max_cqes;
 	int	max_wqes;
+	u32	max_eqes;
+	u32	max_indirection;
 	int	max_sq_desc_sz;
 	int	max_rq_desc_sz;
+	int	max_dc_sq_desc_sz;
 	u64	flags;
 	u16	stat_rate_support;
 	int	log_max_msg;
 	int	num_ports;
-	int	max_ra_res_qp;
-	int	max_ra_req_qp;
+	u8	log_max_ra_res_qp;
+	u8	log_max_ra_req_qp;
 	int	max_srq_wqes;
 	int	bf_reg_size;
 	int	bf_regs_per_page;
@@ -363,6 +370,19 @@ struct mlx5_caps {
 	u8	log_max_mcg;
 	u32	max_qp_mcg;
 	int	min_page_sz;
+	int	pd_cap;
+	u32	max_qp_counters;
+	u32	pkey_table_size;
+	u8	log_max_ra_req_dc;
+	u8	log_max_ra_res_dc;
+	u32	uar_sz;
+	u8	min_log_pg_sz;
+	u8	log_max_xrcd;
+	u16	log_uar_page_sz;
+};
+
+struct mlx5_caps {
+	struct mlx5_general_caps gen;
 };
 
 struct mlx5_cmd_mailbox {
@@ -695,6 +715,8 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
 int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr);
+int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps,
+		       u16 opmod);
 int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		  int out_size);
 int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size,
-- 
cgit v1.2.3


From d29b796adada8780db3512c4a34b339f9aeef1ae Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Thu, 2 Oct 2014 12:19:43 +0300
Subject: net/mlx5_core: Use hardware registers description header file

Add an auto generated header file that describes hardware registers along with
set of macros that set/get values. The macros do static checks to avoid
overflow, handle endianess, and overall provide a clean way to code commands.
Currently the header file is small and we will add structs as we make use of
the macros.
A few commands were removed from the commands enum since they are not supported
currently and will be added when support is available.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c |  36 -------
 drivers/net/ethernet/mellanox/mlx5/core/qp.c  |   3 -
 include/linux/mlx5/device.h                   |  44 ++++++++
 include/linux/mlx5/driver.h                   |  76 +-------------
 include/linux/mlx5/mlx5_ifc.h                 | 143 ++++++++++++++++++++++++++
 5 files changed, 188 insertions(+), 114 deletions(-)
 create mode 100644 include/linux/mlx5/mlx5_ifc.h

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 6eb0f85cf872..3ecef1310bae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -357,60 +357,24 @@ const char *mlx5_command_str(int command)
 	case MLX5_CMD_OP_2ERR_QP:
 		return "2ERR_QP";
 
-	case MLX5_CMD_OP_RTS2SQD_QP:
-		return "RTS2SQD_QP";
-
-	case MLX5_CMD_OP_SQD2RTS_QP:
-		return "SQD2RTS_QP";
-
 	case MLX5_CMD_OP_2RST_QP:
 		return "2RST_QP";
 
 	case MLX5_CMD_OP_QUERY_QP:
 		return "QUERY_QP";
 
-	case MLX5_CMD_OP_CONF_SQP:
-		return "CONF_SQP";
-
 	case MLX5_CMD_OP_MAD_IFC:
 		return "MAD_IFC";
 
 	case MLX5_CMD_OP_INIT2INIT_QP:
 		return "INIT2INIT_QP";
 
-	case MLX5_CMD_OP_SUSPEND_QP:
-		return "SUSPEND_QP";
-
-	case MLX5_CMD_OP_UNSUSPEND_QP:
-		return "UNSUSPEND_QP";
-
-	case MLX5_CMD_OP_SQD2SQD_QP:
-		return "SQD2SQD_QP";
-
-	case MLX5_CMD_OP_ALLOC_QP_COUNTER_SET:
-		return "ALLOC_QP_COUNTER_SET";
-
-	case MLX5_CMD_OP_DEALLOC_QP_COUNTER_SET:
-		return "DEALLOC_QP_COUNTER_SET";
-
-	case MLX5_CMD_OP_QUERY_QP_COUNTER_SET:
-		return "QUERY_QP_COUNTER_SET";
-
 	case MLX5_CMD_OP_CREATE_PSV:
 		return "CREATE_PSV";
 
 	case MLX5_CMD_OP_DESTROY_PSV:
 		return "DESTROY_PSV";
 
-	case MLX5_CMD_OP_QUERY_PSV:
-		return "QUERY_PSV";
-
-	case MLX5_CMD_OP_QUERY_SIG_RULE_TABLE:
-		return "QUERY_SIG_RULE_TABLE";
-
-	case MLX5_CMD_OP_QUERY_BLOCK_SIZE_TABLE:
-		return "QUERY_BLOCK_SIZE_TABLE";
-
 	case MLX5_CMD_OP_CREATE_SRQ:
 		return "CREATE_SRQ";
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 8145b4668229..415b67ce379e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -184,13 +184,10 @@ int mlx5_core_qp_modify(struct mlx5_core_dev *dev, enum mlx5_qp_state cur_state,
 			[MLX5_QP_STATE_RST]	= MLX5_CMD_OP_2RST_QP,
 			[MLX5_QP_STATE_ERR]	= MLX5_CMD_OP_2ERR_QP,
 			[MLX5_QP_STATE_RTS]	= MLX5_CMD_OP_RTS2RTS_QP,
-			[MLX5_QP_STATE_SQD]	= MLX5_CMD_OP_RTS2SQD_QP,
 		},
 		[MLX5_QP_STATE_SQD] = {
 			[MLX5_QP_STATE_RST]	= MLX5_CMD_OP_2RST_QP,
 			[MLX5_QP_STATE_ERR]	= MLX5_CMD_OP_2ERR_QP,
-			[MLX5_QP_STATE_RTS]	= MLX5_CMD_OP_SQD2RTS_QP,
-			[MLX5_QP_STATE_SQD]	= MLX5_CMD_OP_SQD2SQD_QP,
 		},
 		[MLX5_QP_STATE_SQER] = {
 			[MLX5_QP_STATE_RST]	= MLX5_CMD_OP_2RST_QP,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index dce01fd854a8..0032687f58c7 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -44,6 +44,50 @@
 #error Host endianness not defined
 #endif
 
+/* helper macros */
+#define __mlx5_nullp(typ) ((struct mlx5_ifc_##typ##_bits *)0)
+#define __mlx5_bit_sz(typ, fld) sizeof(__mlx5_nullp(typ)->fld)
+#define __mlx5_bit_off(typ, fld) ((unsigned)(unsigned long)(&(__mlx5_nullp(typ)->fld)))
+#define __mlx5_dw_off(typ, fld) (__mlx5_bit_off(typ, fld) / 32)
+#define __mlx5_64_off(typ, fld) (__mlx5_bit_off(typ, fld) / 64)
+#define __mlx5_dw_bit_off(typ, fld) (32 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0x1f))
+#define __mlx5_mask(typ, fld) ((u32)((1ull << __mlx5_bit_sz(typ, fld)) - 1))
+#define __mlx5_dw_mask(typ, fld) (__mlx5_mask(typ, fld) << __mlx5_dw_bit_off(typ, fld))
+#define __mlx5_st_sz_bits(typ) sizeof(struct mlx5_ifc_##typ##_bits)
+
+#define MLX5_FLD_SZ_BYTES(typ, fld) (__mlx5_bit_sz(typ, fld) / 8)
+#define MLX5_ST_SZ_BYTES(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 8)
+#define MLX5_ST_SZ_DW(typ) (sizeof(struct mlx5_ifc_##typ##_bits) / 32)
+#define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8)
+#define MLX5_ADDR_OF(typ, p, fld) ((char *)(p) + MLX5_BYTE_OFF(typ, fld))
+
+/* insert a value to a struct */
+#define MLX5_SET(typ, p, fld, v) do { \
+	BUILD_BUG_ON(__mlx5_st_sz_bits(typ) % 32);             \
+	*((__be32 *)(p) + __mlx5_dw_off(typ, fld)) = \
+	cpu_to_be32((be32_to_cpu(*((__be32 *)(p) + __mlx5_dw_off(typ, fld))) & \
+		     (~__mlx5_dw_mask(typ, fld))) | (((v) & __mlx5_mask(typ, fld)) \
+		     << __mlx5_dw_bit_off(typ, fld))); \
+} while (0)
+
+#define MLX5_GET(typ, p, fld) ((be32_to_cpu(*((__be32 *)(p) +\
+__mlx5_dw_off(typ, fld))) >> __mlx5_dw_bit_off(typ, fld)) & \
+__mlx5_mask(typ, fld))
+
+#define MLX5_GET_PR(typ, p, fld) ({ \
+	u32 ___t = MLX5_GET(typ, p, fld); \
+	pr_debug(#fld " = 0x%x\n", ___t); \
+	___t; \
+})
+
+#define MLX5_SET64(typ, p, fld, v) do { \
+	BUILD_BUG_ON(__mlx5_bit_sz(typ, fld) != 64); \
+	BUILD_BUG_ON(__mlx5_bit_off(typ, fld) % 64); \
+	*((__be64 *)(p) + __mlx5_64_off(typ, fld)) = cpu_to_be64(v); \
+} while (0)
+
+#define MLX5_GET64(typ, p, fld) be64_to_cpu(*((__be64 *)(p) + __mlx5_64_off(typ, fld)))
+
 enum {
 	MLX5_MAX_COMMANDS		= 32,
 	MLX5_CMD_DATA_BLOCK_SIZE	= 512,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 45a2add747e0..6f48dc793b9f 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -44,6 +44,7 @@
 
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/doorbell.h>
+#include <linux/mlx5/mlx5_ifc.h>
 
 enum {
 	MLX5_BOARD_ID_LEN = 64,
@@ -98,81 +99,6 @@ enum {
 	MLX5_ATOMIC_MODE_256B		= 8 << 16,
 };
 
-enum {
-	MLX5_CMD_OP_QUERY_HCA_CAP		= 0x100,
-	MLX5_CMD_OP_QUERY_ADAPTER		= 0x101,
-	MLX5_CMD_OP_INIT_HCA			= 0x102,
-	MLX5_CMD_OP_TEARDOWN_HCA		= 0x103,
-	MLX5_CMD_OP_ENABLE_HCA			= 0x104,
-	MLX5_CMD_OP_DISABLE_HCA			= 0x105,
-	MLX5_CMD_OP_QUERY_PAGES			= 0x107,
-	MLX5_CMD_OP_MANAGE_PAGES		= 0x108,
-	MLX5_CMD_OP_SET_HCA_CAP			= 0x109,
-
-	MLX5_CMD_OP_CREATE_MKEY			= 0x200,
-	MLX5_CMD_OP_QUERY_MKEY			= 0x201,
-	MLX5_CMD_OP_DESTROY_MKEY		= 0x202,
-	MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS	= 0x203,
-
-	MLX5_CMD_OP_CREATE_EQ			= 0x301,
-	MLX5_CMD_OP_DESTROY_EQ			= 0x302,
-	MLX5_CMD_OP_QUERY_EQ			= 0x303,
-
-	MLX5_CMD_OP_CREATE_CQ			= 0x400,
-	MLX5_CMD_OP_DESTROY_CQ			= 0x401,
-	MLX5_CMD_OP_QUERY_CQ			= 0x402,
-	MLX5_CMD_OP_MODIFY_CQ			= 0x403,
-
-	MLX5_CMD_OP_CREATE_QP			= 0x500,
-	MLX5_CMD_OP_DESTROY_QP			= 0x501,
-	MLX5_CMD_OP_RST2INIT_QP			= 0x502,
-	MLX5_CMD_OP_INIT2RTR_QP			= 0x503,
-	MLX5_CMD_OP_RTR2RTS_QP			= 0x504,
-	MLX5_CMD_OP_RTS2RTS_QP			= 0x505,
-	MLX5_CMD_OP_SQERR2RTS_QP		= 0x506,
-	MLX5_CMD_OP_2ERR_QP			= 0x507,
-	MLX5_CMD_OP_RTS2SQD_QP			= 0x508,
-	MLX5_CMD_OP_SQD2RTS_QP			= 0x509,
-	MLX5_CMD_OP_2RST_QP			= 0x50a,
-	MLX5_CMD_OP_QUERY_QP			= 0x50b,
-	MLX5_CMD_OP_CONF_SQP			= 0x50c,
-	MLX5_CMD_OP_MAD_IFC			= 0x50d,
-	MLX5_CMD_OP_INIT2INIT_QP		= 0x50e,
-	MLX5_CMD_OP_SUSPEND_QP			= 0x50f,
-	MLX5_CMD_OP_UNSUSPEND_QP		= 0x510,
-	MLX5_CMD_OP_SQD2SQD_QP			= 0x511,
-	MLX5_CMD_OP_ALLOC_QP_COUNTER_SET	= 0x512,
-	MLX5_CMD_OP_DEALLOC_QP_COUNTER_SET	= 0x513,
-	MLX5_CMD_OP_QUERY_QP_COUNTER_SET	= 0x514,
-
-	MLX5_CMD_OP_CREATE_PSV			= 0x600,
-	MLX5_CMD_OP_DESTROY_PSV			= 0x601,
-	MLX5_CMD_OP_QUERY_PSV			= 0x602,
-	MLX5_CMD_OP_QUERY_SIG_RULE_TABLE	= 0x603,
-	MLX5_CMD_OP_QUERY_BLOCK_SIZE_TABLE	= 0x604,
-
-	MLX5_CMD_OP_CREATE_SRQ			= 0x700,
-	MLX5_CMD_OP_DESTROY_SRQ			= 0x701,
-	MLX5_CMD_OP_QUERY_SRQ			= 0x702,
-	MLX5_CMD_OP_ARM_RQ			= 0x703,
-	MLX5_CMD_OP_RESIZE_SRQ			= 0x704,
-
-	MLX5_CMD_OP_ALLOC_PD			= 0x800,
-	MLX5_CMD_OP_DEALLOC_PD			= 0x801,
-	MLX5_CMD_OP_ALLOC_UAR			= 0x802,
-	MLX5_CMD_OP_DEALLOC_UAR			= 0x803,
-
-	MLX5_CMD_OP_ATTACH_TO_MCG		= 0x806,
-	MLX5_CMD_OP_DETACH_FROM_MCG		= 0x807,
-
-
-	MLX5_CMD_OP_ALLOC_XRCD			= 0x80e,
-	MLX5_CMD_OP_DEALLOC_XRCD		= 0x80f,
-
-	MLX5_CMD_OP_ACCESS_REG			= 0x805,
-	MLX5_CMD_OP_MAX				= 0x810,
-};
-
 enum {
 	MLX5_REG_PCAP		 = 0x5001,
 	MLX5_REG_PMTU		 = 0x5003,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
new file mode 100644
index 000000000000..df3bd9b5fbcf
--- /dev/null
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -0,0 +1,143 @@
+/*
+ * Copyright (c) 2014, Mellanox Technologies inc.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef MLX5_IFC_H
+#define MLX5_IFC_H
+
+enum {
+	MLX5_CMD_OP_QUERY_HCA_CAP                 = 0x100,
+	MLX5_CMD_OP_QUERY_ADAPTER                 = 0x101,
+	MLX5_CMD_OP_INIT_HCA                      = 0x102,
+	MLX5_CMD_OP_TEARDOWN_HCA                  = 0x103,
+	MLX5_CMD_OP_ENABLE_HCA                    = 0x104,
+	MLX5_CMD_OP_DISABLE_HCA                   = 0x105,
+	MLX5_CMD_OP_QUERY_PAGES                   = 0x107,
+	MLX5_CMD_OP_MANAGE_PAGES                  = 0x108,
+	MLX5_CMD_OP_SET_HCA_CAP                   = 0x109,
+	MLX5_CMD_OP_CREATE_MKEY                   = 0x200,
+	MLX5_CMD_OP_QUERY_MKEY                    = 0x201,
+	MLX5_CMD_OP_DESTROY_MKEY                  = 0x202,
+	MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS        = 0x203,
+	MLX5_CMD_OP_PAGE_FAULT_RESUME             = 0x204,
+	MLX5_CMD_OP_CREATE_EQ                     = 0x301,
+	MLX5_CMD_OP_DESTROY_EQ                    = 0x302,
+	MLX5_CMD_OP_QUERY_EQ                      = 0x303,
+	MLX5_CMD_OP_GEN_EQE                       = 0x304,
+	MLX5_CMD_OP_CREATE_CQ                     = 0x400,
+	MLX5_CMD_OP_DESTROY_CQ                    = 0x401,
+	MLX5_CMD_OP_QUERY_CQ                      = 0x402,
+	MLX5_CMD_OP_MODIFY_CQ                     = 0x403,
+	MLX5_CMD_OP_CREATE_QP                     = 0x500,
+	MLX5_CMD_OP_DESTROY_QP                    = 0x501,
+	MLX5_CMD_OP_RST2INIT_QP                   = 0x502,
+	MLX5_CMD_OP_INIT2RTR_QP                   = 0x503,
+	MLX5_CMD_OP_RTR2RTS_QP                    = 0x504,
+	MLX5_CMD_OP_RTS2RTS_QP                    = 0x505,
+	MLX5_CMD_OP_SQERR2RTS_QP                  = 0x506,
+	MLX5_CMD_OP_2ERR_QP                       = 0x507,
+	MLX5_CMD_OP_2RST_QP                       = 0x50a,
+	MLX5_CMD_OP_QUERY_QP                      = 0x50b,
+	MLX5_CMD_OP_INIT2INIT_QP                  = 0x50e,
+	MLX5_CMD_OP_CREATE_PSV                    = 0x600,
+	MLX5_CMD_OP_DESTROY_PSV                   = 0x601,
+	MLX5_CMD_OP_CREATE_SRQ                    = 0x700,
+	MLX5_CMD_OP_DESTROY_SRQ                   = 0x701,
+	MLX5_CMD_OP_QUERY_SRQ                     = 0x702,
+	MLX5_CMD_OP_ARM_RQ                        = 0x703,
+	MLX5_CMD_OP_RESIZE_SRQ                    = 0x704,
+	MLX5_CMD_OP_CREATE_DCT                    = 0x710,
+	MLX5_CMD_OP_DESTROY_DCT                   = 0x711,
+	MLX5_CMD_OP_DRAIN_DCT                     = 0x712,
+	MLX5_CMD_OP_QUERY_DCT                     = 0x713,
+	MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION     = 0x714,
+	MLX5_CMD_OP_QUERY_VPORT_STATE             = 0x750,
+	MLX5_CMD_OP_MODIFY_VPORT_STATE            = 0x751,
+	MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT       = 0x752,
+	MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT      = 0x753,
+	MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT       = 0x754,
+	MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT      = 0x755,
+	MLX5_CMD_OP_QUERY_RCOE_ADDRESS            = 0x760,
+	MLX5_CMD_OP_SET_ROCE_ADDRESS              = 0x761,
+	MLX5_CMD_OP_QUERY_VPORT_COUNTER           = 0x770,
+	MLX5_CMD_OP_ALLOC_Q_COUNTER               = 0x771,
+	MLX5_CMD_OP_DEALLOC_Q_COUNTER             = 0x772,
+	MLX5_CMD_OP_QUERY_Q_COUNTER               = 0x773,
+	MLX5_CMD_OP_ALLOC_PD                      = 0x800,
+	MLX5_CMD_OP_DEALLOC_PD                    = 0x801,
+	MLX5_CMD_OP_ALLOC_UAR                     = 0x802,
+	MLX5_CMD_OP_DEALLOC_UAR                   = 0x803,
+	MLX5_CMD_OP_CONFIG_INT_MODERATION         = 0x804,
+	MLX5_CMD_OP_ACCESS_REG                    = 0x805,
+	MLX5_CMD_OP_ATTACH_TO_MCG                 = 0x806,
+	MLX5_CMD_OP_DETACH_FROM_MCG               = 0x807,
+	MLX5_CMD_OP_GET_DROPPED_PACKET_LOG        = 0x80a,
+	MLX5_CMD_OP_MAD_IFC                       = 0x50d,
+	MLX5_CMD_OP_QUERY_MAD_DEMUX               = 0x80b,
+	MLX5_CMD_OP_SET_MAD_DEMUX                 = 0x80c,
+	MLX5_CMD_OP_NOP                           = 0x80d,
+	MLX5_CMD_OP_ALLOC_XRCD                    = 0x80e,
+	MLX5_CMD_OP_DEALLOC_XRCD                  = 0x80f,
+	MLX5_CMD_OP_SET_BURST_SIZE                = 0x812,
+	MLX5_CMD_OP_QUERY_BURST_SZIE              = 0x813,
+	MLX5_CMD_OP_ACTIVATE_TRACER               = 0x814,
+	MLX5_CMD_OP_DEACTIVATE_TRACER             = 0x815,
+	MLX5_CMD_OP_CREATE_SNIFFER_RULE           = 0x820,
+	MLX5_CMD_OP_DESTROY_SNIFFER_RULE          = 0x821,
+	MLX5_CMD_OP_QUERY_CONG_PARAMS             = 0x822,
+	MLX5_CMD_OP_MODIFY_CONG_PARAMS            = 0x823,
+	MLX5_CMD_OP_QUERY_CONG_STATISTICS         = 0x824,
+	MLX5_CMD_OP_CREATE_TIR                    = 0x900,
+	MLX5_CMD_OP_MODIFY_TIR                    = 0x901,
+	MLX5_CMD_OP_DESTROY_TIR                   = 0x902,
+	MLX5_CMD_OP_QUERY_TIR                     = 0x903,
+	MLX5_CMD_OP_CREATE_TIS                    = 0x912,
+	MLX5_CMD_OP_MODIFY_TIS                    = 0x913,
+	MLX5_CMD_OP_DESTROY_TIS                   = 0x914,
+	MLX5_CMD_OP_QUERY_TIS                     = 0x915,
+	MLX5_CMD_OP_CREATE_SQ                     = 0x904,
+	MLX5_CMD_OP_MODIFY_SQ                     = 0x905,
+	MLX5_CMD_OP_DESTROY_SQ                    = 0x906,
+	MLX5_CMD_OP_QUERY_SQ                      = 0x907,
+	MLX5_CMD_OP_CREATE_RQ                     = 0x908,
+	MLX5_CMD_OP_MODIFY_RQ                     = 0x909,
+	MLX5_CMD_OP_DESTROY_RQ                    = 0x90a,
+	MLX5_CMD_OP_QUERY_RQ                      = 0x90b,
+	MLX5_CMD_OP_CREATE_RMP                    = 0x90c,
+	MLX5_CMD_OP_MODIFY_RMP                    = 0x90d,
+	MLX5_CMD_OP_DESTROY_RMP                   = 0x90e,
+	MLX5_CMD_OP_QUERY_RMP                     = 0x90f,
+	MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY          = 0x910,
+	MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY        = 0x911,
+	MLX5_CMD_OP_MAX				  = 0x911
+};
+
+#endif /* MLX5_IFC_H */
-- 
cgit v1.2.3


From b775516b042f9e35f856bd2914afefd9d23021d7 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Thu, 2 Oct 2014 12:19:44 +0300
Subject: net/mlx5_core: use set/get macros in device caps

Transform device capabilities related commands to use set/get macros to
manipulate command mailboxes.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c  |  17 ++
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 150 +++++++++---------
 include/linux/mlx5/device.h                    |  92 -----------
 include/linux/mlx5/driver.h                    |   1 +
 include/linux/mlx5/mlx5_ifc.h                  | 206 +++++++++++++++++++++++++
 5 files changed, 298 insertions(+), 168 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3ecef1310bae..368c6c5ea014 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1537,3 +1537,20 @@ int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr)
 
 	return cmd_status_to_err(hdr->status);
 }
+
+int mlx5_cmd_status_to_err_v2(void *ptr)
+{
+	u32	syndrome;
+	u8	status;
+
+	status = be32_to_cpu(*(__be32 *)ptr) >> 24;
+	if (!status)
+		return 0;
+
+	syndrome = be32_to_cpu(*(__be32 *)(ptr + 4));
+
+	pr_warn("command failed, status %s(0x%x), syndrome 0x%x\n",
+		cmd_status_str(status), status, syndrome);
+
+	return cmd_status_to_err(status);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d9f74618befa..b9e3259e415f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -43,6 +43,7 @@
 #include <linux/mlx5/qp.h>
 #include <linux/mlx5/srq.h>
 #include <linux/debugfs.h>
+#include <linux/mlx5/mlx5_ifc.h>
 #include "mlx5_core.h"
 
 #define DRIVER_NAME "mlx5_core"
@@ -277,18 +278,20 @@ static u16 to_fw_pkey_sz(u32 size)
 
 /* selectively copy writable fields clearing any reserved area
  */
-static void copy_rw_fields(struct mlx5_hca_cap *to, struct mlx5_general_caps *from)
+static void copy_rw_fields(void *to, struct mlx5_caps *from)
 {
+	__be64 *flags_off = (__be64 *)MLX5_ADDR_OF(cmd_hca_cap, to, reserved_22);
 	u64 v64;
 
-	to->log_max_qp = from->log_max_qp & 0x1f;
-	to->log_max_ra_req_dc = from->log_max_ra_req_dc & 0x3f;
-	to->log_max_ra_res_dc = from->log_max_ra_res_dc & 0x3f;
-	to->log_max_ra_req_qp = from->log_max_ra_req_qp & 0x3f;
-	to->log_max_ra_res_qp = from->log_max_ra_res_qp & 0x3f;
-	to->pkey_table_size = cpu_to_be16(to_fw_pkey_sz(from->pkey_table_size));
-	v64 = from->flags & MLX5_CAP_BITS_RW_MASK;
-	to->flags = cpu_to_be64(v64);
+	MLX5_SET(cmd_hca_cap, to, log_max_qp, from->gen.log_max_qp);
+	MLX5_SET(cmd_hca_cap, to, log_max_ra_req_qp, from->gen.log_max_ra_req_qp);
+	MLX5_SET(cmd_hca_cap, to, log_max_ra_res_qp, from->gen.log_max_ra_res_qp);
+	MLX5_SET(cmd_hca_cap, to, pkey_table_size, from->gen.pkey_table_size);
+	MLX5_SET(cmd_hca_cap, to, log_max_ra_req_dc, from->gen.log_max_ra_req_dc);
+	MLX5_SET(cmd_hca_cap, to, log_max_ra_res_dc, from->gen.log_max_ra_res_dc);
+	MLX5_SET(cmd_hca_cap, to, pkey_table_size, to_fw_pkey_sz(from->gen.pkey_table_size));
+	v64 = from->gen.flags & MLX5_CAP_BITS_RW_MASK;
+	*flags_off = cpu_to_be64(v64);
 }
 
 static u16 get_pkey_table_size(int pkey)
@@ -299,55 +302,47 @@ static u16 get_pkey_table_size(int pkey)
 	return MLX5_MIN_PKEY_TABLE_SIZE << pkey;
 }
 
-static void fw2drv_caps(struct mlx5_caps *caps,
-			struct mlx5_cmd_query_hca_cap_mbox_out *out)
+static void fw2drv_caps(struct mlx5_caps *caps, void *out)
 {
 	struct mlx5_general_caps *gen = &caps->gen;
-	u16 t16;
-
-	gen->max_srq_wqes = 1 << out->hca_cap.log_max_srq_sz;
-	gen->max_wqes = 1 << out->hca_cap.log_max_qp_sz;
-	gen->log_max_qp = out->hca_cap.log_max_qp & 0x1f;
-	gen->log_max_strq = out->hca_cap.log_max_strq_sz;
-	gen->log_max_srq = out->hca_cap.log_max_srqs & 0x1f;
-	gen->max_cqes = 1 << out->hca_cap.log_max_cq_sz;
-	gen->log_max_cq = out->hca_cap.log_max_cq & 0x1f;
-	gen->max_eqes = out->hca_cap.log_max_eq_sz;
-	gen->log_max_mkey = out->hca_cap.log_max_mkey & 0x3f;
-	gen->log_max_eq = out->hca_cap.log_max_eq & 0xf;
-	gen->max_indirection = out->hca_cap.max_indirection;
-	gen->log_max_mrw_sz = out->hca_cap.log_max_mrw_sz;
-	gen->log_max_bsf_list_size = 0;
-	gen->log_max_klm_list_size = 0;
-	gen->log_max_ra_req_dc = out->hca_cap.log_max_ra_req_dc;
-	gen->log_max_ra_res_dc = out->hca_cap.log_max_ra_res_dc;
-	gen->log_max_ra_req_qp = out->hca_cap.log_max_ra_req_qp;
-	gen->log_max_ra_res_qp = out->hca_cap.log_max_ra_res_qp;
-	gen->max_qp_counters = be16_to_cpu(out->hca_cap.max_qp_count);
-	gen->pkey_table_size = get_pkey_table_size(be16_to_cpu(out->hca_cap.pkey_table_size));
-	gen->local_ca_ack_delay = out->hca_cap.local_ca_ack_delay & 0x1f;
-	gen->num_ports = out->hca_cap.num_ports & 0xf;
-	gen->log_max_msg = out->hca_cap.log_max_msg & 0x1f;
-	gen->stat_rate_support = be16_to_cpu(out->hca_cap.stat_rate_support);
-	gen->flags = be64_to_cpu(out->hca_cap.flags);
-	pr_debug("flags = 0x%llx\n", gen->flags);
-	gen->uar_sz = out->hca_cap.uar_sz;
-	gen->min_log_pg_sz = out->hca_cap.log_pg_sz;
 
-	t16 = be16_to_cpu(out->hca_cap.bf_log_bf_reg_size);
-	if (t16 & 0x8000) {
-		gen->bf_reg_size = 1 << (t16 & 0x1f);
-		gen->bf_regs_per_page = MLX5_BF_REGS_PER_PAGE;
-	} else {
-		gen->bf_reg_size = 0;
-		gen->bf_regs_per_page = 0;
-	}
-	gen->max_sq_desc_sz = be16_to_cpu(out->hca_cap.max_desc_sz_sq);
-	gen->max_rq_desc_sz = be16_to_cpu(out->hca_cap.max_desc_sz_rq);
-	gen->max_qp_mcg = be32_to_cpu(out->hca_cap.max_qp_mcg) & 0xffffff;
-	gen->log_max_pd = out->hca_cap.log_max_pd & 0x1f;
-	gen->log_max_xrcd = out->hca_cap.log_max_xrcd;
-	gen->log_uar_page_sz = be16_to_cpu(out->hca_cap.log_uar_page_sz);
+	gen->max_srq_wqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_srq_sz);
+	gen->max_wqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_qp_sz);
+	gen->log_max_qp = MLX5_GET_PR(cmd_hca_cap, out, log_max_qp);
+	gen->log_max_strq = MLX5_GET_PR(cmd_hca_cap, out, log_max_strq_sz);
+	gen->log_max_srq = MLX5_GET_PR(cmd_hca_cap, out, log_max_srqs);
+	gen->max_cqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_cq_sz);
+	gen->log_max_cq = MLX5_GET_PR(cmd_hca_cap, out, log_max_cq);
+	gen->max_eqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_eq_sz);
+	gen->log_max_mkey = MLX5_GET_PR(cmd_hca_cap, out, log_max_mkey);
+	gen->log_max_eq = MLX5_GET_PR(cmd_hca_cap, out, log_max_eq);
+	gen->max_indirection = MLX5_GET_PR(cmd_hca_cap, out, max_indirection);
+	gen->log_max_mrw_sz = MLX5_GET_PR(cmd_hca_cap, out, log_max_mrw_sz);
+	gen->log_max_bsf_list_size = MLX5_GET_PR(cmd_hca_cap, out, log_max_bsf_list_size);
+	gen->log_max_klm_list_size = MLX5_GET_PR(cmd_hca_cap, out, log_max_klm_list_size);
+	gen->log_max_ra_req_dc = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_req_dc);
+	gen->log_max_ra_res_dc = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_res_dc);
+	gen->log_max_ra_req_qp = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_req_qp);
+	gen->log_max_ra_res_qp = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_res_qp);
+	gen->max_qp_counters = MLX5_GET_PR(cmd_hca_cap, out, max_qp_cnt);
+	gen->pkey_table_size = get_pkey_table_size(MLX5_GET_PR(cmd_hca_cap, out, pkey_table_size));
+	gen->local_ca_ack_delay = MLX5_GET_PR(cmd_hca_cap, out, local_ca_ack_delay);
+	gen->num_ports = MLX5_GET_PR(cmd_hca_cap, out, num_ports);
+	gen->log_max_msg = MLX5_GET_PR(cmd_hca_cap, out, log_max_msg);
+	gen->stat_rate_support = MLX5_GET_PR(cmd_hca_cap, out, stat_rate_support);
+	gen->flags = be64_to_cpu(*(__be64 *)MLX5_ADDR_OF(cmd_hca_cap, out, reserved_22));
+	pr_debug("flags = 0x%llx\n", gen->flags);
+	gen->uar_sz = MLX5_GET_PR(cmd_hca_cap, out, uar_sz);
+	gen->min_log_pg_sz = MLX5_GET_PR(cmd_hca_cap, out, log_pg_sz);
+	gen->bf_reg_size = MLX5_GET_PR(cmd_hca_cap, out, bf);
+	gen->bf_reg_size = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_bf_reg_size);
+	gen->max_sq_desc_sz = MLX5_GET_PR(cmd_hca_cap, out, max_wqe_sz_sq);
+	gen->max_rq_desc_sz = MLX5_GET_PR(cmd_hca_cap, out, max_wqe_sz_rq);
+	gen->max_dc_sq_desc_sz = MLX5_GET_PR(cmd_hca_cap, out, max_wqe_sz_sq_dc);
+	gen->max_qp_mcg = MLX5_GET_PR(cmd_hca_cap, out, max_qp_mcg);
+	gen->log_max_pd = MLX5_GET_PR(cmd_hca_cap, out, log_max_pd);
+	gen->log_max_xrcd = MLX5_GET_PR(cmd_hca_cap, out, log_max_xrcd);
+	gen->log_uar_page_sz = MLX5_GET_PR(cmd_hca_cap, out, log_uar_page_sz);
 }
 
 static const char *caps_opmod_str(u16 opmod)
@@ -365,59 +360,61 @@ static const char *caps_opmod_str(u16 opmod)
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps,
 		       u16 opmod)
 {
-	struct mlx5_cmd_query_hca_cap_mbox_out *out;
-	struct mlx5_cmd_query_hca_cap_mbox_in in;
+	u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)];
+	int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *out;
 	int err;
 
-	memset(&in, 0, sizeof(in));
-	out = kzalloc(sizeof(*out), GFP_KERNEL);
+	memset(in, 0, sizeof(in));
+	out = kzalloc(out_sz, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
+	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
+	MLX5_SET(query_hca_cap_in, in, op_mod, opmod);
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
+	if (err)
+		goto query_ex;
 
-	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_HCA_CAP);
-	in.hdr.opmod  = cpu_to_be16(opmod);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, sizeof(*out));
-
-	err = mlx5_cmd_status_to_err(&out->hdr);
+	err = mlx5_cmd_status_to_err_v2(out);
 	if (err) {
 		mlx5_core_warn(dev, "query max hca cap failed, %d\n", err);
 		goto query_ex;
 	}
 	mlx5_core_dbg(dev, "%s\n", caps_opmod_str(opmod));
-	fw2drv_caps(caps, out);
+	fw2drv_caps(caps, MLX5_ADDR_OF(query_hca_cap_out, out, capability_struct));
 
 query_ex:
 	kfree(out);
 	return err;
 }
 
-static int set_caps(struct mlx5_core_dev *dev,
-		    struct mlx5_cmd_set_hca_cap_mbox_in *in)
+static int set_caps(struct mlx5_core_dev *dev, void *in, int in_sz)
 {
-	struct mlx5_cmd_set_hca_cap_mbox_out out;
+	u32 out[MLX5_ST_SZ_DW(set_hca_cap_out)];
 	int err;
 
-	memset(&out, 0, sizeof(out));
+	memset(out, 0, sizeof(out));
 
-	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_SET_HCA_CAP);
-	err = mlx5_cmd_exec(dev, in, sizeof(*in), &out, sizeof(out));
+	MLX5_SET(set_hca_cap_in, in, opcode, MLX5_CMD_OP_SET_HCA_CAP);
+	err = mlx5_cmd_exec(dev, in, in_sz, out, sizeof(out));
 	if (err)
 		return err;
 
-	err = mlx5_cmd_status_to_err(&out.hdr);
+	err = mlx5_cmd_status_to_err_v2(out);
 
 	return err;
 }
 
 static int handle_hca_cap(struct mlx5_core_dev *dev)
 {
-	struct mlx5_cmd_set_hca_cap_mbox_in *set_ctx = NULL;
+	void *set_ctx = NULL;
 	struct mlx5_profile *prof = dev->profile;
 	struct mlx5_caps *cur_caps = NULL;
 	struct mlx5_caps *max_caps = NULL;
 	int err = -ENOMEM;
+	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
 
-	set_ctx = kzalloc(sizeof(*set_ctx), GFP_KERNEL);
+	set_ctx = kzalloc(set_sz, GFP_KERNEL);
 	if (!set_ctx)
 		goto query_ex;
 
@@ -446,8 +443,9 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 	/* disable checksum */
 	cur_caps->gen.flags &= ~MLX5_DEV_CAP_FLAG_CMDIF_CSUM;
 
-	copy_rw_fields(&set_ctx->hca_cap, &cur_caps->gen);
-	err = set_caps(dev, set_ctx);
+	copy_rw_fields(MLX5_ADDR_OF(set_hca_cap_in, set_ctx, hca_capability_struct),
+		       cur_caps);
+	err = set_caps(dev, set_ctx, set_sz);
 
 query_ex:
 	kfree(cur_caps);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 0032687f58c7..1d67fd32e71c 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -327,98 +327,6 @@ struct mlx5_cmd_query_adapter_mbox_out {
 	u8			vsd_psid[16];
 };
 
-struct mlx5_hca_cap {
-	u8	rsvd1[16];
-	u8	log_max_srq_sz;
-	u8	log_max_qp_sz;
-	u8	rsvd2;
-	u8	log_max_qp;
-	u8	log_max_strq_sz;
-	u8	log_max_srqs;
-	u8	rsvd4[2];
-	u8	rsvd5;
-	u8	log_max_cq_sz;
-	u8	rsvd6;
-	u8	log_max_cq;
-	u8	log_max_eq_sz;
-	u8	log_max_mkey;
-	u8	rsvd7;
-	u8	log_max_eq;
-	u8	max_indirection;
-	u8	log_max_mrw_sz;
-	u8	log_max_bsf_list_sz;
-	u8	log_max_klm_list_sz;
-	u8	rsvd_8_0;
-	u8	log_max_ra_req_dc;
-	u8	rsvd_8_1;
-	u8	log_max_ra_res_dc;
-	u8	rsvd9;
-	u8	log_max_ra_req_qp;
-	u8	rsvd10;
-	u8	log_max_ra_res_qp;
-	u8	pad_cap;
-	u8	rsvd11[3];
-	__be16	max_qp_count;
-	__be16	pkey_table_size;
-	u8	rsvd13;
-	u8	local_ca_ack_delay;
-	u8	rsvd14;
-	u8	num_ports;
-	u8	log_max_msg;
-	u8	rsvd15[3];
-	__be16	stat_rate_support;
-	u8	rsvd16[2];
-	__be64	flags;
-	u8	rsvd17;
-	u8	uar_sz;
-	u8	rsvd18;
-	u8	log_pg_sz;
-	__be16	bf_log_bf_reg_size;
-	u8	rsvd19[4];
-	__be16	max_desc_sz_sq;
-	u8	rsvd20[2];
-	__be16	max_desc_sz_rq;
-	u8	rsvd21[2];
-	__be16	max_desc_sz_sq_dc;
-	__be32	max_qp_mcg;
-	u8	rsvd22[3];
-	u8	log_max_mcg;
-	u8	rsvd23;
-	u8	log_max_pd;
-	u8	rsvd24;
-	u8	log_max_xrcd;
-	u8	rsvd25[42];
-	__be16  log_uar_page_sz;
-	u8	rsvd26[108];
-};
-
-
-struct mlx5_cmd_query_hca_cap_mbox_in {
-	struct mlx5_inbox_hdr	hdr;
-	u8			rsvd[8];
-};
-
-
-struct mlx5_cmd_query_hca_cap_mbox_out {
-	struct mlx5_outbox_hdr	hdr;
-	u8			rsvd0[8];
-	struct mlx5_hca_cap     hca_cap;
-};
-
-
-struct mlx5_cmd_set_hca_cap_mbox_in {
-	struct mlx5_inbox_hdr	hdr;
-	u8			rsvd[8];
-	struct mlx5_hca_cap     hca_cap;
-};
-
-
-struct mlx5_cmd_set_hca_cap_mbox_out {
-	struct mlx5_outbox_hdr	hdr;
-	u8			rsvd0[8];
-};
-
-
 struct mlx5_cmd_init_hca_mbox_in {
 	struct mlx5_inbox_hdr	hdr;
 	u8			rsvd0[2];
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6f48dc793b9f..c439f9c59b93 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -641,6 +641,7 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
 int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr);
+int mlx5_cmd_status_to_err_v2(void *ptr);
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps,
 		       u16 opmod);
 int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index df3bd9b5fbcf..5f48b8f592c5 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -140,4 +140,210 @@ enum {
 	MLX5_CMD_OP_MAX				  = 0x911
 };
 
+struct mlx5_ifc_cmd_hca_cap_bits {
+	u8         reserved_0[0x80];
+
+	u8         log_max_srq_sz[0x8];
+	u8         log_max_qp_sz[0x8];
+	u8         reserved_1[0xb];
+	u8         log_max_qp[0x5];
+
+	u8         log_max_strq_sz[0x8];
+	u8         reserved_2[0x3];
+	u8         log_max_srqs[0x5];
+	u8         reserved_3[0x10];
+
+	u8         reserved_4[0x8];
+	u8         log_max_cq_sz[0x8];
+	u8         reserved_5[0xb];
+	u8         log_max_cq[0x5];
+
+	u8         log_max_eq_sz[0x8];
+	u8         reserved_6[0x2];
+	u8         log_max_mkey[0x6];
+	u8         reserved_7[0xc];
+	u8         log_max_eq[0x4];
+
+	u8         max_indirection[0x8];
+	u8         reserved_8[0x1];
+	u8         log_max_mrw_sz[0x7];
+	u8         reserved_9[0x2];
+	u8         log_max_bsf_list_size[0x6];
+	u8         reserved_10[0x2];
+	u8         log_max_klm_list_size[0x6];
+
+	u8         reserved_11[0xa];
+	u8         log_max_ra_req_dc[0x6];
+	u8         reserved_12[0xa];
+	u8         log_max_ra_res_dc[0x6];
+
+	u8         reserved_13[0xa];
+	u8         log_max_ra_req_qp[0x6];
+	u8         reserved_14[0xa];
+	u8         log_max_ra_res_qp[0x6];
+
+	u8         pad_cap[0x1];
+	u8         cc_query_allowed[0x1];
+	u8         cc_modify_allowed[0x1];
+	u8         reserved_15[0x1d];
+
+	u8         reserved_16[0x6];
+	u8         max_qp_cnt[0xa];
+	u8         pkey_table_size[0x10];
+
+	u8         eswitch_owner[0x1];
+	u8         reserved_17[0xa];
+	u8         local_ca_ack_delay[0x5];
+	u8         reserved_18[0x8];
+	u8         num_ports[0x8];
+
+	u8         reserved_19[0x3];
+	u8         log_max_msg[0x5];
+	u8         reserved_20[0x18];
+
+	u8         stat_rate_support[0x10];
+	u8         reserved_21[0x10];
+
+	u8         reserved_22[0x10];
+	u8         cmdif_checksum[0x2];
+	u8         sigerr_cqe[0x1];
+	u8         reserved_23[0x1];
+	u8         wq_signature[0x1];
+	u8         sctr_data_cqe[0x1];
+	u8         reserved_24[0x1];
+	u8         sho[0x1];
+	u8         tph[0x1];
+	u8         rf[0x1];
+	u8         dc[0x1];
+	u8         reserved_25[0x2];
+	u8         roce[0x1];
+	u8         atomic[0x1];
+	u8         rsz_srq[0x1];
+
+	u8         cq_oi[0x1];
+	u8         cq_resize[0x1];
+	u8         cq_moderation[0x1];
+	u8         sniffer_rule_flow[0x1];
+	u8         sniffer_rule_vport[0x1];
+	u8         sniffer_rule_phy[0x1];
+	u8         reserved_26[0x1];
+	u8         pg[0x1];
+	u8         block_lb_mc[0x1];
+	u8         reserved_27[0x3];
+	u8         cd[0x1];
+	u8         reserved_28[0x1];
+	u8         apm[0x1];
+	u8         reserved_29[0x7];
+	u8         qkv[0x1];
+	u8         pkv[0x1];
+	u8         reserved_30[0x4];
+	u8         xrc[0x1];
+	u8         ud[0x1];
+	u8         uc[0x1];
+	u8         rc[0x1];
+
+	u8         reserved_31[0xa];
+	u8         uar_sz[0x6];
+	u8         reserved_32[0x8];
+	u8         log_pg_sz[0x8];
+
+	u8         bf[0x1];
+	u8         reserved_33[0xa];
+	u8         log_bf_reg_size[0x5];
+	u8         reserved_34[0x10];
+
+	u8         reserved_35[0x10];
+	u8         max_wqe_sz_sq[0x10];
+
+	u8         reserved_36[0x10];
+	u8         max_wqe_sz_rq[0x10];
+
+	u8         reserved_37[0x10];
+	u8         max_wqe_sz_sq_dc[0x10];
+
+	u8         reserved_38[0x7];
+	u8         max_qp_mcg[0x19];
+
+	u8         reserved_39[0x18];
+	u8         log_max_mcg[0x8];
+
+	u8         reserved_40[0xb];
+	u8         log_max_pd[0x5];
+	u8         reserved_41[0xb];
+	u8         log_max_xrcd[0x5];
+
+	u8         reserved_42[0x20];
+
+	u8         reserved_43[0x3];
+	u8         log_max_rq[0x5];
+	u8         reserved_44[0x3];
+	u8         log_max_sq[0x5];
+	u8         reserved_45[0x3];
+	u8         log_max_tir[0x5];
+	u8         reserved_46[0x3];
+	u8         log_max_tis[0x5];
+
+	u8         reserved_47[0x13];
+	u8         log_max_rq_per_tir[0x5];
+	u8         reserved_48[0x3];
+	u8         log_max_tis_per_sq[0x5];
+
+	u8         reserved_49[0xe0];
+
+	u8         reserved_50[0x10];
+	u8         log_uar_page_sz[0x10];
+
+	u8         reserved_51[0x100];
+
+	u8         reserved_52[0x1f];
+	u8         cqe_zip[0x1];
+
+	u8         cqe_zip_timeout[0x10];
+	u8         cqe_zip_max_num[0x10];
+
+	u8         reserved_53[0x220];
+};
+
+struct mlx5_ifc_set_hca_cap_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_0[0x10];
+
+	u8         reserved_1[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_2[0x40];
+
+	struct mlx5_ifc_cmd_hca_cap_bits hca_capability_struct;
+};
+
+struct mlx5_ifc_query_hca_cap_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_0[0x10];
+
+	u8         reserved_1[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_2[0x40];
+};
+
+struct mlx5_ifc_query_hca_cap_out_bits {
+	u8         status[0x8];
+	u8         reserved_0[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_1[0x40];
+
+	u8         capability_struct[256][0x8];
+};
+
+struct mlx5_ifc_set_hca_cap_out_bits {
+	u8         status[0x8];
+	u8         reserved_0[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_1[0x40];
+};
+
 #endif /* MLX5_IFC_H */
-- 
cgit v1.2.3


From 5903325a64834211daf63a62db3b35ee580cb8bf Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Thu, 2 Oct 2014 12:19:45 +0300
Subject: net/mlx5_core: Identify resources by their type

This patch puts a common part as the first field of mlx5_core_qp. This field is
used to identify which resource generated an event. This is required since upcoming
new resource types such as DC targets are allocated for the same numerical space
as regular QPs and may generate the same events. By searching the resource in the
same table we can then look at the common field to identify the resource.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 12 +++---
 drivers/net/ethernet/mellanox/mlx5/core/qp.c | 57 ++++++++++++++++++++--------
 include/linux/mlx5/driver.h                  | 13 ++++++-
 include/linux/mlx5/qp.h                      |  3 +-
 4 files changed, 60 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 11b9b840ad4d..ed53291468f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -198,7 +198,7 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 	int eqes_found = 0;
 	int set_ci = 0;
 	u32 cqn;
-	u32 srqn;
+	u32 rsn;
 	u8 port;
 
 	while ((eqe = next_eqe_sw(eq))) {
@@ -224,18 +224,18 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 		case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
 		case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
 		case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+			rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
 			mlx5_core_dbg(dev, "event %s(%d) arrived\n",
 				      eqe_type_str(eqe->type), eqe->type);
-			mlx5_qp_event(dev, be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff,
-				      eqe->type);
+			mlx5_rsc_event(dev, rsn, eqe->type);
 			break;
 
 		case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
 		case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
-			srqn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
+			rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
 			mlx5_core_dbg(dev, "SRQ event %s(%d): srqn 0x%x\n",
-				      eqe_type_str(eqe->type), eqe->type, srqn);
-			mlx5_srq_event(dev, srqn, eqe->type);
+				      eqe_type_str(eqe->type), eqe->type, rsn);
+			mlx5_srq_event(dev, rsn, eqe->type);
 			break;
 
 		case MLX5_EVENT_TYPE_CMD:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 415b67ce379e..5261a2b0da43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -39,28 +39,53 @@
 
 #include "mlx5_core.h"
 
-void mlx5_qp_event(struct mlx5_core_dev *dev, u32 qpn, int event_type)
+static struct mlx5_core_rsc_common *mlx5_get_rsc(struct mlx5_core_dev *dev,
+						 u32 rsn)
 {
 	struct mlx5_qp_table *table = &dev->priv.qp_table;
-	struct mlx5_core_qp *qp;
+	struct mlx5_core_rsc_common *common;
 
 	spin_lock(&table->lock);
 
-	qp = radix_tree_lookup(&table->tree, qpn);
-	if (qp)
-		atomic_inc(&qp->refcount);
+	common = radix_tree_lookup(&table->tree, rsn);
+	if (common)
+		atomic_inc(&common->refcount);
 
 	spin_unlock(&table->lock);
 
-	if (!qp) {
-		mlx5_core_warn(dev, "Async event for bogus QP 0x%x\n", qpn);
-		return;
+	if (!common) {
+		mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n",
+			       rsn);
+		return NULL;
 	}
+	return common;
+}
 
-	qp->event(qp, event_type);
+void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common)
+{
+	if (atomic_dec_and_test(&common->refcount))
+		complete(&common->free);
+}
+
+void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
+{
+	struct mlx5_core_rsc_common *common = mlx5_get_rsc(dev, rsn);
+	struct mlx5_core_qp *qp;
+
+	if (!common)
+		return;
+
+	switch (common->res) {
+	case MLX5_RES_QP:
+		qp = (struct mlx5_core_qp *)common;
+		qp->event(qp, event_type);
+		break;
+
+	default:
+		mlx5_core_warn(dev, "invalid resource type for 0x%x\n", rsn);
+	}
 
-	if (atomic_dec_and_test(&qp->refcount))
-		complete(&qp->free);
+	mlx5_core_put_rsc(common);
 }
 
 int mlx5_core_create_qp(struct mlx5_core_dev *dev,
@@ -92,6 +117,7 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 	qp->qpn = be32_to_cpu(out.qpn) & 0xffffff;
 	mlx5_core_dbg(dev, "qpn = 0x%x\n", qp->qpn);
 
+	qp->common.res = MLX5_RES_QP;
 	spin_lock_irq(&table->lock);
 	err = radix_tree_insert(&table->tree, qp->qpn, qp);
 	spin_unlock_irq(&table->lock);
@@ -106,9 +132,9 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 			      qp->qpn);
 
 	qp->pid = current->pid;
-	atomic_set(&qp->refcount, 1);
+	atomic_set(&qp->common.refcount, 1);
 	atomic_inc(&dev->num_qps);
-	init_completion(&qp->free);
+	init_completion(&qp->common.free);
 
 	return 0;
 
@@ -138,9 +164,8 @@ int mlx5_core_destroy_qp(struct mlx5_core_dev *dev,
 	radix_tree_delete(&table->tree, qp->qpn);
 	spin_unlock_irqrestore(&table->lock, flags);
 
-	if (atomic_dec_and_test(&qp->refcount))
-		complete(&qp->free);
-	wait_for_completion(&qp->free);
+	mlx5_core_put_rsc((struct mlx5_core_rsc_common *)qp);
+	wait_for_completion(&qp->common.free);
 
 	memset(&in, 0, sizeof(in));
 	memset(&out, 0, sizeof(out));
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c439f9c59b93..246310dc8bef 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -375,6 +375,16 @@ struct mlx5_core_mr {
 	u32			pd;
 };
 
+enum mlx5_res_type {
+	MLX5_RES_QP,
+};
+
+struct mlx5_core_rsc_common {
+	enum mlx5_res_type	res;
+	atomic_t		refcount;
+	struct completion	free;
+};
+
 struct mlx5_core_srq {
 	u32		srqn;
 	int		max;
@@ -700,7 +710,7 @@ int mlx5_eq_init(struct mlx5_core_dev *dev);
 void mlx5_eq_cleanup(struct mlx5_core_dev *dev);
 void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas);
 void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn);
-void mlx5_qp_event(struct mlx5_core_dev *dev, u32 qpn, int event_type);
+void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
 void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);
 struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
 void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector);
@@ -737,6 +747,7 @@ void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev);
 int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
 			 int npsvs, u32 *sig_index);
 int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num);
+void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common);
 
 static inline u32 mlx5_mkey_to_idx(u32 mkey)
 {
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 9709b30e2d69..7c4c0f1f5805 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -342,10 +342,9 @@ struct mlx5_stride_block_ctrl_seg {
 };
 
 struct mlx5_core_qp {
+	struct mlx5_core_rsc_common	common; /* must be first */
 	void (*event)		(struct mlx5_core_qp *, int);
 	int			qpn;
-	atomic_t		refcount;
-	struct completion	free;
 	struct mlx5_rsc_debug	*dbg;
 	int			pid;
 };
-- 
cgit v1.2.3


From efc98d08e1ec4fd131f794370b274dceaf32c958 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Fri, 3 Oct 2014 15:48:08 -0700
Subject: fou: eliminate IPv4,v6 specific GRO functions

This patch removes fou[46]_gro_receive and fou[46]_gro_complete
functions. The v4 or v6 variants were chosen for the UDP offloads
based on the address family of the socket this is not necessary
or correct. Alternatively, this patch adds is_ipv6 to napi_gro_skb.
This is set in udp6_gro_receive and unset in udp4_gro_receive. In
fou_gro_receive the value is used to select the correct inet_offloads
for the protocol of the outer IP header.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  3 +++
 net/ipv4/fou.c            | 48 ++++++++---------------------------------------
 net/ipv4/udp_offload.c    |  1 +
 net/ipv6/udp_offload.c    |  1 +
 4 files changed, 13 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 910fb17ad148..22d54b9b700d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1886,6 +1886,9 @@ struct napi_gro_cb {
 	/* Number of checksums via CHECKSUM_UNNECESSARY */
 	u8	csum_cnt:3;
 
+	/* Used in foo-over-udp, set in udp[46]_gro_receive */
+	u8	is_ipv6:1;
+
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
 
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index dced89fbe480..7e2126a31f2e 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -65,14 +65,15 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 }
 
 static struct sk_buff **fou_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb,
-					const struct net_offload **offloads)
+					struct sk_buff *skb)
 {
 	const struct net_offload *ops;
 	struct sk_buff **pp = NULL;
 	u8 proto = NAPI_GRO_CB(skb)->proto;
+	const struct net_offload **offloads;
 
 	rcu_read_lock();
+	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
 	ops = rcu_dereference(offloads[proto]);
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out_unlock;
@@ -85,14 +86,15 @@ out_unlock:
 	return pp;
 }
 
-static int fou_gro_complete(struct sk_buff *skb, int nhoff,
-			    const struct net_offload **offloads)
+static int fou_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;
 	u8 proto = NAPI_GRO_CB(skb)->proto;
 	int err = -ENOSYS;
+	const struct net_offload **offloads;
 
 	rcu_read_lock();
+	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
 	ops = rcu_dereference(offloads[proto]);
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out_unlock;
@@ -105,28 +107,6 @@ out_unlock:
 	return err;
 }
 
-static struct sk_buff **fou4_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
-{
-	return fou_gro_receive(head, skb, inet_offloads);
-}
-
-static int fou4_gro_complete(struct sk_buff *skb, int nhoff)
-{
-	return fou_gro_complete(skb, nhoff, inet_offloads);
-}
-
-static struct sk_buff **fou6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
-{
-	return fou_gro_receive(head, skb, inet6_offloads);
-}
-
-static int fou6_gro_complete(struct sk_buff *skb, int nhoff)
-{
-	return fou_gro_complete(skb, nhoff, inet6_offloads);
-}
-
 static int fou_add_to_port_list(struct fou *fou)
 {
 	struct fou *fout;
@@ -199,20 +179,8 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 
 	sk->sk_allocation = GFP_ATOMIC;
 
-	switch (cfg->udp_config.family) {
-	case AF_INET:
-		fou->udp_offloads.callbacks.gro_receive = fou4_gro_receive;
-		fou->udp_offloads.callbacks.gro_complete = fou4_gro_complete;
-		break;
-	case AF_INET6:
-		fou->udp_offloads.callbacks.gro_receive = fou6_gro_receive;
-		fou->udp_offloads.callbacks.gro_complete = fou6_gro_complete;
-		break;
-	default:
-		err = -EPFNOSUPPORT;
-		goto error;
-	}
-
+	fou->udp_offloads.callbacks.gro_receive = fou_gro_receive;
+	fou->udp_offloads.callbacks.gro_complete = fou_gro_complete;
 	fou->udp_offloads.port = cfg->udp_config.local_udp_port;
 	fou->udp_offloads.ipproto = cfg->protocol;
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 8c35f2c939ee..507310ef4b56 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -334,6 +334,7 @@ static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
 		skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
 					     inet_gro_compute_pseudo);
 skip:
+	NAPI_GRO_CB(skb)->is_ipv6 = 0;
 	return udp_gro_receive(head, skb, uh);
 
 flush:
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 8f96988c1db2..6b8f543f6ac6 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -140,6 +140,7 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
 					     ip6_gro_compute_pseudo);
 
 skip:
+	NAPI_GRO_CB(skb)->is_ipv6 = 1;
 	return udp_gro_receive(head, skb, uh);
 
 flush:
-- 
cgit v1.2.3


From 37dd0247797b168ad1cc7f5dbec825a1ee66535b Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Fri, 3 Oct 2014 15:48:09 -0700
Subject: gue: Receive side for Generic UDP Encapsulation

This patch adds support receiving for GUE packets in the fou module. The
fou module now supports direct foo-over-udp (no encapsulation header)
and GUE. To support this a type parameter is added to the fou netlink
parameters.

For a GUE socket we define gue_udp_recv, gue_gro_receive, and
gue_gro_complete to handle the specifics of the GUE protocol. Most
of the code to manage and configure sockets is common with the fou.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gue.h        |  23 ++++++
 include/uapi/linux/fou.h |   7 ++
 net/ipv4/fou.c           | 196 ++++++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 217 insertions(+), 9 deletions(-)
 create mode 100644 include/net/gue.h

(limited to 'include')

diff --git a/include/net/gue.h b/include/net/gue.h
new file mode 100644
index 000000000000..b6c332788084
--- /dev/null
+++ b/include/net/gue.h
@@ -0,0 +1,23 @@
+#ifndef __NET_GUE_H
+#define __NET_GUE_H
+
+struct guehdr {
+	union {
+		struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+			__u8	hlen:4,
+			version:4;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+			__u8	version:4,
+				hlen:4;
+#else
+#error  "Please fix <asm/byteorder.h>"
+#endif
+			__u8    next_hdr;
+			__u16   flags;
+		};
+		__u32 word;
+	};
+};
+
+#endif
diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h
index e03376de453d..8df06894da23 100644
--- a/include/uapi/linux/fou.h
+++ b/include/uapi/linux/fou.h
@@ -13,6 +13,7 @@ enum {
 	FOU_ATTR_PORT,				/* u16 */
 	FOU_ATTR_AF,				/* u8 */
 	FOU_ATTR_IPPROTO,			/* u8 */
+	FOU_ATTR_TYPE,				/* u8 */
 
 	__FOU_ATTR_MAX,
 };
@@ -27,6 +28,12 @@ enum {
 	__FOU_CMD_MAX,
 };
 
+enum {
+	FOU_ENCAP_UNSPEC,
+	FOU_ENCAP_DIRECT,
+	FOU_ENCAP_GUE,
+};
+
 #define FOU_CMD_MAX	(__FOU_CMD_MAX - 1)
 
 #endif /* _UAPI_LINUX_FOU_H */
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 7e2126a31f2e..efa70ad44906 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <net/genetlink.h>
+#include <net/gue.h>
 #include <net/ip.h>
 #include <net/protocol.h>
 #include <net/udp.h>
@@ -27,6 +28,7 @@ struct fou {
 };
 
 struct fou_cfg {
+	u16 type;
 	u8 protocol;
 	struct udp_port_cfg udp_config;
 };
@@ -64,6 +66,41 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 					  sizeof(struct udphdr));
 }
 
+static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct fou *fou = fou_from_sock(sk);
+	size_t len;
+	struct guehdr *guehdr;
+	struct udphdr *uh;
+
+	if (!fou)
+		return 1;
+
+	len = sizeof(struct udphdr) + sizeof(struct guehdr);
+	if (!pskb_may_pull(skb, len))
+		goto drop;
+
+	uh = udp_hdr(skb);
+	guehdr = (struct guehdr *)&uh[1];
+
+	len += guehdr->hlen << 2;
+	if (!pskb_may_pull(skb, len))
+		goto drop;
+
+	if (guehdr->version != 0)
+		goto drop;
+
+	if (guehdr->flags) {
+		/* No support yet */
+		goto drop;
+	}
+
+	return fou_udp_encap_recv_deliver(skb, guehdr->next_hdr, len);
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+
 static struct sk_buff **fou_gro_receive(struct sk_buff **head,
 					struct sk_buff *skb)
 {
@@ -107,6 +144,112 @@ out_unlock:
 	return err;
 }
 
+static struct sk_buff **gue_gro_receive(struct sk_buff **head,
+					struct sk_buff *skb)
+{
+	const struct net_offload **offloads;
+	const struct net_offload *ops;
+	struct sk_buff **pp = NULL;
+	struct sk_buff *p;
+	u8 proto;
+	struct guehdr *guehdr;
+	unsigned int hlen, guehlen;
+	unsigned int off;
+	int flush = 1;
+
+	off = skb_gro_offset(skb);
+	hlen = off + sizeof(*guehdr);
+	guehdr = skb_gro_header_fast(skb, off);
+	if (skb_gro_header_hard(skb, hlen)) {
+		guehdr = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!guehdr))
+			goto out;
+	}
+
+	proto = guehdr->next_hdr;
+
+	rcu_read_lock();
+	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
+	ops = rcu_dereference(offloads[proto]);
+	if (WARN_ON(!ops || !ops->callbacks.gro_receive))
+		goto out_unlock;
+
+	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
+
+	hlen = off + guehlen;
+	if (skb_gro_header_hard(skb, hlen)) {
+		guehdr = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!guehdr))
+			goto out_unlock;
+	}
+
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		const struct guehdr *guehdr2;
+
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		guehdr2 = (struct guehdr *)(p->data + off);
+
+		/* Compare base GUE header to be equal (covers
+		 * hlen, version, next_hdr, and flags.
+		 */
+		if (guehdr->word != guehdr2->word) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+
+		/* Compare optional fields are the same. */
+		if (guehdr->hlen && memcmp(&guehdr[1], &guehdr2[1],
+					   guehdr->hlen << 2)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+	}
+
+	skb_gro_pull(skb, guehlen);
+
+	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
+	skb_gro_postpull_rcsum(skb, guehdr, guehlen);
+
+	pp = ops->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+
+static int gue_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	const struct net_offload **offloads;
+	struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff);
+	const struct net_offload *ops;
+	unsigned int guehlen;
+	u8 proto;
+	int err = -ENOENT;
+
+	proto = guehdr->next_hdr;
+
+	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
+
+	rcu_read_lock();
+	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
+	ops = rcu_dereference(offloads[proto]);
+	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
+		goto out_unlock;
+
+	err = ops->callbacks.gro_complete(skb, nhoff + guehlen);
+
+out_unlock:
+	rcu_read_unlock();
+	return err;
+}
+
 static int fou_add_to_port_list(struct fou *fou)
 {
 	struct fou *fout;
@@ -142,6 +285,28 @@ static void fou_release(struct fou *fou)
 	kfree(fou);
 }
 
+static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
+{
+	udp_sk(sk)->encap_rcv = fou_udp_recv;
+	fou->protocol = cfg->protocol;
+	fou->udp_offloads.callbacks.gro_receive = fou_gro_receive;
+	fou->udp_offloads.callbacks.gro_complete = fou_gro_complete;
+	fou->udp_offloads.port = cfg->udp_config.local_udp_port;
+	fou->udp_offloads.ipproto = cfg->protocol;
+
+	return 0;
+}
+
+static int gue_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
+{
+	udp_sk(sk)->encap_rcv = gue_udp_recv;
+	fou->udp_offloads.callbacks.gro_receive = gue_gro_receive;
+	fou->udp_offloads.callbacks.gro_complete = gue_gro_complete;
+	fou->udp_offloads.port = cfg->udp_config.local_udp_port;
+
+	return 0;
+}
+
 static int fou_create(struct net *net, struct fou_cfg *cfg,
 		      struct socket **sockp)
 {
@@ -164,10 +329,24 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 
 	sk = sock->sk;
 
-	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
-	fou->protocol = cfg->protocol;
-	fou->port =  cfg->udp_config.local_udp_port;
-	udp_sk(sk)->encap_rcv = fou_udp_recv;
+	fou->port = cfg->udp_config.local_udp_port;
+
+	/* Initial for fou type */
+	switch (cfg->type) {
+	case FOU_ENCAP_DIRECT:
+		err = fou_encap_init(sk, fou, cfg);
+		if (err)
+			goto error;
+		break;
+	case FOU_ENCAP_GUE:
+		err = gue_encap_init(sk, fou, cfg);
+		if (err)
+			goto error;
+		break;
+	default:
+		err = -EINVAL;
+		goto error;
+	}
 
 	udp_sk(sk)->encap_type = 1;
 	udp_encap_enable();
@@ -179,11 +358,6 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 
 	sk->sk_allocation = GFP_ATOMIC;
 
-	fou->udp_offloads.callbacks.gro_receive = fou_gro_receive;
-	fou->udp_offloads.callbacks.gro_complete = fou_gro_complete;
-	fou->udp_offloads.port = cfg->udp_config.local_udp_port;
-	fou->udp_offloads.ipproto = cfg->protocol;
-
 	if (cfg->udp_config.family == AF_INET) {
 		err = udp_add_offload(&fou->udp_offloads);
 		if (err)
@@ -240,6 +414,7 @@ static struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
 	[FOU_ATTR_PORT] = { .type = NLA_U16, },
 	[FOU_ATTR_AF] = { .type = NLA_U8, },
 	[FOU_ATTR_IPPROTO] = { .type = NLA_U8, },
+	[FOU_ATTR_TYPE] = { .type = NLA_U8, },
 };
 
 static int parse_nl_config(struct genl_info *info,
@@ -267,6 +442,9 @@ static int parse_nl_config(struct genl_info *info,
 	if (info->attrs[FOU_ATTR_IPPROTO])
 		cfg->protocol = nla_get_u8(info->attrs[FOU_ATTR_IPPROTO]);
 
+	if (info->attrs[FOU_ATTR_TYPE])
+		cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From bc1fc390e1728672b5b343b85185fcc1fe41043b Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Fri, 3 Oct 2014 15:48:10 -0700
Subject: ip_tunnel: Add GUE support

This patch allows configuring IPIP, sit, and GRE tunnels to use GUE.
This is very similar to fou excpet that we need to insert the GUE header
in addition to the UDP header on transmit.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_tunnel.h |  1 +
 net/ipv4/ip_tunnel.c           | 13 +++++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index 7c832afdfa94..280d9e092283 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -64,6 +64,7 @@ enum {
 enum tunnel_encap_types {
 	TUNNEL_ENCAP_NONE,
 	TUNNEL_ENCAP_FOU,
+	TUNNEL_ENCAP_GUE,
 };
 
 #define TUNNEL_ENCAP_FLAG_CSUM		(1<<0)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index d9c9dc4ffeaf..0bb8e141eacc 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -56,6 +56,7 @@
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 #include <net/udp.h>
+#include <net/gue.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -495,6 +496,8 @@ static int ip_encap_hlen(struct ip_tunnel_encap *e)
 		return 0;
 	case TUNNEL_ENCAP_FOU:
 		return sizeof(struct udphdr);
+	case TUNNEL_ENCAP_GUE:
+		return sizeof(struct udphdr) + sizeof(struct guehdr);
 	default:
 		return -EINVAL;
 	}
@@ -546,6 +549,15 @@ static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 	skb_reset_transport_header(skb);
 	uh = udp_hdr(skb);
 
+	if (e->type == TUNNEL_ENCAP_GUE) {
+		struct guehdr *guehdr = (struct guehdr *)&uh[1];
+
+		guehdr->version = 0;
+		guehdr->hlen = 0;
+		guehdr->flags = 0;
+		guehdr->next_hdr = *protocol;
+	}
+
 	uh->dest = e->dport;
 	uh->source = sport;
 	uh->len = htons(skb->len);
@@ -565,6 +577,7 @@ int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 	case TUNNEL_ENCAP_NONE:
 		return 0;
 	case TUNNEL_ENCAP_FOU:
+	case TUNNEL_ENCAP_GUE:
 		return fou_build_header(skb, &t->encap, t->encap_hlen,
 					protocol, fl4);
 	default:
-- 
cgit v1.2.3


From 7941b27b16e3282f6ec8817e36492f1deec753a7 Mon Sep 17 00:00:00 2001
From: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Date: Fri, 4 Jul 2014 19:59:20 +0300
Subject: of: Introduce Device Tree resolve support.

Introduce support for dynamic device tree resolution.
Using it, it is possible to prepare a device tree that's
been loaded on runtime to be modified and inserted at the kernel
live tree.

Export of of_resolve and bug fix of double free by
	Guenter Roeck <groeck@juniper.net>

Signed-off-by: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
[grant.likely: Don't need to select CONFIG_OF_DYNAMIC and CONFIG_OF_DEVICE]
[grant.likely: Don't need to depend on OF or !SPARC]
[grant.likely: Factor out duplicate code blocks into single function]
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 .../devicetree/dynamic-resolution-notes.txt        |  25 ++
 drivers/of/Kconfig                                 |   3 +
 drivers/of/Makefile                                |   1 +
 drivers/of/resolver.c                              | 336 +++++++++++++++++++++
 include/linux/of.h                                 |   3 +
 5 files changed, 368 insertions(+)
 create mode 100644 Documentation/devicetree/dynamic-resolution-notes.txt
 create mode 100644 drivers/of/resolver.c

(limited to 'include')

diff --git a/Documentation/devicetree/dynamic-resolution-notes.txt b/Documentation/devicetree/dynamic-resolution-notes.txt
new file mode 100644
index 000000000000..083d23262abe
--- /dev/null
+++ b/Documentation/devicetree/dynamic-resolution-notes.txt
@@ -0,0 +1,25 @@
+Device Tree Dynamic Resolver Notes
+----------------------------------
+
+This document describes the implementation of the in-kernel
+Device Tree resolver, residing in drivers/of/resolver.c and is a
+companion document to Documentation/devicetree/dt-object-internal.txt[1]
+
+How the resolver works
+----------------------
+
+The resolver is given as an input an arbitrary tree compiled with the
+proper dtc option and having a /plugin/ tag. This generates the
+appropriate __fixups__ & __local_fixups__ nodes as described in [1].
+
+In sequence the resolver works by the following steps:
+
+1. Get the maximum device tree phandle value from the live tree + 1.
+2. Adjust all the local phandles of the tree to resolve by that amount.
+3. Using the __local__fixups__ node information adjust all local references
+   by the same amount.
+4. For each property in the __fixups__ node locate the node it references
+   in the live tree. This is the label used to tag the node.
+5. Retrieve the phandle of the target of the fixup.
+6. For each fixup in the property locate the node:property:offset location
+   and replace it with the phandle value.
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 5160c4eb73c2..6b81a36f6420 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -79,4 +79,7 @@ config OF_RESERVED_MEM
 	help
 	  Helpers to allow for reservation of memory regions
 
+config OF_RESOLVE
+	bool
+
 endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index 2b6a7b129d10..ca9209ce50cd 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_OF_PCI)	+= of_pci.o
 obj-$(CONFIG_OF_PCI_IRQ)  += of_pci_irq.o
 obj-$(CONFIG_OF_MTD)	+= of_mtd.o
 obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
+obj-$(CONFIG_OF_RESOLVE)  += resolver.o
 
 CFLAGS_fdt.o = -I$(src)/../../scripts/dtc/libfdt
 CFLAGS_fdt_address.o = -I$(src)/../../scripts/dtc/libfdt
diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c
new file mode 100644
index 000000000000..aed7959f800d
--- /dev/null
+++ b/drivers/of/resolver.c
@@ -0,0 +1,336 @@
+/*
+ * Functions for dealing with DT resolution
+ *
+ * Copyright (C) 2012 Pantelis Antoniou <panto@antoniou-consulting.com>
+ * Copyright (C) 2012 Texas Instruments Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+
+/* illegal phandle value (set when unresolved) */
+#define OF_PHANDLE_ILLEGAL	0xdeadbeef
+
+/**
+ * Find a node with the give full name by recursively following any of
+ * the child node links.
+ */
+static struct device_node *__of_find_node_by_full_name(struct device_node *node,
+		const char *full_name)
+{
+	struct device_node *child, *found;
+
+	if (node == NULL)
+		return NULL;
+
+	/* check */
+	if (of_node_cmp(node->full_name, full_name) == 0)
+		return node;
+
+	for_each_child_of_node(node, child) {
+		found = __of_find_node_by_full_name(child, full_name);
+		if (found != NULL)
+			return found;
+	}
+
+	return NULL;
+}
+
+/*
+ * Find live tree's maximum phandle value.
+ */
+static phandle of_get_tree_max_phandle(void)
+{
+	struct device_node *node;
+	phandle phandle;
+	unsigned long flags;
+
+	/* now search recursively */
+	raw_spin_lock_irqsave(&devtree_lock, flags);
+	phandle = 0;
+	for_each_of_allnodes(node) {
+		if (node->phandle != OF_PHANDLE_ILLEGAL &&
+				node->phandle > phandle)
+			phandle = node->phandle;
+	}
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+	return phandle;
+}
+
+/*
+ * Adjust a subtree's phandle values by a given delta.
+ * Makes sure not to just adjust the device node's phandle value,
+ * but modify the phandle properties values as well.
+ */
+static void __of_adjust_tree_phandles(struct device_node *node,
+		int phandle_delta)
+{
+	struct device_node *child;
+	struct property *prop;
+	phandle phandle;
+
+	/* first adjust the node's phandle direct value */
+	if (node->phandle != 0 && node->phandle != OF_PHANDLE_ILLEGAL)
+		node->phandle += phandle_delta;
+
+	/* now adjust phandle & linux,phandle values */
+	for_each_property_of_node(node, prop) {
+
+		/* only look for these two */
+		if (of_prop_cmp(prop->name, "phandle") != 0 &&
+		    of_prop_cmp(prop->name, "linux,phandle") != 0)
+			continue;
+
+		/* must be big enough */
+		if (prop->length < 4)
+			continue;
+
+		/* read phandle value */
+		phandle = be32_to_cpup(prop->value);
+		if (phandle == OF_PHANDLE_ILLEGAL)	/* unresolved */
+			continue;
+
+		/* adjust */
+		*(uint32_t *)prop->value = cpu_to_be32(node->phandle);
+	}
+
+	/* now do the children recursively */
+	for_each_child_of_node(node, child)
+		__of_adjust_tree_phandles(child, phandle_delta);
+}
+
+static int __of_adjust_phandle_ref(struct device_node *node, struct property *rprop, int value, bool is_delta)
+{
+	phandle phandle;
+	struct device_node *refnode;
+	struct property *sprop;
+	char *propval, *propcur, *propend, *nodestr, *propstr, *s;
+	int offset, propcurlen;
+	int err = 0;
+
+	/* make a copy */
+	propval = kmalloc(rprop->length, GFP_KERNEL);
+	if (!propval) {
+		pr_err("%s: Could not copy value of '%s'\n",
+				__func__, rprop->name);
+		return -ENOMEM;
+	}
+	memcpy(propval, rprop->value, rprop->length);
+
+	propend = propval + rprop->length;
+	for (propcur = propval; propcur < propend; propcur += propcurlen + 1) {
+		propcurlen = strlen(propcur);
+
+		nodestr = propcur;
+		s = strchr(propcur, ':');
+		if (!s) {
+			pr_err("%s: Illegal symbol entry '%s' (1)\n",
+				__func__, propcur);
+			err = -EINVAL;
+			goto err_fail;
+		}
+		*s++ = '\0';
+
+		propstr = s;
+		s = strchr(s, ':');
+		if (!s) {
+			pr_err("%s: Illegal symbol entry '%s' (2)\n",
+				__func__, (char *)rprop->value);
+			err = -EINVAL;
+			goto err_fail;
+		}
+
+		*s++ = '\0';
+		err = kstrtoint(s, 10, &offset);
+		if (err != 0) {
+			pr_err("%s: Could get offset '%s'\n",
+				__func__, (char *)rprop->value);
+			goto err_fail;
+		}
+
+		/* look into the resolve node for the full path */
+		refnode = __of_find_node_by_full_name(node, nodestr);
+		if (!refnode) {
+			pr_warn("%s: Could not find refnode '%s'\n",
+				__func__, (char *)rprop->value);
+			continue;
+		}
+
+		/* now find the property */
+		for_each_property_of_node(refnode, sprop) {
+			if (of_prop_cmp(sprop->name, propstr) == 0)
+				break;
+		}
+
+		if (!sprop) {
+			pr_err("%s: Could not find property '%s'\n",
+				__func__, (char *)rprop->value);
+			err = -ENOENT;
+			goto err_fail;
+		}
+
+		phandle = is_delta ? be32_to_cpup(sprop->value + offset) + value : value;
+		*(__be32 *)(sprop->value + offset) = cpu_to_be32(phandle);
+	}
+
+err_fail:
+	kfree(propval);
+	return err;
+}
+
+/*
+ * Adjust the local phandle references by the given phandle delta.
+ * Assumes the existances of a __local_fixups__ node at the root
+ * of the tree. Does not take any devtree locks so make sure you
+ * call this on a tree which is at the detached state.
+ */
+static int __of_adjust_tree_phandle_references(struct device_node *node,
+		int phandle_delta)
+{
+	struct device_node *child;
+	struct property *rprop;
+	int err;
+
+	/* locate the symbols & fixups nodes on resolve */
+	for_each_child_of_node(node, child)
+		if (of_node_cmp(child->name, "__local_fixups__") == 0)
+			break;
+
+	/* no local fixups */
+	if (!child)
+		return 0;
+
+	/* find the local fixups property */
+	for_each_property_of_node(child, rprop) {
+		/* skip properties added automatically */
+		if (of_prop_cmp(rprop->name, "name") == 0)
+			continue;
+
+		err = __of_adjust_phandle_ref(node, rprop, phandle_delta, true);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * of_resolve	- Resolve the given node against the live tree.
+ *
+ * @resolve:	Node to resolve
+ *
+ * Perform dynamic Device Tree resolution against the live tree
+ * to the given node to resolve. This depends on the live tree
+ * having a __symbols__ node, and the resolve node the __fixups__ &
+ * __local_fixups__ nodes (if needed).
+ * The result of the operation is a resolve node that it's contents
+ * are fit to be inserted or operate upon the live tree.
+ * Returns 0 on success or a negative error value on error.
+ */
+int of_resolve_phandles(struct device_node *resolve)
+{
+	struct device_node *child, *refnode;
+	struct device_node *root_sym, *resolve_sym, *resolve_fix;
+	struct property *rprop;
+	const char *refpath;
+	phandle phandle, phandle_delta;
+	int err;
+
+	/* the resolve node must exist, and be detached */
+	if (!resolve || !of_node_check_flag(resolve, OF_DETACHED))
+		return -EINVAL;
+
+	/* first we need to adjust the phandles */
+	phandle_delta = of_get_tree_max_phandle() + 1;
+	__of_adjust_tree_phandles(resolve, phandle_delta);
+	err = __of_adjust_tree_phandle_references(resolve, phandle_delta);
+	if (err != 0)
+		return err;
+
+	root_sym = NULL;
+	resolve_sym = NULL;
+	resolve_fix = NULL;
+
+	/* this may fail (if no fixups are required) */
+	root_sym = of_find_node_by_path("/__symbols__");
+
+	/* locate the symbols & fixups nodes on resolve */
+	for_each_child_of_node(resolve, child) {
+
+		if (!resolve_sym &&
+				of_node_cmp(child->name, "__symbols__") == 0)
+			resolve_sym = child;
+
+		if (!resolve_fix &&
+				of_node_cmp(child->name, "__fixups__") == 0)
+			resolve_fix = child;
+
+		/* both found, don't bother anymore */
+		if (resolve_sym && resolve_fix)
+			break;
+	}
+
+	/* we do allow for the case where no fixups are needed */
+	if (!resolve_fix) {
+		err = 0;	/* no error */
+		goto out;
+	}
+
+	/* we need to fixup, but no root symbols... */
+	if (!root_sym) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	for_each_property_of_node(resolve_fix, rprop) {
+
+		/* skip properties added automatically */
+		if (of_prop_cmp(rprop->name, "name") == 0)
+			continue;
+
+		err = of_property_read_string(root_sym,
+				rprop->name, &refpath);
+		if (err != 0) {
+			pr_err("%s: Could not find symbol '%s'\n",
+					__func__, rprop->name);
+			goto out;
+		}
+
+		refnode = of_find_node_by_path(refpath);
+		if (!refnode) {
+			pr_err("%s: Could not find node by path '%s'\n",
+					__func__, refpath);
+			err = -ENOENT;
+			goto out;
+		}
+
+		phandle = refnode->phandle;
+		of_node_put(refnode);
+
+		pr_debug("%s: %s phandle is 0x%08x\n",
+				__func__, rprop->name, phandle);
+
+		err = __of_adjust_phandle_ref(resolve, rprop, phandle, false);
+		if (err)
+			break;
+	}
+
+out:
+	/* NULL is handled by of_node_put as NOP */
+	of_node_put(root_sym);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(of_resolve_phandles);
diff --git a/include/linux/of.h b/include/linux/of.h
index 6c4363b8ddc3..6545e7aec7bb 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -863,4 +863,7 @@ static inline int of_changeset_update_property(struct of_changeset *ocs,
 }
 #endif
 
+/* CONFIG_OF_RESOLVE api */
+extern int of_resolve_phandles(struct device_node *tree);
+
 #endif /* _LINUX_OF_H */
-- 
cgit v1.2.3


From c8753d55afb436fd6a25c8bbe8d783f6dcf1c9f8 Mon Sep 17 00:00:00 2001
From: Vijay Subramanian <subramanian.vijay@gmail.com>
Date: Thu, 2 Oct 2014 10:00:43 -0700
Subject: net: Cleanup skb cloning by adding SKB_FCLONE_FREE

SKB_FCLONE_UNAVAILABLE has overloaded meaning depending on type of skb.
1: If skb is allocated from head_cache, it indicates fclone is not available.
2: If skb is a companion fclone skb (allocated from fclone_cache), it indicates
it is available to be used.

To avoid confusion for case 2 above, this patch  replaces
SKB_FCLONE_UNAVAILABLE with SKB_FCLONE_FREE where appropriate. For fclone
companion skbs, this indicates it is free for use.

SKB_FCLONE_UNAVAILABLE will now simply indicate skb is from head_cache and
cannot / will not have a companion fclone.

Signed-off-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 7 ++++---
 net/core/skbuff.c      | 8 ++++----
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7c5036d11feb..3a5ec7638627 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -339,9 +339,10 @@ struct skb_shared_info {
 
 
 enum {
-	SKB_FCLONE_UNAVAILABLE,
-	SKB_FCLONE_ORIG,
-	SKB_FCLONE_CLONE,
+	SKB_FCLONE_UNAVAILABLE,	/* skb has no fclone (from head_cache) */
+	SKB_FCLONE_ORIG,	/* orig skb (from fclone_cache) */
+	SKB_FCLONE_CLONE,	/* companion fclone skb (from fclone_cache) */
+	SKB_FCLONE_FREE,	/* this companion fclone skb is available */
 };
 
 enum {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a0b312fa3047..28916e47f959 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -265,7 +265,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 		skb->fclone = SKB_FCLONE_ORIG;
 		atomic_set(&fclones->fclone_ref, 1);
 
-		fclones->skb2.fclone = SKB_FCLONE_UNAVAILABLE;
+		fclones->skb2.fclone = SKB_FCLONE_FREE;
 		fclones->skb2.pfmemalloc = pfmemalloc;
 	}
 out:
@@ -542,7 +542,7 @@ static void kfree_skbmem(struct sk_buff *skb)
 		fclones = container_of(skb, struct sk_buff_fclones, skb2);
 
 		/* Warning : We must perform the atomic_dec_and_test() before
-		 * setting skb->fclone back to SKB_FCLONE_UNAVAILABLE, otherwise
+		 * setting skb->fclone back to SKB_FCLONE_FREE, otherwise
 		 * skb_clone() could set clone_ref to 2 before our decrement.
 		 * Anyway, if we are going to free the structure, no need to
 		 * rewrite skb->fclone.
@@ -553,7 +553,7 @@ static void kfree_skbmem(struct sk_buff *skb)
 			/* The clone portion is available for
 			 * fast-cloning again.
 			 */
-			skb->fclone = SKB_FCLONE_UNAVAILABLE;
+			skb->fclone = SKB_FCLONE_FREE;
 		}
 		break;
 	}
@@ -874,7 +874,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 		return NULL;
 
 	if (skb->fclone == SKB_FCLONE_ORIG &&
-	    n->fclone == SKB_FCLONE_UNAVAILABLE) {
+	    n->fclone == SKB_FCLONE_FREE) {
 		n->fclone = SKB_FCLONE_CLONE;
 		/* As our fastclone was free, clone_ref must be 1 at this point.
 		 * We could use atomic_inc() here, but it is faster
-- 
cgit v1.2.3


From dd3619f2ed5bd5ffce90f4fd8361ccd46d59b9b6 Mon Sep 17 00:00:00 2001
From: Sébastien Barré <sebastien.barre@uclouvain.be>
Date: Thu, 2 Oct 2014 21:15:22 +0200
Subject: Removed unused inet6 address state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

the inet6 state INET6_IFADDR_STATE_UP only appeared in its definition.

Cc: Christoph Paasch <christoph.paasch@uclouvain.be>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sébastien Barré <sebastien.barre@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/if_inet6.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index d07b1a64b4e7..55a8d4056cc9 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -35,7 +35,6 @@ enum {
 	INET6_IFADDR_STATE_DAD,
 	INET6_IFADDR_STATE_POSTDAD,
 	INET6_IFADDR_STATE_ERRDAD,
-	INET6_IFADDR_STATE_UP,
 	INET6_IFADDR_STATE_DEAD,
 };
 
-- 
cgit v1.2.3


From 86f1152b117a404229fd6f08ec3faca779f37b92 Mon Sep 17 00:00:00 2001
From: Benjamin Marzinski <bmarzins@redhat.com>
Date: Wed, 13 Aug 2014 13:53:43 -0500
Subject: dm: allow active and inactive tables to share dm_devs

Until this change, when loading a new DM table, DM core would re-open
all of the devices in the DM table.  Now, DM core will avoid redundant
device opens (and closes when destroying the old table) if the old
table already has a device open using the same mode.  This is achieved
by managing reference counts on the table_devices that DM core now
stores in the mapped_device structure (rather than in the dm_table
structure).  So a mapped_device's active and inactive dm_tables' dm_dev
lists now just point to the dm_devs stored in the mapped_device's
table_devices list.

This improvement in DM core's device reference counting has the
side-effect of fixing a long-standing limitation of the multipath
target: a DM multipath table couldn't include any paths that were unusable
(failed).  For example: if all paths have failed and you add a new,
working, path to the table; you can't use it since the table load would
fail due to it still containing failed paths.  Now a re-load of a
multipath table can include failed devices and when those devices become
active again they can be used instantly.

The device list code in dm.c isn't a straight copy/paste from the code in
dm-table.c, but it's very close (aside from some variable renames).  One
subtle difference is that find_table_device for the tables_devices list
will only match devices with the same name and mode.  This is because we
don't want to upgrade a device's mode in the active table when an
inactive table is loaded.

Access to the mapped_device structure's tables_devices list requires a
mutex (tables_devices_lock), so that tables cannot be created and
destroyed concurrently.

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-ioctl.c         |   2 +-
 drivers/md/dm-table.c         | 102 ++++++++++++----------------------
 drivers/md/dm.c               | 126 ++++++++++++++++++++++++++++++++++++++++++
 drivers/md/dm.h               |   5 +-
 include/uapi/linux/dm-ioctl.h |   4 +-
 5 files changed, 167 insertions(+), 72 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 51521429fb59..0be9381365d7 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1418,7 +1418,7 @@ static void retrieve_deps(struct dm_table *table,
 	deps->count = count;
 	count = 0;
 	list_for_each_entry (dd, dm_table_get_devices(table), list)
-		deps->dev[count++] = huge_encode_dev(dd->dm_dev.bdev->bd_dev);
+		deps->dev[count++] = huge_encode_dev(dd->dm_dev->bdev->bd_dev);
 
 	param->data_size = param->data_start + needed;
 }
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index f9c6cb8dbcf8..b2bd1ebf4562 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -210,15 +210,16 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 	return 0;
 }
 
-static void free_devices(struct list_head *devices)
+static void free_devices(struct list_head *devices, struct mapped_device *md)
 {
 	struct list_head *tmp, *next;
 
 	list_for_each_safe(tmp, next, devices) {
 		struct dm_dev_internal *dd =
 		    list_entry(tmp, struct dm_dev_internal, list);
-		DMWARN("dm_table_destroy: dm_put_device call missing for %s",
-		       dd->dm_dev.name);
+		DMWARN("%s: dm_table_destroy: dm_put_device call missing for %s",
+		       dm_device_name(md), dd->dm_dev->name);
+		dm_put_table_device(md, dd->dm_dev);
 		kfree(dd);
 	}
 }
@@ -247,7 +248,7 @@ void dm_table_destroy(struct dm_table *t)
 	vfree(t->highs);
 
 	/* free the device list */
-	free_devices(&t->devices);
+	free_devices(&t->devices, t->md);
 
 	dm_free_md_mempools(t->mempools);
 
@@ -262,52 +263,12 @@ static struct dm_dev_internal *find_device(struct list_head *l, dev_t dev)
 	struct dm_dev_internal *dd;
 
 	list_for_each_entry (dd, l, list)
-		if (dd->dm_dev.bdev->bd_dev == dev)
+		if (dd->dm_dev->bdev->bd_dev == dev)
 			return dd;
 
 	return NULL;
 }
 
-/*
- * Open a device so we can use it as a map destination.
- */
-static int open_dev(struct dm_dev_internal *d, dev_t dev,
-		    struct mapped_device *md)
-{
-	static char *_claim_ptr = "I belong to device-mapper";
-	struct block_device *bdev;
-
-	int r;
-
-	BUG_ON(d->dm_dev.bdev);
-
-	bdev = blkdev_get_by_dev(dev, d->dm_dev.mode | FMODE_EXCL, _claim_ptr);
-	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
-
-	r = bd_link_disk_holder(bdev, dm_disk(md));
-	if (r) {
-		blkdev_put(bdev, d->dm_dev.mode | FMODE_EXCL);
-		return r;
-	}
-
-	d->dm_dev.bdev = bdev;
-	return 0;
-}
-
-/*
- * Close a device that we've been using.
- */
-static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
-{
-	if (!d->dm_dev.bdev)
-		return;
-
-	bd_unlink_disk_holder(d->dm_dev.bdev, dm_disk(md));
-	blkdev_put(d->dm_dev.bdev, d->dm_dev.mode | FMODE_EXCL);
-	d->dm_dev.bdev = NULL;
-}
-
 /*
  * If possible, this checks an area of a destination device is invalid.
  */
@@ -386,19 +347,17 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 			struct mapped_device *md)
 {
 	int r;
-	struct dm_dev_internal dd_new, dd_old;
+	struct dm_dev *old_dev, *new_dev;
 
-	dd_new = dd_old = *dd;
+	old_dev = dd->dm_dev;
 
-	dd_new.dm_dev.mode |= new_mode;
-	dd_new.dm_dev.bdev = NULL;
-
-	r = open_dev(&dd_new, dd->dm_dev.bdev->bd_dev, md);
+	r = dm_get_table_device(md, dd->dm_dev->bdev->bd_dev,
+				dd->dm_dev->mode | new_mode, &new_dev);
 	if (r)
 		return r;
 
-	dd->dm_dev.mode |= new_mode;
-	close_dev(&dd_old, md);
+	dd->dm_dev = new_dev;
+	dm_put_table_device(md, old_dev);
 
 	return 0;
 }
@@ -440,27 +399,22 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 		if (!dd)
 			return -ENOMEM;
 
-		dd->dm_dev.mode = mode;
-		dd->dm_dev.bdev = NULL;
-
-		if ((r = open_dev(dd, dev, t->md))) {
+		if ((r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev))) {
 			kfree(dd);
 			return r;
 		}
 
-		format_dev_t(dd->dm_dev.name, dev);
-
 		atomic_set(&dd->count, 0);
 		list_add(&dd->list, &t->devices);
 
-	} else if (dd->dm_dev.mode != (mode | dd->dm_dev.mode)) {
+	} else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) {
 		r = upgrade_mode(dd, mode, t->md);
 		if (r)
 			return r;
 	}
 	atomic_inc(&dd->count);
 
-	*result = &dd->dm_dev;
+	*result = dd->dm_dev;
 	return 0;
 }
 EXPORT_SYMBOL(dm_get_device);
@@ -505,11 +459,23 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
  */
 void dm_put_device(struct dm_target *ti, struct dm_dev *d)
 {
-	struct dm_dev_internal *dd = container_of(d, struct dm_dev_internal,
-						  dm_dev);
+	int found = 0;
+	struct list_head *devices = &ti->table->devices;
+	struct dm_dev_internal *dd;
 
+	list_for_each_entry(dd, devices, list) {
+		if (dd->dm_dev == d) {
+			found = 1;
+			break;
+		}
+	}
+	if (!found) {
+		DMWARN("%s: device %s not in table devices list",
+		       dm_device_name(ti->table->md), d->name);
+		return;
+	}
 	if (atomic_dec_and_test(&dd->count)) {
-		close_dev(dd, ti->table->md);
+		dm_put_table_device(ti->table->md, d);
 		list_del(&dd->list);
 		kfree(dd);
 	}
@@ -906,7 +872,7 @@ static int dm_table_set_type(struct dm_table *t)
 	/* Non-request-stackable devices can't be used for request-based dm */
 	devices = dm_table_get_devices(t);
 	list_for_each_entry(dd, devices, list) {
-		if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev.bdev))) {
+		if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev->bdev))) {
 			DMWARN("table load rejected: including"
 			       " non-request-stackable devices");
 			return -EINVAL;
@@ -1043,7 +1009,7 @@ static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t,
 	struct gendisk *prev_disk = NULL, *template_disk = NULL;
 
 	list_for_each_entry(dd, devices, list) {
-		template_disk = dd->dm_dev.bdev->bd_disk;
+		template_disk = dd->dm_dev->bdev->bd_disk;
 		if (!blk_get_integrity(template_disk))
 			goto no_integrity;
 		if (!match_all && !blk_integrity_is_initialized(template_disk))
@@ -1629,7 +1595,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 	int r = 0;
 
 	list_for_each_entry(dd, devices, list) {
-		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);
+		struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
 		char b[BDEVNAME_SIZE];
 
 		if (likely(q))
@@ -1637,7 +1603,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 		else
 			DMWARN_LIMIT("%s: any_congested: nonexistent device %s",
 				     dm_device_name(t->md),
-				     bdevname(dd->dm_dev.bdev, b));
+				     bdevname(dd->dm_dev->bdev, b));
 	}
 
 	list_for_each_entry(cb, &t->target_callbacks, list)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 56a2c74c9a3f..58f3927fd7cc 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -142,6 +142,9 @@ struct mapped_device {
 	 */
 	struct dm_table *map;
 
+	struct list_head table_devices;
+	struct mutex table_devices_lock;
+
 	unsigned long flags;
 
 	struct request_queue *queue;
@@ -212,6 +215,12 @@ struct dm_md_mempools {
 	struct bio_set *bs;
 };
 
+struct table_device {
+	struct list_head list;
+	atomic_t count;
+	struct dm_dev dm_dev;
+};
+
 #define RESERVED_BIO_BASED_IOS		16
 #define RESERVED_REQUEST_BASED_IOS	256
 #define RESERVED_MAX_IOS		1024
@@ -669,6 +678,120 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU)
 	rcu_read_unlock();
 }
 
+/*
+ * Open a table device so we can use it as a map destination.
+ */
+static int open_table_device(struct table_device *td, dev_t dev,
+			     struct mapped_device *md)
+{
+	static char *_claim_ptr = "I belong to device-mapper";
+	struct block_device *bdev;
+
+	int r;
+
+	BUG_ON(td->dm_dev.bdev);
+
+	bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _claim_ptr);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
+
+	r = bd_link_disk_holder(bdev, dm_disk(md));
+	if (r) {
+		blkdev_put(bdev, td->dm_dev.mode | FMODE_EXCL);
+		return r;
+	}
+
+	td->dm_dev.bdev = bdev;
+	return 0;
+}
+
+/*
+ * Close a table device that we've been using.
+ */
+static void close_table_device(struct table_device *td, struct mapped_device *md)
+{
+	if (!td->dm_dev.bdev)
+		return;
+
+	bd_unlink_disk_holder(td->dm_dev.bdev, dm_disk(md));
+	blkdev_put(td->dm_dev.bdev, td->dm_dev.mode | FMODE_EXCL);
+	td->dm_dev.bdev = NULL;
+}
+
+static struct table_device *find_table_device(struct list_head *l, dev_t dev,
+					      fmode_t mode) {
+	struct table_device *td;
+
+	list_for_each_entry(td, l, list)
+		if (td->dm_dev.bdev->bd_dev == dev && td->dm_dev.mode == mode)
+			return td;
+
+	return NULL;
+}
+
+int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
+			struct dm_dev **result) {
+	int r;
+	struct table_device *td;
+
+	mutex_lock(&md->table_devices_lock);
+	td = find_table_device(&md->table_devices, dev, mode);
+	if (!td) {
+		td = kmalloc(sizeof(*td), GFP_KERNEL);
+		if (!td) {
+			mutex_unlock(&md->table_devices_lock);
+			return -ENOMEM;
+		}
+
+		td->dm_dev.mode = mode;
+		td->dm_dev.bdev = NULL;
+
+		if ((r = open_table_device(td, dev, md))) {
+			mutex_unlock(&md->table_devices_lock);
+			kfree(td);
+			return r;
+		}
+
+		format_dev_t(td->dm_dev.name, dev);
+
+		atomic_set(&td->count, 0);
+		list_add(&td->list, &md->table_devices);
+	}
+	atomic_inc(&td->count);
+	mutex_unlock(&md->table_devices_lock);
+
+	*result = &td->dm_dev;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dm_get_table_device);
+
+void dm_put_table_device(struct mapped_device *md, struct dm_dev *d)
+{
+	struct table_device *td = container_of(d, struct table_device, dm_dev);
+
+	mutex_lock(&md->table_devices_lock);
+	if (atomic_dec_and_test(&td->count)) {
+		close_table_device(td, md);
+		list_del(&td->list);
+		kfree(td);
+	}
+	mutex_unlock(&md->table_devices_lock);
+}
+EXPORT_SYMBOL(dm_put_table_device);
+
+static void free_table_devices(struct list_head *devices)
+{
+	struct list_head *tmp, *next;
+
+	list_for_each_safe(tmp, next, devices) {
+		struct table_device *td = list_entry(tmp, struct table_device, list);
+
+		DMWARN("dm_destroy: %s still exists with %d references",
+		       td->dm_dev.name, atomic_read(&td->count));
+		kfree(td);
+	}
+}
+
 /*
  * Get the geometry associated with a dm device
  */
@@ -1944,12 +2067,14 @@ static struct mapped_device *alloc_dev(int minor)
 	md->type = DM_TYPE_NONE;
 	mutex_init(&md->suspend_lock);
 	mutex_init(&md->type_lock);
+	mutex_init(&md->table_devices_lock);
 	spin_lock_init(&md->deferred_lock);
 	atomic_set(&md->holders, 1);
 	atomic_set(&md->open_count, 0);
 	atomic_set(&md->event_nr, 0);
 	atomic_set(&md->uevent_seq, 0);
 	INIT_LIST_HEAD(&md->uevent_list);
+	INIT_LIST_HEAD(&md->table_devices);
 	spin_lock_init(&md->uevent_lock);
 
 	md->queue = blk_alloc_queue(GFP_KERNEL);
@@ -2035,6 +2160,7 @@ static void free_dev(struct mapped_device *md)
 	blk_integrity_unregister(md->disk);
 	del_gendisk(md->disk);
 	cleanup_srcu_struct(&md->io_barrier);
+	free_table_devices(&md->table_devices);
 	free_minor(minor);
 
 	spin_lock(&_minor_lock);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index e81d2152fa68..988c7fb7b145 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -44,7 +44,7 @@
 struct dm_dev_internal {
 	struct list_head list;
 	atomic_t count;
-	struct dm_dev dm_dev;
+	struct dm_dev *dm_dev;
 };
 
 struct dm_table;
@@ -188,6 +188,9 @@ int dm_cancel_deferred_remove(struct mapped_device *md);
 int dm_request_based(struct mapped_device *md);
 sector_t dm_get_size(struct mapped_device *md);
 struct request_queue *dm_get_md_queue(struct mapped_device *md);
+int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
+			struct dm_dev **result);
+void dm_put_table_device(struct mapped_device *md, struct dm_dev *d);
 struct dm_stats *dm_get_stats(struct mapped_device *md);
 
 int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index c8a4302093a3..3315ab21f728 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	27
+#define DM_VERSION_MINOR	28
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2013-10-30)"
+#define DM_VERSION_EXTRA	"-ioctl (2014-09-17)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
-- 
cgit v1.2.3


From bdf6fa52f01b941d4a80372d56de465bdbbd1d23 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Fri, 3 Oct 2014 18:16:20 -0400
Subject: sctp: handle association restarts when the socket is closed.

Currently association restarts do not take into consideration the
state of the socket.  When a restart happens, the current assocation
simply transitions into established state.  This creates a condition
where a remote system, through a the restart procedure, may create a
local association that is no way reachable by user.  The conditions
to trigger this are as follows:
  1) Remote does not acknoledge some data causing data to remain
     outstanding.
  2) Local application calls close() on the socket.  Since data
     is still outstanding, the association is placed in SHUTDOWN_PENDING
     state.  However, the socket is closed.
  3) The remote tries to create a new association, triggering a restart
     on the local system.  The association moves from SHUTDOWN_PENDING
     to ESTABLISHED.  At this point, it is no longer reachable by
     any socket on the local system.

This patch addresses the above situation by moving the newly ESTABLISHED
association into SHUTDOWN-SENT state and bundling a SHUTDOWN after
the COOKIE-ACK chunk.  This way, the restarted associate immidiately
enters the shutdown procedure and forces the termination of the
unreachable association.

Reported-by: David Laight <David.Laight@aculab.com>
Signed-off-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/command.h |  2 +-
 net/sctp/sm_statefuns.c    | 19 ++++++++++++++++---
 2 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index f22538e68245..d4a20d00461c 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -115,7 +115,7 @@ typedef enum {
  * analysis of the state functions, but in reality just taken from
  * thin air in the hopes othat we don't trigger a kernel panic.
  */
-#define SCTP_MAX_NUM_COMMANDS 14
+#define SCTP_MAX_NUM_COMMANDS 20
 
 typedef union {
 	void *zero_all;	/* Set to NULL to clear the entire union */
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index d3f1ea460c50..c8f606324134 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1775,9 +1775,22 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net,
 	/* Update the content of current association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
-	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
-			SCTP_STATE(SCTP_STATE_ESTABLISHED));
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+	if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+	    (sctp_sstate(asoc->base.sk, CLOSING) ||
+	     sock_flag(asoc->base.sk, SOCK_DEAD))) {
+		/* if were currently in SHUTDOWN_PENDING, but the socket
+		 * has been closed by user, don't transition to ESTABLISHED.
+		 * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+		 */
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+		return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
+						     SCTP_ST_CHUNK(0), NULL,
+						     commands);
+	} else {
+		sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
+				SCTP_STATE(SCTP_STATE_ESTABLISHED));
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+	}
 	return SCTP_DISPOSITION_CONSUME;
 
 nomem_ev:
-- 
cgit v1.2.3


From 0b5e8b8eeae40bae6ad7c7e91c97c3c0d0e57882 Mon Sep 17 00:00:00 2001
From: Andy Zhou <azhou@nicira.com>
Date: Fri, 3 Oct 2014 15:35:28 -0700
Subject: net: Add Geneve tunneling protocol driver

This adds a device level support for Geneve -- Generic Network
Virtualization Encapsulation. The protocol is documented at
http://tools.ietf.org/html/draft-gross-geneve-01

Only protocol layer Geneve support is provided by this driver.
Openvswitch can be used for configuring, set up and tear down
functional Geneve tunnels.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/geneve.h     |  91 ++++++++++++
 include/net/ip_tunnels.h |   2 +
 net/ipv4/Kconfig         |  14 ++
 net/ipv4/Makefile        |   1 +
 net/ipv4/geneve.c        | 373 +++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 481 insertions(+)
 create mode 100644 include/net/geneve.h
 create mode 100644 net/ipv4/geneve.c

(limited to 'include')

diff --git a/include/net/geneve.h b/include/net/geneve.h
new file mode 100644
index 000000000000..ce98865318bf
--- /dev/null
+++ b/include/net/geneve.h
@@ -0,0 +1,91 @@
+#ifndef __NET_GENEVE_H
+#define __NET_GENEVE_H  1
+
+#include <net/udp_tunnel.h>
+
+struct geneve_sock;
+
+typedef void (geneve_rcv_t)(struct geneve_sock *gs, struct sk_buff *skb);
+
+struct geneve_sock {
+	struct hlist_node	hlist;
+	geneve_rcv_t		*rcv;
+	void			*rcv_data;
+	struct work_struct	del_work;
+	struct socket		*sock;
+	struct rcu_head		rcu;
+	atomic_t		refcnt;
+	struct udp_offload	udp_offloads;
+};
+
+/* Geneve Header:
+ *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *  |Ver|  Opt Len  |O|C|    Rsvd.  |          Protocol Type        |
+ *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *  |        Virtual Network Identifier (VNI)       |    Reserved   |
+ *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *  |                    Variable Length Options                    |
+ *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * Option Header:
+ *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *  |          Option Class         |      Type     |R|R|R| Length  |
+ *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *  |                      Variable Option Data                     |
+ *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+
+struct geneve_opt {
+	__be16	opt_class;
+	u8	type;
+#ifdef __LITTLE_ENDIAN_BITFIELD
+	u8	length:5;
+	u8	r3:1;
+	u8	r2:1;
+	u8	r1:1;
+#else
+	u8	r1:1;
+	u8	r2:1;
+	u8	r3:1;
+	u8	length:5;
+#endif
+	u8	opt_data[];
+};
+
+#define GENEVE_CRIT_OPT_TYPE (1 << 7)
+
+struct genevehdr {
+#ifdef __LITTLE_ENDIAN_BITFIELD
+	u8 opt_len:6;
+	u8 ver:2;
+	u8 rsvd1:6;
+	u8 critical:1;
+	u8 oam:1;
+#else
+	u8 ver:2;
+	u8 opt_len:6;
+	u8 oam:1;
+	u8 critical:1;
+	u8 rsvd1:6;
+#endif
+	__be16 proto_type;
+	u8 vni[3];
+	u8 rsvd2;
+	struct geneve_opt options[];
+};
+
+#define GENEVE_VER 0
+#define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr))
+
+struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
+				    geneve_rcv_t *rcv, void *data,
+				    bool no_share, bool ipv6);
+
+void geneve_sock_release(struct geneve_sock *vs);
+
+int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
+		    struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos,
+		    __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
+		    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
+		    bool xnet);
+#endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 7f538ba6e267..a9ce1556d773 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -95,6 +95,8 @@ struct ip_tunnel {
 #define TUNNEL_VERSION	__cpu_to_be16(0x40)
 #define TUNNEL_NO_KEY	__cpu_to_be16(0x80)
 #define TUNNEL_DONT_FRAGMENT    __cpu_to_be16(0x0100)
+#define TUNNEL_OAM	__cpu_to_be16(0x0200)
+#define TUNNEL_CRIT_OPT	__cpu_to_be16(0x0400)
 
 struct tnl_ptk_info {
 	__be16 flags;
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 69fb37854449..c2035447e649 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -453,6 +453,20 @@ config TCP_CONG_BIC
 	increase provides TCP friendliness.
 	See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
 
+config GENEVE
+	tristate "Generic Network Virtualization Encapsulation (Geneve)"
+	depends on INET
+	select NET_IP_TUNNEL
+	select NET_UDP_TUNNEL
+	---help---
+	This allows one to create Geneve virtual interfaces that provide
+	Layer 2 Networks over Layer 3 Networks. Geneve is often used
+	to tunnel virtual network infrastructure in virtualized environments.
+	For more information see:
+	  http://tools.ietf.org/html/draft-gross-geneve-01
+
+	  To compile this driver as a module, choose M here: the module
+
 config TCP_CONG_CUBIC
 	tristate "CUBIC TCP"
 	default y
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index d8105787c199..518c04ed666e 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
 obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
 obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
+obj-$(CONFIG_GENEVE) += geneve.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
 		      xfrm4_output.o xfrm4_protocol.o
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
new file mode 100644
index 000000000000..f008c5515f48
--- /dev/null
+++ b/net/ipv4/geneve.c
@@ -0,0 +1,373 @@
+/*
+ * Geneve: Generic Network Virtualization Encapsulation
+ *
+ * Copyright (c) 2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/skbuff.h>
+#include <linux/rculist.h>
+#include <linux/netdevice.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/igmp.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/hash.h>
+#include <linux/ethtool.h>
+#include <net/arp.h>
+#include <net/ndisc.h>
+#include <net/ip.h>
+#include <net/ip_tunnels.h>
+#include <net/icmp.h>
+#include <net/udp.h>
+#include <net/rtnetlink.h>
+#include <net/route.h>
+#include <net/dsfield.h>
+#include <net/inet_ecn.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/geneve.h>
+#include <net/protocol.h>
+#include <net/udp_tunnel.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+#include <net/ip6_tunnel.h>
+#include <net/ip6_checksum.h>
+#endif
+
+#define PORT_HASH_BITS 8
+#define PORT_HASH_SIZE (1<<PORT_HASH_BITS)
+
+/* per-network namespace private data for this module */
+struct geneve_net {
+	struct hlist_head	sock_list[PORT_HASH_SIZE];
+	spinlock_t		sock_lock;   /* Protects sock_list */
+};
+
+static int geneve_net_id;
+
+static struct workqueue_struct *geneve_wq;
+
+static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
+{
+	return (struct genevehdr *)(udp_hdr(skb) + 1);
+}
+
+static struct hlist_head *gs_head(struct net *net, __be16 port)
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+
+	return &gn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
+}
+
+/* Find geneve socket based on network namespace and UDP port */
+static struct geneve_sock *geneve_find_sock(struct net *net, __be16 port)
+{
+	struct geneve_sock *gs;
+
+	hlist_for_each_entry_rcu(gs, gs_head(net, port), hlist) {
+		if (inet_sk(gs->sock->sk)->inet_sport == port)
+			return gs;
+	}
+
+	return NULL;
+}
+
+static void geneve_build_header(struct genevehdr *geneveh,
+				__be16 tun_flags, u8 vni[3],
+				u8 options_len, u8 *options)
+{
+	geneveh->ver = GENEVE_VER;
+	geneveh->opt_len = options_len / 4;
+	geneveh->oam = !!(tun_flags & TUNNEL_OAM);
+	geneveh->critical = !!(tun_flags & TUNNEL_CRIT_OPT);
+	geneveh->rsvd1 = 0;
+	memcpy(geneveh->vni, vni, 3);
+	geneveh->proto_type = htons(ETH_P_TEB);
+	geneveh->rsvd2 = 0;
+
+	memcpy(geneveh->options, options, options_len);
+}
+
+/* Transmit a fully formated Geneve frame.
+ *
+ * When calling this function. The skb->data should point
+ * to the geneve header which is fully formed.
+ *
+ * This function will add other UDP tunnel headers.
+ */
+int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
+		    struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos,
+		    __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
+		    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
+		    bool xnet)
+{
+	struct genevehdr *gnvh;
+	int min_headroom;
+	int err;
+
+	skb = udp_tunnel_handle_offloads(skb, !gs->sock->sk->sk_no_check_tx);
+
+	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr)
+			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+
+	err = skb_cow_head(skb, min_headroom);
+	if (unlikely(err))
+		return err;
+
+	if (vlan_tx_tag_present(skb)) {
+		if (unlikely(!__vlan_put_tag(skb,
+					     skb->vlan_proto,
+					     vlan_tx_tag_get(skb)))) {
+			err = -ENOMEM;
+			return err;
+		}
+		skb->vlan_tci = 0;
+	}
+
+	gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len);
+	geneve_build_header(gnvh, tun_flags, vni, opt_len, opt);
+
+	return udp_tunnel_xmit_skb(gs->sock, rt, skb, src, dst,
+				   tos, ttl, df, src_port, dst_port, xnet);
+}
+EXPORT_SYMBOL_GPL(geneve_xmit_skb);
+
+static void geneve_notify_add_rx_port(struct geneve_sock *gs)
+{
+	struct sock *sk = gs->sock->sk;
+	sa_family_t sa_family = sk->sk_family;
+	int err;
+
+	if (sa_family == AF_INET) {
+		err = udp_add_offload(&gs->udp_offloads);
+		if (err)
+			pr_warn("geneve: udp_add_offload failed with status %d\n",
+				err);
+	}
+}
+
+/* Callback from net/ipv4/udp.c to receive packets */
+static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct genevehdr *geneveh;
+	struct geneve_sock *gs;
+	int opts_len;
+
+	/* Need Geneve and inner Ethernet header to be present */
+	if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN)))
+		goto error;
+
+	/* Return packets with reserved bits set */
+	geneveh = geneve_hdr(skb);
+
+	if (unlikely(geneveh->ver != GENEVE_VER))
+		goto error;
+
+	if (unlikely(geneveh->proto_type != htons(ETH_P_TEB)))
+		goto error;
+
+	opts_len = geneveh->opt_len * 4;
+	if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len,
+				 htons(ETH_P_TEB)))
+		goto drop;
+
+	gs = rcu_dereference_sk_user_data(sk);
+	if (!gs)
+		goto drop;
+
+	gs->rcv(gs, skb);
+	return 0;
+
+drop:
+	/* Consume bad packet */
+	kfree_skb(skb);
+	return 0;
+
+error:
+	/* Let the UDP layer deal with the skb */
+	return 1;
+}
+
+static void geneve_del_work(struct work_struct *work)
+{
+	struct geneve_sock *gs = container_of(work, struct geneve_sock,
+					      del_work);
+
+	udp_tunnel_sock_release(gs->sock);
+	kfree_rcu(gs, rcu);
+}
+
+static struct socket *geneve_create_sock(struct net *net, bool ipv6,
+					 __be16 port)
+{
+	struct socket *sock;
+	struct udp_port_cfg udp_conf;
+	int err;
+
+	memset(&udp_conf, 0, sizeof(udp_conf));
+
+	if (ipv6) {
+		udp_conf.family = AF_INET6;
+	} else {
+		udp_conf.family = AF_INET;
+		udp_conf.local_ip.s_addr = INADDR_ANY;
+	}
+
+	udp_conf.local_udp_port = port;
+
+	/* Open UDP socket */
+	err = udp_sock_create(net, &udp_conf, &sock);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	return sock;
+}
+
+/* Create new listen socket if needed */
+static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
+						geneve_rcv_t *rcv, void *data,
+						bool ipv6)
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	struct geneve_sock *gs;
+	struct socket *sock;
+	struct udp_tunnel_sock_cfg tunnel_cfg;
+
+	gs = kzalloc(sizeof(*gs), GFP_KERNEL);
+	if (!gs)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_WORK(&gs->del_work, geneve_del_work);
+
+	sock = geneve_create_sock(net, ipv6, port);
+	if (IS_ERR(sock)) {
+		kfree(gs);
+		return ERR_CAST(sock);
+	}
+
+	gs->sock = sock;
+	atomic_set(&gs->refcnt, 1);
+	gs->rcv = rcv;
+	gs->rcv_data = data;
+
+	/* Initialize the geneve udp offloads structure */
+	gs->udp_offloads.port = port;
+	gs->udp_offloads.callbacks.gro_receive = NULL;
+	gs->udp_offloads.callbacks.gro_complete = NULL;
+
+	spin_lock(&gn->sock_lock);
+	hlist_add_head_rcu(&gs->hlist, gs_head(net, port));
+	geneve_notify_add_rx_port(gs);
+	spin_unlock(&gn->sock_lock);
+
+	/* Mark socket as an encapsulation socket */
+	tunnel_cfg.sk_user_data = gs;
+	tunnel_cfg.encap_type = 1;
+	tunnel_cfg.encap_rcv = geneve_udp_encap_recv;
+	tunnel_cfg.encap_destroy = NULL;
+	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
+
+	return gs;
+}
+
+struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
+				    geneve_rcv_t *rcv, void *data,
+				    bool no_share, bool ipv6)
+{
+	struct geneve_sock *gs;
+
+	gs = geneve_socket_create(net, port, rcv, data, ipv6);
+	if (!IS_ERR(gs))
+		return gs;
+
+	if (no_share)	/* Return error if sharing is not allowed. */
+		return ERR_PTR(-EINVAL);
+
+	gs = geneve_find_sock(net, port);
+	if (gs) {
+		if (gs->rcv == rcv)
+			atomic_inc(&gs->refcnt);
+		else
+			gs = ERR_PTR(-EBUSY);
+	} else {
+		gs = ERR_PTR(-EINVAL);
+	}
+
+	return gs;
+}
+EXPORT_SYMBOL_GPL(geneve_sock_add);
+
+void geneve_sock_release(struct geneve_sock *gs)
+{
+	if (!atomic_dec_and_test(&gs->refcnt))
+		return;
+
+	queue_work(geneve_wq, &gs->del_work);
+}
+EXPORT_SYMBOL_GPL(geneve_sock_release);
+
+static __net_init int geneve_init_net(struct net *net)
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	unsigned int h;
+
+	spin_lock_init(&gn->sock_lock);
+
+	for (h = 0; h < PORT_HASH_SIZE; ++h)
+		INIT_HLIST_HEAD(&gn->sock_list[h]);
+
+	return 0;
+}
+
+static struct pernet_operations geneve_net_ops = {
+	.init = geneve_init_net,
+	.exit = NULL,
+	.id   = &geneve_net_id,
+	.size = sizeof(struct geneve_net),
+};
+
+static int __init geneve_init_module(void)
+{
+	int rc;
+
+	geneve_wq = alloc_workqueue("geneve", 0, 0);
+	if (!geneve_wq)
+		return -ENOMEM;
+
+	rc = register_pernet_subsys(&geneve_net_ops);
+	if (rc)
+		return rc;
+
+	pr_info("Geneve driver\n");
+
+	return 0;
+}
+late_initcall(geneve_init_module);
+
+static void __exit geneve_cleanup_module(void)
+{
+	destroy_workqueue(geneve_wq);
+}
+module_exit(geneve_cleanup_module);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jesse Gross <jesse@nicira.com>");
+MODULE_DESCRIPTION("Driver for GENEVE encapsulated traffic");
+MODULE_ALIAS_RTNL_LINK("geneve");
-- 
cgit v1.2.3


From 67fa034194bf82a3d5ca841759d921297daa63ca Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Fri, 3 Oct 2014 15:35:30 -0700
Subject: openvswitch: Add support for matching on OAM packets.

Some tunnel formats have mechanisms for indicating that packets are
OAM frames that should be handled specially (either as high priority or
not forwarded beyond an endpoint). This provides support for allowing
those types of packets to be matched.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/openvswitch.h |  1 +
 net/openvswitch/datapath.c       |  1 +
 net/openvswitch/flow_netlink.c   | 17 ++++++++++++-----
 3 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index f7fc507d82ab..7c06106f5af5 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -309,6 +309,7 @@ enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_TTL,                /* u8 Tunnel IP TTL. */
 	OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT,      /* No argument, set DF. */
 	OVS_TUNNEL_KEY_ATTR_CSUM,               /* No argument. CSUM packet. */
+	OVS_TUNNEL_KEY_ATTR_OAM,                /* No argument. OAM frame.  */
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 9e3a2fae6a8f..f6bd93d5f435 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -369,6 +369,7 @@ static size_t key_attr_size(void)
 		  + nla_total_size(1)   /* OVS_TUNNEL_KEY_ATTR_TTL */
 		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
 		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_CSUM */
+		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_OAM */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_IN_PORT */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_SKB_MARK */
 		+ nla_total_size(12)  /* OVS_KEY_ATTR_ETHERNET */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index f4c8daa73965..22c855fa0bc2 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -346,6 +346,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			[OVS_TUNNEL_KEY_ATTR_TTL] = 1,
 			[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0,
 			[OVS_TUNNEL_KEY_ATTR_CSUM] = 0,
+			[OVS_TUNNEL_KEY_ATTR_OAM] = 0,
 		};
 
 		if (type > OVS_TUNNEL_KEY_ATTR_MAX) {
@@ -390,6 +391,9 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 		case OVS_TUNNEL_KEY_ATTR_CSUM:
 			tun_flags |= TUNNEL_CSUM;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_OAM:
+			tun_flags |= TUNNEL_OAM;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -431,21 +435,24 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
 	    nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
 		return -EMSGSIZE;
 	if (output->ipv4_src &&
-		nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src))
+	    nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src))
 		return -EMSGSIZE;
 	if (output->ipv4_dst &&
-		nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst))
+	    nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst))
 		return -EMSGSIZE;
 	if (output->ipv4_tos &&
-		nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos))
+	    nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos))
 		return -EMSGSIZE;
 	if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ipv4_ttl))
 		return -EMSGSIZE;
 	if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) &&
-		nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT))
+	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT))
 		return -EMSGSIZE;
 	if ((output->tun_flags & TUNNEL_CSUM) &&
-		nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
+	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
+		return -EMSGSIZE;
+	if ((output->tun_flags & TUNNEL_OAM) &&
+	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
 		return -EMSGSIZE;
 
 	nla_nest_end(skb, nla);
-- 
cgit v1.2.3


From f0b128c1e2cc33ad104daf0f51a51e34f7763c5f Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Fri, 3 Oct 2014 15:35:31 -0700
Subject: openvswitch: Wrap struct ovs_key_ipv4_tunnel in a new structure.

Currently, the flow information that is matched for tunnels and
the tunnel data passed around with packets is the same. However,
as additional information is added this is not necessarily desirable,
as in the case of pointers.

This adds a new structure for tunnel metadata which currently contains
only the existing struct. This change is purely internal to the kernel
since the current OVS_KEY_ATTR_IPV4_TUNNEL is simply a compressed version
of OVS_KEY_ATTR_TUNNEL that is translated at flow setup.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/openvswitch.h |  2 +-
 net/openvswitch/actions.c        |  5 +++--
 net/openvswitch/datapath.h       |  2 +-
 net/openvswitch/flow.c           |  6 +++---
 net/openvswitch/flow.h           | 30 +++++++++++++++++-------------
 net/openvswitch/flow_netlink.c   | 38 +++++++++++++++++++++++++++++++-------
 net/openvswitch/vport-gre.c      | 16 +++++++++-------
 net/openvswitch/vport-vxlan.c    | 10 +++++-----
 net/openvswitch/vport.c          |  6 +++---
 net/openvswitch/vport.h          |  2 +-
 10 files changed, 74 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 7c06106f5af5..6753032832e2 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -294,7 +294,7 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_RECIRC_ID, /* u32 recirc id */
 
 #ifdef __KERNEL__
-	OVS_KEY_ATTR_IPV4_TUNNEL,  /* struct ovs_key_ipv4_tunnel */
+	OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ovs_tunnel_info */
 #endif
 	__OVS_KEY_ATTR_MAX
 };
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 6932a42e41a2..006886dbee36 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -590,8 +590,8 @@ static int execute_set_action(struct sk_buff *skb,
 		skb->mark = nla_get_u32(nested_attr);
 		break;
 
-	case OVS_KEY_ATTR_IPV4_TUNNEL:
-		OVS_CB(skb)->egress_tun_key = nla_data(nested_attr);
+	case OVS_KEY_ATTR_TUNNEL_INFO:
+		OVS_CB(skb)->egress_tun_info = nla_data(nested_attr);
 		break;
 
 	case OVS_KEY_ATTR_ETHERNET:
@@ -778,6 +778,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
 
 	this_cpu_inc(exec_actions_level);
+	OVS_CB(skb)->egress_tun_info = NULL;
 	err = do_execute_actions(dp, skb, key,
 				 acts->actions, acts->actions_len);
 
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index ac3f3df96961..974135439c5c 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -102,8 +102,8 @@ struct datapath {
  */
 struct ovs_skb_cb {
 	struct sw_flow		*flow;
+	struct ovs_tunnel_info  *egress_tun_info;
 	struct vport		*input_vport;
-	struct ovs_key_ipv4_tunnel  *egress_tun_key;
 };
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
 
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 913bdc1a83c0..2924cb340868 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -642,12 +642,12 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
 	return key_extract(skb, key);
 }
 
-int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key,
+int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
 			 struct sk_buff *skb, struct sw_flow_key *key)
 {
 	/* Extract metadata from packet. */
-	if (tun_key)
-		memcpy(&key->tun_key, tun_key, sizeof(key->tun_key));
+	if (tun_info)
+		memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key));
 	else
 		memset(&key->tun_key, 0, sizeof(key->tun_key));
 
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 0f5db4ec565d..fe5a71b81c1f 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -49,20 +49,24 @@ struct ovs_key_ipv4_tunnel {
 	u8   ipv4_ttl;
 } __packed __aligned(4); /* Minimize padding. */
 
-static inline void ovs_flow_tun_key_init(struct ovs_key_ipv4_tunnel *tun_key,
-					 const struct iphdr *iph, __be64 tun_id,
-					 __be16 tun_flags)
+struct ovs_tunnel_info {
+	struct ovs_key_ipv4_tunnel tunnel;
+};
+
+static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+					  const struct iphdr *iph,
+					  __be64 tun_id, __be16 tun_flags)
 {
-	tun_key->tun_id = tun_id;
-	tun_key->ipv4_src = iph->saddr;
-	tun_key->ipv4_dst = iph->daddr;
-	tun_key->ipv4_tos = iph->tos;
-	tun_key->ipv4_ttl = iph->ttl;
-	tun_key->tun_flags = tun_flags;
+	tun_info->tunnel.tun_id = tun_id;
+	tun_info->tunnel.ipv4_src = iph->saddr;
+	tun_info->tunnel.ipv4_dst = iph->daddr;
+	tun_info->tunnel.ipv4_tos = iph->tos;
+	tun_info->tunnel.ipv4_ttl = iph->ttl;
+	tun_info->tunnel.tun_flags = tun_flags;
 
 	/* clear struct padding. */
-	memset((unsigned char *) tun_key + OVS_TUNNEL_KEY_SIZE, 0,
-	       sizeof(*tun_key) - OVS_TUNNEL_KEY_SIZE);
+	memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
+	       sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
 }
 
 struct sw_flow_key {
@@ -190,8 +194,8 @@ void ovs_flow_stats_clear(struct sw_flow *);
 u64 ovs_flow_used_time(unsigned long flow_jiffies);
 
 int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
-int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key,
-			 struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info, struct sk_buff *skb,
+			 struct sw_flow_key *key);
 /* Extract key from packet coming from userspace. */
 int ovs_flow_key_extract_userspace(const struct nlattr *attr,
 				   struct sk_buff *skb,
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 22c855fa0bc2..5d6194d9dadc 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1148,13 +1148,14 @@ out:
 	return  (struct nlattr *) ((unsigned char *)(*sfa) + next_offset);
 }
 
-static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len)
+static struct nlattr *__add_action(struct sw_flow_actions **sfa,
+				   int attrtype, void *data, int len)
 {
 	struct nlattr *a;
 
 	a = reserve_sfa_size(sfa, nla_attr_size(len));
 	if (IS_ERR(a))
-		return PTR_ERR(a);
+		return a;
 
 	a->nla_type = attrtype;
 	a->nla_len = nla_attr_size(len);
@@ -1163,6 +1164,18 @@ static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, in
 		memcpy(nla_data(a), data, len);
 	memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len));
 
+	return a;
+}
+
+static int add_action(struct sw_flow_actions **sfa, int attrtype,
+		      void *data, int len)
+{
+	struct nlattr *a;
+
+	a = __add_action(sfa, attrtype, data, len);
+	if (IS_ERR(a))
+		return PTR_ERR(a);
+
 	return 0;
 }
 
@@ -1268,6 +1281,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 {
 	struct sw_flow_match match;
 	struct sw_flow_key key;
+	struct ovs_tunnel_info *tun_info;
+	struct nlattr *a;
 	int err, start;
 
 	ovs_match_init(&match, &key, NULL);
@@ -1279,8 +1294,14 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	if (start < 0)
 		return start;
 
-	err = add_action(sfa, OVS_KEY_ATTR_IPV4_TUNNEL, &match.key->tun_key,
-			sizeof(match.key->tun_key));
+	a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
+			 sizeof(*tun_info));
+	if (IS_ERR(a))
+		return PTR_ERR(a);
+
+	tun_info = nla_data(a);
+	tun_info->tunnel = key.tun_key;
+
 	add_nested_action_end(*sfa, start);
 
 	return err;
@@ -1563,17 +1584,20 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 	int err;
 
 	switch (key_type) {
-	case OVS_KEY_ATTR_IPV4_TUNNEL:
+	case OVS_KEY_ATTR_TUNNEL_INFO: {
+		struct ovs_tunnel_info *tun_info = nla_data(ovs_key);
+
 		start = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
 		if (!start)
 			return -EMSGSIZE;
 
-		err = ipv4_tun_to_nlattr(skb, nla_data(ovs_key),
-					     nla_data(ovs_key));
+		err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel,
+					 nla_data(ovs_key));
 		if (err)
 			return err;
 		nla_nest_end(skb, start);
 		break;
+	}
 	default:
 		if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a), ovs_key))
 			return -EMSGSIZE;
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 309cca6e816f..fe768bd600eb 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -63,8 +63,10 @@ static __be16 filter_tnl_flags(__be16 flags)
 static struct sk_buff *__build_header(struct sk_buff *skb,
 				      int tunnel_hlen)
 {
-	const struct ovs_key_ipv4_tunnel *tun_key = OVS_CB(skb)->egress_tun_key;
 	struct tnl_ptk_info tpi;
+	const struct ovs_key_ipv4_tunnel *tun_key;
+
+	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
 
 	skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM));
 	if (IS_ERR(skb))
@@ -92,7 +94,7 @@ static __be64 key_to_tunnel_id(__be32 key, __be32 seq)
 static int gre_rcv(struct sk_buff *skb,
 		   const struct tnl_ptk_info *tpi)
 {
-	struct ovs_key_ipv4_tunnel tun_key;
+	struct ovs_tunnel_info tun_info;
 	struct ovs_net *ovs_net;
 	struct vport *vport;
 	__be64 key;
@@ -103,10 +105,10 @@ static int gre_rcv(struct sk_buff *skb,
 		return PACKET_REJECT;
 
 	key = key_to_tunnel_id(tpi->key, tpi->seq);
-	ovs_flow_tun_key_init(&tun_key, ip_hdr(skb), key,
-			      filter_tnl_flags(tpi->flags));
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
+			       filter_tnl_flags(tpi->flags));
 
-	ovs_vport_receive(vport, skb, &tun_key);
+	ovs_vport_receive(vport, skb, &tun_info);
 	return PACKET_RCVD;
 }
 
@@ -137,12 +139,12 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 	__be16 df;
 	int err;
 
-	if (unlikely(!OVS_CB(skb)->egress_tun_key)) {
+	if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
 		err = -EINVAL;
 		goto error;
 	}
 
-	tun_key = OVS_CB(skb)->egress_tun_key;
+	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
 	/* Route lookup */
 	memset(&fl, 0, sizeof(fl));
 	fl.daddr = tun_key->ipv4_dst;
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index f19539bb8adc..5fbff2c1ee49 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -58,7 +58,7 @@ static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
 /* Called with rcu_read_lock and BH disabled. */
 static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
 {
-	struct ovs_key_ipv4_tunnel tun_key;
+	struct ovs_tunnel_info tun_info;
 	struct vport *vport = vs->data;
 	struct iphdr *iph;
 	__be64 key;
@@ -66,9 +66,9 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
 	/* Save outer tunnel values */
 	iph = ip_hdr(skb);
 	key = cpu_to_be64(ntohl(vx_vni) >> 8);
-	ovs_flow_tun_key_init(&tun_key, iph, key, TUNNEL_KEY);
+	ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY);
 
-	ovs_vport_receive(vport, skb, &tun_key);
+	ovs_vport_receive(vport, skb, &tun_info);
 }
 
 static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
@@ -147,12 +147,12 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	__be16 df;
 	int err;
 
-	if (unlikely(!OVS_CB(skb)->egress_tun_key)) {
+	if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
 		err = -EINVAL;
 		goto error;
 	}
 
-	tun_key = OVS_CB(skb)->egress_tun_key;
+	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
 	/* Route lookup */
 	memset(&fl, 0, sizeof(fl));
 	fl.daddr = tun_key->ipv4_dst;
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 5df8377fcfb1..3e50ee8a218c 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -432,7 +432,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *p, struct sk_buff *skb)
  * skb->data should point to the Ethernet header.
  */
 void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
-		       struct ovs_key_ipv4_tunnel *tun_key)
+		       struct ovs_tunnel_info *tun_info)
 {
 	struct pcpu_sw_netstats *stats;
 	struct sw_flow_key key;
@@ -445,9 +445,9 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 	u64_stats_update_end(&stats->syncp);
 
 	OVS_CB(skb)->input_vport = vport;
-	OVS_CB(skb)->egress_tun_key = NULL;
+	OVS_CB(skb)->egress_tun_info = NULL;
 	/* Extract flow from 'skb' into 'key'. */
-	error = ovs_flow_key_extract(tun_key, skb, &key);
+	error = ovs_flow_key_extract(tun_info, skb, &key);
 	if (unlikely(error)) {
 		kfree_skb(skb);
 		return;
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 0efd62fef1e8..e28964aba021 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -207,7 +207,7 @@ static inline struct vport *vport_from_priv(void *priv)
 }
 
 void ovs_vport_receive(struct vport *, struct sk_buff *,
-		       struct ovs_key_ipv4_tunnel *);
+		       struct ovs_tunnel_info *);
 
 /* List of statically compiled vport implementations.  Don't forget to also
  * add yours to the list at the top of vport.c. */
-- 
cgit v1.2.3


From f5796684069e0c71c65bce6a6d4766114aec1396 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Fri, 3 Oct 2014 15:35:33 -0700
Subject: openvswitch: Add support for Geneve tunneling.

The Openvswitch implementation is completely agnostic to the options
that are in use and can handle newly defined options without
further work. It does this by simply matching on a byte array
of options and allowing userspace to setup flows on this array.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Singed-off-by: Ansis Atteka <aatteka@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
Acked-by: Thomas Graf <tgraf@noironetworks.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_tunnels.h         |  21 ++--
 include/uapi/linux/openvswitch.h |   2 +
 net/openvswitch/Kconfig          |  11 ++
 net/openvswitch/Makefile         |   4 +
 net/openvswitch/datapath.c       |   5 +-
 net/openvswitch/flow.c           |  20 +++-
 net/openvswitch/flow.h           |  20 +++-
 net/openvswitch/flow_netlink.c   | 176 ++++++++++++++++++++++++-----
 net/openvswitch/vport-geneve.c   | 236 +++++++++++++++++++++++++++++++++++++++
 net/openvswitch/vport-gre.c      |   2 +-
 net/openvswitch/vport-vxlan.c    |   2 +-
 net/openvswitch/vport.c          |   3 +
 net/openvswitch/vport.h          |   1 +
 13 files changed, 461 insertions(+), 42 deletions(-)
 create mode 100644 net/openvswitch/vport-geneve.c

(limited to 'include')

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index a9ce1556d773..5bc6edeb7143 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -86,17 +86,18 @@ struct ip_tunnel {
 	struct gro_cells	gro_cells;
 };
 
-#define TUNNEL_CSUM	__cpu_to_be16(0x01)
-#define TUNNEL_ROUTING	__cpu_to_be16(0x02)
-#define TUNNEL_KEY	__cpu_to_be16(0x04)
-#define TUNNEL_SEQ	__cpu_to_be16(0x08)
-#define TUNNEL_STRICT	__cpu_to_be16(0x10)
-#define TUNNEL_REC	__cpu_to_be16(0x20)
-#define TUNNEL_VERSION	__cpu_to_be16(0x40)
-#define TUNNEL_NO_KEY	__cpu_to_be16(0x80)
+#define TUNNEL_CSUM		__cpu_to_be16(0x01)
+#define TUNNEL_ROUTING		__cpu_to_be16(0x02)
+#define TUNNEL_KEY		__cpu_to_be16(0x04)
+#define TUNNEL_SEQ		__cpu_to_be16(0x08)
+#define TUNNEL_STRICT		__cpu_to_be16(0x10)
+#define TUNNEL_REC		__cpu_to_be16(0x20)
+#define TUNNEL_VERSION		__cpu_to_be16(0x40)
+#define TUNNEL_NO_KEY		__cpu_to_be16(0x80)
 #define TUNNEL_DONT_FRAGMENT    __cpu_to_be16(0x0100)
-#define TUNNEL_OAM	__cpu_to_be16(0x0200)
-#define TUNNEL_CRIT_OPT	__cpu_to_be16(0x0400)
+#define TUNNEL_OAM		__cpu_to_be16(0x0200)
+#define TUNNEL_CRIT_OPT		__cpu_to_be16(0x0400)
+#define TUNNEL_OPTIONS_PRESENT	__cpu_to_be16(0x0800)
 
 struct tnl_ptk_info {
 	__be16 flags;
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 6753032832e2..435eabc5ffaa 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -192,6 +192,7 @@ enum ovs_vport_type {
 	OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */
 	OVS_VPORT_TYPE_GRE,      /* GRE tunnel. */
 	OVS_VPORT_TYPE_VXLAN,	 /* VXLAN tunnel. */
+	OVS_VPORT_TYPE_GENEVE,	 /* Geneve tunnel. */
 	__OVS_VPORT_TYPE_MAX
 };
 
@@ -310,6 +311,7 @@ enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT,      /* No argument, set DF. */
 	OVS_TUNNEL_KEY_ATTR_CSUM,               /* No argument. CSUM packet. */
 	OVS_TUNNEL_KEY_ATTR_OAM,                /* No argument. OAM frame.  */
+	OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,        /* Array of Geneve options. */
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 6ecf491ad509..ba3bb8203b99 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -54,3 +54,14 @@ config OPENVSWITCH_VXLAN
 	  Say N to exclude this support and reduce the binary size.
 
 	  If unsure, say Y.
+
+config OPENVSWITCH_GENEVE
+	bool "Open vSwitch Geneve tunneling support"
+	depends on INET
+	depends on OPENVSWITCH
+	depends on GENEVE && !(OPENVSWITCH=y && GENEVE=m)
+	default y
+	---help---
+	  If you say Y here, then the Open vSwitch will be able create geneve vport.
+
+	  Say N to exclude this support and reduce the binary size.
diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile
index 3591cb5dae91..9a33a273c375 100644
--- a/net/openvswitch/Makefile
+++ b/net/openvswitch/Makefile
@@ -15,6 +15,10 @@ openvswitch-y := \
 	vport-internal_dev.o \
 	vport-netdev.o
 
+ifneq ($(CONFIG_OPENVSWITCH_GENEVE),)
+openvswitch-y += vport-geneve.o
+endif
+
 ifneq ($(CONFIG_OPENVSWITCH_VXLAN),)
 openvswitch-y += vport-vxlan.o
 endif
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 010125c48244..2e31d9e7f4dc 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -370,6 +370,7 @@ static size_t key_attr_size(void)
 		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
 		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_CSUM */
 		  + nla_total_size(0)   /* OVS_TUNNEL_KEY_ATTR_OAM */
+		  + nla_total_size(256)   /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_IN_PORT */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_SKB_MARK */
 		+ nla_total_size(12)  /* OVS_KEY_ATTR_ETHERNET */
@@ -556,10 +557,12 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 
 	err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
 				   &flow->key, 0, &acts);
-	rcu_assign_pointer(flow->sf_acts, acts);
 	if (err)
 		goto err_flow_free;
 
+	rcu_assign_pointer(flow->sf_acts, acts);
+
+	OVS_CB(packet)->egress_tun_info = NULL;
 	OVS_CB(packet)->flow = flow;
 	packet->priority = flow->key.phy.priority;
 	packet->mark = flow->key.phy.skb_mark;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 2924cb340868..62db02ba36bc 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -448,6 +448,9 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 	int error;
 	struct ethhdr *eth;
 
+	/* Flags are always used as part of stats */
+	key->tp.flags = 0;
+
 	skb_reset_mac_header(skb);
 
 	/* Link layer.  We are guaranteed to have at least the 14 byte Ethernet
@@ -646,10 +649,23 @@ int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
 			 struct sk_buff *skb, struct sw_flow_key *key)
 {
 	/* Extract metadata from packet. */
-	if (tun_info)
+	if (tun_info) {
 		memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key));
-	else
+
+		if (tun_info->options) {
+			BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) *
+						   8)) - 1
+					> sizeof(key->tun_opts));
+			memcpy(GENEVE_OPTS(key, tun_info->options_len),
+			       tun_info->options, tun_info->options_len);
+			key->tun_opts_len = tun_info->options_len;
+		} else {
+			key->tun_opts_len = 0;
+		}
+	} else  {
+		key->tun_opts_len = 0;
 		memset(&key->tun_key, 0, sizeof(key->tun_key));
+	}
 
 	key->phy.priority = skb->priority;
 	key->phy.in_port = OVS_CB(skb)->input_vport->port_no;
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index fe5a71b81c1f..71813318c8c7 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -51,11 +51,24 @@ struct ovs_key_ipv4_tunnel {
 
 struct ovs_tunnel_info {
 	struct ovs_key_ipv4_tunnel tunnel;
+	struct geneve_opt *options;
+	u8 options_len;
 };
 
+/* Store options at the end of the array if they are less than the
+ * maximum size. This allows us to get the benefits of variable length
+ * matching for small options.
+ */
+#define GENEVE_OPTS(flow_key, opt_len)	\
+	((struct geneve_opt *)((flow_key)->tun_opts + \
+			       FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \
+			       opt_len))
+
 static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
 					  const struct iphdr *iph,
-					  __be64 tun_id, __be16 tun_flags)
+					  __be64 tun_id, __be16 tun_flags,
+					  struct geneve_opt *opts,
+					  u8 opts_len)
 {
 	tun_info->tunnel.tun_id = tun_id;
 	tun_info->tunnel.ipv4_src = iph->saddr;
@@ -67,9 +80,14 @@ static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
 	/* clear struct padding. */
 	memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
 	       sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+
+	tun_info->options = opts;
+	tun_info->options_len = opts_len;
 }
 
 struct sw_flow_key {
+	u8 tun_opts[255];
+	u8 tun_opts_len;
 	struct ovs_key_ipv4_tunnel tun_key;  /* Encapsulating tunnel key. */
 	struct {
 		u32	priority;	/* Packet QoS priority. */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 5d6194d9dadc..368f23307911 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -42,6 +42,7 @@
 #include <linux/icmp.h>
 #include <linux/icmpv6.h>
 #include <linux/rculist.h>
+#include <net/geneve.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ndisc.h>
@@ -88,18 +89,20 @@ static void update_range__(struct sw_flow_match *match,
 		}                                                           \
 	} while (0)
 
-#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \
-	do { \
-		update_range__(match, offsetof(struct sw_flow_key, field),  \
-				len, is_mask);                              \
-		if (is_mask) {						    \
-			if ((match)->mask)				    \
-				memcpy(&(match)->mask->key.field, value_p, len);\
-		} else {                                                    \
-			memcpy(&(match)->key->field, value_p, len);         \
-		}                                                           \
+#define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask)	    \
+	do {								    \
+		update_range__(match, offset, len, is_mask);		    \
+		if (is_mask)						    \
+			memcpy((u8 *)&(match)->mask->key + offset, value_p, \
+			       len);					    \
+		else							    \
+			memcpy((u8 *)(match)->key + offset, value_p, len);  \
 	} while (0)
 
+#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask)		      \
+	SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \
+				  value_p, len, is_mask)
+
 static u16 range_n_bytes(const struct sw_flow_key_range *range)
 {
 	return range->end - range->start;
@@ -335,6 +338,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 	int rem;
 	bool ttl = false;
 	__be16 tun_flags = 0;
+	unsigned long opt_key_offset;
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
@@ -347,6 +351,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0,
 			[OVS_TUNNEL_KEY_ATTR_CSUM] = 0,
 			[OVS_TUNNEL_KEY_ATTR_OAM] = 0,
+			[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1,
 		};
 
 		if (type > OVS_TUNNEL_KEY_ATTR_MAX) {
@@ -355,7 +360,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			return -EINVAL;
 		}
 
-		if (ovs_tunnel_key_lens[type] != nla_len(a)) {
+		if (ovs_tunnel_key_lens[type] != nla_len(a) &&
+		    ovs_tunnel_key_lens[type] != -1) {
 			OVS_NLERR("IPv4 tunnel attribute type has unexpected "
 				  " length (type=%d, length=%d, expected=%d).\n",
 				  type, nla_len(a), ovs_tunnel_key_lens[type]);
@@ -394,7 +400,60 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 		case OVS_TUNNEL_KEY_ATTR_OAM:
 			tun_flags |= TUNNEL_OAM;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
+			tun_flags |= TUNNEL_OPTIONS_PRESENT;
+			if (nla_len(a) > sizeof(match->key->tun_opts)) {
+				OVS_NLERR("Geneve option length exceeds maximum size (len %d, max %zu).\n",
+					  nla_len(a),
+					  sizeof(match->key->tun_opts));
+				return -EINVAL;
+			}
+
+			if (nla_len(a) % 4 != 0) {
+				OVS_NLERR("Geneve option length is not a multiple of 4 (len %d).\n",
+					  nla_len(a));
+				return -EINVAL;
+			}
+
+			/* We need to record the length of the options passed
+			 * down, otherwise packets with the same format but
+			 * additional options will be silently matched.
+			 */
+			if (!is_mask) {
+				SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a),
+						false);
+			} else {
+				/* This is somewhat unusual because it looks at
+				 * both the key and mask while parsing the
+				 * attributes (and by extension assumes the key
+				 * is parsed first). Normally, we would verify
+				 * that each is the correct length and that the
+				 * attributes line up in the validate function.
+				 * However, that is difficult because this is
+				 * variable length and we won't have the
+				 * information later.
+				 */
+				if (match->key->tun_opts_len != nla_len(a)) {
+					OVS_NLERR("Geneve option key length (%d) is different from mask length (%d).",
+						  match->key->tun_opts_len,
+						  nla_len(a));
+					return -EINVAL;
+				}
+
+				SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff,
+						true);
+			}
+
+			opt_key_offset = (unsigned long)GENEVE_OPTS(
+					  (struct sw_flow_key *)0,
+					  nla_len(a));
+			SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset,
+						  nla_data(a), nla_len(a),
+						  is_mask);
+			break;
 		default:
+			OVS_NLERR("Unknown IPv4 tunnel attribute (%d).\n",
+				  type);
 			return -EINVAL;
 		}
 	}
@@ -421,16 +480,11 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 	return 0;
 }
 
-static int ipv4_tun_to_nlattr(struct sk_buff *skb,
-			      const struct ovs_key_ipv4_tunnel *tun_key,
-			      const struct ovs_key_ipv4_tunnel *output)
+static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
+				const struct ovs_key_ipv4_tunnel *output,
+				const struct geneve_opt *tun_opts,
+				int swkey_tun_opts_len)
 {
-	struct nlattr *nla;
-
-	nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
-	if (!nla)
-		return -EMSGSIZE;
-
 	if (output->tun_flags & TUNNEL_KEY &&
 	    nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
 		return -EMSGSIZE;
@@ -454,12 +508,35 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
 	if ((output->tun_flags & TUNNEL_OAM) &&
 	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
 		return -EMSGSIZE;
+	if (tun_opts &&
+	    nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
+		    swkey_tun_opts_len, tun_opts))
+		return -EMSGSIZE;
 
-	nla_nest_end(skb, nla);
 	return 0;
 }
 
 
+static int ipv4_tun_to_nlattr(struct sk_buff *skb,
+			      const struct ovs_key_ipv4_tunnel *output,
+			      const struct geneve_opt *tun_opts,
+			      int swkey_tun_opts_len)
+{
+	struct nlattr *nla;
+	int err;
+
+	nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
+	if (!nla)
+		return -EMSGSIZE;
+
+	err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len);
+	if (err)
+		return err;
+
+	nla_nest_end(skb, nla);
+	return 0;
+}
+
 static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 				 const struct nlattr **a, bool is_mask)
 {
@@ -905,9 +982,16 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 	if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
 		goto nla_put_failure;
 
-	if ((swkey->tun_key.ipv4_dst || is_mask) &&
-	    ipv4_tun_to_nlattr(skb, &swkey->tun_key, &output->tun_key))
-		goto nla_put_failure;
+	if ((swkey->tun_key.ipv4_dst || is_mask)) {
+		const struct geneve_opt *opts = NULL;
+
+		if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
+			opts = GENEVE_OPTS(output, swkey->tun_opts_len);
+
+		if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts,
+				       swkey->tun_opts_len))
+			goto nla_put_failure;
+	}
 
 	if (swkey->phy.in_port == DP_MAX_PORTS) {
 		if (is_mask && (output->phy.in_port == 0xffff))
@@ -1290,17 +1374,55 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	if (err)
 		return err;
 
+	if (key.tun_opts_len) {
+		struct geneve_opt *option = GENEVE_OPTS(&key,
+							key.tun_opts_len);
+		int opts_len = key.tun_opts_len;
+		bool crit_opt = false;
+
+		while (opts_len > 0) {
+			int len;
+
+			if (opts_len < sizeof(*option))
+				return -EINVAL;
+
+			len = sizeof(*option) + option->length * 4;
+			if (len > opts_len)
+				return -EINVAL;
+
+			crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE);
+
+			option = (struct geneve_opt *)((u8 *)option + len);
+			opts_len -= len;
+		};
+
+		key.tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0;
+	};
+
 	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET);
 	if (start < 0)
 		return start;
 
 	a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
-			 sizeof(*tun_info));
+			 sizeof(*tun_info) + key.tun_opts_len);
 	if (IS_ERR(a))
 		return PTR_ERR(a);
 
 	tun_info = nla_data(a);
 	tun_info->tunnel = key.tun_key;
+	tun_info->options_len = key.tun_opts_len;
+
+	if (tun_info->options_len) {
+		/* We need to store the options in the action itself since
+		 * everything else will go away after flow setup. We can append
+		 * it to tun_info and then point there.
+		 */
+		memcpy((tun_info + 1), GENEVE_OPTS(&key, key.tun_opts_len),
+		       key.tun_opts_len);
+		tun_info->options = (struct geneve_opt *)(tun_info + 1);
+	} else {
+		tun_info->options = NULL;
+	}
 
 	add_nested_action_end(*sfa, start);
 
@@ -1592,7 +1714,9 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 			return -EMSGSIZE;
 
 		err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel,
-					 nla_data(ovs_key));
+					 tun_info->options_len ?
+						tun_info->options : NULL,
+					 tun_info->options_len);
 		if (err)
 			return err;
 		nla_nest_end(skb, start);
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
new file mode 100644
index 000000000000..5572d482f285
--- /dev/null
+++ b/net/openvswitch/vport-geneve.c
@@ -0,0 +1,236 @@
+/*
+ * Copyright (c) 2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/version.h>
+
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/net.h>
+#include <linux/rculist.h>
+#include <linux/udp.h>
+#include <linux/if_vlan.h>
+
+#include <net/geneve.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include "datapath.h"
+#include "vport.h"
+
+/**
+ * struct geneve_port - Keeps track of open UDP ports
+ * @sock: The socket created for this port number.
+ * @name: vport name.
+ */
+struct geneve_port {
+	struct geneve_sock *gs;
+	char name[IFNAMSIZ];
+};
+
+static LIST_HEAD(geneve_ports);
+
+static inline struct geneve_port *geneve_vport(const struct vport *vport)
+{
+	return vport_priv(vport);
+}
+
+static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
+{
+	return (struct genevehdr *)(udp_hdr(skb) + 1);
+}
+
+/* Convert 64 bit tunnel ID to 24 bit VNI. */
+static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+	vni[0] = (__force __u8)(tun_id >> 16);
+	vni[1] = (__force __u8)(tun_id >> 8);
+	vni[2] = (__force __u8)tun_id;
+#else
+	vni[0] = (__force __u8)((__force u64)tun_id >> 40);
+	vni[1] = (__force __u8)((__force u64)tun_id >> 48);
+	vni[2] = (__force __u8)((__force u64)tun_id >> 56);
+#endif
+}
+
+/* Convert 24 bit VNI to 64 bit tunnel ID. */
+static __be64 vni_to_tunnel_id(__u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+	return (vni[0] << 16) | (vni[1] << 8) | vni[2];
+#else
+	return (__force __be64)(((__force u64)vni[0] << 40) |
+				((__force u64)vni[1] << 48) |
+				((__force u64)vni[2] << 56));
+#endif
+}
+
+static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
+{
+	struct vport *vport = gs->rcv_data;
+	struct genevehdr *geneveh = geneve_hdr(skb);
+	int opts_len;
+	struct ovs_tunnel_info tun_info;
+	__be64 key;
+	__be16 flags;
+
+	opts_len = geneveh->opt_len * 4;
+
+	flags = TUNNEL_KEY | TUNNEL_OPTIONS_PRESENT |
+		(udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) |
+		(geneveh->oam ? TUNNEL_OAM : 0) |
+		(geneveh->critical ? TUNNEL_CRIT_OPT : 0);
+
+	key = vni_to_tunnel_id(geneveh->vni);
+
+	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, flags,
+			       geneveh->options, opts_len);
+
+	ovs_vport_receive(vport, skb, &tun_info);
+}
+
+static int geneve_get_options(const struct vport *vport,
+			      struct sk_buff *skb)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+	__be16 sport;
+
+	sport = ntohs(inet_sk(geneve_port->gs->sock->sk)->inet_sport);
+	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, sport))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static void geneve_tnl_destroy(struct vport *vport)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+
+	geneve_sock_release(geneve_port->gs);
+
+	ovs_vport_deferred_free(vport);
+}
+
+static struct vport *geneve_tnl_create(const struct vport_parms *parms)
+{
+	struct net *net = ovs_dp_get_net(parms->dp);
+	struct nlattr *options = parms->options;
+	struct geneve_port *geneve_port;
+	struct geneve_sock *gs;
+	struct vport *vport;
+	struct nlattr *a;
+	int err;
+	u16 dst_port;
+
+	if (!options) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
+	if (a && nla_len(a) == sizeof(u16)) {
+		dst_port = nla_get_u16(a);
+	} else {
+		/* Require destination port from userspace. */
+		err = -EINVAL;
+		goto error;
+	}
+
+	vport = ovs_vport_alloc(sizeof(struct geneve_port),
+				&ovs_geneve_vport_ops, parms);
+	if (IS_ERR(vport))
+		return vport;
+
+	geneve_port = geneve_vport(vport);
+	strncpy(geneve_port->name, parms->name, IFNAMSIZ);
+
+	gs = geneve_sock_add(net, htons(dst_port), geneve_rcv, vport, true, 0);
+	if (IS_ERR(gs)) {
+		ovs_vport_free(vport);
+		return (void *)gs;
+	}
+	geneve_port->gs = gs;
+
+	return vport;
+error:
+	return ERR_PTR(err);
+}
+
+static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
+{
+	struct ovs_key_ipv4_tunnel *tun_key;
+	struct ovs_tunnel_info *tun_info;
+	struct net *net = ovs_dp_get_net(vport->dp);
+	struct geneve_port *geneve_port = geneve_vport(vport);
+	__be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
+	__be16 sport;
+	struct rtable *rt;
+	struct flowi4 fl;
+	u8 vni[3];
+	__be16 df;
+	int err;
+
+	tun_info = OVS_CB(skb)->egress_tun_info;
+	if (unlikely(!tun_info)) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	tun_key = &tun_info->tunnel;
+
+	/* Route lookup */
+	memset(&fl, 0, sizeof(fl));
+	fl.daddr = tun_key->ipv4_dst;
+	fl.saddr = tun_key->ipv4_src;
+	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+	fl.flowi4_mark = skb->mark;
+	fl.flowi4_proto = IPPROTO_UDP;
+
+	rt = ip_route_output_key(net, &fl);
+	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
+		goto error;
+	}
+
+	df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
+	sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
+	tunnel_id_to_vni(tun_key->tun_id, vni);
+	skb->ignore_df = 1;
+
+	err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr,
+			      tun_key->ipv4_dst, tun_key->ipv4_tos,
+			      tun_key->ipv4_ttl, df, sport, dport,
+			      tun_key->tun_flags, vni,
+			      tun_info->options_len, (u8 *)tun_info->options,
+			      false);
+	if (err < 0)
+		ip_rt_put(rt);
+error:
+	return err;
+}
+
+static const char *geneve_get_name(const struct vport *vport)
+{
+	struct geneve_port *geneve_port = geneve_vport(vport);
+
+	return geneve_port->name;
+}
+
+const struct vport_ops ovs_geneve_vport_ops = {
+	.type		= OVS_VPORT_TYPE_GENEVE,
+	.create		= geneve_tnl_create,
+	.destroy	= geneve_tnl_destroy,
+	.get_name	= geneve_get_name,
+	.get_options	= geneve_get_options,
+	.send		= geneve_tnl_send,
+};
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index fe768bd600eb..108b82da2fd9 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -106,7 +106,7 @@ static int gre_rcv(struct sk_buff *skb,
 
 	key = key_to_tunnel_id(tpi->key, tpi->seq);
 	ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
-			       filter_tnl_flags(tpi->flags));
+			       filter_tnl_flags(tpi->flags), NULL, 0);
 
 	ovs_vport_receive(vport, skb, &tun_info);
 	return PACKET_RCVD;
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 5fbff2c1ee49..2735e01dca73 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -66,7 +66,7 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
 	/* Save outer tunnel values */
 	iph = ip_hdr(skb);
 	key = cpu_to_be64(ntohl(vx_vni) >> 8);
-	ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY);
+	ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY, NULL, 0);
 
 	ovs_vport_receive(vport, skb, &tun_info);
 }
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 3e50ee8a218c..53001b020ca7 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -48,6 +48,9 @@ static const struct vport_ops *vport_ops_list[] = {
 #ifdef CONFIG_OPENVSWITCH_VXLAN
 	&ovs_vxlan_vport_ops,
 #endif
+#ifdef CONFIG_OPENVSWITCH_GENEVE
+	&ovs_geneve_vport_ops,
+#endif
 };
 
 /* Protected by RCU read lock for reading, ovs_mutex for writing. */
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index e28964aba021..8942125de3a6 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -215,6 +215,7 @@ extern const struct vport_ops ovs_netdev_vport_ops;
 extern const struct vport_ops ovs_internal_vport_ops;
 extern const struct vport_ops ovs_gre_vport_ops;
 extern const struct vport_ops ovs_vxlan_vport_ops;
+extern const struct vport_ops ovs_geneve_vport_ops;
 
 static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
 				      const void *start, unsigned int len)
-- 
cgit v1.2.3


From f2600cf02b5b59aaee082c3485b7f01fc7f7b70c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 4 Oct 2014 10:11:31 -0700
Subject: net: sched: avoid costly atomic operation in fq_dequeue()

Standard qdisc API to setup a timer implies an atomic operation on every
packet dequeue : qdisc_unthrottled()

It turns out this is not really needed for FQ, as FQ has no concept of
global qdisc throttling, being a qdisc handling many different flows,
some of them can be throttled, while others are not.

Fix is straightforward : add a 'bool throttle' to
qdisc_watchdog_schedule_ns(), and remove calls to qdisc_unthrottled()
in sch_fq.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_sched.h | 4 ++--
 net/sched/sch_api.c     | 5 +++--
 net/sched/sch_fq.c      | 6 ++----
 net/sched/sch_tbf.c     | 3 ++-
 4 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index e4b3c828c1c2..27a33833ff4a 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -65,12 +65,12 @@ struct qdisc_watchdog {
 };
 
 void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires);
+void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle);
 
 static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd,
 					   psched_time_t expires)
 {
-	qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires));
+	qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires), true);
 }
 
 void qdisc_watchdog_cancel(struct qdisc_watchdog *wd);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index c79a226cc25c..2cf61b3e633c 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -594,13 +594,14 @@ void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
 }
 EXPORT_SYMBOL(qdisc_watchdog_init);
 
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
+void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle)
 {
 	if (test_bit(__QDISC_STATE_DEACTIVATED,
 		     &qdisc_root_sleeping(wd->qdisc)->state))
 		return;
 
-	qdisc_throttled(wd->qdisc);
+	if (throttle)
+		qdisc_throttled(wd->qdisc);
 
 	hrtimer_start(&wd->timer,
 		      ns_to_ktime(expires),
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index c9b9fcb53206..cbd7e1fd23b4 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -377,7 +377,6 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		if (time_after(jiffies, f->age + q->flow_refill_delay))
 			f->credit = max_t(u32, f->credit, q->quantum);
 		q->inactive_flows--;
-		qdisc_unthrottled(sch);
 	}
 
 	/* Note: this overwrites f->age */
@@ -385,7 +384,6 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	if (unlikely(f == &q->internal)) {
 		q->stat_internal_packets++;
-		qdisc_unthrottled(sch);
 	}
 	sch->q.qlen++;
 
@@ -433,7 +431,8 @@ begin:
 		if (!head->first) {
 			if (q->time_next_delayed_flow != ~0ULL)
 				qdisc_watchdog_schedule_ns(&q->watchdog,
-							   q->time_next_delayed_flow);
+							   q->time_next_delayed_flow,
+							   false);
 			return NULL;
 		}
 	}
@@ -495,7 +494,6 @@ begin:
 	}
 out:
 	qdisc_bstats_update(sch, skb);
-	qdisc_unthrottled(sch);
 	return skb;
 }
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 77edffe329c4..a4afde14e865 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -268,7 +268,8 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 		}
 
 		qdisc_watchdog_schedule_ns(&q->watchdog,
-					   now + max_t(long, -toks, -ptoks));
+					   now + max_t(long, -toks, -ptoks),
+					   true);
 
 		/* Maybe we have a shorter packet in the queue,
 		   which can be sent now. It sounds cool,
-- 
cgit v1.2.3


From 7dfa4b414d4eec8da56e44fb2b4aea3e549b092f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 5 Oct 2014 12:35:09 +0300
Subject: net/mlx4_en: Code cleanups in tx path

- Remove unused variable ring->poll_cnt
- No need to set some fields if using blueflame
- Add missing const's
- Use unlikely
- Remove unneeded new line
- Make some comments more precise
- struct mlx4_bf @offset field reduced to unsigned int to save space

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c   | 49 +++++++++++++++-------------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  1 -
 include/linux/mlx4/device.h                  |  2 +-
 3 files changed, 27 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 0c501253fdab..eaf23eb7266a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -191,7 +191,6 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 	ring->prod = 0;
 	ring->cons = 0xffffffff;
 	ring->last_nr_txbb = 1;
-	ring->poll_cnt = 0;
 	memset(ring->tx_info, 0, ring->size * sizeof(struct mlx4_en_tx_info));
 	memset(ring->buf, 0, ring->buf_size);
 
@@ -512,7 +511,8 @@ static struct mlx4_en_tx_desc *mlx4_en_bounce_to_desc(struct mlx4_en_priv *priv,
 	return ring->buf + index * TXBB_SIZE;
 }
 
-static int is_inline(int inline_thold, struct sk_buff *skb, void **pfrag)
+static bool is_inline(int inline_thold, const struct sk_buff *skb,
+		      void **pfrag)
 {
 	void *ptr;
 
@@ -535,7 +535,7 @@ static int is_inline(int inline_thold, struct sk_buff *skb, void **pfrag)
 	return 0;
 }
 
-static int inline_size(struct sk_buff *skb)
+static int inline_size(const struct sk_buff *skb)
 {
 	if (skb->len + CTRL_SIZE + sizeof(struct mlx4_wqe_inline_seg)
 	    <= MLX4_INLINE_ALIGN)
@@ -546,7 +546,8 @@ static int inline_size(struct sk_buff *skb)
 			     sizeof(struct mlx4_wqe_inline_seg), 16);
 }
 
-static int get_real_size(struct sk_buff *skb, struct net_device *dev,
+static int get_real_size(const struct sk_buff *skb,
+			 struct net_device *dev,
 			 int *lso_header_size)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
@@ -581,8 +582,10 @@ static int get_real_size(struct sk_buff *skb, struct net_device *dev,
 	return real_size;
 }
 
-static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *skb,
-			     int real_size, u16 *vlan_tag, int tx_ind, void *fragptr)
+static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
+			     const struct sk_buff *skb,
+			     int real_size, u16 *vlan_tag,
+			     int tx_ind, void *fragptr)
 {
 	struct mlx4_wqe_inline_seg *inl = &tx_desc->inl;
 	int spc = MLX4_INLINE_ALIGN - CTRL_SIZE - sizeof *inl;
@@ -642,7 +645,8 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return fallback(dev, skb) % rings_p_up + up * rings_p_up;
 }
 
-static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt)
+static void mlx4_bf_copy(void __iomem *dst, const void *src,
+			 unsigned int bytecnt)
 {
 	__iowrite64_copy(dst, src, bytecnt / 8);
 }
@@ -736,11 +740,10 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	tx_info->skb = skb;
 	tx_info->nr_txbb = nr_txbb;
 
+	data = &tx_desc->data;
 	if (lso_header_size)
 		data = ((void *)&tx_desc->lso + ALIGN(lso_header_size + 4,
 						      DS_SIZE));
-	else
-		data = &tx_desc->data;
 
 	/* valid only for none inline segments */
 	tx_info->data_offset = (void *)data - (void *)tx_desc;
@@ -753,9 +756,9 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (is_inline(ring->inline_thold, skb, &fragptr)) {
 		tx_info->inl = 1;
 	} else {
-		/* Map fragments */
+		/* Map fragments if any */
 		for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
-			struct skb_frag_struct *frag;
+			const struct skb_frag_struct *frag;
 			dma_addr_t dma;
 
 			frag = &skb_shinfo(skb)->frags[i];
@@ -772,7 +775,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 			--data;
 		}
 
-		/* Map linear part */
+		/* Map linear part if needed */
 		if (tx_info->linear) {
 			u32 byte_count = skb_headlen(skb) - lso_header_size;
 			dma_addr_t dma;
@@ -795,18 +798,14 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * For timestamping add flag to skb_shinfo and
 	 * set flag for further reference
 	 */
-	if (ring->hwtstamp_tx_type == HWTSTAMP_TX_ON &&
-	    skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
-		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+	if (unlikely(ring->hwtstamp_tx_type == HWTSTAMP_TX_ON &&
+		     shinfo->tx_flags & SKBTX_HW_TSTAMP)) {
+		shinfo->tx_flags |= SKBTX_IN_PROGRESS;
 		tx_info->ts_requested = 1;
 	}
 
 	/* Prepare ctrl segement apart opcode+ownership, which depends on
 	 * whether LSO is used */
-	tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag);
-	tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
-		!!vlan_tx_tag_present(skb);
-	tx_desc->ctrl.fence_size = (real_size / 16) & 0x3f;
 	tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
 	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM |
@@ -852,7 +851,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 			 cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
 		tx_info->nr_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 		ring->packets++;
-
 	}
 	ring->bytes += tx_info->nr_bytes;
 	netdev_tx_sent_queue(ring->tx_queue, tx_info->nr_bytes);
@@ -874,7 +872,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	ring->prod += nr_txbb;
 
 	/* If we used a bounce buffer then copy descriptor back into place */
-	if (bounce)
+	if (unlikely(bounce))
 		tx_desc = mlx4_en_bounce_to_desc(priv, ring, index, desc_size);
 
 	skb_tx_timestamp(skb);
@@ -894,13 +892,18 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		wmb();
 
-		mlx4_bf_copy(ring->bf.reg + ring->bf.offset, (unsigned long *) &tx_desc->ctrl,
-		     desc_size);
+		mlx4_bf_copy(ring->bf.reg + ring->bf.offset, &tx_desc->ctrl,
+			     desc_size);
 
 		wmb();
 
 		ring->bf.offset ^= ring->bf.buf_size;
 	} else {
+		tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag);
+		tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
+			!!vlan_tx_tag_present(skb);
+		tx_desc->ctrl.fence_size = real_size;
+
 		/* Ensure new descriptor hits memory
 		 * before setting ownership of this descriptor to HW
 		 */
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 84c9d5dbfa4f..e54b653de3d4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -263,7 +263,6 @@ struct mlx4_en_tx_ring {
 	u32 buf_size;
 	u32 doorbell_qpn;
 	void *buf;
-	u16 poll_cnt;
 	struct mlx4_en_tx_info *tx_info;
 	u8 *bounce_buf;
 	u8 queue_index;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index b2f8ab9a57c4..37e4404d0227 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -583,7 +583,7 @@ struct mlx4_uar {
 };
 
 struct mlx4_bf {
-	unsigned long		offset;
+	unsigned int		offset;
 	int			buf_size;
 	struct mlx4_uar	       *uar;
 	void __iomem	       *reg;
-- 
cgit v1.2.3


From 1255a5055449781a92076fc5429952f2b33cf309 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 5 Oct 2014 12:35:21 +0300
Subject: ethtool: Ethtool parameter to dynamically change tx_copybreak

Use new ethtool [sg]et_tunable() to set tx_copybread (inline threshold)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 1 +
 net/core/ethtool.c           | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 7a364f2f3d3f..99b43056a6fe 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -212,6 +212,7 @@ struct ethtool_value {
 enum tunable_id {
 	ETHTOOL_ID_UNSPEC,
 	ETHTOOL_RX_COPYBREAK,
+	ETHTOOL_TX_COPYBREAK,
 };
 
 enum tunable_type_id {
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 27e61b886520..1600aa24d36b 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1625,6 +1625,7 @@ static int ethtool_tunable_valid(const struct ethtool_tunable *tuna)
 {
 	switch (tuna->id) {
 	case ETHTOOL_RX_COPYBREAK:
+	case ETHTOOL_TX_COPYBREAK:
 		if (tuna->len != sizeof(u32) ||
 		    tuna->type_id != ETHTOOL_TUNABLE_U32)
 			return -EINVAL;
-- 
cgit v1.2.3


From 95afae481414cbdb0567bf82d5e5077c3ac9da20 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@citrix.com>
Date: Mon, 8 Sep 2014 17:30:41 +0100
Subject: xen: remove DEFINE_XENBUS_DRIVER() macro

The DEFINE_XENBUS_DRIVER() macro looks a bit weird and causes sparse
errors.

Replace the uses with standard structure definitions instead.  This is
similar to pci and usb device registration.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 drivers/block/xen-blkback/xenbus.c         | 11 +++--------
 drivers/block/xen-blkfront.c               |  5 +++--
 drivers/char/tpm/xen-tpmfront.c            | 13 +++++++------
 drivers/input/misc/xen-kbdfront.c          |  5 +++--
 drivers/net/xen-netback/xenbus.c           | 10 +++-------
 drivers/net/xen-netfront.c                 | 16 ++++++++--------
 drivers/pci/xen-pcifront.c                 |  6 ++++--
 drivers/scsi/xen-scsifront.c               |  5 +++--
 drivers/tty/hvc/hvc_xen.c                  |  9 ++++-----
 drivers/video/fbdev/xen-fbfront.c          |  5 +++--
 drivers/xen/xen-pciback/xenbus.c           |  6 ++++--
 drivers/xen/xen-scsiback.c                 |  5 +++--
 drivers/xen/xenbus/xenbus_probe.c          |  6 +++++-
 drivers/xen/xenbus/xenbus_probe.h          |  4 +++-
 drivers/xen/xenbus/xenbus_probe_backend.c  |  8 +++++---
 drivers/xen/xenbus/xenbus_probe_frontend.c |  8 +++++---
 include/xen/xenbus.h                       | 21 ++++++++++++---------
 17 files changed, 78 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 3a8b810b4980..0b13b1c9a01e 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -907,22 +907,17 @@ static int connect_ring(struct backend_info *be)
 	return 0;
 }
 
-
-/* ** Driver Registration ** */
-
-
 static const struct xenbus_device_id xen_blkbk_ids[] = {
 	{ "vbd" },
 	{ "" }
 };
 
-
-static DEFINE_XENBUS_DRIVER(xen_blkbk, ,
+static struct xenbus_driver xen_blkbk_driver = {
+	.ids  = xen_blkbk_ids,
 	.probe = xen_blkbk_probe,
 	.remove = xen_blkbk_remove,
 	.otherend_changed = frontend_changed
-);
-
+};
 
 int xen_blkif_xenbus_init(void)
 {
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 5deb235bd18f..37af03e9d859 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -2055,13 +2055,14 @@ static const struct xenbus_device_id blkfront_ids[] = {
 	{ "" }
 };
 
-static DEFINE_XENBUS_DRIVER(blkfront, ,
+static struct xenbus_driver blkfront_driver = {
+	.ids  = blkfront_ids,
 	.probe = blkfront_probe,
 	.remove = blkfront_remove,
 	.resume = blkfront_resume,
 	.otherend_changed = blkback_changed,
 	.is_ready = blkfront_is_ready,
-);
+};
 
 static int __init xlblk_init(void)
 {
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
index 2064b4527040..441b44e54226 100644
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -367,12 +367,13 @@ static const struct xenbus_device_id tpmfront_ids[] = {
 };
 MODULE_ALIAS("xen:vtpm");
 
-static DEFINE_XENBUS_DRIVER(tpmfront, ,
-		.probe = tpmfront_probe,
-		.remove = tpmfront_remove,
-		.resume = tpmfront_resume,
-		.otherend_changed = backend_changed,
-	);
+static struct xenbus_driver tpmfront_driver = {
+	.ids = tpmfront_ids,
+	.probe = tpmfront_probe,
+	.remove = tpmfront_remove,
+	.resume = tpmfront_resume,
+	.otherend_changed = backend_changed,
+};
 
 static int __init xen_tpmfront_init(void)
 {
diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c
index fbfdc10573be..1af28b06c713 100644
--- a/drivers/input/misc/xen-kbdfront.c
+++ b/drivers/input/misc/xen-kbdfront.c
@@ -365,12 +365,13 @@ static const struct xenbus_device_id xenkbd_ids[] = {
 	{ "" }
 };
 
-static DEFINE_XENBUS_DRIVER(xenkbd, ,
+static struct xenbus_driver xenkbd_driver = {
+	.ids = xenkbd_ids,
 	.probe = xenkbd_probe,
 	.remove = xenkbd_remove,
 	.resume = xenkbd_resume,
 	.otherend_changed = xenkbd_backend_changed,
-);
+};
 
 static int __init xenkbd_init(void)
 {
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 9c47b897b6d2..8079c31ac5e6 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -937,22 +937,18 @@ static int read_xenbus_vif_flags(struct backend_info *be)
 	return 0;
 }
 
-
-/* ** Driver Registration ** */
-
-
 static const struct xenbus_device_id netback_ids[] = {
 	{ "vif" },
 	{ "" }
 };
 
-
-static DEFINE_XENBUS_DRIVER(netback, ,
+static struct xenbus_driver netback_driver = {
+	.ids = netback_ids,
 	.probe = netback_probe,
 	.remove = netback_remove,
 	.uevent = netback_uevent,
 	.otherend_changed = frontend_changed,
-);
+};
 
 int xenvif_xenbus_init(void)
 {
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index ca82f545ec2c..fa671442f420 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -2300,12 +2300,6 @@ static void xennet_sysfs_delif(struct net_device *netdev)
 
 #endif /* CONFIG_SYSFS */
 
-static const struct xenbus_device_id netfront_ids[] = {
-	{ "vif" },
-	{ "" }
-};
-
-
 static int xennet_remove(struct xenbus_device *dev)
 {
 	struct netfront_info *info = dev_get_drvdata(&dev->dev);
@@ -2338,12 +2332,18 @@ static int xennet_remove(struct xenbus_device *dev)
 	return 0;
 }
 
-static DEFINE_XENBUS_DRIVER(netfront, ,
+static const struct xenbus_device_id netfront_ids[] = {
+	{ "vif" },
+	{ "" }
+};
+
+static struct xenbus_driver netfront_driver = {
+	.ids = netfront_ids,
 	.probe = netfront_probe,
 	.remove = xennet_remove,
 	.resume = netfront_resume,
 	.otherend_changed = netback_changed,
-);
+};
 
 static int __init netif_init(void)
 {
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 53df39a22c8a..116ca3746adb 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -1136,11 +1136,13 @@ static const struct xenbus_device_id xenpci_ids[] = {
 	{""},
 };
 
-static DEFINE_XENBUS_DRIVER(xenpci, "pcifront",
+static struct xenbus_driver xenpci_driver = {
+	.name			= "pcifront",
+	.ids			= xenpci_ids,
 	.probe			= pcifront_xenbus_probe,
 	.remove			= pcifront_xenbus_remove,
 	.otherend_changed	= pcifront_backend_changed,
-);
+};
 
 static int __init pcifront_init(void)
 {
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
index cc14c8ddd369..34199d206ba6 100644
--- a/drivers/scsi/xen-scsifront.c
+++ b/drivers/scsi/xen-scsifront.c
@@ -998,11 +998,12 @@ static const struct xenbus_device_id scsifront_ids[] = {
 	{ "" }
 };
 
-static DEFINE_XENBUS_DRIVER(scsifront, ,
+static struct xenbus_driver scsifront_driver = {
+	.ids			= scsifront_ids,
 	.probe			= scsifront_probe,
 	.remove			= scsifront_remove,
 	.otherend_changed	= scsifront_backend_changed,
-);
+};
 
 static int __init scsifront_init(void)
 {
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 2dc2831840ca..c3d8af917ffc 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -347,8 +347,6 @@ static int xen_console_remove(struct xencons_info *info)
 }
 
 #ifdef CONFIG_HVC_XEN_FRONTEND
-static struct xenbus_driver xencons_driver;
-
 static int xencons_remove(struct xenbus_device *dev)
 {
 	return xen_console_remove(dev_get_drvdata(&dev->dev));
@@ -502,13 +500,14 @@ static const struct xenbus_device_id xencons_ids[] = {
 	{ "" }
 };
 
-
-static DEFINE_XENBUS_DRIVER(xencons, "xenconsole",
+static struct xenbus_driver xencons_driver = {
+	.name = "xenconsole",
+	.ids = xencons_ids,
 	.probe = xencons_probe,
 	.remove = xencons_remove,
 	.resume = xencons_resume,
 	.otherend_changed = xencons_backend_changed,
-);
+};
 #endif /* CONFIG_HVC_XEN_FRONTEND */
 
 static int __init xen_hvc_init(void)
diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c
index 901014bbc821..09dc44736c1a 100644
--- a/drivers/video/fbdev/xen-fbfront.c
+++ b/drivers/video/fbdev/xen-fbfront.c
@@ -684,12 +684,13 @@ static const struct xenbus_device_id xenfb_ids[] = {
 	{ "" }
 };
 
-static DEFINE_XENBUS_DRIVER(xenfb, ,
+static struct xenbus_driver xenfb_driver = {
+	.ids = xenfb_ids,
 	.probe = xenfb_probe,
 	.remove = xenfb_remove,
 	.resume = xenfb_resume,
 	.otherend_changed = xenfb_backend_changed,
-);
+};
 
 static int __init xenfb_init(void)
 {
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index c214daab4829..ad8d30c088fe 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -719,11 +719,13 @@ static const struct xenbus_device_id xen_pcibk_ids[] = {
 	{""},
 };
 
-static DEFINE_XENBUS_DRIVER(xen_pcibk, DRV_NAME,
+static struct xenbus_driver xen_pcibk_driver = {
+	.name                   = DRV_NAME,
+	.ids                    = xen_pcibk_ids,
 	.probe			= xen_pcibk_xenbus_probe,
 	.remove			= xen_pcibk_xenbus_remove,
 	.otherend_changed	= xen_pcibk_frontend_changed,
-);
+};
 
 const struct xen_pcibk_backend *__read_mostly xen_pcibk_backend;
 
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index ad11258a78d6..3e32146472a5 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -2056,11 +2056,12 @@ static const struct xenbus_device_id scsiback_ids[] = {
 	{ "" }
 };
 
-static DEFINE_XENBUS_DRIVER(scsiback, ,
+static struct xenbus_driver scsiback_driver = {
+	.ids			= scsiback_ids,
 	.probe			= scsiback_probe,
 	.remove			= scsiback_remove,
 	.otherend_changed	= scsiback_frontend_changed
-);
+};
 
 static void scsiback_init_pend(void *p)
 {
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 3c0a74b3e9b1..564b31584860 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -297,9 +297,13 @@ void xenbus_dev_shutdown(struct device *_dev)
 EXPORT_SYMBOL_GPL(xenbus_dev_shutdown);
 
 int xenbus_register_driver_common(struct xenbus_driver *drv,
-				  struct xen_bus_type *bus)
+				  struct xen_bus_type *bus,
+				  struct module *owner, const char *mod_name)
 {
+	drv->driver.name = drv->name ? drv->name : drv->ids[0].devicetype;
 	drv->driver.bus = &bus->bus;
+	drv->driver.owner = owner;
+	drv->driver.mod_name = mod_name;
 
 	return driver_register(&drv->driver);
 }
diff --git a/drivers/xen/xenbus/xenbus_probe.h b/drivers/xen/xenbus/xenbus_probe.h
index 1085ec294a19..c9ec7ca1f7ab 100644
--- a/drivers/xen/xenbus/xenbus_probe.h
+++ b/drivers/xen/xenbus/xenbus_probe.h
@@ -60,7 +60,9 @@ extern int xenbus_match(struct device *_dev, struct device_driver *_drv);
 extern int xenbus_dev_probe(struct device *_dev);
 extern int xenbus_dev_remove(struct device *_dev);
 extern int xenbus_register_driver_common(struct xenbus_driver *drv,
-					 struct xen_bus_type *bus);
+					 struct xen_bus_type *bus,
+					 struct module *owner,
+					 const char *mod_name);
 extern int xenbus_probe_node(struct xen_bus_type *bus,
 			     const char *type,
 			     const char *nodename);
diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c
index 5125dce11a60..04f7f85a5edf 100644
--- a/drivers/xen/xenbus/xenbus_probe_backend.c
+++ b/drivers/xen/xenbus/xenbus_probe_backend.c
@@ -234,13 +234,15 @@ int xenbus_dev_is_online(struct xenbus_device *dev)
 }
 EXPORT_SYMBOL_GPL(xenbus_dev_is_online);
 
-int xenbus_register_backend(struct xenbus_driver *drv)
+int __xenbus_register_backend(struct xenbus_driver *drv, struct module *owner,
+			      const char *mod_name)
 {
 	drv->read_otherend_details = read_frontend_details;
 
-	return xenbus_register_driver_common(drv, &xenbus_backend);
+	return xenbus_register_driver_common(drv, &xenbus_backend,
+					     owner, mod_name);
 }
-EXPORT_SYMBOL_GPL(xenbus_register_backend);
+EXPORT_SYMBOL_GPL(__xenbus_register_backend);
 
 static int backend_probe_and_watch(struct notifier_block *notifier,
 				   unsigned long event,
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index cb385c10d2b1..bcb53bdc469c 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -317,13 +317,15 @@ static void wait_for_devices(struct xenbus_driver *xendrv)
 			 print_device_status);
 }
 
-int xenbus_register_frontend(struct xenbus_driver *drv)
+int __xenbus_register_frontend(struct xenbus_driver *drv, struct module *owner,
+			       const char *mod_name)
 {
 	int ret;
 
 	drv->read_otherend_details = read_backend_details;
 
-	ret = xenbus_register_driver_common(drv, &xenbus_frontend);
+	ret = xenbus_register_driver_common(drv, &xenbus_frontend,
+					    owner, mod_name);
 	if (ret)
 		return ret;
 
@@ -332,7 +334,7 @@ int xenbus_register_frontend(struct xenbus_driver *drv)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(xenbus_register_frontend);
+EXPORT_SYMBOL_GPL(__xenbus_register_frontend);
 
 static DECLARE_WAIT_QUEUE_HEAD(backend_state_wq);
 static int backend_state;
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 0324c6d340c1..b78f21caf55a 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -86,6 +86,7 @@ struct xenbus_device_id
 
 /* A xenbus driver. */
 struct xenbus_driver {
+	const char *name;       /* defaults to ids[0].devicetype */
 	const struct xenbus_device_id *ids;
 	int (*probe)(struct xenbus_device *dev,
 		     const struct xenbus_device_id *id);
@@ -100,20 +101,22 @@ struct xenbus_driver {
 	int (*is_ready)(struct xenbus_device *dev);
 };
 
-#define DEFINE_XENBUS_DRIVER(var, drvname, methods...)		\
-struct xenbus_driver var ## _driver = {				\
-	.driver.name = drvname + 0 ?: var ## _ids->devicetype,	\
-	.driver.owner = THIS_MODULE,				\
-	.ids = var ## _ids, ## methods				\
-}
-
 static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv)
 {
 	return container_of(drv, struct xenbus_driver, driver);
 }
 
-int __must_check xenbus_register_frontend(struct xenbus_driver *);
-int __must_check xenbus_register_backend(struct xenbus_driver *);
+int __must_check __xenbus_register_frontend(struct xenbus_driver *drv,
+					    struct module *owner,
+					    const char *mod_name);
+int __must_check __xenbus_register_backend(struct xenbus_driver *drv,
+					   struct module *owner,
+					   const char *mod_name);
+
+#define xenbus_register_frontend(drv) \
+	__xenbus_register_frontend(drv, THIS_MODULE, KBUILD_MODNAME);
+#define xenbus_register_backend(drv) \
+	__xenbus_register_backend(drv, THIS_MODULE, KBUILD_MODNAME);
 
 void xenbus_unregister_driver(struct xenbus_driver *drv);
 
-- 
cgit v1.2.3


From f1b731dbc2530cab93fcfc5fcb18c9f3a100feeb Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Mon, 6 Oct 2014 15:21:05 +0100
Subject: KEYS: Restore partial ID matching functionality for asymmetric keys

Bring back the functionality whereby an asymmetric key can be matched with a
partial match on one of its IDs.

Whilst we're at it, allow for the possibility of having an increased number of
IDs.

Reported-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 crypto/asymmetric_keys/asymmetric_keys.h |  3 --
 crypto/asymmetric_keys/asymmetric_type.c | 70 ++++++++++++++++++++++++++------
 crypto/asymmetric_keys/pkcs7_trust.c     |  9 ++--
 crypto/asymmetric_keys/x509_public_key.c | 18 +++++---
 include/crypto/public_key.h              |  3 +-
 include/keys/asymmetric-type.h           |  3 ++
 6 files changed, 81 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/asymmetric_keys.h b/crypto/asymmetric_keys/asymmetric_keys.h
index fd21ac28e0a0..f97330886d58 100644
--- a/crypto/asymmetric_keys/asymmetric_keys.h
+++ b/crypto/asymmetric_keys/asymmetric_keys.h
@@ -9,9 +9,6 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
-extern bool asymmetric_match_key_ids(const struct asymmetric_key_ids *kids,
-				     const struct asymmetric_key_id *match_id);
-
 extern struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id);
 
 static inline
diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index 29983cbb658d..052e944bb109 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -65,23 +65,44 @@ bool asymmetric_key_id_same(const struct asymmetric_key_id *kid1,
 }
 EXPORT_SYMBOL_GPL(asymmetric_key_id_same);
 
+/**
+ * asymmetric_key_id_partial - Return true if two asymmetric keys IDs
+ * partially match
+ * @kid_1, @kid_2: The key IDs to compare
+ */
+bool asymmetric_key_id_partial(const struct asymmetric_key_id *kid1,
+			       const struct asymmetric_key_id *kid2)
+{
+	if (!kid1 || !kid2)
+		return false;
+	if (kid1->len < kid2->len)
+		return false;
+	return memcmp(kid1->data + (kid1->len - kid2->len),
+		      kid2->data, kid2->len) == 0;
+}
+EXPORT_SYMBOL_GPL(asymmetric_key_id_partial);
+
 /**
  * asymmetric_match_key_ids - Search asymmetric key IDs
  * @kids: The list of key IDs to check
  * @match_id: The key ID we're looking for
+ * @match: The match function to use
  */
-bool asymmetric_match_key_ids(const struct asymmetric_key_ids *kids,
-			      const struct asymmetric_key_id *match_id)
+static bool asymmetric_match_key_ids(
+	const struct asymmetric_key_ids *kids,
+	const struct asymmetric_key_id *match_id,
+	bool (*match)(const struct asymmetric_key_id *kid1,
+		      const struct asymmetric_key_id *kid2))
 {
+	int i;
+
 	if (!kids || !match_id)
 		return false;
-	if (asymmetric_key_id_same(kids->id[0], match_id))
-		return true;
-	if (asymmetric_key_id_same(kids->id[1], match_id))
-		return true;
+	for (i = 0; i < ARRAY_SIZE(kids->id); i++)
+		if (match(kids->id[i], match_id))
+			return true;
 	return false;
 }
-EXPORT_SYMBOL_GPL(asymmetric_match_key_ids);
 
 /**
  * asymmetric_key_hex_to_key_id - Convert a hex string into a key ID.
@@ -113,7 +134,7 @@ struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id)
 }
 
 /*
- * Match asymmetric keys by ID.
+ * Match asymmetric keys by an exact match on an ID.
  */
 static bool asymmetric_key_cmp(const struct key *key,
 			       const struct key_match_data *match_data)
@@ -121,7 +142,21 @@ static bool asymmetric_key_cmp(const struct key *key,
 	const struct asymmetric_key_ids *kids = asymmetric_key_ids(key);
 	const struct asymmetric_key_id *match_id = match_data->preparsed;
 
-	return asymmetric_match_key_ids(kids, match_id);
+	return asymmetric_match_key_ids(kids, match_id,
+					asymmetric_key_id_same);
+}
+
+/*
+ * Match asymmetric keys by a partial match on an IDs.
+ */
+static bool asymmetric_key_cmp_partial(const struct key *key,
+				       const struct key_match_data *match_data)
+{
+	const struct asymmetric_key_ids *kids = asymmetric_key_ids(key);
+	const struct asymmetric_key_id *match_id = match_data->preparsed;
+
+	return asymmetric_match_key_ids(kids, match_id,
+					asymmetric_key_id_partial);
 }
 
 /*
@@ -131,7 +166,8 @@ static bool asymmetric_key_cmp(const struct key *key,
  * There are some specifiers for matching key IDs rather than by the key
  * description:
  *
- *	"id:<id>" - request a key by any available ID
+ *	"id:<id>" - find a key by partial match on any available ID
+ *	"ex:<id>" - find a key by exact match on any available ID
  *
  * These have to be searched by iteration rather than by direct lookup because
  * the key is hashed according to its description.
@@ -141,6 +177,8 @@ static int asymmetric_key_match_preparse(struct key_match_data *match_data)
 	struct asymmetric_key_id *match_id;
 	const char *spec = match_data->raw_data;
 	const char *id;
+	bool (*cmp)(const struct key *, const struct key_match_data *) =
+		asymmetric_key_cmp;
 
 	if (!spec || !*spec)
 		return -EINVAL;
@@ -148,6 +186,11 @@ static int asymmetric_key_match_preparse(struct key_match_data *match_data)
 	    spec[1] == 'd' &&
 	    spec[2] == ':') {
 		id = spec + 3;
+		cmp = asymmetric_key_cmp_partial;
+	} else if (spec[0] == 'e' &&
+		   spec[1] == 'x' &&
+		   spec[2] == ':') {
+		id = spec + 3;
 	} else {
 		goto default_match;
 	}
@@ -157,7 +200,7 @@ static int asymmetric_key_match_preparse(struct key_match_data *match_data)
 		return PTR_ERR(match_id);
 
 	match_data->preparsed = match_id;
-	match_data->cmp = asymmetric_key_cmp;
+	match_data->cmp = cmp;
 	match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE;
 	return 0;
 
@@ -251,6 +294,7 @@ static void asymmetric_key_free_preparse(struct key_preparsed_payload *prep)
 {
 	struct asymmetric_key_subtype *subtype = prep->type_data[0];
 	struct asymmetric_key_ids *kids = prep->type_data[1];
+	int i;
 
 	pr_devel("==>%s()\n", __func__);
 
@@ -259,8 +303,8 @@ static void asymmetric_key_free_preparse(struct key_preparsed_payload *prep)
 		module_put(subtype->owner);
 	}
 	if (kids) {
-		kfree(kids->id[0]);
-		kfree(kids->id[1]);
+		for (i = 0; i < ARRAY_SIZE(kids->id); i++)
+			kfree(kids->id[i]);
 		kfree(kids);
 	}
 	kfree(prep->description);
diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c
index ae47be6128c4..1d29376072da 100644
--- a/crypto/asymmetric_keys/pkcs7_trust.c
+++ b/crypto/asymmetric_keys/pkcs7_trust.c
@@ -54,7 +54,8 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 		/* Look to see if this certificate is present in the trusted
 		 * keys.
 		 */
-		key = x509_request_asymmetric_key(trust_keyring, x509->id);
+		key = x509_request_asymmetric_key(trust_keyring, x509->id,
+						  false);
 		if (!IS_ERR(key)) {
 			/* One of the X.509 certificates in the PKCS#7 message
 			 * is apparently the same as one we already trust.
@@ -85,7 +86,8 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 	 * trusted keys.
 	 */
 	if (last && last->authority) {
-		key = x509_request_asymmetric_key(trust_keyring, last->authority);
+		key = x509_request_asymmetric_key(trust_keyring, last->authority,
+						  false);
 		if (!IS_ERR(key)) {
 			x509 = last;
 			pr_devel("sinfo %u: Root cert %u signer is key %x\n",
@@ -100,7 +102,8 @@ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 	 * the signed info directly.
 	 */
 	key = x509_request_asymmetric_key(trust_keyring,
-					  sinfo->signing_cert_id);
+					  sinfo->signing_cert_id,
+					  false);
 	if (!IS_ERR(key)) {
 		pr_devel("sinfo %u: Direct signer is key %x\n",
 			 sinfo->index, key_serial(key));
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 8bffb06b2683..6ef54495be87 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -53,13 +53,15 @@ __setup("ca_keys=", ca_keys_setup);
  * x509_request_asymmetric_key - Request a key by X.509 certificate params.
  * @keyring: The keys to search.
  * @kid: The key ID.
+ * @partial: Use partial match if true, exact if false.
  *
  * Find a key in the given keyring by subject name and key ID.  These might,
  * for instance, be the issuer name and the authority key ID of an X.509
  * certificate that needs to be verified.
  */
 struct key *x509_request_asymmetric_key(struct key *keyring,
-					const struct asymmetric_key_id *kid)
+					const struct asymmetric_key_id *kid,
+					bool partial)
 {
 	key_ref_t key;
 	char *id, *p;
@@ -69,8 +71,13 @@ struct key *x509_request_asymmetric_key(struct key *keyring,
 	if (!id)
 		return ERR_PTR(-ENOMEM);
 
-	*p++ = 'i';
-	*p++ = 'd';
+	if (partial) {
+		*p++ = 'i';
+		*p++ = 'd';
+	} else {
+		*p++ = 'e';
+		*p++ = 'x';
+	}
 	*p++ = ':';
 	p = bin2hex(p, kid->data, kid->len);
 	*p = 0;
@@ -207,10 +214,11 @@ static int x509_validate_trust(struct x509_certificate *cert,
 	if (!trust_keyring)
 		return -EOPNOTSUPP;
 
-	if (ca_keyid && !asymmetric_key_id_same(cert->authority, ca_keyid))
+	if (ca_keyid && !asymmetric_key_id_partial(cert->authority, ca_keyid))
 		return -EPERM;
 
-	key = x509_request_asymmetric_key(trust_keyring, cert->authority);
+	key = x509_request_asymmetric_key(trust_keyring, cert->authority,
+					  false);
 	if (!IS_ERR(key))  {
 		if (!use_builtin_keys
 		    || test_bit(KEY_FLAG_BUILTIN, &key->flags))
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index fa73a6fd536c..54add2069901 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -101,6 +101,7 @@ extern int verify_signature(const struct key *key,
 
 struct asymmetric_key_id;
 extern struct key *x509_request_asymmetric_key(struct key *keyring,
-					       const struct asymmetric_key_id *kid);
+					       const struct asymmetric_key_id *kid,
+					       bool partial);
 
 #endif /* _LINUX_PUBLIC_KEY_H */
diff --git a/include/keys/asymmetric-type.h b/include/keys/asymmetric-type.h
index 044ab0d3aa45..c0754abb2f56 100644
--- a/include/keys/asymmetric-type.h
+++ b/include/keys/asymmetric-type.h
@@ -51,6 +51,9 @@ struct asymmetric_key_ids {
 extern bool asymmetric_key_id_same(const struct asymmetric_key_id *kid1,
 				   const struct asymmetric_key_id *kid2);
 
+extern bool asymmetric_key_id_partial(const struct asymmetric_key_id *kid1,
+				      const struct asymmetric_key_id *kid2);
+
 extern struct asymmetric_key_id *asymmetric_key_generate_id(const void *val_1,
 							    size_t len_1,
 							    const void *val_2,
-- 
cgit v1.2.3


From a6551a76fff15056fde2342d0f7de41ee605264e Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@chromium.org>
Date: Thu, 18 Sep 2014 17:18:56 +0200
Subject: mfd: cros_ec: stop calling ->cmd_xfer() directly

Instead of having users of the ChromeOS EC call the interface-specific
cmd_xfer() callback directly, introduce a central cros_ec_cmd_xfer()
to use instead.  This will allow us to put all the locking and retry
logic in one place instead of duplicating it across the different
drivers.

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Reviewed-by: Simon Glass <sjg@chromium.org>
Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Reviewed-by: Doug Anderson <dianders@chromium.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/i2c/busses/i2c-cros-ec-tunnel.c |  2 +-
 drivers/input/keyboard/cros_ec_keyb.c   |  2 +-
 drivers/mfd/cros_ec.c                   |  7 +++++++
 include/linux/mfd/cros_ec.h             | 24 ++++++++++++++++++------
 4 files changed, 27 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
index 05e033c98115..43be23dfb115 100644
--- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c
+++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
@@ -227,7 +227,7 @@ static int ec_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg i2c_msgs[],
 	msg.indata = response;
 	msg.insize = response_len;
 
-	result = bus->ec->cmd_xfer(bus->ec, &msg);
+	result = cros_ec_cmd_xfer(bus->ec, &msg);
 	if (result < 0)
 		goto exit;
 
diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c
index 791781ade4e7..93111d1aa617 100644
--- a/drivers/input/keyboard/cros_ec_keyb.c
+++ b/drivers/input/keyboard/cros_ec_keyb.c
@@ -182,7 +182,7 @@ static int cros_ec_keyb_get_state(struct cros_ec_keyb *ckdev, uint8_t *kb_state)
 		.insize = ckdev->cols,
 	};
 
-	return ckdev->ec->cmd_xfer(ckdev->ec, &msg);
+	return cros_ec_cmd_xfer(ckdev->ec, &msg);
 }
 
 static irqreturn_t cros_ec_keyb_irq(int irq, void *data)
diff --git a/drivers/mfd/cros_ec.c b/drivers/mfd/cros_ec.c
index 4873f9c50452..a9faebdcfa14 100644
--- a/drivers/mfd/cros_ec.c
+++ b/drivers/mfd/cros_ec.c
@@ -62,6 +62,13 @@ int cros_ec_check_result(struct cros_ec_device *ec_dev,
 }
 EXPORT_SYMBOL(cros_ec_check_result);
 
+int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
+		     struct cros_ec_command *msg)
+{
+	return ec_dev->cmd_xfer(ec_dev, msg);
+}
+EXPORT_SYMBOL(cros_ec_cmd_xfer);
+
 static const struct mfd_cell cros_devs[] = {
 	{
 		.name = "cros-ec-keyb",
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index fcbe9d129a9d..0e166b92f5b4 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -62,10 +62,6 @@ struct cros_ec_command {
  * @dev: Device pointer
  * @was_wake_device: true if this device was set to wake the system from
  * sleep at the last suspend
- * @cmd_xfer: send command to EC and get response
- *     Returns the number of bytes received if the communication succeeded, but
- *     that doesn't mean the EC was happy with the command. The caller
- *     should check msg.result for the EC's result code.
  *
  * @priv: Private data
  * @irq: Interrupt to use
@@ -82,6 +78,10 @@ struct cros_ec_command {
  * @dout_size: size of dout buffer to allocate (zero to use static dout)
  * @parent: pointer to parent device (e.g. i2c or spi device)
  * @wake_enabled: true if this device can wake the system from sleep
+ * @cmd_xfer: send command to EC and get response
+ *     Returns the number of bytes received if the communication succeeded, but
+ *     that doesn't mean the EC was happy with the command. The caller
+ *     should check msg.result for the EC's result code.
  * @lock: one transaction at a time
  */
 struct cros_ec_device {
@@ -92,8 +92,6 @@ struct cros_ec_device {
 	struct device *dev;
 	bool was_wake_device;
 	struct class *cros_class;
-	int (*cmd_xfer)(struct cros_ec_device *ec,
-			struct cros_ec_command *msg);
 
 	/* These are used to implement the platform-specific interface */
 	void *priv;
@@ -104,6 +102,8 @@ struct cros_ec_device {
 	int dout_size;
 	struct device *parent;
 	bool wake_enabled;
+	int (*cmd_xfer)(struct cros_ec_device *ec,
+			struct cros_ec_command *msg);
 	struct mutex lock;
 };
 
@@ -152,6 +152,18 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev,
 int cros_ec_check_result(struct cros_ec_device *ec_dev,
 			 struct cros_ec_command *msg);
 
+/**
+ * cros_ec_cmd_xfer - Send a command to the ChromeOS EC
+ *
+ * Call this to send a command to the ChromeOS EC.  This should be used
+ * instead of calling the EC's cmd_xfer() callback directly.
+ *
+ * @ec_dev: EC device
+ * @msg: Message to write
+ */
+int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
+		     struct cros_ec_command *msg);
+
 /**
  * cros_ec_remove - Remove a ChromeOS EC
  *
-- 
cgit v1.2.3


From fcbeb976d7ce783fd58e63e61c196d9a8912b3be Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 5 Oct 2014 10:11:27 -0700
Subject: net: introduce netdevice gso_min_segs attribute

Some TSO engines might have a too heavy setup cost, that impacts
performance on hosts sending small bursts (2 MSS per packet).

This patch adds a device gso_min_segs, allowing drivers to set
a minimum segment size for TSO packets, according to the NIC
performance.

Tested on a mlx4 NIC, this allows to get a ~110% increase of
throughput when sending 2 MSS per packet.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 4 +++-
 net/core/dev.c            | 9 ++++++---
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 22d54b9b700d..2df86f50261c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1416,6 +1416,8 @@ enum netdev_priv_flags {
  *	@gso_max_size:	Maximum size of generic segmentation offload
  *	@gso_max_segs:	Maximum number of segments that can be passed to the
  *			NIC for GSO
+ *	@gso_min_segs:	Minimum number of segments that can be passed to the
+ *			NIC for GSO
  *
  *	@dcbnl_ops:	Data Center Bridging netlink ops
  *	@num_tc:	Number of traffic classes in the net device
@@ -1666,7 +1668,7 @@ struct net_device {
 	unsigned int		gso_max_size;
 #define GSO_MAX_SEGS		65535
 	u16			gso_max_segs;
-
+	u16			gso_min_segs;
 #ifdef CONFIG_DCB
 	const struct dcbnl_rtnl_ops *dcbnl_ops;
 #endif
diff --git a/net/core/dev.c b/net/core/dev.c
index 7d5691cc1f47..c1a4de275576 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2567,10 +2567,12 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 
 netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
+	const struct net_device *dev = skb->dev;
+	netdev_features_t features = dev->features;
+	u16 gso_segs = skb_shinfo(skb)->gso_segs;
 	__be16 protocol = skb->protocol;
-	netdev_features_t features = skb->dev->features;
 
-	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+	if (gso_segs > dev->gso_max_segs || gso_segs < dev->gso_min_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
 	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
@@ -2581,7 +2583,7 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 	}
 
 	features = netdev_intersect_features(features,
-					     skb->dev->vlan_features |
+					     dev->vlan_features |
 					     NETIF_F_HW_VLAN_CTAG_TX |
 					     NETIF_F_HW_VLAN_STAG_TX);
 
@@ -6661,6 +6663,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
+	dev->gso_min_segs = 0;
 
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
-- 
cgit v1.2.3


From 82a470f1119eb7d2e4941b915bf9cd6fd8d54494 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 5 Oct 2014 21:27:53 -0700
Subject: net: sched: remove tcf_proto from ematch calls

This removes the tcf_proto argument from the ematch code paths that
only need it to reference the net namespace. This allows simplifying
qdisc code paths especially when we need to tear down the ematch
from an RCU callback. In this case we can not guarentee that the
tcf_proto structure is still valid.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h  | 10 +++++-----
 net/sched/cls_basic.c  |  2 +-
 net/sched/cls_cgroup.c |  4 ++--
 net/sched/cls_flow.c   |  4 ++--
 net/sched/em_canid.c   |  4 ++--
 net/sched/em_ipset.c   |  7 +++----
 net/sched/em_meta.c    |  4 ++--
 net/sched/em_nbyte.c   |  2 +-
 net/sched/em_text.c    |  4 ++--
 net/sched/ematch.c     | 10 ++++++----
 10 files changed, 26 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index ef44ad9a6426..bc49967e1a68 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -166,6 +166,7 @@ struct tcf_ematch {
 	unsigned int		datalen;
 	u16			matchid;
 	u16			flags;
+	struct net		*net;
 };
 
 static inline int tcf_em_is_container(struct tcf_ematch *em)
@@ -229,12 +230,11 @@ struct tcf_ematch_tree {
 struct tcf_ematch_ops {
 	int			kind;
 	int			datalen;
-	int			(*change)(struct tcf_proto *, void *,
+	int			(*change)(struct net *net, void *,
 					  int, struct tcf_ematch *);
 	int			(*match)(struct sk_buff *, struct tcf_ematch *,
 					 struct tcf_pkt_info *);
-	void			(*destroy)(struct tcf_proto *,
-					   struct tcf_ematch *);
+	void			(*destroy)(struct tcf_ematch *);
 	int			(*dump)(struct sk_buff *, struct tcf_ematch *);
 	struct module		*owner;
 	struct list_head	link;
@@ -244,7 +244,7 @@ int tcf_em_register(struct tcf_ematch_ops *);
 void tcf_em_unregister(struct tcf_ematch_ops *);
 int tcf_em_tree_validate(struct tcf_proto *, struct nlattr *,
 			 struct tcf_ematch_tree *);
-void tcf_em_tree_destroy(struct tcf_proto *, struct tcf_ematch_tree *);
+void tcf_em_tree_destroy(struct tcf_ematch_tree *);
 int tcf_em_tree_dump(struct sk_buff *, struct tcf_ematch_tree *, int);
 int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *,
 			struct tcf_pkt_info *);
@@ -301,7 +301,7 @@ struct tcf_ematch_tree {
 };
 
 #define tcf_em_tree_validate(tp, tb, t) ((void)(t), 0)
-#define tcf_em_tree_destroy(tp, t) do { (void)(t); } while(0)
+#define tcf_em_tree_destroy(t) do { (void)(t); } while(0)
 #define tcf_em_tree_dump(skb, t, tlv) (0)
 #define tcf_em_tree_change(tp, dst, src) do { } while(0)
 #define tcf_em_tree_match(skb, t, info) ((void)(info), 1)
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index fe20826a79e7..90647a8af8ca 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -95,7 +95,7 @@ static void basic_delete_filter(struct rcu_head *head)
 
 	tcf_unbind_filter(tp, &f->res);
 	tcf_exts_destroy(&f->exts);
-	tcf_em_tree_destroy(tp, &f->ematches);
+	tcf_em_tree_destroy(&f->ematches);
 	kfree(f);
 }
 
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 3409f168225f..2f77a89655dc 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -87,7 +87,7 @@ static void cls_cgroup_destroy_rcu(struct rcu_head *root)
 						    rcu);
 
 	tcf_exts_destroy(&head->exts);
-	tcf_em_tree_destroy(head->tp, &head->ematches);
+	tcf_em_tree_destroy(&head->ematches);
 	kfree(head);
 }
 
@@ -157,7 +157,7 @@ static void cls_cgroup_destroy(struct tcf_proto *tp)
 
 	if (head) {
 		tcf_exts_destroy(&head->exts);
-		tcf_em_tree_destroy(tp, &head->ematches);
+		tcf_em_tree_destroy(&head->ematches);
 		RCU_INIT_POINTER(tp->root, NULL);
 		kfree_rcu(head, rcu);
 	}
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index f18d27f7b5f2..a5d2b20db560 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -355,7 +355,7 @@ static void flow_destroy_filter(struct rcu_head *head)
 
 	del_timer_sync(&f->perturb_timer);
 	tcf_exts_destroy(&f->exts);
-	tcf_em_tree_destroy(f->tp, &f->ematches);
+	tcf_em_tree_destroy(&f->ematches);
 	kfree(f);
 }
 
@@ -530,7 +530,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	return 0;
 
 err2:
-	tcf_em_tree_destroy(tp, &t);
+	tcf_em_tree_destroy(&t);
 	kfree(fnew);
 err1:
 	tcf_exts_destroy(&e);
diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c
index 7c292d474f47..ddd883ca55b2 100644
--- a/net/sched/em_canid.c
+++ b/net/sched/em_canid.c
@@ -120,7 +120,7 @@ static int em_canid_match(struct sk_buff *skb, struct tcf_ematch *m,
 	return match;
 }
 
-static int em_canid_change(struct tcf_proto *tp, void *data, int len,
+static int em_canid_change(struct net *net, void *data, int len,
 			  struct tcf_ematch *m)
 {
 	struct can_filter *conf = data; /* Array with rules */
@@ -183,7 +183,7 @@ static int em_canid_change(struct tcf_proto *tp, void *data, int len,
 	return 0;
 }
 
-static void em_canid_destroy(struct tcf_proto *tp, struct tcf_ematch *m)
+static void em_canid_destroy(struct tcf_ematch *m)
 {
 	struct canid_match *cm = em_canid_priv(m);
 
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index 527aeb7a3ff0..5b4a4efe468c 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -19,12 +19,11 @@
 #include <net/ip.h>
 #include <net/pkt_cls.h>
 
-static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len,
+static int em_ipset_change(struct net *net, void *data, int data_len,
 			   struct tcf_ematch *em)
 {
 	struct xt_set_info *set = data;
 	ip_set_id_t index;
-	struct net *net = dev_net(qdisc_dev(tp->q));
 
 	if (data_len != sizeof(*set))
 		return -EINVAL;
@@ -42,11 +41,11 @@ static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len,
 	return -ENOMEM;
 }
 
-static void em_ipset_destroy(struct tcf_proto *p, struct tcf_ematch *em)
+static void em_ipset_destroy(struct tcf_ematch *em)
 {
 	const struct xt_set_info *set = (const void *) em->data;
 	if (set) {
-		ip_set_nfnl_put(dev_net(qdisc_dev(p->q)), set->index);
+		ip_set_nfnl_put(em->net, set->index);
 		kfree((void *) em->data);
 	}
 }
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 9b8c0b0e60d7..c8f8c399b99a 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -856,7 +856,7 @@ static const struct nla_policy meta_policy[TCA_EM_META_MAX + 1] = {
 	[TCA_EM_META_HDR]	= { .len = sizeof(struct tcf_meta_hdr) },
 };
 
-static int em_meta_change(struct tcf_proto *tp, void *data, int len,
+static int em_meta_change(struct net *net, void *data, int len,
 			  struct tcf_ematch *m)
 {
 	int err;
@@ -908,7 +908,7 @@ errout:
 	return err;
 }
 
-static void em_meta_destroy(struct tcf_proto *tp, struct tcf_ematch *m)
+static void em_meta_destroy(struct tcf_ematch *m)
 {
 	if (m)
 		meta_delete((struct meta_match *) m->data);
diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c
index a3bed07a008b..df3110d69585 100644
--- a/net/sched/em_nbyte.c
+++ b/net/sched/em_nbyte.c
@@ -23,7 +23,7 @@ struct nbyte_data {
 	char			pattern[0];
 };
 
-static int em_nbyte_change(struct tcf_proto *tp, void *data, int data_len,
+static int em_nbyte_change(struct net *net, void *data, int data_len,
 			   struct tcf_ematch *em)
 {
 	struct tcf_em_nbyte *nbyte = data;
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
index 15d353d2e4be..f03c3de16c27 100644
--- a/net/sched/em_text.c
+++ b/net/sched/em_text.c
@@ -45,7 +45,7 @@ static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m,
 	return skb_find_text(skb, from, to, tm->config, &state) != UINT_MAX;
 }
 
-static int em_text_change(struct tcf_proto *tp, void *data, int len,
+static int em_text_change(struct net *net, void *data, int len,
 			  struct tcf_ematch *m)
 {
 	struct text_match *tm;
@@ -100,7 +100,7 @@ retry:
 	return 0;
 }
 
-static void em_text_destroy(struct tcf_proto *tp, struct tcf_ematch *m)
+static void em_text_destroy(struct tcf_ematch *m)
 {
 	if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config)
 		textsearch_destroy(EM_TEXT_PRIV(m)->config);
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index ad57f4444b9c..8250c36543d8 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -178,6 +178,7 @@ static int tcf_em_validate(struct tcf_proto *tp,
 	struct tcf_ematch_hdr *em_hdr = nla_data(nla);
 	int data_len = nla_len(nla) - sizeof(*em_hdr);
 	void *data = (void *) em_hdr + sizeof(*em_hdr);
+	struct net *net = dev_net(qdisc_dev(tp->q));
 
 	if (!TCF_EM_REL_VALID(em_hdr->flags))
 		goto errout;
@@ -240,7 +241,7 @@ static int tcf_em_validate(struct tcf_proto *tp,
 			goto errout;
 
 		if (em->ops->change) {
-			err = em->ops->change(tp, data, data_len, em);
+			err = em->ops->change(net, data, data_len, em);
 			if (err < 0)
 				goto errout;
 		} else if (data_len > 0) {
@@ -271,6 +272,7 @@ static int tcf_em_validate(struct tcf_proto *tp,
 	em->matchid = em_hdr->matchid;
 	em->flags = em_hdr->flags;
 	em->datalen = data_len;
+	em->net = net;
 
 	err = 0;
 errout:
@@ -378,7 +380,7 @@ errout:
 	return err;
 
 errout_abort:
-	tcf_em_tree_destroy(tp, tree);
+	tcf_em_tree_destroy(tree);
 	return err;
 }
 EXPORT_SYMBOL(tcf_em_tree_validate);
@@ -393,7 +395,7 @@ EXPORT_SYMBOL(tcf_em_tree_validate);
  * tcf_em_tree_validate()/tcf_em_tree_change(). You must ensure that
  * the ematch tree is not in use before calling this function.
  */
-void tcf_em_tree_destroy(struct tcf_proto *tp, struct tcf_ematch_tree *tree)
+void tcf_em_tree_destroy(struct tcf_ematch_tree *tree)
 {
 	int i;
 
@@ -405,7 +407,7 @@ void tcf_em_tree_destroy(struct tcf_proto *tp, struct tcf_ematch_tree *tree)
 
 		if (em->ops) {
 			if (em->ops->destroy)
-				em->ops->destroy(tp, em);
+				em->ops->destroy(em);
 			else if (!tcf_em_is_simple(em))
 				kfree((void *) em->data);
 			module_put(em->ops->owner);
-- 
cgit v1.2.3


From 94b2cfe02bfe3f1918d91bd6f498e308c5605cbc Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 6 Oct 2014 19:58:34 +0200
Subject: ipv6: minor fib6 cleanups like type safety, bool conversion, inline
 removal

Also renamed struct fib6_walker_t to fib6_walker and enum fib_walk_state_t
to fib6_walk_state as recommended by Cong Wang.

Cc: Cong Wang <cwang@twopensource.com>
Cc: YOSHIFUJI Hideaki <hideaki@yoshifuji.org>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 18 ++++++++++---
 net/ipv6/ip6_fib.c    | 71 ++++++++++++++++++++++-----------------------------
 2 files changed, 45 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index cf485f9aa563..9221bf4c64f7 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -202,15 +202,25 @@ static inline void ip6_rt_put(struct rt6_info *rt)
 	dst_release(&rt->dst);
 }
 
-struct fib6_walker_t {
+enum fib6_walk_state {
+#ifdef CONFIG_IPV6_SUBTREES
+	FWS_S,
+#endif
+	FWS_L,
+	FWS_R,
+	FWS_C,
+	FWS_U
+};
+
+struct fib6_walker {
 	struct list_head lh;
 	struct fib6_node *root, *node;
 	struct rt6_info *leaf;
-	unsigned char state;
-	unsigned char prune;
+	enum fib6_walk_state state;
+	bool prune;
 	unsigned int skip;
 	unsigned int count;
-	int (*func)(struct fib6_walker_t *);
+	int (*func)(struct fib6_walker *);
 	void *args;
 };
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 97b9fa8de377..e8d7465b1597 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -46,18 +46,8 @@
 
 static struct kmem_cache *fib6_node_kmem __read_mostly;
 
-enum fib_walk_state_t {
-#ifdef CONFIG_IPV6_SUBTREES
-	FWS_S,
-#endif
-	FWS_L,
-	FWS_R,
-	FWS_C,
-	FWS_U
-};
-
-struct fib6_cleaner_t {
-	struct fib6_walker_t w;
+struct fib6_cleaner {
+	struct fib6_walker w;
 	struct net *net;
 	int (*func)(struct rt6_info *, void *arg);
 	void *arg;
@@ -74,8 +64,8 @@ static DEFINE_RWLOCK(fib6_walker_lock);
 static void fib6_prune_clones(struct net *net, struct fib6_node *fn);
 static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
 static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
-static int fib6_walk(struct fib6_walker_t *w);
-static int fib6_walk_continue(struct fib6_walker_t *w);
+static int fib6_walk(struct fib6_walker *w);
+static int fib6_walk_continue(struct fib6_walker *w);
 
 /*
  *	A routing update causes an increase of the serial number on the
@@ -91,20 +81,21 @@ static void fib6_gc_timer_cb(unsigned long arg);
 static LIST_HEAD(fib6_walkers);
 #define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh)
 
-static inline void fib6_walker_link(struct fib6_walker_t *w)
+static void fib6_walker_link(struct fib6_walker *w)
 {
 	write_lock_bh(&fib6_walker_lock);
 	list_add(&w->lh, &fib6_walkers);
 	write_unlock_bh(&fib6_walker_lock);
 }
 
-static inline void fib6_walker_unlink(struct fib6_walker_t *w)
+static void fib6_walker_unlink(struct fib6_walker *w)
 {
 	write_lock_bh(&fib6_walker_lock);
 	list_del(&w->lh);
 	write_unlock_bh(&fib6_walker_lock);
 }
-static __inline__ u32 fib6_new_sernum(void)
+
+static u32 fib6_new_sernum(void)
 {
 	u32 n = ++rt_sernum;
 	if ((__s32)n <= 0)
@@ -128,7 +119,7 @@ static __inline__ u32 fib6_new_sernum(void)
 # define BITOP_BE32_SWIZZLE	0
 #endif
 
-static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
+static __be32 addr_bit_set(const void *token, int fn_bit)
 {
 	const __be32 *addr = token;
 	/*
@@ -142,7 +133,7 @@ static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
 	       addr[fn_bit >> 5];
 }
 
-static __inline__ struct fib6_node *node_alloc(void)
+static struct fib6_node *node_alloc(void)
 {
 	struct fib6_node *fn;
 
@@ -151,12 +142,12 @@ static __inline__ struct fib6_node *node_alloc(void)
 	return fn;
 }
 
-static __inline__ void node_free(struct fib6_node *fn)
+static void node_free(struct fib6_node *fn)
 {
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
-static __inline__ void rt6_release(struct rt6_info *rt)
+static void rt6_release(struct rt6_info *rt)
 {
 	if (atomic_dec_and_test(&rt->rt6i_ref))
 		dst_free(&rt->dst);
@@ -267,7 +258,7 @@ static void __net_init fib6_tables_init(struct net *net)
 
 #endif
 
-static int fib6_dump_node(struct fib6_walker_t *w)
+static int fib6_dump_node(struct fib6_walker *w)
 {
 	int res;
 	struct rt6_info *rt;
@@ -287,7 +278,7 @@ static int fib6_dump_node(struct fib6_walker_t *w)
 
 static void fib6_dump_end(struct netlink_callback *cb)
 {
-	struct fib6_walker_t *w = (void *)cb->args[2];
+	struct fib6_walker *w = (void *)cb->args[2];
 
 	if (w) {
 		if (cb->args[4]) {
@@ -310,7 +301,7 @@ static int fib6_dump_done(struct netlink_callback *cb)
 static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
 			   struct netlink_callback *cb)
 {
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	int res;
 
 	w = (void *)cb->args[2];
@@ -355,7 +346,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned int h, s_h;
 	unsigned int e = 0, s_e;
 	struct rt6_rtnl_dump_arg arg;
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	struct fib6_table *tb;
 	struct hlist_head *head;
 	int res = 0;
@@ -627,7 +618,7 @@ insert_above:
 	return ln;
 }
 
-static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt)
+static bool rt6_qualify_for_ecmp(struct rt6_info *rt)
 {
 	return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
 	       RTF_GATEWAY;
@@ -820,7 +811,7 @@ add:
 	return 0;
 }
 
-static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt)
+static void fib6_start_gc(struct net *net, struct rt6_info *rt)
 {
 	if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
 	    (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
@@ -1174,7 +1165,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 	int children;
 	int nstate;
 	struct fib6_node *child, *pn;
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	int iter = 0;
 
 	for (;;) {
@@ -1276,7 +1267,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 			   struct nl_info *info)
 {
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	struct rt6_info *rt = *rtp;
 	struct net *net = info->nl_net;
 
@@ -1414,7 +1405,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
  *	<0  -> walk is terminated by an error.
  */
 
-static int fib6_walk_continue(struct fib6_walker_t *w)
+static int fib6_walk_continue(struct fib6_walker *w)
 {
 	struct fib6_node *fn, *pn;
 
@@ -1498,7 +1489,7 @@ skip:
 	}
 }
 
-static int fib6_walk(struct fib6_walker_t *w)
+static int fib6_walk(struct fib6_walker *w)
 {
 	int res;
 
@@ -1512,11 +1503,11 @@ static int fib6_walk(struct fib6_walker_t *w)
 	return res;
 }
 
-static int fib6_clean_node(struct fib6_walker_t *w)
+static int fib6_clean_node(struct fib6_walker *w)
 {
 	int res;
 	struct rt6_info *rt;
-	struct fib6_cleaner_t *c = container_of(w, struct fib6_cleaner_t, w);
+	struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
 	struct nl_info info = {
 		.nl_net = c->net,
 	};
@@ -1554,9 +1545,9 @@ static int fib6_clean_node(struct fib6_walker_t *w)
 
 static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 			    int (*func)(struct rt6_info *, void *arg),
-			    int prune, void *arg)
+			    bool prune, void *arg)
 {
-	struct fib6_cleaner_t c;
+	struct fib6_cleaner c;
 
 	c.w.root = root;
 	c.w.func = fib6_clean_node;
@@ -1583,7 +1574,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
 			write_lock_bh(&table->tb6_lock);
 			fib6_clean_tree(net, &table->tb6_root,
-					func, 0, arg);
+					func, false, arg);
 			write_unlock_bh(&table->tb6_lock);
 		}
 	}
@@ -1602,7 +1593,7 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
 
 static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
 {
-	fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL);
+	fib6_clean_tree(net, fn, fib6_prune_clone, true, NULL);
 }
 
 static int fib6_update_sernum(struct rt6_info *rt, void *arg)
@@ -1828,7 +1819,7 @@ void fib6_gc_cleanup(void)
 
 struct ipv6_route_iter {
 	struct seq_net_private p;
-	struct fib6_walker_t w;
+	struct fib6_walker w;
 	loff_t skip;
 	struct fib6_table *tbl;
 	__u32 sernum;
@@ -1859,7 +1850,7 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int ipv6_route_yield(struct fib6_walker_t *w)
+static int ipv6_route_yield(struct fib6_walker *w)
 {
 	struct ipv6_route_iter *iter = w->args;
 
@@ -1980,7 +1971,7 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
 
 static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
 {
-	struct fib6_walker_t *w = &iter->w;
+	struct fib6_walker *w = &iter->w;
 	return w->node && !(w->state == FWS_U && w->node == w->root);
 }
 
-- 
cgit v1.2.3


From 42b18706469a02c1f84375ac0ee2f30f28d85d4c Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 6 Oct 2014 19:58:35 +0200
Subject: ipv6: make rt_sernum atomic and serial number fields ordinary ints

Cc: YOSHIFUJI Hideaki <hideaki@yoshifuji.org>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  2 +-
 net/ipv6/ip6_fib.c    | 23 +++++++++++++----------
 2 files changed, 14 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 9221bf4c64f7..8eea35d32a75 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -64,7 +64,7 @@ struct fib6_node {
 
 	__u16			fn_bit;		/* bit key */
 	__u16			fn_flags;
-	__u32			fn_sernum;
+	int			fn_sernum;
 	struct rt6_info		*rr_ptr;
 };
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e8d7465b1597..332f1e0ff8e2 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -74,7 +74,7 @@ static int fib6_walk_continue(struct fib6_walker *w);
  *	result of redirects, path MTU changes, etc.
  */
 
-static __u32 rt_sernum;
+static atomic_t rt_sernum = ATOMIC_INIT(1);
 
 static void fib6_gc_timer_cb(unsigned long arg);
 
@@ -95,12 +95,15 @@ static void fib6_walker_unlink(struct fib6_walker *w)
 	write_unlock_bh(&fib6_walker_lock);
 }
 
-static u32 fib6_new_sernum(void)
+static int fib6_new_sernum(void)
 {
-	u32 n = ++rt_sernum;
-	if ((__s32)n <= 0)
-		rt_sernum = n = 1;
-	return n;
+	int new, old;
+
+	do {
+		old = atomic_read(&rt_sernum);
+		new = old < INT_MAX ? old + 1 : 1;
+	} while (atomic_cmpxchg(&rt_sernum, old, new) != old);
+	return new;
 }
 
 /*
@@ -421,7 +424,7 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 	struct rt6key *key;
 	int	bit;
 	__be32	dir = 0;
-	__u32	sernum = fib6_new_sernum();
+	int	sernum = fib6_new_sernum();
 
 	RT6_TRACE("fib6_add_1\n");
 
@@ -1598,7 +1601,7 @@ static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
 
 static int fib6_update_sernum(struct rt6_info *rt, void *arg)
 {
-	__u32 sernum = *(__u32 *)arg;
+	int sernum = *(int *)arg;
 
 	if (rt->rt6i_node &&
 	    rt->rt6i_node->fn_sernum != sernum)
@@ -1609,7 +1612,7 @@ static int fib6_update_sernum(struct rt6_info *rt, void *arg)
 
 static void fib6_flush_trees(struct net *net)
 {
-	__u32 new_sernum = fib6_new_sernum();
+	int new_sernum = fib6_new_sernum();
 
 	fib6_clean_all(net, fib6_update_sernum, &new_sernum);
 }
@@ -1822,7 +1825,7 @@ struct ipv6_route_iter {
 	struct fib6_walker w;
 	loff_t skip;
 	struct fib6_table *tbl;
-	__u32 sernum;
+	int sernum;
 };
 
 static int ipv6_route_seq_show(struct seq_file *seq, void *v)
-- 
cgit v1.2.3


From 812918c464eca0e8c145f975932ca5020e9c05cb Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 6 Oct 2014 19:58:37 +0200
Subject: ipv6: make fib6 serial number per namespace

Try to reduce number of possible fn_sernum mutation by constraining them
to their namespace.

Also remove rt_genid which I forgot to remove in 705f1c869d577c ("ipv6:
remove rt6i_genid").

Cc: YOSHIFUJI Hideaki <hideaki@yoshifuji.org>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv6.h |  2 +-
 net/ipv6/af_inet6.c      |  2 +-
 net/ipv6/ip6_fib.c       | 13 ++++++-------
 3 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index eade27adecf3..69ae41f2098c 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -76,7 +76,7 @@ struct netns_ipv6 {
 #endif
 #endif
 	atomic_t		dev_addr_genid;
-	atomic_t		rt_genid;
+	atomic_t		fib6_sernum;
 };
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 34f726f59814..e8c4400f23e9 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -766,7 +766,7 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.icmpv6_time = 1*HZ;
 	net->ipv6.sysctl.flowlabel_consistency = 1;
 	net->ipv6.sysctl.auto_flowlabels = 0;
-	atomic_set(&net->ipv6.rt_genid, 0);
+	atomic_set(&net->ipv6.fib6_sernum, 1);
 
 	err = ipv6_init_mibs(net);
 	if (err)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index be9cb09b05f7..6f9beb1f2861 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -74,8 +74,6 @@ static int fib6_walk_continue(struct fib6_walker *w);
  *	result of redirects, path MTU changes, etc.
  */
 
-static atomic_t rt_sernum = ATOMIC_INIT(1);
-
 static void fib6_gc_timer_cb(unsigned long arg);
 
 static LIST_HEAD(fib6_walkers);
@@ -95,14 +93,15 @@ static void fib6_walker_unlink(struct fib6_walker *w)
 	write_unlock_bh(&fib6_walker_lock);
 }
 
-static int fib6_new_sernum(void)
+static int fib6_new_sernum(struct net *net)
 {
 	int new, old;
 
 	do {
-		old = atomic_read(&rt_sernum);
+		old = atomic_read(&net->ipv6.fib6_sernum);
 		new = old < INT_MAX ? old + 1 : 1;
-	} while (atomic_cmpxchg(&rt_sernum, old, new) != old);
+	} while (atomic_cmpxchg(&net->ipv6.fib6_sernum,
+				old, new) != old);
 	return new;
 }
 
@@ -841,7 +840,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 	int err = -ENOMEM;
 	int allow_create = 1;
 	int replace_required = 0;
-	int sernum = fib6_new_sernum();
+	int sernum = fib6_new_sernum(info->nl_net);
 
 	if (info->nlh) {
 		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -1612,7 +1611,7 @@ static int fib6_update_sernum(struct rt6_info *rt, void *arg)
 
 static void fib6_flush_trees(struct net *net)
 {
-	int new_sernum = fib6_new_sernum();
+	int new_sernum = fib6_new_sernum(net);
 
 	fib6_clean_all(net, fib6_update_sernum, &new_sernum);
 }
-- 
cgit v1.2.3


From 7c5df8fa1921450d2210db9928f43cf4f414982c Mon Sep 17 00:00:00 2001
From: Andy Zhou <azhou@nicira.com>
Date: Mon, 6 Oct 2014 15:15:14 -0700
Subject: openvswitch: fix a compilation error when CONFIG_INET is not setW!

Fix a openvswitch compilation error when CONFIG_INET is not set:

=====================================================
   In file included from include/net/geneve.h:4:0,
                       from net/openvswitch/flow_netlink.c:45:
		          include/net/udp_tunnel.h: In function 'udp_tunnel_handle_offloads':
			  >> include/net/udp_tunnel.h:100:2: error: implicit declaration of function 'iptunnel_handle_offloads' [-Werror=implicit-function-declaration]
			  >>      return iptunnel_handle_offloads(skb, udp_csum, type);
			  >>           ^
			  >>           >> include/net/udp_tunnel.h:100:2: warning: return makes pointer from integer without a cast
			  >>           >>    cc1: some warnings being treated as errors

=====================================================

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Kconfig  |  1 -
 include/net/geneve.h | 36 +++++++++++++++++++++---------------
 net/ipv4/Kconfig     | 29 +++++++++++++++--------------
 3 files changed, 36 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index c6f6f69f8961..4706386b7d34 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -147,7 +147,6 @@ config MACVTAP
 config VXLAN
        tristate "Virtual eXtensible Local Area Network (VXLAN)"
        depends on INET
-       select NET_IP_TUNNEL
        select NET_UDP_TUNNEL
        ---help---
 	  This allows one to create vxlan virtual interfaces that provide
diff --git a/include/net/geneve.h b/include/net/geneve.h
index ce98865318bf..112132cf8e2e 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -1,22 +1,10 @@
 #ifndef __NET_GENEVE_H
 #define __NET_GENEVE_H  1
 
+#ifdef CONFIG_INET
 #include <net/udp_tunnel.h>
+#endif
 
-struct geneve_sock;
-
-typedef void (geneve_rcv_t)(struct geneve_sock *gs, struct sk_buff *skb);
-
-struct geneve_sock {
-	struct hlist_node	hlist;
-	geneve_rcv_t		*rcv;
-	void			*rcv_data;
-	struct work_struct	del_work;
-	struct socket		*sock;
-	struct rcu_head		rcu;
-	atomic_t		refcnt;
-	struct udp_offload	udp_offloads;
-};
 
 /* Geneve Header:
  *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -74,6 +62,22 @@ struct genevehdr {
 	struct geneve_opt options[];
 };
 
+#ifdef CONFIG_INET
+struct geneve_sock;
+
+typedef void (geneve_rcv_t)(struct geneve_sock *gs, struct sk_buff *skb);
+
+struct geneve_sock {
+	struct hlist_node	hlist;
+	geneve_rcv_t		*rcv;
+	void			*rcv_data;
+	struct work_struct	del_work;
+	struct socket		*sock;
+	struct rcu_head		rcu;
+	atomic_t		refcnt;
+	struct udp_offload	udp_offloads;
+};
+
 #define GENEVE_VER 0
 #define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr))
 
@@ -88,4 +92,6 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 		    __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
 		    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
 		    bool xnet);
-#endif
+#endif /*ifdef CONFIG_INET */
+
+#endif /*ifdef__NET_GENEVE_H */
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index c2035447e649..e682b48e0709 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -309,6 +309,7 @@ config NET_IPVTI
 
 config NET_UDP_TUNNEL
 	tristate
+	select NET_IP_TUNNEL
 	default n
 
 config NET_FOU
@@ -321,6 +322,20 @@ config NET_FOU
 	  network mechanisms and optimizations for UDP (such as ECMP
 	  and RSS) can be leveraged to provide better service.
 
+config GENEVE
+	tristate "Generic Network Virtualization Encapsulation (Geneve)"
+	depends on INET
+	select NET_UDP_TUNNEL
+	---help---
+	This allows one to create Geneve virtual interfaces that provide
+	Layer 2 Networks over Layer 3 Networks. Geneve is often used
+	to tunnel virtual network infrastructure in virtualized environments.
+	For more information see:
+	  http://tools.ietf.org/html/draft-gross-geneve-01
+
+	  To compile this driver as a module, choose M here: the module
+
+
 config INET_AH
 	tristate "IP: AH transformation"
 	select XFRM_ALGO
@@ -453,20 +468,6 @@ config TCP_CONG_BIC
 	increase provides TCP friendliness.
 	See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
 
-config GENEVE
-	tristate "Generic Network Virtualization Encapsulation (Geneve)"
-	depends on INET
-	select NET_IP_TUNNEL
-	select NET_UDP_TUNNEL
-	---help---
-	This allows one to create Geneve virtual interfaces that provide
-	Layer 2 Networks over Layer 3 Networks. Geneve is often used
-	to tunnel virtual network infrastructure in virtualized environments.
-	For more information see:
-	  http://tools.ietf.org/html/draft-gross-geneve-01
-
-	  To compile this driver as a module, choose M here: the module
-
 config TCP_CONG_CUBIC
 	tristate "CUBIC TCP"
 	default y
-- 
cgit v1.2.3


From 422b67e0b31a0ed132f8091b6f3d5465d9df9387 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ti.com>
Date: Mon, 6 Oct 2014 15:03:57 +0300
Subject: videomode: provide dummy inline functions for !CONFIG_OF

If CONFIG_OF is disabled but we build any driver that tries to
use of_get_display_timing, we get this link error:

ERROR: "of_get_display_timing" [drivers/gpu/drm/rcar-du/rcar-du-drm.ko] undefined!

This adds an empty inline function as an alternative, to avoid changing
each driver using this function when we want to build them without
CONFIG_OF.

Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 include/video/of_display_timing.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/video/of_display_timing.h b/include/video/of_display_timing.h
index 79e6697af6cf..ea755b5616d8 100644
--- a/include/video/of_display_timing.h
+++ b/include/video/of_display_timing.h
@@ -15,9 +15,25 @@ struct display_timings;
 
 #define OF_USE_NATIVE_MODE -1
 
+#ifdef CONFIG_OF
 int of_get_display_timing(struct device_node *np, const char *name,
 		struct display_timing *dt);
 struct display_timings *of_get_display_timings(struct device_node *np);
 int of_display_timings_exist(struct device_node *np);
+#else
+static inline int of_get_display_timing(struct device_node *np, const char *name,
+		struct display_timing *dt)
+{
+	return -ENOSYS;
+}
+static inline struct display_timings *of_get_display_timings(struct device_node *np)
+{
+	return NULL;
+}
+static inline int of_display_timings_exist(struct device_node *np)
+{
+	return -ENOSYS;
+}
+#endif
 
 #endif
-- 
cgit v1.2.3


From b5e7a955a3515bf6b568050533fa9b1b72460a95 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 30 Sep 2014 13:38:20 +0200
Subject: ARM: KVM: fix vgic-disabled build

The vgic code can be disabled in Kconfig and there are dummy implementations
of most of the provided API functions for the disabled case.

However, the newly introduced kvm_vgic_destroy/kvm_vgic_vcpu_destroy
functions are lacking those dummies, resulting in this build error:

arch/arm/kvm/arm.c: In function 'kvm_arch_destroy_vm':
arch/arm/kvm/arm.c:165:2: error: implicit declaration of function 'kvm_vgic_destroy' [-Werror=implicit-function-declaration]
  kvm_vgic_destroy(kvm);
  ^
arch/arm/kvm/arm.c: In function 'kvm_arch_vcpu_free':
arch/arm/kvm/arm.c:248:2: error: implicit declaration of function 'kvm_vgic_vcpu_destroy' [-Werror=implicit-function-declaration]
  kvm_vgic_vcpu_destroy(vcpu);
  ^

This adds two inline helpers to get it to build again in this configuration.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: c1bfb577add ("arm/arm64: KVM: vgic: switch to dynamic allocation")
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 include/kvm/arm_vgic.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 2f2aac8448a4..ec559d3264cc 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -331,6 +331,14 @@ static inline int kvm_vgic_create(struct kvm *kvm)
 	return 0;
 }
 
+static inline void kvm_vgic_destroy(struct kvm *kvm)
+{
+}
+
+static inline void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+}
+
 static inline int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	return 0;
-- 
cgit v1.2.3


From fd2ef0ba3071c92ac6272ab22ea3f2b16d88a4eb Mon Sep 17 00:00:00 2001
From: Petri Gynther <pgynther@google.com>
Date: Mon, 6 Oct 2014 11:38:30 -0700
Subject: net: phy: adjust fixed_phy_register() return value

Adjust fixed_phy_register() to return struct phy_device *, so that
it becomes easy to use fixed PHYs without device tree support:

  phydev = fixed_phy_register(PHY_POLL, &fixed_phy_status, NULL);
  fixed_phy_set_link_update(phydev, fixed_phy_link_update);
  phy_connect_direct(netdev, phydev, handler_fn, phy_interface);

This change is a prerequisite for modifying bcmgenet driver to work
without a device tree on Broadcom's MIPS-based 7xxx platforms.

Signed-off-by: Petri Gynther <pgynther@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/fixed.c   | 16 ++++++++--------
 drivers/of/of_mdio.c      |  7 +++++--
 include/linux/phy_fixed.h | 14 +++++++-------
 3 files changed, 20 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/fixed.c b/drivers/net/phy/fixed.c
index 5b19fbbda6d4..47872caa0081 100644
--- a/drivers/net/phy/fixed.c
+++ b/drivers/net/phy/fixed.c
@@ -233,9 +233,9 @@ EXPORT_SYMBOL_GPL(fixed_phy_del);
 static int phy_fixed_addr;
 static DEFINE_SPINLOCK(phy_fixed_addr_lock);
 
-int fixed_phy_register(unsigned int irq,
-		       struct fixed_phy_status *status,
-		       struct device_node *np)
+struct phy_device *fixed_phy_register(unsigned int irq,
+				      struct fixed_phy_status *status,
+				      struct device_node *np)
 {
 	struct fixed_mdio_bus *fmb = &platform_fmb;
 	struct phy_device *phy;
@@ -246,19 +246,19 @@ int fixed_phy_register(unsigned int irq,
 	spin_lock(&phy_fixed_addr_lock);
 	if (phy_fixed_addr == PHY_MAX_ADDR) {
 		spin_unlock(&phy_fixed_addr_lock);
-		return -ENOSPC;
+		return ERR_PTR(-ENOSPC);
 	}
 	phy_addr = phy_fixed_addr++;
 	spin_unlock(&phy_fixed_addr_lock);
 
 	ret = fixed_phy_add(PHY_POLL, phy_addr, status);
 	if (ret < 0)
-		return ret;
+		return ERR_PTR(ret);
 
 	phy = get_phy_device(fmb->mii_bus, phy_addr, false);
 	if (!phy || IS_ERR(phy)) {
 		fixed_phy_del(phy_addr);
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 	}
 
 	of_node_get(np);
@@ -269,10 +269,10 @@ int fixed_phy_register(unsigned int irq,
 		phy_device_free(phy);
 		of_node_put(np);
 		fixed_phy_del(phy_addr);
-		return ret;
+		return ERR_PTR(ret);
 	}
 
-	return 0;
+	return phy;
 }
 
 static int __init fixed_mdio_bus_init(void)
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index a85d80012993..1bd43053b8c7 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -286,6 +286,7 @@ int of_phy_register_fixed_link(struct device_node *np)
 	struct device_node *fixed_link_node;
 	const __be32 *fixed_link_prop;
 	int len;
+	struct phy_device *phy;
 
 	/* New binding */
 	fixed_link_node = of_get_child_by_name(np, "fixed-link");
@@ -299,7 +300,8 @@ int of_phy_register_fixed_link(struct device_node *np)
 		status.asym_pause = of_property_read_bool(fixed_link_node,
 							  "asym-pause");
 		of_node_put(fixed_link_node);
-		return fixed_phy_register(PHY_POLL, &status, np);
+		phy = fixed_phy_register(PHY_POLL, &status, np);
+		return IS_ERR(phy) ? PTR_ERR(phy) : 0;
 	}
 
 	/* Old binding */
@@ -310,7 +312,8 @@ int of_phy_register_fixed_link(struct device_node *np)
 		status.speed = be32_to_cpu(fixed_link_prop[2]);
 		status.pause = be32_to_cpu(fixed_link_prop[3]);
 		status.asym_pause = be32_to_cpu(fixed_link_prop[4]);
-		return fixed_phy_register(PHY_POLL, &status, np);
+		phy = fixed_phy_register(PHY_POLL, &status, np);
+		return IS_ERR(phy) ? PTR_ERR(phy) : 0;
 	}
 
 	return -ENODEV;
diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index 941138664c1d..f2ca1b459377 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -14,9 +14,9 @@ struct device_node;
 #ifdef CONFIG_FIXED_PHY
 extern int fixed_phy_add(unsigned int irq, int phy_id,
 			 struct fixed_phy_status *status);
-extern int fixed_phy_register(unsigned int irq,
-			      struct fixed_phy_status *status,
-			      struct device_node *np);
+extern struct phy_device *fixed_phy_register(unsigned int irq,
+					     struct fixed_phy_status *status,
+					     struct device_node *np);
 extern void fixed_phy_del(int phy_addr);
 extern int fixed_phy_set_link_update(struct phy_device *phydev,
 			int (*link_update)(struct net_device *,
@@ -27,11 +27,11 @@ static inline int fixed_phy_add(unsigned int irq, int phy_id,
 {
 	return -ENODEV;
 }
-static inline int fixed_phy_register(unsigned int irq,
-				     struct fixed_phy_status *status,
-				     struct device_node *np)
+static inline struct phy_device *fixed_phy_register(unsigned int irq,
+						struct fixed_phy_status *status,
+						struct device_node *np)
 {
-	return -ENODEV;
+	return ERR_PTR(-ENODEV);
 }
 static inline int fixed_phy_del(int phy_addr)
 {
-- 
cgit v1.2.3


From 0287587884b15041203b3a362d485e1ab1f24445 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 5 Oct 2014 18:38:35 -0700
Subject: net: better IFF_XMIT_DST_RELEASE support

Testing xmit_more support with netperf and connected UDP sockets,
I found strange dst refcount false sharing.

Current handling of IFF_XMIT_DST_RELEASE is not optimal.

Dropping dst in validate_xmit_skb() is certainly too late in case
packet was queued by cpu X but dequeued by cpu Y

The logical point to take care of drop/force is in __dev_queue_xmit()
before even taking qdisc lock.

As Julian Anastasov pointed out, need for skb_dst() might come from some
packet schedulers or classifiers.

This patch adds new helper to cleanly express needs of various drivers
or qdiscs/classifiers.

Drivers that need skb_dst() in their ndo_start_xmit() should call
following helper in their setup instead of the prior :

	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
->
	netif_keep_dst(dev);

Instead of using a single bit, we use two bits, one being
eventually rebuilt in bonding/team drivers.

The other one, is permanent and blocks IFF_XMIT_DST_RELEASE being
rebuilt in bonding/team. Eventually, we could add something
smarter later.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/ulp/ipoib/ipoib_main.c |  2 +-
 drivers/net/appletalk/ipddp.c             |  2 +-
 drivers/net/bonding/bond_main.c           |  9 ++++++---
 drivers/net/eql.c                         |  2 +-
 drivers/net/ifb.c                         |  3 ++-
 drivers/net/loopback.c                    |  2 +-
 drivers/net/macvlan.c                     |  3 ++-
 drivers/net/ppp/ppp_generic.c             |  2 +-
 drivers/net/team/team.c                   |  8 +++++---
 drivers/net/vxlan.c                       |  2 +-
 drivers/net/wan/hdlc_fr.c                 |  2 +-
 drivers/s390/net/qeth_l3_main.c           |  2 +-
 include/linux/netdevice.h                 |  8 ++++++++
 net/8021q/vlan_dev.c                      |  3 ++-
 net/atm/clip.c                            |  2 +-
 net/core/dev.c                            | 19 +++++++++----------
 net/ipv4/ip_gre.c                         |  2 +-
 net/ipv4/ip_vti.c                         |  2 +-
 net/ipv4/ipip.c                           |  2 +-
 net/ipv6/ip6_gre.c                        |  2 +-
 net/ipv6/ip6_tunnel.c                     |  2 +-
 net/ipv6/ip6_vti.c                        |  2 +-
 net/ipv6/sit.c                            |  2 +-
 net/sched/cls_flow.c                      |  2 ++
 net/sched/cls_route.c                     |  1 +
 net/sched/sch_generic.c                   |  3 ---
 net/sched/sch_teql.c                      |  2 +-
 27 files changed, 54 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 13e6e0431592..58b5aa3b6f2d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1364,7 +1364,7 @@ void ipoib_setup(struct net_device *dev)
 	dev->tx_queue_len	 = ipoib_sendq_size * 2;
 	dev->features		 = (NETIF_F_VLAN_CHALLENGED	|
 				    NETIF_F_HIGHDMA);
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 
 	memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN);
 
diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
index 10d0dba572c2..e90c6a7333d7 100644
--- a/drivers/net/appletalk/ipddp.c
+++ b/drivers/net/appletalk/ipddp.c
@@ -74,7 +74,7 @@ static struct net_device * __init ipddp_init(void)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	strcpy(dev->name, "ipddp%d");
 
 	if (version_printed++ == 0)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3ad5413d4f57..c9ac06cfe6b7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1002,7 +1002,8 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 
 static void bond_compute_features(struct bonding *bond)
 {
-	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
+	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
+					IFF_XMIT_DST_RELEASE_PERM;
 	netdev_features_t vlan_features = BOND_VLAN_FEATURES;
 	netdev_features_t enc_features  = BOND_ENC_FEATURES;
 	struct net_device *bond_dev = bond->dev;
@@ -1038,8 +1039,10 @@ done:
 	bond_dev->gso_max_segs = gso_max_segs;
 	netif_set_gso_max_size(bond_dev, gso_max_size);
 
-	flags = bond_dev->priv_flags & ~IFF_XMIT_DST_RELEASE;
-	bond_dev->priv_flags = flags | dst_release_flag;
+	bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) &&
+	    dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
+		bond_dev->priv_flags |= IFF_XMIT_DST_RELEASE;
 
 	netdev_change_features(bond_dev);
 }
diff --git a/drivers/net/eql.c b/drivers/net/eql.c
index 957e5c0cede3..a10ad74cc8d2 100644
--- a/drivers/net/eql.c
+++ b/drivers/net/eql.c
@@ -199,7 +199,7 @@ static void __init eql_setup(struct net_device *dev)
 
 	dev->type       	= ARPHRD_SLIP;
 	dev->tx_queue_len 	= 5;		/* Hands them off fast */
-	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static int eql_open(struct net_device *dev)
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index d2d4a3d2237f..34f846b4bd05 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -185,7 +185,8 @@ static void ifb_setup(struct net_device *dev)
 
 	dev->flags |= IFF_NOARP;
 	dev->flags &= ~IFF_MULTICAST;
-	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	netif_keep_dst(dev);
 	eth_hw_addr_random(dev);
 }
 
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 8f2262540561..c76283c2f84a 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -169,7 +169,7 @@ static void loopback_setup(struct net_device *dev)
 	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
 	dev->flags		= IFF_LOOPBACK;
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE;
-	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	dev->hw_features	= NETIF_F_ALL_TSO | NETIF_F_UFO;
 	dev->features 		= NETIF_F_SG | NETIF_F_FRAGLIST
 		| NETIF_F_ALL_TSO
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index e8a453f1b458..38b4fae61f04 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1025,7 +1025,8 @@ void macvlan_common_setup(struct net_device *dev)
 {
 	ether_setup(dev);
 
-	dev->priv_flags	       &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->priv_flags	       &= ~IFF_TX_SKB_SHARING;
+	netif_keep_dst(dev);
 	dev->priv_flags	       |= IFF_UNICAST_FLT;
 	dev->netdev_ops		= &macvlan_netdev_ops;
 	dev->destructor		= free_netdev;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index fa0d71727894..80e6f3430f65 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1103,7 +1103,7 @@ static void ppp_setup(struct net_device *dev)
 	dev->type = ARPHRD_PPP;
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
 	dev->features |= NETIF_F_NETNS_LOCAL;
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 /*
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2277c3679a51..a94a9df3e6bd 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -970,7 +970,8 @@ static void __team_compute_features(struct team *team)
 	struct team_port *port;
 	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
 	unsigned short max_hard_header_len = ETH_HLEN;
-	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
+	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
+					IFF_XMIT_DST_RELEASE_PERM;
 
 	list_for_each_entry(port, &team->port_list, list) {
 		vlan_features = netdev_increment_features(vlan_features,
@@ -985,8 +986,9 @@ static void __team_compute_features(struct team *team)
 	team->dev->vlan_features = vlan_features;
 	team->dev->hard_header_len = max_hard_header_len;
 
-	flags = team->dev->priv_flags & ~IFF_XMIT_DST_RELEASE;
-	team->dev->priv_flags = flags | dst_release_flag;
+	team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
+		team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
 
 	netdev_change_features(team->dev);
 }
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2af795d6ba05..2a51e6e48e1e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2193,7 +2193,7 @@ static void vxlan_setup(struct net_device *dev)
 	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
-	dev->priv_flags	&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	INIT_LIST_HEAD(&vxlan->next);
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index e5c7e6165a4b..3ebed1c40abb 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -1047,7 +1047,7 @@ static void pvc_setup(struct net_device *dev)
 	dev->flags = IFF_POINTOPOINT;
 	dev->hard_header_len = 10;
 	dev->addr_len = 2;
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static const struct net_device_ops pvc_ops = {
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index f8427a2c4840..afebb9709763 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3306,7 +3306,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 	card->dev->features |=	NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
-	card->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(card->dev);
 	card->dev->gso_max_size = 15 * PAGE_SIZE;
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2df86f50261c..3a4315b39d20 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1206,6 +1206,7 @@ enum netdev_priv_flags {
 	IFF_SUPP_NOFCS			= 1<<19,
 	IFF_LIVE_ADDR_CHANGE		= 1<<20,
 	IFF_MACVLAN			= 1<<21,
+	IFF_XMIT_DST_RELEASE_PERM	= 1<<22,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1230,6 +1231,7 @@ enum netdev_priv_flags {
 #define IFF_SUPP_NOFCS			IFF_SUPP_NOFCS
 #define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
 #define IFF_MACVLAN			IFF_MACVLAN
+#define IFF_XMIT_DST_RELEASE_PERM	IFF_XMIT_DST_RELEASE_PERM
 
 /**
  *	struct net_device - The DEVICE structure.
@@ -3588,6 +3590,12 @@ static inline bool netif_supports_nofcs(struct net_device *dev)
 	return dev->priv_flags & IFF_SUPP_NOFCS;
 }
 
+/* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
+static inline void netif_keep_dst(struct net_device *dev)
+{
+	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM);
+}
+
 extern struct pernet_operations __net_initdata loopback_net_ops;
 
 /* Logging, debugging and troubleshooting/diagnostic helpers. */
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 35a6b6b15e8a..0d441ec8763e 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -799,7 +799,8 @@ void vlan_setup(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->priv_flags		|= IFF_802_1Q_VLAN;
-	dev->priv_flags		&= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->priv_flags		&= ~IFF_TX_SKB_SHARING;
+	netif_keep_dst(dev);
 	dev->tx_queue_len	= 0;
 
 	dev->netdev_ops		= &vlan_netdev_ops;
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 1d9eaa4f041a..17e55dfecbe2 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -501,7 +501,7 @@ static void clip_setup(struct net_device *dev)
 	/* without any more elaborate queuing. 100 is a reasonable */
 	/* compromise between decent burst-tolerance and protection */
 	/* against memory hogs. */
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static int clip_create(int number)
diff --git a/net/core/dev.c b/net/core/dev.c
index a63b8c43c1b6..3c5bdaa44486 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2665,12 +2665,6 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 	if (skb->next)
 		return skb;
 
-	/* If device doesn't need skb->dst, release it right now while
-	 * its hot in this cpu cache
-	 */
-	if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
-		skb_dst_drop(skb);
-
 	features = netif_skb_features(skb);
 	skb = validate_xmit_vlan(skb, features);
 	if (unlikely(!skb))
@@ -2811,8 +2805,6 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		 * waiting to be sent out; and the qdisc is not running -
 		 * xmit the skb directly.
 		 */
-		if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
-			skb_dst_force(skb);
 
 		qdisc_bstats_update(q, skb);
 
@@ -2827,7 +2819,6 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 		rc = NET_XMIT_SUCCESS;
 	} else {
-		skb_dst_force(skb);
 		rc = q->enqueue(skb, q) & NET_XMIT_MASK;
 		if (qdisc_run_begin(q)) {
 			if (unlikely(contended)) {
@@ -2924,6 +2915,14 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 
 	skb_update_prio(skb);
 
+	/* If device/qdisc don't need skb->dst, release it right now while
+	 * its hot in this cpu cache.
+	 */
+	if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+		skb_dst_drop(skb);
+	else
+		skb_dst_force(skb);
+
 	txq = netdev_pick_tx(dev, skb, accel_priv);
 	q = rcu_dereference_bh(txq->qdisc);
 
@@ -6674,7 +6673,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	INIT_LIST_HEAD(&dev->adj_list.lower);
 	INIT_LIST_HEAD(&dev->all_adj_list.upper);
 	INIT_LIST_HEAD(&dev->all_adj_list.lower);
-	dev->priv_flags = IFF_XMIT_DST_RELEASE;
+	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
 	dev->num_tx_queues = txqs;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0485ef18d254..12055fdbe716 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -510,7 +510,7 @@ static int ipgre_tunnel_init(struct net_device *dev)
 	memcpy(dev->broadcast, &iph->daddr, 4);
 
 	dev->flags		= IFF_NOARP;
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	dev->addr_len		= 4;
 
 	if (iph->daddr) {
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e453cb724a95..3e861011e4a3 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -364,7 +364,7 @@ static int vti_tunnel_init(struct net_device *dev)
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 
 	return ip_tunnel_init(dev);
 }
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index ea88ab3102a8..37096d64730e 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -289,7 +289,7 @@ static void ipip_tunnel_setup(struct net_device *dev)
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 
 	dev->features		|= IPIP_FEATURES;
 	dev->hw_features	|= IPIP_FEATURES;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 74b677916a70..de3b1c86b8d3 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1242,7 +1242,7 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 	dev->flags |= IFF_NOARP;
 	dev->iflink = 0;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static int ip6gre_tunnel_init(struct net_device *dev)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index d3e8888ad611..9409887fb664 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1493,7 +1493,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
 		dev->mtu -= 8;
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	/* This perm addr will be used as interface identifier by IPv6 */
 	dev->addr_assign_type = NET_ADDR_RANDOM;
 	eth_random_addr(dev->perm_addr);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 5833a2244467..d440bb585524 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -807,7 +807,7 @@ static void vti6_dev_setup(struct net_device *dev)
 	dev->mtu = ETH_DATA_LEN;
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 /**
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 0d4e27466f82..6eab37cf5345 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1364,7 +1364,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;
 	dev->mtu		= ETH_DATA_LEN - t_hlen;
 	dev->flags		= IFF_NOARP;
-	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index a5d2b20db560..4ac515f2a6ce 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -493,6 +493,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	tcf_exts_change(tp, &fnew->exts, &e);
 	tcf_em_tree_change(tp, &fnew->ematches, &t);
 
+	netif_keep_dst(qdisc_dev(tp->q));
+
 	if (tb[TCA_FLOW_KEYS]) {
 		fnew->keymask = keymask;
 		fnew->nkeys   = nkeys;
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 6f22baae0afa..109a329b7198 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -524,6 +524,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 		if (f->handle < f1->handle)
 			break;
 
+	netif_keep_dst(qdisc_dev(tp->q));
 	rcu_assign_pointer(f->next, f1);
 	rcu_assign_pointer(*fp, f);
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2b349a4de3c8..38d58e6cef07 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -47,7 +47,6 @@ EXPORT_SYMBOL(default_qdisc_ops);
 
 static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
-	skb_dst_force(skb);
 	q->gso_skb = skb;
 	q->qstats.requeues++;
 	q->q.qlen++;	/* it's still part of the queue */
@@ -218,8 +217,6 @@ static inline int qdisc_restart(struct Qdisc *q)
 	if (unlikely(!skb))
 		return 0;
 
-	WARN_ON_ONCE(skb_dst_is_noref(skb));
-
 	root_lock = qdisc_lock(q);
 	dev = qdisc_dev(q);
 	txq = skb_get_tx_queue(dev, skb);
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 5cd291bd00e4..6ada42396a24 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -470,7 +470,7 @@ static __init void teql_master_setup(struct net_device *dev)
 	dev->tx_queue_len	= 100;
 	dev->flags		= IFF_NOARP;
 	dev->hard_header_len	= LL_MAX_HEADER;
-	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
+	netif_keep_dst(dev);
 }
 
 static LIST_HEAD(master_dev_list);
-- 
cgit v1.2.3


From 91c1a09b33c902e20e09d9742560cc238a714de5 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 7 Oct 2014 18:48:12 +0200
Subject: netfilter: kill nf_send_reset6() from
 include/net/netfilter/ipv6/nf_reject.h

nf_send_reset6() now resides in net/ipv6/netfilter/nf_reject_ipv6.c

Fixes: c8d7b98 ("netfilter: move nf_send_resetX() code to nf_reject_ipvX modules")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Eric Dumazet <edumazet@google.com>
---
 include/net/netfilter/ipv6/nf_reject.h | 157 +--------------------------------
 1 file changed, 2 insertions(+), 155 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/ipv6/nf_reject.h b/include/net/netfilter/ipv6/nf_reject.h
index 7a10cfcd8e33..48e18810a9be 100644
--- a/include/net/netfilter/ipv6/nf_reject.h
+++ b/include/net/netfilter/ipv6/nf_reject.h
@@ -1,11 +1,7 @@
 #ifndef _IPV6_NF_REJECT_H
 #define _IPV6_NF_REJECT_H
 
-#include <net/ipv6.h>
-#include <net/ip6_route.h>
-#include <net/ip6_fib.h>
-#include <net/ip6_checksum.h>
-#include <linux/netfilter_ipv6.h>
+#include <linux/icmpv6.h>
 
 static inline void
 nf_send_unreach6(struct net *net, struct sk_buff *skb_in, unsigned char code,
@@ -17,155 +13,6 @@ nf_send_unreach6(struct net *net, struct sk_buff *skb_in, unsigned char code,
 	icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
 }
 
-/* Send RST reply */
-static void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
-{
-	struct sk_buff *nskb;
-	struct tcphdr otcph, *tcph;
-	unsigned int otcplen, hh_len;
-	int tcphoff, needs_ack;
-	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
-	struct ipv6hdr *ip6h;
-#define DEFAULT_TOS_VALUE	0x0U
-	const __u8 tclass = DEFAULT_TOS_VALUE;
-	struct dst_entry *dst = NULL;
-	u8 proto;
-	__be16 frag_off;
-	struct flowi6 fl6;
-
-	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
-	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
-		pr_debug("addr is not unicast.\n");
-		return;
-	}
-
-	proto = oip6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
-
-	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
-		pr_debug("Cannot get TCP header.\n");
-		return;
-	}
-
-	otcplen = oldskb->len - tcphoff;
-
-	/* IP header checks: fragment, too short. */
-	if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
-		pr_debug("proto(%d) != IPPROTO_TCP, "
-			 "or too short. otcplen = %d\n",
-			 proto, otcplen);
-		return;
-	}
-
-	if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
-		BUG();
-
-	/* No RST for RST. */
-	if (otcph.rst) {
-		pr_debug("RST is set\n");
-		return;
-	}
-
-	/* Check checksum. */
-	if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) {
-		pr_debug("TCP checksum is invalid\n");
-		return;
-	}
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_TCP;
-	fl6.saddr = oip6h->daddr;
-	fl6.daddr = oip6h->saddr;
-	fl6.fl6_sport = otcph.dest;
-	fl6.fl6_dport = otcph.source;
-	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst == NULL || dst->error) {
-		dst_release(dst);
-		return;
-	}
-	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
-	if (IS_ERR(dst))
-		return;
-
-	hh_len = (dst->dev->hard_header_len + 15)&~15;
-	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
-			 + sizeof(struct tcphdr) + dst->trailer_len,
-			 GFP_ATOMIC);
-
-	if (!nskb) {
-		net_dbg_ratelimited("cannot alloc skb\n");
-		dst_release(dst);
-		return;
-	}
-
-	skb_dst_set(nskb, dst);
-
-	skb_reserve(nskb, hh_len + dst->header_len);
-
-	skb_put(nskb, sizeof(struct ipv6hdr));
-	skb_reset_network_header(nskb);
-	ip6h = ipv6_hdr(nskb);
-	ip6_flow_hdr(ip6h, tclass, 0);
-	ip6h->hop_limit = ip6_dst_hoplimit(dst);
-	ip6h->nexthdr = IPPROTO_TCP;
-	ip6h->saddr = oip6h->daddr;
-	ip6h->daddr = oip6h->saddr;
-
-	skb_reset_transport_header(nskb);
-	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
-	/* Truncate to length (no data) */
-	tcph->doff = sizeof(struct tcphdr)/4;
-	tcph->source = otcph.dest;
-	tcph->dest = otcph.source;
-
-	if (otcph.ack) {
-		needs_ack = 0;
-		tcph->seq = otcph.ack_seq;
-		tcph->ack_seq = 0;
-	} else {
-		needs_ack = 1;
-		tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
-				      + otcplen - (otcph.doff<<2));
-		tcph->seq = 0;
-	}
-
-	/* Reset flags */
-	((u_int8_t *)tcph)[13] = 0;
-	tcph->rst = 1;
-	tcph->ack = needs_ack;
-	tcph->window = 0;
-	tcph->urg_ptr = 0;
-	tcph->check = 0;
-
-	/* Adjust TCP checksum */
-	tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
-				      &ipv6_hdr(nskb)->daddr,
-				      sizeof(struct tcphdr), IPPROTO_TCP,
-				      csum_partial(tcph,
-						   sizeof(struct tcphdr), 0));
-
-	nf_ct_attach(nskb, oldskb);
-
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	/* If we use ip6_local_out for bridged traffic, the MAC source on
-	 * the RST will be ours, instead of the destination's.  This confuses
-	 * some routers/firewalls, and they drop the packet.  So we need to
-	 * build the eth header using the original destination's MAC as the
-	 * source, and send the RST packet directly.
-	 */
-	if (oldskb->nf_bridge) {
-		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
-		nskb->protocol = htons(ETH_P_IPV6);
-		ip6h->payload_len = htons(sizeof(struct tcphdr));
-		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
-				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
-			return;
-		dev_queue_xmit(nskb);
-	} else
-#endif
-		ip6_local_out(nskb);
-}
+void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook);
 
 #endif /* _IPV6_NF_REJECT_H */
-- 
cgit v1.2.3


From 0efaa7e82f02fe69c05ad28e905f31fc86e6f08e Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 22 Aug 2014 10:18:45 -0400
Subject: locks: generic_delete_lease doesn't need a file_lock at all

Ensure that it's OK to pass in a NULL file_lock double pointer on
a F_UNLCK request and convert the vfs_setlease F_UNLCK callers to
do just that.

Finally, turn the BUG_ON in generic_setlease into a WARN_ON_ONCE
with an error return. That's a problem we can handle without
crashing the box if it occurs.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/locks.c                      | 34 ++++++++++++++--------------------
 fs/nfsd/nfs4state.c             |  2 +-
 include/trace/events/filelock.h | 14 +++++++-------
 3 files changed, 22 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index def1ac2e87bd..f79c74ef51ef 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1637,22 +1637,23 @@ out:
 	return error;
 }
 
-static int generic_delete_lease(struct file *filp, struct file_lock **flp)
+static int generic_delete_lease(struct file *filp)
 {
+	int error = -EAGAIN;
 	struct file_lock *fl, **before;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 
-	trace_generic_delete_lease(inode, *flp);
-
 	for (before = &inode->i_flock;
 			((fl = *before) != NULL) && IS_LEASE(fl);
 			before = &fl->fl_next) {
-		if (fl->fl_file != filp)
-			continue;
-		return (*flp)->fl_lmops->lm_change(before, F_UNLCK);
+		if (fl->fl_file == filp)
+			break;
 	}
-	return -EAGAIN;
+	trace_generic_delete_lease(inode, fl);
+	if (fl)
+		error = fl->fl_lmops->lm_change(before, F_UNLCK);
+	return error;
 }
 
 /**
@@ -1682,13 +1683,15 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 
 	time_out_leases(inode);
 
-	BUG_ON(!(*flp)->fl_lmops->lm_break);
-
 	switch (arg) {
 	case F_UNLCK:
-		return generic_delete_lease(filp, flp);
+		return generic_delete_lease(filp);
 	case F_RDLCK:
 	case F_WRLCK:
+		if (!(*flp)->fl_lmops->lm_break) {
+			WARN_ON_ONCE(1);
+			return -ENOLCK;
+		}
 		return generic_add_lease(filp, arg, flp);
 	default:
 		return -EINVAL;
@@ -1744,15 +1747,6 @@ int vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
 }
 EXPORT_SYMBOL_GPL(vfs_setlease);
 
-static int do_fcntl_delete_lease(struct file *filp)
-{
-	struct file_lock fl, *flp = &fl;
-
-	lease_init(filp, F_UNLCK, flp);
-
-	return vfs_setlease(filp, F_UNLCK, &flp);
-}
-
 static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 {
 	struct file_lock *fl, *ret;
@@ -1809,7 +1803,7 @@ out_unlock:
 int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
 	if (arg == F_UNLCK)
-		return do_fcntl_delete_lease(filp);
+		return vfs_setlease(filp, F_UNLCK, NULL);
 	return do_fcntl_add_lease(fd, filp, arg);
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 5bb4952faf5b..89d54e505155 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -690,7 +690,7 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 	spin_unlock(&fp->fi_lock);
 
 	if (filp) {
-		vfs_setlease(filp, F_UNLCK, &fl);
+		vfs_setlease(filp, F_UNLCK, NULL);
 		fput(filp);
 	}
 }
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index 59d11c22f076..a0d008070962 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -53,15 +53,15 @@ DECLARE_EVENT_CLASS(filelock_lease,
 	),
 
 	TP_fast_assign(
-		__entry->fl = fl;
+		__entry->fl = fl ? fl : NULL;
 		__entry->s_dev = inode->i_sb->s_dev;
 		__entry->i_ino = inode->i_ino;
-		__entry->fl_next = fl->fl_next;
-		__entry->fl_owner = fl->fl_owner;
-		__entry->fl_flags = fl->fl_flags;
-		__entry->fl_type = fl->fl_type;
-		__entry->fl_break_time = fl->fl_break_time;
-		__entry->fl_downgrade_time = fl->fl_downgrade_time;
+		__entry->fl_next = fl ? fl->fl_next : NULL;
+		__entry->fl_owner = fl ? fl->fl_owner : NULL;
+		__entry->fl_flags = fl ? fl->fl_flags : 0;
+		__entry->fl_type = fl ? fl->fl_type : 0;
+		__entry->fl_break_time = fl ? fl->fl_break_time : 0;
+		__entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0;
 	),
 
 	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_next=0x%p fl_owner=0x%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",
-- 
cgit v1.2.3


From e6f5c78930e409f3a6b37f5484313a416359ac7f Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 22 Aug 2014 10:40:25 -0400
Subject: locks: plumb a "priv" pointer into the setlease routines

In later patches, we're going to add a new lock_manager_operation to
finish setting up the lease while still holding the i_lock.  To do
this, we'll need to pass a little bit of info in the fcntl setlease
case (primarily an fasync structure). Plumb the extra pointer into
there in advance of that.

We declare this pointer as a void ** to make it clear that this is
private info, and that the caller isn't required to set this unless
the lm_setup specifically requires it.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/filesystems/Locking |  2 +-
 Documentation/filesystems/vfs.txt |  2 +-
 fs/cifs/cifsfs.c                  |  7 ++++---
 fs/libfs.c                        |  4 +++-
 fs/locks.c                        | 32 ++++++++++++++++++++------------
 fs/nfsd/nfs4state.c               |  4 ++--
 include/linux/fs.h                | 12 ++++++------
 7 files changed, 37 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index f1997e9da61f..3d92049ae71d 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -464,7 +464,7 @@ prototypes:
 			size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
 			size_t, unsigned int);
-	int (*setlease)(struct file *, long, struct file_lock **);
+	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *, int, loff_t, loff_t);
 };
 
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 61d65cc65c54..28ebd49f169f 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -826,7 +826,7 @@ struct file_operations {
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int);
-	int (*setlease)(struct file *, long arg, struct file_lock **);
+	int (*setlease)(struct file *, long arg, struct file_lock **, void **);
 	long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len);
 	int (*show_fdinfo)(struct seq_file *m, struct file *f);
 };
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index ac4f260155c8..85c70d5969ac 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -800,7 +800,8 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence)
 	return generic_file_llseek(file, offset, whence);
 }
 
-static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
+static int
+cifs_setlease(struct file *file, long arg, struct file_lock **lease, void **priv)
 {
 	/*
 	 * Note that this is called by vfs setlease with i_lock held to
@@ -815,7 +816,7 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
 	/* check if file is oplocked */
 	if (((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) ||
 	    ((arg == F_WRLCK) && CIFS_CACHE_WRITE(CIFS_I(inode))))
-		return generic_setlease(file, arg, lease);
+		return generic_setlease(file, arg, lease, priv);
 	else if (tlink_tcon(cfile->tlink)->local_lease &&
 		 !CIFS_CACHE_READ(CIFS_I(inode)))
 		/*
@@ -826,7 +827,7 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
 		 * knows that the file won't be changed on the server by anyone
 		 * else.
 		 */
-		return generic_setlease(file, arg, lease);
+		return generic_setlease(file, arg, lease, priv);
 	else
 		return -EAGAIN;
 }
diff --git a/fs/libfs.c b/fs/libfs.c
index 29012a303ef8..171d2846f2a3 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1081,12 +1081,14 @@ EXPORT_SYMBOL(alloc_anon_inode);
  * @filp: file pointer
  * @arg: type of lease to obtain
  * @flp: new lease supplied for insertion
+ * @priv: private data for lm_setup operation
  *
  * Generic helper for filesystems that do not wish to allow leases to be set.
  * All arguments are ignored and it just returns -EINVAL.
  */
 int
-simple_nosetlease(struct file *filp, long arg, struct file_lock **flp)
+simple_nosetlease(struct file *filp, long arg, struct file_lock **flp,
+		  void **priv)
 {
 	return -EINVAL;
 }
diff --git a/fs/locks.c b/fs/locks.c
index e16c2c61a44f..4fa269b0bdef 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1297,7 +1297,6 @@ int lease_modify(struct file_lock **before, int arg)
 	}
 	return 0;
 }
-
 EXPORT_SYMBOL(lease_modify);
 
 static bool past_time(unsigned long then)
@@ -1543,7 +1542,8 @@ check_conflicting_open(const struct dentry *dentry, const long arg)
 	return ret;
 }
 
-static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp)
+static int
+generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv)
 {
 	struct file_lock *fl, **before, **my_before = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
@@ -1630,11 +1630,14 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	smp_mb();
 	error = check_conflicting_open(dentry, arg);
 	if (error)
-		locks_unlink_lock(before);
+		goto out_unlink;
 out:
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
 	return error;
+out_unlink:
+	locks_unlink_lock(before);
+	goto out;
 }
 
 static int generic_delete_lease(struct file *filp)
@@ -1661,13 +1664,15 @@ static int generic_delete_lease(struct file *filp)
  *	@filp: file pointer
  *	@arg: type of lease to obtain
  *	@flp: input - file_lock to use, output - file_lock inserted
+ *	@priv: private data for lm_setup
  *
  *	The (input) flp->fl_lmops->lm_break function is required
  *	by break_lease().
  *
  *	Called with inode->i_lock held.
  */
-int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
+int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
+			void **priv)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
@@ -1692,19 +1697,20 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 			WARN_ON_ONCE(1);
 			return -ENOLCK;
 		}
-		return generic_add_lease(filp, arg, flp);
+		return generic_add_lease(filp, arg, flp, priv);
 	default:
 		return -EINVAL;
 	}
 }
 EXPORT_SYMBOL(generic_setlease);
 
-static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
+static int
+__vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
 {
 	if (filp->f_op->setlease)
-		return filp->f_op->setlease(filp, arg, lease);
+		return filp->f_op->setlease(filp, arg, lease, priv);
 	else
-		return generic_setlease(filp, arg, lease);
+		return generic_setlease(filp, arg, lease, priv);
 }
 
 /**
@@ -1712,6 +1718,7 @@ static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
  * @filp: file pointer
  * @arg: type of lease to obtain
  * @lease: file_lock to use when adding a lease
+ * @priv: private info for lm_setup when adding a lease
  *
  * Call this to establish a lease on the file. The "lease" argument is not
  * used for F_UNLCK requests and may be NULL. For commands that set or alter
@@ -1720,13 +1727,14 @@ static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
  * stack trace).
  */
 
-int vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
+int
+vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
 {
 	struct inode *inode = file_inode(filp);
 	int error;
 
 	spin_lock(&inode->i_lock);
-	error = __vfs_setlease(filp, arg, lease);
+	error = __vfs_setlease(filp, arg, lease, priv);
 	spin_unlock(&inode->i_lock);
 
 	return error;
@@ -1751,7 +1759,7 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 	}
 	ret = fl;
 	spin_lock(&inode->i_lock);
-	error = __vfs_setlease(filp, arg, &ret);
+	error = __vfs_setlease(filp, arg, &ret, NULL);
 	if (error)
 		goto out_unlock;
 	if (ret == fl)
@@ -1789,7 +1797,7 @@ out_unlock:
 int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
 	if (arg == F_UNLCK)
-		return vfs_setlease(filp, F_UNLCK, NULL);
+		return vfs_setlease(filp, F_UNLCK, NULL, NULL);
 	return do_fcntl_add_lease(fd, filp, arg);
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 188cd68aefb6..7c803db2a027 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -686,7 +686,7 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 	spin_unlock(&fp->fi_lock);
 
 	if (filp) {
-		vfs_setlease(filp, F_UNLCK, NULL);
+		vfs_setlease(filp, F_UNLCK, NULL, NULL);
 		fput(filp);
 	}
 }
@@ -3792,7 +3792,7 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	}
 	fl->fl_file = filp;
 	ret = fl;
-	status = vfs_setlease(filp, fl->fl_type, &ret);
+	status = vfs_setlease(filp, fl->fl_type, &fl, NULL);
 	if (status) {
 		locks_free_lock(fl);
 		goto out_fput;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96528f73dda4..f1870eb67b02 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -982,8 +982,8 @@ extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
 extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
 extern void lease_get_mtime(struct inode *, struct timespec *time);
-extern int generic_setlease(struct file *, long, struct file_lock **);
-extern int vfs_setlease(struct file *, long, struct file_lock **);
+extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
+extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
 extern int lease_modify(struct file_lock **, int);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
@@ -1100,13 +1100,13 @@ static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
 }
 
 static inline int generic_setlease(struct file *filp, long arg,
-				    struct file_lock **flp)
+				    struct file_lock **flp, void **priv)
 {
 	return -EINVAL;
 }
 
 static inline int vfs_setlease(struct file *filp, long arg,
-			       struct file_lock **lease)
+			       struct file_lock **lease, void **priv)
 {
 	return -EINVAL;
 }
@@ -1494,7 +1494,7 @@ struct file_operations {
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
-	int (*setlease)(struct file *, long, struct file_lock **);
+	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	int (*show_fdinfo)(struct seq_file *m, struct file *f);
@@ -2599,7 +2599,7 @@ extern int simple_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata);
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
-extern int simple_nosetlease(struct file *, long, struct file_lock **);
+extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
 extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
-- 
cgit v1.2.3


From 1c7dd2ff430fa14b45c9def54468e3a25ab8342b Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 22 Aug 2014 10:55:47 -0400
Subject: locks: define a lm_setup handler for leases

...and move the fasync setup into it for fcntl lease calls. At the same
time, change the semantics of how the file_lock double-pointer is
handled. Up until now, on a successful lease return you got a pointer to
the lock on the list. This is bad, since that pointer can no longer be
relied on as valid once the inode->i_lock has been released.

Change the code to instead just zero out the pointer if the lease we
passed in ended up being used. Then the callers can just check to see
if it's NULL after the call and free it if it isn't.

The priv argument has the same semantics. The lm_setup function can
zero the pointer out to signal to the caller that it should not be
freed after the function returns.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/locks.c          | 92 ++++++++++++++++++++++++++++-------------------------
 fs/nfsd/nfs4state.c |  6 ++--
 include/linux/fs.h  |  1 +
 3 files changed, 51 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index 4fa269b0bdef..a237ba632e8d 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -432,9 +432,27 @@ static void lease_break_callback(struct file_lock *fl)
 	kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
 }
 
+static void
+lease_setup(struct file_lock *fl, void **priv)
+{
+	struct file *filp = fl->fl_file;
+	struct fasync_struct *fa = *priv;
+
+	/*
+	 * fasync_insert_entry() returns the old entry if any. If there was no
+	 * old entry, then it used "priv" and inserted it into the fasync list.
+	 * Clear the pointer to indicate that it shouldn't be freed.
+	 */
+	if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa))
+		*priv = NULL;
+
+	__f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
+}
+
 static const struct lock_manager_operations lease_manager_ops = {
 	.lm_break = lease_break_callback,
 	.lm_change = lease_modify,
+	.lm_setup = lease_setup,
 };
 
 /*
@@ -1607,10 +1625,11 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	}
 
 	if (my_before != NULL) {
+		lease = *my_before;
 		error = lease->fl_lmops->lm_change(my_before, arg);
-		if (!error)
-			*flp = *my_before;
-		goto out;
+		if (error)
+			goto out;
+		goto out_setup;
 	}
 
 	error = -EINVAL;
@@ -1631,9 +1650,15 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	error = check_conflicting_open(dentry, arg);
 	if (error)
 		goto out_unlink;
+
+out_setup:
+	if (lease->fl_lmops->lm_setup)
+		lease->fl_lmops->lm_setup(lease, priv);
 out:
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
+	if (!error && !my_before)
+		*flp = NULL;
 	return error;
 out_unlink:
 	locks_unlink_lock(before);
@@ -1661,10 +1686,11 @@ static int generic_delete_lease(struct file *filp)
 
 /**
  *	generic_setlease	-	sets a lease on an open file
- *	@filp: file pointer
- *	@arg: type of lease to obtain
- *	@flp: input - file_lock to use, output - file_lock inserted
- *	@priv: private data for lm_setup
+ *	@filp:	file pointer
+ *	@arg:	type of lease to obtain
+ *	@flp:	input - file_lock to use, output - file_lock inserted
+ *	@priv:	private data for lm_setup (may be NULL if lm_setup
+ *		doesn't require it)
  *
  *	The (input) flp->fl_lmops->lm_break function is required
  *	by break_lease().
@@ -1704,29 +1730,23 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
 }
 EXPORT_SYMBOL(generic_setlease);
 
-static int
-__vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
-{
-	if (filp->f_op->setlease)
-		return filp->f_op->setlease(filp, arg, lease, priv);
-	else
-		return generic_setlease(filp, arg, lease, priv);
-}
-
 /**
  * vfs_setlease        -       sets a lease on an open file
- * @filp: file pointer
- * @arg: type of lease to obtain
- * @lease: file_lock to use when adding a lease
- * @priv: private info for lm_setup when adding a lease
+ * @filp:	file pointer
+ * @arg:	type of lease to obtain
+ * @lease:	file_lock to use when adding a lease
+ * @priv:	private info for lm_setup when adding a lease (may be
+ * 		NULL if lm_setup doesn't require it)
  *
  * Call this to establish a lease on the file. The "lease" argument is not
  * used for F_UNLCK requests and may be NULL. For commands that set or alter
  * an existing lease, the (*lease)->fl_lmops->lm_break operation must be set;
  * if not, this function will return -ENOLCK (and generate a scary-looking
  * stack trace).
+ *
+ * The "priv" pointer is passed directly to the lm_setup function as-is. It
+ * may be NULL if the lm_setup operation doesn't require it.
  */
-
 int
 vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
 {
@@ -1734,17 +1754,18 @@ vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
 	int error;
 
 	spin_lock(&inode->i_lock);
-	error = __vfs_setlease(filp, arg, lease, priv);
+	if (filp->f_op->setlease)
+		error = filp->f_op->setlease(filp, arg, lease, priv);
+	else
+		error = generic_setlease(filp, arg, lease, priv);
 	spin_unlock(&inode->i_lock);
-
 	return error;
 }
 EXPORT_SYMBOL_GPL(vfs_setlease);
 
 static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 {
-	struct file_lock *fl, *ret;
-	struct inode *inode = file_inode(filp);
+	struct file_lock *fl;
 	struct fasync_struct *new;
 	int error;
 
@@ -1757,26 +1778,9 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 		locks_free_lock(fl);
 		return -ENOMEM;
 	}
-	ret = fl;
-	spin_lock(&inode->i_lock);
-	error = __vfs_setlease(filp, arg, &ret, NULL);
-	if (error)
-		goto out_unlock;
-	if (ret == fl)
-		fl = NULL;
+	new->fa_fd = fd;
 
-	/*
-	 * fasync_insert_entry() returns the old entry if any.
-	 * If there was no old entry, then it used 'new' and
-	 * inserted it into the fasync list. Clear new so that
-	 * we don't release it here.
-	 */
-	if (!fasync_insert_entry(fd, filp, &ret->fl_fasync, new))
-		new = NULL;
-
-	__f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
-out_unlock:
-	spin_unlock(&inode->i_lock);
+	error = vfs_setlease(filp, arg, &fl, (void **)&new);
 	if (fl)
 		locks_free_lock(fl);
 	if (new)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7c803db2a027..5349528136e2 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3793,12 +3793,10 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	fl->fl_file = filp;
 	ret = fl;
 	status = vfs_setlease(filp, fl->fl_type, &fl, NULL);
-	if (status) {
+	if (fl)
 		locks_free_lock(fl);
+	if (status)
 		goto out_fput;
-	}
-	if (ret != fl)
-		locks_free_lock(fl);
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
 	/* Did the lease get broken before we took the lock? */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f1870eb67b02..9a6d56154dd5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -874,6 +874,7 @@ struct lock_manager_operations {
 	int (*lm_grant)(struct file_lock *, int);
 	void (*lm_break)(struct file_lock *);
 	int (*lm_change)(struct file_lock **, int);
+	void (*lm_setup)(struct file_lock *, void **);
 };
 
 struct lock_manager {
-- 
cgit v1.2.3


From c45198eda2794bb72601c9f96266d8b95db66dd5 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Mon, 1 Sep 2014 07:12:07 -0400
Subject: locks: move freeing of leases outside of i_lock

There was only one place where we still could free a file_lock while
holding the i_lock -- lease_modify. Add a new list_head argument to the
lm_change operation, pass in a private list when calling it, and fix
those callers to dispose of the list once the lock has been dropped.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/filesystems/Locking |  3 +--
 fs/locks.c                        | 34 ++++++++++++++++++++++------------
 fs/nfsd/nfs4state.c               |  6 +++---
 include/linux/fs.h                |  7 ++++---
 4 files changed, 30 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 4af288e38f13..94d93b1f8b53 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -469,8 +469,7 @@ prototypes:
 };
 
 locking rules:
-	All may block except for ->setlease.
-	No VFS locks held on entry except for ->setlease.
+	All may block.
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you
diff --git a/fs/locks.c b/fs/locks.c
index eb463257f867..c0f789dfa655 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1292,7 +1292,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg)
 }
 
 /* We already had a lease on this file; just change its type */
-int lease_modify(struct file_lock **before, int arg)
+int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
 {
 	struct file_lock *fl = *before;
 	int error = assign_type(fl, arg);
@@ -1311,7 +1311,7 @@ int lease_modify(struct file_lock **before, int arg)
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
 			fl->fl_fasync = NULL;
 		}
-		locks_delete_lock(before, NULL);
+		locks_delete_lock(before, dispose);
 	}
 	return 0;
 }
@@ -1325,7 +1325,7 @@ static bool past_time(unsigned long then)
 	return time_after(jiffies, then);
 }
 
-static void time_out_leases(struct inode *inode)
+static void time_out_leases(struct inode *inode, struct list_head *dispose)
 {
 	struct file_lock **before;
 	struct file_lock *fl;
@@ -1336,9 +1336,9 @@ static void time_out_leases(struct inode *inode)
 	while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) {
 		trace_time_out_leases(inode, fl);
 		if (past_time(fl->fl_downgrade_time))
-			lease_modify(before, F_RDLCK);
+			lease_modify(before, F_RDLCK, dispose);
 		if (past_time(fl->fl_break_time))
-			lease_modify(before, F_UNLCK);
+			lease_modify(before, F_UNLCK, dispose);
 		if (fl == *before)	/* lease_modify may have freed fl */
 			before = &fl->fl_next;
 	}
@@ -1373,6 +1373,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 	int i_have_this_lease = 0;
 	bool lease_conflict = false;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
+	LIST_HEAD(dispose);
 
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 	if (IS_ERR(new_fl))
@@ -1381,7 +1382,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 
 	spin_lock(&inode->i_lock);
 
-	time_out_leases(inode);
+	time_out_leases(inode, &dispose);
 
 	flock = inode->i_flock;
 	if ((flock == NULL) || !IS_LEASE(flock))
@@ -1436,6 +1437,7 @@ restart:
 	locks_insert_block(flock, new_fl);
 	trace_break_lease_block(inode, new_fl);
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
 						!new_fl->fl_next, break_time);
 	spin_lock(&inode->i_lock);
@@ -1443,7 +1445,7 @@ restart:
 	locks_delete_block(new_fl);
 	if (error >= 0) {
 		if (error == 0)
-			time_out_leases(inode);
+			time_out_leases(inode, &dispose);
 		/*
 		 * Wait for the next conflicting lease that has not been
 		 * broken yet
@@ -1458,6 +1460,7 @@ restart:
 
 out:
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	locks_free_lock(new_fl);
 	return error;
 }
@@ -1522,9 +1525,10 @@ int fcntl_getlease(struct file *filp)
 	struct file_lock *fl;
 	struct inode *inode = file_inode(filp);
 	int type = F_UNLCK;
+	LIST_HEAD(dispose);
 
 	spin_lock(&inode->i_lock);
-	time_out_leases(file_inode(filp));
+	time_out_leases(file_inode(filp), &dispose);
 	for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl);
 			fl = fl->fl_next) {
 		if (fl->fl_file == filp) {
@@ -1533,6 +1537,7 @@ int fcntl_getlease(struct file *filp)
 		}
 	}
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	return type;
 }
 
@@ -1570,6 +1575,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	struct inode *inode = dentry->d_inode;
 	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
+	LIST_HEAD(dispose);
 
 	lease = *flp;
 	trace_generic_add_lease(inode, lease);
@@ -1593,7 +1599,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	}
 
 	spin_lock(&inode->i_lock);
-	time_out_leases(inode);
+	time_out_leases(inode, &dispose);
 	error = check_conflicting_open(dentry, arg);
 	if (error)
 		goto out;
@@ -1630,7 +1636,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 
 	if (my_before != NULL) {
 		lease = *my_before;
-		error = lease->fl_lmops->lm_change(my_before, arg);
+		error = lease->fl_lmops->lm_change(my_before, arg, &dispose);
 		if (error)
 			goto out;
 		goto out_setup;
@@ -1660,6 +1666,7 @@ out_setup:
 		lease->fl_lmops->lm_setup(lease, priv);
 out:
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
 	if (!error && !my_before)
@@ -1676,8 +1683,10 @@ static int generic_delete_lease(struct file *filp)
 	struct file_lock *fl, **before;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	LIST_HEAD(dispose);
 
 	spin_lock(&inode->i_lock);
+	time_out_leases(inode, &dispose);
 	for (before = &inode->i_flock;
 			((fl = *before) != NULL) && IS_LEASE(fl);
 			before = &fl->fl_next) {
@@ -1686,8 +1695,9 @@ static int generic_delete_lease(struct file *filp)
 	}
 	trace_generic_delete_lease(inode, fl);
 	if (fl)
-		error = fl->fl_lmops->lm_change(before, F_UNLCK);
+		error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose);
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	return error;
 }
 
@@ -2372,7 +2382,7 @@ void locks_remove_file(struct file *filp)
 	while ((fl = *before) != NULL) {
 		if (fl->fl_file == filp) {
 			if (IS_LEASE(fl)) {
-				lease_modify(before, F_UNLCK);
+				lease_modify(before, F_UNLCK, &dispose);
 				continue;
 			}
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 5349528136e2..604ab6decd28 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3427,11 +3427,11 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
 	spin_unlock(&fp->fi_lock);
 }
 
-static
-int nfsd_change_deleg_cb(struct file_lock **onlist, int arg)
+static int
+nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose)
 {
 	if (arg & F_UNLCK)
-		return lease_modify(onlist, arg);
+		return lease_modify(onlist, arg, dispose);
 	else
 		return -EAGAIN;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9a6d56154dd5..f419f718e447 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -873,7 +873,7 @@ struct lock_manager_operations {
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
 	int (*lm_grant)(struct file_lock *, int);
 	void (*lm_break)(struct file_lock *);
-	int (*lm_change)(struct file_lock **, int);
+	int (*lm_change)(struct file_lock **, int, struct list_head *);
 	void (*lm_setup)(struct file_lock *, void **);
 };
 
@@ -985,7 +985,7 @@ extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int t
 extern void lease_get_mtime(struct inode *, struct timespec *time);
 extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
 extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
-extern int lease_modify(struct file_lock **, int);
+extern int lease_modify(struct file_lock **, int, struct list_head *);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
 			      struct flock __user *user)
@@ -1112,7 +1112,8 @@ static inline int vfs_setlease(struct file *filp, long arg,
 	return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock **before, int arg)
+static inline int lease_modify(struct file_lock **before, int arg,
+			       struct list_head *dispose)
 {
 	return -EINVAL;
 }
-- 
cgit v1.2.3


From 4d01b7f5e7576858b71cbaa72b541e17a229cb91 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Mon, 1 Sep 2014 15:06:54 -0400
Subject: locks: give lm_break a return value

Christoph suggests:

   "Add a return value to lm_break so that the lock manager can tell the
    core code "you can delete this lease right now".  That gets rid of
    the games with the timeout which require all kinds of race avoidance
    code in the users."

Do that here and have the nfsd lease break routine use it when it detects
that there was a race between setting up the lease and it being broken.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/locks.c          | 17 +++++++++++++----
 fs/nfsd/nfs4state.c | 17 +++++++++--------
 include/linux/fs.h  |  2 +-
 3 files changed, 23 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index 7d627ac0ed87..aed4a957d232 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -427,9 +427,11 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
 }
 
 /* default lease lock manager operations */
-static void lease_break_callback(struct file_lock *fl)
+static bool
+lease_break_callback(struct file_lock *fl)
 {
 	kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
+	return false;
 }
 
 static void
@@ -1382,7 +1384,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
 	struct file_lock *new_fl;
-	struct file_lock *fl;
+	struct file_lock *fl, **before;
 	unsigned long break_time;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 	LIST_HEAD(dispose);
@@ -1406,7 +1408,9 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			break_time++;	/* so that 0 means no break time */
 	}
 
-	for (fl = inode->i_flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+	for (before = &inode->i_flock;
+			((fl = *before) != NULL) && IS_LEASE(fl);
+			before = &fl->fl_next) {
 		if (!leases_conflict(fl, new_fl))
 			continue;
 		if (want_write) {
@@ -1420,9 +1424,14 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			fl->fl_flags |= FL_DOWNGRADE_PENDING;
 			fl->fl_downgrade_time = break_time;
 		}
-		fl->fl_lmops->lm_break(fl);
+		if (fl->fl_lmops->lm_break(fl))
+			locks_delete_lock(before, &dispose);
 	}
 
+	fl = inode->i_flock;
+	if (!fl || !IS_LEASE(fl))
+		goto out;
+
 	if (mode & O_NONBLOCK) {
 		trace_break_lease_noblock(inode, new_fl);
 		error = -EWOULDBLOCK;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 604ab6decd28..d1b851548b7a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3391,18 +3391,20 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 }
 
 /* Called from break_lease() with i_lock held. */
-static void nfsd_break_deleg_cb(struct file_lock *fl)
+static bool
+nfsd_break_deleg_cb(struct file_lock *fl)
 {
+	bool ret = false;
 	struct nfs4_file *fp = (struct nfs4_file *)fl->fl_owner;
 	struct nfs4_delegation *dp;
 
 	if (!fp) {
 		WARN(1, "(%p)->fl_owner NULL\n", fl);
-		return;
+		return ret;
 	}
 	if (fp->fi_had_conflict) {
 		WARN(1, "duplicate break on %p\n", fp);
-		return;
+		return ret;
 	}
 	/*
 	 * We don't want the locks code to timeout the lease for us;
@@ -3414,17 +3416,16 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
 	spin_lock(&fp->fi_lock);
 	fp->fi_had_conflict = true;
 	/*
-	 * If there are no delegations on the list, then we can't count on this
-	 * lease ever being cleaned up. Set the fl_break_time to jiffies so that
-	 * time_out_leases will do it ASAP. The fact that fi_had_conflict is now
-	 * true should keep any new delegations from being hashed.
+	 * If there are no delegations on the list, then return true
+	 * so that the lease code will go ahead and delete it.
 	 */
 	if (list_empty(&fp->fi_delegations))
-		fl->fl_break_time = jiffies;
+		ret = true;
 	else
 		list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
 			nfsd_break_one_deleg(dp);
 	spin_unlock(&fp->fi_lock);
+	return ret;
 }
 
 static int
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f419f718e447..ed4e1897099c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -872,7 +872,7 @@ struct lock_manager_operations {
 	void (*lm_put_owner)(struct file_lock *);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
 	int (*lm_grant)(struct file_lock *, int);
-	void (*lm_break)(struct file_lock *);
+	bool (*lm_break)(struct file_lock *);
 	int (*lm_change)(struct file_lock **, int, struct list_head *);
 	void (*lm_setup)(struct file_lock *, void **);
 };
-- 
cgit v1.2.3


From 7ca76311fe6c397e9f332e5e6c79e3310d5ee98a Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Mon, 1 Sep 2014 19:04:48 -0400
Subject: locks: set fl_owner for leases to filp instead of current->files

Like flock locks, leases are owned by the file description. Now that the
i_have_this_lease check in __break_lease is gone, we don't actually use
the fl_owner for leases for anything. So, it's now safe to set this more
appropriately to the same value as the fl_file.

While we're at it, fix up the comments over the fl_owner_t definition
since they're rather out of date.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
 fs/locks.c         | 2 +-
 include/linux/fs.h | 8 +-------
 2 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index aed4a957d232..314135ad820b 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -465,7 +465,7 @@ static int lease_init(struct file *filp, long type, struct file_lock *fl)
 	if (assign_type(fl, type) != 0)
 		return -EINVAL;
 
-	fl->fl_owner = current->files;
+	fl->fl_owner = filp;
 	fl->fl_pid = current->tgid;
 
 	fl->fl_file = filp;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed4e1897099c..bb9484ae1eef 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -851,13 +851,7 @@ static inline struct file *get_file(struct file *f)
  */
 #define FILE_LOCK_DEFERRED 1
 
-/*
- * The POSIX file lock owner is determined by
- * the "struct files_struct" in the thread group
- * (or NULL for no owner - BSD locks).
- *
- * Lockd stuffs a "host" pointer into this.
- */
+/* legacy typedef, should eventually be removed */
 typedef void *fl_owner_t;
 
 struct file_lock_operations {
-- 
cgit v1.2.3


From 1b2b32dcdb3df28dd103033c73cac2417fa05845 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Wed, 24 Sep 2014 08:38:44 -0400
Subject: locks: fix fcntl_setlease/getlease return when !CONFIG_FILE_LOCKING

Currently they both just return 0. Fix them to return more appropriate
values instead.

For better or worse, most places in the kernel return -EINVAL when
leases aren't available. -ENOLCK would probably have been better, but
let's follow suit here in the case of F_SETLEASE.

In the F_GETLEASE case, just return F_UNLCK since we know that no
lease will have been set.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/fs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index bb9484ae1eef..2023306c620e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1008,12 +1008,12 @@ static inline int fcntl_setlk64(unsigned int fd, struct file *file,
 #endif
 static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
-	return 0;
+	return -EINVAL;
 }
 
 static inline int fcntl_getlease(struct file *filp)
 {
-	return 0;
+	return F_UNLCK;
 }
 
 static inline void locks_init_lock(struct file_lock *fl)
-- 
cgit v1.2.3


From f0d1f04f0a2f662b6b617e24d115fddcf6ef8723 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 7 Oct 2014 19:02:11 +0200
Subject: netfilter: fix wrong arithmetics regarding NFT_REJECT_ICMPX_MAX

NFT_REJECT_ICMPX_MAX should be __NFT_REJECT_ICMPX_MAX - 1.

nft_reject_icmp_code() and nft_reject_icmpv6_code() are called from the
packet path, so BUG_ON in case we try to access an unknown abstracted
ICMP code. This should not happen since we already validate this from
nft_reject_{inet,bridge}_init().

Fixes: 51b0a5d ("netfilter: nft_reject: introduce icmp code abstraction for inet and bridge")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  2 +-
 net/netfilter/nft_reject.c               | 10 ++++------
 2 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index c26df6787fb0..f31fe7b660a5 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -774,7 +774,7 @@ enum nft_reject_inet_code {
 	NFT_REJECT_ICMPX_ADMIN_PROHIBITED,
 	__NFT_REJECT_ICMPX_MAX
 };
-#define NFT_REJECT_ICMPX_MAX	(__NFT_REJECT_ICMPX_MAX + 1)
+#define NFT_REJECT_ICMPX_MAX	(__NFT_REJECT_ICMPX_MAX - 1)
 
 /**
  * enum nft_reject_attributes - nf_tables reject expression netlink attributes
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index ec8a456092a7..57d3e1af5630 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -72,7 +72,7 @@ nla_put_failure:
 }
 EXPORT_SYMBOL_GPL(nft_reject_dump);
 
-static u8 icmp_code_v4[NFT_REJECT_ICMPX_MAX] = {
+static u8 icmp_code_v4[NFT_REJECT_ICMPX_MAX + 1] = {
 	[NFT_REJECT_ICMPX_NO_ROUTE]		= ICMP_NET_UNREACH,
 	[NFT_REJECT_ICMPX_PORT_UNREACH]		= ICMP_PORT_UNREACH,
 	[NFT_REJECT_ICMPX_HOST_UNREACH]		= ICMP_HOST_UNREACH,
@@ -81,8 +81,7 @@ static u8 icmp_code_v4[NFT_REJECT_ICMPX_MAX] = {
 
 int nft_reject_icmp_code(u8 code)
 {
-	if (code > NFT_REJECT_ICMPX_MAX)
-		return -EINVAL;
+	BUG_ON(code > NFT_REJECT_ICMPX_MAX);
 
 	return icmp_code_v4[code];
 }
@@ -90,7 +89,7 @@ int nft_reject_icmp_code(u8 code)
 EXPORT_SYMBOL_GPL(nft_reject_icmp_code);
 
 
-static u8 icmp_code_v6[NFT_REJECT_ICMPX_MAX] = {
+static u8 icmp_code_v6[NFT_REJECT_ICMPX_MAX + 1] = {
 	[NFT_REJECT_ICMPX_NO_ROUTE]		= ICMPV6_NOROUTE,
 	[NFT_REJECT_ICMPX_PORT_UNREACH]		= ICMPV6_PORT_UNREACH,
 	[NFT_REJECT_ICMPX_HOST_UNREACH]		= ICMPV6_ADDR_UNREACH,
@@ -99,8 +98,7 @@ static u8 icmp_code_v6[NFT_REJECT_ICMPX_MAX] = {
 
 int nft_reject_icmpv6_code(u8 code)
 {
-	if (code > NFT_REJECT_ICMPX_MAX)
-		return -EINVAL;
+	BUG_ON(code > NFT_REJECT_ICMPX_MAX);
 
 	return icmp_code_v6[code];
 }
-- 
cgit v1.2.3


From 1cd258d7faccb330145f08d838608b2c6ad41604 Mon Sep 17 00:00:00 2001
From: Ian Munsie <imunsie@au1.ibm.com>
Date: Wed, 8 Oct 2014 19:54:56 +1100
Subject: cxl: Add new header for call backs and structs

This new header adds callbacks and structs needed by the rest of the kernel to
hook into the cxl infrastructure.

This adds the cxl_ctx_in_use() function for use in the mm code to see if any
cxl contexts are currently in use. This is used by the tlbie() to determine if
it can do local TLB invalidations or not. This also adds get/put calls for the
cxl driver module to refcount the active cxl contexts.

cxl_ctx_get/put/in_use are static inlined here as they are called in tlbie
which we want to be fast (mpe's suggestion).

Empty functions are provided when CONFIG_CXL_BASE is not enabled.

Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 include/misc/cxl.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 include/misc/cxl.h

(limited to 'include')

diff --git a/include/misc/cxl.h b/include/misc/cxl.h
new file mode 100644
index 000000000000..975cc7861f18
--- /dev/null
+++ b/include/misc/cxl.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _MISC_CXL_H
+#define _MISC_CXL_H
+
+#ifdef CONFIG_CXL_BASE
+
+#define CXL_IRQ_RANGES 4
+
+struct cxl_irq_ranges {
+	irq_hw_number_t offset[CXL_IRQ_RANGES];
+	irq_hw_number_t range[CXL_IRQ_RANGES];
+};
+
+extern atomic_t cxl_use_count;
+
+static inline bool cxl_ctx_in_use(void)
+{
+       return (atomic_read(&cxl_use_count) != 0);
+}
+
+static inline void cxl_ctx_get(void)
+{
+       atomic_inc(&cxl_use_count);
+}
+
+static inline void cxl_ctx_put(void)
+{
+       atomic_dec(&cxl_use_count);
+}
+
+void cxl_slbia(struct mm_struct *mm);
+
+#else /* CONFIG_CXL_BASE */
+
+static inline bool cxl_ctx_in_use(void) { return false; }
+static inline void cxl_slbia(struct mm_struct *mm) {}
+
+#endif /* CONFIG_CXL_BASE */
+
+#endif
-- 
cgit v1.2.3


From 66b43081c0bde3171208a7cb52f5807dce4a79e4 Mon Sep 17 00:00:00 2001
From: Ian Munsie <imunsie@au1.ibm.com>
Date: Wed, 8 Oct 2014 19:55:03 +1100
Subject: cxl: Add userspace header file

This adds a header file for use by userspace programs wanting to interact with
the kernel cxl driver.  It defines structs and magic numbers required for
userspace to interact with devices in /dev/cxl/afuM.N.

Further documentation on this interface is added in a subsequent patch in
Documentation/powerpc/cxl.txt.

It also adds this new userspace header file to Kbuild so it's exported when
doing "make headers_installs".

Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 include/uapi/Kbuild      |  1 +
 include/uapi/misc/Kbuild |  2 ++
 include/uapi/misc/cxl.h  | 87 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 90 insertions(+)
 create mode 100644 include/uapi/misc/Kbuild
 create mode 100644 include/uapi/misc/cxl.h

(limited to 'include')

diff --git a/include/uapi/Kbuild b/include/uapi/Kbuild
index 81d2106287fe..245aa6e05e6a 100644
--- a/include/uapi/Kbuild
+++ b/include/uapi/Kbuild
@@ -12,3 +12,4 @@ header-y += video/
 header-y += drm/
 header-y += xen/
 header-y += scsi/
+header-y += misc/
diff --git a/include/uapi/misc/Kbuild b/include/uapi/misc/Kbuild
new file mode 100644
index 000000000000..e96cae7d58c9
--- /dev/null
+++ b/include/uapi/misc/Kbuild
@@ -0,0 +1,2 @@
+# misc Header export list
+header-y += cxl.h
diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h
new file mode 100644
index 000000000000..c232be6ae21f
--- /dev/null
+++ b/include/uapi/misc/cxl.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_MISC_CXL_H
+#define _UAPI_MISC_CXL_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/* Structs for IOCTLS for userspace to talk to the kernel */
+struct cxl_ioctl_start_work {
+	__u64 flags;
+	__u64 work_element_descriptor;
+	__u64 amr;
+	__s16 num_interrupts;
+	__s16 reserved1;
+	__s32 reserved2;
+	__u64 reserved3;
+	__u64 reserved4;
+	__u64 reserved5;
+	__u64 reserved6;
+};
+#define CXL_START_WORK_AMR		0x0000000000000001ULL
+#define CXL_START_WORK_NUM_IRQS		0x0000000000000002ULL
+#define CXL_START_WORK_ALL		(CXL_START_WORK_AMR |\
+					 CXL_START_WORK_NUM_IRQS)
+
+/* IOCTL numbers */
+#define CXL_MAGIC 0xCA
+#define CXL_IOCTL_START_WORK		_IOW(CXL_MAGIC, 0x00, struct cxl_ioctl_start_work)
+#define CXL_IOCTL_GET_PROCESS_ELEMENT	_IOR(CXL_MAGIC, 0x01, __u32)
+
+/* Events from read() */
+#define CXL_READ_MIN_SIZE 0x1000 /* 4K */
+
+enum cxl_event_type {
+	CXL_EVENT_RESERVED      = 0,
+	CXL_EVENT_AFU_INTERRUPT = 1,
+	CXL_EVENT_DATA_STORAGE  = 2,
+	CXL_EVENT_AFU_ERROR     = 3,
+};
+
+struct cxl_event_header {
+	__u16 type;
+	__u16 size;
+	__u16 process_element;
+	__u16 reserved1;
+};
+
+struct cxl_event_afu_interrupt {
+	__u16 flags;
+	__u16 irq; /* Raised AFU interrupt number */
+	__u32 reserved1;
+};
+
+struct cxl_event_data_storage {
+	__u16 flags;
+	__u16 reserved1;
+	__u32 reserved2;
+	__u64 addr;
+	__u64 dsisr;
+	__u64 reserved3;
+};
+
+struct cxl_event_afu_error {
+	__u16 flags;
+	__u16 reserved1;
+	__u32 reserved2;
+	__u64 error;
+};
+
+struct cxl_event {
+	struct cxl_event_header header;
+	union {
+		struct cxl_event_afu_interrupt irq;
+		struct cxl_event_data_storage fault;
+		struct cxl_event_afu_error afu_error;
+	};
+};
+
+#endif /* _UAPI_MISC_CXL_H */
-- 
cgit v1.2.3


From a9282d01cf357379ce29103cec5e7651a53c634d Mon Sep 17 00:00:00 2001
From: Ian Munsie <imunsie@au1.ibm.com>
Date: Wed, 8 Oct 2014 19:55:05 +1100
Subject: cxl: Add documentation for userspace APIs

This documentation gives an overview of the hardware architecture, userspace
APIs via /dev/cxl/afuM.N and the syfs files. It also adds a MAINTAINERS file
entry for cxl.

Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 Documentation/ABI/testing/sysfs-class-cxl | 129 ++++++++++
 Documentation/ioctl/ioctl-number.txt      |   1 +
 Documentation/powerpc/00-INDEX            |   2 +
 Documentation/powerpc/cxl.txt             | 379 ++++++++++++++++++++++++++++++
 MAINTAINERS                               |  12 +
 include/uapi/misc/cxl.h                   |   7 +-
 6 files changed, 527 insertions(+), 3 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-class-cxl
 create mode 100644 Documentation/powerpc/cxl.txt

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
new file mode 100644
index 000000000000..554405ec1955
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -0,0 +1,129 @@
+Slave contexts (eg. /sys/class/cxl/afu0.0s):
+
+What:           /sys/class/cxl/<afu>/irqs_max
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read/write
+                Decimal value of maximum number of interrupts that can be
+                requested by userspace.  The default on probe is the maximum
+                that hardware can support (eg. 2037). Write values will limit
+                userspace applications to that many userspace interrupts. Must
+                be >= irqs_min.
+
+What:           /sys/class/cxl/<afu>/irqs_min
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the minimum number of interrupts that
+                userspace must request on a CXL_START_WORK ioctl. Userspace may
+                omit the num_interrupts field in the START_WORK IOCTL to get
+                this minimum automatically.
+
+What:           /sys/class/cxl/<afu>/mmio_size
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the size of the MMIO space that may be mmaped
+                by userspace.
+
+What:           /sys/class/cxl/<afu>/modes_supported
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                List of the modes this AFU supports. One per line.
+                Valid entries are: "dedicated_process" and "afu_directed"
+
+What:           /sys/class/cxl/<afu>/mode
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read/write
+                The current mode the AFU is using. Will be one of the modes
+                given in modes_supported. Writing will change the mode
+                provided that no user contexts are attached.
+
+
+What:           /sys/class/cxl/<afu>/prefault_mode
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read/write
+                Set the mode for prefaulting in segments into the segment table
+                when performing the START_WORK ioctl. Possible values:
+                        none: No prefaulting (default)
+                        work_element_descriptor: Treat the work element
+                                 descriptor as an effective address and
+                                 prefault what it points to.
+                        all: all segments process calling START_WORK maps.
+
+What:           /sys/class/cxl/<afu>/reset
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    write only
+                Writing 1 here will reset the AFU provided there are not
+                contexts active on the AFU.
+
+What:           /sys/class/cxl/<afu>/api_version
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the current version of the kernel/user API.
+
+What:           /sys/class/cxl/<afu>/api_version_com
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the the lowest version of the userspace API
+                this this kernel supports.
+
+
+
+Master contexts (eg. /sys/class/cxl/afu0.0m)
+
+What:           /sys/class/cxl/<afu>m/mmio_size
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the size of the MMIO space that may be mmaped
+                by userspace. This includes all slave contexts space also.
+
+What:           /sys/class/cxl/<afu>m/pp_mmio_len
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the Per Process MMIO space length.
+
+What:           /sys/class/cxl/<afu>m/pp_mmio_off
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the Per Process MMIO space offset.
+
+
+Card info (eg. /sys/class/cxl/card0)
+
+What:           /sys/class/cxl/<card>/caia_version
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Identifies the CAIA Version the card implements.
+
+What:           /sys/class/cxl/<card>/psl_version
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Identifies the revision level of the PSL.
+
+What:           /sys/class/cxl/<card>/base_image
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Identifies the revision level of the base image for devices
+                that support loadable PSLs. For FPGAs this field identifies
+                the image contained in the on-adapter flash which is loaded
+                during the initial program load.
+
+What:           /sys/class/cxl/<card>/image_loaded
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Will return "user" or "factory" depending on the image loaded
+                onto the card.
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 7e240a7c9ab1..8136e1fd30fd 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -313,6 +313,7 @@ Code  Seq#(hex)	Include File		Comments
 0xB1	00-1F	PPPoX			<mailto:mostrows@styx.uwaterloo.ca>
 0xB3	00	linux/mmc/ioctl.h
 0xC0	00-0F	linux/usb/iowarrior.h
+0xCA	00-0F	uapi/misc/cxl.h
 0xCB	00-1F	CBM serial IEC bus	in development:
 					<mailto:michael.klein@puffin.lb.shuttle.de>
 0xCD	01	linux/reiserfs_fs.h
diff --git a/Documentation/powerpc/00-INDEX b/Documentation/powerpc/00-INDEX
index a68784d0a1ee..6fd0e8bb8140 100644
--- a/Documentation/powerpc/00-INDEX
+++ b/Documentation/powerpc/00-INDEX
@@ -11,6 +11,8 @@ bootwrapper.txt
 cpu_features.txt
 	- info on how we support a variety of CPUs with minimal compile-time
 	options.
+cxl.txt
+	- Overview of the CXL driver.
 eeh-pci-error-recovery.txt
 	- info on PCI Bus EEH Error Recovery
 firmware-assisted-dump.txt
diff --git a/Documentation/powerpc/cxl.txt b/Documentation/powerpc/cxl.txt
new file mode 100644
index 000000000000..2c71ecc519d9
--- /dev/null
+++ b/Documentation/powerpc/cxl.txt
@@ -0,0 +1,379 @@
+Coherent Accelerator Interface (CXL)
+====================================
+
+Introduction
+============
+
+    The coherent accelerator interface is designed to allow the
+    coherent connection of accelerators (FPGAs and other devices) to a
+    POWER system. These devices need to adhere to the Coherent
+    Accelerator Interface Architecture (CAIA).
+
+    IBM refers to this as the Coherent Accelerator Processor Interface
+    or CAPI. In the kernel it's referred to by the name CXL to avoid
+    confusion with the ISDN CAPI subsystem.
+
+    Coherent in this context means that the accelerator and CPUs can
+    both access system memory directly and with the same effective
+    addresses.
+
+
+Hardware overview
+=================
+
+          POWER8               FPGA
+       +----------+        +---------+
+       |          |        |         |
+       |   CPU    |        |   AFU   |
+       |          |        |         |
+       |          |        |         |
+       |          |        |         |
+       +----------+        +---------+
+       |   PHB    |        |         |
+       |   +------+        |   PSL   |
+       |   | CAPP |<------>|         |
+       +---+------+  PCIE  +---------+
+
+    The POWER8 chip has a Coherently Attached Processor Proxy (CAPP)
+    unit which is part of the PCIe Host Bridge (PHB). This is managed
+    by Linux by calls into OPAL. Linux doesn't directly program the
+    CAPP.
+
+    The FPGA (or coherently attached device) consists of two parts.
+    The POWER Service Layer (PSL) and the Accelerator Function Unit
+    (AFU). The AFU is used to implement specific functionality behind
+    the PSL. The PSL, among other things, provides memory address
+    translation services to allow each AFU direct access to userspace
+    memory.
+
+    The AFU is the core part of the accelerator (eg. the compression,
+    crypto etc function). The kernel has no knowledge of the function
+    of the AFU. Only userspace interacts directly with the AFU.
+
+    The PSL provides the translation and interrupt services that the
+    AFU needs. This is what the kernel interacts with. For example, if
+    the AFU needs to read a particular effective address, it sends
+    that address to the PSL, the PSL then translates it, fetches the
+    data from memory and returns it to the AFU. If the PSL has a
+    translation miss, it interrupts the kernel and the kernel services
+    the fault. The context to which this fault is serviced is based on
+    who owns that acceleration function.
+
+
+AFU Modes
+=========
+
+    There are two programming modes supported by the AFU. Dedicated
+    and AFU directed. AFU may support one or both modes.
+
+    When using dedicated mode only one MMU context is supported. In
+    this mode, only one userspace process can use the accelerator at
+    time.
+
+    When using AFU directed mode, up to 16K simultaneous contexts can
+    be supported. This means up to 16K simultaneous userspace
+    applications may use the accelerator (although specific AFUs may
+    support fewer). In this mode, the AFU sends a 16 bit context ID
+    with each of its requests. This tells the PSL which context is
+    associated with each operation. If the PSL can't translate an
+    operation, the ID can also be accessed by the kernel so it can
+    determine the userspace context associated with an operation.
+
+
+MMIO space
+==========
+
+    A portion of the accelerator MMIO space can be directly mapped
+    from the AFU to userspace. Either the whole space can be mapped or
+    just a per context portion. The hardware is self describing, hence
+    the kernel can determine the offset and size of the per context
+    portion.
+
+
+Interrupts
+==========
+
+    AFUs may generate interrupts that are destined for userspace. These
+    are received by the kernel as hardware interrupts and passed onto
+    userspace by a read syscall documented below.
+
+    Data storage faults and error interrupts are handled by the kernel
+    driver.
+
+
+Work Element Descriptor (WED)
+=============================
+
+    The WED is a 64-bit parameter passed to the AFU when a context is
+    started. Its format is up to the AFU hence the kernel has no
+    knowledge of what it represents. Typically it will be the
+    effective address of a work queue or status block where the AFU
+    and userspace can share control and status information.
+
+
+
+
+User API
+========
+
+    For AFUs operating in AFU directed mode, two character device
+    files will be created. /dev/cxl/afu0.0m will correspond to a
+    master context and /dev/cxl/afu0.0s will correspond to a slave
+    context. Master contexts have access to the full MMIO space an
+    AFU provides. Slave contexts have access to only the per process
+    MMIO space an AFU provides.
+
+    For AFUs operating in dedicated process mode, the driver will
+    only create a single character device per AFU called
+    /dev/cxl/afu0.0d. This will have access to the entire MMIO space
+    that the AFU provides (like master contexts in AFU directed).
+
+    The types described below are defined in include/uapi/misc/cxl.h
+
+    The following file operations are supported on both slave and
+    master devices.
+
+
+open
+----
+
+    Opens the device and allocates a file descriptor to be used with
+    the rest of the API.
+
+    A dedicated mode AFU only has one context and only allows the
+    device to be opened once.
+
+    An AFU directed mode AFU can have many contexts, the device can be
+    opened once for each context that is available.
+
+    When all available contexts are allocated the open call will fail
+    and return -ENOSPC.
+
+    Note: IRQs need to be allocated for each context, which may limit
+          the number of contexts that can be created, and therefore
+          how many times the device can be opened. The POWER8 CAPP
+          supports 2040 IRQs and 3 are used by the kernel, so 2037 are
+          left. If 1 IRQ is needed per context, then only 2037
+          contexts can be allocated. If 4 IRQs are needed per context,
+          then only 2037/4 = 509 contexts can be allocated.
+
+
+ioctl
+-----
+
+    CXL_IOCTL_START_WORK:
+        Starts the AFU context and associates it with the current
+        process. Once this ioctl is successfully executed, all memory
+        mapped into this process is accessible to this AFU context
+        using the same effective addresses. No additional calls are
+        required to map/unmap memory. The AFU memory context will be
+        updated as userspace allocates and frees memory. This ioctl
+        returns once the AFU context is started.
+
+        Takes a pointer to a struct cxl_ioctl_start_work:
+
+                struct cxl_ioctl_start_work {
+                        __u64 flags;
+                        __u64 work_element_descriptor;
+                        __u64 amr;
+                        __s16 num_interrupts;
+                        __s16 reserved1;
+                        __s32 reserved2;
+                        __u64 reserved3;
+                        __u64 reserved4;
+                        __u64 reserved5;
+                        __u64 reserved6;
+                };
+
+            flags:
+                Indicates which optional fields in the structure are
+                valid.
+
+            work_element_descriptor:
+                The Work Element Descriptor (WED) is a 64-bit argument
+                defined by the AFU. Typically this is an effective
+                address pointing to an AFU specific structure
+                describing what work to perform.
+
+            amr:
+                Authority Mask Register (AMR), same as the powerpc
+                AMR. This field is only used by the kernel when the
+                corresponding CXL_START_WORK_AMR value is specified in
+                flags. If not specified the kernel will use a default
+                value of 0.
+
+            num_interrupts:
+                Number of userspace interrupts to request. This field
+                is only used by the kernel when the corresponding
+                CXL_START_WORK_NUM_IRQS value is specified in flags.
+                If not specified the minimum number required by the
+                AFU will be allocated. The min and max number can be
+                obtained from sysfs.
+
+            reserved fields:
+                For ABI padding and future extensions
+
+    CXL_IOCTL_GET_PROCESS_ELEMENT:
+        Get the current context id, also known as the process element.
+        The value is returned from the kernel as a __u32.
+
+
+mmap
+----
+
+    An AFU may have an MMIO space to facilitate communication with the
+    AFU. If it does, the MMIO space can be accessed via mmap. The size
+    and contents of this area are specific to the particular AFU. The
+    size can be discovered via sysfs.
+
+    In AFU directed mode, master contexts are allowed to map all of
+    the MMIO space and slave contexts are allowed to only map the per
+    process MMIO space associated with the context. In dedicated
+    process mode the entire MMIO space can always be mapped.
+
+    This mmap call must be done after the START_WORK ioctl.
+
+    Care should be taken when accessing MMIO space. Only 32 and 64-bit
+    accesses are supported by POWER8. Also, the AFU will be designed
+    with a specific endianness, so all MMIO accesses should consider
+    endianness (recommend endian(3) variants like: le64toh(),
+    be64toh() etc). These endian issues equally apply to shared memory
+    queues the WED may describe.
+
+
+read
+----
+
+    Reads events from the AFU. Blocks if no events are pending
+    (unless O_NONBLOCK is supplied). Returns -EIO in the case of an
+    unrecoverable error or if the card is removed.
+
+    read() will always return an integral number of events.
+
+    The buffer passed to read() must be at least 4K bytes.
+
+    The result of the read will be a buffer of one or more events,
+    each event is of type struct cxl_event, of varying size.
+
+            struct cxl_event {
+                    struct cxl_event_header header;
+                    union {
+                            struct cxl_event_afu_interrupt irq;
+                            struct cxl_event_data_storage fault;
+                            struct cxl_event_afu_error afu_error;
+                    };
+            };
+
+    The struct cxl_event_header is defined as:
+
+            struct cxl_event_header {
+                    __u16 type;
+                    __u16 size;
+                    __u16 process_element;
+                    __u16 reserved1;
+            };
+
+        type:
+            This defines the type of event. The type determines how
+            the rest of the event is structured. These types are
+            described below and defined by enum cxl_event_type.
+
+        size:
+            This is the size of the event in bytes including the
+            struct cxl_event_header. The start of the next event can
+            be found at this offset from the start of the current
+            event.
+
+        process_element:
+            Context ID of the event.
+
+        reserved field:
+            For future extensions and padding.
+
+    If the event type is CXL_EVENT_AFU_INTERRUPT then the event
+    structure is defined as:
+
+            struct cxl_event_afu_interrupt {
+                    __u16 flags;
+                    __u16 irq; /* Raised AFU interrupt number */
+                    __u32 reserved1;
+            };
+
+        flags:
+            These flags indicate which optional fields are present
+            in this struct. Currently all fields are mandatory.
+
+        irq:
+            The IRQ number sent by the AFU.
+
+        reserved field:
+            For future extensions and padding.
+
+    If the event type is CXL_EVENT_DATA_STORAGE then the event
+    structure is defined as:
+
+            struct cxl_event_data_storage {
+                    __u16 flags;
+                    __u16 reserved1;
+                    __u32 reserved2;
+                    __u64 addr;
+                    __u64 dsisr;
+                    __u64 reserved3;
+            };
+
+        flags:
+            These flags indicate which optional fields are present in
+            this struct. Currently all fields are mandatory.
+
+        address:
+            The address that the AFU unsuccessfully attempted to
+            access. Valid accesses will be handled transparently by the
+            kernel but invalid accesses will generate this event.
+
+        dsisr:
+            This field gives information on the type of fault. It is a
+            copy of the DSISR from the PSL hardware when the address
+            fault occurred. The form of the DSISR is as defined in the
+            CAIA.
+
+        reserved fields:
+            For future extensions
+
+    If the event type is CXL_EVENT_AFU_ERROR then the event structure
+    is defined as:
+
+            struct cxl_event_afu_error {
+                    __u16 flags;
+                    __u16 reserved1;
+                    __u32 reserved2;
+                    __u64 error;
+            };
+
+        flags:
+            These flags indicate which optional fields are present in
+            this struct. Currently all fields are Mandatory.
+
+        error:
+            Error status from the AFU. Defined by the AFU.
+
+        reserved fields:
+            For future extensions and padding
+
+Sysfs Class
+===========
+
+    A cxl sysfs class is added under /sys/class/cxl to facilitate
+    enumeration and tuning of the accelerators. Its layout is
+    described in Documentation/ABI/testing/sysfs-class-cxl
+
+Udev rules
+==========
+
+    The following udev rules could be used to create a symlink to the
+    most logical chardev to use in any programming mode (afuX.Yd for
+    dedicated, afuX.Ys for afu directed), since the API is virtually
+    identical for each:
+
+	SUBSYSTEM=="cxl", ATTRS{mode}=="dedicated_process", SYMLINK="cxl/%b"
+	SUBSYSTEM=="cxl", ATTRS{mode}=="afu_directed", \
+	                  KERNEL=="afu[0-9]*.[0-9]*s", SYMLINK="cxl/%b"
diff --git a/MAINTAINERS b/MAINTAINERS
index 809ecd680d88..facc2198eaba 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2711,6 +2711,18 @@ W:	http://www.chelsio.com
 S:	Supported
 F:	drivers/net/ethernet/chelsio/cxgb4vf/
 
+CXL (IBM Coherent Accelerator Processor Interface CAPI) DRIVER
+M:	Ian Munsie <imunsie@au1.ibm.com>
+M:	Michael Neuling <mikey@neuling.org>
+L:	linuxppc-dev@lists.ozlabs.org
+S:	Supported
+F:	drivers/misc/cxl/
+F:	include/misc/cxl.h
+F:	include/uapi/misc/cxl.h
+F:	Documentation/powerpc/cxl.txt
+F:	Documentation/powerpc/cxl.txt
+F:	Documentation/ABI/testing/sysfs-class-cxl
+
 STMMAC ETHERNET DRIVER
 M:	Giuseppe Cavallaro <peppe.cavallaro@st.com>
 L:	netdev@vger.kernel.org
diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h
index c232be6ae21f..cd6d789b73ec 100644
--- a/include/uapi/misc/cxl.h
+++ b/include/uapi/misc/cxl.h
@@ -13,7 +13,7 @@
 #include <linux/types.h>
 #include <linux/ioctl.h>
 
-/* Structs for IOCTLS for userspace to talk to the kernel */
+
 struct cxl_ioctl_start_work {
 	__u64 flags;
 	__u64 work_element_descriptor;
@@ -26,19 +26,20 @@ struct cxl_ioctl_start_work {
 	__u64 reserved5;
 	__u64 reserved6;
 };
+
 #define CXL_START_WORK_AMR		0x0000000000000001ULL
 #define CXL_START_WORK_NUM_IRQS		0x0000000000000002ULL
 #define CXL_START_WORK_ALL		(CXL_START_WORK_AMR |\
 					 CXL_START_WORK_NUM_IRQS)
 
-/* IOCTL numbers */
+/* ioctl numbers */
 #define CXL_MAGIC 0xCA
 #define CXL_IOCTL_START_WORK		_IOW(CXL_MAGIC, 0x00, struct cxl_ioctl_start_work)
 #define CXL_IOCTL_GET_PROCESS_ELEMENT	_IOR(CXL_MAGIC, 0x01, __u32)
 
-/* Events from read() */
 #define CXL_READ_MIN_SIZE 0x1000 /* 4K */
 
+/* Events from read() */
 enum cxl_event_type {
 	CXL_EVENT_RESERVED      = 0,
 	CXL_EVENT_AFU_INTERRUPT = 1,
-- 
cgit v1.2.3


From 583d4a6885cfa75a3d189f6bb69b5c545e961c75 Mon Sep 17 00:00:00 2001
From: LEROY Christophe <christophe.leroy@c-s.fr>
Date: Tue, 7 Oct 2014 15:04:57 +0200
Subject: net: fs_enet: Remove non NAPI RX

In the probe function, use_napi is inconditionnaly set to 1. This patch removes
all the code which is conditional to !use_napi, and removes use_napi which has
then become useless.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/freescale/fs_enet/fs_enet-main.c  | 164 ++-------------------
 include/linux/fs_enet_pd.h                         |   1 -
 2 files changed, 15 insertions(+), 150 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 748fd24d3d9e..71a25b4e2d5a 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -215,128 +215,6 @@ static int fs_enet_rx_napi(struct napi_struct *napi, int budget)
 	return received;
 }
 
-/* non NAPI receive function */
-static int fs_enet_rx_non_napi(struct net_device *dev)
-{
-	struct fs_enet_private *fep = netdev_priv(dev);
-	const struct fs_platform_info *fpi = fep->fpi;
-	cbd_t __iomem *bdp;
-	struct sk_buff *skb, *skbn, *skbt;
-	int received = 0;
-	u16 pkt_len, sc;
-	int curidx;
-	/*
-	 * First, grab all of the stats for the incoming packet.
-	 * These get messed up if we get called due to a busy condition.
-	 */
-	bdp = fep->cur_rx;
-
-	while (((sc = CBDR_SC(bdp)) & BD_ENET_RX_EMPTY) == 0) {
-
-		curidx = bdp - fep->rx_bd_base;
-
-		/*
-		 * Since we have allocated space to hold a complete frame,
-		 * the last indicator should be set.
-		 */
-		if ((sc & BD_ENET_RX_LAST) == 0)
-			dev_warn(fep->dev, "rcv is not +last\n");
-
-		/*
-		 * Check for errors.
-		 */
-		if (sc & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_CL |
-			  BD_ENET_RX_NO | BD_ENET_RX_CR | BD_ENET_RX_OV)) {
-			fep->stats.rx_errors++;
-			/* Frame too long or too short. */
-			if (sc & (BD_ENET_RX_LG | BD_ENET_RX_SH))
-				fep->stats.rx_length_errors++;
-			/* Frame alignment */
-			if (sc & (BD_ENET_RX_NO | BD_ENET_RX_CL))
-				fep->stats.rx_frame_errors++;
-			/* CRC Error */
-			if (sc & BD_ENET_RX_CR)
-				fep->stats.rx_crc_errors++;
-			/* FIFO overrun */
-			if (sc & BD_ENET_RX_OV)
-				fep->stats.rx_crc_errors++;
-
-			skb = fep->rx_skbuff[curidx];
-
-			dma_unmap_single(fep->dev, CBDR_BUFADDR(bdp),
-				L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
-				DMA_FROM_DEVICE);
-
-			skbn = skb;
-
-		} else {
-
-			skb = fep->rx_skbuff[curidx];
-
-			dma_unmap_single(fep->dev, CBDR_BUFADDR(bdp),
-				L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
-				DMA_FROM_DEVICE);
-
-			/*
-			 * Process the incoming frame.
-			 */
-			fep->stats.rx_packets++;
-			pkt_len = CBDR_DATLEN(bdp) - 4;	/* remove CRC */
-			fep->stats.rx_bytes += pkt_len + 4;
-
-			if (pkt_len <= fpi->rx_copybreak) {
-				/* +2 to make IP header L1 cache aligned */
-				skbn = netdev_alloc_skb(dev, pkt_len + 2);
-				if (skbn != NULL) {
-					skb_reserve(skbn, 2);	/* align IP header */
-					skb_copy_from_linear_data(skb,
-						      skbn->data, pkt_len);
-					/* swap */
-					skbt = skb;
-					skb = skbn;
-					skbn = skbt;
-				}
-			} else {
-				skbn = netdev_alloc_skb(dev, ENET_RX_FRSIZE);
-
-				if (skbn)
-					skb_align(skbn, ENET_RX_ALIGN);
-			}
-
-			if (skbn != NULL) {
-				skb_put(skb, pkt_len);	/* Make room */
-				skb->protocol = eth_type_trans(skb, dev);
-				received++;
-				netif_rx(skb);
-			} else {
-				fep->stats.rx_dropped++;
-				skbn = skb;
-			}
-		}
-
-		fep->rx_skbuff[curidx] = skbn;
-		CBDW_BUFADDR(bdp, dma_map_single(fep->dev, skbn->data,
-			     L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
-			     DMA_FROM_DEVICE));
-		CBDW_DATLEN(bdp, 0);
-		CBDW_SC(bdp, (sc & ~BD_ENET_RX_STATS) | BD_ENET_RX_EMPTY);
-
-		/*
-		 * Update BD pointer to next entry.
-		 */
-		if ((sc & BD_ENET_RX_WRAP) == 0)
-			bdp++;
-		else
-			bdp = fep->rx_bd_base;
-
-		(*fep->ops->rx_bd_done)(dev);
-	}
-
-	fep->cur_rx = bdp;
-
-	return 0;
-}
-
 static void fs_enet_tx(struct net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
@@ -453,8 +331,7 @@ fs_enet_interrupt(int irq, void *dev_id)
 		nr++;
 
 		int_clr_events = int_events;
-		if (fpi->use_napi)
-			int_clr_events &= ~fep->ev_napi_rx;
+		int_clr_events &= ~fep->ev_napi_rx;
 
 		(*fep->ops->clear_int_events)(dev, int_clr_events);
 
@@ -462,19 +339,15 @@ fs_enet_interrupt(int irq, void *dev_id)
 			(*fep->ops->ev_error)(dev, int_events);
 
 		if (int_events & fep->ev_rx) {
-			if (!fpi->use_napi)
-				fs_enet_rx_non_napi(dev);
-			else {
-				napi_ok = napi_schedule_prep(&fep->napi);
-
-				(*fep->ops->napi_disable_rx)(dev);
-				(*fep->ops->clear_int_events)(dev, fep->ev_napi_rx);
-
-				/* NOTE: it is possible for FCCs in NAPI mode    */
-				/* to submit a spurious interrupt while in poll  */
-				if (napi_ok)
-					__napi_schedule(&fep->napi);
-			}
+			napi_ok = napi_schedule_prep(&fep->napi);
+
+			(*fep->ops->napi_disable_rx)(dev);
+			(*fep->ops->clear_int_events)(dev, fep->ev_napi_rx);
+
+			/* NOTE: it is possible for FCCs in NAPI mode    */
+			/* to submit a spurious interrupt while in poll  */
+			if (napi_ok)
+				__napi_schedule(&fep->napi);
 		}
 
 		if (int_events & fep->ev_tx)
@@ -811,24 +684,21 @@ static int fs_enet_open(struct net_device *dev)
 	/* not doing this, will cause a crash in fs_enet_rx_napi */
 	fs_init_bds(fep->ndev);
 
-	if (fep->fpi->use_napi)
-		napi_enable(&fep->napi);
+	napi_enable(&fep->napi);
 
 	/* Install our interrupt handler. */
 	r = request_irq(fep->interrupt, fs_enet_interrupt, IRQF_SHARED,
 			"fs_enet-mac", dev);
 	if (r != 0) {
 		dev_err(fep->dev, "Could not allocate FS_ENET IRQ!");
-		if (fep->fpi->use_napi)
-			napi_disable(&fep->napi);
+		napi_disable(&fep->napi);
 		return -EINVAL;
 	}
 
 	err = fs_init_phy(dev);
 	if (err) {
 		free_irq(fep->interrupt, dev);
-		if (fep->fpi->use_napi)
-			napi_disable(&fep->napi);
+		napi_disable(&fep->napi);
 		return err;
 	}
 	phy_start(fep->phydev);
@@ -845,8 +715,7 @@ static int fs_enet_close(struct net_device *dev)
 
 	netif_stop_queue(dev);
 	netif_carrier_off(dev);
-	if (fep->fpi->use_napi)
-		napi_disable(&fep->napi);
+	napi_disable(&fep->napi);
 	phy_stop(fep->phydev);
 
 	spin_lock_irqsave(&fep->lock, flags);
@@ -1022,7 +891,6 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	fpi->rx_ring = 32;
 	fpi->tx_ring = 32;
 	fpi->rx_copybreak = 240;
-	fpi->use_napi = 1;
 	fpi->napi_weight = 17;
 	fpi->phy_node = of_parse_phandle(ofdev->dev.of_node, "phy-handle", 0);
 	if (!fpi->phy_node && of_phy_is_fixed_link(ofdev->dev.of_node)) {
@@ -1102,9 +970,7 @@ static int fs_enet_probe(struct platform_device *ofdev)
 
 	ndev->netdev_ops = &fs_enet_netdev_ops;
 	ndev->watchdog_timeo = 2 * HZ;
-	if (fpi->use_napi)
-		netif_napi_add(ndev, &fep->napi, fs_enet_rx_napi,
-		               fpi->napi_weight);
+	netif_napi_add(ndev, &fep->napi, fs_enet_rx_napi, fpi->napi_weight);
 
 	ndev->ethtool_ops = &fs_ethtool_ops;
 
diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h
index efb05961bdd8..77d783f71527 100644
--- a/include/linux/fs_enet_pd.h
+++ b/include/linux/fs_enet_pd.h
@@ -139,7 +139,6 @@ struct fs_platform_info {
 	int rx_ring, tx_ring;	/* number of buffers on rx     */
 	__u8 macaddr[ETH_ALEN];	/* mac address                 */
 	int rx_copybreak;	/* limit we copy small frames  */
-	int use_napi;		/* use NAPI                    */
 	int napi_weight;	/* NAPI weight                 */
 
 	int use_rmii;		/* use RMII mode 	       */
-- 
cgit v1.2.3


From 68939df1d7d8da9088d51000bd334f4c59ea0cb3 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@amacapital.net>
Date: Thu, 14 Aug 2014 14:45:40 -0700
Subject: Move Intel SNB device ids from sb_edac to pci_ids.h

The i2c_imc driver will use two of them, and moving only part of
the list seems messier.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Aristeu Rozanski <aris@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/edac/sb_edac.c  | 30 ------------------------------
 include/linux/pci_ids.h | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 07efed452a15..449622935816 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -52,36 +52,6 @@ static int probed;
 #define GET_BITFIELD(v, lo, hi)	\
 	(((v) & GENMASK_ULL(hi, lo)) >> (lo))
 
-/*
- * sbridge Memory Controller Registers
- */
-
-/*
- * FIXME: For now, let's order by device function, as it makes
- * easier for driver's development process. This table should be
- * moved to pci_id.h when submitted upstream
- */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0	0x3cf4	/* 12.6 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1	0x3cf6	/* 12.7 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_BR		0x3cf5	/* 13.6 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0	0x3ca0	/* 14.0 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA	0x3ca8	/* 15.0 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS	0x3c71	/* 15.1 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0	0x3caa	/* 15.2 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1	0x3cab	/* 15.3 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2	0x3cac	/* 15.4 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3	0x3cad	/* 15.5 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO	0x3cb8	/* 17.0 */
-
-	/*
-	 * Currently, unused, but will be needed in the future
-	 * implementations, as they hold the error counters
-	 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR0	0x3c72	/* 16.2 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR1	0x3c73	/* 16.3 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR2	0x3c76	/* 16.6 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR3	0x3c77	/* 16.7 */
-
 /* Devices 12 Function 6, Offsets 0x80 to 0xcc */
 static const u32 sbridge_dram_rule[] = {
 	0x80, 0x88, 0x90, 0x98, 0xa0,
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 6ed0bb73a864..58aa8d78353f 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2818,7 +2818,22 @@
 #define PCI_DEVICE_ID_INTEL_UNC_R2PCIE	0x3c43
 #define PCI_DEVICE_ID_INTEL_UNC_R3QPI0	0x3c44
 #define PCI_DEVICE_ID_INTEL_UNC_R3QPI1	0x3c45
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS	0x3c71	/* 15.1 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR0	0x3c72	/* 16.2 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR1	0x3c73	/* 16.3 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR2	0x3c76	/* 16.6 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR3	0x3c77	/* 16.7 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0	0x3ca0	/* 14.0 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA	0x3ca8	/* 15.0 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0	0x3caa	/* 15.2 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1	0x3cab	/* 15.3 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2	0x3cac	/* 15.4 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3	0x3cad	/* 15.5 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO	0x3cb8	/* 17.0 */
 #define PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX	0x3ce0
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0	0x3cf4	/* 12.6 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_BR		0x3cf5	/* 13.6 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1	0x3cf6	/* 12.7 */
 #define PCI_DEVICE_ID_INTEL_IOAT_SNB	0x402f
 #define PCI_DEVICE_ID_INTEL_5100_16	0x65f0
 #define PCI_DEVICE_ID_INTEL_5100_19	0x65f3
-- 
cgit v1.2.3


From 709c48b39ecf11a81f3820c13a828c330fd832b9 Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Wed, 8 Oct 2014 23:53:39 +0900
Subject: net: description of dma_cookie cause make xmldocs warning

In commit 7bced397510ab569d31de4c70b39e13355046387,
dma_cookie was removed from struct skbuff.
But the description of dma_cookie still exist.
So the "make xmldocs" output following warning.

Warning(.//include/linux/skbuff.h:609): Excess struct/union
/enum/typedef member 'dma_cookie' description in 'sk_buff'

Remove description of dma_cookie fix the symptom.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3a5ec7638627..776104ba02ce 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -483,8 +483,6 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
  *	@wifi_acked_valid: wifi_acked was set
  *	@wifi_acked: whether frame was acked on wifi or not
  *	@no_fcs:  Request NIC to treat last 4 bytes as Ethernet FCS
- *	@dma_cookie: a cookie to one of several possible DMA operations
- *		done by skb DMA functions
   *	@napi_id: id of the NAPI struct this skb came from
  *	@secmark: security marking
  *	@mark: Generic packet mark
-- 
cgit v1.2.3


From 535114539bb2c081b6680cb5a34be17e7b45df37 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 8 Oct 2014 08:19:27 -0700
Subject: net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers

Add two helpers so that drivers do not have to care of BQL being
available or not.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jim Davis <jim.epost@gmail.com>
Fixes: 29d40c903247 ("net/mlx4_en: Use prefetch in tx path")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c |  5 +++--
 include/linux/netdevice.h                  | 29 +++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 8726a4aee5a7..34c137878545 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -392,7 +392,8 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 	if (!priv->port_up)
 		return true;
 
-	prefetchw(&ring->tx_queue->dql.limit);
+	netdev_txq_bql_complete_prefetchw(ring->tx_queue);
+
 	index = cons_index & size_mask;
 	cqe = mlx4_en_get_cqe(buf, index, priv->cqe_size) + factor;
 	last_nr_txbb = ACCESS_ONCE(ring->last_nr_txbb);
@@ -737,7 +738,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		vlan_tag = vlan_tx_tag_get(skb);
 
 
-	prefetchw(&ring->tx_queue->dql);
+	netdev_txq_bql_enqueue_prefetchw(ring->tx_queue);
 
 	/* Track current inflight packets for performance analysis */
 	AVG_PERF_COUNTER(priv->pstats.inflight_avg,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3a4315b39d20..838407aea705 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -30,6 +30,7 @@
 #include <linux/bug.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <linux/prefetch.h>
 #include <asm/cache.h>
 #include <asm/byteorder.h>
 
@@ -2480,6 +2481,34 @@ netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue)
 	return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN;
 }
 
+/**
+ *	netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
+ *	@dev_queue: pointer to transmit queue
+ *
+ * BQL enabled drivers might use this helper in their ndo_start_xmit(),
+ * to give appropriate hint to the cpu.
+ */
+static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue)
+{
+#ifdef CONFIG_BQL
+	prefetchw(&dev_queue->dql.num_queued);
+#endif
+}
+
+/**
+ *	netdev_txq_bql_complete_prefetchw - prefetch bql data for write
+ *	@dev_queue: pointer to transmit queue
+ *
+ * BQL enabled drivers might use this helper in their TX completion path,
+ * to give appropriate hint to the cpu.
+ */
+static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue)
+{
+#ifdef CONFIG_BQL
+	prefetchw(&dev_queue->dql.limit);
+#endif
+}
+
 static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 					unsigned int bytes)
 {
-- 
cgit v1.2.3


From 1ffe46d11cc88479797b262f60d92e5fb461b411 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 13 Feb 2014 09:39:37 -0800
Subject: vfs: Merge check_submounts_and_drop and d_invalidate

Now that d_invalidate is the only caller of check_submounts_and_drop,
expand check_submounts_and_drop inline in d_invalidate.

Reviewed-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 55 ++++++++++++++++++++------------------------------
 include/linux/dcache.h |  1 -
 2 files changed, 22 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index 484114a4db93..5e02b9eee6b1 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -645,32 +645,6 @@ kill_it:
 }
 EXPORT_SYMBOL(dput);
 
-/**
- * d_invalidate - invalidate a dentry
- * @dentry: dentry to invalidate
- *
- * Try to invalidate the dentry if it turns out to be
- * possible. If there are reasons not to delete it
- * return -EBUSY. On success return 0.
- *
- * no dcache lock.
- */
- 
-int d_invalidate(struct dentry * dentry)
-{
-	/*
-	 * If it's already been dropped, return OK.
-	 */
-	spin_lock(&dentry->d_lock);
-	if (d_unhashed(dentry)) {
-		spin_unlock(&dentry->d_lock);
-		return 0;
-	}
-	spin_unlock(&dentry->d_lock);
-
-	return check_submounts_and_drop(dentry);
-}
-EXPORT_SYMBOL(d_invalidate);
 
 /* This must be called with d_lock held */
 static inline void __dget_dlock(struct dentry *dentry)
@@ -1190,7 +1164,7 @@ EXPORT_SYMBOL(have_submounts);
  * reachable (e.g. NFS can unhash a directory dentry and then the complete
  * subtree can become unreachable).
  *
- * Only one of check_submounts_and_drop() and d_set_mounted() must succeed.  For
+ * Only one of d_invalidate() and d_set_mounted() must succeed.  For
  * this reason take rename_lock and d_lock on dentry and ancestors.
  */
 int d_set_mounted(struct dentry *dentry)
@@ -1199,7 +1173,7 @@ int d_set_mounted(struct dentry *dentry)
 	int ret = -ENOENT;
 	write_seqlock(&rename_lock);
 	for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) {
-		/* Need exclusion wrt. check_submounts_and_drop() */
+		/* Need exclusion wrt. d_invalidate() */
 		spin_lock(&p->d_lock);
 		if (unlikely(d_unhashed(p))) {
 			spin_unlock(&p->d_lock);
@@ -1369,18 +1343,33 @@ static void check_and_drop(void *_data)
 }
 
 /**
- * check_submounts_and_drop - detach submounts, prune dcache, and drop
+ * d_invalidate - detach submounts, prune dcache, and drop
+ * @dentry: dentry to invalidate (aka detach, prune and drop)
+ *
+ * Try to invalidate the dentry if it turns out to be
+ * possible. If there are reasons not to delete it
+ * return -EBUSY. On success return 0.
+ *
+ * no dcache lock.
  *
  * The final d_drop is done as an atomic operation relative to
  * rename_lock ensuring there are no races with d_set_mounted.  This
  * ensures there are no unhashed dentries on the path to a mountpoint.
- *
- * @dentry: dentry to detach, prune and drop
  */
-int check_submounts_and_drop(struct dentry *dentry)
+int d_invalidate(struct dentry *dentry)
 {
 	int ret = 0;
 
+	/*
+	 * If it's already been dropped, return OK.
+	 */
+	spin_lock(&dentry->d_lock);
+	if (d_unhashed(dentry)) {
+		spin_unlock(&dentry->d_lock);
+		return 0;
+	}
+	spin_unlock(&dentry->d_lock);
+
 	/* Negative dentries can be dropped without further checks */
 	if (!dentry->d_inode) {
 		d_drop(dentry);
@@ -1414,7 +1403,7 @@ int check_submounts_and_drop(struct dentry *dentry)
 out:
 	return ret;
 }
-EXPORT_SYMBOL(check_submounts_and_drop);
+EXPORT_SYMBOL(d_invalidate);
 
 /**
  * __d_alloc	-	allocate a dcache entry
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 75a227cc7ce2..595af29ad145 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -269,7 +269,6 @@ extern void d_prune_aliases(struct inode *);
 
 /* test whether we have any submounts in a subdir tree */
 extern int have_submounts(struct dentry *);
-extern int check_submounts_and_drop(struct dentry *);
 
 /*
  * This adds the entry to the hash queues.
-- 
cgit v1.2.3


From 5542aa2fa7f6cddb03c4ac3135e390adffda98ca Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 13 Feb 2014 09:46:25 -0800
Subject: vfs: Make d_invalidate return void

Now that d_invalidate can no longer fail, stop returning a useless
return code.  For the few callers that checked the return code update
remove the handling of d_invalidate failure.

Reviewed-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/btrfs/ioctl.c       |  5 +----
 fs/cifs/readdir.c      |  6 +-----
 fs/dcache.c            | 15 +++------------
 fs/fuse/dir.c          |  4 +---
 fs/namei.c             | 10 +++++-----
 fs/nfs/dir.c           |  3 +--
 include/linux/dcache.h |  2 +-
 7 files changed, 13 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 8a8e29878c34..996eb192fa77 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2423,9 +2423,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		goto out_dput;
 	}
 
-	err = d_invalidate(dentry);
-	if (err)
-		goto out_unlock;
+	d_invalidate(dentry);
 
 	down_write(&root->fs_info->subvol_sem);
 
@@ -2510,7 +2508,6 @@ out_release:
 	btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
 out_up_write:
 	up_write(&root->fs_info->subvol_sem);
-out_unlock:
 	if (err) {
 		spin_lock(&dest->root_item_lock);
 		root_flags = btrfs_root_flags(&dest->root_item);
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index b334a89d6a66..d2141f101382 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -87,8 +87,6 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 		return;
 
 	if (dentry) {
-		int err;
-
 		inode = dentry->d_inode;
 		if (inode) {
 			/*
@@ -105,10 +103,8 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 				goto out;
 			}
 		}
-		err = d_invalidate(dentry);
+		d_invalidate(dentry);
 		dput(dentry);
-		if (err)
-			return;
 	}
 
 	/*
diff --git a/fs/dcache.c b/fs/dcache.c
index 5e02b9eee6b1..70d102e70271 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1346,34 +1346,28 @@ static void check_and_drop(void *_data)
  * d_invalidate - detach submounts, prune dcache, and drop
  * @dentry: dentry to invalidate (aka detach, prune and drop)
  *
- * Try to invalidate the dentry if it turns out to be
- * possible. If there are reasons not to delete it
- * return -EBUSY. On success return 0.
- *
  * no dcache lock.
  *
  * The final d_drop is done as an atomic operation relative to
  * rename_lock ensuring there are no races with d_set_mounted.  This
  * ensures there are no unhashed dentries on the path to a mountpoint.
  */
-int d_invalidate(struct dentry *dentry)
+void d_invalidate(struct dentry *dentry)
 {
-	int ret = 0;
-
 	/*
 	 * If it's already been dropped, return OK.
 	 */
 	spin_lock(&dentry->d_lock);
 	if (d_unhashed(dentry)) {
 		spin_unlock(&dentry->d_lock);
-		return 0;
+		return;
 	}
 	spin_unlock(&dentry->d_lock);
 
 	/* Negative dentries can be dropped without further checks */
 	if (!dentry->d_inode) {
 		d_drop(dentry);
-		goto out;
+		return;
 	}
 
 	for (;;) {
@@ -1399,9 +1393,6 @@ int d_invalidate(struct dentry *dentry)
 
 		cond_resched();
 	}
-
-out:
-	return ret;
 }
 EXPORT_SYMBOL(d_invalidate);
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 820efd74ca9f..dbab798f5caf 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1286,9 +1286,7 @@ static int fuse_direntplus_link(struct file *file,
 			d_drop(dentry);
 		} else if (get_node_id(inode) != o->nodeid ||
 			   ((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
-			err = d_invalidate(dentry);
-			if (err)
-				goto out;
+			d_invalidate(dentry);
 		} else if (is_bad_inode(inode)) {
 			err = -EIO;
 			goto out;
diff --git a/fs/namei.c b/fs/namei.c
index 2ba10904dba0..d20d579a022e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1306,7 +1306,8 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
 				if (error < 0) {
 					dput(dentry);
 					return ERR_PTR(error);
-				} else if (!d_invalidate(dentry)) {
+				} else {
+					d_invalidate(dentry);
 					dput(dentry);
 					dentry = NULL;
 				}
@@ -1435,10 +1436,9 @@ unlazy:
 			dput(dentry);
 			return status;
 		}
-		if (!d_invalidate(dentry)) {
-			dput(dentry);
-			goto need_lookup;
-		}
+		d_invalidate(dentry);
+		dput(dentry);
+		goto need_lookup;
 	}
 
 	path->mnt = mnt;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8be6988a1c6c..06e8cfcbb670 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -486,8 +486,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 				nfs_setsecurity(dentry->d_inode, entry->fattr, entry->label);
 			goto out;
 		} else {
-			if (d_invalidate(dentry) != 0)
-				goto out;
+			d_invalidate(dentry);
 			dput(dentry);
 		}
 	}
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 595af29ad145..81b03150f39a 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -254,7 +254,7 @@ extern struct dentry * d_obtain_root(struct inode *);
 extern void shrink_dcache_sb(struct super_block *);
 extern void shrink_dcache_parent(struct dentry *);
 extern void shrink_dcache_for_umount(struct super_block *);
-extern int d_invalidate(struct dentry *);
+extern void d_invalidate(struct dentry *);
 
 /* only used at mount-time */
 extern struct dentry * d_make_root(struct inode *);
-- 
cgit v1.2.3


From 1fa97e8b1f327059aa98089abd8c3378cdf43017 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 7 May 2014 20:47:49 -0400
Subject: constify file_inode()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 94187721ad41..75bdd51ec9b8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1874,7 +1874,7 @@ extern int current_umask(void);
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 
-static inline struct inode *file_inode(struct file *f)
+static inline struct inode *file_inode(const struct file *f)
 {
 	return f->f_inode;
 }
-- 
cgit v1.2.3


From c35e02480014f7a86e264a2fda39a568690163da Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@linux.intel.com>
Date: Fri, 1 Aug 2014 09:27:22 -0400
Subject: Add copy_to_iter(), copy_from_iter() and iov_iter_zero()

For DAX, we want to be able to copy between iovecs and kernel addresses
that don't necessarily have a struct page.  This is a fairly simple
rearrangement for bvec iters to kmap the pages outside and pass them in,
but for user iovecs it gets more complicated because we might try various
different ways to kmap the memory.  Duplicating the existing logic works
out best in this case.

We need to be able to write zeroes to an iovec for reads from unwritten
ranges in a file.  This is performed by the new iov_iter_zero() function,
again patterned after the existing code that handles iovec iterators.

[AV: and export the buggers...]

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/uio.h |   3 +
 mm/iov_iter.c       | 240 +++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 229 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 290fbf0b6b8a..9b1581414cd4 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -80,6 +80,9 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
+size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
 			unsigned long nr_segs, size_t count);
diff --git a/mm/iov_iter.c b/mm/iov_iter.c
index 9a09f2034fcc..eafcf60f6b83 100644
--- a/mm/iov_iter.c
+++ b/mm/iov_iter.c
@@ -4,6 +4,96 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
+static size_t copy_to_iter_iovec(void *from, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __copy_to_user(buf, from, copy);
+	copy -= left;
+	skip += copy;
+	from += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_to_user(buf, from, copy);
+		copy -= left;
+		skip = copy;
+		from += copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_from_iter_iovec(void *to, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __copy_from_user(to, buf, copy);
+	copy -= left;
+	skip += copy;
+	to += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_from_user(to, buf, copy);
+		copy -= left;
+		skip = copy;
+		to += copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
 static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {
@@ -166,6 +256,50 @@ done:
 	return wanted - bytes;
 }
 
+static size_t zero_iovec(size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __clear_user(buf, copy);
+	copy -= left;
+	skip += copy;
+	bytes -= copy;
+
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __clear_user(buf, copy);
+		copy -= left;
+		skip = copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
 static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 			const struct iovec *iov, size_t base, size_t bytes)
 {
@@ -414,12 +548,17 @@ static void memcpy_to_page(struct page *page, size_t offset, char *from, size_t
 	kunmap_atomic(to);
 }
 
-static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t bytes,
-			 struct iov_iter *i)
+static void memzero_page(struct page *page, size_t offset, size_t len)
+{
+	char *addr = kmap_atomic(page);
+	memset(addr + offset, 0, len);
+	kunmap_atomic(addr);
+}
+
+static size_t copy_to_iter_bvec(void *from, size_t bytes, struct iov_iter *i)
 {
 	size_t skip, copy, wanted;
 	const struct bio_vec *bvec;
-	void *kaddr, *from;
 
 	if (unlikely(bytes > i->count))
 		bytes = i->count;
@@ -432,8 +571,6 @@ static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t by
 	skip = i->iov_offset;
 	copy = min_t(size_t, bytes, bvec->bv_len - skip);
 
-	kaddr = kmap_atomic(page);
-	from = kaddr + offset;
 	memcpy_to_page(bvec->bv_page, skip + bvec->bv_offset, from, copy);
 	skip += copy;
 	from += copy;
@@ -446,7 +583,6 @@ static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t by
 		from += copy;
 		bytes -= copy;
 	}
-	kunmap_atomic(kaddr);
 	if (skip == bvec->bv_len) {
 		bvec++;
 		skip = 0;
@@ -458,12 +594,10 @@ static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t by
 	return wanted - bytes;
 }
 
-static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t bytes,
-			 struct iov_iter *i)
+static size_t copy_from_iter_bvec(void *to, size_t bytes, struct iov_iter *i)
 {
 	size_t skip, copy, wanted;
 	const struct bio_vec *bvec;
-	void *kaddr, *to;
 
 	if (unlikely(bytes > i->count))
 		bytes = i->count;
@@ -475,10 +609,6 @@ static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t
 	bvec = i->bvec;
 	skip = i->iov_offset;
 
-	kaddr = kmap_atomic(page);
-
-	to = kaddr + offset;
-
 	copy = min(bytes, bvec->bv_len - skip);
 
 	memcpy_from_page(to, bvec->bv_page, bvec->bv_offset + skip, copy);
@@ -495,7 +625,6 @@ static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t
 		to += copy;
 		bytes -= copy;
 	}
-	kunmap_atomic(kaddr);
 	if (skip == bvec->bv_len) {
 		bvec++;
 		skip = 0;
@@ -507,6 +636,61 @@ static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t
 	return wanted;
 }
 
+static size_t copy_page_to_iter_bvec(struct page *page, size_t offset,
+					size_t bytes, struct iov_iter *i)
+{
+	void *kaddr = kmap_atomic(page);
+	size_t wanted = copy_to_iter_bvec(kaddr + offset, bytes, i);
+	kunmap_atomic(kaddr);
+	return wanted;
+}
+
+static size_t copy_page_from_iter_bvec(struct page *page, size_t offset,
+					size_t bytes, struct iov_iter *i)
+{
+	void *kaddr = kmap_atomic(page);
+	size_t wanted = copy_from_iter_bvec(kaddr + offset, bytes, i);
+	kunmap_atomic(kaddr);
+	return wanted;
+}
+
+static size_t zero_bvec(size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, wanted;
+	const struct bio_vec *bvec;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	bvec = i->bvec;
+	skip = i->iov_offset;
+	copy = min_t(size_t, bytes, bvec->bv_len - skip);
+
+	memzero_page(bvec->bv_page, skip + bvec->bv_offset, copy);
+	skip += copy;
+	bytes -= copy;
+	while (bytes) {
+		bvec++;
+		copy = min(bytes, (size_t)bvec->bv_len);
+		memzero_page(bvec->bv_page, bvec->bv_offset, copy);
+		skip = copy;
+		bytes -= copy;
+	}
+	if (skip == bvec->bv_len) {
+		bvec++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= bvec - i->bvec;
+	i->bvec = bvec;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
 static size_t copy_from_user_bvec(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes)
 {
@@ -672,6 +856,34 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 }
 EXPORT_SYMBOL(copy_page_from_iter);
 
+size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_to_iter_bvec(addr, bytes, i);
+	else
+		return copy_to_iter_iovec(addr, bytes, i);
+}
+EXPORT_SYMBOL(copy_to_iter);
+
+size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_from_iter_bvec(addr, bytes, i);
+	else
+		return copy_from_iter_iovec(addr, bytes, i);
+}
+EXPORT_SYMBOL(copy_from_iter);
+
+size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC) {
+		return zero_bvec(bytes, i);
+	} else {
+		return zero_iovec(bytes, i);
+	}
+}
+EXPORT_SYMBOL(iov_iter_zero);
+
 size_t iov_iter_copy_from_user_atomic(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes)
 {
-- 
cgit v1.2.3


From 5e6123f3477e4260fb14392f0a88f1a842fa4d42 Mon Sep 17 00:00:00 2001
From: Seunghun Lee <waydi1@gmail.com>
Date: Sun, 14 Sep 2014 22:15:10 +0900
Subject: vfs: move getname() from callers to do_mount()

It would make more sense to pass char __user * instead of
char * in callers of do_mount() and do getname() inside do_mount().

Suggested-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Seunghun Lee <waydi1@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/kernel/osf_sys.c | 23 ++++++++++-------------
 fs/compat.c                 | 20 ++++++--------------
 fs/namespace.c              | 19 +++----------------
 include/linux/fs.h          |  3 ++-
 4 files changed, 21 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 1402fcc11c2c..f9c732e18284 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -446,7 +446,8 @@ struct procfs_args {
  * unhappy with OSF UFS. [CHECKME]
  */
 static int
-osf_ufs_mount(const char *dirname, struct ufs_args __user *args, int flags)
+osf_ufs_mount(const char __user *dirname,
+	      struct ufs_args __user *args, int flags)
 {
 	int retval;
 	struct cdfs_args tmp;
@@ -466,7 +467,8 @@ osf_ufs_mount(const char *dirname, struct ufs_args __user *args, int flags)
 }
 
 static int
-osf_cdfs_mount(const char *dirname, struct cdfs_args __user *args, int flags)
+osf_cdfs_mount(const char __user *dirname,
+	       struct cdfs_args __user *args, int flags)
 {
 	int retval;
 	struct cdfs_args tmp;
@@ -486,7 +488,8 @@ osf_cdfs_mount(const char *dirname, struct cdfs_args __user *args, int flags)
 }
 
 static int
-osf_procfs_mount(const char *dirname, struct procfs_args __user *args, int flags)
+osf_procfs_mount(const char __user *dirname,
+		 struct procfs_args __user *args, int flags)
 {
 	struct procfs_args tmp;
 
@@ -500,28 +503,22 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path,
 		int, flag, void __user *, data)
 {
 	int retval;
-	struct filename *name;
 
-	name = getname(path);
-	retval = PTR_ERR(name);
-	if (IS_ERR(name))
-		goto out;
 	switch (typenr) {
 	case 1:
-		retval = osf_ufs_mount(name->name, data, flag);
+		retval = osf_ufs_mount(path, data, flag);
 		break;
 	case 6:
-		retval = osf_cdfs_mount(name->name, data, flag);
+		retval = osf_cdfs_mount(path, data, flag);
 		break;
 	case 9:
-		retval = osf_procfs_mount(name->name, data, flag);
+		retval = osf_procfs_mount(path, data, flag);
 		break;
 	default:
 		retval = -EINVAL;
 		printk("osf_mount(%ld, %x)\n", typenr, flag);
 	}
-	putname(name);
- out:
+
 	return retval;
 }
 
diff --git a/fs/compat.c b/fs/compat.c
index 6205c247a6e3..b13df99f3534 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -794,7 +794,6 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
 	char *kernel_type;
 	unsigned long data_page;
 	char *kernel_dev;
-	struct filename *dir;
 	int retval;
 
 	kernel_type = copy_mount_string(type);
@@ -802,19 +801,14 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
 	if (IS_ERR(kernel_type))
 		goto out;
 
-	dir = getname(dir_name);
-	retval = PTR_ERR(dir);
-	if (IS_ERR(dir))
-		goto out1;
-
 	kernel_dev = copy_mount_string(dev_name);
 	retval = PTR_ERR(kernel_dev);
 	if (IS_ERR(kernel_dev))
-		goto out2;
+		goto out1;
 
 	retval = copy_mount_options(data, &data_page);
 	if (retval < 0)
-		goto out3;
+		goto out2;
 
 	retval = -EINVAL;
 
@@ -823,19 +817,17 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
 			do_ncp_super_data_conv((void *)data_page);
 		} else if (!strcmp(kernel_type, NFS4_NAME)) {
 			if (do_nfs4_super_data_conv((void *) data_page))
-				goto out4;
+				goto out3;
 		}
 	}
 
-	retval = do_mount(kernel_dev, dir->name, kernel_type,
+	retval = do_mount(kernel_dev, dir_name, kernel_type,
 			flags, (void*)data_page);
 
- out4:
-	free_page(data_page);
  out3:
-	kfree(kernel_dev);
+	free_page(data_page);
  out2:
-	putname(dir);
+	kfree(kernel_dev);
  out1:
 	kfree(kernel_type);
  out:
diff --git a/fs/namespace.c b/fs/namespace.c
index abd3abb52616..348562f14e93 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2533,7 +2533,7 @@ char *copy_mount_string(const void __user *data)
  * Therefore, if this magic number is present, it carries no information
  * and must be discarded.
  */
-long do_mount(const char *dev_name, const char *dir_name,
+long do_mount(const char *dev_name, const char __user *dir_name,
 		const char *type_page, unsigned long flags, void *data_page)
 {
 	struct path path;
@@ -2545,15 +2545,11 @@ long do_mount(const char *dev_name, const char *dir_name,
 		flags &= ~MS_MGC_MSK;
 
 	/* Basic sanity checks */
-
-	if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))
-		return -EINVAL;
-
 	if (data_page)
 		((char *)data_page)[PAGE_SIZE - 1] = 0;
 
 	/* ... and get the mountpoint */
-	retval = kern_path(dir_name, LOOKUP_FOLLOW, &path);
+	retval = user_path(dir_name, &path);
 	if (retval)
 		return retval;
 
@@ -2778,7 +2774,6 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 {
 	int ret;
 	char *kernel_type;
-	struct filename *kernel_dir;
 	char *kernel_dev;
 	unsigned long data_page;
 
@@ -2787,12 +2782,6 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	if (IS_ERR(kernel_type))
 		goto out_type;
 
-	kernel_dir = getname(dir_name);
-	if (IS_ERR(kernel_dir)) {
-		ret = PTR_ERR(kernel_dir);
-		goto out_dir;
-	}
-
 	kernel_dev = copy_mount_string(dev_name);
 	ret = PTR_ERR(kernel_dev);
 	if (IS_ERR(kernel_dev))
@@ -2802,15 +2791,13 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	if (ret < 0)
 		goto out_data;
 
-	ret = do_mount(kernel_dev, kernel_dir->name, kernel_type, flags,
+	ret = do_mount(kernel_dev, dir_name, kernel_type, flags,
 		(void *) data_page);
 
 	free_page(data_page);
 out_data:
 	kfree(kernel_dev);
 out_dev:
-	putname(kernel_dir);
-out_dir:
 	kfree(kernel_type);
 out_type:
 	return ret;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 75bdd51ec9b8..92148361bef8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1855,7 +1855,8 @@ extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
 extern void kern_unmount(struct vfsmount *mnt);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
-extern long do_mount(const char *, const char *, const char *, unsigned long, void *);
+extern long do_mount(const char *, const char __user *,
+		     const char *, unsigned long, void *);
 extern struct vfsmount *collect_mounts(struct path *);
 extern void drop_collected_mounts(struct vfsmount *);
 extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
-- 
cgit v1.2.3


From fd22f78cf7b95102d8e5b988afe27165e47471fc Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagig@mellanox.com>
Date: Wed, 13 Aug 2014 19:54:29 +0300
Subject: IB/mlx5: Use enumerations for PI copy mask

In case input and output space parameters match, we can use a copy
mask from input and output space.  Use enums for those.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 6 +++---
 include/linux/mlx5/qp.h         | 3 +++
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 8c574b63d77b..554410c2655d 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -2095,11 +2095,11 @@ static int mlx5_set_bsf(struct ib_mr *sig_mr,
 			/* Same block structure */
 			basic->bsf_size_sbs = 1 << 4;
 			if (mem->sig.dif.bg_type == wire->sig.dif.bg_type)
-				basic->wire.copy_byte_mask |= 0xc0;
+				basic->wire.copy_byte_mask |= MLX5_CPY_GRD_MASK;
 			if (mem->sig.dif.app_tag == wire->sig.dif.app_tag)
-				basic->wire.copy_byte_mask |= 0x30;
+				basic->wire.copy_byte_mask |= MLX5_CPY_APP_MASK;
 			if (mem->sig.dif.ref_tag == wire->sig.dif.ref_tag)
-				basic->wire.copy_byte_mask |= 0x0f;
+				basic->wire.copy_byte_mask |= MLX5_CPY_REF_MASK;
 		} else
 			basic->wire.bs_selector = bs_selector(wire->sig.dif.pi_interval);
 
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 9709b30e2d69..4aa5634dc210 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -40,6 +40,9 @@
 #define MLX5_SIG_WQE_SIZE	(MLX5_SEND_WQE_BB * 5)
 #define MLX5_DIF_SIZE		8
 #define MLX5_STRIDE_BLOCK_OP	0x400
+#define MLX5_CPY_GRD_MASK	0xc0
+#define MLX5_CPY_APP_MASK	0x30
+#define MLX5_CPY_REF_MASK	0x0f
 
 enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_ALT_ADDR_PATH		= 1 << 0,
-- 
cgit v1.2.3


From 142537f4e5f7ffd3e34b0c46646ac9cb5d986d06 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagig@mellanox.com>
Date: Wed, 13 Aug 2014 19:54:32 +0300
Subject: IB/mlx5: Use extended internal signature layout

Rather than using the basic BSF layout which utilizes a pre-configured
signature settings (sufficient for current DIF implementation), we use
the extended BSF layout to expose advanced signature settings. These
settings will also be exposed to the user later.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 80 +++++++++++++++++++----------------------
 include/linux/mlx5/qp.h         | 32 ++++++++++++-----
 2 files changed, 61 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 554410c2655d..13924a256290 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -2020,53 +2020,47 @@ static u8 bs_selector(int block_size)
 	}
 }
 
-static int format_selector(struct ib_sig_attrs *attr,
-			   struct ib_sig_domain *domain,
-			   int *selector)
+static int mlx5_fill_inl_bsf(struct ib_sig_domain *domain,
+			     struct mlx5_bsf_inl *inl)
 {
-
-#define FORMAT_DIF_NONE		0
-#define FORMAT_DIF_CRC_INC	8
-#define FORMAT_DIF_CRC_NO_INC	12
-#define FORMAT_DIF_CSUM_INC	13
-#define FORMAT_DIF_CSUM_NO_INC	14
+	/* Valid inline section and allow BSF refresh */
+	inl->vld_refresh = cpu_to_be16(MLX5_BSF_INL_VALID |
+				       MLX5_BSF_REFRESH_DIF);
+	inl->dif_apptag = cpu_to_be16(domain->sig.dif.app_tag);
+	inl->dif_reftag = cpu_to_be32(domain->sig.dif.ref_tag);
 
 	switch (domain->sig.dif.type) {
 	case IB_T10DIF_NONE:
 		/* No DIF */
-		*selector = FORMAT_DIF_NONE;
 		break;
 	case IB_T10DIF_TYPE1: /* Fall through */
 	case IB_T10DIF_TYPE2:
-		switch (domain->sig.dif.bg_type) {
-		case IB_T10DIF_CRC:
-			*selector = FORMAT_DIF_CRC_INC;
-			break;
-		case IB_T10DIF_CSUM:
-			*selector = FORMAT_DIF_CSUM_INC;
-			break;
-		default:
-			return 1;
-		}
+		inl->sig_type = domain->sig.dif.bg_type == IB_T10DIF_CRC ?
+				MLX5_DIF_CRC : MLX5_DIF_IPCS;
+		/*
+		 * increment reftag and don't check if
+		 * apptag=0xffff and reftag=0xffffffff
+		 */
+		inl->dif_inc_ref_guard_check = MLX5_BSF_INC_REFTAG |
+					       MLX5_BSF_APPREF_ESCAPE;
+		inl->dif_app_bitmask_check = 0xffff;
+		/* repeating block */
+		inl->rp_inv_seed = MLX5_BSF_REPEAT_BLOCK;
 		break;
 	case IB_T10DIF_TYPE3:
-		switch (domain->sig.dif.bg_type) {
-		case IB_T10DIF_CRC:
-			*selector = domain->sig.dif.type3_inc_reftag ?
-					   FORMAT_DIF_CRC_INC :
-					   FORMAT_DIF_CRC_NO_INC;
-			break;
-		case IB_T10DIF_CSUM:
-			*selector = domain->sig.dif.type3_inc_reftag ?
-					   FORMAT_DIF_CSUM_INC :
-					   FORMAT_DIF_CSUM_NO_INC;
-			break;
-		default:
-			return 1;
-		}
+		inl->sig_type = domain->sig.dif.bg_type == IB_T10DIF_CRC ?
+				MLX5_DIF_CRC : MLX5_DIF_IPCS;
+		/*
+		 * Don't inc reftag and don't check if
+		 * apptag=0xffff and reftag=0xffffffff
+		 */
+		inl->dif_inc_ref_guard_check = MLX5_BSF_APPREF_ESCAPE;
+		inl->dif_app_bitmask_check = 0xffff;
+		/* Repeating block */
+		inl->rp_inv_seed = MLX5_BSF_REPEAT_BLOCK;
 		break;
 	default:
-		return 1;
+		return -EINVAL;
 	}
 
 	return 0;
@@ -2080,7 +2074,7 @@ static int mlx5_set_bsf(struct ib_mr *sig_mr,
 	struct mlx5_bsf_basic *basic = &bsf->basic;
 	struct ib_sig_domain *mem = &sig_attrs->mem;
 	struct ib_sig_domain *wire = &sig_attrs->wire;
-	int ret, selector;
+	int ret;
 
 	memset(bsf, 0, sizeof(*bsf));
 	switch (sig_attrs->mem.sig_type) {
@@ -2088,12 +2082,14 @@ static int mlx5_set_bsf(struct ib_mr *sig_mr,
 		if (sig_attrs->wire.sig_type != IB_SIG_TYPE_T10_DIF)
 			return -EINVAL;
 
+		/* Basic + Extended + Inline */
+		basic->bsf_size_sbs = 1 << 7;
 		/* Input domain check byte mask */
 		basic->check_byte_mask = sig_attrs->check_mask;
 		if (mem->sig.dif.pi_interval == wire->sig.dif.pi_interval &&
 		    mem->sig.dif.type == wire->sig.dif.type) {
 			/* Same block structure */
-			basic->bsf_size_sbs = 1 << 4;
+			basic->bsf_size_sbs |= 1 << 4;
 			if (mem->sig.dif.bg_type == wire->sig.dif.bg_type)
 				basic->wire.copy_byte_mask |= MLX5_CPY_GRD_MASK;
 			if (mem->sig.dif.app_tag == wire->sig.dif.app_tag)
@@ -2105,18 +2101,16 @@ static int mlx5_set_bsf(struct ib_mr *sig_mr,
 
 		basic->mem.bs_selector = bs_selector(mem->sig.dif.pi_interval);
 		basic->raw_data_size = cpu_to_be32(data_size);
+		basic->m_bfs_psv = cpu_to_be32(msig->psv_memory.psv_idx);
+		basic->w_bfs_psv = cpu_to_be32(msig->psv_wire.psv_idx);
 
-		ret = format_selector(sig_attrs, mem, &selector);
+		ret = mlx5_fill_inl_bsf(wire, &bsf->w_inl);
 		if (ret)
 			return -EINVAL;
-		basic->m_bfs_psv = cpu_to_be32(selector << 24 |
-					       msig->psv_memory.psv_idx);
 
-		ret = format_selector(sig_attrs, wire, &selector);
+		ret = mlx5_fill_inl_bsf(mem, &bsf->m_inl);
 		if (ret)
 			return -EINVAL;
-		basic->w_bfs_psv = cpu_to_be32(selector << 24 |
-					       msig->psv_wire.psv_idx);
 		break;
 
 	default:
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 4aa5634dc210..69f5378455b7 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -43,6 +43,12 @@
 #define MLX5_CPY_GRD_MASK	0xc0
 #define MLX5_CPY_APP_MASK	0x30
 #define MLX5_CPY_REF_MASK	0x0f
+#define MLX5_BSF_INC_REFTAG	(1 << 6)
+#define MLX5_BSF_INL_VALID	(1 << 15)
+#define MLX5_BSF_REFRESH_DIF	(1 << 14)
+#define MLX5_BSF_REPEAT_BLOCK	(1 << 7)
+#define MLX5_BSF_APPTAG_ESCAPE	0x1
+#define MLX5_BSF_APPREF_ESCAPE	0x2
 
 enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_ALT_ADDR_PATH		= 1 << 0,
@@ -290,6 +296,22 @@ struct mlx5_wqe_inline_seg {
 	__be32	byte_count;
 };
 
+enum mlx5_sig_type {
+	MLX5_DIF_CRC = 0x1,
+	MLX5_DIF_IPCS = 0x2,
+};
+
+struct mlx5_bsf_inl {
+	__be16		vld_refresh;
+	__be16		dif_apptag;
+	__be32		dif_reftag;
+	u8		sig_type;
+	u8		rp_inv_seed;
+	u8		rsvd[3];
+	u8		dif_inc_ref_guard_check;
+	__be16		dif_app_bitmask_check;
+};
+
 struct mlx5_bsf {
 	struct mlx5_bsf_basic {
 		u8		bsf_size_sbs;
@@ -313,14 +335,8 @@ struct mlx5_bsf {
 		__be32		w_tfs_psv;
 		__be32		m_tfs_psv;
 	} ext;
-	struct mlx5_bsf_inl {
-		__be32		w_inl_vld;
-		__be32		w_rsvd;
-		__be64		w_block_format;
-		__be32		m_inl_vld;
-		__be32		m_rsvd;
-		__be64		m_block_format;
-	} inl;
+	struct mlx5_bsf_inl	w_inl;
+	struct mlx5_bsf_inl	m_inl;
 };
 
 struct mlx5_klm {
-- 
cgit v1.2.3


From 78eda2bb6542057b214af3bc1cae09c63e65d1d1 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagig@mellanox.com>
Date: Wed, 13 Aug 2014 19:54:35 +0300
Subject: IB/mlx5, iser, isert: Add Signature API additions

Expose more signature setting parameters. We modify the signature API
to allow usage of some new execution parameters relevant to data
integrity feature.

This patch modifies ib_sig_domain structure by:

- Deprecate DIF type in signature API (operation will
  be determined by the parameters alone, no DIF type awareness)
- Add APPTAG check bitmask (for input domain)
- Add REFTAG remap (increment) flag for each domain
- Add APPTAG/REFTAG escape options for each domain

The mlx5 driver is modified to follow the new parameters in HW
signature setup.

At the moment the callers (iser/isert) hard-code new parameters (by
DIF type). In the future, callers will retrieve them from the scsi
command structure.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/qp.c           | 104 +++++++++++++-----------------
 drivers/infiniband/ulp/iser/iser_memory.c |  50 +++++++-------
 drivers/infiniband/ulp/isert/ib_isert.c   |  40 ++++--------
 include/rdma/ib_verbs.h                   |  32 ++++-----
 4 files changed, 97 insertions(+), 129 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 13924a256290..d7f35e9e6522 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -2020,50 +2020,31 @@ static u8 bs_selector(int block_size)
 	}
 }
 
-static int mlx5_fill_inl_bsf(struct ib_sig_domain *domain,
-			     struct mlx5_bsf_inl *inl)
+static void mlx5_fill_inl_bsf(struct ib_sig_domain *domain,
+			      struct mlx5_bsf_inl *inl)
 {
 	/* Valid inline section and allow BSF refresh */
 	inl->vld_refresh = cpu_to_be16(MLX5_BSF_INL_VALID |
 				       MLX5_BSF_REFRESH_DIF);
 	inl->dif_apptag = cpu_to_be16(domain->sig.dif.app_tag);
 	inl->dif_reftag = cpu_to_be32(domain->sig.dif.ref_tag);
+	/* repeating block */
+	inl->rp_inv_seed = MLX5_BSF_REPEAT_BLOCK;
+	inl->sig_type = domain->sig.dif.bg_type == IB_T10DIF_CRC ?
+			MLX5_DIF_CRC : MLX5_DIF_IPCS;
 
-	switch (domain->sig.dif.type) {
-	case IB_T10DIF_NONE:
-		/* No DIF */
-		break;
-	case IB_T10DIF_TYPE1: /* Fall through */
-	case IB_T10DIF_TYPE2:
-		inl->sig_type = domain->sig.dif.bg_type == IB_T10DIF_CRC ?
-				MLX5_DIF_CRC : MLX5_DIF_IPCS;
-		/*
-		 * increment reftag and don't check if
-		 * apptag=0xffff and reftag=0xffffffff
-		 */
-		inl->dif_inc_ref_guard_check = MLX5_BSF_INC_REFTAG |
-					       MLX5_BSF_APPREF_ESCAPE;
-		inl->dif_app_bitmask_check = 0xffff;
-		/* repeating block */
-		inl->rp_inv_seed = MLX5_BSF_REPEAT_BLOCK;
-		break;
-	case IB_T10DIF_TYPE3:
-		inl->sig_type = domain->sig.dif.bg_type == IB_T10DIF_CRC ?
-				MLX5_DIF_CRC : MLX5_DIF_IPCS;
-		/*
-		 * Don't inc reftag and don't check if
-		 * apptag=0xffff and reftag=0xffffffff
-		 */
-		inl->dif_inc_ref_guard_check = MLX5_BSF_APPREF_ESCAPE;
-		inl->dif_app_bitmask_check = 0xffff;
-		/* Repeating block */
-		inl->rp_inv_seed = MLX5_BSF_REPEAT_BLOCK;
-		break;
-	default:
-		return -EINVAL;
+	if (domain->sig.dif.ref_remap)
+		inl->dif_inc_ref_guard_check |= MLX5_BSF_INC_REFTAG;
+
+	if (domain->sig.dif.app_escape) {
+		if (domain->sig.dif.ref_escape)
+			inl->dif_inc_ref_guard_check |= MLX5_BSF_APPREF_ESCAPE;
+		else
+			inl->dif_inc_ref_guard_check |= MLX5_BSF_APPTAG_ESCAPE;
 	}
 
-	return 0;
+	inl->dif_app_bitmask_check =
+		cpu_to_be16(domain->sig.dif.apptag_check_mask);
 }
 
 static int mlx5_set_bsf(struct ib_mr *sig_mr,
@@ -2074,20 +2055,35 @@ static int mlx5_set_bsf(struct ib_mr *sig_mr,
 	struct mlx5_bsf_basic *basic = &bsf->basic;
 	struct ib_sig_domain *mem = &sig_attrs->mem;
 	struct ib_sig_domain *wire = &sig_attrs->wire;
-	int ret;
 
 	memset(bsf, 0, sizeof(*bsf));
+
+	/* Basic + Extended + Inline */
+	basic->bsf_size_sbs = 1 << 7;
+	/* Input domain check byte mask */
+	basic->check_byte_mask = sig_attrs->check_mask;
+	basic->raw_data_size = cpu_to_be32(data_size);
+
+	/* Memory domain */
 	switch (sig_attrs->mem.sig_type) {
+	case IB_SIG_TYPE_NONE:
+		break;
 	case IB_SIG_TYPE_T10_DIF:
-		if (sig_attrs->wire.sig_type != IB_SIG_TYPE_T10_DIF)
-			return -EINVAL;
+		basic->mem.bs_selector = bs_selector(mem->sig.dif.pi_interval);
+		basic->m_bfs_psv = cpu_to_be32(msig->psv_memory.psv_idx);
+		mlx5_fill_inl_bsf(mem, &bsf->m_inl);
+		break;
+	default:
+		return -EINVAL;
+	}
 
-		/* Basic + Extended + Inline */
-		basic->bsf_size_sbs = 1 << 7;
-		/* Input domain check byte mask */
-		basic->check_byte_mask = sig_attrs->check_mask;
+	/* Wire domain */
+	switch (sig_attrs->wire.sig_type) {
+	case IB_SIG_TYPE_NONE:
+		break;
+	case IB_SIG_TYPE_T10_DIF:
 		if (mem->sig.dif.pi_interval == wire->sig.dif.pi_interval &&
-		    mem->sig.dif.type == wire->sig.dif.type) {
+		    mem->sig_type == wire->sig_type) {
 			/* Same block structure */
 			basic->bsf_size_sbs |= 1 << 4;
 			if (mem->sig.dif.bg_type == wire->sig.dif.bg_type)
@@ -2099,20 +2095,9 @@ static int mlx5_set_bsf(struct ib_mr *sig_mr,
 		} else
 			basic->wire.bs_selector = bs_selector(wire->sig.dif.pi_interval);
 
-		basic->mem.bs_selector = bs_selector(mem->sig.dif.pi_interval);
-		basic->raw_data_size = cpu_to_be32(data_size);
-		basic->m_bfs_psv = cpu_to_be32(msig->psv_memory.psv_idx);
 		basic->w_bfs_psv = cpu_to_be32(msig->psv_wire.psv_idx);
-
-		ret = mlx5_fill_inl_bsf(wire, &bsf->w_inl);
-		if (ret)
-			return -EINVAL;
-
-		ret = mlx5_fill_inl_bsf(mem, &bsf->m_inl);
-		if (ret)
-			return -EINVAL;
+		mlx5_fill_inl_bsf(wire, &bsf->w_inl);
 		break;
-
 	default:
 		return -EINVAL;
 	}
@@ -2311,20 +2296,21 @@ static int set_psv_wr(struct ib_sig_domain *domain,
 	memset(psv_seg, 0, sizeof(*psv_seg));
 	psv_seg->psv_num = cpu_to_be32(psv_idx);
 	switch (domain->sig_type) {
+	case IB_SIG_TYPE_NONE:
+		break;
 	case IB_SIG_TYPE_T10_DIF:
 		psv_seg->transient_sig = cpu_to_be32(domain->sig.dif.bg << 16 |
 						     domain->sig.dif.app_tag);
 		psv_seg->ref_tag = cpu_to_be32(domain->sig.dif.ref_tag);
-
-		*seg += sizeof(*psv_seg);
-		*size += sizeof(*psv_seg) / 16;
 		break;
-
 	default:
 		pr_err("Bad signature type given.\n");
 		return 1;
 	}
 
+	*seg += sizeof(*psv_seg);
+	*size += sizeof(*psv_seg) / 16;
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index d9ed6234c505..6c5ce357fba6 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -440,51 +440,44 @@ int iser_reg_rdma_mem_fmr(struct iscsi_iser_task *iser_task,
 	return 0;
 }
 
-static inline enum ib_t10_dif_type
-scsi2ib_prot_type(unsigned char prot_type)
-{
-	switch (prot_type) {
-	case SCSI_PROT_DIF_TYPE0:
-		return IB_T10DIF_NONE;
-	case SCSI_PROT_DIF_TYPE1:
-		return IB_T10DIF_TYPE1;
-	case SCSI_PROT_DIF_TYPE2:
-		return IB_T10DIF_TYPE2;
-	case SCSI_PROT_DIF_TYPE3:
-		return IB_T10DIF_TYPE3;
-	default:
-		return IB_T10DIF_NONE;
-	}
-}
-
 static inline void
 iser_set_dif_domain(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs,
 		    struct ib_sig_domain *domain)
 {
-	unsigned char scsi_ptype = scsi_get_prot_type(sc);
-
-	domain->sig.dif.type = scsi2ib_prot_type(scsi_ptype);
+	domain->sig_type = IB_SIG_TYPE_T10_DIF;
 	domain->sig.dif.pi_interval = sc->device->sector_size;
 	domain->sig.dif.ref_tag = scsi_get_lba(sc) & 0xffffffff;
+	/*
+	 * At the moment we hard code those, but in the future
+	 * we will take them from sc.
+	 */
+	domain->sig.dif.apptag_check_mask = 0xffff;
+	domain->sig.dif.app_escape = true;
+	domain->sig.dif.ref_escape = true;
+	if (scsi_get_prot_type(sc) == SCSI_PROT_DIF_TYPE1 ||
+	    scsi_get_prot_type(sc) == SCSI_PROT_DIF_TYPE2)
+		domain->sig.dif.ref_remap = true;
 };
 
 static int
 iser_set_sig_attrs(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs)
 {
-	sig_attrs->mem.sig_type = IB_SIG_TYPE_T10_DIF;
-	sig_attrs->wire.sig_type = IB_SIG_TYPE_T10_DIF;
-
 	switch (scsi_get_prot_op(sc)) {
 	case SCSI_PROT_WRITE_INSERT:
 	case SCSI_PROT_READ_STRIP:
-		sig_attrs->mem.sig.dif.type = IB_T10DIF_NONE;
+		sig_attrs->mem.sig_type = IB_SIG_TYPE_NONE;
 		iser_set_dif_domain(sc, sig_attrs, &sig_attrs->wire);
 		sig_attrs->wire.sig.dif.bg_type = IB_T10DIF_CRC;
 		break;
 	case SCSI_PROT_READ_INSERT:
 	case SCSI_PROT_WRITE_STRIP:
-		sig_attrs->wire.sig.dif.type = IB_T10DIF_NONE;
+		sig_attrs->wire.sig_type = IB_SIG_TYPE_NONE;
 		iser_set_dif_domain(sc, sig_attrs, &sig_attrs->mem);
+		/*
+		 * At the moment we use this modparam to tell what is
+		 * the memory bg_type, in the future we will take it
+		 * from sc.
+		 */
 		sig_attrs->mem.sig.dif.bg_type = iser_pi_guard ? IB_T10DIF_CSUM :
 						 IB_T10DIF_CRC;
 		break;
@@ -493,6 +486,11 @@ iser_set_sig_attrs(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs)
 		iser_set_dif_domain(sc, sig_attrs, &sig_attrs->wire);
 		sig_attrs->wire.sig.dif.bg_type = IB_T10DIF_CRC;
 		iser_set_dif_domain(sc, sig_attrs, &sig_attrs->mem);
+		/*
+		 * At the moment we use this modparam to tell what is
+		 * the memory bg_type, in the future we will take it
+		 * from sc.
+		 */
 		sig_attrs->mem.sig.dif.bg_type = iser_pi_guard ? IB_T10DIF_CSUM :
 						 IB_T10DIF_CRC;
 		break;
@@ -501,10 +499,10 @@ iser_set_sig_attrs(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs)
 			 scsi_get_prot_op(sc));
 		return -EINVAL;
 	}
+
 	return 0;
 }
 
-
 static int
 iser_set_prot_checks(struct scsi_cmnd *sc, u8 *mask)
 {
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 73092756460b..0bea5776bcbc 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -2609,51 +2609,39 @@ isert_fast_reg_mr(struct isert_conn *isert_conn,
 	return ret;
 }
 
-static inline enum ib_t10_dif_type
-se2ib_prot_type(enum target_prot_type prot_type)
-{
-	switch (prot_type) {
-	case TARGET_DIF_TYPE0_PROT:
-		return IB_T10DIF_NONE;
-	case TARGET_DIF_TYPE1_PROT:
-		return IB_T10DIF_TYPE1;
-	case TARGET_DIF_TYPE2_PROT:
-		return IB_T10DIF_TYPE2;
-	case TARGET_DIF_TYPE3_PROT:
-		return IB_T10DIF_TYPE3;
-	default:
-		return IB_T10DIF_NONE;
-	}
-}
-
 static inline void
 isert_set_dif_domain(struct se_cmd *se_cmd, struct ib_sig_attrs *sig_attrs,
 		     struct ib_sig_domain *domain)
 {
-	enum ib_t10_dif_type ib_prot_type = se2ib_prot_type(se_cmd->prot_type);
-
-	domain->sig.dif.type = ib_prot_type;
+	domain->sig_type = IB_SIG_TYPE_T10_DIF;
 	domain->sig.dif.bg_type = IB_T10DIF_CRC;
 	domain->sig.dif.pi_interval = se_cmd->se_dev->dev_attrib.block_size;
 	domain->sig.dif.ref_tag = se_cmd->reftag_seed;
+	/*
+	 * At the moment we hard code those, but if in the future
+	 * the target core would like to use it, we will take it
+	 * from se_cmd.
+	 */
+	domain->sig.dif.apptag_check_mask = 0xffff;
+	domain->sig.dif.app_escape = true;
+	domain->sig.dif.ref_escape = true;
+	if (se_cmd->prot_type == TARGET_DIF_TYPE1_PROT ||
+	    se_cmd->prot_type == TARGET_DIF_TYPE2_PROT)
+		domain->sig.dif.ref_remap = true;
 };
 
 static int
 isert_set_sig_attrs(struct se_cmd *se_cmd, struct ib_sig_attrs *sig_attrs)
 {
-
-	sig_attrs->mem.sig_type = IB_SIG_TYPE_T10_DIF;
-	sig_attrs->wire.sig_type = IB_SIG_TYPE_T10_DIF;
-
 	switch (se_cmd->prot_op) {
 	case TARGET_PROT_DIN_INSERT:
 	case TARGET_PROT_DOUT_STRIP:
-		sig_attrs->mem.sig.dif.type = IB_T10DIF_NONE;
+		sig_attrs->mem.sig_type = IB_SIG_TYPE_NONE;
 		isert_set_dif_domain(se_cmd, sig_attrs, &sig_attrs->wire);
 		break;
 	case TARGET_PROT_DOUT_INSERT:
 	case TARGET_PROT_DIN_STRIP:
-		sig_attrs->wire.sig.dif.type = IB_T10DIF_NONE;
+		sig_attrs->wire.sig_type = IB_SIG_TYPE_NONE;
 		isert_set_dif_domain(se_cmd, sig_attrs, &sig_attrs->mem);
 		break;
 	case TARGET_PROT_DIN_PASS:
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index ed44cc07a7b3..470a011d6fa4 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -491,20 +491,14 @@ struct ib_mr_init_attr {
 	u32	    flags;
 };
 
-enum ib_signature_type {
-	IB_SIG_TYPE_T10_DIF,
-};
-
 /**
- * T10-DIF Signature types
- * T10-DIF types are defined by SCSI
- * specifications.
+ * Signature types
+ * IB_SIG_TYPE_NONE: Unprotected.
+ * IB_SIG_TYPE_T10_DIF: Type T10-DIF
  */
-enum ib_t10_dif_type {
-	IB_T10DIF_NONE,
-	IB_T10DIF_TYPE1,
-	IB_T10DIF_TYPE2,
-	IB_T10DIF_TYPE3
+enum ib_signature_type {
+	IB_SIG_TYPE_NONE,
+	IB_SIG_TYPE_T10_DIF,
 };
 
 /**
@@ -520,24 +514,26 @@ enum ib_t10_dif_bg_type {
 /**
  * struct ib_t10_dif_domain - Parameters specific for T10-DIF
  *     domain.
- * @type: T10-DIF type (0|1|2|3)
  * @bg_type: T10-DIF block guard type (CRC|CSUM)
  * @pi_interval: protection information interval.
  * @bg: seed of guard computation.
  * @app_tag: application tag of guard block
  * @ref_tag: initial guard block reference tag.
- * @type3_inc_reftag: T10-DIF type 3 does not state
- *     about the reference tag, it is the user
- *     choice to increment it or not.
+ * @ref_remap: Indicate wethear the reftag increments each block
+ * @app_escape: Indicate to skip block check if apptag=0xffff
+ * @ref_escape: Indicate to skip block check if reftag=0xffffffff
+ * @apptag_check_mask: check bitmask of application tag.
  */
 struct ib_t10_dif_domain {
-	enum ib_t10_dif_type	type;
 	enum ib_t10_dif_bg_type bg_type;
 	u16			pi_interval;
 	u16			bg;
 	u16			app_tag;
 	u32			ref_tag;
-	bool			type3_inc_reftag;
+	bool			ref_remap;
+	bool			app_escape;
+	bool			ref_escape;
+	u16			apptag_check_mask;
 };
 
 /**
-- 
cgit v1.2.3


From fe0f49768d807a8fe6336b097feb8c4441951710 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 30 Sep 2014 17:37:52 +0200
Subject: s390/nohz: use a per-cpu flag for arch_needs_cpu

Move the nohz_delay bit from the s390_idle data structure to the
per-cpu flags. Clear the nohz delay flag in __cpu_disable and
remove the cpu hotplug notifier that used to do this.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/cputime.h   |  8 --------
 arch/s390/include/asm/processor.h |  4 ++++
 arch/s390/kernel/irq.c            |  2 +-
 arch/s390/kernel/smp.c            |  1 +
 arch/s390/kernel/vtime.c          | 19 +------------------
 drivers/s390/cio/airq.c           |  2 +-
 drivers/s390/cio/cio.c            |  2 +-
 include/linux/tick.h              |  2 +-
 kernel/time/tick-sched.c          |  2 +-
 9 files changed, 11 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index f65bd3634519..01887b1fade5 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -166,7 +166,6 @@ static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
 }
 
 struct s390_idle_data {
-	int nohz_delay;
 	unsigned int sequence;
 	unsigned long long idle_count;
 	unsigned long long idle_time;
@@ -182,11 +181,4 @@ cputime64_t s390_get_idle_time(int cpu);
 
 #define arch_idle_time(cpu) s390_get_idle_time(cpu)
 
-static inline int s390_nohz_delay(int cpu)
-{
-	return __get_cpu_var(s390_idle).nohz_delay != 0;
-}
-
-#define arch_needs_cpu(cpu) s390_nohz_delay(cpu)
-
 #endif /* _S390_CPUTIME_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index e568fc8a7250..bc796d73129b 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -13,9 +13,11 @@
 
 #define CIF_MCCK_PENDING	0	/* machine check handling is pending */
 #define CIF_ASCE		1	/* user asce needs fixup / uaccess */
+#define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
 
 #define _CIF_MCCK_PENDING	(1<<CIF_MCCK_PENDING)
 #define _CIF_ASCE		(1<<CIF_ASCE)
+#define _CIF_NOHZ_DELAY		(1<<CIF_NOHZ_DELAY)
 
 
 #ifndef __ASSEMBLY__
@@ -43,6 +45,8 @@ static inline int test_cpu_flag(int flag)
 	return !!(S390_lowcore.cpu_flags & (1U << flag));
 }
 
+#define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)
+
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 051574ee5366..1b8a38ab7861 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -259,7 +259,7 @@ static irqreturn_t do_ext_interrupt(int irq, void *dummy)
 
 	ext_code = *(struct ext_code *) &regs->int_code;
 	if (ext_code.code != EXT_IRQ_CLK_COMP)
-		__get_cpu_var(s390_idle).nohz_delay = 1;
+		set_cpu_flag(CIF_NOHZ_DELAY);
 
 	index = ext_hash(ext_code.code);
 	rcu_read_lock();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index abec97b4ddbf..46317d6951c4 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -720,6 +720,7 @@ int __cpu_disable(void)
 	cregs[6]  &= ~0xff000000UL;	/* disable all I/O interrupts */
 	cregs[14] &= ~0x1f000000UL;	/* disable most machine checks */
 	__ctl_load(cregs, 0, 15);
+	clear_cpu_flag(CIF_NOHZ_DELAY);
 	return 0;
 }
 
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 8c34363d6f1e..40709821abde 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -163,7 +163,7 @@ void __kprobes vtime_stop_cpu(void)
 	/* Wait for external, I/O or machine check interrupt. */
 	psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT | PSW_MASK_DAT |
 		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-	idle->nohz_delay = 0;
+	clear_cpu_flag(CIF_NOHZ_DELAY);
 
 	/* Call the assembler magic in entry.S */
 	psw_idle(idle, psw_mask);
@@ -378,25 +378,8 @@ void init_cpu_vtimer(void)
 	set_vtimer(VTIMER_MAX_SLICE);
 }
 
-static int s390_nohz_notify(struct notifier_block *self, unsigned long action,
-			    void *hcpu)
-{
-	struct s390_idle_data *idle;
-	long cpu = (long) hcpu;
-
-	idle = &per_cpu(s390_idle, cpu);
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DYING:
-		idle->nohz_delay = 0;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
 void __init vtime_init(void)
 {
 	/* Enable cpu timer interrupts on the boot cpu. */
 	init_cpu_vtimer();
-	cpu_notifier(s390_nohz_notify, 0);
 }
diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c
index 00bfbee0af9e..56eb4ee4deba 100644
--- a/drivers/s390/cio/airq.c
+++ b/drivers/s390/cio/airq.c
@@ -87,7 +87,7 @@ static irqreturn_t do_airq_interrupt(int irq, void *dummy)
 	struct airq_struct *airq;
 	struct hlist_head *head;
 
-	__this_cpu_write(s390_idle.nohz_delay, 1);
+	set_cpu_flag(CIF_NOHZ_DELAY);
 	tpi_info = (struct tpi_info *) &get_irq_regs()->int_code;
 	head = &airq_lists[tpi_info->isc];
 	rcu_read_lock();
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 2905d8b0ec95..d5a6f287d2fe 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -561,7 +561,7 @@ static irqreturn_t do_cio_interrupt(int irq, void *dummy)
 	struct subchannel *sch;
 	struct irb *irb;
 
-	__this_cpu_write(s390_idle.nohz_delay, 1);
+	set_cpu_flag(CIF_NOHZ_DELAY);
 	tpi_info = (struct tpi_info *) &get_irq_regs()->int_code;
 	irb = &__get_cpu_var(cio_irb);
 	sch = (struct subchannel *)(unsigned long) tpi_info->intparm;
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 9a82c7dc3fdd..e5832d03da19 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -108,7 +108,7 @@ extern struct tick_sched *tick_get_tick_sched(int cpu);
 extern void tick_irq_enter(void);
 extern int tick_oneshot_mode_active(void);
 #  ifndef arch_needs_cpu
-#   define arch_needs_cpu(cpu) (0)
+#   define arch_needs_cpu() (0)
 #  endif
 # else
 static inline void tick_clock_notify(void) { }
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f654a8a298fa..01d512fd45f1 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -572,7 +572,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	} while (read_seqretry(&jiffies_lock, seq));
 
 	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
-	    arch_needs_cpu(cpu) || irq_work_needs_cpu()) {
+	    arch_needs_cpu() || irq_work_needs_cpu()) {
 		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
 	} else {
-- 
cgit v1.2.3


From 8070361799ae1e3f4ef347bd10f0a508ac10acfb Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Mon, 6 Oct 2014 17:53:53 +0200
Subject: s390: add support for vector extension

The vector extension introduces 32 128-bit vector registers and a set of
instruction to operate on the vector registers.

The kernel can control the use of vector registers for the problem state
program with a bit in control register 0. Once enabled for a process the
kernel needs to retain the content of the vector registers on context
switch. The signal frame is extended to include the vector registers.
Two new register sets NT_S390_VXRS_LOW and NT_S390_VXRS_HIGH are added
to the regset interface for the debugger and core dumps.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/elf.h             |   1 +
 arch/s390/include/asm/lowcore.h         |  10 +-
 arch/s390/include/asm/nmi.h             |   2 +-
 arch/s390/include/asm/processor.h       |   1 +
 arch/s390/include/asm/setup.h           |   3 +
 arch/s390/include/asm/switch_to.h       |  48 +++++-
 arch/s390/include/uapi/asm/sigcontext.h |  20 ++-
 arch/s390/include/uapi/asm/types.h      |   4 +
 arch/s390/include/uapi/asm/ucontext.h   |  15 +-
 arch/s390/kernel/compat_linux.h         |   9 +
 arch/s390/kernel/compat_signal.c        | 212 +++++++++++++++++------
 arch/s390/kernel/early.c                |   2 +
 arch/s390/kernel/entry.h                |   3 +
 arch/s390/kernel/nmi.c                  |  16 ++
 arch/s390/kernel/pgm_check.S            |   2 +-
 arch/s390/kernel/processor.c            |   2 +-
 arch/s390/kernel/ptrace.c               | 249 +++++++++++++++++++++------
 arch/s390/kernel/setup.c                |   9 +
 arch/s390/kernel/signal.c               | 296 +++++++++++++++++++++++++-------
 arch/s390/kernel/smp.c                  |   3 +
 arch/s390/kernel/traps.c                |  82 +++++++++
 include/uapi/linux/elf.h                |   2 +
 22 files changed, 804 insertions(+), 187 deletions(-)

(limited to 'include')

diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 78f4f8711d58..27735ae06a78 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -102,6 +102,7 @@
 #define HWCAP_S390_ETF3EH	256
 #define HWCAP_S390_HIGH_GPRS	512
 #define HWCAP_S390_TE		1024
+#define HWCAP_S390_VXRS		2048
 
 /*
  * These are used to set parameters in the core dumps.
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 4349197ab9df..d812cf1a8177 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -310,7 +310,10 @@ struct _lowcore {
 
 	/* Extended facility list */
 	__u64	stfle_fac_list[32];		/* 0x0f00 */
-	__u8	pad_0x1000[0x11b8-0x1000];	/* 0x1000 */
+	__u8	pad_0x1000[0x11b0-0x1000];	/* 0x1000 */
+
+	/* Pointer to vector register save area */
+	__u64	vector_save_area_addr;		/* 0x11b0 */
 
 	/* 64 bit extparam used for pfault/diag 250: defined by architecture */
 	__u64	ext_params2;			/* 0x11B8 */
@@ -334,9 +337,10 @@ struct _lowcore {
 
 	/* Transaction abort diagnostic block */
 	__u8	pgm_tdb[256];			/* 0x1800 */
+	__u8	pad_0x1900[0x1c00-0x1900];	/* 0x1900 */
 
-	/* align to the top of the prefix area */
-	__u8	pad_0x1900[0x2000-0x1900];	/* 0x1900 */
+	/* Software defined save area for vector registers */
+	__u8	vector_save_area[1024];		/* 0x1c00 */
 } __packed;
 
 #endif /* CONFIG_32BIT */
diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h
index 35f8ec185616..3027a5a72b74 100644
--- a/arch/s390/include/asm/nmi.h
+++ b/arch/s390/include/asm/nmi.h
@@ -38,7 +38,7 @@ struct mci {
 	__u32 pm :  1; /* 22 psw program mask and cc validity */
 	__u32 ia :  1; /* 23 psw instruction address validity */
 	__u32 fa :  1; /* 24 failing storage address validity */
-	__u32	 :  1; /* 25 */
+	__u32 vr :  1; /* 25 vector register validity */
 	__u32 ec :  1; /* 26 external damage code validity */
 	__u32 fp :  1; /* 27 floating point register validity */
 	__u32 gr :  1; /* 28 general register validity */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 3d0871058306..d559bdb03d18 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -117,6 +117,7 @@ struct thread_struct {
 	int ri_signum;
 #ifdef CONFIG_64BIT
 	unsigned char trap_tdb[256];	/* Transaction abort diagnose block */
+	__vector128 *vxrs;		/* Vector register save area */
 #endif
 };
 
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index dbde7c236577..7736fdd72595 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -56,6 +56,7 @@ extern void detect_memory_memblock(void);
 #define MACHINE_FLAG_TOPOLOGY	(1UL << 14)
 #define MACHINE_FLAG_TE		(1UL << 15)
 #define MACHINE_FLAG_TLB_LC	(1UL << 17)
+#define MACHINE_FLAG_VX		(1UL << 18)
 
 #define MACHINE_IS_VM		(S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM		(S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -78,6 +79,7 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_TOPOLOGY	(0)
 #define MACHINE_HAS_TE		(0)
 #define MACHINE_HAS_TLB_LC	(0)
+#define MACHINE_HAS_VX		(0)
 #else /* CONFIG_64BIT */
 #define MACHINE_HAS_IEEE	(1)
 #define MACHINE_HAS_CSP		(1)
@@ -90,6 +92,7 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_TOPOLOGY	(S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
 #define MACHINE_HAS_TE		(S390_lowcore.machine_flags & MACHINE_FLAG_TE)
 #define MACHINE_HAS_TLB_LC	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
+#define MACHINE_HAS_VX		(S390_lowcore.machine_flags & MACHINE_FLAG_VX)
 #endif /* CONFIG_64BIT */
 
 /*
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 18ea9e3f8142..0e0109578021 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -103,6 +103,48 @@ static inline void restore_fp_regs(freg_t *fprs)
 	asm volatile("ld 15,%0" : : "Q" (fprs[15]));
 }
 
+static inline void save_vx_regs(__vector128 *vxrs)
+{
+	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
+
+	asm volatile(
+		"	la	1,%0\n"
+		"	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
+		"	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
+		: "=Q" (*(addrtype *) vxrs) : : "1");
+}
+
+static inline void restore_vx_regs(__vector128 *vxrs)
+{
+	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
+
+	asm volatile(
+		"	la	1,%0\n"
+		"	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
+		"	.word	0xe70f,0x1100,0x0c36\n"	/* vlm 16,31,256(1) */
+		: : "Q" (*(addrtype *) vxrs) : "1");
+}
+
+static inline void save_fp_vx_regs(struct task_struct *task)
+{
+#ifdef CONFIG_64BIT
+	if (task->thread.vxrs)
+		save_vx_regs(task->thread.vxrs);
+	else
+#endif
+	save_fp_regs(task->thread.fp_regs.fprs);
+}
+
+static inline void restore_fp_vx_regs(struct task_struct *task)
+{
+#ifdef CONFIG_64BIT
+	if (task->thread.vxrs)
+		restore_vx_regs(task->thread.vxrs);
+	else
+#endif
+	restore_fp_regs(task->thread.fp_regs.fprs);
+}
+
 static inline void save_access_regs(unsigned int *acrs)
 {
 	typedef struct { int _[NUM_ACRS]; } acrstype;
@@ -120,16 +162,16 @@ static inline void restore_access_regs(unsigned int *acrs)
 #define switch_to(prev,next,last) do {					\
 	if (prev->mm) {							\
 		save_fp_ctl(&prev->thread.fp_regs.fpc);			\
-		save_fp_regs(prev->thread.fp_regs.fprs);		\
+		save_fp_vx_regs(prev);					\
 		save_access_regs(&prev->thread.acrs[0]);		\
 		save_ri_cb(prev->thread.ri_cb);				\
 	}								\
 	if (next->mm) {							\
+		update_cr_regs(next);					\
 		restore_fp_ctl(&next->thread.fp_regs.fpc);		\
-		restore_fp_regs(next->thread.fp_regs.fprs);		\
+		restore_fp_vx_regs(next);				\
 		restore_access_regs(&next->thread.acrs[0]);		\
 		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\
-		update_cr_regs(next);					\
 	}								\
 	prev = __switch_to(prev,next);					\
 } while (0)
diff --git a/arch/s390/include/uapi/asm/sigcontext.h b/arch/s390/include/uapi/asm/sigcontext.h
index b30de9c01bbe..5f0b8d7ddb0b 100644
--- a/arch/s390/include/uapi/asm/sigcontext.h
+++ b/arch/s390/include/uapi/asm/sigcontext.h
@@ -7,10 +7,14 @@
 #define _ASM_S390_SIGCONTEXT_H
 
 #include <linux/compiler.h>
+#include <linux/types.h>
 
-#define __NUM_GPRS 16
-#define __NUM_FPRS 16
-#define __NUM_ACRS 16
+#define __NUM_GPRS		16
+#define __NUM_FPRS		16
+#define __NUM_ACRS		16
+#define __NUM_VXRS		32
+#define __NUM_VXRS_LOW		16
+#define __NUM_VXRS_HIGH		16
 
 #ifndef __s390x__
 
@@ -59,6 +63,16 @@ typedef struct
 	_s390_fp_regs     fpregs;
 } _sigregs;
 
+typedef struct
+{
+#ifndef __s390x__
+	unsigned long gprs_high[__NUM_GPRS];
+#endif
+	unsigned long long vxrs_low[__NUM_VXRS_LOW];
+	__vector128 vxrs_high[__NUM_VXRS_HIGH];
+	unsigned char __reserved[128];
+} _sigregs_ext;
+
 struct sigcontext
 {
 	unsigned long	oldmask[_SIGCONTEXT_NSIG_WORDS];
diff --git a/arch/s390/include/uapi/asm/types.h b/arch/s390/include/uapi/asm/types.h
index 038f2b9178a4..3c3951e3415b 100644
--- a/arch/s390/include/uapi/asm/types.h
+++ b/arch/s390/include/uapi/asm/types.h
@@ -17,6 +17,10 @@
 typedef unsigned long addr_t; 
 typedef __signed__ long saddr_t;
 
+typedef struct {
+	__u32 u[4];
+} __vector128;
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI_S390_TYPES_H */
diff --git a/arch/s390/include/uapi/asm/ucontext.h b/arch/s390/include/uapi/asm/ucontext.h
index 3e077b2a4705..64a69aa5dde0 100644
--- a/arch/s390/include/uapi/asm/ucontext.h
+++ b/arch/s390/include/uapi/asm/ucontext.h
@@ -7,10 +7,15 @@
 #ifndef _ASM_S390_UCONTEXT_H
 #define _ASM_S390_UCONTEXT_H
 
-#define UC_EXTENDED	0x00000001
-
-#ifndef __s390x__
+#define UC_GPRS_HIGH	1	/* uc_mcontext_ext has valid high gprs */
+#define UC_VXRS		2	/* uc_mcontext_ext has valid vector regs */
 
+/*
+ * The struct ucontext_extended describes how the registers are stored
+ * on a rt signal frame. Please note that the structure is not fixed,
+ * if new CPU registers are added to the user state the size of the
+ * struct ucontext_extended will increase.
+ */
 struct ucontext_extended {
 	unsigned long	  uc_flags;
 	struct ucontext  *uc_link;
@@ -19,11 +24,9 @@ struct ucontext_extended {
 	sigset_t	  uc_sigmask;
 	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
 	unsigned char	  __unused[128 - sizeof(sigset_t)];
-	unsigned long	  uc_gprs_high[16];
+	_sigregs_ext	  uc_mcontext_ext;
 };
 
-#endif
-
 struct ucontext {
 	unsigned long	  uc_flags;
 	struct ucontext  *uc_link;
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index 70d4b7c4beaa..a0a886c04977 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -50,6 +50,14 @@ typedef struct
 	_s390_fp_regs32     fpregs;
 } _sigregs32;
 
+typedef struct
+{
+	__u32 gprs_high[__NUM_GPRS];
+	__u64 vxrs_low[__NUM_VXRS_LOW];
+	__vector128 vxrs_high[__NUM_VXRS_HIGH];
+	__u8 __reserved[128];
+} _sigregs_ext32;
+
 #define _SIGCONTEXT_NSIG32	64
 #define _SIGCONTEXT_NSIG_BPW32	32
 #define __SIGNAL_FRAMESIZE32	96
@@ -72,6 +80,7 @@ struct ucontext32 {
 	compat_sigset_t		uc_sigmask;
 	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
 	unsigned char		__unused[128 - sizeof(compat_sigset_t)];
+	_sigregs_ext32		uc_mcontext_ext;
 };
 
 struct stat64_emu31;
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 598b0b42668b..009f5eb11125 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -36,17 +36,16 @@ typedef struct
 	struct sigcontext32 sc;
 	_sigregs32 sregs;
 	int signo;
-	__u32 gprs_high[NUM_GPRS];
-	__u8 retcode[S390_SYSCALL_SIZE];
+	_sigregs_ext32 sregs_ext;
+	__u16 svc_insn;		/* Offset of svc_insn is NOT fixed! */
 } sigframe32;
 
 typedef struct 
 {
 	__u8 callee_used_stack[__SIGNAL_FRAMESIZE32];
-	__u8 retcode[S390_SYSCALL_SIZE];
+	__u16 svc_insn;
 	compat_siginfo_t info;
 	struct ucontext32 uc;
-	__u32 gprs_high[NUM_GPRS];
 } rt_sigframe32;
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
@@ -151,6 +150,38 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	return err ? -EFAULT : 0;
 }
 
+/* Store registers needed to create the signal frame */
+static void store_sigregs(void)
+{
+	int i;
+
+	save_access_regs(current->thread.acrs);
+	save_fp_ctl(&current->thread.fp_regs.fpc);
+	if (current->thread.vxrs) {
+		save_vx_regs(current->thread.vxrs);
+		for (i = 0; i < __NUM_FPRS; i++)
+			current->thread.fp_regs.fprs[i] =
+				*(freg_t *)(current->thread.vxrs + i);
+	} else
+		save_fp_regs(current->thread.fp_regs.fprs);
+}
+
+/* Load registers after signal return */
+static void load_sigregs(void)
+{
+	int i;
+
+	restore_access_regs(current->thread.acrs);
+	/* restore_fp_ctl is done in restore_sigregs */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_FPRS; i++)
+			*(freg_t *)(current->thread.vxrs + i) =
+				current->thread.fp_regs.fprs[i];
+		restore_vx_regs(current->thread.vxrs);
+	} else
+		restore_fp_regs(current->thread.fp_regs.fprs);
+}
+
 static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
 {
 	_sigregs32 user_sregs;
@@ -163,11 +194,8 @@ static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
 		(__u32)(regs->psw.mask & PSW_MASK_BA);
 	for (i = 0; i < NUM_GPRS; i++)
 		user_sregs.regs.gprs[i] = (__u32) regs->gprs[i];
-	save_access_regs(current->thread.acrs);
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	save_fp_ctl(&current->thread.fp_regs.fpc);
-	save_fp_regs(current->thread.fp_regs.fprs);
 	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
 	       sizeof(user_sregs.fpregs));
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs32)))
@@ -207,37 +235,67 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 		regs->gprs[i] = (__u64) user_sregs.regs.gprs[i];
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
-	restore_access_regs(current->thread.acrs);
 
 	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
 	       sizeof(current->thread.fp_regs));
 
-	restore_fp_regs(current->thread.fp_regs.fprs);
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
 }
 
-static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs)
+static int save_sigregs_ext32(struct pt_regs *regs,
+			      _sigregs_ext32 __user *sregs_ext)
 {
 	__u32 gprs_high[NUM_GPRS];
+	__u64 vxrs[__NUM_VXRS_LOW];
 	int i;
 
+	/* Save high gprs to signal stack */
 	for (i = 0; i < NUM_GPRS; i++)
 		gprs_high[i] = regs->gprs[i] >> 32;
-	if (__copy_to_user(uregs, &gprs_high, sizeof(gprs_high)))
+	if (__copy_to_user(&sregs_ext->gprs_high, &gprs_high,
+			   sizeof(sregs_ext->gprs_high)))
 		return -EFAULT;
+
+	/* Save vector registers to signal stack */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
+				   sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_to_user(&sregs_ext->vxrs_high,
+				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
-static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs)
+static int restore_sigregs_ext32(struct pt_regs *regs,
+				 _sigregs_ext32 __user *sregs_ext)
 {
 	__u32 gprs_high[NUM_GPRS];
+	__u64 vxrs[__NUM_VXRS_LOW];
 	int i;
 
-	if (__copy_from_user(&gprs_high, uregs, sizeof(gprs_high)))
+	/* Restore high gprs from signal stack */
+	if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high,
+			     sizeof(&sregs_ext->gprs_high)))
 		return -EFAULT;
 	for (i = 0; i < NUM_GPRS; i++)
 		*(__u32 *)&regs->gprs[i] = gprs_high[i];
+
+	/* Restore vector registers from signal stack */
+	if (current->thread.vxrs) {
+		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
+				     sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+				     &sregs_ext->vxrs_high,
+				     sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+	}
 	return 0;
 }
 
@@ -252,8 +310,9 @@ COMPAT_SYSCALL_DEFINE0(sigreturn)
 	set_current_blocked(&set);
 	if (restore_sigregs32(regs, &frame->sregs))
 		goto badframe;
-	if (restore_sigregs_gprs_high(regs, frame->gprs_high))
+	if (restore_sigregs_ext32(regs, &frame->sregs_ext))
 		goto badframe;
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -269,12 +328,13 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
 	set_current_blocked(&set);
+	if (compat_restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
 	if (restore_sigregs32(regs, &frame->uc.uc_mcontext))
 		goto badframe;
-	if (restore_sigregs_gprs_high(regs, frame->gprs_high))
+	if (restore_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
 		goto badframe;
-	if (compat_restore_altstack(&frame->uc.uc_stack))
-		goto badframe; 
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -324,37 +384,64 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 			 struct pt_regs *regs)
 {
 	int sig = ksig->sig;
-	sigframe32 __user *frame = get_sigframe(&ksig->ka, regs, sizeof(sigframe32));
-
+	sigframe32 __user *frame;
+	struct sigcontext32 sc;
+	unsigned long restorer;
+	size_t frame_size;
+
+	/*
+	 * gprs_high are always present for 31-bit compat tasks.
+	 * The space for vector registers is only allocated if
+	 * the machine supports it
+	 */
+	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext.__reserved);
+	if (!MACHINE_HAS_VX)
+		frame_size -= sizeof(frame->sregs_ext.vxrs_low) +
+			      sizeof(frame->sregs_ext.vxrs_high);
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32))
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (unsigned int __user *) frame))
+		return -EFAULT;
+
+	/* Create struct sigcontext32 on the signal stack */
+	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32);
+	sc.sregs = (__u32)(unsigned long __force) &frame->sregs;
+	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
 		return -EFAULT;
 
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create _sigregs32 on the signal stack */
 	if (save_sigregs32(regs, &frame->sregs))
 		return -EFAULT;
-	if (save_sigregs_gprs_high(regs, frame->gprs_high))
+
+	/* Place signal number on stack to allow backtrace from handler.  */
+	if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo))
 		return -EFAULT;
-	if (__put_user((unsigned long) &frame->sregs, &frame->sc.sregs))
+
+	/* Create _sigregs_ext32 on the signal stack */
+	if (save_sigregs_ext32(regs, &frame->sregs_ext))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-		regs->gprs[14] = (__u64 __force) ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
+		restorer = (unsigned long __force)
+			ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
-		regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn,
-			       (u16 __force __user *)(frame->retcode)))
+		/* Signal frames without vectors registers are short ! */
+		__u16 __user *svc = (void *) frame + frame_size - 2;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long __force) svc | PSW32_ADDR_AMODE;
         }
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (unsigned int __user *) frame))
-		return -EFAULT;
-
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (__force __u64) frame;
 	/* Force 31 bit amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_BA |
@@ -375,50 +462,69 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 		regs->gprs[6] = task_thread_info(current)->last_break;
 	}
 
-	/* Place signal number on stack to allow backtrace from handler.  */
-	if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo))
-		return -EFAULT;
 	return 0;
 }
 
 static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 			    struct pt_regs *regs)
 {
-	int err = 0;
-	rt_sigframe32 __user *frame = get_sigframe(&ksig->ka, regs, sizeof(rt_sigframe32));
-
+	rt_sigframe32 __user *frame;
+	unsigned long restorer;
+	size_t frame_size;
+	u32 uc_flags;
+
+	frame_size = sizeof(*frame) -
+		     sizeof(frame->uc.uc_mcontext_ext.__reserved);
+	/*
+	 * gprs_high are always present for 31-bit compat tasks.
+	 * The space for vector registers is only allocated if
+	 * the machine supports it
+	 */
+	uc_flags = UC_GPRS_HIGH;
+	if (MACHINE_HAS_VX) {
+		if (current->thread.vxrs)
+			uc_flags |= UC_VXRS;
+	} else
+		frame_size -= sizeof(frame->uc.uc_mcontext_ext.vxrs_low) +
+			      sizeof(frame->uc.uc_mcontext_ext.vxrs_high);
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (copy_siginfo_to_user32(&frame->info, &ksig->info))
-		return -EFAULT;
-
-	/* Create the ucontext.  */
-	err |= __put_user(UC_EXTENDED, &frame->uc.uc_flags);
-	err |= __put_user(0, &frame->uc.uc_link);
-	err |= __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]);
-	err |= save_sigregs32(regs, &frame->uc.uc_mcontext);
-	err |= save_sigregs_gprs_high(regs, frame->gprs_high);
-	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-	if (err)
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-		regs->gprs[14] = (__u64 __force) ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
+		restorer = (unsigned long __force)
+			ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
-		regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
-			       (u16 __force __user *)(frame->retcode)))
+		__u16 __user *svc = &frame->svc_insn;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long __force) svc | PSW32_ADDR_AMODE;
 	}
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame))
+	/* Create siginfo on the signal stack */
+	if (copy_siginfo_to_user32(&frame->info, &ksig->info))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create ucontext on the signal stack. */
+	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
+	    __put_user(0, &frame->uc.uc_link) ||
+	    __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
+	    save_sigregs32(regs, &frame->uc.uc_mcontext) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    save_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
 		return -EFAULT;
 
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (__force __u64) frame;
 	/* Force 31 bit amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_BA |
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index f6c66b5d0cfa..cef2879edff3 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -392,6 +392,8 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TE;
 	if (test_facility(51))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;
+	if (test_facility(129))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
 #endif
 }
 
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index cd68869f9504..0554b9771c9f 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -21,6 +21,8 @@ void psw_idle(struct s390_idle_data *, unsigned long);
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs);
 
+int alloc_vector_registers(struct task_struct *tsk);
+
 void do_protection_exception(struct pt_regs *regs);
 void do_dat_exception(struct pt_regs *regs);
 
@@ -43,6 +45,7 @@ void special_op_exception(struct pt_regs *regs);
 void specification_exception(struct pt_regs *regs);
 void transaction_exception(struct pt_regs *regs);
 void translation_exception(struct pt_regs *regs);
+void vector_exception(struct pt_regs *regs);
 
 void do_per_trap(struct pt_regs *regs);
 void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str);
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 210e1285f75a..db96b418160a 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -20,6 +20,7 @@
 #include <asm/cputime.h>
 #include <asm/nmi.h>
 #include <asm/crw.h>
+#include <asm/switch_to.h>
 
 struct mcck_struct {
 	int kill_task;
@@ -163,6 +164,21 @@ static int notrace s390_revalidate_registers(struct mci *mci)
 			"	ld	15,120(%0)\n"
 			: : "a" (fpt_save_area));
 	}
+
+#ifdef CONFIG_64BIT
+	/* Revalidate vector registers */
+	if (MACHINE_HAS_VX && current->thread.vxrs) {
+		if (!mci->vr) {
+			/*
+			 * Vector registers can't be restored and therefore
+			 * the process needs to be terminated.
+			 */
+			kill_task = 1;
+		}
+		restore_vx_regs((__vector128 *)
+				S390_lowcore.vector_save_area_addr);
+	}
+#endif
 	/* Revalidate access registers */
 	asm volatile(
 		"	lam	0,15,0(%0)"
diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S
index 813ec7260878..f6f8886399f6 100644
--- a/arch/s390/kernel/pgm_check.S
+++ b/arch/s390/kernel/pgm_check.S
@@ -49,7 +49,7 @@ PGM_CHECK_DEFAULT			/* 17 */
 PGM_CHECK_64BIT(transaction_exception)	/* 18 */
 PGM_CHECK_DEFAULT			/* 19 */
 PGM_CHECK_DEFAULT			/* 1a */
-PGM_CHECK_DEFAULT			/* 1b */
+PGM_CHECK_64BIT(vector_exception)	/* 1b */
 PGM_CHECK(space_switch_exception)	/* 1c */
 PGM_CHECK(hfp_sqrt_exception)		/* 1d */
 PGM_CHECK_DEFAULT			/* 1e */
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 32587cc76306..edefead3b43a 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -39,7 +39,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	static const char *hwcap_str[] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
-		"edat", "etf3eh", "highgprs", "te"
+		"edat", "etf3eh", "highgprs", "te", "vx"
 	};
 	unsigned long n = (unsigned long) v - 1;
 	int i;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index fe99d6b3f185..0ecfdb3c6f8e 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -38,15 +38,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-enum s390_regset {
-	REGSET_GENERAL,
-	REGSET_FP,
-	REGSET_LAST_BREAK,
-	REGSET_TDB,
-	REGSET_SYSTEM_CALL,
-	REGSET_GENERAL_EXTENDED,
-};
-
 void update_cr_regs(struct task_struct *task)
 {
 	struct pt_regs *regs = task_pt_regs(task);
@@ -55,27 +46,39 @@ void update_cr_regs(struct task_struct *task)
 
 #ifdef CONFIG_64BIT
 	/* Take care of the enable/disable of transactional execution. */
-	if (MACHINE_HAS_TE) {
+	if (MACHINE_HAS_TE || MACHINE_HAS_VX) {
 		unsigned long cr, cr_new;
 
 		__ctl_store(cr, 0, 0);
-		/* Set or clear transaction execution TXC bit 8. */
-		cr_new = cr | (1UL << 55);
-		if (task->thread.per_flags & PER_FLAG_NO_TE)
-			cr_new &= ~(1UL << 55);
+		cr_new = cr;
+		if (MACHINE_HAS_TE) {
+			/* Set or clear transaction execution TXC bit 8. */
+			cr_new |= (1UL << 55);
+			if (task->thread.per_flags & PER_FLAG_NO_TE)
+				cr_new &= ~(1UL << 55);
+		}
+		if (MACHINE_HAS_VX) {
+			/* Enable/disable of vector extension */
+			cr_new &= ~(1UL << 17);
+			if (task->thread.vxrs)
+				cr_new |= (1UL << 17);
+		}
 		if (cr_new != cr)
 			__ctl_load(cr_new, 0, 0);
-		/* Set or clear transaction execution TDC bits 62 and 63. */
-		__ctl_store(cr, 2, 2);
-		cr_new = cr & ~3UL;
-		if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
-			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND_TEND)
-				cr_new |= 1UL;
-			else
-				cr_new |= 2UL;
+		if (MACHINE_HAS_TE) {
+			/* Set/clear transaction execution TDC bits 62/63. */
+			__ctl_store(cr, 2, 2);
+			cr_new = cr & ~3UL;
+			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
+				if (task->thread.per_flags &
+				    PER_FLAG_TE_ABORT_RAND_TEND)
+					cr_new |= 1UL;
+				else
+					cr_new |= 2UL;
+			}
+			if (cr_new != cr)
+				__ctl_load(cr_new, 2, 2);
 		}
-		if (cr_new != cr)
-			__ctl_load(cr_new, 2, 2);
 	}
 #endif
 	/* Copy user specified PER registers */
@@ -926,7 +929,15 @@ static int s390_fpregs_get(struct task_struct *target,
 		save_fp_ctl(&target->thread.fp_regs.fpc);
 		save_fp_regs(target->thread.fp_regs.fprs);
 	}
+#ifdef CONFIG_64BIT
+	else if (target->thread.vxrs) {
+		int i;
 
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			target->thread.fp_regs.fprs[i] =
+				*(freg_t *)(target->thread.vxrs + i);
+	}
+#endif
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				   &target->thread.fp_regs, 0, -1);
 }
@@ -960,9 +971,20 @@ static int s390_fpregs_set(struct task_struct *target,
 					target->thread.fp_regs.fprs,
 					offsetof(s390_fp_regs, fprs), -1);
 
-	if (rc == 0 && target == current) {
-		restore_fp_ctl(&target->thread.fp_regs.fpc);
-		restore_fp_regs(target->thread.fp_regs.fprs);
+	if (rc == 0) {
+		if (target == current) {
+			restore_fp_ctl(&target->thread.fp_regs.fpc);
+			restore_fp_regs(target->thread.fp_regs.fprs);
+		}
+#ifdef CONFIG_64BIT
+		else if (target->thread.vxrs) {
+			int i;
+
+			for (i = 0; i < __NUM_VXRS_LOW; i++)
+				*(freg_t *)(target->thread.vxrs + i) =
+					target->thread.fp_regs.fprs[i];
+		}
+#endif
 	}
 
 	return rc;
@@ -1018,6 +1040,95 @@ static int s390_tdb_set(struct task_struct *target,
 	return 0;
 }
 
+static int s390_vxrs_active(struct task_struct *target,
+			      const struct user_regset *regset)
+{
+	return !!target->thread.vxrs;
+}
+
+static int s390_vxrs_low_get(struct task_struct *target,
+			     const struct user_regset *regset,
+			     unsigned int pos, unsigned int count,
+			     void *kbuf, void __user *ubuf)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	if (target->thread.vxrs) {
+		if (target == current)
+			save_vx_regs(target->thread.vxrs);
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(target->thread.vxrs + i) + 1);
+	} else
+		memset(vxrs, 0, sizeof(vxrs));
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+}
+
+static int s390_vxrs_low_set(struct task_struct *target,
+			     const struct user_regset *regset,
+			     unsigned int pos, unsigned int count,
+			     const void *kbuf, const void __user *ubuf)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i, rc;
+
+	if (!target->thread.vxrs) {
+		rc = alloc_vector_registers(target);
+		if (rc)
+			return rc;
+	} else if (target == current)
+		save_vx_regs(target->thread.vxrs);
+
+	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+	if (rc == 0) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(target->thread.vxrs + i) + 1) = vxrs[i];
+		if (target == current)
+			restore_vx_regs(target->thread.vxrs);
+	}
+
+	return rc;
+}
+
+static int s390_vxrs_high_get(struct task_struct *target,
+			      const struct user_regset *regset,
+			      unsigned int pos, unsigned int count,
+			      void *kbuf, void __user *ubuf)
+{
+	__vector128 vxrs[__NUM_VXRS_HIGH];
+
+	if (target->thread.vxrs) {
+		if (target == current)
+			save_vx_regs(target->thread.vxrs);
+		memcpy(vxrs, target->thread.vxrs + __NUM_VXRS_LOW,
+		       sizeof(vxrs));
+	} else
+		memset(vxrs, 0, sizeof(vxrs));
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+}
+
+static int s390_vxrs_high_set(struct task_struct *target,
+			      const struct user_regset *regset,
+			      unsigned int pos, unsigned int count,
+			      const void *kbuf, const void __user *ubuf)
+{
+	int rc;
+
+	if (!target->thread.vxrs) {
+		rc = alloc_vector_registers(target);
+		if (rc)
+			return rc;
+	} else if (target == current)
+		save_vx_regs(target->thread.vxrs);
+
+	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				target->thread.vxrs + __NUM_VXRS_LOW, 0, -1);
+	if (rc == 0 && target == current)
+		restore_vx_regs(target->thread.vxrs);
+
+	return rc;
+}
+
 #endif
 
 static int s390_system_call_get(struct task_struct *target,
@@ -1041,7 +1152,7 @@ static int s390_system_call_set(struct task_struct *target,
 }
 
 static const struct user_regset s390_regsets[] = {
-	[REGSET_GENERAL] = {
+	{
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(s390_regs) / sizeof(long),
 		.size = sizeof(long),
@@ -1049,7 +1160,7 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_regs_get,
 		.set = s390_regs_set,
 	},
-	[REGSET_FP] = {
+	{
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(s390_fp_regs) / sizeof(long),
 		.size = sizeof(long),
@@ -1057,8 +1168,16 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_fpregs_get,
 		.set = s390_fpregs_set,
 	},
+	{
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(unsigned int),
+		.align = sizeof(unsigned int),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
 #ifdef CONFIG_64BIT
-	[REGSET_LAST_BREAK] = {
+	{
 		.core_note_type = NT_S390_LAST_BREAK,
 		.n = 1,
 		.size = sizeof(long),
@@ -1066,7 +1185,7 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_last_break_get,
 		.set = s390_last_break_set,
 	},
-	[REGSET_TDB] = {
+	{
 		.core_note_type = NT_S390_TDB,
 		.n = 1,
 		.size = 256,
@@ -1074,15 +1193,25 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_tdb_get,
 		.set = s390_tdb_set,
 	},
-#endif
-	[REGSET_SYSTEM_CALL] = {
-		.core_note_type = NT_S390_SYSTEM_CALL,
-		.n = 1,
-		.size = sizeof(unsigned int),
-		.align = sizeof(unsigned int),
-		.get = s390_system_call_get,
-		.set = s390_system_call_set,
+	{
+		.core_note_type = NT_S390_VXRS_LOW,
+		.n = __NUM_VXRS_LOW,
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_low_get,
+		.set = s390_vxrs_low_set,
+	},
+	{
+		.core_note_type = NT_S390_VXRS_HIGH,
+		.n = __NUM_VXRS_HIGH,
+		.size = sizeof(__vector128),
+		.align = sizeof(__vector128),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_high_get,
+		.set = s390_vxrs_high_set,
 	},
+#endif
 };
 
 static const struct user_regset_view user_s390_view = {
@@ -1247,7 +1376,7 @@ static int s390_compat_last_break_set(struct task_struct *target,
 }
 
 static const struct user_regset s390_compat_regsets[] = {
-	[REGSET_GENERAL] = {
+	{
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(s390_compat_regs) / sizeof(compat_long_t),
 		.size = sizeof(compat_long_t),
@@ -1255,7 +1384,7 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_compat_regs_get,
 		.set = s390_compat_regs_set,
 	},
-	[REGSET_FP] = {
+	{
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(s390_fp_regs) / sizeof(compat_long_t),
 		.size = sizeof(compat_long_t),
@@ -1263,7 +1392,15 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_fpregs_get,
 		.set = s390_fpregs_set,
 	},
-	[REGSET_LAST_BREAK] = {
+	{
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(compat_uint_t),
+		.align = sizeof(compat_uint_t),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
+	{
 		.core_note_type = NT_S390_LAST_BREAK,
 		.n = 1,
 		.size = sizeof(long),
@@ -1271,7 +1408,7 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_compat_last_break_get,
 		.set = s390_compat_last_break_set,
 	},
-	[REGSET_TDB] = {
+	{
 		.core_note_type = NT_S390_TDB,
 		.n = 1,
 		.size = 256,
@@ -1279,15 +1416,25 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_tdb_get,
 		.set = s390_tdb_set,
 	},
-	[REGSET_SYSTEM_CALL] = {
-		.core_note_type = NT_S390_SYSTEM_CALL,
-		.n = 1,
-		.size = sizeof(compat_uint_t),
-		.align = sizeof(compat_uint_t),
-		.get = s390_system_call_get,
-		.set = s390_system_call_set,
+	{
+		.core_note_type = NT_S390_VXRS_LOW,
+		.n = __NUM_VXRS_LOW,
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_low_get,
+		.set = s390_vxrs_low_set,
+	},
+	{
+		.core_note_type = NT_S390_VXRS_HIGH,
+		.n = __NUM_VXRS_HIGH,
+		.size = sizeof(__vector128),
+		.align = sizeof(__vector128),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_high_get,
+		.set = s390_vxrs_high_set,
 	},
-	[REGSET_GENERAL_EXTENDED] = {
+	{
 		.core_note_type = NT_S390_HIGH_GPRS,
 		.n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t),
 		.size = sizeof(compat_long_t),
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index cdfc060dd319..e80d9ff9a56d 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -343,6 +343,9 @@ static void __init setup_lowcore(void)
 		__ctl_set_bit(14, 29);
 	}
 #else
+	if (MACHINE_HAS_VX)
+		lc->vector_save_area_addr =
+			(unsigned long) &lc->vector_save_area;
 	lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0];
 #endif
 	lc->sync_enter_timer = S390_lowcore.sync_enter_timer;
@@ -765,6 +768,12 @@ static void __init setup_hwcaps(void)
 	 */
 	if (test_facility(50) && test_facility(73))
 		elf_hwcap |= HWCAP_S390_TE;
+
+	/*
+	 * Vector extension HWCAP_S390_VXRS is bit 11.
+	 */
+	if (test_facility(129))
+		elf_hwcap |= HWCAP_S390_VXRS;
 #endif
 
 	get_cpu_id(&cpu_id);
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 469c4c6d9182..0c1a0ff0a558 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -31,30 +31,117 @@
 #include <asm/switch_to.h>
 #include "entry.h"
 
-typedef struct 
+/*
+ * Layout of an old-style signal-frame:
+ *	-----------------------------------------
+ *	| save area (_SIGNAL_FRAMESIZE)		|
+ *	-----------------------------------------
+ *	| struct sigcontext			|
+ *	|	oldmask				|
+ *	|	_sigregs *			|
+ *	-----------------------------------------
+ *	| _sigregs with				|
+ *	|	_s390_regs_common		|
+ *	|	_s390_fp_regs			|
+ *	-----------------------------------------
+ *	| int signo				|
+ *	-----------------------------------------
+ *	| _sigregs_ext with			|
+ *	|	gprs_high 64 byte (opt)		|
+ *	|	vxrs_low 128 byte (opt)		|
+ *	|	vxrs_high 256 byte (opt)	|
+ *	|	reserved 128 byte (opt)		|
+ *	-----------------------------------------
+ *	| __u16 svc_insn			|
+ *	-----------------------------------------
+ * The svc_insn entry with the sigreturn system call opcode does not
+ * have a fixed position and moves if gprs_high or vxrs exist.
+ * Future extensions will be added to _sigregs_ext.
+ */
+struct sigframe
 {
 	__u8 callee_used_stack[__SIGNAL_FRAMESIZE];
 	struct sigcontext sc;
 	_sigregs sregs;
 	int signo;
-	__u8 retcode[S390_SYSCALL_SIZE];
-} sigframe;
+	_sigregs_ext sregs_ext;
+	__u16 svc_insn;		/* Offset of svc_insn is NOT fixed! */
+};
 
-typedef struct 
+/*
+ * Layout of an rt signal-frame:
+ *	-----------------------------------------
+ *	| save area (_SIGNAL_FRAMESIZE)		|
+ *	-----------------------------------------
+ *	| svc __NR_rt_sigreturn 2 byte		|
+ *	-----------------------------------------
+ *	| struct siginfo			|
+ *	-----------------------------------------
+ *	| struct ucontext_extended with		|
+ *	|	unsigned long uc_flags		|
+ *	|	struct ucontext *uc_link	|
+ *	|	stack_t uc_stack		|
+ *	|	_sigregs uc_mcontext with	|
+ *	|		_s390_regs_common	|
+ *	|		_s390_fp_regs		|
+ *	|	sigset_t uc_sigmask		|
+ *	|	_sigregs_ext uc_mcontext_ext	|
+ *	|		gprs_high 64 byte (opt)	|
+ *	|		vxrs_low 128 byte (opt)	|
+ *	|		vxrs_high 256 byte (opt)|
+ *	|		reserved 128 byte (opt)	|
+ *	-----------------------------------------
+ * Future extensions will be added to _sigregs_ext.
+ */
+struct rt_sigframe
 {
 	__u8 callee_used_stack[__SIGNAL_FRAMESIZE];
-	__u8 retcode[S390_SYSCALL_SIZE];
+	__u16 svc_insn;
 	struct siginfo info;
-	struct ucontext uc;
-} rt_sigframe;
+	struct ucontext_extended uc;
+};
+
+/* Store registers needed to create the signal frame */
+static void store_sigregs(void)
+{
+	save_access_regs(current->thread.acrs);
+	save_fp_ctl(&current->thread.fp_regs.fpc);
+#ifdef CONFIG_64BIT
+	if (current->thread.vxrs) {
+		int i;
+
+		save_vx_regs(current->thread.vxrs);
+		for (i = 0; i < __NUM_FPRS; i++)
+			current->thread.fp_regs.fprs[i] =
+				*(freg_t *)(current->thread.vxrs + i);
+	} else
+#endif
+		save_fp_regs(current->thread.fp_regs.fprs);
+}
+
+/* Load registers after signal return */
+static void load_sigregs(void)
+{
+	restore_access_regs(current->thread.acrs);
+	/* restore_fp_ctl is done in restore_sigregs */
+#ifdef CONFIG_64BIT
+	if (current->thread.vxrs) {
+		int i;
+
+		for (i = 0; i < __NUM_FPRS; i++)
+			*(freg_t *)(current->thread.vxrs + i) =
+				current->thread.fp_regs.fprs[i];
+		restore_vx_regs(current->thread.vxrs);
+	} else
+#endif
+		restore_fp_regs(current->thread.fp_regs.fprs);
+}
 
 /* Returns non-zero on fault. */
 static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 {
 	_sigregs user_sregs;
 
-	save_access_regs(current->thread.acrs);
-
 	/* Copy a 'clean' PSW mask to the user to avoid leaking
 	   information about whether PER is currently on.  */
 	user_sregs.regs.psw.mask = PSW_USER_BITS |
@@ -63,12 +150,6 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&user_sregs.regs.gprs, &regs->gprs, sizeof(sregs->regs.gprs));
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	/* 
-	 * We have to store the fp registers to current->thread.fp_regs
-	 * to merge them with the emulated registers.
-	 */
-	save_fp_ctl(&current->thread.fp_regs.fpc);
-	save_fp_regs(current->thread.fp_regs.fprs);
 	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
 	       sizeof(user_sregs.fpregs));
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs)))
@@ -107,20 +188,64 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&regs->gprs, &user_sregs.regs.gprs, sizeof(sregs->regs.gprs));
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
-	restore_access_regs(current->thread.acrs);
 
 	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
 	       sizeof(current->thread.fp_regs));
 
-	restore_fp_regs(current->thread.fp_regs.fprs);
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
 }
 
+/* Returns non-zero on fault. */
+static int save_sigregs_ext(struct pt_regs *regs,
+			    _sigregs_ext __user *sregs_ext)
+{
+#ifdef CONFIG_64BIT
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Save vector registers to signal stack */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
+				   sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_to_user(&sregs_ext->vxrs_high,
+				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+	}
+#endif
+	return 0;
+}
+
+static int restore_sigregs_ext(struct pt_regs *regs,
+			       _sigregs_ext __user *sregs_ext)
+{
+#ifdef CONFIG_64BIT
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Restore vector registers from signal stack */
+	if (current->thread.vxrs) {
+		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
+				     sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+				     &sregs_ext->vxrs_high,
+				     sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+	}
+#endif
+	return 0;
+}
+
 SYSCALL_DEFINE0(sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
-	sigframe __user *frame = (sigframe __user *)regs->gprs[15];
+	struct sigframe __user *frame =
+		(struct sigframe __user *) regs->gprs[15];
 	sigset_t set;
 
 	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE))
@@ -128,6 +253,9 @@ SYSCALL_DEFINE0(sigreturn)
 	set_current_blocked(&set);
 	if (restore_sigregs(regs, &frame->sregs))
 		goto badframe;
+	if (restore_sigregs_ext(regs, &frame->sregs_ext))
+		goto badframe;
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -137,27 +265,26 @@ badframe:
 SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
-	rt_sigframe __user *frame = (rt_sigframe __user *)regs->gprs[15];
+	struct rt_sigframe __user *frame =
+		(struct rt_sigframe __user *)regs->gprs[15];
 	sigset_t set;
 
 	if (__copy_from_user(&set.sig, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
 	set_current_blocked(&set);
+	if (restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
 	if (restore_sigregs(regs, &frame->uc.uc_mcontext))
 		goto badframe;
-	if (restore_altstack(&frame->uc.uc_stack))
+	if (restore_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
 		goto badframe;
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
 	return 0;
 }
 
-/*
- * Set up a signal frame.
- */
-
-
 /*
  * Determine which stack to use..
  */
@@ -195,39 +322,63 @@ static inline int map_signal(int sig)
 static int setup_frame(int sig, struct k_sigaction *ka,
 		       sigset_t *set, struct pt_regs * regs)
 {
-	sigframe __user *frame;
-
-	frame = get_sigframe(ka, regs, sizeof(sigframe));
+	struct sigframe __user *frame;
+	struct sigcontext sc;
+	unsigned long restorer;
+	size_t frame_size;
 
+	/*
+	 * gprs_high are only present for a 31-bit task running on
+	 * a 64-bit kernel (see compat_signal.c) but the space for
+	 * gprs_high need to be allocated if vector registers are
+	 * included in the signal frame on a 31-bit system.
+	 */
+	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext);
+	if (MACHINE_HAS_VX)
+		frame_size += sizeof(frame->sregs_ext);
+	frame = get_sigframe(ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE))
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
 		return -EFAULT;
 
+	/* Create struct sigcontext on the signal stack */
+	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE);
+	sc.sregs = (_sigregs __user __force *) &frame->sregs;
+	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create _sigregs on the signal stack */
 	if (save_sigregs(regs, &frame->sregs))
 		return -EFAULT;
-	if (__put_user(&frame->sregs, &frame->sc.sregs))
+
+	/* Place signal number on stack to allow backtrace from handler.  */
+	if (__put_user(regs->gprs[2], (int __user *) &frame->signo))
+		return -EFAULT;
+
+	/* Create _sigregs_ext on the signal stack */
+	if (save_sigregs_ext(regs, &frame->sregs_ext))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ka->sa.sa_flags & SA_RESTORER) {
-                regs->gprs[14] = (unsigned long)
-			ka->sa.sa_restorer | PSW_ADDR_AMODE;
+		restorer = (unsigned long) ka->sa.sa_restorer | PSW_ADDR_AMODE;
 	} else {
-                regs->gprs[14] = (unsigned long)
-			frame->retcode | PSW_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn,
-	                       (u16 __user *)(frame->retcode)))
+		/* Signal frame without vector registers are short ! */
+		__u16 __user *svc = (void *) frame + frame_size - 2;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
 	}
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
-		return -EFAULT;
-
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (unsigned long) frame;
 	/* Force default amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
@@ -247,54 +398,69 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 		regs->gprs[5] = regs->int_parm_long;
 		regs->gprs[6] = task_thread_info(current)->last_break;
 	}
-
-	/* Place signal number on stack to allow backtrace from handler.  */
-	if (__put_user(regs->gprs[2], (int __user *) &frame->signo))
-		return -EFAULT;
 	return 0;
 }
 
 static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 			  struct pt_regs *regs)
 {
-	int err = 0;
-	rt_sigframe __user *frame;
-
-	frame = get_sigframe(&ksig->ka, regs, sizeof(rt_sigframe));
+	struct rt_sigframe __user *frame;
+	unsigned long uc_flags, restorer;
+	size_t frame_size;
 
+	frame_size = sizeof(struct rt_sigframe) - sizeof(_sigregs_ext);
+	/*
+	 * gprs_high are only present for a 31-bit task running on
+	 * a 64-bit kernel (see compat_signal.c) but the space for
+	 * gprs_high need to be allocated if vector registers are
+	 * included in the signal frame on a 31-bit system.
+	 */
+	uc_flags = 0;
+#ifdef CONFIG_64BIT
+	if (MACHINE_HAS_VX) {
+		frame_size += sizeof(_sigregs_ext);
+		if (current->thread.vxrs)
+			uc_flags |= UC_VXRS;
+	}
+#endif
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (copy_siginfo_to_user(&frame->info, &ksig->info))
-		return -EFAULT;
-
-	/* Create the ucontext.  */
-	err |= __put_user(0, &frame->uc.uc_flags);
-	err |= __put_user(NULL, &frame->uc.uc_link);
-	err |= __save_altstack(&frame->uc.uc_stack, regs->gprs[15]);
-	err |= save_sigregs(regs, &frame->uc.uc_mcontext);
-	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-	if (err)
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-                regs->gprs[14] = (unsigned long)
+		restorer = (unsigned long)
 			ksig->ka.sa.sa_restorer | PSW_ADDR_AMODE;
 	} else {
-                regs->gprs[14] = (unsigned long)
-			frame->retcode | PSW_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
-			       (u16 __user *)(frame->retcode)))
+		__u16 __user *svc = &frame->svc_insn;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
 	}
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
+	/* Create siginfo on the signal stack */
+	if (copy_siginfo_to_user(&frame->info, &ksig->info))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create ucontext on the signal stack. */
+	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
+	    __put_user(NULL, &frame->uc.uc_link) ||
+	    __save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
+	    save_sigregs(regs, &frame->uc.uc_mcontext) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    save_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
 		return -EFAULT;
 
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (unsigned long) frame;
 	/* Force default amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index bba0e2469254..13cae5b152d7 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -179,6 +179,9 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 			goto out;
 	}
 #else
+	if (MACHINE_HAS_VX)
+		lc->vector_save_area_addr =
+			(unsigned long) &lc->vector_save_area;
 	if (vdso_alloc_per_cpu(lc))
 		goto out;
 #endif
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index e3e06a4fdfce..9ff5ecba26ab 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -18,6 +18,8 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 int show_unhandled_signals = 1;
@@ -303,6 +305,74 @@ DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN,
 	      "specification exception");
 #endif
 
+#ifdef CONFIG_64BIT
+int alloc_vector_registers(struct task_struct *tsk)
+{
+	__vector128 *vxrs;
+	int i;
+
+	/* Allocate vector register save area. */
+	vxrs = kzalloc(sizeof(__vector128) * __NUM_VXRS,
+		       GFP_KERNEL|__GFP_REPEAT);
+	if (!vxrs)
+		return -ENOMEM;
+	preempt_disable();
+	if (tsk == current)
+		save_fp_regs(tsk->thread.fp_regs.fprs);
+	/* Copy the 16 floating point registers */
+	for (i = 0; i < 16; i++)
+		*(freg_t *) &vxrs[i] = tsk->thread.fp_regs.fprs[i];
+	tsk->thread.vxrs = vxrs;
+	if (tsk == current) {
+		__ctl_set_bit(0, 17);
+		restore_vx_regs(vxrs);
+	}
+	preempt_enable();
+	return 0;
+}
+
+void vector_exception(struct pt_regs *regs)
+{
+	int si_code, vic;
+
+	if (!MACHINE_HAS_VX) {
+		do_trap(regs, SIGILL, ILL_ILLOPN, "illegal operation");
+		return;
+	}
+
+	/* get vector interrupt code from fpc */
+	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	vic = (current->thread.fp_regs.fpc & 0xf00) >> 8;
+	switch (vic) {
+	case 1: /* invalid vector operation */
+		si_code = FPE_FLTINV;
+		break;
+	case 2: /* division by zero */
+		si_code = FPE_FLTDIV;
+		break;
+	case 3: /* overflow */
+		si_code = FPE_FLTOVF;
+		break;
+	case 4: /* underflow */
+		si_code = FPE_FLTUND;
+		break;
+	case 5:	/* inexact */
+		si_code = FPE_FLTRES;
+		break;
+	default: /* unknown cause */
+		si_code = 0;
+	}
+	do_trap(regs, SIGFPE, si_code, "vector exception");
+}
+
+static int __init disable_vector_extension(char *str)
+{
+	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
+	return 1;
+}
+__setup("novx", disable_vector_extension);
+#endif
+
 void data_exception(struct pt_regs *regs)
 {
 	__u16 __user *location;
@@ -368,6 +438,18 @@ void data_exception(struct pt_regs *regs)
                 }
         }
 #endif 
+#ifdef CONFIG_64BIT
+	/* Check for vector register enablement */
+	if (MACHINE_HAS_VX && !current->thread.vxrs &&
+	    (current->thread.fp_regs.fpc & FPC_DXC_MASK) == 0xfe00) {
+		alloc_vector_registers(current);
+		/* Vector data exception is suppressing, rewind psw. */
+		regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
+		clear_pt_regs_flag(regs, PIF_PER_TRAP);
+		return;
+	}
+#endif
+
 	if (current->thread.fp_regs.fpc & FPC_DXC_MASK)
 		signal = SIGFPE;
 	else
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index ef6103bf1f9b..ea9bf2561b9e 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -391,6 +391,8 @@ typedef struct elf64_shdr {
 #define NT_S390_LAST_BREAK	0x306	/* s390 breaking event address */
 #define NT_S390_SYSTEM_CALL	0x307	/* s390 system call restart data */
 #define NT_S390_TDB	0x308		/* s390 transaction diagnostic block */
+#define NT_S390_VXRS_LOW	0x309	/* s390 vector registers 0-15 upper half */
+#define NT_S390_VXRS_HIGH	0x30a	/* s390 vector registers 16-31 */
 #define NT_ARM_VFP	0x400		/* ARM VFP/NEON registers */
 #define NT_ARM_TLS	0x401		/* ARM TLS register */
 #define NT_ARM_HW_BREAK	0x402		/* ARM hardware breakpoint registers */
-- 
cgit v1.2.3


From 33ac9dba859b07d40e9ec826057d20c857fdede5 Mon Sep 17 00:00:00 2001
From: Maarten ter Huurne <maarten@treewalker.org>
Date: Tue, 9 Sep 2014 13:46:28 +0200
Subject: fonts: Add 6x10 font

This font is suitable for framebuffer consoles on devices with a
320x240 screen, to get a reasonable number of characters (53x24) that
are still at a readable size.

The font is derived from the existing 6x11 font, but gets 3 extra
lines without sacrificing readability. Also I redesigned a some glyhps
so they are more distinct and better fill the available space.

Signed-off-by: Maarten ter Huurne <maarten@treewalker.org>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 include/linux/font.h  |    4 +-
 lib/fonts/Kconfig     |    9 +
 lib/fonts/Makefile    |    1 +
 lib/fonts/font_6x10.c | 3086 +++++++++++++++++++++++++++++++++++++++++++++++++
 lib/fonts/fonts.c     |    4 +
 5 files changed, 3103 insertions(+), 1 deletion(-)
 create mode 100644 lib/fonts/font_6x10.c

(limited to 'include')

diff --git a/include/linux/font.h b/include/linux/font.h
index 40a24ab41b36..d6821769dd1e 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -31,6 +31,7 @@ struct font_desc {
 #define SUN12x22_IDX	7
 #define ACORN8x8_IDX	8
 #define	MINI4x6_IDX	9
+#define FONT6x10_IDX	10
 
 extern const struct font_desc	font_vga_8x8,
 			font_vga_8x16,
@@ -41,7 +42,8 @@ extern const struct font_desc	font_vga_8x8,
 			font_sun_8x16,
 			font_sun_12x22,
 			font_acorn_8x8,
-			font_mini_4x6;
+			font_mini_4x6,
+			font_6x10;
 
 /* Find a font with a specific name */
 
diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig
index 34fd931b54b5..e77dfe00de36 100644
--- a/lib/fonts/Kconfig
+++ b/lib/fonts/Kconfig
@@ -79,6 +79,14 @@ config FONT_MINI_4x6
 	bool "Mini 4x6 font"
 	depends on !SPARC && FONTS
 
+config FONT_6x10
+	bool "Medium-size 6x10 font"
+	depends on !SPARC && FONTS
+	help
+	  Medium-size console font. Suitable for framebuffer consoles on
+	  embedded devices with a 320x240 screen, to get a reasonable number
+	  of characters (53x24) that are still at a readable size.
+
 config FONT_SUN8x16
 	bool "Sparc console 8x16 font"
 	depends on FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC)
@@ -109,6 +117,7 @@ config FONT_AUTOSELECT
 	depends on !FONT_PEARL_8x8
 	depends on !FONT_ACORN_8x8
 	depends on !FONT_MINI_4x6
+	depends on !FONT_6x10
 	depends on !FONT_SUN8x16
 	depends on !FONT_SUN12x22
 	depends on !FONT_10x18
diff --git a/lib/fonts/Makefile b/lib/fonts/Makefile
index 2761560f3f15..e04d010cfbf5 100644
--- a/lib/fonts/Makefile
+++ b/lib/fonts/Makefile
@@ -12,6 +12,7 @@ font-objs-$(CONFIG_FONT_10x18)     += font_10x18.o
 font-objs-$(CONFIG_FONT_PEARL_8x8) += font_pearl_8x8.o
 font-objs-$(CONFIG_FONT_ACORN_8x8) += font_acorn_8x8.o
 font-objs-$(CONFIG_FONT_MINI_4x6)  += font_mini_4x6.o
+font-objs-$(CONFIG_FONT_6x10)      += font_6x10.o
 
 font-objs += $(font-objs-y)
 
diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c
new file mode 100644
index 000000000000..b20620904d31
--- /dev/null
+++ b/lib/fonts/font_6x10.c
@@ -0,0 +1,3086 @@
+#include <linux/font.h>
+
+static const unsigned char fontdata_6x10[] = {
+
+	/* 0 0x00 '^@' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 1 0x01 '^A' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x84, /* 10000100 */
+	0xCC, /* 11001100 */
+	0x84, /* 10000100 */
+	0xCC, /* 11001100 */
+	0xB4, /* 10110100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 2 0x02 '^B' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0xFC, /* 11111100 */
+	0xB4, /* 10110100 */
+	0xFC, /* 11111100 */
+	0xB4, /* 10110100 */
+	0xCC, /* 11001100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 3 0x03 '^C' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x7C, /* 01111100 */
+	0x7C, /* 01111100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 4 0x04 '^D' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x7C, /* 01111100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 5 0x05 '^E' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x6C, /* 01101100 */
+	0x6C, /* 01101100 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 6 0x06 '^F' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x7C, /* 01111100 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 7 0x07 '^G' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x78, /* 01111000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 8 0x08 '^H' */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xCC, /* 11001100 */
+	0x84, /* 10000100 */
+	0xCC, /* 11001100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+
+	/* 9 0x09 '^I' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x84, /* 10000100 */
+	0x48, /* 01001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 10 0x0A '^J' */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xCC, /* 11001100 */
+	0xB4, /* 10110100 */
+	0x78, /* 01111000 */
+	0xB4, /* 10110100 */
+	0xCC, /* 11001100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+
+	/* 11 0x0B '^K' */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x14, /* 00010100 */
+	0x20, /* 00100000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 12 0x0C '^L' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 13 0x0D '^M' */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x14, /* 00010100 */
+	0x14, /* 00010100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x70, /* 01110000 */
+	0x60, /* 01100000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 14 0x0E '^N' */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x24, /* 00100100 */
+	0x3C, /* 00111100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x6C, /* 01101100 */
+	0x6C, /* 01101100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 15 0x0F '^O' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x6C, /* 01101100 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 16 0x10 '^P' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x60, /* 01100000 */
+	0x70, /* 01110000 */
+	0x78, /* 01111000 */
+	0x70, /* 01110000 */
+	0x60, /* 01100000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 17 0x11 '^Q' */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x0C, /* 00001100 */
+	0x1C, /* 00011100 */
+	0x3C, /* 00111100 */
+	0x1C, /* 00011100 */
+	0x0C, /* 00001100 */
+	0x04, /* 00000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 18 0x12 '^R' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 19 0x13 '^S' */
+	0x00, /* 00000000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x00, /* 00000000 */
+	0x48, /* 01001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 20 0x14 '^T' */
+	0x3C, /* 00111100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x3C, /* 00111100 */
+	0x14, /* 00010100 */
+	0x14, /* 00010100 */
+	0x14, /* 00010100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 21 0x15 '^U' */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x20, /* 00100000 */
+	0x50, /* 01010000 */
+	0x48, /* 01001000 */
+	0x24, /* 00100100 */
+	0x14, /* 00010100 */
+	0x08, /* 00001000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+
+	/* 22 0x16 '^V' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF8, /* 11111000 */
+	0xF8, /* 11111000 */
+	0xF8, /* 11111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 23 0x17 '^W' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+
+	/* 24 0x18 '^X' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 25 0x19 '^Y' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 26 0x1A '^Z' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x7C, /* 01111100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 27 0x1B '^[' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x7C, /* 01111100 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 28 0x1C '^\' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 29 0x1D '^]' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x48, /* 01001000 */
+	0x84, /* 10000100 */
+	0xFC, /* 11111100 */
+	0x84, /* 10000100 */
+	0x48, /* 01001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 30 0x1E '^^' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x7C, /* 01111100 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 31 0x1F '^_' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x7C, /* 01111100 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 32 0x20 ' ' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 33 0x21 '!' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 34 0x22 '"' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 35 0x23 '#' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x7C, /* 01111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x7C, /* 01111100 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 36 0x24 '$' */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x50, /* 01010000 */
+	0x38, /* 00111000 */
+	0x14, /* 00010100 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+
+	/* 37 0x25 '%' */
+	0x00, /* 00000000 */
+	0x64, /* 01100100 */
+	0x64, /* 01100100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x4C, /* 01001100 */
+	0x4C, /* 01001100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 38 0x26 '&' */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x50, /* 01010000 */
+	0x20, /* 00100000 */
+	0x54, /* 01010100 */
+	0x48, /* 01001000 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 39 0x27 ''' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 40 0x28 '(' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+
+	/* 41 0x29 ')' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+
+	/* 42 0x2A '*' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 43 0x2B '+' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 44 0x2C ',' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+
+	/* 45 0x2D '-' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 46 0x2E '.' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 47 0x2F '/' */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+
+	/* 48 0x30 '0' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x54, /* 01010100 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 49 0x31 '1' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x30, /* 00110000 */
+	0x50, /* 01010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 50 0x32 '2' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 51 0x33 '3' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x04, /* 00000100 */
+	0x18, /* 00011000 */
+	0x04, /* 00000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 52 0x34 '4' */
+	0x00, /* 00000000 */
+	0x08, /* 00001000 */
+	0x18, /* 00011000 */
+	0x28, /* 00101000 */
+	0x48, /* 01001000 */
+	0x7C, /* 01111100 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 53 0x35 '5' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 54 0x36 '6' */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x20, /* 00100000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 55 0x37 '7' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 56 0x38 '8' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 57 0x39 '9' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 58 0x3A ':' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 59 0x3B ';' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+
+	/* 60 0x3C '<' */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x04, /* 00000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 61 0x3D '=' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 62 0x3E '>' */
+	0x00, /* 00000000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 63 0x3F '?' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 64 0x40 '@' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x5C, /* 01011100 */
+	0x54, /* 01010100 */
+	0x5C, /* 01011100 */
+	0x40, /* 01000000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 65 0x41 'A' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 66 0x42 'B' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x38, /* 00111000 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 67 0x43 'C' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 68 0x44 'D' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 69 0x45 'E' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 70 0x46 'F' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 71 0x47 'G' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x5C, /* 01011100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 72 0x48 'H' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 73 0x49 'I' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 74 0x4A 'J' */
+	0x00, /* 00000000 */
+	0x1C, /* 00011100 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 75 0x4B 'K' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x48, /* 01001000 */
+	0x50, /* 01010000 */
+	0x60, /* 01100000 */
+	0x50, /* 01010000 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 76 0x4C 'L' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 77 0x4D 'M' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x6C, /* 01101100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 78 0x4E 'N' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x64, /* 01100100 */
+	0x54, /* 01010100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 79 0x4F 'O' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 80 0x50 'P' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x78, /* 01111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 81 0x51 'Q' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x54, /* 01010100 */
+	0x48, /* 01001000 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 82 0x52 'R' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x78, /* 01111000 */
+	0x50, /* 01010000 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 83 0x53 'S' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 84 0x54 'T' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 85 0x55 'U' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 86 0x56 'V' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 87 0x57 'W' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x6C, /* 01101100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 88 0x58 'X' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 89 0x59 'Y' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 90 0x5A 'Z' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x40, /* 01000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 91 0x5B '[' */
+	0x18, /* 00011000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+
+	/* 92 0x5C '\' */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+
+	/* 93 0x5D ']' */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+
+	/* 94 0x5E '^' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 95 0x5F '_' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+
+	/* 96 0x60 '`' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 97 0x61 'a' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 98 0x62 'b' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x64, /* 01100100 */
+	0x58, /* 01011000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 99 0x63 'c' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 100 0x64 'd' */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x34, /* 00110100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 101 0x65 'e' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 102 0x66 'f' */
+	0x00, /* 00000000 */
+	0x0C, /* 00001100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 103 0x67 'g' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x34, /* 00110100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x04, /* 00000100 */
+	0x38, /* 00111000 */
+
+	/* 104 0x68 'h' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 105 0x69 'i' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 106 0x6A 'j' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x60, /* 01100000 */
+
+	/* 107 0x6B 'k' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x48, /* 01001000 */
+	0x50, /* 01010000 */
+	0x70, /* 01110000 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 108 0x6C 'l' */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 109 0x6D 'm' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x68, /* 01101000 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 110 0x6E 'n' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 111 0x6F 'o' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 112 0x70 'p' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x64, /* 01100100 */
+	0x58, /* 01011000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+
+	/* 113 0x71 'q' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x34, /* 00110100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+
+	/* 114 0x72 'r' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 115 0x73 's' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x40, /* 01000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 116 0x74 't' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x0C, /* 00001100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 117 0x75 'u' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 118 0x76 'v' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 119 0x77 'w' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 120 0x78 'x' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 121 0x79 'y' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x04, /* 00000100 */
+	0x38, /* 00111000 */
+
+	/* 122 0x7A 'z' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 123 0x7B '{' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+
+	/* 124 0x7C '|' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+
+	/* 125 0x7D '}' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+
+	/* 126 0x7E '~' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x20, /* 00100000 */
+	0x54, /* 01010100 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 127 0x7F '' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 128 0x80 '\200' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+
+	/* 129 0x81 '\201' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 130 0x82 '\202' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 131 0x83 '\203' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 132 0x84 '\204' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 133 0x85 '\205' */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 134 0x86 '\206' */
+	0x18, /* 00011000 */
+	0x24, /* 00100100 */
+	0x18, /* 00011000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 135 0x87 '\207' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+
+	/* 136 0x88 '\210' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 137 0x89 '\211' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 138 0x8A '\212' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 139 0x8B '\213' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 140 0x8C '\214' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 141 0x8D '\215' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 142 0x8E '\216' */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 143 0x8F '\217' */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 144 0x90 '\220' */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 145 0x91 '\221' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x14, /* 00010100 */
+	0x7C, /* 01111100 */
+	0x50, /* 01010000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 146 0x92 '\222' */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x78, /* 01111000 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x5C, /* 01011100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 147 0x93 '\223' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 148 0x94 '\224' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 149 0x95 '\225' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 150 0x96 '\226' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 151 0x97 '\227' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 152 0x98 '\230' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x04, /* 00000100 */
+	0x38, /* 00111000 */
+
+	/* 153 0x99 '\231' */
+	0x84, /* 10000100 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 154 0x9A '\232' */
+	0x88, /* 10001000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 155 0x9B '\233' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x50, /* 01010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+
+	/* 156 0x9C '\234' */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x40, /* 01000000 */
+	0x70, /* 01110000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 157 0x9D '\235' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 158 0x9E '\236' */
+	0x00, /* 00000000 */
+	0x70, /* 01110000 */
+	0x48, /* 01001000 */
+	0x70, /* 01110000 */
+	0x48, /* 01001000 */
+	0x5C, /* 01011100 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 159 0x9F '\237' */
+	0x00, /* 00000000 */
+	0x0C, /* 00001100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x60, /* 01100000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 160 0xA0 '\240' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 161 0xA1 '\241' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 162 0xA2 '\242' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 163 0xA3 '\243' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 164 0xA4 '\244' */
+	0x34, /* 00110100 */
+	0x58, /* 01011000 */
+	0x00, /* 00000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 165 0xA5 '\245' */
+	0x58, /* 01011000 */
+	0x44, /* 01000100 */
+	0x64, /* 01100100 */
+	0x54, /* 01010100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 166 0xA6 '\246' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 167 0xA7 '\247' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 168 0xA8 '\250' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 169 0xA9 '\251' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 170 0xAA '\252' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 171 0xAB '\253' */
+	0x20, /* 00100000 */
+	0x60, /* 01100000 */
+	0x24, /* 00100100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x08, /* 00001000 */
+	0x1C, /* 00011100 */
+	0x00, /* 00000000 */
+
+	/* 172 0xAC '\254' */
+	0x20, /* 00100000 */
+	0x60, /* 01100000 */
+	0x24, /* 00100100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x58, /* 01011000 */
+	0x3C, /* 00111100 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+
+	/* 173 0xAD '\255' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 174 0xAE '\256' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x24, /* 00100100 */
+	0x48, /* 01001000 */
+	0x90, /* 10010000 */
+	0x48, /* 01001000 */
+	0x24, /* 00100100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 175 0xAF '\257' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x90, /* 10010000 */
+	0x48, /* 01001000 */
+	0x24, /* 00100100 */
+	0x48, /* 01001000 */
+	0x90, /* 10010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 176 0xB0 '\260' */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+
+	/* 177 0xB1 '\261' */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+
+	/* 178 0xB2 '\262' */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+
+	/* 179 0xB3 '\263' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 180 0xB4 '\264' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 181 0xB5 '\265' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 182 0xB6 '\266' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xE8, /* 11101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 183 0xB7 '\267' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF8, /* 11111000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 184 0xB8 '\270' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 185 0xB9 '\271' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xE8, /* 11101000 */
+	0x08, /* 00001000 */
+	0xE8, /* 11101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 186 0xBA '\272' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 187 0xBB '\273' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF8, /* 11111000 */
+	0x08, /* 00001000 */
+	0xE8, /* 11101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 188 0xBC '\274' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xE8, /* 11101000 */
+	0x08, /* 00001000 */
+	0xF8, /* 11111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 189 0xBD '\275' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xF8, /* 11111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 190 0xBE '\276' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 191 0xBF '\277' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 192 0xC0 '\300' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 193 0xC1 '\301' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 194 0xC2 '\302' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 195 0xC3 '\303' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 196 0xC4 '\304' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 197 0xC5 '\305' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 198 0xC6 '\306' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 199 0xC7 '\307' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x2C, /* 00101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 200 0xC8 '\310' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x2C, /* 00101100 */
+	0x20, /* 00100000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 201 0xC9 '\311' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x20, /* 00100000 */
+	0x2C, /* 00101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 202 0xCA '\312' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xEC, /* 11101100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 203 0xCB '\313' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xEC, /* 11101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 204 0xCC '\314' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x2C, /* 00101100 */
+	0x20, /* 00100000 */
+	0x2C, /* 00101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 205 0xCD '\315' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 206 0xCE '\316' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xEC, /* 11101100 */
+	0x00, /* 00000000 */
+	0xEC, /* 11101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 207 0xCF '\317' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 208 0xD0 '\320' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 209 0xD1 '\321' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 210 0xD2 '\322' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 211 0xD3 '\323' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 212 0xD4 '\324' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 213 0xD5 '\325' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 214 0xD6 '\326' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 215 0xD7 '\327' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xFC, /* 11111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 216 0xD8 '\330' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 217 0xD9 '\331' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 218 0xDA '\332' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 219 0xDB '\333' */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+
+	/* 220 0xDC '\334' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+
+	/* 221 0xDD '\335' */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+
+	/* 222 0xDE '\336' */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+
+	/* 223 0xDF '\337' */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 224 0xE0 '\340' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x34, /* 00110100 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 225 0xE1 '\341' */
+	0x18, /* 00011000 */
+	0x24, /* 00100100 */
+	0x44, /* 01000100 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x58, /* 01011000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+
+	/* 226 0xE2 '\342' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 227 0xE3 '\343' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 228 0xE4 '\344' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x24, /* 00100100 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x24, /* 00100100 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 229 0xE5 '\345' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 230 0xE6 '\346' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x74, /* 01110100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+
+	/* 231 0xE7 '\347' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x0C, /* 00001100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 232 0xE8 '\350' */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 233 0xE9 '\351' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 234 0xEA '\352' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x6C, /* 01101100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 235 0xEB '\353' */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x20, /* 00100000 */
+	0x18, /* 00011000 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 236 0xEC '\354' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 237 0xED '\355' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 238 0xEE '\356' */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x38, /* 00111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 239 0xEF '\357' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 240 0xF0 '\360' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 241 0xF1 '\361' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 242 0xF2 '\362' */
+	0x00, /* 00000000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 243 0xF3 '\363' */
+	0x00, /* 00000000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 244 0xF4 '\364' */
+	0x00, /* 00000000 */
+	0x0C, /* 00001100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 245 0xF5 '\365' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x60, /* 01100000 */
+	0x00, /* 00000000 */
+
+	/* 246 0xF6 '\366' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 247 0xF7 '\367' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x20, /* 00100000 */
+	0x54, /* 01010100 */
+	0x08, /* 00001000 */
+	0x20, /* 00100000 */
+	0x54, /* 01010100 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 248 0xF8 '\370' */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 249 0xF9 '\371' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 250 0xFA '\372' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 251 0xFB '\373' */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 252 0xFC '\374' */
+	0x60, /* 01100000 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 253 0xFD '\375' */
+	0x60, /* 01100000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x70, /* 01110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 254 0xFE '\376' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 255 0xFF '\377' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+};
+
+const struct font_desc font_6x10 = {
+	.idx	= FONT6x10_IDX,
+	.name	= "6x10",
+	.width	= 6,
+	.height	= 10,
+	.data	= fontdata_6x10,
+	.pref	= 0,
+};
diff --git a/lib/fonts/fonts.c b/lib/fonts/fonts.c
index f947189efe6d..823376ca0a8b 100644
--- a/lib/fonts/fonts.c
+++ b/lib/fonts/fonts.c
@@ -63,6 +63,10 @@ static const struct font_desc *fonts[] = {
 #undef NO_FONTS
     &font_mini_4x6,
 #endif
+#ifdef CONFIG_FONT_6x10
+#undef NO_FONTS
+    &font_6x10,
+#endif
 };
 
 #define num_fonts ARRAY_SIZE(fonts)
-- 
cgit v1.2.3


From b8839b8c55f3fdd60dc36abcda7e0266aff7985c Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Wed, 8 Oct 2014 18:26:13 -0400
Subject: block: fix alignment_offset math that assumes io_min is a power-of-2

The math in both blk_stack_limits() and queue_limit_alignment_offset()
assume that a block device's io_min (aka minimum_io_size) is always a
power-of-2.  Fix the math such that it works for non-power-of-2 io_min.

This issue (of alignment_offset != 0) became apparent when testing
dm-thinp with a thinp blocksize that matches a RAID6 stripesize of
1280K.  Commit fdfb4c8c1 ("dm thin: set minimum_io_size to pool's data
block size") unlocked the potential for alignment_offset != 0 due to
the dm-thin-pool's io_min possibly being a non-power-of-2.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-settings.c   | 4 ++--
 include/linux/blkdev.h | 5 ++---
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index f1a1795a5683..aa02247d227e 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -574,7 +574,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		bottom = max(b->physical_block_size, b->io_min) + alignment;
 
 		/* Verify that top and bottom intervals line up */
-		if (max(top, bottom) & (min(top, bottom) - 1)) {
+		if (max(top, bottom) % min(top, bottom)) {
 			t->misaligned = 1;
 			ret = -1;
 		}
@@ -619,7 +619,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	/* Find lowest common alignment_offset */
 	t->alignment_offset = lcm(t->alignment_offset, alignment)
-		& (max(t->physical_block_size, t->io_min) - 1);
+		% max(t->physical_block_size, t->io_min);
 
 	/* Verify that new alignment_offset is on a logical block boundary */
 	if (t->alignment_offset & (t->logical_block_size - 1)) {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 038b40f84c7a..554639249fd6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1279,10 +1279,9 @@ static inline int queue_alignment_offset(struct request_queue *q)
 static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
-	unsigned int alignment = (sector << 9) & (granularity - 1);
+	unsigned int alignment = sector_div(sector, granularity >> 9) << 9;
 
-	return (granularity + lim->alignment_offset - alignment)
-		& (granularity - 1);
+	return (granularity + lim->alignment_offset - alignment) % granularity;
 }
 
 static inline int bdev_alignment_offset(struct block_device *bdev)
-- 
cgit v1.2.3


From 58cb65487e92b47448d00a711c9f5922137d5678 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Thu, 9 Oct 2014 15:25:54 -0700
Subject: proc/maps: make vm_is_stack() logic namespace-friendly

- Rename vm_is_stack() to task_of_stack() and change it to return
  "struct task_struct *" rather than the global (and thus wrong in
  general) pid_t.

- Add the new pid_of_stack() helper which calls task_of_stack() and
  uses the right namespace to report the correct pid_t.

  Unfortunately we need to define this helper twice, in task_mmu.c
  and in task_nommu.c. perhaps it makes sense to add fs/proc/util.c
  and move at least pid_of_stack/task_of_stack there to avoid the
  code duplication.

- Change show_map_vma() and show_numa_map() to use the new helper.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Greg Ungerer <gerg@uclinux.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c   | 25 +++++++++++++++++++++----
 fs/proc/task_nommu.c | 21 ++++++++++++++++++++-
 include/linux/mm.h   |  4 ++--
 mm/util.c            | 23 ++++++++---------------
 4 files changed, 51 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4793e4a843b0..adddf697c4ea 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -261,13 +261,31 @@ static int do_maps_open(struct inode *inode, struct file *file,
 				sizeof(struct proc_maps_private));
 }
 
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+				struct vm_area_struct *vma, bool is_pid)
+{
+	struct inode *inode = priv->inode;
+	struct task_struct *task;
+	pid_t ret = 0;
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (task) {
+		task = task_of_stack(task, vma, is_pid);
+		if (task)
+			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static void
 show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
 	struct proc_maps_private *priv = m->private;
-	struct task_struct *task = priv->task;
 	vm_flags_t flags = vma->vm_flags;
 	unsigned long ino = 0;
 	unsigned long long pgoff = 0;
@@ -332,8 +350,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			goto done;
 		}
 
-		tid = vm_is_stack(task, vma, is_pid);
-
+		tid = pid_of_stack(priv, vma, is_pid);
 		if (tid != 0) {
 			/*
 			 * Thread stack in /proc/PID/task/TID/maps or
@@ -1446,7 +1463,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
 	} else {
-		pid_t tid = vm_is_stack(task, vma, is_pid);
+		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
 		if (tid != 0) {
 			/*
 			 * Thread stack in /proc/PID/task/TID/maps or
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index f36e213835cc..599ec2e20104 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -123,6 +123,25 @@ unsigned long task_statm(struct mm_struct *mm,
 	return size;
 }
 
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+				struct vm_area_struct *vma, bool is_pid)
+{
+	struct inode *inode = priv->inode;
+	struct task_struct *task;
+	pid_t ret = 0;
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (task) {
+		task = task_of_stack(task, vma, is_pid);
+		if (task)
+			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /*
  * display a single VMA to a sequenced file
  */
@@ -163,7 +182,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
 		seq_pad(m, ' ');
 		seq_path(m, &file->f_path, "");
 	} else if (mm) {
-		pid_t tid = vm_is_stack(priv->task, vma, is_pid);
+		pid_t tid = pid_of_stack(priv, vma, is_pid);
 
 		if (tid != 0) {
 			seq_pad(m, ' ');
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0f4196a0bc20..28df70774b81 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1247,8 +1247,8 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
 		!vma_growsup(vma->vm_next, addr);
 }
 
-extern pid_t
-vm_is_stack(struct task_struct *task, struct vm_area_struct *vma, int in_group);
+extern struct task_struct *task_of_stack(struct task_struct *task,
+				struct vm_area_struct *vma, bool in_group);
 
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
diff --git a/mm/util.c b/mm/util.c
index 093c973f1697..fec39d4509a9 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -170,32 +170,25 @@ static int vm_is_stack_for_task(struct task_struct *t,
 /*
  * Check if the vma is being used as a stack.
  * If is_group is non-zero, check in the entire thread group or else
- * just check in the current task. Returns the pid of the task that
- * the vma is stack for.
+ * just check in the current task. Returns the task_struct of the task
+ * that the vma is stack for. Must be called under rcu_read_lock().
  */
-pid_t vm_is_stack(struct task_struct *task,
-		  struct vm_area_struct *vma, int in_group)
+struct task_struct *task_of_stack(struct task_struct *task,
+				struct vm_area_struct *vma, bool in_group)
 {
-	pid_t ret = 0;
-
 	if (vm_is_stack_for_task(task, vma))
-		return task->pid;
+		return task;
 
 	if (in_group) {
 		struct task_struct *t;
 
-		rcu_read_lock();
 		for_each_thread(task, t) {
-			if (vm_is_stack_for_task(t, vma)) {
-				ret = t->pid;
-				goto done;
-			}
+			if (vm_is_stack_for_task(t, vma))
+				return t;
 		}
-done:
-		rcu_read_unlock();
 	}
 
-	return ret;
+	return NULL;
 }
 
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
-- 
cgit v1.2.3


From 07f361b2bee38896df8be17d8c3f8af3f3610606 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Thu, 9 Oct 2014 15:26:00 -0700
Subject: mm/slab_common: move kmem_cache definition to internal header

We don't need to keep kmem_cache definition in include/linux/slab.h if we
don't need to inline kmem_cache_size().  According to my code inspection,
this function is only called at lc_create() in lib/lru_cache.c which may
be called at initialization phase of something, so we don't need to inline
it.  Therfore, move it to slab_common.c and move kmem_cache definition to
internal header.

After this change, we can change kmem_cache definition easily without full
kernel build.  For instance, we can turn on/off CONFIG_SLUB_STATS without
full kernel build.

[akpm@linux-foundation.org: export kmem_cache_size() to modules]
[rdunlap@infradead.org: add header files to fix kmemcheck.c build errors]
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slab.h | 42 +-----------------------------------------
 mm/kmemcheck.c       |  1 +
 mm/slab.h            | 35 +++++++++++++++++++++++++++++++++++
 mm/slab_common.c     |  9 +++++++++
 4 files changed, 46 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 1d9abb7d22a0..9062e4ad1787 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -158,31 +158,6 @@ size_t ksize(const void *);
 #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
 #endif
 
-#ifdef CONFIG_SLOB
-/*
- * Common fields provided in kmem_cache by all slab allocators
- * This struct is either used directly by the allocator (SLOB)
- * or the allocator must include definitions for all fields
- * provided in kmem_cache_common in their definition of kmem_cache.
- *
- * Once we can do anonymous structs (C11 standard) we could put a
- * anonymous struct definition in these allocators so that the
- * separate allocations in the kmem_cache structure of SLAB and
- * SLUB is no longer needed.
- */
-struct kmem_cache {
-	unsigned int object_size;/* The original size of the object */
-	unsigned int size;	/* The aligned/padded/added on size  */
-	unsigned int align;	/* Alignment as calculated */
-	unsigned long flags;	/* Active flags on the slab */
-	const char *name;	/* Slab name for sysfs */
-	int refcount;		/* Use counter */
-	void (*ctor)(void *);	/* Called on object slot creation */
-	struct list_head list;	/* List of all slab caches on the system */
-};
-
-#endif /* CONFIG_SLOB */
-
 /*
  * Kmalloc array related definitions
  */
@@ -363,14 +338,6 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s,
 }
 #endif /* CONFIG_TRACING */
 
-#ifdef CONFIG_SLAB
-#include <linux/slab_def.h>
-#endif
-
-#ifdef CONFIG_SLUB
-#include <linux/slub_def.h>
-#endif
-
 extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order);
 
 #ifdef CONFIG_TRACING
@@ -650,14 +617,7 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node)
 	return kmalloc_node(size, flags | __GFP_ZERO, node);
 }
 
-/*
- * Determine the size of a slab object
- */
-static inline unsigned int kmem_cache_size(struct kmem_cache *s)
-{
-	return s->object_size;
-}
-
+unsigned int kmem_cache_size(struct kmem_cache *s);
 void __init kmem_cache_init_late(void);
 
 #endif	/* _LINUX_SLAB_H */
diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c
index fd814fd61319..cab58bb592d8 100644
--- a/mm/kmemcheck.c
+++ b/mm/kmemcheck.c
@@ -2,6 +2,7 @@
 #include <linux/mm_types.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include "slab.h"
 #include <linux/kmemcheck.h>
 
 void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
diff --git a/mm/slab.h b/mm/slab.h
index 0e0fdd365840..026e7c393f0b 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -4,6 +4,41 @@
  * Internal slab definitions
  */
 
+#ifdef CONFIG_SLOB
+/*
+ * Common fields provided in kmem_cache by all slab allocators
+ * This struct is either used directly by the allocator (SLOB)
+ * or the allocator must include definitions for all fields
+ * provided in kmem_cache_common in their definition of kmem_cache.
+ *
+ * Once we can do anonymous structs (C11 standard) we could put a
+ * anonymous struct definition in these allocators so that the
+ * separate allocations in the kmem_cache structure of SLAB and
+ * SLUB is no longer needed.
+ */
+struct kmem_cache {
+	unsigned int object_size;/* The original size of the object */
+	unsigned int size;	/* The aligned/padded/added on size  */
+	unsigned int align;	/* Alignment as calculated */
+	unsigned long flags;	/* Active flags on the slab */
+	const char *name;	/* Slab name for sysfs */
+	int refcount;		/* Use counter */
+	void (*ctor)(void *);	/* Called on object slot creation */
+	struct list_head list;	/* List of all slab caches on the system */
+};
+
+#endif /* CONFIG_SLOB */
+
+#ifdef CONFIG_SLAB
+#include <linux/slab_def.h>
+#endif
+
+#ifdef CONFIG_SLUB
+#include <linux/slub_def.h>
+#endif
+
+#include <linux/memcontrol.h>
+
 /*
  * State of the slab allocator.
  *
diff --git a/mm/slab_common.c b/mm/slab_common.c
index cabb842c4e7c..d7d8ffd0c306 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -30,6 +30,15 @@ LIST_HEAD(slab_caches);
 DEFINE_MUTEX(slab_mutex);
 struct kmem_cache *kmem_cache;
 
+/*
+ * Determine the size of a slab object
+ */
+unsigned int kmem_cache_size(struct kmem_cache *s)
+{
+	return s->object_size;
+}
+EXPORT_SYMBOL(kmem_cache_size);
+
 #ifdef CONFIG_DEBUG_VM
 static int kmem_cache_sanity_check(const char *name, size_t size)
 {
-- 
cgit v1.2.3


From 61f47105a2c9c60e950ca808b7560f776f9bfa31 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Thu, 9 Oct 2014 15:26:02 -0700
Subject: mm/sl[ao]b: always track caller in kmalloc_(node_)track_caller()

Now, we track caller if tracing or slab debugging is enabled.  If they are
disabled, we could save one argument passing overhead by calling
__kmalloc(_node)().  But, I think that it would be marginal.  Furthermore,
default slab allocator, SLUB, doesn't use this technique so I think that
it's okay to change this situation.

After this change, we can turn on/off CONFIG_DEBUG_SLAB without full
kernel build and remove some complicated '#if' defintion.  It looks more
benefitial to me.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slab.h | 22 ----------------------
 mm/slab.c            | 18 ------------------
 mm/slob.c            |  2 --
 3 files changed, 42 deletions(-)

(limited to 'include')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9062e4ad1787..c265bec6a57d 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -549,37 +549,15 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
  * allocator where we care about the real place the memory allocation
  * request comes from.
  */
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
-	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) || \
-	(defined(CONFIG_SLOB) && defined(CONFIG_TRACING))
 extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
 #define kmalloc_track_caller(size, flags) \
 	__kmalloc_track_caller(size, flags, _RET_IP_)
-#else
-#define kmalloc_track_caller(size, flags) \
-	__kmalloc(size, flags)
-#endif /* DEBUG_SLAB */
 
 #ifdef CONFIG_NUMA
-/*
- * kmalloc_node_track_caller is a special version of kmalloc_node that
- * records the calling function of the routine calling it for slab leak
- * tracking instead of just the calling function (confusing, eh?).
- * It's useful when the call to kmalloc_node comes from a widely-used
- * standard allocator where we care about the real place the memory
- * allocation request comes from.
- */
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
-	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) || \
-	(defined(CONFIG_SLOB) && defined(CONFIG_TRACING))
 extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long);
 #define kmalloc_node_track_caller(size, flags, node) \
 	__kmalloc_node_track_caller(size, flags, node, \
 			_RET_IP_)
-#else
-#define kmalloc_node_track_caller(size, flags, node) \
-	__kmalloc_node(size, flags, node)
-#endif
 
 #else /* CONFIG_NUMA */
 
diff --git a/mm/slab.c b/mm/slab.c
index 7c52b3890d25..c52bc5aa6ba0 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3496,7 +3496,6 @@ __do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
 	return kmem_cache_alloc_node_trace(cachep, flags, node, size);
 }
 
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
 void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
 	return __do_kmalloc_node(size, flags, node, _RET_IP_);
@@ -3509,13 +3508,6 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
 	return __do_kmalloc_node(size, flags, node, caller);
 }
 EXPORT_SYMBOL(__kmalloc_node_track_caller);
-#else
-void *__kmalloc_node(size_t size, gfp_t flags, int node)
-{
-	return __do_kmalloc_node(size, flags, node, 0);
-}
-EXPORT_SYMBOL(__kmalloc_node);
-#endif /* CONFIG_DEBUG_SLAB || CONFIG_TRACING */
 #endif /* CONFIG_NUMA */
 
 /**
@@ -3541,8 +3533,6 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	return ret;
 }
 
-
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
 void *__kmalloc(size_t size, gfp_t flags)
 {
 	return __do_kmalloc(size, flags, _RET_IP_);
@@ -3555,14 +3545,6 @@ void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller)
 }
 EXPORT_SYMBOL(__kmalloc_track_caller);
 
-#else
-void *__kmalloc(size_t size, gfp_t flags)
-{
-	return __do_kmalloc(size, flags, 0);
-}
-EXPORT_SYMBOL(__kmalloc);
-#endif
-
 /**
  * kmem_cache_free - Deallocate an object
  * @cachep: The cache the allocation was from.
diff --git a/mm/slob.c b/mm/slob.c
index 21980e0f39a8..96a86206a26b 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -468,7 +468,6 @@ void *__kmalloc(size_t size, gfp_t gfp)
 }
 EXPORT_SYMBOL(__kmalloc);
 
-#ifdef CONFIG_TRACING
 void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller)
 {
 	return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller);
@@ -481,7 +480,6 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
 	return __do_kmalloc_node(size, gfp, node, caller);
 }
 #endif
-#endif
 
 void kfree(const void *block)
 {
-- 
cgit v1.2.3


From ad2c8144418c6a81cefe65379fd47bbe8344cef2 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Thu, 9 Oct 2014 15:26:13 -0700
Subject: topology: add support for node_to_mem_node() to determine the
 fallback node

Anton noticed (http://www.spinics.net/lists/linux-mm/msg67489.html) that
on ppc LPARs with memoryless nodes, a large amount of memory was consumed
by slabs and was marked unreclaimable.  He tracked it down to slab
deactivations in the SLUB core when we allocate remotely, leading to poor
efficiency always when memoryless nodes are present.

After much discussion, Joonsoo provided a few patches that help
significantly.  They don't resolve the problem altogether:

 - memory hotplug still needs testing, that is when a memoryless node
   becomes memory-ful, we want to dtrt
 - there are other reasons for going off-node than memoryless nodes,
   e.g., fully exhausted local nodes

Neither case is resolved with this series, but I don't think that should
block their acceptance, as they can be explored/resolved with follow-on
patches.

The series consists of:

[1/3] topology: add support for node_to_mem_node() to determine the
      fallback node

[2/3] slub: fallback to node_to_mem_node() node if allocating on
      memoryless node

      - Joonsoo's patches to cache the nearest node with memory for each
        NUMA node

[3/3] Partial revert of 81c98869faa5 (""kthread: ensure locality of
      task_struct allocations")

 - At Tejun's request, keep the knowledge of memoryless node fallback
   to the allocator core.

This patch (of 3):

We need to determine the fallback node in slub allocator if the allocation
target node is memoryless node.  Without it, the SLUB wrongly select the
node which has no memory and can't use a partial slab, because of node
mismatch.  Introduced function, node_to_mem_node(X), will return a node Y
with memory that has the nearest distance.  If X is memoryless node, it
will return nearest distance node, but, if X is normal node, it will
return itself.

We will use this function in following patch to determine the fallback
node.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Han Pingtian <hanpt@linux.vnet.ibm.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Anton Blanchard <anton@samba.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/topology.h | 17 +++++++++++++++++
 mm/page_alloc.c          |  1 +
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/linux/topology.h b/include/linux/topology.h
index dda6ee521e74..909b6e43b694 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -119,11 +119,20 @@ static inline int numa_node_id(void)
  * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem().
  */
 DECLARE_PER_CPU(int, _numa_mem_);
+extern int _node_numa_mem_[MAX_NUMNODES];
 
 #ifndef set_numa_mem
 static inline void set_numa_mem(int node)
 {
 	this_cpu_write(_numa_mem_, node);
+	_node_numa_mem_[numa_node_id()] = node;
+}
+#endif
+
+#ifndef node_to_mem_node
+static inline int node_to_mem_node(int node)
+{
+	return _node_numa_mem_[node];
 }
 #endif
 
@@ -146,6 +155,7 @@ static inline int cpu_to_mem(int cpu)
 static inline void set_cpu_numa_mem(int cpu, int node)
 {
 	per_cpu(_numa_mem_, cpu) = node;
+	_node_numa_mem_[cpu_to_node(cpu)] = node;
 }
 #endif
 
@@ -159,6 +169,13 @@ static inline int numa_mem_id(void)
 }
 #endif
 
+#ifndef node_to_mem_node
+static inline int node_to_mem_node(int node)
+{
+	return node;
+}
+#endif
+
 #ifndef cpu_to_mem
 static inline int cpu_to_mem(int cpu)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eee961958021..f3bc59f2ed52 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -85,6 +85,7 @@ EXPORT_PER_CPU_SYMBOL(numa_node);
  */
 DEFINE_PER_CPU(int, _numa_mem_);		/* Kernel "local memory" node */
 EXPORT_PER_CPU_SYMBOL(_numa_mem_);
+int _node_numa_mem_[MAX_NUMNODES];
 #endif
 
 /*
-- 
cgit v1.2.3


From bf0dea23a9c094ae869a88bb694fbe966671bf6d Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Thu, 9 Oct 2014 15:26:27 -0700
Subject: mm/slab: use percpu allocator for cpu cache

Because of chicken and egg problem, initialization of SLAB is really
complicated.  We need to allocate cpu cache through SLAB to make the
kmem_cache work, but before initialization of kmem_cache, allocation
through SLAB is impossible.

On the other hand, SLUB does initialization in a more simple way.  It uses
percpu allocator to allocate cpu cache so there is no chicken and egg
problem.

So, this patch try to use percpu allocator in SLAB.  This simplifies the
initialization step in SLAB so that we could maintain SLAB code more
easily.

In my testing there is no performance difference.

This implementation relies on percpu allocator.  Because percpu allocator
uses vmalloc address space, vmalloc address space could be exhausted by
this change on many cpu system with *32 bit* kernel.  This implementation
can cover 1024 cpus in worst case by following calculation.

Worst: 1024 cpus * 4 bytes for pointer * 300 kmem_caches *
	120 objects per cpu_cache = 140 MB
Normal: 1024 cpus * 4 bytes for pointer * 150 kmem_caches(slab merge) *
	80 objects per cpu_cache = 46 MB

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Jeremiah Mahler <jmmahler@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slab_def.h |  20 +---
 mm/slab.c                | 239 +++++++++++++++--------------------------------
 mm/slab.h                |   1 -
 3 files changed, 78 insertions(+), 182 deletions(-)

(limited to 'include')

diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 8235dfbb3b05..b869d1662ba3 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -8,6 +8,8 @@
  */
 
 struct kmem_cache {
+	struct array_cache __percpu *cpu_cache;
+
 /* 1) Cache tunables. Protected by slab_mutex */
 	unsigned int batchcount;
 	unsigned int limit;
@@ -71,23 +73,7 @@ struct kmem_cache {
 	struct memcg_cache_params *memcg_params;
 #endif
 
-/* 6) per-cpu/per-node data, touched during every alloc/free */
-	/*
-	 * We put array[] at the end of kmem_cache, because we want to size
-	 * this array to nr_cpu_ids slots instead of NR_CPUS
-	 * (see kmem_cache_init())
-	 * We still use [NR_CPUS] and not [1] or [0] because cache_cache
-	 * is statically defined, so we reserve the max number of cpus.
-	 *
-	 * We also need to guarantee that the list is able to accomodate a
-	 * pointer for each node since "nodelists" uses the remainder of
-	 * available pointers.
-	 */
-	struct kmem_cache_node **node;
-	struct array_cache *array[NR_CPUS + MAX_NUMNODES];
-	/*
-	 * Do not add fields after array[]
-	 */
+	struct kmem_cache_node *node[MAX_NUMNODES];
 };
 
 #endif	/* _LINUX_SLAB_DEF_H */
diff --git a/mm/slab.c b/mm/slab.c
index 328233a724af..655d65c3f010 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -237,11 +237,10 @@ struct arraycache_init {
 /*
  * Need this for bootstrapping a per node allocator.
  */
-#define NUM_INIT_LISTS (3 * MAX_NUMNODES)
+#define NUM_INIT_LISTS (2 * MAX_NUMNODES)
 static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS];
 #define	CACHE_CACHE 0
-#define	SIZE_AC MAX_NUMNODES
-#define	SIZE_NODE (2 * MAX_NUMNODES)
+#define	SIZE_NODE (MAX_NUMNODES)
 
 static int drain_freelist(struct kmem_cache *cache,
 			struct kmem_cache_node *n, int tofree);
@@ -253,7 +252,6 @@ static void cache_reap(struct work_struct *unused);
 
 static int slab_early_init = 1;
 
-#define INDEX_AC kmalloc_index(sizeof(struct arraycache_init))
 #define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node))
 
 static void kmem_cache_node_init(struct kmem_cache_node *parent)
@@ -458,9 +456,6 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
 }
 
-static struct arraycache_init initarray_generic =
-    { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
-
 /* internal cache of cache description objs */
 static struct kmem_cache kmem_cache_boot = {
 	.batchcount = 1,
@@ -476,7 +471,7 @@ static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
 
 static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {
-	return cachep->array[smp_processor_id()];
+	return this_cpu_ptr(cachep->cpu_cache);
 }
 
 static size_t calculate_freelist_size(int nr_objs, size_t align)
@@ -1096,24 +1091,25 @@ static void cpuup_canceled(long cpu)
 		struct alien_cache **alien;
 		LIST_HEAD(list);
 
-		/* cpu is dead; no one can alloc from it. */
-		nc = cachep->array[cpu];
-		cachep->array[cpu] = NULL;
 		n = get_node(cachep, node);
-
 		if (!n)
-			goto free_array_cache;
+			continue;
 
 		spin_lock_irq(&n->list_lock);
 
 		/* Free limit for this kmem_cache_node */
 		n->free_limit -= cachep->batchcount;
-		if (nc)
+
+		/* cpu is dead; no one can alloc from it. */
+		nc = per_cpu_ptr(cachep->cpu_cache, cpu);
+		if (nc) {
 			free_block(cachep, nc->entry, nc->avail, node, &list);
+			nc->avail = 0;
+		}
 
 		if (!cpumask_empty(mask)) {
 			spin_unlock_irq(&n->list_lock);
-			goto free_array_cache;
+			goto free_slab;
 		}
 
 		shared = n->shared;
@@ -1133,9 +1129,9 @@ static void cpuup_canceled(long cpu)
 			drain_alien_cache(cachep, alien);
 			free_alien_cache(alien);
 		}
-free_array_cache:
+
+free_slab:
 		slabs_destroy(cachep, &list);
-		kfree(nc);
 	}
 	/*
 	 * In the previous loop, all the objects were freed to
@@ -1172,32 +1168,23 @@ static int cpuup_prepare(long cpu)
 	 * array caches
 	 */
 	list_for_each_entry(cachep, &slab_caches, list) {
-		struct array_cache *nc;
 		struct array_cache *shared = NULL;
 		struct alien_cache **alien = NULL;
 
-		nc = alloc_arraycache(node, cachep->limit,
-					cachep->batchcount, GFP_KERNEL);
-		if (!nc)
-			goto bad;
 		if (cachep->shared) {
 			shared = alloc_arraycache(node,
 				cachep->shared * cachep->batchcount,
 				0xbaadf00d, GFP_KERNEL);
-			if (!shared) {
-				kfree(nc);
+			if (!shared)
 				goto bad;
-			}
 		}
 		if (use_alien_caches) {
 			alien = alloc_alien_cache(node, cachep->limit, GFP_KERNEL);
 			if (!alien) {
 				kfree(shared);
-				kfree(nc);
 				goto bad;
 			}
 		}
-		cachep->array[cpu] = nc;
 		n = get_node(cachep, node);
 		BUG_ON(!n);
 
@@ -1388,15 +1375,6 @@ static void __init set_up_node(struct kmem_cache *cachep, int index)
 	}
 }
 
-/*
- * The memory after the last cpu cache pointer is used for the
- * the node pointer.
- */
-static void setup_node_pointer(struct kmem_cache *cachep)
-{
-	cachep->node = (struct kmem_cache_node **)&cachep->array[nr_cpu_ids];
-}
-
 /*
  * Initialisation.  Called after the page allocator have been initialised and
  * before smp_init().
@@ -1408,7 +1386,6 @@ void __init kmem_cache_init(void)
 	BUILD_BUG_ON(sizeof(((struct page *)NULL)->lru) <
 					sizeof(struct rcu_head));
 	kmem_cache = &kmem_cache_boot;
-	setup_node_pointer(kmem_cache);
 
 	if (num_possible_nodes() == 1)
 		use_alien_caches = 0;
@@ -1416,8 +1393,6 @@ void __init kmem_cache_init(void)
 	for (i = 0; i < NUM_INIT_LISTS; i++)
 		kmem_cache_node_init(&init_kmem_cache_node[i]);
 
-	set_up_node(kmem_cache, CACHE_CACHE);
-
 	/*
 	 * Fragmentation resistance on low memory - only use bigger
 	 * page orders on machines with more than 32MB of memory if
@@ -1452,49 +1427,22 @@ void __init kmem_cache_init(void)
 	 * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
 	 */
 	create_boot_cache(kmem_cache, "kmem_cache",
-		offsetof(struct kmem_cache, array[nr_cpu_ids]) +
+		offsetof(struct kmem_cache, node) +
 				  nr_node_ids * sizeof(struct kmem_cache_node *),
 				  SLAB_HWCACHE_ALIGN);
 	list_add(&kmem_cache->list, &slab_caches);
-
-	/* 2+3) create the kmalloc caches */
+	slab_state = PARTIAL;
 
 	/*
-	 * Initialize the caches that provide memory for the array cache and the
-	 * kmem_cache_node structures first.  Without this, further allocations will
-	 * bug.
+	 * Initialize the caches that provide memory for the  kmem_cache_node
+	 * structures first.  Without this, further allocations will bug.
 	 */
-
-	kmalloc_caches[INDEX_AC] = create_kmalloc_cache("kmalloc-ac",
-					kmalloc_size(INDEX_AC), ARCH_KMALLOC_FLAGS);
-
-	if (INDEX_AC != INDEX_NODE)
-		kmalloc_caches[INDEX_NODE] =
-			create_kmalloc_cache("kmalloc-node",
+	kmalloc_caches[INDEX_NODE] = create_kmalloc_cache("kmalloc-node",
 				kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS);
+	slab_state = PARTIAL_NODE;
 
 	slab_early_init = 0;
 
-	/* 4) Replace the bootstrap head arrays */
-	{
-		struct array_cache *ptr;
-
-		ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
-
-		memcpy(ptr, cpu_cache_get(kmem_cache),
-		       sizeof(struct arraycache_init));
-
-		kmem_cache->array[smp_processor_id()] = ptr;
-
-		ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
-
-		BUG_ON(cpu_cache_get(kmalloc_caches[INDEX_AC])
-		       != &initarray_generic.cache);
-		memcpy(ptr, cpu_cache_get(kmalloc_caches[INDEX_AC]),
-		       sizeof(struct arraycache_init));
-
-		kmalloc_caches[INDEX_AC]->array[smp_processor_id()] = ptr;
-	}
 	/* 5) Replace the bootstrap kmem_cache_node */
 	{
 		int nid;
@@ -1502,13 +1450,8 @@ void __init kmem_cache_init(void)
 		for_each_online_node(nid) {
 			init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid);
 
-			init_list(kmalloc_caches[INDEX_AC],
-				  &init_kmem_cache_node[SIZE_AC + nid], nid);
-
-			if (INDEX_AC != INDEX_NODE) {
-				init_list(kmalloc_caches[INDEX_NODE],
+			init_list(kmalloc_caches[INDEX_NODE],
 					  &init_kmem_cache_node[SIZE_NODE + nid], nid);
-			}
 		}
 	}
 
@@ -2041,56 +1984,53 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 	return left_over;
 }
 
+static struct array_cache __percpu *alloc_kmem_cache_cpus(
+		struct kmem_cache *cachep, int entries, int batchcount)
+{
+	int cpu;
+	size_t size;
+	struct array_cache __percpu *cpu_cache;
+
+	size = sizeof(void *) * entries + sizeof(struct array_cache);
+	cpu_cache = __alloc_percpu(size, 0);
+
+	if (!cpu_cache)
+		return NULL;
+
+	for_each_possible_cpu(cpu) {
+		init_arraycache(per_cpu_ptr(cpu_cache, cpu),
+				entries, batchcount);
+	}
+
+	return cpu_cache;
+}
+
 static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	if (slab_state >= FULL)
 		return enable_cpucache(cachep, gfp);
 
+	cachep->cpu_cache = alloc_kmem_cache_cpus(cachep, 1, 1);
+	if (!cachep->cpu_cache)
+		return 1;
+
 	if (slab_state == DOWN) {
-		/*
-		 * Note: Creation of first cache (kmem_cache).
-		 * The setup_node is taken care
-		 * of by the caller of __kmem_cache_create
-		 */
-		cachep->array[smp_processor_id()] = &initarray_generic.cache;
-		slab_state = PARTIAL;
+		/* Creation of first cache (kmem_cache). */
+		set_up_node(kmem_cache, CACHE_CACHE);
 	} else if (slab_state == PARTIAL) {
-		/*
-		 * Note: the second kmem_cache_create must create the cache
-		 * that's used by kmalloc(24), otherwise the creation of
-		 * further caches will BUG().
-		 */
-		cachep->array[smp_processor_id()] = &initarray_generic.cache;
-
-		/*
-		 * If the cache that's used by kmalloc(sizeof(kmem_cache_node)) is
-		 * the second cache, then we need to set up all its node/,
-		 * otherwise the creation of further caches will BUG().
-		 */
-		set_up_node(cachep, SIZE_AC);
-		if (INDEX_AC == INDEX_NODE)
-			slab_state = PARTIAL_NODE;
-		else
-			slab_state = PARTIAL_ARRAYCACHE;
+		/* For kmem_cache_node */
+		set_up_node(cachep, SIZE_NODE);
 	} else {
-		/* Remaining boot caches */
-		cachep->array[smp_processor_id()] =
-			kmalloc(sizeof(struct arraycache_init), gfp);
+		int node;
 
-		if (slab_state == PARTIAL_ARRAYCACHE) {
-			set_up_node(cachep, SIZE_NODE);
-			slab_state = PARTIAL_NODE;
-		} else {
-			int node;
-			for_each_online_node(node) {
-				cachep->node[node] =
-				    kmalloc_node(sizeof(struct kmem_cache_node),
-						gfp, node);
-				BUG_ON(!cachep->node[node]);
-				kmem_cache_node_init(cachep->node[node]);
-			}
+		for_each_online_node(node) {
+			cachep->node[node] = kmalloc_node(
+				sizeof(struct kmem_cache_node), gfp, node);
+			BUG_ON(!cachep->node[node]);
+			kmem_cache_node_init(cachep->node[node]);
 		}
 	}
+
 	cachep->node[numa_mem_id()]->next_reap =
 			jiffies + REAPTIMEOUT_NODE +
 			((unsigned long)cachep) % REAPTIMEOUT_NODE;
@@ -2213,7 +2153,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	else
 		gfp = GFP_NOWAIT;
 
-	setup_node_pointer(cachep);
 #if DEBUG
 
 	/*
@@ -2470,8 +2409,7 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
 	if (rc)
 		return rc;
 
-	for_each_online_cpu(i)
-	    kfree(cachep->array[i]);
+	free_percpu(cachep->cpu_cache);
 
 	/* NUMA: free the node structures */
 	for_each_kmem_cache_node(cachep, i, n) {
@@ -3719,72 +3657,45 @@ fail:
 	return -ENOMEM;
 }
 
-struct ccupdate_struct {
-	struct kmem_cache *cachep;
-	struct array_cache *new[0];
-};
-
-static void do_ccupdate_local(void *info)
-{
-	struct ccupdate_struct *new = info;
-	struct array_cache *old;
-
-	check_irq_off();
-	old = cpu_cache_get(new->cachep);
-
-	new->cachep->array[smp_processor_id()] = new->new[smp_processor_id()];
-	new->new[smp_processor_id()] = old;
-}
-
 /* Always called with the slab_mutex held */
 static int __do_tune_cpucache(struct kmem_cache *cachep, int limit,
 				int batchcount, int shared, gfp_t gfp)
 {
-	struct ccupdate_struct *new;
-	int i;
+	struct array_cache __percpu *cpu_cache, *prev;
+	int cpu;
 
-	new = kzalloc(sizeof(*new) + nr_cpu_ids * sizeof(struct array_cache *),
-		      gfp);
-	if (!new)
+	cpu_cache = alloc_kmem_cache_cpus(cachep, limit, batchcount);
+	if (!cpu_cache)
 		return -ENOMEM;
 
-	for_each_online_cpu(i) {
-		new->new[i] = alloc_arraycache(cpu_to_mem(i), limit,
-						batchcount, gfp);
-		if (!new->new[i]) {
-			for (i--; i >= 0; i--)
-				kfree(new->new[i]);
-			kfree(new);
-			return -ENOMEM;
-		}
-	}
-	new->cachep = cachep;
-
-	on_each_cpu(do_ccupdate_local, (void *)new, 1);
+	prev = cachep->cpu_cache;
+	cachep->cpu_cache = cpu_cache;
+	kick_all_cpus_sync();
 
 	check_irq_on();
 	cachep->batchcount = batchcount;
 	cachep->limit = limit;
 	cachep->shared = shared;
 
-	for_each_online_cpu(i) {
+	if (!prev)
+		goto alloc_node;
+
+	for_each_online_cpu(cpu) {
 		LIST_HEAD(list);
-		struct array_cache *ccold = new->new[i];
 		int node;
 		struct kmem_cache_node *n;
+		struct array_cache *ac = per_cpu_ptr(prev, cpu);
 
-		if (!ccold)
-			continue;
-
-		node = cpu_to_mem(i);
+		node = cpu_to_mem(cpu);
 		n = get_node(cachep, node);
 		spin_lock_irq(&n->list_lock);
-		free_block(cachep, ccold->entry, ccold->avail, node, &list);
+		free_block(cachep, ac->entry, ac->avail, node, &list);
 		spin_unlock_irq(&n->list_lock);
 		slabs_destroy(cachep, &list);
-		kfree(ccold);
 	}
-	kfree(new);
+	free_percpu(prev);
+
+alloc_node:
 	return alloc_kmem_cache_node(cachep, gfp);
 }
 
diff --git a/mm/slab.h b/mm/slab.h
index 50d29d716db4..ab019e63e3c2 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -50,7 +50,6 @@ struct kmem_cache {
 enum slab_state {
 	DOWN,			/* No slab functionality yet */
 	PARTIAL,		/* SLUB: kmem_cache_node available */
-	PARTIAL_ARRAYCACHE,	/* SLAB: kmalloc size for arraycache available */
 	PARTIAL_NODE,		/* SLAB: kmalloc size for node struct available */
 	UP,			/* Slab caches usable but not all extras yet */
 	FULL			/* Everything is working */
-- 
cgit v1.2.3


From ed2f240094f900833ac06f533ab8bbcf0a1e8199 Mon Sep 17 00:00:00 2001
From: Zhang Zhen <zhenzhang.zhang@huawei.com>
Date: Thu, 9 Oct 2014 15:26:31 -0700
Subject: memory-hotplug: add sysfs valid_zones attribute

Currently memory-hotplug has two limits:

1. If the memory block is in ZONE_NORMAL, you can change it to
   ZONE_MOVABLE, but this memory block must be adjacent to ZONE_MOVABLE.

2. If the memory block is in ZONE_MOVABLE, you can change it to
   ZONE_NORMAL, but this memory block must be adjacent to ZONE_NORMAL.

With this patch, we can easy to know a memory block can be onlined to
which zone, and don't need to know the above two limits.

Updated the related Documentation.

[akpm@linux-foundation.org: use conventional comment layout]
[akpm@linux-foundation.org: fix build with CONFIG_MEMORY_HOTREMOVE=n]
[akpm@linux-foundation.org: remove unused local zone_prev]
Signed-off-by: Zhang Zhen <zhenzhang.zhang@huawei.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Wang Nan <wangnan0@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/ABI/testing/sysfs-devices-memory |  8 +++++
 Documentation/memory-hotplug.txt               | 11 ++++++-
 drivers/base/memory.c                          | 42 ++++++++++++++++++++++++++
 include/linux/memory_hotplug.h                 |  1 +
 mm/memory_hotplug.c                            |  2 +-
 5 files changed, 62 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory
index 7405de26ee60..deef3b5723cf 100644
--- a/Documentation/ABI/testing/sysfs-devices-memory
+++ b/Documentation/ABI/testing/sysfs-devices-memory
@@ -61,6 +61,14 @@ Users:		hotplug memory remove tools
 		http://www.ibm.com/developerworks/wikis/display/LinuxP/powerpc-utils
 
 
+What:           /sys/devices/system/memory/memoryX/valid_zones
+Date:           July 2014
+Contact:	Zhang Zhen <zhenzhang.zhang@huawei.com>
+Description:
+		The file /sys/devices/system/memory/memoryX/valid_zones	is
+		read-only and is designed to show which zone this memory
+		block can be onlined to.
+
 What:		/sys/devices/system/memoryX/nodeY
 Date:		October 2009
 Contact:	Linux Memory Management list <linux-mm@kvack.org>
diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index 45134dc23854..ea03abfc97e9 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -155,6 +155,7 @@ Under each memory block, you can see 4 files:
 /sys/devices/system/memory/memoryXXX/phys_device
 /sys/devices/system/memory/memoryXXX/state
 /sys/devices/system/memory/memoryXXX/removable
+/sys/devices/system/memory/memoryXXX/valid_zones
 
 'phys_index'      : read-only and contains memory block id, same as XXX.
 'state'           : read-write
@@ -170,6 +171,15 @@ Under each memory block, you can see 4 files:
                     block is removable and a value of 0 indicates that
                     it is not removable. A memory block is removable only if
                     every section in the block is removable.
+'valid_zones'     : read-only: designed to show which zones this memory block
+		    can be onlined to.
+		    The first column shows it's default zone.
+		    "memory6/valid_zones: Normal Movable" shows this memoryblock
+		    can be onlined to ZONE_NORMAL by default and to ZONE_MOVABLE
+		    by online_movable.
+		    "memory7/valid_zones: Movable Normal" shows this memoryblock
+		    can be onlined to ZONE_MOVABLE by default and to ZONE_NORMAL
+		    by online_kernel.
 
 NOTE:
   These directories/files appear after physical memory hotplug phase.
@@ -408,7 +418,6 @@ node if necessary.
   - allowing memory hot-add to ZONE_MOVABLE. maybe we need some switch like
     sysctl or new control file.
   - showing memory block and physical device relationship.
-  - showing memory block is under ZONE_MOVABLE or not
   - test and make it better memory offlining.
   - support HugeTLB page migration and offlining.
   - memmap removing at memory offline.
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index a2e13e250bba..7c5d87191b28 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -373,6 +373,45 @@ static ssize_t show_phys_device(struct device *dev,
 	return sprintf(buf, "%d\n", mem->phys_device);
 }
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static ssize_t show_valid_zones(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct memory_block *mem = to_memory_block(dev);
+	unsigned long start_pfn, end_pfn;
+	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+	struct page *first_page;
+	struct zone *zone;
+
+	start_pfn = section_nr_to_pfn(mem->start_section_nr);
+	end_pfn = start_pfn + nr_pages;
+	first_page = pfn_to_page(start_pfn);
+
+	/* The block contains more than one zone can not be offlined. */
+	if (!test_pages_in_a_zone(start_pfn, end_pfn))
+		return sprintf(buf, "none\n");
+
+	zone = page_zone(first_page);
+
+	if (zone_idx(zone) == ZONE_MOVABLE - 1) {
+		/*The mem block is the last memoryblock of this zone.*/
+		if (end_pfn == zone_end_pfn(zone))
+			return sprintf(buf, "%s %s\n",
+					zone->name, (zone + 1)->name);
+	}
+
+	if (zone_idx(zone) == ZONE_MOVABLE) {
+		/*The mem block is the first memoryblock of ZONE_MOVABLE.*/
+		if (start_pfn == zone->zone_start_pfn)
+			return sprintf(buf, "%s %s\n",
+					zone->name, (zone - 1)->name);
+	}
+
+	return sprintf(buf, "%s\n", zone->name);
+}
+static DEVICE_ATTR(valid_zones, 0444, show_valid_zones, NULL);
+#endif
+
 static DEVICE_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
 static DEVICE_ATTR(state, 0644, show_mem_state, store_mem_state);
 static DEVICE_ATTR(phys_device, 0444, show_phys_device, NULL);
@@ -523,6 +562,9 @@ static struct attribute *memory_memblk_attrs[] = {
 	&dev_attr_state.attr,
 	&dev_attr_phys_device.attr,
 	&dev_attr_removable.attr,
+#ifdef CONFIG_MEMORY_HOTREMOVE
+	&dev_attr_valid_zones.attr,
+#endif
 	NULL
 };
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index d9524c49d767..8f1a41951df9 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -84,6 +84,7 @@ extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
 /* VM interface that may be used by firmware interface */
 extern int online_pages(unsigned long, unsigned long, int);
+extern int test_pages_in_a_zone(unsigned long, unsigned long);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
 
 typedef void (*online_page_callback_t)(struct page *page);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 2ff8c2325e96..29d8693d0c61 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1307,7 +1307,7 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 /*
  * Confirm all pages in a range [start, end) is belongs to the same zone.
  */
-static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
+int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long pfn;
 	struct zone *zone = NULL;
-- 
cgit v1.2.3


From 6a33979d5bd7521497121c5ae4435d7003115a0f Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Thu, 9 Oct 2014 15:26:33 -0700
Subject: mm: remove misleading ARCH_USES_NUMA_PROT_NONE

ARCH_USES_NUMA_PROT_NONE was defined for architectures that implemented
_PAGE_NUMA using _PROT_NONE.  This saved using an additional PTE bit and
relied on the fact that PROT_NONE vmas were skipped by the NUMA hinting
fault scanner.  This was found to be conceptually confusing with a lot of
implicit assumptions and it was asked that an alternative be found.

Commit c46a7c81 "x86: define _PAGE_NUMA by reusing software bits on the
PMD and PTE levels" redefined _PAGE_NUMA on x86 to be one of the swap PTE
bits and shrunk the maximum possible swap size but it did not go far
enough.  There are no architectures that reuse _PROT_NONE as _PROT_NUMA
but the relics still exist.

This patch removes ARCH_USES_NUMA_PROT_NONE and removes some unnecessary
duplication in powerpc vs the generic implementation by defining the types
the core NUMA helpers expected to exist from x86 with their ppc64
equivalent.  This necessitated that a PTE bit mask be created that
identified the bits that distinguish present from NUMA pte entries but it
is expected this will only differ between arches based on _PAGE_PROTNONE.
The naming for the generic helpers was taken from x86 originally but ppc64
has types that are equivalent for the purposes of the helper so they are
mapped instead of duplicating code.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/include/asm/pgtable.h    | 57 ++++++++---------------------------
 arch/powerpc/include/asm/pte-common.h |  5 +++
 arch/x86/Kconfig                      |  1 -
 arch/x86/include/asm/pgtable_types.h  | 14 +++++++++
 include/asm-generic/pgtable.h         | 27 ++++++-----------
 init/Kconfig                          | 11 -------
 6 files changed, 40 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index d98c1ecc3266..f60d4ea8b50c 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -38,10 +38,9 @@ static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK)
 static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
 
 #ifdef CONFIG_NUMA_BALANCING
-
 static inline int pte_present(pte_t pte)
 {
-	return pte_val(pte) & (_PAGE_PRESENT | _PAGE_NUMA);
+	return pte_val(pte) & _PAGE_NUMA_MASK;
 }
 
 #define pte_present_nonuma pte_present_nonuma
@@ -50,37 +49,6 @@ static inline int pte_present_nonuma(pte_t pte)
 	return pte_val(pte) & (_PAGE_PRESENT);
 }
 
-#define pte_numa pte_numa
-static inline int pte_numa(pte_t pte)
-{
-	return (pte_val(pte) &
-		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
-}
-
-#define pte_mknonnuma pte_mknonnuma
-static inline pte_t pte_mknonnuma(pte_t pte)
-{
-	pte_val(pte) &= ~_PAGE_NUMA;
-	pte_val(pte) |=  _PAGE_PRESENT | _PAGE_ACCESSED;
-	return pte;
-}
-
-#define pte_mknuma pte_mknuma
-static inline pte_t pte_mknuma(pte_t pte)
-{
-	/*
-	 * We should not set _PAGE_NUMA on non present ptes. Also clear the
-	 * present bit so that hash_page will return 1 and we collect this
-	 * as numa fault.
-	 */
-	if (pte_present(pte)) {
-		pte_val(pte) |= _PAGE_NUMA;
-		pte_val(pte) &= ~_PAGE_PRESENT;
-	} else
-		VM_BUG_ON(1);
-	return pte;
-}
-
 #define ptep_set_numa ptep_set_numa
 static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep)
@@ -92,12 +60,6 @@ static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
 	return;
 }
 
-#define pmd_numa pmd_numa
-static inline int pmd_numa(pmd_t pmd)
-{
-	return pte_numa(pmd_pte(pmd));
-}
-
 #define pmdp_set_numa pmdp_set_numa
 static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
 				 pmd_t *pmdp)
@@ -109,16 +71,21 @@ static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
 	return;
 }
 
-#define pmd_mknonnuma pmd_mknonnuma
-static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+/*
+ * Generic NUMA pte helpers expect pteval_t and pmdval_t types to exist
+ * which was inherited from x86. For the purposes of powerpc pte_basic_t and
+ * pmd_t are equivalent
+ */
+#define pteval_t pte_basic_t
+#define pmdval_t pmd_t
+static inline pteval_t ptenuma_flags(pte_t pte)
 {
-	return pte_pmd(pte_mknonnuma(pmd_pte(pmd)));
+	return pte_val(pte) & _PAGE_NUMA_MASK;
 }
 
-#define pmd_mknuma pmd_mknuma
-static inline pmd_t pmd_mknuma(pmd_t pmd)
+static inline pmdval_t pmdnuma_flags(pmd_t pmd)
 {
-	return pte_pmd(pte_mknuma(pmd_pte(pmd)));
+	return pmd_val(pmd) & _PAGE_NUMA_MASK;
 }
 
 # else
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index 8d1569c29042..e040c3595129 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -98,6 +98,11 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 			 _PAGE_USER | _PAGE_ACCESSED | \
 			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC)
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Mask of bits that distinguish present and numa ptes */
+#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PRESENT)
+#endif
+
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
  * cacheable kernel and user pages) and one for non cacheable
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e4b1f431c7ed..3eb8a41509b3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -30,7 +30,6 @@ config X86
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
 	select ARCH_SUPPORTS_INT128 if X86_64
-	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_PCSPKR_PLATFORM
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f216963760e5..0f9724c9c510 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -325,6 +325,20 @@ static inline pteval_t pte_flags(pte_t pte)
 	return native_pte_val(pte) & PTE_FLAGS_MASK;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Set of bits that distinguishes present, prot_none and numa ptes */
+#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)
+static inline pteval_t ptenuma_flags(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_NUMA_MASK;
+}
+
+static inline pmdval_t pmdnuma_flags(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_NUMA_MASK;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #define pgprot_val(x)	((x).pgprot)
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 53b2acc38213..281870f56450 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -660,11 +660,12 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 }
 
 #ifdef CONFIG_NUMA_BALANCING
-#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
 /*
- * _PAGE_NUMA works identical to _PAGE_PROTNONE (it's actually the
- * same bit too). It's set only when _PAGE_PRESET is not set and it's
- * never set if _PAGE_PRESENT is set.
+ * _PAGE_NUMA distinguishes between an unmapped page table entry, an entry that
+ * is protected for PROT_NONE and a NUMA hinting fault entry. If the
+ * architecture defines __PAGE_PROTNONE then it should take that into account
+ * but those that do not can rely on the fact that the NUMA hinting scanner
+ * skips inaccessible VMAs.
  *
  * pte/pmd_present() returns true if pte/pmd_numa returns true. Page
  * fault triggers on those regions if pte/pmd_numa returns true
@@ -673,16 +674,14 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 #ifndef pte_numa
 static inline int pte_numa(pte_t pte)
 {
-	return (pte_flags(pte) &
-		(_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA;
+	return ptenuma_flags(pte) == _PAGE_NUMA;
 }
 #endif
 
 #ifndef pmd_numa
 static inline int pmd_numa(pmd_t pmd)
 {
-	return (pmd_flags(pmd) &
-		(_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA;
+	return pmdnuma_flags(pmd) == _PAGE_NUMA;
 }
 #endif
 
@@ -722,6 +721,8 @@ static inline pte_t pte_mknuma(pte_t pte)
 {
 	pteval_t val = pte_val(pte);
 
+	VM_BUG_ON(!(val & _PAGE_PRESENT));
+
 	val &= ~_PAGE_PRESENT;
 	val |= _PAGE_NUMA;
 
@@ -765,16 +766,6 @@ static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
 }
 #endif
 #else
-extern int pte_numa(pte_t pte);
-extern int pmd_numa(pmd_t pmd);
-extern pte_t pte_mknonnuma(pte_t pte);
-extern pmd_t pmd_mknonnuma(pmd_t pmd);
-extern pte_t pte_mknuma(pte_t pte);
-extern pmd_t pmd_mknuma(pmd_t pmd);
-extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
-extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp);
-#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
-#else
 static inline int pmd_numa(pmd_t pmd)
 {
 	return 0;
diff --git a/init/Kconfig b/init/Kconfig
index e25a82a291a6..d2355812ba48 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -889,17 +889,6 @@ config ARCH_SUPPORTS_INT128
 config ARCH_WANT_NUMA_VARIABLE_LOCALITY
 	bool
 
-#
-# For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE
-config ARCH_WANTS_PROT_NUMA_PROT_NONE
-	bool
-
-config ARCH_USES_NUMA_PROT_NONE
-	bool
-	default y
-	depends on ARCH_WANTS_PROT_NUMA_PROT_NONE
-	depends on NUMA_BALANCING
-
 config NUMA_BALANCING_DEFAULT_ENABLED
 	bool "Automatically enable NUMA aware memory/task placement"
 	default y
-- 
cgit v1.2.3


From 505e3be6c082489a32a88e042f930d047b6415bc Mon Sep 17 00:00:00 2001
From: Laura Abbott <lauraa@codeaurora.org>
Date: Thu, 9 Oct 2014 15:26:35 -0700
Subject: lib/genalloc.c: add power aligned algorithm

One of the more common algorithms used for allocation is to align the
start address of the allocation to the order of size requested.  Add this
as an algorithm option for genalloc.

Signed-off-by: Laura Abbott <lauraa@codeaurora.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Olof Johansson <olof@lixom.net>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Riley <davidriley@chromium.org>
Cc: Ritesh Harjain <ritesh.harjani@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thierry Reding <thierry.reding@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/genalloc.h |  4 ++++
 lib/genalloc.c           | 20 ++++++++++++++++++++
 2 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 1c2fdaa2ffc3..3cd0934d62ba 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -110,6 +110,10 @@ extern void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo,
 extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data);
 
+extern unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+		unsigned long size, unsigned long start, unsigned int nr,
+		void *data);
+
 extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data);
 
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 38d2db82228c..166f17b9f169 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -480,6 +480,26 @@ unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 }
 EXPORT_SYMBOL(gen_pool_first_fit);
 
+/**
+ * gen_pool_first_fit_order_align - find the first available region
+ * of memory matching the size requirement. The region will be aligned
+ * to the order of the size specified.
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @data: additional data - unused
+ */
+unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+		unsigned long size, unsigned long start,
+		unsigned int nr, void *data)
+{
+	unsigned long align_mask = roundup_pow_of_two(nr) - 1;
+
+	return bitmap_find_next_zero_area(map, size, start, nr, align_mask);
+}
+EXPORT_SYMBOL(gen_pool_first_fit_order_align);
+
 /**
  * gen_pool_best_fit - find the best fitting region of memory
  * macthing the size requirement (no alignment constraint)
-- 
cgit v1.2.3


From 9efb3a421d55d30b65fb0dbee05108d15c6c55f7 Mon Sep 17 00:00:00 2001
From: Laura Abbott <lauraa@codeaurora.org>
Date: Thu, 9 Oct 2014 15:26:38 -0700
Subject: lib/genalloc.c: add genpool range check function

After allocating an address from a particular genpool, there is no good
way to verify if that address actually belongs to a genpool.  Introduce
addr_in_gen_pool which will return if an address plus size falls
completely within the genpool range.

Signed-off-by: Laura Abbott <lauraa@codeaurora.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Reviewed-by: Olof Johansson <olof@lixom.net>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Riley <davidriley@chromium.org>
Cc: Ritesh Harjain <ritesh.harjani@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thierry Reding <thierry.reding@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/genalloc.h |  3 +++
 lib/genalloc.c           | 29 +++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+)

(limited to 'include')

diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 3cd0934d62ba..1ccaab44abcc 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -121,6 +121,9 @@ extern struct gen_pool *devm_gen_pool_create(struct device *dev,
 		int min_alloc_order, int nid);
 extern struct gen_pool *dev_get_gen_pool(struct device *dev);
 
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+			size_t size);
+
 #ifdef CONFIG_OF
 extern struct gen_pool *of_get_named_gen_pool(struct device_node *np,
 	const char *propname, int index);
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 166f17b9f169..cce4dd68c40d 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -402,6 +402,35 @@ void gen_pool_for_each_chunk(struct gen_pool *pool,
 }
 EXPORT_SYMBOL(gen_pool_for_each_chunk);
 
+/**
+ * addr_in_gen_pool - checks if an address falls within the range of a pool
+ * @pool:	the generic memory pool
+ * @start:	start address
+ * @size:	size of the region
+ *
+ * Check if the range of addresses falls within the specified pool. Returns
+ * true if the entire range is contained in the pool and false otherwise.
+ */
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+			size_t size)
+{
+	bool found = false;
+	unsigned long end = start + size;
+	struct gen_pool_chunk *chunk;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk) {
+		if (start >= chunk->start_addr && start <= chunk->end_addr) {
+			if (end <= chunk->end_addr) {
+				found = true;
+				break;
+			}
+		}
+	}
+	rcu_read_unlock();
+	return found;
+}
+
 /**
  * gen_pool_avail - get available free space of the pool
  * @pool: pool to get available free space
-- 
cgit v1.2.3


From 513510ddba9650fc7da456eefeb0ead7632324f6 Mon Sep 17 00:00:00 2001
From: Laura Abbott <lauraa@codeaurora.org>
Date: Thu, 9 Oct 2014 15:26:40 -0700
Subject: common: dma-mapping: introduce common remapping functions

For architectures without coherent DMA, memory for DMA may need to be
remapped with coherent attributes.  Factor out the the remapping code from
arm and put it in a common location to reduce code duplication.

As part of this, the arm APIs are now migrated away from
ioremap_page_range to the common APIs which use map_vm_area for remapping.
 This should be an equivalent change and using map_vm_area is more correct
as ioremap_page_range is intended to bring in io addresses into the cpu
space and not regular kernel managed memory.

Signed-off-by: Laura Abbott <lauraa@codeaurora.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Riley <davidriley@chromium.org>
Cc: Olof Johansson <olof@lixom.net>
Cc: Ritesh Harjain <ritesh.harjani@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Laura Abbott <lauraa@codeaurora.org>
Cc: Mitchel Humpherys <mitchelh@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/mm/dma-mapping.c                | 57 ++++---------------------
 drivers/base/dma-mapping.c               | 72 ++++++++++++++++++++++++++++++++
 include/asm-generic/dma-mapping-common.h |  9 ++++
 3 files changed, 90 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7a996aaa061e..eecc8e60deea 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -298,37 +298,19 @@ static void *
 __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
 	const void *caller)
 {
-	struct vm_struct *area;
-	unsigned long addr;
-
 	/*
 	 * DMA allocation can be mapped to user space, so lets
 	 * set VM_USERMAP flags too.
 	 */
-	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-				  caller);
-	if (!area)
-		return NULL;
-	addr = (unsigned long)area->addr;
-	area->phys_addr = __pfn_to_phys(page_to_pfn(page));
-
-	if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {
-		vunmap((void *)addr);
-		return NULL;
-	}
-	return (void *)addr;
+	return dma_common_contiguous_remap(page, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+			prot, caller);
 }
 
 static void __dma_free_remap(void *cpu_addr, size_t size)
 {
-	unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP;
-	struct vm_struct *area = find_vm_area(cpu_addr);
-	if (!area || (area->flags & flags) != flags) {
-		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
-		return;
-	}
-	unmap_kernel_range((unsigned long)cpu_addr, size);
-	vunmap(cpu_addr);
+	dma_common_free_remap(cpu_addr, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 }
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
@@ -1271,29 +1253,8 @@ static void *
 __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
 		    const void *caller)
 {
-	unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct vm_struct *area;
-	unsigned long p;
-
-	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-				  caller);
-	if (!area)
-		return NULL;
-
-	area->pages = pages;
-	area->nr_pages = nr_pages;
-	p = (unsigned long)area->addr;
-
-	for (i = 0; i < nr_pages; i++) {
-		phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i]));
-		if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot))
-			goto err;
-		p += PAGE_SIZE;
-	}
-	return area->addr;
-err:
-	unmap_kernel_range((unsigned long)area->addr, size);
-	vunmap(area->addr);
+	return dma_common_pages_remap(pages, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
 	return NULL;
 }
 
@@ -1501,8 +1462,8 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	}
 
 	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
-		unmap_kernel_range((unsigned long)cpu_addr, size);
-		vunmap(cpu_addr);
+		dma_common_free_remap(cpu_addr, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 	}
 
 	__iommu_remove_mapping(dev, handle, size);
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index 6cd08e145bfa..9e8bbdd470ca 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -10,6 +10,8 @@
 #include <linux/dma-mapping.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm-generic/dma-coherent.h>
 
 /*
@@ -267,3 +269,73 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 EXPORT_SYMBOL(dma_common_mmap);
+
+#ifdef CONFIG_MMU
+/*
+ * remaps an array of PAGE_SIZE pages into another vm_area
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller)
+{
+	struct vm_struct *area;
+
+	area = get_vm_area_caller(size, vm_flags, caller);
+	if (!area)
+		return NULL;
+
+	area->pages = pages;
+
+	if (map_vm_area(area, prot, pages)) {
+		vunmap(area->addr);
+		return NULL;
+	}
+
+	return area->addr;
+}
+
+/*
+ * remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller)
+{
+	int i;
+	struct page **pages;
+	void *ptr;
+	unsigned long pfn;
+
+	pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+
+	for (i = 0, pfn = page_to_pfn(page); i < (size >> PAGE_SHIFT); i++)
+		pages[i] = pfn_to_page(pfn + i);
+
+	ptr = dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+
+	kfree(pages);
+
+	return ptr;
+}
+
+/*
+ * unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+{
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || (area->flags & vm_flags) != vm_flags) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+		return;
+	}
+
+	unmap_kernel_range((unsigned long)cpu_addr, size);
+	vunmap(cpu_addr);
+}
+#endif
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index de8bf89940f8..a9fd248f5d48 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -179,6 +179,15 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
 
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller);
+
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
+
 /**
  * dma_mmap_attrs - map a coherent DMA allocation into user space
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
-- 
cgit v1.2.3


From 53853e2d2bfb748a8b5aa2fd1de15699266865e0 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Thu, 9 Oct 2014 15:27:02 -0700
Subject: mm, compaction: defer each zone individually instead of preferred
 zone

When direct sync compaction is often unsuccessful, it may become deferred
for some time to avoid further useless attempts, both sync and async.
Successful high-order allocations un-defer compaction, while further
unsuccessful compaction attempts prolong the compaction deferred period.

Currently the checking and setting deferred status is performed only on
the preferred zone of the allocation that invoked direct compaction.  But
compaction itself is attempted on all eligible zones in the zonelist, so
the behavior is suboptimal and may lead both to scenarios where 1)
compaction is attempted uselessly, or 2) where it's not attempted despite
good chances of succeeding, as shown on the examples below:

1) A direct compaction with Normal preferred zone failed and set
   deferred compaction for the Normal zone.  Another unrelated direct
   compaction with DMA32 as preferred zone will attempt to compact DMA32
   zone even though the first compaction attempt also included DMA32 zone.

   In another scenario, compaction with Normal preferred zone failed to
   compact Normal zone, but succeeded in the DMA32 zone, so it will not
   defer compaction.  In the next attempt, it will try Normal zone which
   will fail again, instead of skipping Normal zone and trying DMA32
   directly.

2) Kswapd will balance DMA32 zone and reset defer status based on
   watermarks looking good.  A direct compaction with preferred Normal
   zone will skip compaction of all zones including DMA32 because Normal
   was still deferred.  The allocation might have succeeded in DMA32, but
   won't.

This patch makes compaction deferring work on individual zone basis
instead of preferred zone.  For each zone, it checks compaction_deferred()
to decide if the zone should be skipped.  If watermarks fail after
compacting the zone, defer_compaction() is called.  The zone where
watermarks passed can still be deferred when the allocation attempt is
unsuccessful.  When allocation is successful, compaction_defer_reset() is
called for the zone containing the allocated page.  This approach should
approximate calling defer_compaction() only on zones where compaction was
attempted and did not yield allocated page.  There might be corner cases
but that is inevitable as long as the decision to stop compacting dues not
guarantee that a page will be allocated.

Due to a new COMPACT_DEFERRED return value, some functions relying
implicitly on COMPACT_SKIPPED = 0 had to be updated, with comments made
more accurate.  The did_some_progress output parameter of
__alloc_pages_direct_compact() is removed completely, as the caller
actually does not use it after compaction sets it - it is only considered
when direct reclaim sets it.

During testing on a two-node machine with a single very small Normal zone
on node 1, this patch has improved success rates in stress-highalloc
mmtests benchmark.  The success here were previously made worse by commit
3a025760fc15 ("mm: page_alloc: spill to remote nodes before waking
kswapd") as kswapd was no longer resetting often enough the deferred
compaction for the Normal zone, and DMA32 zones on both nodes were thus
not considered for compaction.  On different machine, success rates were
improved with __GFP_NO_KSWAPD allocations.

[akpm@linux-foundation.org: fix CONFIG_COMPACTION=n build]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h | 16 ++++++++-----
 mm/compaction.c            | 32 ++++++++++++++++++++------
 mm/page_alloc.c            | 57 +++++++++++++++++++++++++---------------------
 mm/vmscan.c                | 14 ++++++++----
 4 files changed, 76 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 01e3132820da..b2e4c92d0445 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -2,14 +2,16 @@
 #define _LINUX_COMPACTION_H
 
 /* Return values for compact_zone() and try_to_compact_pages() */
+/* compaction didn't start as it was deferred due to past failures */
+#define COMPACT_DEFERRED	0
 /* compaction didn't start as it was not possible or direct reclaim was more suitable */
-#define COMPACT_SKIPPED		0
+#define COMPACT_SKIPPED		1
 /* compaction should continue to another pageblock */
-#define COMPACT_CONTINUE	1
+#define COMPACT_CONTINUE	2
 /* direct compaction partially compacted a zone and there are suitable pages */
-#define COMPACT_PARTIAL		2
+#define COMPACT_PARTIAL		3
 /* The full zone was compacted */
-#define COMPACT_COMPLETE	3
+#define COMPACT_COMPLETE	4
 
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
@@ -22,7 +24,8 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			enum migrate_mode mode, bool *contended);
+			enum migrate_mode mode, bool *contended,
+			struct zone **candidate_zone);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
@@ -91,7 +94,8 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			enum migrate_mode mode, bool *contended)
+			enum migrate_mode mode, bool *contended,
+			struct zone **candidate_zone)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index 21bf292b642a..1c7195d42e83 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1125,27 +1125,26 @@ int sysctl_extfrag_threshold = 500;
  * @nodemask: The allowed nodes to allocate from
  * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that is true if compaction was aborted due to lock contention
- * @page: Optionally capture a free page of the requested order during compaction
+ * @candidate_zone: Return the zone where we think allocation should succeed
  *
  * This is the main entry point for direct page compaction.
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			enum migrate_mode mode, bool *contended)
+			enum migrate_mode mode, bool *contended,
+			struct zone **candidate_zone)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
 	int may_perform_io = gfp_mask & __GFP_IO;
 	struct zoneref *z;
 	struct zone *zone;
-	int rc = COMPACT_SKIPPED;
+	int rc = COMPACT_DEFERRED;
 	int alloc_flags = 0;
 
 	/* Check if the GFP flags allow compaction */
 	if (!order || !may_enter_fs || !may_perform_io)
-		return rc;
-
-	count_compact_event(COMPACTSTALL);
+		return COMPACT_SKIPPED;
 
 #ifdef CONFIG_CMA
 	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
@@ -1156,14 +1155,33 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 								nodemask) {
 		int status;
 
+		if (compaction_deferred(zone, order))
+			continue;
+
 		status = compact_zone_order(zone, order, gfp_mask, mode,
 						contended);
 		rc = max(status, rc);
 
 		/* If a normal allocation would succeed, stop compacting */
 		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
-				      alloc_flags))
+				      alloc_flags)) {
+			*candidate_zone = zone;
+			/*
+			 * We think the allocation will succeed in this zone,
+			 * but it is not certain, hence the false. The caller
+			 * will repeat this with true if allocation indeed
+			 * succeeds in this zone.
+			 */
+			compaction_defer_reset(zone, order, false);
 			break;
+		} else if (mode != MIGRATE_ASYNC) {
+			/*
+			 * We think that allocation won't succeed in this zone
+			 * so we defer compaction there. If it ends up
+			 * succeeding after all, it will be reset.
+			 */
+			defer_compaction(zone, order);
+		}
 	}
 
 	return rc;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e63bf7744a0c..514fd8008114 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2297,24 +2297,28 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
 	int classzone_idx, int migratetype, enum migrate_mode mode,
-	bool *contended_compaction, bool *deferred_compaction,
-	unsigned long *did_some_progress)
+	bool *contended_compaction, bool *deferred_compaction)
 {
-	if (!order)
-		return NULL;
+	struct zone *last_compact_zone = NULL;
+	unsigned long compact_result;
 
-	if (compaction_deferred(preferred_zone, order)) {
-		*deferred_compaction = true;
+
+	if (!order)
 		return NULL;
-	}
 
 	current->flags |= PF_MEMALLOC;
-	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
+	compact_result = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, mode,
-						contended_compaction);
+						contended_compaction,
+						&last_compact_zone);
 	current->flags &= ~PF_MEMALLOC;
 
-	if (*did_some_progress != COMPACT_SKIPPED) {
+	if (compact_result > COMPACT_DEFERRED)
+		count_vm_event(COMPACTSTALL);
+	else
+		*deferred_compaction = true;
+
+	if (compact_result > COMPACT_SKIPPED) {
 		struct page *page;
 
 		/* Page migration frees to the PCP lists but we want merging */
@@ -2325,13 +2329,24 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 				order, zonelist, high_zoneidx,
 				alloc_flags & ~ALLOC_NO_WATERMARKS,
 				preferred_zone, classzone_idx, migratetype);
+
 		if (page) {
-			preferred_zone->compact_blockskip_flush = false;
-			compaction_defer_reset(preferred_zone, order, true);
+			struct zone *zone = page_zone(page);
+
+			zone->compact_blockskip_flush = false;
+			compaction_defer_reset(zone, order, true);
 			count_vm_event(COMPACTSUCCESS);
 			return page;
 		}
 
+		/*
+		 * last_compact_zone is where try_to_compact_pages thought
+		 * allocation should succeed, so it did not defer compaction.
+		 * But now we know that it didn't succeed, so we do the defer.
+		 */
+		if (last_compact_zone && mode != MIGRATE_ASYNC)
+			defer_compaction(last_compact_zone, order);
+
 		/*
 		 * It's bad if compaction run occurs and fails.
 		 * The most likely reason is that pages exist,
@@ -2339,13 +2354,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		 */
 		count_vm_event(COMPACTFAIL);
 
-		/*
-		 * As async compaction considers a subset of pageblocks, only
-		 * defer if the failure was a sync compaction failure.
-		 */
-		if (mode != MIGRATE_ASYNC)
-			defer_compaction(preferred_zone, order);
-
 		cond_resched();
 	}
 
@@ -2356,9 +2364,8 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int classzone_idx, int migratetype,
-	enum migrate_mode mode, bool *contended_compaction,
-	bool *deferred_compaction, unsigned long *did_some_progress)
+	int classzone_idx, int migratetype, enum migrate_mode mode,
+	bool *contended_compaction, bool *deferred_compaction)
 {
 	return NULL;
 }
@@ -2634,8 +2641,7 @@ rebalance:
 					preferred_zone,
 					classzone_idx, migratetype,
 					migration_mode, &contended_compaction,
-					&deferred_compaction,
-					&did_some_progress);
+					&deferred_compaction);
 	if (page)
 		goto got_pg;
 
@@ -2727,8 +2733,7 @@ rebalance:
 					preferred_zone,
 					classzone_idx, migratetype,
 					migration_mode, &contended_compaction,
-					&deferred_compaction,
-					&did_some_progress);
+					&deferred_compaction);
 		if (page)
 			goto got_pg;
 	}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2836b5373b2e..1a71b8b1ea34 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2315,7 +2315,10 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc)
 	return reclaimable;
 }
 
-/* Returns true if compaction should go ahead for a high-order request */
+/*
+ * Returns true if compaction should go ahead for a high-order request, or
+ * the high-order allocation would succeed without compaction.
+ */
 static inline bool compaction_ready(struct zone *zone, int order)
 {
 	unsigned long balance_gap, watermark;
@@ -2339,8 +2342,11 @@ static inline bool compaction_ready(struct zone *zone, int order)
 	if (compaction_deferred(zone, order))
 		return watermark_ok;
 
-	/* If compaction is not ready to start, keep reclaiming */
-	if (!compaction_suitable(zone, order))
+	/*
+	 * If compaction is not ready to start and allocation is not likely
+	 * to succeed without it, then keep reclaiming.
+	 */
+	if (compaction_suitable(zone, order) == COMPACT_SKIPPED)
 		return false;
 
 	return watermark_ok;
@@ -2818,7 +2824,7 @@ static bool zone_balanced(struct zone *zone, int order,
 		return false;
 
 	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
-	    !compaction_suitable(zone, order))
+	    compaction_suitable(zone, order) == COMPACT_SKIPPED)
 		return false;
 
 	return true;
-- 
cgit v1.2.3


From 1f9efdef4f3f1d2a073e524113fd0038af636f2b Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Thu, 9 Oct 2014 15:27:14 -0700
Subject: mm, compaction: khugepaged should not give up due to need_resched()

Async compaction aborts when it detects zone lock contention or
need_resched() is true.  David Rientjes has reported that in practice,
most direct async compactions for THP allocation abort due to
need_resched().  This means that a second direct compaction is never
attempted, which might be OK for a page fault, but khugepaged is intended
to attempt a sync compaction in such case and in these cases it won't.

This patch replaces "bool contended" in compact_control with an int that
distinguishes between aborting due to need_resched() and aborting due to
lock contention.  This allows propagating the abort through all compaction
functions as before, but passing the abort reason up to
__alloc_pages_slowpath() which decides when to continue with direct
reclaim and another compaction attempt.

Another problem is that try_to_compact_pages() did not act upon the
reported contention (both need_resched() or lock contention) immediately
and would proceed with another zone from the zonelist.  When
need_resched() is true, that means initializing another zone compaction,
only to check again need_resched() in isolate_migratepages() and aborting.
 For zone lock contention, the unintended consequence is that the lock
contended status reported back to the allocator is detrmined from the last
zone where compaction was attempted, which is rather arbitrary.

This patch fixes the problem in the following way:
- async compaction of a zone aborting due to need_resched() or fatal signal
  pending means that further zones should not be tried. We report
  COMPACT_CONTENDED_SCHED to the allocator.
- aborting zone compaction due to lock contention means we can still try
  another zone, since it has different set of locks. We report back
  COMPACT_CONTENDED_LOCK only if *all* zones where compaction was attempted,
  it was aborted due to lock contention.

As a result of these fixes, khugepaged will proceed with second sync
compaction as intended, when the preceding async compaction aborted due to
need_resched().  Page fault compactions aborting due to need_resched()
will spare some cycles previously wasted by initializing another zone
compaction only to abort again.  Lock contention will be reported only
when compaction in all zones aborted due to lock contention, and therefore
it's not a good idea to try again after reclaim.

In stress-highalloc from mmtests configured to use __GFP_NO_KSWAPD, this
has improved number of THP collapse allocations by 10%, which shows
positive effect on khugepaged.  The benchmark's success rates are
unchanged as it is not recognized as khugepaged.  Numbers of compact_stall
and compact_fail events have however decreased by 20%, with
compact_success still a bit improved, which is good.  With benchmark
configured not to use __GFP_NO_KSWAPD, there is 6% improvement in THP
collapse allocations, and only slight improvement in stalls and failures.

[akpm@linux-foundation.org: fix warnings]
Reported-by: David Rientjes <rientjes@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h | 12 +++++--
 mm/compaction.c            | 87 ++++++++++++++++++++++++++++++++++++++++------
 mm/internal.h              |  4 +--
 mm/page_alloc.c            | 45 +++++++++++++++++-------
 4 files changed, 121 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index b2e4c92d0445..60bdf8dc02a3 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -13,6 +13,14 @@
 /* The full zone was compacted */
 #define COMPACT_COMPLETE	4
 
+/* Used to signal whether compaction detected need_sched() or lock contention */
+/* No contention detected */
+#define COMPACT_CONTENDED_NONE	0
+/* Either need_sched() was true or fatal signal pending */
+#define COMPACT_CONTENDED_SCHED	1
+/* Zone lock or lru_lock was contended in async compaction */
+#define COMPACT_CONTENDED_LOCK	2
+
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
@@ -24,7 +32,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			enum migrate_mode mode, bool *contended,
+			enum migrate_mode mode, int *contended,
 			struct zone **candidate_zone);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
@@ -94,7 +102,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			enum migrate_mode mode, bool *contended,
+			enum migrate_mode mode, int *contended,
 			struct zone **candidate_zone)
 {
 	return COMPACT_CONTINUE;
diff --git a/mm/compaction.c b/mm/compaction.c
index 1067c07cb33d..26bb20ef853d 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -223,9 +223,21 @@ static void update_pageblock_skip(struct compact_control *cc,
 }
 #endif /* CONFIG_COMPACTION */
 
-static inline bool should_release_lock(spinlock_t *lock)
+static int should_release_lock(spinlock_t *lock)
 {
-	return need_resched() || spin_is_contended(lock);
+	/*
+	 * Sched contention has higher priority here as we may potentially
+	 * have to abort whole compaction ASAP. Returning with lock contention
+	 * means we will try another zone, and further decisions are
+	 * influenced only when all zones are lock contended. That means
+	 * potentially missing a lock contention is less critical.
+	 */
+	if (need_resched())
+		return COMPACT_CONTENDED_SCHED;
+	else if (spin_is_contended(lock))
+		return COMPACT_CONTENDED_LOCK;
+
+	return COMPACT_CONTENDED_NONE;
 }
 
 /*
@@ -240,7 +252,9 @@ static inline bool should_release_lock(spinlock_t *lock)
 static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
 				      bool locked, struct compact_control *cc)
 {
-	if (should_release_lock(lock)) {
+	int contended = should_release_lock(lock);
+
+	if (contended) {
 		if (locked) {
 			spin_unlock_irqrestore(lock, *flags);
 			locked = false;
@@ -248,7 +262,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
 
 		/* async aborts if taking too long or contended */
 		if (cc->mode == MIGRATE_ASYNC) {
-			cc->contended = true;
+			cc->contended = contended;
 			return false;
 		}
 
@@ -274,7 +288,7 @@ static inline bool compact_should_abort(struct compact_control *cc)
 	/* async compaction aborts if contended */
 	if (need_resched()) {
 		if (cc->mode == MIGRATE_ASYNC) {
-			cc->contended = true;
+			cc->contended = COMPACT_CONTENDED_SCHED;
 			return true;
 		}
 
@@ -1140,7 +1154,7 @@ out:
 }
 
 static unsigned long compact_zone_order(struct zone *zone, int order,
-		gfp_t gfp_mask, enum migrate_mode mode, bool *contended)
+		gfp_t gfp_mask, enum migrate_mode mode, int *contended)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1172,14 +1186,15 @@ int sysctl_extfrag_threshold = 500;
  * @gfp_mask: The GFP mask of the current allocation
  * @nodemask: The allowed nodes to allocate from
  * @mode: The migration mode for async, sync light, or sync migration
- * @contended: Return value that is true if compaction was aborted due to lock contention
+ * @contended: Return value that determines if compaction was aborted due to
+ *	       need_resched() or lock contention
  * @candidate_zone: Return the zone where we think allocation should succeed
  *
  * This is the main entry point for direct page compaction.
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			enum migrate_mode mode, bool *contended,
+			enum migrate_mode mode, int *contended,
 			struct zone **candidate_zone)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
@@ -1189,6 +1204,9 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	struct zone *zone;
 	int rc = COMPACT_DEFERRED;
 	int alloc_flags = 0;
+	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
+
+	*contended = COMPACT_CONTENDED_NONE;
 
 	/* Check if the GFP flags allow compaction */
 	if (!order || !may_enter_fs || !may_perform_io)
@@ -1202,13 +1220,19 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
 		int status;
+		int zone_contended;
 
 		if (compaction_deferred(zone, order))
 			continue;
 
 		status = compact_zone_order(zone, order, gfp_mask, mode,
-						contended);
+							&zone_contended);
 		rc = max(status, rc);
+		/*
+		 * It takes at least one zone that wasn't lock contended
+		 * to clear all_zones_contended.
+		 */
+		all_zones_contended &= zone_contended;
 
 		/* If a normal allocation would succeed, stop compacting */
 		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
@@ -1221,8 +1245,21 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			 * succeeds in this zone.
 			 */
 			compaction_defer_reset(zone, order, false);
-			break;
-		} else if (mode != MIGRATE_ASYNC) {
+			/*
+			 * It is possible that async compaction aborted due to
+			 * need_resched() and the watermarks were ok thanks to
+			 * somebody else freeing memory. The allocation can
+			 * however still fail so we better signal the
+			 * need_resched() contention anyway (this will not
+			 * prevent the allocation attempt).
+			 */
+			if (zone_contended == COMPACT_CONTENDED_SCHED)
+				*contended = COMPACT_CONTENDED_SCHED;
+
+			goto break_loop;
+		}
+
+		if (mode != MIGRATE_ASYNC) {
 			/*
 			 * We think that allocation won't succeed in this zone
 			 * so we defer compaction there. If it ends up
@@ -1230,8 +1267,36 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			 */
 			defer_compaction(zone, order);
 		}
+
+		/*
+		 * We might have stopped compacting due to need_resched() in
+		 * async compaction, or due to a fatal signal detected. In that
+		 * case do not try further zones and signal need_resched()
+		 * contention.
+		 */
+		if ((zone_contended == COMPACT_CONTENDED_SCHED)
+					|| fatal_signal_pending(current)) {
+			*contended = COMPACT_CONTENDED_SCHED;
+			goto break_loop;
+		}
+
+		continue;
+break_loop:
+		/*
+		 * We might not have tried all the zones, so  be conservative
+		 * and assume they are not all lock contended.
+		 */
+		all_zones_contended = 0;
+		break;
 	}
 
+	/*
+	 * If at least one zone wasn't deferred or skipped, we report if all
+	 * zones that were tried were lock contended.
+	 */
+	if (rc > COMPACT_SKIPPED && all_zones_contended)
+		*contended = COMPACT_CONTENDED_LOCK;
+
 	return rc;
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index 5a0738fa649c..4c1d604c396c 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -144,8 +144,8 @@ struct compact_control {
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
-	bool contended;			/* True if a lock was contended, or
-					 * need_resched() true during async
+	int contended;			/* Signal need_sched() or lock
+					 * contention detected during
 					 * compaction
 					 */
 };
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index dfbf54b51649..313338d74095 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2297,7 +2297,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
 	int classzone_idx, int migratetype, enum migrate_mode mode,
-	bool *contended_compaction, bool *deferred_compaction)
+	int *contended_compaction, bool *deferred_compaction)
 {
 	struct zone *last_compact_zone = NULL;
 	unsigned long compact_result;
@@ -2371,7 +2371,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
 	int classzone_idx, int migratetype, enum migrate_mode mode,
-	bool *contended_compaction, bool *deferred_compaction)
+	int *contended_compaction, bool *deferred_compaction)
 {
 	return NULL;
 }
@@ -2547,7 +2547,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long did_some_progress;
 	enum migrate_mode migration_mode = MIGRATE_ASYNC;
 	bool deferred_compaction = false;
-	bool contended_compaction = false;
+	int contended_compaction = COMPACT_CONTENDED_NONE;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -2651,15 +2651,36 @@ rebalance:
 	if (page)
 		goto got_pg;
 
-	/*
-	 * If compaction is deferred for high-order allocations, it is because
-	 * sync compaction recently failed. In this is the case and the caller
-	 * requested a movable allocation that does not heavily disrupt the
-	 * system then fail the allocation instead of entering direct reclaim.
-	 */
-	if ((deferred_compaction || contended_compaction) &&
-						(gfp_mask & __GFP_NO_KSWAPD))
-		goto nopage;
+	/* Checks for THP-specific high-order allocations */
+	if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) {
+		/*
+		 * If compaction is deferred for high-order allocations, it is
+		 * because sync compaction recently failed. If this is the case
+		 * and the caller requested a THP allocation, we do not want
+		 * to heavily disrupt the system, so we fail the allocation
+		 * instead of entering direct reclaim.
+		 */
+		if (deferred_compaction)
+			goto nopage;
+
+		/*
+		 * In all zones where compaction was attempted (and not
+		 * deferred or skipped), lock contention has been detected.
+		 * For THP allocation we do not want to disrupt the others
+		 * so we fallback to base pages instead.
+		 */
+		if (contended_compaction == COMPACT_CONTENDED_LOCK)
+			goto nopage;
+
+		/*
+		 * If compaction was aborted due to need_resched(), we do not
+		 * want to further increase allocation latency, unless it is
+		 * khugepaged trying to collapse.
+		 */
+		if (contended_compaction == COMPACT_CONTENDED_SCHED
+			&& !(current->flags & PF_KTHREAD))
+			goto nopage;
+	}
 
 	/*
 	 * It can become very expensive to allocate transparent hugepages at
-- 
cgit v1.2.3


From 43e7a34d265e884b7cf34f9b05e6f2e0c05bf120 Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Thu, 9 Oct 2014 15:27:25 -0700
Subject: mm: rename allocflags_to_migratetype for clarity

The page allocator has gfp flags (like __GFP_WAIT) and alloc flags (like
ALLOC_CPUSET) that have separate semantics.

The function allocflags_to_migratetype() actually takes gfp flags, not
alloc flags, and returns a migratetype.  Rename it to
gfpflags_to_migratetype().

Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 2 +-
 mm/compaction.c     | 4 ++--
 mm/page_alloc.c     | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 5e7219dc0fae..41b30fd4d041 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -156,7 +156,7 @@ struct vm_area_struct;
 #define GFP_DMA32	__GFP_DMA32
 
 /* Convert GFP flags to their corresponding migrate type */
-static inline int allocflags_to_migratetype(gfp_t gfp_flags)
+static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
 {
 	WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
 
diff --git a/mm/compaction.c b/mm/compaction.c
index b9cf751cc00e..7c687c0eef6e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1242,7 +1242,7 @@ static unsigned long compact_zone_order(struct zone *zone, int order,
 		.nr_freepages = 0,
 		.nr_migratepages = 0,
 		.order = order,
-		.migratetype = allocflags_to_migratetype(gfp_mask),
+		.migratetype = gfpflags_to_migratetype(gfp_mask),
 		.zone = zone,
 		.mode = mode,
 	};
@@ -1294,7 +1294,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		return COMPACT_SKIPPED;
 
 #ifdef CONFIG_CMA
-	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 #endif
 	/* Compact each zone in the list */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 313338d74095..f07588b11d59 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2523,7 +2523,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
 #ifdef CONFIG_CMA
-	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 #endif
 	return alloc_flags;
@@ -2786,7 +2786,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	struct zone *preferred_zone;
 	struct zoneref *preferred_zoneref;
 	struct page *page = NULL;
-	int migratetype = allocflags_to_migratetype(gfp_mask);
+	int migratetype = gfpflags_to_migratetype(gfp_mask);
 	unsigned int cpuset_mems_cookie;
 	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
 	int classzone_idx;
-- 
cgit v1.2.3


From 9c5990240e076ae564cccbd921868cd08f6daaa5 Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@openvz.org>
Date: Thu, 9 Oct 2014 15:27:29 -0700
Subject: mm: introduce check_data_rlimit helper

To eliminate code duplication lets introduce check_data_rlimit helper
which we will use in brk() and prctl() syscalls.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrew Vagin <avagin@openvz.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Vasiliy Kulikov <segoon@openwall.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Julien Tinnes <jln@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 28df70774b81..4d814aa97785 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -18,6 +18,7 @@
 #include <linux/pfn.h>
 #include <linux/bit_spinlock.h>
 #include <linux/shrinker.h>
+#include <linux/resource.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -1780,6 +1781,20 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
 	bool *need_rmap_locks);
 extern void exit_mmap(struct mm_struct *);
 
+static inline int check_data_rlimit(unsigned long rlim,
+				    unsigned long new,
+				    unsigned long start,
+				    unsigned long end_data,
+				    unsigned long start_data)
+{
+	if (rlim < RLIM_INFINITY) {
+		if (((new - start) + (end_data - start_data)) > rlim)
+			return -ENOSPC;
+	}
+
+	return 0;
+}
+
 extern int mm_take_all_locks(struct mm_struct *mm);
 extern void mm_drop_all_locks(struct mm_struct *mm);
 
-- 
cgit v1.2.3


From f606b77f1a9e362451aca8f81d8f36a3a112139e Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@openvz.org>
Date: Thu, 9 Oct 2014 15:27:37 -0700
Subject: prctl: PR_SET_MM -- introduce PR_SET_MM_MAP operation

During development of c/r we've noticed that in case if we need to support
user namespaces we face a problem with capabilities in prctl(PR_SET_MM,
...) call, in particular once new user namespace is created
capable(CAP_SYS_RESOURCE) no longer passes.

A approach is to eliminate CAP_SYS_RESOURCE check but pass all new values
in one bundle, which would allow the kernel to make more intensive test
for sanity of values and same time allow us to support checkpoint/restore
of user namespaces.

Thus a new command PR_SET_MM_MAP introduced. It takes a pointer of
prctl_mm_map structure which carries all the members to be updated.

	prctl(PR_SET_MM, PR_SET_MM_MAP, struct prctl_mm_map *, size)

	struct prctl_mm_map {
		__u64	start_code;
		__u64	end_code;
		__u64	start_data;
		__u64	end_data;
		__u64	start_brk;
		__u64	brk;
		__u64	start_stack;
		__u64	arg_start;
		__u64	arg_end;
		__u64	env_start;
		__u64	env_end;
		__u64	*auxv;
		__u32	auxv_size;
		__u32	exe_fd;
	};

All members except @exe_fd correspond ones of struct mm_struct.  To figure
out which available values these members may take here are meanings of the
members.

 - start_code, end_code: represent bounds of executable code area
 - start_data, end_data: represent bounds of data area
 - start_brk, brk: used to calculate bounds for brk() syscall
 - start_stack: used when accounting space needed for command
   line arguments, environment and shmat() syscall
 - arg_start, arg_end, env_start, env_end: represent memory area
   supplied for command line arguments and environment variables
 - auxv, auxv_size: carries auxiliary vector, Elf format specifics
 - exe_fd: file descriptor number for executable link (/proc/self/exe)

Thus we apply the following requirements to the values

1) Any member except @auxv, @auxv_size, @exe_fd is rather an address
   in user space thus it must be laying inside [mmap_min_addr, mmap_max_addr)
   interval.

2) While @[start|end]_code and @[start|end]_data may point to an nonexisting
   VMAs (say a program maps own new .text and .data segments during execution)
   the rest of members should belong to VMA which must exist.

3) Addresses must be ordered, ie @start_ member must not be greater or
   equal to appropriate @end_ member.

4) As in regular Elf loading procedure we require that @start_brk and
   @brk be greater than @end_data.

5) If RLIMIT_DATA rlimit is set to non-infinity new values should not
   exceed existing limit. Same applies to RLIMIT_STACK.

6) Auxiliary vector size must not exceed existing one (which is
   predefined as AT_VECTOR_SIZE and depends on architecture).

7) File descriptor passed in @exe_file should be pointing
   to executable file (because we use existing prctl_set_mm_exe_file_locked
   helper it ensures that the file we are going to use as exe link has all
   required permission granted).

Now about where these members are involved inside kernel code:

 - @start_code and @end_code are used in /proc/$pid/[stat|statm] output;

 - @start_data and @end_data are used in /proc/$pid/[stat|statm] output,
   also they are considered if there enough space for brk() syscall
   result if RLIMIT_DATA is set;

 - @start_brk shown in /proc/$pid/stat output and accounted in brk()
   syscall if RLIMIT_DATA is set; also this member is tested to
   find a symbolic name of mmap event for perf system (we choose
   if event is generated for "heap" area); one more aplication is
   selinux -- we test if a process has PROCESS__EXECHEAP permission
   if trying to make heap area being executable with mprotect() syscall;

 - @brk is a current value for brk() syscall which lays inside heap
   area, it's shown in /proc/$pid/stat. When syscall brk() succesfully
   provides new memory area to a user space upon brk() completion the
   mm::brk is updated to carry new value;

   Both @start_brk and @brk are actively used in /proc/$pid/maps
   and /proc/$pid/smaps output to find a symbolic name "heap" for
   VMA being scanned;

 - @start_stack is printed out in /proc/$pid/stat and used to
   find a symbolic name "stack" for task and threads in
   /proc/$pid/maps and /proc/$pid/smaps output, and as the same
   as with @start_brk -- perf system uses it for event naming.
   Also kernel treat this member as a start address of where
   to map vDSO pages and to check if there is enough space
   for shmat() syscall;

 - @arg_start, @arg_end, @env_start and @env_end are printed out
   in /proc/$pid/stat. Another access to the data these members
   represent is to read /proc/$pid/environ or /proc/$pid/cmdline.
   Any attempt to read these areas kernel tests with access_process_vm
   helper so a user must have enough rights for this action;

 - @auxv and @auxv_size may be read from /proc/$pid/auxv. Strictly
   speaking kernel doesn't care much about which exactly data is
   sitting there because it is solely for userspace;

 - @exe_fd is referred from /proc/$pid/exe and when generating
   coredump. We uses prctl_set_mm_exe_file_locked helper to update
   this member, so exe-file link modification remains one-shot
   action.

Still note that updating exe-file link now doesn't require sys-resource
capability anymore, after all there is no much profit in preventing setup
own file link (there are a number of ways to execute own code -- ptrace,
ld-preload, so that the only reliable way to find which exactly code is
executed is to inspect running program memory).  Still we require the
caller to be at least user-namespace root user.

I believe the old interface should be deprecated and ripped off in a
couple of kernel releases if no one against.

To test if new interface is implemented in the kernel one can pass
PR_SET_MM_MAP_SIZE opcode and the kernel returns the size of currently
supported struct prctl_mm_map.

[akpm@linux-foundation.org: fix 80-col wordwrap in macro definitions]
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Tejun Heo <tj@kernel.org>
Acked-by: Andrew Vagin <avagin@openvz.org>
Tested-by: Andrew Vagin <avagin@openvz.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Vasiliy Kulikov <segoon@openwall.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Julien Tinnes <jln@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/prctl.h |  27 +++++++
 kernel/sys.c               | 190 ++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 216 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 58afc04c107e..513df75d0fc9 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_PRCTL_H
 #define _LINUX_PRCTL_H
 
+#include <linux/types.h>
+
 /* Values to pass as first argument to prctl() */
 
 #define PR_SET_PDEATHSIG  1  /* Second arg is a signal */
@@ -119,6 +121,31 @@
 # define PR_SET_MM_ENV_END		11
 # define PR_SET_MM_AUXV			12
 # define PR_SET_MM_EXE_FILE		13
+# define PR_SET_MM_MAP			14
+# define PR_SET_MM_MAP_SIZE		15
+
+/*
+ * This structure provides new memory descriptor
+ * map which mostly modifies /proc/pid/stat[m]
+ * output for a task. This mostly done in a
+ * sake of checkpoint/restore functionality.
+ */
+struct prctl_mm_map {
+	__u64	start_code;		/* code section bounds */
+	__u64	end_code;
+	__u64	start_data;		/* data section bounds */
+	__u64	end_data;
+	__u64	start_brk;		/* heap for brk() syscall */
+	__u64	brk;
+	__u64	start_stack;		/* stack starts at */
+	__u64	arg_start;		/* command line arguments bounds */
+	__u64	arg_end;
+	__u64	env_start;		/* environment variables bounds */
+	__u64	env_end;
+	__u64	*auxv;			/* auxiliary vector */
+	__u32	auxv_size;		/* vector size */
+	__u32	exe_fd;			/* /proc/$pid/exe link file */
+};
 
 /*
  * Set specific pid that is allowed to ptrace the current task.
diff --git a/kernel/sys.c b/kernel/sys.c
index 14222a1699c0..f7030b060018 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1687,6 +1687,187 @@ exit:
 	return err;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+/*
+ * WARNING: we don't require any capability here so be very careful
+ * in what is allowed for modification from userspace.
+ */
+static int validate_prctl_map(struct prctl_mm_map *prctl_map)
+{
+	unsigned long mmap_max_addr = TASK_SIZE;
+	struct mm_struct *mm = current->mm;
+	int error = -EINVAL, i;
+
+	static const unsigned char offsets[] = {
+		offsetof(struct prctl_mm_map, start_code),
+		offsetof(struct prctl_mm_map, end_code),
+		offsetof(struct prctl_mm_map, start_data),
+		offsetof(struct prctl_mm_map, end_data),
+		offsetof(struct prctl_mm_map, start_brk),
+		offsetof(struct prctl_mm_map, brk),
+		offsetof(struct prctl_mm_map, start_stack),
+		offsetof(struct prctl_mm_map, arg_start),
+		offsetof(struct prctl_mm_map, arg_end),
+		offsetof(struct prctl_mm_map, env_start),
+		offsetof(struct prctl_mm_map, env_end),
+	};
+
+	/*
+	 * Make sure the members are not somewhere outside
+	 * of allowed address space.
+	 */
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		u64 val = *(u64 *)((char *)prctl_map + offsets[i]);
+
+		if ((unsigned long)val >= mmap_max_addr ||
+		    (unsigned long)val < mmap_min_addr)
+			goto out;
+	}
+
+	/*
+	 * Make sure the pairs are ordered.
+	 */
+#define __prctl_check_order(__m1, __op, __m2)				\
+	((unsigned long)prctl_map->__m1 __op				\
+	 (unsigned long)prctl_map->__m2) ? 0 : -EINVAL
+	error  = __prctl_check_order(start_code, <, end_code);
+	error |= __prctl_check_order(start_data, <, end_data);
+	error |= __prctl_check_order(start_brk, <=, brk);
+	error |= __prctl_check_order(arg_start, <=, arg_end);
+	error |= __prctl_check_order(env_start, <=, env_end);
+	if (error)
+		goto out;
+#undef __prctl_check_order
+
+	error = -EINVAL;
+
+	/*
+	 * @brk should be after @end_data in traditional maps.
+	 */
+	if (prctl_map->start_brk <= prctl_map->end_data ||
+	    prctl_map->brk <= prctl_map->end_data)
+		goto out;
+
+	/*
+	 * Neither we should allow to override limits if they set.
+	 */
+	if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk,
+			      prctl_map->start_brk, prctl_map->end_data,
+			      prctl_map->start_data))
+			goto out;
+
+	/*
+	 * Someone is trying to cheat the auxv vector.
+	 */
+	if (prctl_map->auxv_size) {
+		if (!prctl_map->auxv || prctl_map->auxv_size > sizeof(mm->saved_auxv))
+			goto out;
+	}
+
+	/*
+	 * Finally, make sure the caller has the rights to
+	 * change /proc/pid/exe link: only local root should
+	 * be allowed to.
+	 */
+	if (prctl_map->exe_fd != (u32)-1) {
+		struct user_namespace *ns = current_user_ns();
+		const struct cred *cred = current_cred();
+
+		if (!uid_eq(cred->uid, make_kuid(ns, 0)) ||
+		    !gid_eq(cred->gid, make_kgid(ns, 0)))
+			goto out;
+	}
+
+	error = 0;
+out:
+	return error;
+}
+
+static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size)
+{
+	struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, };
+	unsigned long user_auxv[AT_VECTOR_SIZE];
+	struct mm_struct *mm = current->mm;
+	int error;
+
+	BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
+	BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256);
+
+	if (opt == PR_SET_MM_MAP_SIZE)
+		return put_user((unsigned int)sizeof(prctl_map),
+				(unsigned int __user *)addr);
+
+	if (data_size != sizeof(prctl_map))
+		return -EINVAL;
+
+	if (copy_from_user(&prctl_map, addr, sizeof(prctl_map)))
+		return -EFAULT;
+
+	error = validate_prctl_map(&prctl_map);
+	if (error)
+		return error;
+
+	if (prctl_map.auxv_size) {
+		memset(user_auxv, 0, sizeof(user_auxv));
+		if (copy_from_user(user_auxv,
+				   (const void __user *)prctl_map.auxv,
+				   prctl_map.auxv_size))
+			return -EFAULT;
+
+		/* Last entry must be AT_NULL as specification requires */
+		user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL;
+		user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL;
+	}
+
+	down_write(&mm->mmap_sem);
+	if (prctl_map.exe_fd != (u32)-1)
+		error = prctl_set_mm_exe_file_locked(mm, prctl_map.exe_fd);
+	downgrade_write(&mm->mmap_sem);
+	if (error)
+		goto out;
+
+	/*
+	 * We don't validate if these members are pointing to
+	 * real present VMAs because application may have correspond
+	 * VMAs already unmapped and kernel uses these members for statistics
+	 * output in procfs mostly, except
+	 *
+	 *  - @start_brk/@brk which are used in do_brk but kernel lookups
+	 *    for VMAs when updating these memvers so anything wrong written
+	 *    here cause kernel to swear at userspace program but won't lead
+	 *    to any problem in kernel itself
+	 */
+
+	mm->start_code	= prctl_map.start_code;
+	mm->end_code	= prctl_map.end_code;
+	mm->start_data	= prctl_map.start_data;
+	mm->end_data	= prctl_map.end_data;
+	mm->start_brk	= prctl_map.start_brk;
+	mm->brk		= prctl_map.brk;
+	mm->start_stack	= prctl_map.start_stack;
+	mm->arg_start	= prctl_map.arg_start;
+	mm->arg_end	= prctl_map.arg_end;
+	mm->env_start	= prctl_map.env_start;
+	mm->env_end	= prctl_map.env_end;
+
+	/*
+	 * Note this update of @saved_auxv is lockless thus
+	 * if someone reads this member in procfs while we're
+	 * updating -- it may get partly updated results. It's
+	 * known and acceptable trade off: we leave it as is to
+	 * not introduce additional locks here making the kernel
+	 * more complex.
+	 */
+	if (prctl_map.auxv_size)
+		memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv));
+
+	error = 0;
+out:
+	up_read(&mm->mmap_sem);
+	return error;
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
 static int prctl_set_mm(int opt, unsigned long addr,
 			unsigned long arg4, unsigned long arg5)
 {
@@ -1694,9 +1875,16 @@ static int prctl_set_mm(int opt, unsigned long addr,
 	struct vm_area_struct *vma;
 	int error;
 
-	if (arg5 || (arg4 && opt != PR_SET_MM_AUXV))
+	if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV &&
+			      opt != PR_SET_MM_MAP &&
+			      opt != PR_SET_MM_MAP_SIZE)))
 		return -EINVAL;
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE)
+		return prctl_set_mm_map(opt, (const void __user *)addr, arg4);
+#endif
+
 	if (!capable(CAP_SYS_RESOURCE))
 		return -EPERM;
 
-- 
cgit v1.2.3


From 1f13ae399c58af5a05b5cee61da864e1f4071de4 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 9 Oct 2014 15:27:39 -0700
Subject: mm: remove noisy remainder of the scan_unevictable interface

The deprecation warnings for the scan_unevictable interface triggers by
scripts doing `sysctl -a | grep something else'.  This is annoying and not
helpful.

The interface has been defunct since 264e56d8247e ("mm: disable user
interface to manually rescue unevictable pages"), which was in 2011, and
there haven't been any reports of usecases for it, only reports that the
deprecation warnings are annying.  It's unlikely that anybody is using
this interface specifically at this point, so remove it.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/ABI/stable/sysfs-devices-node |  8 ----
 drivers/base/node.c                         |  3 --
 include/linux/swap.h                        | 16 --------
 kernel/sysctl.c                             |  7 ----
 mm/vmscan.c                                 | 63 -----------------------------
 5 files changed, 97 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
index ce259c13c36a..5b2d0f08867c 100644
--- a/Documentation/ABI/stable/sysfs-devices-node
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -85,14 +85,6 @@ Description:
 		will be compacted. When it completes, memory will be freed
 		into blocks which have as many contiguous pages as possible
 
-What:		/sys/devices/system/node/nodeX/scan_unevictable_pages
-Date:		October 2008
-Contact:	Lee Schermerhorn <lee.schermerhorn@hp.com>
-Description:
-		When set, it triggers scanning the node's unevictable lists
-		and move any pages that have become evictable onto the respective
-		zone's inactive list. See mm/vmscan.c
-
 What:		/sys/devices/system/node/nodeX/hugepages/hugepages-<size>/
 Date:		December 2009
 Contact:	Lee Schermerhorn <lee.schermerhorn@hp.com>
diff --git a/drivers/base/node.c b/drivers/base/node.c
index d51c49c9bafa..472168cd0c97 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -289,8 +289,6 @@ static int register_node(struct node *node, int num, struct node *parent)
 		device_create_file(&node->dev, &dev_attr_distance);
 		device_create_file(&node->dev, &dev_attr_vmstat);
 
-		scan_unevictable_register_node(node);
-
 		hugetlb_register_node(node);
 
 		compaction_register_node(node);
@@ -314,7 +312,6 @@ void unregister_node(struct node *node)
 	device_remove_file(&node->dev, &dev_attr_distance);
 	device_remove_file(&node->dev, &dev_attr_vmstat);
 
-	scan_unevictable_unregister_node(node);
 	hugetlb_unregister_node(node);		/* no-op, if memoryless node */
 
 	device_unregister(&node->dev);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 1b72060f093a..ea4f926e6b9b 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -354,22 +354,6 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 extern int page_evictable(struct page *page);
 extern void check_move_unevictable_pages(struct page **, int nr_pages);
 
-extern unsigned long scan_unevictable_pages;
-extern int scan_unevictable_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-#ifdef CONFIG_NUMA
-extern int scan_unevictable_register_node(struct node *node);
-extern void scan_unevictable_unregister_node(struct node *node);
-#else
-static inline int scan_unevictable_register_node(struct node *node)
-{
-	return 0;
-}
-static inline void scan_unevictable_unregister_node(struct node *node)
-{
-}
-#endif
-
 extern int kswapd_run(int nid);
 extern void kswapd_stop(int nid);
 #ifdef CONFIG_MEMCG
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 75875a741b5e..91180987e40e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1460,13 +1460,6 @@ static struct ctl_table vm_table[] = {
 		.extra2		= &one,
 	},
 #endif
-	{
-		.procname	= "scan_unevictable_pages",
-		.data		= &scan_unevictable_pages,
-		.maxlen		= sizeof(scan_unevictable_pages),
-		.mode		= 0644,
-		.proc_handler	= scan_unevictable_handler,
-	},
 #ifdef CONFIG_MEMORY_FAILURE
 	{
 		.procname	= "memory_failure_early_kill",
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1a71b8b1ea34..af72fe8e8d74 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3797,66 +3797,3 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages)
 	}
 }
 #endif /* CONFIG_SHMEM */
-
-static void warn_scan_unevictable_pages(void)
-{
-	printk_once(KERN_WARNING
-		    "%s: The scan_unevictable_pages sysctl/node-interface has been "
-		    "disabled for lack of a legitimate use case.  If you have "
-		    "one, please send an email to linux-mm@kvack.org.\n",
-		    current->comm);
-}
-
-/*
- * scan_unevictable_pages [vm] sysctl handler.  On demand re-scan of
- * all nodes' unevictable lists for evictable pages
- */
-unsigned long scan_unevictable_pages;
-
-int scan_unevictable_handler(struct ctl_table *table, int write,
-			   void __user *buffer,
-			   size_t *length, loff_t *ppos)
-{
-	warn_scan_unevictable_pages();
-	proc_doulongvec_minmax(table, write, buffer, length, ppos);
-	scan_unevictable_pages = 0;
-	return 0;
-}
-
-#ifdef CONFIG_NUMA
-/*
- * per node 'scan_unevictable_pages' attribute.  On demand re-scan of
- * a specified node's per zone unevictable lists for evictable pages.
- */
-
-static ssize_t read_scan_unevictable_node(struct device *dev,
-					  struct device_attribute *attr,
-					  char *buf)
-{
-	warn_scan_unevictable_pages();
-	return sprintf(buf, "0\n");	/* always zero; should fit... */
-}
-
-static ssize_t write_scan_unevictable_node(struct device *dev,
-					   struct device_attribute *attr,
-					const char *buf, size_t count)
-{
-	warn_scan_unevictable_pages();
-	return 1;
-}
-
-
-static DEVICE_ATTR(scan_unevictable_pages, S_IRUGO | S_IWUSR,
-			read_scan_unevictable_node,
-			write_scan_unevictable_node);
-
-int scan_unevictable_register_node(struct node *node)
-{
-	return device_create_file(&node->dev, &dev_attr_scan_unevictable_pages);
-}
-
-void scan_unevictable_unregister_node(struct node *node)
-{
-	device_remove_file(&node->dev, &dev_attr_scan_unevictable_pages);
-}
-#endif
-- 
cgit v1.2.3


From 6b6482bbf64ef6f6dbc8b52f7a7cf88a0498bd51 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Thu, 9 Oct 2014 15:27:48 -0700
Subject: mempolicy: remove the "task" arg of vma_policy_mof() and simplify it

1. vma_policy_mof(task) is simply not safe unless task == current,
   it can race with do_exit()->mpol_put(). Remove this arg and update
   its single caller.

2. vma can not be NULL, remove this check and simplify the code.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h |  2 +-
 kernel/sched/fair.c       |  2 +-
 mm/mempolicy.c            | 25 +++++++++++--------------
 3 files changed, 13 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index f230a978e6ba..5e4bfcedd2ce 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -136,7 +136,7 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 
 struct mempolicy *get_vma_policy(struct task_struct *tsk,
 		struct vm_area_struct *vma, unsigned long addr);
-bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma);
+bool vma_policy_mof(struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
 extern void numa_policy_init(void);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bfa3c86d0d68..82088b29704e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1946,7 +1946,7 @@ void task_numa_work(struct callback_head *work)
 		vma = mm->mmap;
 	}
 	for (; vma; vma = vma->vm_next) {
-		if (!vma_migratable(vma) || !vma_policy_mof(p, vma))
+		if (!vma_migratable(vma) || !vma_policy_mof(vma))
 			continue;
 
 		/*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b86b08e77b8d..ad27bbc757bf 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1646,27 +1646,24 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 	return pol;
 }
 
-bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma)
+bool vma_policy_mof(struct vm_area_struct *vma)
 {
-	struct mempolicy *pol = NULL;
-
-	if (vma) {
-		if (vma->vm_ops && vma->vm_ops->get_policy) {
-			bool ret = false;
+	struct mempolicy *pol;
 
-			pol = vma->vm_ops->get_policy(vma, vma->vm_start);
-			if (pol && (pol->flags & MPOL_F_MOF))
-				ret = true;
-			mpol_cond_put(pol);
+	if (vma->vm_ops && vma->vm_ops->get_policy) {
+		bool ret = false;
 
-			return ret;
-		}
+		pol = vma->vm_ops->get_policy(vma, vma->vm_start);
+		if (pol && (pol->flags & MPOL_F_MOF))
+			ret = true;
+		mpol_cond_put(pol);
 
-		pol = vma->vm_policy;
+		return ret;
 	}
 
+	pol = vma->vm_policy;
 	if (!pol)
-		pol = get_task_policy(task);
+		pol = get_task_policy(current);
 
 	return pol->flags & MPOL_F_MOF;
 }
-- 
cgit v1.2.3


From 74d2c3a05cc6c1eef2d7236a9919036ed85ddaaf Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Thu, 9 Oct 2014 15:27:50 -0700
Subject: mempolicy: introduce __get_vma_policy(), export get_task_policy()

Extract the code which looks for vma's policy from get_vma_policy()
into the new helper, __get_vma_policy(). Export get_task_policy().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h |  3 +++
 mm/mempolicy.c            | 44 ++++++++++++++++++++++++++------------------
 2 files changed, 29 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5e4bfcedd2ce..e1abe249892a 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -134,6 +134,9 @@ void mpol_free_shared_policy(struct shared_policy *p);
 struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 					    unsigned long idx);
 
+struct mempolicy *get_task_policy(struct task_struct *p);
+struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
+		unsigned long addr);
 struct mempolicy *get_vma_policy(struct task_struct *tsk,
 		struct vm_area_struct *vma, unsigned long addr);
 bool vma_policy_mof(struct vm_area_struct *vma);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ad27bbc757bf..4378c334e89b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -123,7 +123,7 @@ static struct mempolicy default_policy = {
 
 static struct mempolicy preferred_node_policy[MAX_NUMNODES];
 
-static struct mempolicy *get_task_policy(struct task_struct *p)
+struct mempolicy *get_task_policy(struct task_struct *p)
 {
 	struct mempolicy *pol = p->mempolicy;
 	int node;
@@ -1603,23 +1603,8 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 
 #endif
 
-/*
- * get_vma_policy(@task, @vma, @addr)
- * @task: task for fallback if vma policy == default
- * @vma: virtual memory area whose policy is sought
- * @addr: address in @vma for shared policy lookup
- *
- * Returns effective policy for a VMA at specified address.
- * Falls back to @task or system default policy, as necessary.
- * Current or other task's task mempolicy and non-shared vma policies must be
- * protected by task_lock(task) by the caller.
- * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
- * count--added by the get_policy() vm_op, as appropriate--to protect against
- * freeing by another task.  It is the caller's responsibility to free the
- * extra reference for shared policies.
- */
-struct mempolicy *get_vma_policy(struct task_struct *task,
-		struct vm_area_struct *vma, unsigned long addr)
+struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
+						unsigned long addr)
 {
 	struct mempolicy *pol = NULL;
 
@@ -1640,6 +1625,29 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 		}
 	}
 
+	return pol;
+}
+
+/*
+ * get_vma_policy(@task, @vma, @addr)
+ * @task: task for fallback if vma policy == default
+ * @vma: virtual memory area whose policy is sought
+ * @addr: address in @vma for shared policy lookup
+ *
+ * Returns effective policy for a VMA at specified address.
+ * Falls back to @task or system default policy, as necessary.
+ * Current or other task's task mempolicy and non-shared vma policies must be
+ * protected by task_lock(task) by the caller.
+ * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
+ * count--added by the get_policy() vm_op, as appropriate--to protect against
+ * freeing by another task.  It is the caller's responsibility to free the
+ * extra reference for shared policies.
+ */
+struct mempolicy *get_vma_policy(struct task_struct *task,
+		struct vm_area_struct *vma, unsigned long addr)
+{
+	struct mempolicy *pol = __get_vma_policy(vma, addr);
+
 	if (!pol)
 		pol = get_task_policy(task);
 
-- 
cgit v1.2.3


From dd6eecb917938c1b7e505a83df307b3476e7c8bd Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Thu, 9 Oct 2014 15:27:57 -0700
Subject: mempolicy: unexport get_vma_policy() and remove its "task" arg

- get_vma_policy(task) is not safe if task != current, remove this
  argument.

- get_vma_policy() no longer has callers outside of mempolicy.c,
  make it static.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h |  2 --
 mm/mempolicy.c            | 19 ++++++++-----------
 2 files changed, 8 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index e1abe249892a..3d385c81c153 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -137,8 +137,6 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 struct mempolicy *get_task_policy(struct task_struct *p);
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
 		unsigned long addr);
-struct mempolicy *get_vma_policy(struct task_struct *tsk,
-		struct vm_area_struct *vma, unsigned long addr);
 bool vma_policy_mof(struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 9695a9a3ab90..008fb32936eb 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1616,27 +1616,24 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
 }
 
 /*
- * get_vma_policy(@task, @vma, @addr)
- * @task: task for fallback if vma policy == default
+ * get_vma_policy(@vma, @addr)
  * @vma: virtual memory area whose policy is sought
  * @addr: address in @vma for shared policy lookup
  *
  * Returns effective policy for a VMA at specified address.
- * Falls back to @task or system default policy, as necessary.
- * Current or other task's task mempolicy and non-shared vma policies must be
- * protected by task_lock(task) by the caller.
+ * Falls back to current->mempolicy or system default policy, as necessary.
  * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
  * count--added by the get_policy() vm_op, as appropriate--to protect against
  * freeing by another task.  It is the caller's responsibility to free the
  * extra reference for shared policies.
  */
-struct mempolicy *get_vma_policy(struct task_struct *task,
-		struct vm_area_struct *vma, unsigned long addr)
+static struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+						unsigned long addr)
 {
 	struct mempolicy *pol = __get_vma_policy(vma, addr);
 
 	if (!pol)
-		pol = get_task_policy(task);
+		pol = get_task_policy(current);
 
 	return pol;
 }
@@ -1864,7 +1861,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
 {
 	struct zonelist *zl;
 
-	*mpol = get_vma_policy(current, vma, addr);
+	*mpol = get_vma_policy(vma, addr);
 	*nodemask = NULL;	/* assume !MPOL_BIND */
 
 	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
@@ -2019,7 +2016,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 	unsigned int cpuset_mems_cookie;
 
 retry_cpuset:
-	pol = get_vma_policy(current, vma, addr);
+	pol = get_vma_policy(vma, addr);
 	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
@@ -2285,7 +2282,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 
 	BUG_ON(!vma);
 
-	pol = get_vma_policy(current, vma, addr);
+	pol = get_vma_policy(vma, addr);
 	if (!(pol->flags & MPOL_F_MOF))
 		goto out;
 
-- 
cgit v1.2.3


From 1c93923cc264105418e6ead149c76bd88302eff4 Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Thu, 9 Oct 2014 15:27:59 -0700
Subject: include/linux/migrate.h: remove migrate_page #define

This is designed to avoid a few ifdefs in .c files but it's obnoxious
because it can cause unsuspecting "migrate_page" symbols to get turned into
"NULL".

Just nuke it and use the ifdefs.

Cc: Konstantin Khlebnikov <k.khlebnikov@samsung.com>
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/migrate.h | 3 ---
 mm/shmem.c              | 2 ++
 mm/swap_state.c         | 2 ++
 3 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index a2901c414664..b66fd10f4b93 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -82,9 +82,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 	return -ENOSYS;
 }
 
-/* Possible settings for the migrate_page() method in address_operations */
-#define migrate_page NULL
-
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/mm/shmem.c b/mm/shmem.c
index 469f90d56051..4fad61bb41e5 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3077,7 +3077,9 @@ static const struct address_space_operations shmem_aops = {
 	.write_begin	= shmem_write_begin,
 	.write_end	= shmem_write_end,
 #endif
+#ifdef CONFIG_MIGRATION
 	.migratepage	= migrate_page,
+#endif
 	.error_remove_page = generic_error_remove_page,
 };
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3e0ec83d000c..ef1f39139b71 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -28,7 +28,9 @@
 static const struct address_space_operations swap_aops = {
 	.writepage	= swap_writepage,
 	.set_page_dirty	= swap_set_page_dirty,
+#ifdef CONFIG_MIGRATION
 	.migratepage	= migrate_page,
+#endif
 };
 
 static struct backing_dev_info swap_backing_dev_info = {
-- 
cgit v1.2.3


From 0bf55139782db1fa96af66e37cc84afde18443ef Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 9 Oct 2014 15:28:06 -0700
Subject: mm: introduce dump_vma

Introduce a helper to dump information about a VMA, this also makes
dump_page_flags more generic and re-uses that so the output looks very
similar to dump_page:

[   61.903437] vma ffff88070f88be00 start 00007fff25970000 end 00007fff25992000
[   61.903437] next ffff88070facd600 prev ffff88070face400 mm ffff88070fade000
[   61.903437] prot 8000000000000025 anon_vma ffff88070fa1e200 vm_ops           (null)
[   61.903437] pgoff 7ffffffdd file           (null) private_data           (null)
[   61.909129] flags: 0x100173(read|write|mayread|maywrite|mayexec|growsdown|account)

[akpm@linux-foundation.org: make dump_vma() require CONFIG_DEBUG_VM]
[swarren@nvidia.com: fix dump_vma() compilation]
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michel Lespinasse <walken@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmdebug.h |  2 ++
 mm/page_alloc.c         | 82 +++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 75 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 2f348d02f640..dfb93333fc62 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -4,10 +4,12 @@
 #include <linux/stringify.h>
 
 struct page;
+struct vm_area_struct;
 
 extern void dump_page(struct page *page, const char *reason);
 extern void dump_page_badflags(struct page *page, const char *reason,
 			       unsigned long badflags);
+void dump_vma(const struct vm_area_struct *vma);
 
 #ifdef CONFIG_DEBUG_VM
 #define VM_BUG_ON(cond) BUG_ON(cond)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f07588b11d59..3a950144f80b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6626,27 +6626,26 @@ static const struct trace_print_flags pageflag_names[] = {
 #endif
 };
 
-static void dump_page_flags(unsigned long flags)
+static void dump_flags(unsigned long flags,
+			const struct trace_print_flags *names, int count)
 {
 	const char *delim = "";
 	unsigned long mask;
 	int i;
 
-	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
-
-	printk(KERN_ALERT "page flags: %#lx(", flags);
+	printk(KERN_ALERT "flags: %#lx(", flags);
 
 	/* remove zone id */
 	flags &= (1UL << NR_PAGEFLAGS) - 1;
 
-	for (i = 0; i < ARRAY_SIZE(pageflag_names) && flags; i++) {
+	for (i = 0; i < count && flags; i++) {
 
-		mask = pageflag_names[i].mask;
+		mask = names[i].mask;
 		if ((flags & mask) != mask)
 			continue;
 
 		flags &= ~mask;
-		printk("%s%s", delim, pageflag_names[i].name);
+		printk("%s%s", delim, names[i].name);
 		delim = "|";
 	}
 
@@ -6664,12 +6663,14 @@ void dump_page_badflags(struct page *page, const char *reason,
 	       "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
 		page, atomic_read(&page->_count), page_mapcount(page),
 		page->mapping, page->index);
-	dump_page_flags(page->flags);
+	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
+	dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names));
 	if (reason)
 		pr_alert("page dumped because: %s\n", reason);
 	if (page->flags & badflags) {
 		pr_alert("bad because of flags:\n");
-		dump_page_flags(page->flags & badflags);
+		dump_flags(page->flags & badflags,
+				pageflag_names, ARRAY_SIZE(pageflag_names));
 	}
 	mem_cgroup_print_bad_page(page);
 }
@@ -6679,3 +6680,66 @@ void dump_page(struct page *page, const char *reason)
 	dump_page_badflags(page, reason, 0);
 }
 EXPORT_SYMBOL(dump_page);
+
+#ifdef CONFIG_DEBUG_VM
+
+static const struct trace_print_flags vmaflags_names[] = {
+	{VM_READ,			"read"		},
+	{VM_WRITE,			"write"		},
+	{VM_EXEC,			"exec"		},
+	{VM_SHARED,			"shared"	},
+	{VM_MAYREAD,			"mayread"	},
+	{VM_MAYWRITE,			"maywrite"	},
+	{VM_MAYEXEC,			"mayexec"	},
+	{VM_MAYSHARE,			"mayshare"	},
+	{VM_GROWSDOWN,			"growsdown"	},
+	{VM_PFNMAP,			"pfnmap"	},
+	{VM_DENYWRITE,			"denywrite"	},
+	{VM_LOCKED,			"locked"	},
+	{VM_IO,				"io"		},
+	{VM_SEQ_READ,			"seqread"	},
+	{VM_RAND_READ,			"randread"	},
+	{VM_DONTCOPY,			"dontcopy"	},
+	{VM_DONTEXPAND,			"dontexpand"	},
+	{VM_ACCOUNT,			"account"	},
+	{VM_NORESERVE,			"noreserve"	},
+	{VM_HUGETLB,			"hugetlb"	},
+	{VM_NONLINEAR,			"nonlinear"	},
+#if defined(CONFIG_X86)
+	{VM_PAT,			"pat"		},
+#elif defined(CONFIG_PPC)
+	{VM_SAO,			"sao"		},
+#elif defined(CONFIG_PARISC) || defined(CONFIG_METAG) || defined(CONFIG_IA64)
+	{VM_GROWSUP,			"growsup"	},
+#elif !defined(CONFIG_MMU)
+	{VM_MAPPED_COPY,		"mappedcopy"	},
+#else
+	{VM_ARCH_1,			"arch_1"	},
+#endif
+	{VM_DONTDUMP,			"dontdump"	},
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	{VM_SOFTDIRTY,			"softdirty"	},
+#endif
+	{VM_MIXEDMAP,			"mixedmap"	},
+	{VM_HUGEPAGE,			"hugepage"	},
+	{VM_NOHUGEPAGE,			"nohugepage"	},
+	{VM_MERGEABLE,			"mergeable"	},
+};
+
+void dump_vma(const struct vm_area_struct *vma)
+{
+	printk(KERN_ALERT
+		"vma %p start %p end %p\n"
+		"next %p prev %p mm %p\n"
+		"prot %lx anon_vma %p vm_ops %p\n"
+		"pgoff %lx file %p private_data %p\n",
+		vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
+		vma->vm_prev, vma->vm_mm,
+		(unsigned long)pgprot_val(vma->vm_page_prot),
+		vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
+		vma->vm_file, vma->vm_private_data);
+	dump_flags(vma->vm_flags, vmaflags_names, ARRAY_SIZE(vmaflags_names));
+}
+EXPORT_SYMBOL(dump_vma);
+
+#endif		/* CONFIG_DEBUG_VM */
-- 
cgit v1.2.3


From fa3759ccd5651c4235f572302d58c8ec9ddf1c4b Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 9 Oct 2014 15:28:08 -0700
Subject: mm: introduce VM_BUG_ON_VMA

Very similar to VM_BUG_ON_PAGE but dumps VMA information instead.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michel Lespinasse <walken@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmdebug.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index dfb93333fc62..569e4c8d0ebb 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -20,12 +20,20 @@ void dump_vma(const struct vm_area_struct *vma);
 			BUG();						\
 		}							\
 	} while (0)
+#define VM_BUG_ON_VMA(cond, vma)					\
+	do {								\
+		if (unlikely(cond)) {					\
+			dump_vma(vma);					\
+			BUG();						\
+		}							\
+	} while (0)
 #define VM_WARN_ON(cond) WARN_ON(cond)
 #define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond)
 #define VM_WARN_ONCE(cond, format...) WARN_ONCE(cond, format)
 #else
 #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond)
+#define VM_BUG_ON_VMA(cond, vma) VM_BUG_ON(cond)
 #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
-- 
cgit v1.2.3


From 81d1b09c6be66afac7d41ee52279d9bccbce56d8 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 9 Oct 2014 15:28:10 -0700
Subject: mm: convert a few VM_BUG_ON callers to VM_BUG_ON_VMA

Trivially convert a few VM_BUG_ON calls to VM_BUG_ON_VMA to extract
more information when they trigger.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michel Lespinasse <walken@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h |  2 +-
 include/linux/rmap.h    |  2 +-
 mm/huge_memory.c        |  6 +++---
 mm/hugetlb.c            | 14 +++++++-------
 mm/interval_tree.c      |  2 +-
 mm/mlock.c              |  4 ++--
 mm/mmap.c               |  6 +++---
 mm/mremap.c             |  3 ++-
 mm/rmap.c               |  8 ++++----
 9 files changed, 24 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 63579cb8d3dc..ad9051bab267 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -132,7 +132,7 @@ extern int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 		spinlock_t **ptl)
 {
-	VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
+	VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
 	if (pmd_trans_huge(*pmd))
 		return __pmd_trans_huge_lock(pmd, vma, ptl);
 	else
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index be574506e6a9..c0c2bce6b0b7 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -150,7 +150,7 @@ int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
 static inline void anon_vma_merge(struct vm_area_struct *vma,
 				  struct vm_area_struct *next)
 {
-	VM_BUG_ON(vma->anon_vma != next->anon_vma);
+	VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma);
 	unlink_anon_vmas(next);
 }
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 55ab569c31b4..c13148cc745f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1096,7 +1096,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
 	ptl = pmd_lockptr(mm, pmd);
-	VM_BUG_ON(!vma->anon_vma);
+	VM_BUG_ON_VMA(!vma->anon_vma, vma);
 	haddr = address & HPAGE_PMD_MASK;
 	if (is_huge_zero_pmd(orig_pmd))
 		goto alloc;
@@ -2083,7 +2083,7 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
 	if (vma->vm_ops)
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
-	VM_BUG_ON(vma->vm_flags & VM_NO_THP);
+	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
@@ -2406,7 +2406,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma)
 		return false;
 	if (is_vma_temporary_stack(vma))
 		return false;
-	VM_BUG_ON(vma->vm_flags & VM_NO_THP);
+	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
 	return true;
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index eeceeeb09019..9fd722769927 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -434,7 +434,7 @@ static inline struct resv_map *inode_resv_map(struct inode *inode)
 
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
 	if (vma->vm_flags & VM_MAYSHARE) {
 		struct address_space *mapping = vma->vm_file->f_mapping;
 		struct inode *inode = mapping->host;
@@ -449,8 +449,8 @@ static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 
 static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
-	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
+	VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);
 
 	set_vma_private_data(vma, (get_vma_private_data(vma) &
 				HPAGE_RESV_MASK) | (unsigned long)map);
@@ -458,15 +458,15 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
 
 static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
-	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
+	VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);
 
 	set_vma_private_data(vma, get_vma_private_data(vma) | flags);
 }
 
 static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
 
 	return (get_vma_private_data(vma) & flag) != 0;
 }
@@ -474,7 +474,7 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 /* Reset counters to 0 and clear all HPAGE_RESV_* flags */
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
 	if (!(vma->vm_flags & VM_MAYSHARE))
 		vma->vm_private_data = (void *)0;
 }
diff --git a/mm/interval_tree.c b/mm/interval_tree.c
index 4a5822a586e6..8da581fa9060 100644
--- a/mm/interval_tree.c
+++ b/mm/interval_tree.c
@@ -34,7 +34,7 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node,
 	struct vm_area_struct *parent;
 	unsigned long last = vma_last_pgoff(node);
 
-	VM_BUG_ON(vma_start_pgoff(node) != vma_start_pgoff(prev));
+	VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node);
 
 	if (!prev->shared.linear.rb.rb_right) {
 		parent = prev;
diff --git a/mm/mlock.c b/mm/mlock.c
index ce84cb0b83ef..d5d09d0786ec 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -233,8 +233,8 @@ long __mlock_vma_pages_range(struct vm_area_struct *vma,
 
 	VM_BUG_ON(start & ~PAGE_MASK);
 	VM_BUG_ON(end   & ~PAGE_MASK);
-	VM_BUG_ON(start < vma->vm_start);
-	VM_BUG_ON(end   > vma->vm_end);
+	VM_BUG_ON_VMA(start < vma->vm_start, vma);
+	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
 	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
 	gup_flags = FOLL_TOUCH | FOLL_MLOCK;
diff --git a/mm/mmap.c b/mm/mmap.c
index 7ff38f1a66ec..69d4c5199fd8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -786,8 +786,8 @@ again:			remove_next = 1 + (end > next->vm_end);
 	if (!anon_vma && adjust_next)
 		anon_vma = next->anon_vma;
 	if (anon_vma) {
-		VM_BUG_ON(adjust_next && next->anon_vma &&
-			  anon_vma != next->anon_vma);
+		VM_BUG_ON_VMA(adjust_next && next->anon_vma &&
+			  anon_vma != next->anon_vma, next);
 		anon_vma_lock_write(anon_vma);
 		anon_vma_interval_tree_pre_update_vma(vma);
 		if (adjust_next)
@@ -2848,7 +2848,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 			 * safe. It is only safe to keep the vm_pgoff
 			 * linear if there are no pages mapped yet.
 			 */
-			VM_BUG_ON(faulted_in_anon_vma);
+			VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma);
 			*vmap = vma = new_vma;
 		}
 		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
diff --git a/mm/mremap.c b/mm/mremap.c
index 05f1180e9f21..89e45d8a983a 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -195,7 +195,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		if (pmd_trans_huge(*old_pmd)) {
 			int err = 0;
 			if (extent == HPAGE_PMD_SIZE) {
-				VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+				VM_BUG_ON_VMA(vma->vm_file || !vma->anon_vma,
+					      vma);
 				/* See comment in move_ptes() */
 				if (need_rmap_locks)
 					anon_vma_lock_write(vma->anon_vma);
diff --git a/mm/rmap.c b/mm/rmap.c
index bc74e0012809..116a5053415b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -527,7 +527,7 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 	unsigned long address = __vma_address(page, vma);
 
 	/* page should be within @vma mapping range */
-	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
 
 	return address;
 }
@@ -897,7 +897,7 @@ void page_move_anon_rmap(struct page *page,
 	struct anon_vma *anon_vma = vma->anon_vma;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON(!anon_vma);
+	VM_BUG_ON_VMA(!anon_vma, vma);
 	VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page);
 
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
@@ -1024,7 +1024,7 @@ void do_page_add_anon_rmap(struct page *page,
 void page_add_new_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address)
 {
-	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
 	SetPageSwapBacked(page);
 	atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
 	if (PageTransHuge(page))
@@ -1670,7 +1670,7 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 	 * structure at mapping cannot be freed and reused yet,
 	 * so we can safely take mapping->i_mmap_mutex.
 	 */
-	VM_BUG_ON(!PageLocked(page));
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	if (!mapping)
 		return ret;
-- 
cgit v1.2.3


From 5705465174686d007473e017b76c4b64b44aa690 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 9 Oct 2014 15:28:17 -0700
Subject: mm: clean up zone flags

Page reclaim tests zone_is_reclaim_dirty(), but the site that actually
sets this state does zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY), sending the
reader through layers indirection just to track down a simple bit.

Remove all zone flag wrappers and just use bitops against zone->flags
directly.  It's just as readable and the lines are barely any longer.

Also rename ZONE_TAIL_LRU_DIRTY to ZONE_DIRTY to match ZONE_WRITEBACK, and
remove the zone_flags_t typedef.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 51 +++-----------------------------------------------
 mm/backing-dev.c       |  2 +-
 mm/oom_kill.c          |  6 +++---
 mm/page_alloc.c        |  8 ++++----
 mm/vmscan.c            | 28 +++++++++++++--------------
 5 files changed, 25 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 318df7051850..48bf12ef6620 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -521,13 +521,13 @@ struct zone {
 	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
 } ____cacheline_internodealigned_in_smp;
 
-typedef enum {
+enum zone_flags {
 	ZONE_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
 	ZONE_OOM_LOCKED,		/* zone is in OOM killer zonelist */
 	ZONE_CONGESTED,			/* zone has many dirty pages backed by
 					 * a congested BDI
 					 */
-	ZONE_TAIL_LRU_DIRTY,		/* reclaim scanning has recently found
+	ZONE_DIRTY,			/* reclaim scanning has recently found
 					 * many dirty file pages at the tail
 					 * of the LRU.
 					 */
@@ -535,52 +535,7 @@ typedef enum {
 					 * many pages under writeback
 					 */
 	ZONE_FAIR_DEPLETED,		/* fair zone policy batch depleted */
-} zone_flags_t;
-
-static inline void zone_set_flag(struct zone *zone, zone_flags_t flag)
-{
-	set_bit(flag, &zone->flags);
-}
-
-static inline int zone_test_and_set_flag(struct zone *zone, zone_flags_t flag)
-{
-	return test_and_set_bit(flag, &zone->flags);
-}
-
-static inline void zone_clear_flag(struct zone *zone, zone_flags_t flag)
-{
-	clear_bit(flag, &zone->flags);
-}
-
-static inline int zone_is_reclaim_congested(const struct zone *zone)
-{
-	return test_bit(ZONE_CONGESTED, &zone->flags);
-}
-
-static inline int zone_is_reclaim_dirty(const struct zone *zone)
-{
-	return test_bit(ZONE_TAIL_LRU_DIRTY, &zone->flags);
-}
-
-static inline int zone_is_reclaim_writeback(const struct zone *zone)
-{
-	return test_bit(ZONE_WRITEBACK, &zone->flags);
-}
-
-static inline int zone_is_reclaim_locked(const struct zone *zone)
-{
-	return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
-}
-
-static inline int zone_is_fair_depleted(const struct zone *zone)
-{
-	return test_bit(ZONE_FAIR_DEPLETED, &zone->flags);
-}
-
-static inline int zone_is_oom_locked(const struct zone *zone)
-{
-	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
-}
+};
 
 static inline unsigned long zone_end_pfn(const struct zone *zone)
 {
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1706cbbdf5f0..b27714f1b40f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -631,7 +631,7 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
 	 * of sleeping on the congestion queue
 	 */
 	if (atomic_read(&nr_bdi_congested[sync]) == 0 ||
-			!zone_is_reclaim_congested(zone)) {
+	    !test_bit(ZONE_CONGESTED, &zone->flags)) {
 		cond_resched();
 
 		/* In case we scheduled, work out time remaining */
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 1e11df8fa7ec..bbf405a3a18f 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -565,7 +565,7 @@ bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_mask)
 
 	spin_lock(&zone_scan_lock);
 	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
-		if (zone_is_oom_locked(zone)) {
+		if (test_bit(ZONE_OOM_LOCKED, &zone->flags)) {
 			ret = false;
 			goto out;
 		}
@@ -575,7 +575,7 @@ bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_mask)
 	 * call to oom_zonelist_trylock() doesn't succeed when it shouldn't.
 	 */
 	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
-		zone_set_flag(zone, ZONE_OOM_LOCKED);
+		set_bit(ZONE_OOM_LOCKED, &zone->flags);
 
 out:
 	spin_unlock(&zone_scan_lock);
@@ -594,7 +594,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask)
 
 	spin_lock(&zone_scan_lock);
 	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
-		zone_clear_flag(zone, ZONE_OOM_LOCKED);
+		clear_bit(ZONE_OOM_LOCKED, &zone->flags);
 	spin_unlock(&zone_scan_lock);
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ae2f8474273c..f3769f0fce3c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1614,8 +1614,8 @@ again:
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
 	if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
-	    !zone_is_fair_depleted(zone))
-		zone_set_flag(zone, ZONE_FAIR_DEPLETED);
+	    !test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
+		set_bit(ZONE_FAIR_DEPLETED, &zone->flags);
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
@@ -1935,7 +1935,7 @@ static void reset_alloc_batches(struct zone *preferred_zone)
 		mod_zone_page_state(zone, NR_ALLOC_BATCH,
 			high_wmark_pages(zone) - low_wmark_pages(zone) -
 			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-		zone_clear_flag(zone, ZONE_FAIR_DEPLETED);
+		clear_bit(ZONE_FAIR_DEPLETED, &zone->flags);
 	} while (zone++ != preferred_zone);
 }
 
@@ -1986,7 +1986,7 @@ zonelist_scan:
 		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
 				break;
-			if (zone_is_fair_depleted(zone)) {
+			if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
 				nr_fair_skipped++;
 				continue;
 			}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index af72fe8e8d74..06123f20a326 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -920,7 +920,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			/* Case 1 above */
 			if (current_is_kswapd() &&
 			    PageReclaim(page) &&
-			    zone_is_reclaim_writeback(zone)) {
+			    test_bit(ZONE_WRITEBACK, &zone->flags)) {
 				nr_immediate++;
 				goto keep_locked;
 
@@ -1002,7 +1002,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			 */
 			if (page_is_file_cache(page) &&
 					(!current_is_kswapd() ||
-					 !zone_is_reclaim_dirty(zone))) {
+					 !test_bit(ZONE_DIRTY, &zone->flags))) {
 				/*
 				 * Immediately reclaim when written back.
 				 * Similar in principal to deactivate_page()
@@ -1563,7 +1563,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	 * are encountered in the nr_immediate check below.
 	 */
 	if (nr_writeback && nr_writeback == nr_taken)
-		zone_set_flag(zone, ZONE_WRITEBACK);
+		set_bit(ZONE_WRITEBACK, &zone->flags);
 
 	/*
 	 * memcg will stall in page writeback so only consider forcibly
@@ -1575,16 +1575,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * backed by a congested BDI and wait_iff_congested will stall.
 		 */
 		if (nr_dirty && nr_dirty == nr_congested)
-			zone_set_flag(zone, ZONE_CONGESTED);
+			set_bit(ZONE_CONGESTED, &zone->flags);
 
 		/*
 		 * If dirty pages are scanned that are not queued for IO, it
 		 * implies that flushers are not keeping up. In this case, flag
-		 * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
-		 * pages from reclaim context.
+		 * the zone ZONE_DIRTY and kswapd will start writing pages from
+		 * reclaim context.
 		 */
 		if (nr_unqueued_dirty == nr_taken)
-			zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
+			set_bit(ZONE_DIRTY, &zone->flags);
 
 		/*
 		 * If kswapd scans pages marked marked for immediate
@@ -2984,7 +2984,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	/* Account for the number of pages attempted to reclaim */
 	*nr_attempted += sc->nr_to_reclaim;
 
-	zone_clear_flag(zone, ZONE_WRITEBACK);
+	clear_bit(ZONE_WRITEBACK, &zone->flags);
 
 	/*
 	 * If a zone reaches its high watermark, consider it to be no longer
@@ -2994,8 +2994,8 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	 */
 	if (zone_reclaimable(zone) &&
 	    zone_balanced(zone, testorder, 0, classzone_idx)) {
-		zone_clear_flag(zone, ZONE_CONGESTED);
-		zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
+		clear_bit(ZONE_CONGESTED, &zone->flags);
+		clear_bit(ZONE_DIRTY, &zone->flags);
 	}
 
 	return sc->nr_scanned >= sc->nr_to_reclaim;
@@ -3086,8 +3086,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 				 * If balanced, clear the dirty and congested
 				 * flags
 				 */
-				zone_clear_flag(zone, ZONE_CONGESTED);
-				zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
+				clear_bit(ZONE_CONGESTED, &zone->flags);
+				clear_bit(ZONE_DIRTY, &zone->flags);
 			}
 		}
 
@@ -3714,11 +3714,11 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	if (node_state(node_id, N_CPU) && node_id != numa_node_id())
 		return ZONE_RECLAIM_NOSCAN;
 
-	if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
+	if (test_and_set_bit(ZONE_RECLAIM_LOCKED, &zone->flags))
 		return ZONE_RECLAIM_NOSCAN;
 
 	ret = __zone_reclaim(zone, gfp_mask, order);
-	zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
+	clear_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
 
 	if (!ret)
 		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
-- 
cgit v1.2.3


From 934f3072c17cc8886f4c043b47eeeb1b12f8de33 Mon Sep 17 00:00:00 2001
From: Junxiao Bi <junxiao.bi@oracle.com>
Date: Thu, 9 Oct 2014 15:28:23 -0700
Subject: mm: clear __GFP_FS when PF_MEMALLOC_NOIO is set

commit 21caf2fc1931 ("mm: teach mm by current context info to not do I/O
during memory allocation") introduces PF_MEMALLOC_NOIO flag to avoid doing
I/O inside memory allocation, __GFP_IO is cleared when this flag is set,
but __GFP_FS implies __GFP_IO, it should also be cleared.  Or it may still
run into I/O, like in superblock shrinker.  And this will make the kernel
run into the deadlock case described in that commit.

See Dave Chinner's comment about io in superblock shrinker:

Filesystem shrinkers do indeed perform IO from the superblock shrinker and
have for years.  Even clean inodes can require IO before they can be freed
- e.g.  on an orphan list, need truncation of post-eof blocks, need to
wait for ordered operations to complete before it can be freed, etc.

IOWs, Ext4, btrfs and XFS all can issue and/or block on arbitrary amounts
of IO in the superblock shrinker context.  XFS, in particular, has been
doing transactions and IO from the VFS inode cache shrinker since it was
first introduced....

Fix this by clearing __GFP_FS in memalloc_noio_flags(), this function has
masked all the gfp_mask that will be passed into fs for the processes
setting PF_MEMALLOC_NOIO in the direct reclaim path.

v1 thread at: https://lkml.org/lkml/2014/9/3/32

Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: joyce.xue <xuejiufei@huawei.com>
Cc: Ming Lei <ming.lei@canonical.com>
Cc: Trond Myklebust <trond.myklebust@primarydata.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9c6353d9e63a..5e63ba59258c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1935,11 +1935,13 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
+ * __GFP_FS is also cleared as it implies __GFP_IO.
+ */
 static inline gfp_t memalloc_noio_flags(gfp_t flags)
 {
 	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
-		flags &= ~__GFP_IO;
+		flags &= ~(__GFP_IO | __GFP_FS);
 	return flags;
 }
 
-- 
cgit v1.2.3


From 31c9afa6db122a5c7a7843278aaf77dd08ea6e98 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 9 Oct 2014 15:28:37 -0700
Subject: mm: introduce VM_BUG_ON_MM

Very similar to VM_BUG_ON_PAGE and VM_BUG_ON_VMA, dump struct_mm when the
bug is hit.

[akpm@linux-foundation.org: coding-style fixes]
[mhocko@suse.cz: fix build]
[mhocko@suse.cz: fix build some more]
[akpm@linux-foundation.org: do strange things to avoid doing strange things for the comma separators]
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Dave Jones <davej@redhat.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmdebug.h | 10 +++++++
 mm/debug.c              | 78 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 88 insertions(+)

(limited to 'include')

diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 569e4c8d0ebb..877ef226f90f 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -5,11 +5,13 @@
 
 struct page;
 struct vm_area_struct;
+struct mm_struct;
 
 extern void dump_page(struct page *page, const char *reason);
 extern void dump_page_badflags(struct page *page, const char *reason,
 			       unsigned long badflags);
 void dump_vma(const struct vm_area_struct *vma);
+void dump_mm(const struct mm_struct *mm);
 
 #ifdef CONFIG_DEBUG_VM
 #define VM_BUG_ON(cond) BUG_ON(cond)
@@ -27,6 +29,13 @@ void dump_vma(const struct vm_area_struct *vma);
 			BUG();						\
 		}							\
 	} while (0)
+#define VM_BUG_ON_MM(cond, mm)						\
+	do {								\
+		if (unlikely(cond)) {					\
+			dump_mm(mm);					\
+			BUG();						\
+		}							\
+	} while (0)
 #define VM_WARN_ON(cond) WARN_ON(cond)
 #define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond)
 #define VM_WARN_ONCE(cond, format...) WARN_ONCE(cond, format)
@@ -34,6 +43,7 @@ void dump_vma(const struct vm_area_struct *vma);
 #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond)
 #define VM_BUG_ON_VMA(cond, vma) VM_BUG_ON(cond)
+#define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond)
 #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
diff --git a/mm/debug.c b/mm/debug.c
index 697df9050193..5a1b6194089c 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -1,3 +1,10 @@
+/*
+ * mm/debug.c
+ *
+ * mm/ specific debug routines.
+ *
+ */
+
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/ftrace_event.h>
@@ -159,4 +166,75 @@ void dump_vma(const struct vm_area_struct *vma)
 }
 EXPORT_SYMBOL(dump_vma);
 
+void dump_mm(const struct mm_struct *mm)
+{
+	printk(KERN_ALERT
+		"mm %p mmap %p seqnum %d task_size %lu\n"
+#ifdef CONFIG_MMU
+		"get_unmapped_area %p\n"
+#endif
+		"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
+		"pgd %p mm_users %d mm_count %d nr_ptes %lu map_count %d\n"
+		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
+		"pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n"
+		"start_code %lx end_code %lx start_data %lx end_data %lx\n"
+		"start_brk %lx brk %lx start_stack %lx\n"
+		"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
+		"binfmt %p flags %lx core_state %p\n"
+#ifdef CONFIG_AIO
+		"ioctx_table %p\n"
+#endif
+#ifdef CONFIG_MEMCG
+		"owner %p "
+#endif
+		"exe_file %p\n"
+#ifdef CONFIG_MMU_NOTIFIER
+		"mmu_notifier_mm %p\n"
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+		"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
+#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+		"tlb_flush_pending %d\n"
+#endif
+		"%s",	/* This is here to hold the comma */
+
+		mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
+#ifdef CONFIG_MMU
+		mm->get_unmapped_area,
+#endif
+		mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
+		mm->pgd, atomic_read(&mm->mm_users),
+		atomic_read(&mm->mm_count),
+		atomic_long_read((atomic_long_t *)&mm->nr_ptes),
+		mm->map_count,
+		mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
+		mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm,
+		mm->start_code, mm->end_code, mm->start_data, mm->end_data,
+		mm->start_brk, mm->brk, mm->start_stack,
+		mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
+		mm->binfmt, mm->flags, mm->core_state,
+#ifdef CONFIG_AIO
+		mm->ioctx_table,
+#endif
+#ifdef CONFIG_MEMCG
+		mm->owner,
+#endif
+		mm->exe_file,
+#ifdef CONFIG_MMU_NOTIFIER
+		mm->mmu_notifier_mm,
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+		mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
+#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+		mm->tlb_flush_pending,
+#endif
+		""		/* This is here to not have a comma! */
+		);
+
+		dump_flags(mm->def_flags, vmaflags_names,
+				ARRAY_SIZE(vmaflags_names));
+}
+
 #endif		/* CONFIG_DEBUG_VM */
-- 
cgit v1.2.3


From 33a690c45b202e4c6483bfd1d93ad8d0f51df2ca Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Thu, 9 Oct 2014 15:28:43 -0700
Subject: memcg: move memcg_{alloc,free}_cache_params to slab_common.c

The only reason why they live in memcontrol.c is that we get/put css
reference to the owner memory cgroup in them.  However, we can do that in
memcg_{un,}register_cache.  OTOH, there are several reasons to move them
to slab_common.c.

First, I think that the less public interface functions we have in
memcontrol.h the better.  Since the functions I move don't depend on
memcontrol, I think it's worth making them private to slab, especially
taking into account that the arrays are defined on the slab's side too.

Second, the way how per-memcg arrays are updated looks rather awkward: it
proceeds from memcontrol.c (__memcg_activate_kmem) to slab_common.c
(memcg_update_all_caches) and back to memcontrol.c again
(memcg_update_array_size).  In the following patches I move the function
relocating the arrays (memcg_update_array_size) to slab_common.c and
therefore get rid this circular call path.  I think we should have the
cache allocation stuff in the same place where we have relocation, because
it's easier to follow the code then.  So I move arrays alloc/free
functions to slab_common.c too.

The third point isn't obvious.  I'm going to make the list_lru structure
per-memcg to allow targeted kmem reclaim.  That means we will have
per-memcg arrays in list_lrus too.  It turns out that it's much easier to
update these arrays in list_lru.c rather than in memcontrol.c, because all
the stuff we need is defined there.  This patch makes memcg caches arrays
allocation path conform that of the upcoming list_lru.

So let's move these functions to slab_common.c and make them static.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 14 --------------
 mm/memcontrol.c            | 41 ++++-------------------------------------
 mm/slab_common.c           | 44 +++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 47 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e0752d204d9e..4d17242eeff7 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -440,10 +440,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
 int memcg_cache_id(struct mem_cgroup *memcg);
 
-int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s,
-			     struct kmem_cache *root_cache);
-void memcg_free_cache_params(struct kmem_cache *s);
-
 int memcg_update_cache_size(struct kmem_cache *s, int num_groups);
 void memcg_update_array_size(int num_groups);
 
@@ -574,16 +570,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return -1;
 }
 
-static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
-		struct kmem_cache *s, struct kmem_cache *root_cache)
-{
-	return 0;
-}
-
-static inline void memcg_free_cache_params(struct kmem_cache *s)
-{
-}
-
 static inline struct kmem_cache *
 memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 28928ce9b07f..865e87c014d6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2984,43 +2984,6 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
 	return 0;
 }
 
-int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s,
-			     struct kmem_cache *root_cache)
-{
-	size_t size;
-
-	if (!memcg_kmem_enabled())
-		return 0;
-
-	if (!memcg) {
-		size = offsetof(struct memcg_cache_params, memcg_caches);
-		size += memcg_limited_groups_array_size * sizeof(void *);
-	} else
-		size = sizeof(struct memcg_cache_params);
-
-	s->memcg_params = kzalloc(size, GFP_KERNEL);
-	if (!s->memcg_params)
-		return -ENOMEM;
-
-	if (memcg) {
-		s->memcg_params->memcg = memcg;
-		s->memcg_params->root_cache = root_cache;
-		css_get(&memcg->css);
-	} else
-		s->memcg_params->is_root_cache = true;
-
-	return 0;
-}
-
-void memcg_free_cache_params(struct kmem_cache *s)
-{
-	if (!s->memcg_params)
-		return;
-	if (!s->memcg_params->is_root_cache)
-		css_put(&s->memcg_params->memcg->css);
-	kfree(s->memcg_params);
-}
-
 static void memcg_register_cache(struct mem_cgroup *memcg,
 				 struct kmem_cache *root_cache)
 {
@@ -3051,6 +3014,7 @@ static void memcg_register_cache(struct mem_cgroup *memcg,
 	if (!cachep)
 		return;
 
+	css_get(&memcg->css);
 	list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches);
 
 	/*
@@ -3084,6 +3048,9 @@ static void memcg_unregister_cache(struct kmem_cache *cachep)
 	list_del(&cachep->memcg_params->list);
 
 	kmem_cache_destroy(cachep);
+
+	/* drop the reference taken in memcg_register_cache */
+	css_put(&memcg->css);
 }
 
 /*
diff --git a/mm/slab_common.c b/mm/slab_common.c
index f206cb10a544..c2a8661f8b81 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -116,6 +116,38 @@ static inline int kmem_cache_sanity_check(const char *name, size_t size)
 #endif
 
 #ifdef CONFIG_MEMCG_KMEM
+static int memcg_alloc_cache_params(struct mem_cgroup *memcg,
+		struct kmem_cache *s, struct kmem_cache *root_cache)
+{
+	size_t size;
+
+	if (!memcg_kmem_enabled())
+		return 0;
+
+	if (!memcg) {
+		size = offsetof(struct memcg_cache_params, memcg_caches);
+		size += memcg_limited_groups_array_size * sizeof(void *);
+	} else
+		size = sizeof(struct memcg_cache_params);
+
+	s->memcg_params = kzalloc(size, GFP_KERNEL);
+	if (!s->memcg_params)
+		return -ENOMEM;
+
+	if (memcg) {
+		s->memcg_params->memcg = memcg;
+		s->memcg_params->root_cache = root_cache;
+	} else
+		s->memcg_params->is_root_cache = true;
+
+	return 0;
+}
+
+static void memcg_free_cache_params(struct kmem_cache *s)
+{
+	kfree(s->memcg_params);
+}
+
 int memcg_update_all_caches(int num_memcgs)
 {
 	struct kmem_cache *s;
@@ -141,7 +173,17 @@ out:
 	mutex_unlock(&slab_mutex);
 	return ret;
 }
-#endif
+#else
+static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
+		struct kmem_cache *s, struct kmem_cache *root_cache)
+{
+	return 0;
+}
+
+static inline void memcg_free_cache_params(struct kmem_cache *s)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
 
 /*
  * Find a mergeable slab cache
-- 
cgit v1.2.3


From 6f817f4cda68b09621312ec5ba84217bc5e37b3d Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Thu, 9 Oct 2014 15:28:47 -0700
Subject: memcg: move memcg_update_cache_size() to slab_common.c

`While growing per memcg caches arrays, we jump between memcontrol.c and
slab_common.c in a weird way:

  memcg_alloc_cache_id - memcontrol.c
    memcg_update_all_caches - slab_common.c
      memcg_update_cache_size - memcontrol.c

There's absolutely no reason why memcg_update_cache_size can't live on the
slab's side though.  So let's move it there and settle it comfortably amid
per-memcg cache allocation functions.

Besides, this patch cleans this function up a bit, removing all the
useless comments from it, and renames it to memcg_update_cache_params to
conform to memcg_alloc/free_cache_params, which we already have in
slab_common.c.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  1 -
 mm/memcontrol.c            | 49 ----------------------------------------------
 mm/slab_common.c           | 30 ++++++++++++++++++++++++++--
 3 files changed, 28 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4d17242eeff7..19df5d857411 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -440,7 +440,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
 int memcg_cache_id(struct mem_cgroup *memcg);
 
-int memcg_update_cache_size(struct kmem_cache *s, int num_groups);
 void memcg_update_array_size(int num_groups);
 
 struct kmem_cache *
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ef4fbc5e4ca3..fff511e25bb2 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2958,55 +2958,6 @@ void memcg_update_array_size(int num)
 	memcg_limited_groups_array_size = num;
 }
 
-int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
-{
-	struct memcg_cache_params *cur_params = s->memcg_params;
-	struct memcg_cache_params *new_params;
-	size_t size;
-	int i;
-
-	VM_BUG_ON(!is_root_cache(s));
-
-	size = num_groups * sizeof(void *);
-	size += offsetof(struct memcg_cache_params, memcg_caches);
-
-	new_params = kzalloc(size, GFP_KERNEL);
-	if (!new_params)
-		return -ENOMEM;
-
-	new_params->is_root_cache = true;
-
-	/*
-	 * There is the chance it will be bigger than
-	 * memcg_limited_groups_array_size, if we failed an allocation
-	 * in a cache, in which case all caches updated before it, will
-	 * have a bigger array.
-	 *
-	 * But if that is the case, the data after
-	 * memcg_limited_groups_array_size is certainly unused
-	 */
-	for (i = 0; i < memcg_limited_groups_array_size; i++) {
-		if (!cur_params->memcg_caches[i])
-			continue;
-		new_params->memcg_caches[i] =
-			cur_params->memcg_caches[i];
-	}
-
-	/*
-	 * Ideally, we would wait until all caches succeed, and only
-	 * then free the old one. But this is not worth the extra
-	 * pointer per-cache we'd have to have for this.
-	 *
-	 * It is not a big deal if some caches are left with a size
-	 * bigger than the others. And all updates will reset this
-	 * anyway.
-	 */
-	rcu_assign_pointer(s->memcg_params, new_params);
-	if (cur_params)
-		kfree_rcu(cur_params, rcu_head);
-	return 0;
-}
-
 static void memcg_register_cache(struct mem_cgroup *memcg,
 				 struct kmem_cache *root_cache)
 {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index c2a8661f8b81..3a6e0cfdf03a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -148,6 +148,33 @@ static void memcg_free_cache_params(struct kmem_cache *s)
 	kfree(s->memcg_params);
 }
 
+static int memcg_update_cache_params(struct kmem_cache *s, int num_memcgs)
+{
+	int size;
+	struct memcg_cache_params *new_params, *cur_params;
+
+	BUG_ON(!is_root_cache(s));
+
+	size = offsetof(struct memcg_cache_params, memcg_caches);
+	size += num_memcgs * sizeof(void *);
+
+	new_params = kzalloc(size, GFP_KERNEL);
+	if (!new_params)
+		return -ENOMEM;
+
+	cur_params = s->memcg_params;
+	memcpy(new_params->memcg_caches, cur_params->memcg_caches,
+	       memcg_limited_groups_array_size * sizeof(void *));
+
+	new_params->is_root_cache = true;
+
+	rcu_assign_pointer(s->memcg_params, new_params);
+	if (cur_params)
+		kfree_rcu(cur_params, rcu_head);
+
+	return 0;
+}
+
 int memcg_update_all_caches(int num_memcgs)
 {
 	struct kmem_cache *s;
@@ -158,9 +185,8 @@ int memcg_update_all_caches(int num_memcgs)
 		if (!is_root_cache(s))
 			continue;
 
-		ret = memcg_update_cache_size(s, num_memcgs);
+		ret = memcg_update_cache_params(s, num_memcgs);
 		/*
-		 * See comment in memcontrol.c, memcg_update_cache_size:
 		 * Instead of freeing the memory, we'll just leave the caches
 		 * up to this point in an updated state.
 		 */
-- 
cgit v1.2.3


From b70a2a21dc9d4ad455931b53131a0cb4fc01fafe Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 9 Oct 2014 15:28:56 -0700
Subject: mm: memcontrol: fix transparent huge page allocations under pressure

In a memcg with even just moderate cache pressure, success rates for
transparent huge page allocations drop to zero, wasting a lot of effort
that the allocator puts into assembling these pages.

The reason for this is that the memcg reclaim code was never designed for
higher-order charges.  It reclaims in small batches until there is room
for at least one page.  Huge page charges only succeed when these batches
add up over a series of huge faults, which is unlikely under any
significant load involving order-0 allocations in the group.

Remove that loop on the memcg side in favor of passing the actual reclaim
goal to direct reclaim, which is already set up and optimized to meet
higher-order goals efficiently.

This brings memcg's THP policy in line with the system policy: if the
allocator painstakingly assembles a hugepage, memcg will at least make an
honest effort to charge it.  As a result, transparent hugepage allocation
rates amid cache activity are drastically improved:

                                      vanilla                 patched
pgalloc                 4717530.80 (  +0.00%)   4451376.40 (  -5.64%)
pgfault                  491370.60 (  +0.00%)    225477.40 ( -54.11%)
pgmajfault                    2.00 (  +0.00%)         1.80 (  -6.67%)
thp_fault_alloc               0.00 (  +0.00%)       531.60 (+100.00%)
thp_fault_fallback          749.00 (  +0.00%)       217.40 ( -70.88%)

[ Note: this may in turn increase memory consumption from internal
  fragmentation, which is an inherent risk of transparent hugepages.
  Some setups may have to adjust the memcg limits accordingly to
  accomodate this - or, if the machine is already packed to capacity,
  disable the transparent huge page feature. ]

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Dave Hansen <dave@sr71.net>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  6 +++--
 mm/memcontrol.c      | 69 +++++++++++++---------------------------------------
 mm/vmscan.c          |  7 +++---
 3 files changed, 25 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index ea4f926e6b9b..37a585beef5c 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -327,8 +327,10 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
 extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
-extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
-						  gfp_t gfp_mask, bool noswap);
+extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
+						  unsigned long nr_pages,
+						  gfp_t gfp_mask,
+						  bool may_swap);
 extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
 						struct zone *zone,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9cda99dfac4f..c86cc442ada4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -480,14 +480,6 @@ enum res_type {
 /* Used for OOM nofiier */
 #define OOM_CONTROL		(0)
 
-/*
- * Reclaim flags for mem_cgroup_hierarchical_reclaim
- */
-#define MEM_CGROUP_RECLAIM_NOSWAP_BIT	0x0
-#define MEM_CGROUP_RECLAIM_NOSWAP	(1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT)
-#define MEM_CGROUP_RECLAIM_SHRINK_BIT	0x1
-#define MEM_CGROUP_RECLAIM_SHRINK	(1 << MEM_CGROUP_RECLAIM_SHRINK_BIT)
-
 /*
  * The memcg_create_mutex will be held whenever a new cgroup is created.
  * As a consequence, any change that needs to protect against new child cgroups
@@ -1805,40 +1797,6 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 			 NULL, "Memory cgroup out of memory");
 }
 
-static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
-					gfp_t gfp_mask,
-					unsigned long flags)
-{
-	unsigned long total = 0;
-	bool noswap = false;
-	int loop;
-
-	if (flags & MEM_CGROUP_RECLAIM_NOSWAP)
-		noswap = true;
-
-	for (loop = 0; loop < MEM_CGROUP_MAX_RECLAIM_LOOPS; loop++) {
-		if (loop)
-			drain_all_stock_async(memcg);
-		total += try_to_free_mem_cgroup_pages(memcg, gfp_mask, noswap);
-		/*
-		 * Allow limit shrinkers, which are triggered directly
-		 * by userspace, to catch signals and stop reclaim
-		 * after minimal progress, regardless of the margin.
-		 */
-		if (total && (flags & MEM_CGROUP_RECLAIM_SHRINK))
-			break;
-		if (mem_cgroup_margin(memcg))
-			break;
-		/*
-		 * If nothing was reclaimed after two attempts, there
-		 * may be no reclaimable pages in this hierarchy.
-		 */
-		if (loop && !total)
-			break;
-	}
-	return total;
-}
-
 /**
  * test_mem_cgroup_node_reclaimable
  * @memcg: the target memcg
@@ -2541,8 +2499,9 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	struct mem_cgroup *mem_over_limit;
 	struct res_counter *fail_res;
 	unsigned long nr_reclaimed;
-	unsigned long flags = 0;
 	unsigned long long size;
+	bool may_swap = true;
+	bool drained = false;
 	int ret = 0;
 
 	if (mem_cgroup_is_root(memcg))
@@ -2561,7 +2520,7 @@ retry:
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
 	} else {
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
-		flags |= MEM_CGROUP_RECLAIM_NOSWAP;
+		may_swap = false;
 	}
 
 	if (batch > nr_pages) {
@@ -2586,11 +2545,18 @@ retry:
 	if (!(gfp_mask & __GFP_WAIT))
 		goto nomem;
 
-	nr_reclaimed = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags);
+	nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
+						    gfp_mask, may_swap);
 
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
 		goto retry;
 
+	if (!drained) {
+		drain_all_stock_async(mem_over_limit);
+		drained = true;
+		goto retry;
+	}
+
 	if (gfp_mask & __GFP_NORETRY)
 		goto nomem;
 	/*
@@ -3666,8 +3632,8 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 		if (!ret)
 			break;
 
-		mem_cgroup_reclaim(memcg, GFP_KERNEL,
-				   MEM_CGROUP_RECLAIM_SHRINK);
+		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true);
+
 		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
@@ -3717,9 +3683,8 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 		if (!ret)
 			break;
 
-		mem_cgroup_reclaim(memcg, GFP_KERNEL,
-				   MEM_CGROUP_RECLAIM_NOSWAP |
-				   MEM_CGROUP_RECLAIM_SHRINK);
+		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, false);
+
 		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
@@ -3968,8 +3933,8 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 		if (signal_pending(current))
 			return -EINTR;
 
-		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL,
-						false);
+		progress = try_to_free_mem_cgroup_pages(memcg, 1,
+							GFP_KERNEL, true);
 		if (!progress) {
 			nr_retries--;
 			/* maybe some writeback is necessary */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 06123f20a326..dcb47074ae03 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2759,21 +2759,22 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 }
 
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
+					   unsigned long nr_pages,
 					   gfp_t gfp_mask,
-					   bool noswap)
+					   bool may_swap)
 {
 	struct zonelist *zonelist;
 	unsigned long nr_reclaimed;
 	int nid;
 	struct scan_control sc = {
-		.nr_to_reclaim = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
 		.target_mem_cgroup = memcg,
 		.priority = DEF_PRIORITY,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
-		.may_swap = !noswap,
+		.may_swap = may_swap,
 	};
 
 	/*
-- 
cgit v1.2.3


From d6d86c0a7f8ddc5b38cf089222cb1d9540762dc2 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <k.khlebnikov@samsung.com>
Date: Thu, 9 Oct 2014 15:29:27 -0700
Subject: mm/balloon_compaction: redesign ballooned pages management

Sasha Levin reported KASAN splash inside isolate_migratepages_range().
Problem is in the function __is_movable_balloon_page() which tests
AS_BALLOON_MAP in page->mapping->flags.  This function has no protection
against anonymous pages.  As result it tried to check address space flags
inside struct anon_vma.

Further investigation shows more problems in current implementation:

* Special branch in __unmap_and_move() never works:
  balloon_page_movable() checks page flags and page_count.  In
  __unmap_and_move() page is locked, reference counter is elevated, thus
  balloon_page_movable() always fails.  As a result execution goes to the
  normal migration path.  virtballoon_migratepage() returns
  MIGRATEPAGE_BALLOON_SUCCESS instead of MIGRATEPAGE_SUCCESS,
  move_to_new_page() thinks this is an error code and assigns
  newpage->mapping to NULL.  Newly migrated page lose connectivity with
  balloon an all ability for further migration.

* lru_lock erroneously required in isolate_migratepages_range() for
  isolation ballooned page.  This function releases lru_lock periodically,
  this makes migration mostly impossible for some pages.

* balloon_page_dequeue have a tight race with balloon_page_isolate:
  balloon_page_isolate could be executed in parallel with dequeue between
  picking page from list and locking page_lock.  Race is rare because they
  use trylock_page() for locking.

This patch fixes all of them.

Instead of fake mapping with special flag this patch uses special state of
page->_mapcount: PAGE_BALLOON_MAPCOUNT_VALUE = -256.  Buddy allocator uses
PAGE_BUDDY_MAPCOUNT_VALUE = -128 for similar purpose.  Storing mark
directly in struct page makes everything safer and easier.

PagePrivate is used to mark pages present in page list (i.e.  not
isolated, like PageLRU for normal pages).  It replaces special rules for
reference counter and makes balloon migration similar to migration of
normal pages.  This flag is protected by page_lock together with link to
the balloon device.

Signed-off-by: Konstantin Khlebnikov <k.khlebnikov@samsung.com>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Link: http://lkml.kernel.org/p/53E6CEAA.9020105@oracle.com
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: <stable@vger.kernel.org>	[3.8+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/virtio/virtio_balloon.c    | 15 +++---
 include/linux/balloon_compaction.h | 97 ++++++++++----------------------------
 include/linux/migrate.h            | 11 +----
 include/linux/mm.h                 | 19 ++++++++
 mm/balloon_compaction.c            | 26 +++++-----
 mm/compaction.c                    |  2 +-
 mm/migrate.c                       | 16 ++-----
 7 files changed, 68 insertions(+), 118 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 25ebe8eecdb7..c3eb93fc9261 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -163,8 +163,8 @@ static void release_pages_by_pfn(const u32 pfns[], unsigned int num)
 	/* Find pfns pointing at start of each page, get pages and free them. */
 	for (i = 0; i < num; i += VIRTIO_BALLOON_PAGES_PER_PAGE) {
 		struct page *page = balloon_pfn_to_page(pfns[i]);
-		balloon_page_free(page);
 		adjust_managed_page_count(page, 1);
+		put_page(page); /* balloon reference */
 	}
 }
 
@@ -395,6 +395,8 @@ static int virtballoon_migratepage(struct address_space *mapping,
 	if (!mutex_trylock(&vb->balloon_lock))
 		return -EAGAIN;
 
+	get_page(newpage); /* balloon reference */
+
 	/* balloon's page migration 1st step  -- inflate "newpage" */
 	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
 	balloon_page_insert(newpage, mapping, &vb_dev_info->pages);
@@ -404,12 +406,7 @@ static int virtballoon_migratepage(struct address_space *mapping,
 	set_page_pfns(vb->pfns, newpage);
 	tell_host(vb, vb->inflate_vq);
 
-	/*
-	 * balloon's page migration 2nd step -- deflate "page"
-	 *
-	 * It's safe to delete page->lru here because this page is at
-	 * an isolated migration list, and this step is expected to happen here
-	 */
+	/* balloon's page migration 2nd step -- deflate "page" */
 	balloon_page_delete(page);
 	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
 	set_page_pfns(vb->pfns, page);
@@ -417,7 +414,9 @@ static int virtballoon_migratepage(struct address_space *mapping,
 
 	mutex_unlock(&vb->balloon_lock);
 
-	return MIGRATEPAGE_BALLOON_SUCCESS;
+	put_page(page); /* balloon reference */
+
+	return MIGRATEPAGE_SUCCESS;
 }
 
 /* define the balloon_mapping->a_ops callback to allow balloon page migration */
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index 089743ade734..38aa07d5b81c 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -27,10 +27,13 @@
  *      counter raised only while it is under our special handling;
  *
  * iii. after the lockless scan step have selected a potential balloon page for
- *      isolation, re-test the page->mapping flags and the page ref counter
+ *      isolation, re-test the PageBalloon mark and the PagePrivate flag
  *      under the proper page lock, to ensure isolating a valid balloon page
  *      (not yet isolated, nor under release procedure)
  *
+ *  iv. isolation or dequeueing procedure must clear PagePrivate flag under
+ *      page lock together with removing page from balloon device page list.
+ *
  * The functions provided by this interface are placed to help on coping with
  * the aforementioned balloon page corner case, as well as to ensure the simple
  * set of exposed rules are satisfied while we are dealing with balloon pages
@@ -71,28 +74,6 @@ static inline void balloon_devinfo_free(struct balloon_dev_info *b_dev_info)
 	kfree(b_dev_info);
 }
 
-/*
- * balloon_page_free - release a balloon page back to the page free lists
- * @page: ballooned page to be set free
- *
- * This function must be used to properly set free an isolated/dequeued balloon
- * page at the end of a sucessful page migration, or at the balloon driver's
- * page release procedure.
- */
-static inline void balloon_page_free(struct page *page)
-{
-	/*
-	 * Balloon pages always get an extra refcount before being isolated
-	 * and before being dequeued to help on sorting out fortuite colisions
-	 * between a thread attempting to isolate and another thread attempting
-	 * to release the very same balloon page.
-	 *
-	 * Before we handle the page back to Buddy, lets drop its extra refcnt.
-	 */
-	put_page(page);
-	__free_page(page);
-}
-
 #ifdef CONFIG_BALLOON_COMPACTION
 extern bool balloon_page_isolate(struct page *page);
 extern void balloon_page_putback(struct page *page);
@@ -108,74 +89,33 @@ static inline void balloon_mapping_free(struct address_space *balloon_mapping)
 }
 
 /*
- * page_flags_cleared - helper to perform balloon @page ->flags tests.
- *
- * As balloon pages are obtained from buddy and we do not play with page->flags
- * at driver level (exception made when we get the page lock for compaction),
- * we can safely identify a ballooned page by checking if the
- * PAGE_FLAGS_CHECK_AT_PREP page->flags are all cleared.  This approach also
- * helps us skip ballooned pages that are locked for compaction or release, thus
- * mitigating their racy check at balloon_page_movable()
- */
-static inline bool page_flags_cleared(struct page *page)
-{
-	return !(page->flags & PAGE_FLAGS_CHECK_AT_PREP);
-}
-
-/*
- * __is_movable_balloon_page - helper to perform @page mapping->flags tests
+ * __is_movable_balloon_page - helper to perform @page PageBalloon tests
  */
 static inline bool __is_movable_balloon_page(struct page *page)
 {
-	struct address_space *mapping = page->mapping;
-	return mapping_balloon(mapping);
+	return PageBalloon(page);
 }
 
 /*
- * balloon_page_movable - test page->mapping->flags to identify balloon pages
- *			  that can be moved by compaction/migration.
- *
- * This function is used at core compaction's page isolation scheme, therefore
- * most pages exposed to it are not enlisted as balloon pages and so, to avoid
- * undesired side effects like racing against __free_pages(), we cannot afford
- * holding the page locked while testing page->mapping->flags here.
+ * balloon_page_movable - test PageBalloon to identify balloon pages
+ *			  and PagePrivate to check that the page is not
+ *			  isolated and can be moved by compaction/migration.
  *
  * As we might return false positives in the case of a balloon page being just
- * released under us, the page->mapping->flags need to be re-tested later,
- * under the proper page lock, at the functions that will be coping with the
- * balloon page case.
+ * released under us, this need to be re-tested later, under the page lock.
  */
 static inline bool balloon_page_movable(struct page *page)
 {
-	/*
-	 * Before dereferencing and testing mapping->flags, let's make sure
-	 * this is not a page that uses ->mapping in a different way
-	 */
-	if (page_flags_cleared(page) && !page_mapped(page) &&
-	    page_count(page) == 1)
-		return __is_movable_balloon_page(page);
-
-	return false;
+	return PageBalloon(page) && PagePrivate(page);
 }
 
 /*
  * isolated_balloon_page - identify an isolated balloon page on private
  *			   compaction/migration page lists.
- *
- * After a compaction thread isolates a balloon page for migration, it raises
- * the page refcount to prevent concurrent compaction threads from re-isolating
- * the same page. For that reason putback_movable_pages(), or other routines
- * that need to identify isolated balloon pages on private pagelists, cannot
- * rely on balloon_page_movable() to accomplish the task.
  */
 static inline bool isolated_balloon_page(struct page *page)
 {
-	/* Already isolated balloon pages, by default, have a raised refcount */
-	if (page_flags_cleared(page) && !page_mapped(page) &&
-	    page_count(page) >= 2)
-		return __is_movable_balloon_page(page);
-
-	return false;
+	return PageBalloon(page);
 }
 
 /*
@@ -192,6 +132,8 @@ static inline void balloon_page_insert(struct page *page,
 				       struct address_space *mapping,
 				       struct list_head *head)
 {
+	__SetPageBalloon(page);
+	SetPagePrivate(page);
 	page->mapping = mapping;
 	list_add(&page->lru, head);
 }
@@ -206,8 +148,12 @@ static inline void balloon_page_insert(struct page *page,
  */
 static inline void balloon_page_delete(struct page *page)
 {
+	__ClearPageBalloon(page);
 	page->mapping = NULL;
-	list_del(&page->lru);
+	if (PagePrivate(page)) {
+		ClearPagePrivate(page);
+		list_del(&page->lru);
+	}
 }
 
 /*
@@ -258,6 +204,11 @@ static inline void balloon_page_delete(struct page *page)
 	list_del(&page->lru);
 }
 
+static inline bool __is_movable_balloon_page(struct page *page)
+{
+	return false;
+}
+
 static inline bool balloon_page_movable(struct page *page)
 {
 	return false;
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index b66fd10f4b93..01aad3ed89ec 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -13,18 +13,9 @@ typedef void free_page_t(struct page *page, unsigned long private);
  * Return values from addresss_space_operations.migratepage():
  * - negative errno on page migration failure;
  * - zero on page migration success;
- *
- * The balloon page migration introduces this special case where a 'distinct'
- * return code is used to flag a successful page migration to unmap_and_move().
- * This approach is necessary because page migration can race against balloon
- * deflation procedure, and for such case we could introduce a nasty page leak
- * if a successfully migrated balloon page gets released concurrently with
- * migration's unmap_and_move() wrap-up steps.
  */
 #define MIGRATEPAGE_SUCCESS		0
-#define MIGRATEPAGE_BALLOON_SUCCESS	1 /* special ret code for balloon page
-					   * sucessful migration case.
-					   */
+
 enum migrate_reason {
 	MR_COMPACTION,
 	MR_MEMORY_FAILURE,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4d814aa97785..fa0d74e06428 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -554,6 +554,25 @@ static inline void __ClearPageBuddy(struct page *page)
 	atomic_set(&page->_mapcount, -1);
 }
 
+#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)
+
+static inline int PageBalloon(struct page *page)
+{
+	return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE;
+}
+
+static inline void __SetPageBalloon(struct page *page)
+{
+	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
+	atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE);
+}
+
+static inline void __ClearPageBalloon(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageBalloon(page), page);
+	atomic_set(&page->_mapcount, -1);
+}
+
 void put_page(struct page *page);
 void put_pages_list(struct list_head *pages);
 
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 6e45a5074bf0..52abeeb3cb9d 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -93,17 +93,12 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
 		 * to be released by the balloon driver.
 		 */
 		if (trylock_page(page)) {
+			if (!PagePrivate(page)) {
+				/* raced with isolation */
+				unlock_page(page);
+				continue;
+			}
 			spin_lock_irqsave(&b_dev_info->pages_lock, flags);
-			/*
-			 * Raise the page refcount here to prevent any wrong
-			 * attempt to isolate this page, in case of coliding
-			 * with balloon_page_isolate() just after we release
-			 * the page lock.
-			 *
-			 * balloon_page_free() will take care of dropping
-			 * this extra refcount later.
-			 */
-			get_page(page);
 			balloon_page_delete(page);
 			spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 			unlock_page(page);
@@ -187,7 +182,9 @@ static inline void __isolate_balloon_page(struct page *page)
 {
 	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
 	unsigned long flags;
+
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	ClearPagePrivate(page);
 	list_del(&page->lru);
 	b_dev_info->isolated_pages++;
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
@@ -197,7 +194,9 @@ static inline void __putback_balloon_page(struct page *page)
 {
 	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
 	unsigned long flags;
+
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	SetPagePrivate(page);
 	list_add(&page->lru, &b_dev_info->pages);
 	b_dev_info->isolated_pages--;
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
@@ -235,12 +234,11 @@ bool balloon_page_isolate(struct page *page)
 		 */
 		if (likely(trylock_page(page))) {
 			/*
-			 * A ballooned page, by default, has just one refcount.
+			 * A ballooned page, by default, has PagePrivate set.
 			 * Prevent concurrent compaction threads from isolating
-			 * an already isolated balloon page by refcount check.
+			 * an already isolated balloon page by clearing it.
 			 */
-			if (__is_movable_balloon_page(page) &&
-			    page_count(page) == 2) {
+			if (balloon_page_movable(page)) {
 				__isolate_balloon_page(page);
 				unlock_page(page);
 				return true;
diff --git a/mm/compaction.c b/mm/compaction.c
index b9972c0fd917..edba18aed173 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -640,7 +640,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 */
 		if (!PageLRU(page)) {
 			if (unlikely(balloon_page_movable(page))) {
-				if (locked && balloon_page_isolate(page)) {
+				if (balloon_page_isolate(page)) {
 					/* Successfully isolated */
 					goto isolate_success;
 				}
diff --git a/mm/migrate.c b/mm/migrate.c
index 2740360cd216..01439953abf5 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -876,7 +876,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		}
 	}
 
-	if (unlikely(balloon_page_movable(page))) {
+	if (unlikely(isolated_balloon_page(page))) {
 		/*
 		 * A ballooned page does not need any special attention from
 		 * physical to virtual reverse mapping procedures.
@@ -955,17 +955,6 @@ static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page,
 
 	rc = __unmap_and_move(page, newpage, force, mode);
 
-	if (unlikely(rc == MIGRATEPAGE_BALLOON_SUCCESS)) {
-		/*
-		 * A ballooned page has been migrated already.
-		 * Now, it's the time to wrap-up counters,
-		 * handle the page back to Buddy and return.
-		 */
-		dec_zone_page_state(page, NR_ISOLATED_ANON +
-				    page_is_file_cache(page));
-		balloon_page_free(page);
-		return MIGRATEPAGE_SUCCESS;
-	}
 out:
 	if (rc != -EAGAIN) {
 		/*
@@ -988,6 +977,9 @@ out:
 	if (rc != MIGRATEPAGE_SUCCESS && put_new_page) {
 		ClearPageSwapBacked(newpage);
 		put_new_page(newpage, private);
+	} else if (unlikely(__is_movable_balloon_page(newpage))) {
+		/* drop our reference, page already in the balloon */
+		put_page(newpage);
 	} else
 		putback_lru_page(newpage);
 
-- 
cgit v1.2.3


From 9d1ba8056474a208ed9efb7e58cd014795d9f818 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <k.khlebnikov@samsung.com>
Date: Thu, 9 Oct 2014 15:29:29 -0700
Subject: mm/balloon_compaction: remove balloon mapping and flag AS_BALLOON_MAP

Now ballooned pages are detected using PageBalloon().  Fake mapping is no
longer required.  This patch links ballooned pages to balloon device using
field page->private instead of page->mapping.  Also this patch embeds
balloon_dev_info directly into struct virtio_balloon.

Signed-off-by: Konstantin Khlebnikov <k.khlebnikov@samsung.com>
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/virtio/virtio_balloon.c    | 60 ++++++------------------
 include/linux/balloon_compaction.h | 72 ++++++++---------------------
 include/linux/pagemap.h            | 18 +-------
 mm/balloon_compaction.c            | 95 +++-----------------------------------
 4 files changed, 39 insertions(+), 206 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index c3eb93fc9261..2bad7f9dd2ac 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -59,7 +59,7 @@ struct virtio_balloon
 	 * Each page on this list adds VIRTIO_BALLOON_PAGES_PER_PAGE
 	 * to num_pages above.
 	 */
-	struct balloon_dev_info *vb_dev_info;
+	struct balloon_dev_info vb_dev_info;
 
 	/* Synchronize access/update to this struct virtio_balloon elements */
 	struct mutex balloon_lock;
@@ -127,7 +127,7 @@ static void set_page_pfns(u32 pfns[], struct page *page)
 
 static void fill_balloon(struct virtio_balloon *vb, size_t num)
 {
-	struct balloon_dev_info *vb_dev_info = vb->vb_dev_info;
+	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
 
 	/* We can only do one array worth at a time. */
 	num = min(num, ARRAY_SIZE(vb->pfns));
@@ -171,7 +171,7 @@ static void release_pages_by_pfn(const u32 pfns[], unsigned int num)
 static void leak_balloon(struct virtio_balloon *vb, size_t num)
 {
 	struct page *page;
-	struct balloon_dev_info *vb_dev_info = vb->vb_dev_info;
+	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
 
 	/* We can only do one array worth at a time. */
 	num = min(num, ARRAY_SIZE(vb->pfns));
@@ -353,12 +353,11 @@ static int init_vqs(struct virtio_balloon *vb)
 	return 0;
 }
 
-static const struct address_space_operations virtio_balloon_aops;
 #ifdef CONFIG_BALLOON_COMPACTION
 /*
  * virtballoon_migratepage - perform the balloon page migration on behalf of
  *			     a compation thread.     (called under page lock)
- * @mapping: the page->mapping which will be assigned to the new migrated page.
+ * @vb_dev_info: the balloon device
  * @newpage: page that will replace the isolated page after migration finishes.
  * @page   : the isolated (old) page that is about to be migrated to newpage.
  * @mode   : compaction mode -- not used for balloon page migration.
@@ -373,17 +372,13 @@ static const struct address_space_operations virtio_balloon_aops;
  * This function preforms the balloon page migration task.
  * Called through balloon_mapping->a_ops->migratepage
  */
-static int virtballoon_migratepage(struct address_space *mapping,
+static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
 		struct page *newpage, struct page *page, enum migrate_mode mode)
 {
-	struct balloon_dev_info *vb_dev_info = balloon_page_device(page);
-	struct virtio_balloon *vb;
+	struct virtio_balloon *vb = container_of(vb_dev_info,
+			struct virtio_balloon, vb_dev_info);
 	unsigned long flags;
 
-	BUG_ON(!vb_dev_info);
-
-	vb = vb_dev_info->balloon_device;
-
 	/*
 	 * In order to avoid lock contention while migrating pages concurrently
 	 * to leak_balloon() or fill_balloon() we just give up the balloon_lock
@@ -399,7 +394,7 @@ static int virtballoon_migratepage(struct address_space *mapping,
 
 	/* balloon's page migration 1st step  -- inflate "newpage" */
 	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
-	balloon_page_insert(newpage, mapping, &vb_dev_info->pages);
+	balloon_page_insert(vb_dev_info, newpage);
 	vb_dev_info->isolated_pages--;
 	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
 	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
@@ -418,18 +413,11 @@ static int virtballoon_migratepage(struct address_space *mapping,
 
 	return MIGRATEPAGE_SUCCESS;
 }
-
-/* define the balloon_mapping->a_ops callback to allow balloon page migration */
-static const struct address_space_operations virtio_balloon_aops = {
-			.migratepage = virtballoon_migratepage,
-};
 #endif /* CONFIG_BALLOON_COMPACTION */
 
 static int virtballoon_probe(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb;
-	struct address_space *vb_mapping;
-	struct balloon_dev_info *vb_devinfo;
 	int err;
 
 	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
@@ -445,30 +433,14 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	vb->vdev = vdev;
 	vb->need_stats_update = 0;
 
-	vb_devinfo = balloon_devinfo_alloc(vb);
-	if (IS_ERR(vb_devinfo)) {
-		err = PTR_ERR(vb_devinfo);
-		goto out_free_vb;
-	}
-
-	vb_mapping = balloon_mapping_alloc(vb_devinfo,
-					   (balloon_compaction_check()) ?
-					   &virtio_balloon_aops : NULL);
-	if (IS_ERR(vb_mapping)) {
-		/*
-		 * IS_ERR(vb_mapping) && PTR_ERR(vb_mapping) == -EOPNOTSUPP
-		 * This means !CONFIG_BALLOON_COMPACTION, otherwise we get off.
-		 */
-		err = PTR_ERR(vb_mapping);
-		if (err != -EOPNOTSUPP)
-			goto out_free_vb_devinfo;
-	}
-
-	vb->vb_dev_info = vb_devinfo;
+	balloon_devinfo_init(&vb->vb_dev_info);
+#ifdef CONFIG_BALLOON_COMPACTION
+	vb->vb_dev_info.migratepage = virtballoon_migratepage;
+#endif
 
 	err = init_vqs(vb);
 	if (err)
-		goto out_free_vb_mapping;
+		goto out_free_vb;
 
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
@@ -480,10 +452,6 @@ static int virtballoon_probe(struct virtio_device *vdev)
 
 out_del_vqs:
 	vdev->config->del_vqs(vdev);
-out_free_vb_mapping:
-	balloon_mapping_free(vb_mapping);
-out_free_vb_devinfo:
-	balloon_devinfo_free(vb_devinfo);
 out_free_vb:
 	kfree(vb);
 out:
@@ -509,8 +477,6 @@ static void virtballoon_remove(struct virtio_device *vdev)
 
 	kthread_stop(vb->thread);
 	remove_common(vb);
-	balloon_mapping_free(vb->vb_dev_info->mapping);
-	balloon_devinfo_free(vb->vb_dev_info);
 	kfree(vb);
 }
 
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index 38aa07d5b81c..bc3d2985cc9a 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -57,21 +57,22 @@
  * balloon driver as a page book-keeper for its registered balloon devices.
  */
 struct balloon_dev_info {
-	void *balloon_device;		/* balloon device descriptor */
-	struct address_space *mapping;	/* balloon special page->mapping */
 	unsigned long isolated_pages;	/* # of isolated pages for migration */
 	spinlock_t pages_lock;		/* Protection to pages list */
 	struct list_head pages;		/* Pages enqueued & handled to Host */
+	int (*migratepage)(struct balloon_dev_info *, struct page *newpage,
+			struct page *page, enum migrate_mode mode);
 };
 
 extern struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info);
 extern struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info);
-extern struct balloon_dev_info *balloon_devinfo_alloc(
-						void *balloon_dev_descriptor);
 
-static inline void balloon_devinfo_free(struct balloon_dev_info *b_dev_info)
+static inline void balloon_devinfo_init(struct balloon_dev_info *balloon)
 {
-	kfree(b_dev_info);
+	balloon->isolated_pages = 0;
+	spin_lock_init(&balloon->pages_lock);
+	INIT_LIST_HEAD(&balloon->pages);
+	balloon->migratepage = NULL;
 }
 
 #ifdef CONFIG_BALLOON_COMPACTION
@@ -79,14 +80,6 @@ extern bool balloon_page_isolate(struct page *page);
 extern void balloon_page_putback(struct page *page);
 extern int balloon_page_migrate(struct page *newpage,
 				struct page *page, enum migrate_mode mode);
-extern struct address_space
-*balloon_mapping_alloc(struct balloon_dev_info *b_dev_info,
-			const struct address_space_operations *a_ops);
-
-static inline void balloon_mapping_free(struct address_space *balloon_mapping)
-{
-	kfree(balloon_mapping);
-}
 
 /*
  * __is_movable_balloon_page - helper to perform @page PageBalloon tests
@@ -120,27 +113,25 @@ static inline bool isolated_balloon_page(struct page *page)
 
 /*
  * balloon_page_insert - insert a page into the balloon's page list and make
- *		         the page->mapping assignment accordingly.
+ *			 the page->private assignment accordingly.
+ * @balloon : pointer to balloon device
  * @page    : page to be assigned as a 'balloon page'
- * @mapping : allocated special 'balloon_mapping'
- * @head    : balloon's device page list head
  *
  * Caller must ensure the page is locked and the spin_lock protecting balloon
  * pages list is held before inserting a page into the balloon device.
  */
-static inline void balloon_page_insert(struct page *page,
-				       struct address_space *mapping,
-				       struct list_head *head)
+static inline void balloon_page_insert(struct balloon_dev_info *balloon,
+				       struct page *page)
 {
 	__SetPageBalloon(page);
 	SetPagePrivate(page);
-	page->mapping = mapping;
-	list_add(&page->lru, head);
+	set_page_private(page, (unsigned long)balloon);
+	list_add(&page->lru, &balloon->pages);
 }
 
 /*
  * balloon_page_delete - delete a page from balloon's page list and clear
- *			 the page->mapping assignement accordingly.
+ *			 the page->private assignement accordingly.
  * @page    : page to be released from balloon's page list
  *
  * Caller must ensure the page is locked and the spin_lock protecting balloon
@@ -149,7 +140,7 @@ static inline void balloon_page_insert(struct page *page,
 static inline void balloon_page_delete(struct page *page)
 {
 	__ClearPageBalloon(page);
-	page->mapping = NULL;
+	set_page_private(page, 0);
 	if (PagePrivate(page)) {
 		ClearPagePrivate(page);
 		list_del(&page->lru);
@@ -162,11 +153,7 @@ static inline void balloon_page_delete(struct page *page)
  */
 static inline struct balloon_dev_info *balloon_page_device(struct page *page)
 {
-	struct address_space *mapping = page->mapping;
-	if (likely(mapping))
-		return mapping->private_data;
-
-	return NULL;
+	return (struct balloon_dev_info *)page_private(page);
 }
 
 static inline gfp_t balloon_mapping_gfp_mask(void)
@@ -174,29 +161,12 @@ static inline gfp_t balloon_mapping_gfp_mask(void)
 	return GFP_HIGHUSER_MOVABLE;
 }
 
-static inline bool balloon_compaction_check(void)
-{
-	return true;
-}
-
 #else /* !CONFIG_BALLOON_COMPACTION */
 
-static inline void *balloon_mapping_alloc(void *balloon_device,
-				const struct address_space_operations *a_ops)
+static inline void balloon_page_insert(struct balloon_dev_info *balloon,
+				       struct page *page)
 {
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
-static inline void balloon_mapping_free(struct address_space *balloon_mapping)
-{
-	return;
-}
-
-static inline void balloon_page_insert(struct page *page,
-				       struct address_space *mapping,
-				       struct list_head *head)
-{
-	list_add(&page->lru, head);
+	list_add(&page->lru, &balloon->pages);
 }
 
 static inline void balloon_page_delete(struct page *page)
@@ -240,9 +210,5 @@ static inline gfp_t balloon_mapping_gfp_mask(void)
 	return GFP_HIGHUSER;
 }
 
-static inline bool balloon_compaction_check(void)
-{
-	return false;
-}
 #endif /* CONFIG_BALLOON_COMPACTION */
 #endif /* _LINUX_BALLOON_COMPACTION_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 19191d39c4f3..7ea069cd3257 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -24,8 +24,7 @@ enum mapping_flags {
 	AS_ENOSPC	= __GFP_BITS_SHIFT + 1,	/* ENOSPC on async write */
 	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
 	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
-	AS_BALLOON_MAP  = __GFP_BITS_SHIFT + 4, /* balloon page special map */
-	AS_EXITING	= __GFP_BITS_SHIFT + 5, /* final truncate in progress */
+	AS_EXITING	= __GFP_BITS_SHIFT + 4, /* final truncate in progress */
 };
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
@@ -55,21 +54,6 @@ static inline int mapping_unevictable(struct address_space *mapping)
 	return !!mapping;
 }
 
-static inline void mapping_set_balloon(struct address_space *mapping)
-{
-	set_bit(AS_BALLOON_MAP, &mapping->flags);
-}
-
-static inline void mapping_clear_balloon(struct address_space *mapping)
-{
-	clear_bit(AS_BALLOON_MAP, &mapping->flags);
-}
-
-static inline int mapping_balloon(struct address_space *mapping)
-{
-	return mapping && test_bit(AS_BALLOON_MAP, &mapping->flags);
-}
-
 static inline void mapping_set_exiting(struct address_space *mapping)
 {
 	set_bit(AS_EXITING, &mapping->flags);
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 52abeeb3cb9d..3afdabdbc0a4 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -10,32 +10,6 @@
 #include <linux/export.h>
 #include <linux/balloon_compaction.h>
 
-/*
- * balloon_devinfo_alloc - allocates a balloon device information descriptor.
- * @balloon_dev_descriptor: pointer to reference the balloon device which
- *                          this struct balloon_dev_info will be servicing.
- *
- * Driver must call it to properly allocate and initialize an instance of
- * struct balloon_dev_info which will be used to reference a balloon device
- * as well as to keep track of the balloon device page list.
- */
-struct balloon_dev_info *balloon_devinfo_alloc(void *balloon_dev_descriptor)
-{
-	struct balloon_dev_info *b_dev_info;
-	b_dev_info = kmalloc(sizeof(*b_dev_info), GFP_KERNEL);
-	if (!b_dev_info)
-		return ERR_PTR(-ENOMEM);
-
-	b_dev_info->balloon_device = balloon_dev_descriptor;
-	b_dev_info->mapping = NULL;
-	b_dev_info->isolated_pages = 0;
-	spin_lock_init(&b_dev_info->pages_lock);
-	INIT_LIST_HEAD(&b_dev_info->pages);
-
-	return b_dev_info;
-}
-EXPORT_SYMBOL_GPL(balloon_devinfo_alloc);
-
 /*
  * balloon_page_enqueue - allocates a new page and inserts it into the balloon
  *			  page list.
@@ -61,7 +35,7 @@ struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
 	 */
 	BUG_ON(!trylock_page(page));
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
-	balloon_page_insert(page, b_dev_info->mapping, &b_dev_info->pages);
+	balloon_page_insert(b_dev_info, page);
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 	unlock_page(page);
 	return page;
@@ -127,60 +101,10 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
 EXPORT_SYMBOL_GPL(balloon_page_dequeue);
 
 #ifdef CONFIG_BALLOON_COMPACTION
-/*
- * balloon_mapping_alloc - allocates a special ->mapping for ballooned pages.
- * @b_dev_info: holds the balloon device information descriptor.
- * @a_ops: balloon_mapping address_space_operations descriptor.
- *
- * Driver must call it to properly allocate and initialize an instance of
- * struct address_space which will be used as the special page->mapping for
- * balloon device enlisted page instances.
- */
-struct address_space *balloon_mapping_alloc(struct balloon_dev_info *b_dev_info,
-				const struct address_space_operations *a_ops)
-{
-	struct address_space *mapping;
-
-	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
-	if (!mapping)
-		return ERR_PTR(-ENOMEM);
-
-	/*
-	 * Give a clean 'zeroed' status to all elements of this special
-	 * balloon page->mapping struct address_space instance.
-	 */
-	address_space_init_once(mapping);
-
-	/*
-	 * Set mapping->flags appropriately, to allow balloon pages
-	 * ->mapping identification.
-	 */
-	mapping_set_balloon(mapping);
-	mapping_set_gfp_mask(mapping, balloon_mapping_gfp_mask());
-
-	/* balloon's page->mapping->a_ops callback descriptor */
-	mapping->a_ops = a_ops;
-
-	/*
-	 * Establish a pointer reference back to the balloon device descriptor
-	 * this particular page->mapping will be servicing.
-	 * This is used by compaction / migration procedures to identify and
-	 * access the balloon device pageset while isolating / migrating pages.
-	 *
-	 * As some balloon drivers can register multiple balloon devices
-	 * for a single guest, this also helps compaction / migration to
-	 * properly deal with multiple balloon pagesets, when required.
-	 */
-	mapping->private_data = b_dev_info;
-	b_dev_info->mapping = mapping;
-
-	return mapping;
-}
-EXPORT_SYMBOL_GPL(balloon_mapping_alloc);
 
 static inline void __isolate_balloon_page(struct page *page)
 {
-	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
+	struct balloon_dev_info *b_dev_info = balloon_page_device(page);
 	unsigned long flags;
 
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
@@ -192,7 +116,7 @@ static inline void __isolate_balloon_page(struct page *page)
 
 static inline void __putback_balloon_page(struct page *page)
 {
-	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
+	struct balloon_dev_info *b_dev_info = balloon_page_device(page);
 	unsigned long flags;
 
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
@@ -202,12 +126,6 @@ static inline void __putback_balloon_page(struct page *page)
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 }
 
-static inline int __migrate_balloon_page(struct address_space *mapping,
-		struct page *newpage, struct page *page, enum migrate_mode mode)
-{
-	return page->mapping->a_ops->migratepage(mapping, newpage, page, mode);
-}
-
 /* __isolate_lru_page() counterpart for a ballooned page */
 bool balloon_page_isolate(struct page *page)
 {
@@ -274,7 +192,7 @@ void balloon_page_putback(struct page *page)
 int balloon_page_migrate(struct page *newpage,
 			 struct page *page, enum migrate_mode mode)
 {
-	struct address_space *mapping;
+	struct balloon_dev_info *balloon = balloon_page_device(page);
 	int rc = -EAGAIN;
 
 	/*
@@ -290,9 +208,8 @@ int balloon_page_migrate(struct page *newpage,
 		return rc;
 	}
 
-	mapping = page->mapping;
-	if (mapping)
-		rc = __migrate_balloon_page(mapping, newpage, page, mode);
+	if (balloon && balloon->migratepage)
+		rc = balloon->migratepage(balloon, newpage, page, mode);
 
 	unlock_page(newpage);
 	return rc;
-- 
cgit v1.2.3


From 09316c09dde33aae14f34489d9e3d243ec0d5938 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <k.khlebnikov@samsung.com>
Date: Thu, 9 Oct 2014 15:29:32 -0700
Subject: mm/balloon_compaction: add vmstat counters and kpageflags bit

Always mark pages with PageBalloon even if balloon compaction is disabled
and expose this mark in /proc/kpageflags as KPF_BALLOON.

Also this patch adds three counters into /proc/vmstat: "balloon_inflate",
"balloon_deflate" and "balloon_migrate".  They accumulate balloon
activity.  Current size of balloon is (balloon_inflate - balloon_deflate)
pages.

All generic balloon code now gathered under option CONFIG_MEMORY_BALLOON.
It should be selected by ballooning driver which wants use this feature.
Currently virtio-balloon is the only user.

Signed-off-by: Konstantin Khlebnikov <k.khlebnikov@samsung.com>
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/virtio/Kconfig                 |  1 +
 drivers/virtio/virtio_balloon.c        |  1 +
 fs/proc/page.c                         |  3 +++
 include/linux/balloon_compaction.h     |  2 ++
 include/linux/vm_event_item.h          |  7 +++++++
 include/uapi/linux/kernel-page-flags.h |  1 +
 mm/Kconfig                             |  7 ++++++-
 mm/Makefile                            |  3 ++-
 mm/balloon_compaction.c                |  2 ++
 mm/vmstat.c                            | 12 +++++++++++-
 tools/vm/page-types.c                  |  1 +
 11 files changed, 37 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index c6683f2e396c..00b228638274 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -25,6 +25,7 @@ config VIRTIO_PCI
 config VIRTIO_BALLOON
 	tristate "Virtio balloon driver"
 	depends on VIRTIO
+	select MEMORY_BALLOON
 	---help---
 	 This driver supports increasing and decreasing the amount
 	 of memory within a KVM guest.
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 2bad7f9dd2ac..f893148a107b 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -396,6 +396,7 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
 	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
 	balloon_page_insert(vb_dev_info, newpage);
 	vb_dev_info->isolated_pages--;
+	__count_vm_event(BALLOON_MIGRATE);
 	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
 	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
 	set_page_pfns(vb->pfns, newpage);
diff --git a/fs/proc/page.c b/fs/proc/page.c
index e647c55275d9..1e3187da1fed 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -133,6 +133,9 @@ u64 stable_page_flags(struct page *page)
 	if (PageBuddy(page))
 		u |= 1 << KPF_BUDDY;
 
+	if (PageBalloon(page))
+		u |= 1 << KPF_BALLOON;
+
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
 
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index bc3d2985cc9a..9b0a15d06a4f 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -166,11 +166,13 @@ static inline gfp_t balloon_mapping_gfp_mask(void)
 static inline void balloon_page_insert(struct balloon_dev_info *balloon,
 				       struct page *page)
 {
+	__SetPageBalloon(page);
 	list_add(&page->lru, &balloon->pages);
 }
 
 static inline void balloon_page_delete(struct page *page)
 {
+	__ClearPageBalloon(page);
 	list_del(&page->lru);
 }
 
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index ced92345c963..730334cdf037 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -72,6 +72,13 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
+#ifdef CONFIG_MEMORY_BALLOON
+		BALLOON_INFLATE,
+		BALLOON_DEFLATE,
+#ifdef CONFIG_BALLOON_COMPACTION
+		BALLOON_MIGRATE,
+#endif
+#endif
 #ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 		NR_TLB_REMOTE_FLUSH,	/* cpu tried to flush others' tlbs */
diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h
index 5116a0e48172..2f96d233c980 100644
--- a/include/uapi/linux/kernel-page-flags.h
+++ b/include/uapi/linux/kernel-page-flags.h
@@ -31,6 +31,7 @@
 
 #define KPF_KSM			21
 #define KPF_THP			22
+#define KPF_BALLOON		23
 
 
 #endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index 0ceb8a567dab..1d1ae6b078fd 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -230,12 +230,17 @@ config SPLIT_PTLOCK_CPUS
 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	boolean
 
+#
+# support for memory balloon
+config MEMORY_BALLOON
+	boolean
+
 #
 # support for memory balloon compaction
 config BALLOON_COMPACTION
 	bool "Allow for balloon memory compaction/migration"
 	def_bool y
-	depends on COMPACTION && VIRTIO_BALLOON
+	depends on COMPACTION && MEMORY_BALLOON
 	help
 	  Memory fragmentation introduced by ballooning might reduce
 	  significantly the number of 2MB contiguous memory blocks that can be
diff --git a/mm/Makefile b/mm/Makefile
index f8ed7ab417b1..1f534a7f0a71 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -16,7 +16,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o balloon_compaction.o vmacache.o \
+			   compaction.o vmacache.o \
 			   interval_tree.o list_lru.o workingset.o \
 			   iov_iter.o debug.o $(mmu-y)
 
@@ -67,3 +67,4 @@ obj-$(CONFIG_ZBUD)	+= zbud.o
 obj-$(CONFIG_ZSMALLOC)	+= zsmalloc.o
 obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o
 obj-$(CONFIG_CMA)	+= cma.o
+obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 3afdabdbc0a4..b3cbe19f71b5 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -36,6 +36,7 @@ struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
 	BUG_ON(!trylock_page(page));
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 	balloon_page_insert(b_dev_info, page);
+	__count_vm_event(BALLOON_INFLATE);
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 	unlock_page(page);
 	return page;
@@ -74,6 +75,7 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
 			}
 			spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 			balloon_page_delete(page);
+			__count_vm_event(BALLOON_DEFLATE);
 			spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 			unlock_page(page);
 			dequeued_page = true;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index e9ab104b956f..cce7c766da7a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -735,7 +735,7 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
 					TEXT_FOR_HIGHMEM(xx) xx "_movable",
 
 const char * const vmstat_text[] = {
-	/* Zoned VM counters */
+	/* enum zone_stat_item countes */
 	"nr_free_pages",
 	"nr_alloc_batch",
 	"nr_inactive_anon",
@@ -778,10 +778,13 @@ const char * const vmstat_text[] = {
 	"workingset_nodereclaim",
 	"nr_anon_transparent_hugepages",
 	"nr_free_cma",
+
+	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
 	"nr_dirty_background_threshold",
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
+	/* enum vm_event_item counters */
 	"pgpgin",
 	"pgpgout",
 	"pswpin",
@@ -860,6 +863,13 @@ const char * const vmstat_text[] = {
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
+#ifdef CONFIG_MEMORY_BALLOON
+	"balloon_inflate",
+	"balloon_deflate",
+#ifdef CONFIG_BALLOON_COMPACTION
+	"balloon_migrate",
+#endif
+#endif /* CONFIG_MEMORY_BALLOON */
 #ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index c4d6d2e20e0d..264fbc297e0b 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -132,6 +132,7 @@ static const char * const page_flag_names[] = {
 	[KPF_NOPAGE]		= "n:nopage",
 	[KPF_KSM]		= "x:ksm",
 	[KPF_THP]		= "t:thp",
+	[KPF_BALLOON]		= "o:balloon",
 
 	[KPF_RESERVED]		= "r:reserved",
 	[KPF_MLOCKED]		= "m:mlocked",
-- 
cgit v1.2.3


From 722cdc17232f0f684011407f7cf3c40d39457971 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Thu, 9 Oct 2014 15:29:50 -0700
Subject: zsmalloc: change return value unit of zs_get_total_size_bytes

zs_get_total_size_bytes returns a amount of memory zsmalloc consumed with
*byte unit* but zsmalloc operates *page unit* rather than byte unit so
let's change the API so benefit we could get is that reduce unnecessary
overhead (ie, change page unit with byte unit) in zsmalloc.

Since return type is pages, "zs_get_total_pages" is better than
"zs_get_total_size_bytes".

Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Dan Streetman <ddstreet@ieee.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: <juno.choi@lge.com>
Cc: <seungho1.park@lge.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Seth Jennings <sjennings@variantweb.net>
Cc: David Horner <ds2horner@gmail.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/block/zram/zram_drv.c | 4 ++--
 include/linux/zsmalloc.h      | 2 +-
 mm/zsmalloc.c                 | 9 ++++-----
 3 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d00831c3d731..f0b8b30a7128 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -103,10 +103,10 @@ static ssize_t mem_used_total_show(struct device *dev,
 
 	down_read(&zram->init_lock);
 	if (init_done(zram))
-		val = zs_get_total_size_bytes(meta->mem_pool);
+		val = zs_get_total_pages(meta->mem_pool);
 	up_read(&zram->init_lock);
 
-	return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
 }
 
 static ssize_t max_comp_streams_show(struct device *dev,
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index e44d634e7fb7..05c214760977 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -46,6 +46,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 			enum zs_mapmode mm);
 void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
 
-u64 zs_get_total_size_bytes(struct zs_pool *pool);
+unsigned long zs_get_total_pages(struct zs_pool *pool);
 
 #endif
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 2a4acf400846..c4a91578dc96 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -297,7 +297,7 @@ static void zs_zpool_unmap(void *pool, unsigned long handle)
 
 static u64 zs_zpool_total_size(void *pool)
 {
-	return zs_get_total_size_bytes(pool);
+	return zs_get_total_pages(pool) << PAGE_SHIFT;
 }
 
 static struct zpool_driver zs_zpool_driver = {
@@ -1181,12 +1181,11 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 }
 EXPORT_SYMBOL_GPL(zs_unmap_object);
 
-u64 zs_get_total_size_bytes(struct zs_pool *pool)
+unsigned long zs_get_total_pages(struct zs_pool *pool)
 {
-	u64 npages = atomic_long_read(&pool->pages_allocated);
-	return npages << PAGE_SHIFT;
+	return atomic_long_read(&pool->pages_allocated);
 }
-EXPORT_SYMBOL_GPL(zs_get_total_size_bytes);
+EXPORT_SYMBOL_GPL(zs_get_total_pages);
 
 module_init(zs_init);
 module_exit(zs_exit);
-- 
cgit v1.2.3


From 2e1d06e1c05af9dbe8a3bfddeefbf041ca637fff Mon Sep 17 00:00:00 2001
From: Michal Nazarewicz <mina86@mina86.com>
Date: Thu, 9 Oct 2014 15:30:13 -0700
Subject: include/linux/kernel.h: rewrite min3, max3 and clamp using min and
 max

It appears that gcc is better at optimising a double call to min and max
rather than open coded min3 and max3.  This can be observed here:

    $ cat min-max.c
    #define min(x, y) ({				\
    	typeof(x) _min1 = (x);			\
    	typeof(y) _min2 = (y);			\
    	(void) (&_min1 == &_min2);		\
    	_min1 < _min2 ? _min1 : _min2; })
    #define min3(x, y, z) ({			\
    	typeof(x) _min1 = (x);			\
    	typeof(y) _min2 = (y);			\
    	typeof(z) _min3 = (z);			\
    	(void) (&_min1 == &_min2);		\
    	(void) (&_min1 == &_min3);		\
    	_min1 < _min2 ? (_min1 < _min3 ? _min1 : _min3) : \
    		(_min2 < _min3 ? _min2 : _min3); })

    int fmin3(int x, int y, int z) { return min3(x, y, z); }
    int fmin2(int x, int y, int z) { return min(min(x, y), z); }

    $ gcc -O2 -o min-max.s -S min-max.c; cat min-max.s
    	.file	"min-max.c"
    	.text
    	.p2align 4,,15
    	.globl	fmin3
    	.type	fmin3, @function
    fmin3:
    .LFB0:
    	.cfi_startproc
    	cmpl	%esi, %edi
    	jl	.L5
    	cmpl	%esi, %edx
    	movl	%esi, %eax
    	cmovle	%edx, %eax
    	ret
    	.p2align 4,,10
    	.p2align 3
    .L5:
    	cmpl	%edi, %edx
    	movl	%edi, %eax
    	cmovle	%edx, %eax
    	ret
    	.cfi_endproc
    .LFE0:
    	.size	fmin3, .-fmin3
    	.p2align 4,,15
    	.globl	fmin2
    	.type	fmin2, @function
    fmin2:
    .LFB1:
    	.cfi_startproc
    	cmpl	%edi, %esi
    	movl	%edx, %eax
    	cmovle	%esi, %edi
    	cmpl	%edx, %edi
    	cmovle	%edi, %eax
    	ret
    	.cfi_endproc
    .LFE1:
    	.size	fmin2, .-fmin2
    	.ident	"GCC: (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3"
    	.section	.note.GNU-stack,"",@progbits

fmin3 function, which uses open-coded min3 macro, is compiled into total
of ten instructions including a conditional branch, whereas fmin2
function, which uses two calls to min2 macro, is compiled into six
instructions with no branches.

Similarly, open-coded clamp produces the same code as clamp using min and
max macros, but the latter is much shorter:

    $ cat clamp.c
    #define clamp(val, min, max) ({			\
    	typeof(val) __val = (val);		\
    	typeof(min) __min = (min);		\
    	typeof(max) __max = (max);		\
    	(void) (&__val == &__min);		\
    	(void) (&__val == &__max);		\
    	__val = __val < __min ? __min: __val;	\
    	__val > __max ? __max: __val; })
    #define min(x, y) ({				\
    	typeof(x) _min1 = (x);			\
    	typeof(y) _min2 = (y);			\
    	(void) (&_min1 == &_min2);		\
    	_min1 < _min2 ? _min1 : _min2; })
    #define max(x, y) ({				\
    	typeof(x) _max1 = (x);			\
    	typeof(y) _max2 = (y);			\
    	(void) (&_max1 == &_max2);		\
    	_max1 > _max2 ? _max1 : _max2; })

    int fclamp(int v, int min, int max) { return clamp(v, min, max); }
    int fclampmm(int v, int min, int max) { return min(max(v, min), max); }

    $ gcc -O2 -o clamp.s -S clamp.c; cat clamp.s
    	.file	"clamp.c"
    	.text
    	.p2align 4,,15
    	.globl	fclamp
    	.type	fclamp, @function
    fclamp:
    .LFB0:
    	.cfi_startproc
    	cmpl	%edi, %esi
    	movl	%edx, %eax
    	cmovge	%esi, %edi
    	cmpl	%edx, %edi
    	cmovle	%edi, %eax
    	ret
    	.cfi_endproc
    .LFE0:
    	.size	fclamp, .-fclamp
    	.p2align 4,,15
    	.globl	fclampmm
    	.type	fclampmm, @function
    fclampmm:
    .LFB1:
    	.cfi_startproc
    	cmpl	%edi, %esi
    	cmovge	%esi, %edi
    	cmpl	%edi, %edx
    	movl	%edi, %eax
    	cmovle	%edx, %eax
    	ret
    	.cfi_endproc
    .LFE1:
    	.size	fclampmm, .-fclampmm
    	.ident	"GCC: (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3"
    	.section	.note.GNU-stack,"",@progbits

    Linux mpn-glaptop 3.13.0-29-generic #53~precise1-Ubuntu SMP Wed Jun 4 22:06:25 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux
    gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3
    Copyright (C) 2011 Free Software Foundation, Inc.
    This is free software; see the source for copying conditions.  There is NO
    warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

    -rwx------ 1 mpn eng 51224656 Jun 17 14:15 vmlinux.before
    -rwx------ 1 mpn eng 51224608 Jun 17 13:57 vmlinux.after

48 bytes reduction.  The do_fault_around was a few instruction shorter
and as far as I can tell saved 12 bytes on the stack, i.e.:

    $ grep -e rsp -e pop -e push do_fault_around.*
    do_fault_around.before.s:push   %rbp
    do_fault_around.before.s:mov    %rsp,%rbp
    do_fault_around.before.s:push   %r13
    do_fault_around.before.s:push   %r12
    do_fault_around.before.s:push   %rbx
    do_fault_around.before.s:sub    $0x38,%rsp
    do_fault_around.before.s:add    $0x38,%rsp
    do_fault_around.before.s:pop    %rbx
    do_fault_around.before.s:pop    %r12
    do_fault_around.before.s:pop    %r13
    do_fault_around.before.s:pop    %rbp

    do_fault_around.after.s:push   %rbp
    do_fault_around.after.s:mov    %rsp,%rbp
    do_fault_around.after.s:push   %r12
    do_fault_around.after.s:push   %rbx
    do_fault_around.after.s:sub    $0x30,%rsp
    do_fault_around.after.s:add    $0x30,%rsp
    do_fault_around.after.s:pop    %rbx
    do_fault_around.after.s:pop    %r12
    do_fault_around.after.s:pop    %rbp

or here side-by-side:

    Before                    After
    push   %rbp               push   %rbp
    mov    %rsp,%rbp          mov    %rsp,%rbp
    push   %r13
    push   %r12               push   %r12
    push   %rbx               push   %rbx
    sub    $0x38,%rsp         sub    $0x30,%rsp
    add    $0x38,%rsp         add    $0x30,%rsp
    pop    %rbx               pop    %rbx
    pop    %r12               pop    %r12
    pop    %r13
    pop    %rbp               pop    %rbp

There are also fewer branches:

    $ grep ^j do_fault_around.*
    do_fault_around.before.s:jae    ffffffff812079b7
    do_fault_around.before.s:jmp    ffffffff812079c5
    do_fault_around.before.s:jmp    ffffffff81207a14
    do_fault_around.before.s:ja     ffffffff812079f9
    do_fault_around.before.s:jb     ffffffff81207a10
    do_fault_around.before.s:jmp    ffffffff81207a63
    do_fault_around.before.s:jne    ffffffff812079df

    do_fault_around.after.s:jmp    ffffffff812079fd
    do_fault_around.after.s:ja     ffffffff812079e2
    do_fault_around.after.s:jb     ffffffff812079f9
    do_fault_around.after.s:jmp    ffffffff81207a4c
    do_fault_around.after.s:jne    ffffffff812079c8

And here's with allyesconfig on a different machine:

    $ uname -a; gcc --version; ls -l vmlinux.*
    Linux erwin 3.14.7-mn #54 SMP Sun Jun 15 11:25:08 CEST 2014 x86_64 AMD Phenom(tm) II X3 710 Processor AuthenticAMD GNU/Linux
    gcc (GCC) 4.8.3
    Copyright (C) 2013 Free Software Foundation, Inc.
    This is free software; see the source for copying conditions.  There is NO
    warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

    -rwx------ 1 mpn eng 437027411 Jun 20 16:04 vmlinux.before
    -rwx------ 1 mpn eng 437026881 Jun 20 15:30 vmlinux.after

530 bytes reduction.

Signed-off-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Cc: David Rientjes <rientjes@google.com>
Cc: "Rustad, Mark D" <mark.d.rustad@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 32 +++++---------------------------
 1 file changed, 5 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 95624bed87ef..aa2a0cb57f50 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -715,23 +715,8 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 	(void) (&_max1 == &_max2);		\
 	_max1 > _max2 ? _max1 : _max2; })
 
-#define min3(x, y, z) ({			\
-	typeof(x) _min1 = (x);			\
-	typeof(y) _min2 = (y);			\
-	typeof(z) _min3 = (z);			\
-	(void) (&_min1 == &_min2);		\
-	(void) (&_min1 == &_min3);		\
-	_min1 < _min2 ? (_min1 < _min3 ? _min1 : _min3) : \
-		(_min2 < _min3 ? _min2 : _min3); })
-
-#define max3(x, y, z) ({			\
-	typeof(x) _max1 = (x);			\
-	typeof(y) _max2 = (y);			\
-	typeof(z) _max3 = (z);			\
-	(void) (&_max1 == &_max2);		\
-	(void) (&_max1 == &_max3);		\
-	_max1 > _max2 ? (_max1 > _max3 ? _max1 : _max3) : \
-		(_max2 > _max3 ? _max2 : _max3); })
+#define min3(x, y, z) min((typeof(x))min(x, y), z)
+#define max3(x, y, z) max((typeof(x))max(x, y), z)
 
 /**
  * min_not_zero - return the minimum that is _not_ zero, unless both are zero
@@ -746,20 +731,13 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 /**
  * clamp - return a value clamped to a given range with strict typechecking
  * @val: current value
- * @min: minimum allowable value
- * @max: maximum allowable value
+ * @lo: lowest allowable value
+ * @hi: highest allowable value
  *
  * This macro does strict typechecking of min/max to make sure they are of the
  * same type as val.  See the unnecessary pointer comparisons.
  */
-#define clamp(val, min, max) ({			\
-	typeof(val) __val = (val);		\
-	typeof(min) __min = (min);		\
-	typeof(max) __max = (max);		\
-	(void) (&__val == &__min);		\
-	(void) (&__val == &__max);		\
-	__val = __val < __min ? __min: __val;	\
-	__val > __max ? __max: __val; })
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
 
 /*
  * ..and if you can't take the strict
-- 
cgit v1.2.3


From c185b07fc9f24d52a864376ed22a6d84384b0c53 Mon Sep 17 00:00:00 2001
From: Michal Nazarewicz <mina86@mina86.com>
Date: Thu, 9 Oct 2014 15:30:15 -0700
Subject: include/linux/kernel.h: deduplicate code implementing clamp* macros

Instead of open-coding clamp_t macro min_t and max_t the way clamp macro
does and instead of open-coding clamp_val simply use clamp_t.
Furthermore, normalise argument naming in the macros to be lo and hi.

Signed-off-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Mark Rustad <mark.d.rustad@intel.com>
Cc: "Kirsher, Jeffrey T" <jeffrey.t.kirsher@intel.com>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 24 +++++++-----------------
 1 file changed, 7 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index aa2a0cb57f50..e9e420b6d931 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -734,7 +734,7 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
  * @lo: lowest allowable value
  * @hi: highest allowable value
  *
- * This macro does strict typechecking of min/max to make sure they are of the
+ * This macro does strict typechecking of lo/hi to make sure they are of the
  * same type as val.  See the unnecessary pointer comparisons.
  */
 #define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
@@ -759,36 +759,26 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
  * clamp_t - return a value clamped to a given range using a given type
  * @type: the type of variable to use
  * @val: current value
- * @min: minimum allowable value
- * @max: maximum allowable value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
  *
  * This macro does no typechecking and uses temporary variables of type
  * 'type' to make all the comparisons.
  */
-#define clamp_t(type, val, min, max) ({		\
-	type __val = (val);			\
-	type __min = (min);			\
-	type __max = (max);			\
-	__val = __val < __min ? __min: __val;	\
-	__val > __max ? __max: __val; })
+#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
 
 /**
  * clamp_val - return a value clamped to a given range using val's type
  * @val: current value
- * @min: minimum allowable value
- * @max: maximum allowable value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
  *
  * This macro does no typechecking and uses temporary variables of whatever
  * type the input argument 'val' is.  This is useful when val is an unsigned
  * type and min and max are literals that will otherwise be assigned a signed
  * integer type.
  */
-#define clamp_val(val, min, max) ({		\
-	typeof(val) __val = (val);		\
-	typeof(val) __min = (min);		\
-	typeof(val) __max = (max);		\
-	__val = __val < __min ? __min: __val;	\
-	__val > __max ? __max: __val; })
+#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
 
 
 /*
-- 
cgit v1.2.3


From 61a04e5b306ab9d6a30f78e86f1f140d7c888304 Mon Sep 17 00:00:00 2001
From: Michele Curti <michele.curti@gmail.com>
Date: Thu, 9 Oct 2014 15:30:17 -0700
Subject: include/linux/blkdev.h: use NULL instead of zero

Quite useless but it shuts up some warnings.

Signed-off-by: Michele Curti <michele.curti@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/blkdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 518b46555b80..87be398166d3 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1564,7 +1564,7 @@ static inline int blk_rq_map_integrity_sg(struct request_queue *q,
 }
 static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
 {
-	return 0;
+	return NULL;
 }
 static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
-- 
cgit v1.2.3


From 578b25dfce2990d8bab5631f33a4283bd5b01556 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 9 Oct 2014 15:30:28 -0700
Subject: include/linux/screen_info.h: remove unused ORIG_* macros

The ORIG_* macros definitions to access struct screen_info members and all
of their users were removed 7 years ago by commit 3ea335100014785f
("Remove magic macros for screen_info structure members"), but (only) the
definitions reappeared a few days later in commit ee8e7cfe9d330d6f ("Make
asm-x86/bootparam.h includable from userspace.").

Remove them for good. Amen.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/screen_info.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h
index 005bf3e38db5..f0f8bad54be9 100644
--- a/include/linux/screen_info.h
+++ b/include/linux/screen_info.h
@@ -5,12 +5,4 @@
 
 extern struct screen_info screen_info;
 
-#define ORIG_X			(screen_info.orig_x)
-#define ORIG_Y			(screen_info.orig_y)
-#define ORIG_VIDEO_MODE		(screen_info.orig_video_mode)
-#define ORIG_VIDEO_COLS 	(screen_info.orig_video_cols)
-#define ORIG_VIDEO_EGA_BX	(screen_info.orig_video_ega_bx)
-#define ORIG_VIDEO_LINES	(screen_info.orig_video_lines)
-#define ORIG_VIDEO_ISVGA	(screen_info.orig_video_isVGA)
-#define ORIG_VIDEO_POINTS       (screen_info.orig_video_points)
 #endif /* _SCREEN_INFO_H */
-- 
cgit v1.2.3


From 7f8998c7aef3ac9c5f3f2943e083dfa6302e90d0 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 9 Oct 2014 15:30:30 -0700
Subject: nosave: consolidate __nosave_{begin,end} in <asm/sections.h>

The different architectures used their own (and different) declarations:

    extern __visible const void __nosave_begin, __nosave_end;
    extern const void __nosave_begin, __nosave_end;
    extern long __nosave_begin, __nosave_end;

Consolidate them using the first variant in <asm/sections.h>.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/kernel/hibernate.c       | 3 +--
 arch/mips/include/asm/suspend.h   | 7 -------
 arch/mips/power/cpu.c             | 2 +-
 arch/powerpc/kernel/suspend.c     | 4 +---
 arch/s390/kernel/suspend.c        | 6 +-----
 arch/sh/include/asm/sections.h    | 1 -
 arch/sparc/power/hibernate.c      | 4 +---
 arch/unicore32/include/mach/pm.h  | 3 ---
 arch/unicore32/kernel/hibernate.c | 1 +
 arch/x86/power/hibernate_32.c     | 4 +---
 arch/x86/power/hibernate_64.c     | 4 +---
 include/asm-generic/sections.h    | 4 ++++
 12 files changed, 12 insertions(+), 31 deletions(-)
 delete mode 100644 arch/mips/include/asm/suspend.h

(limited to 'include')

diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c
index bb8b79648643..c4cc50e58c13 100644
--- a/arch/arm/kernel/hibernate.c
+++ b/arch/arm/kernel/hibernate.c
@@ -21,8 +21,7 @@
 #include <asm/idmap.h>
 #include <asm/suspend.h>
 #include <asm/memory.h>
-
-extern const void __nosave_begin, __nosave_end;
+#include <asm/sections.h>
 
 int pfn_is_nosave(unsigned long pfn)
 {
diff --git a/arch/mips/include/asm/suspend.h b/arch/mips/include/asm/suspend.h
deleted file mode 100644
index 3adac3b53d19..000000000000
--- a/arch/mips/include/asm/suspend.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_SUSPEND_H
-#define __ASM_SUSPEND_H
-
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
-#endif /* __ASM_SUSPEND_H */
diff --git a/arch/mips/power/cpu.c b/arch/mips/power/cpu.c
index 521e5963df05..2129e67723ff 100644
--- a/arch/mips/power/cpu.c
+++ b/arch/mips/power/cpu.c
@@ -7,7 +7,7 @@
  * Author: Hu Hongbing <huhb@lemote.com>
  *	   Wu Zhangjin <wuzhangjin@gmail.com>
  */
-#include <asm/suspend.h>
+#include <asm/sections.h>
 #include <asm/fpu.h>
 #include <asm/dsp.h>
 
diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c
index 0167d53da30c..a531154cc0f3 100644
--- a/arch/powerpc/kernel/suspend.c
+++ b/arch/powerpc/kernel/suspend.c
@@ -9,9 +9,7 @@
 
 #include <linux/mm.h>
 #include <asm/page.h>
-
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
+#include <asm/sections.h>
 
 /*
  *	pfn_is_nosave - check if given pfn is in the 'nosave' section
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index a7a7537ce1e7..1c4c5accd220 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -13,13 +13,9 @@
 #include <asm/ipl.h>
 #include <asm/cio.h>
 #include <asm/pci.h>
+#include <asm/sections.h>
 #include "entry.h"
 
-/*
- * References to section boundaries
- */
-extern const void __nosave_begin, __nosave_end;
-
 /*
  * The restore of the saved pages in an hibernation image will set
  * the change and referenced bits in the storage key for each page.
diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h
index 1b6199740e98..7a99e6af6372 100644
--- a/arch/sh/include/asm/sections.h
+++ b/arch/sh/include/asm/sections.h
@@ -3,7 +3,6 @@
 
 #include <asm-generic/sections.h>
 
-extern long __nosave_begin, __nosave_end;
 extern long __machvec_start, __machvec_end;
 extern char __uncached_start, __uncached_end;
 extern char __start_eh_frame[], __stop_eh_frame[];
diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c
index 42b0b8ce699a..17bd2e167e07 100644
--- a/arch/sparc/power/hibernate.c
+++ b/arch/sparc/power/hibernate.c
@@ -9,11 +9,9 @@
 #include <asm/hibernate.h>
 #include <asm/visasm.h>
 #include <asm/page.h>
+#include <asm/sections.h>
 #include <asm/tlb.h>
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 struct saved_context saved_context;
 
 /*
diff --git a/arch/unicore32/include/mach/pm.h b/arch/unicore32/include/mach/pm.h
index 4dcd34ae194c..77b522694e74 100644
--- a/arch/unicore32/include/mach/pm.h
+++ b/arch/unicore32/include/mach/pm.h
@@ -36,8 +36,5 @@ extern int puv3_pm_enter(suspend_state_t state);
 /* Defined in hibernate_asm.S */
 extern int restore_image(pgd_t *resume_pg_dir, struct pbe *restore_pblist);
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 extern struct pbe *restore_pblist;
 #endif
diff --git a/arch/unicore32/kernel/hibernate.c b/arch/unicore32/kernel/hibernate.c
index d75ef8b6cb56..9969ec374abb 100644
--- a/arch/unicore32/kernel/hibernate.c
+++ b/arch/unicore32/kernel/hibernate.c
@@ -18,6 +18,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/sections.h>
 #include <asm/suspend.h>
 
 #include "mach/pm.h"
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 7d28c885d238..291226b952a9 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -13,13 +13,11 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmzone.h>
+#include <asm/sections.h>
 
 /* Defined in hibernate_asm_32.S */
 extern int restore_image(void);
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 /* Pointer to the temporary resume page tables */
 pgd_t *resume_pg_dir;
 
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 35e2bb6c0f37..009947d419a6 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -17,11 +17,9 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mtrr.h>
+#include <asm/sections.h>
 #include <asm/suspend.h>
 
-/* References to section boundaries */
-extern __visible const void __nosave_begin, __nosave_end;
-
 /* Defined in hibernate_asm_64.S */
 extern asmlinkage __visible int restore_image(void);
 
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index f1a24b5c3b90..b58fd667f87b 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -3,6 +3,8 @@
 
 /* References to section boundaries */
 
+#include <linux/compiler.h>
+
 /*
  * Usage guidelines:
  * _text, _data: architecture specific, don't use them in arch-independent code
@@ -37,6 +39,8 @@ extern char __start_rodata[], __end_rodata[];
 /* Start and end of .ctors section - used for constructor calls. */
 extern char __ctors_start[], __ctors_end[];
 
+extern __visible const void __nosave_begin, __nosave_end;
+
 /* function descriptor handling (if any).  Override
  * in asm/sections.h */
 #ifndef dereference_function_descriptor
-- 
cgit v1.2.3


From 1fadee0c364572f2b2e098b34001fbaa82ee2e00 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Fri, 10 Oct 2014 09:48:05 +0200
Subject: net/phy: micrel: Add clock support for KSZ8021/KSZ8031

The KSZ8021 and KSZ8031 support RMII reference input clocks of 25MHz
and 50MHz. Both PHYs differ in the default frequency they expect
after reset. If this differs from the actual input clock, then
register 0x1f bit 7 must be changed.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/micrel.txt |  6 +++++
 drivers/net/phy/micrel.c                         | 31 ++++++++++++++++++++++--
 include/linux/micrel_phy.h                       |  1 +
 3 files changed, 36 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/net/micrel.txt b/Documentation/devicetree/bindings/net/micrel.txt
index 98a3e61f9ee8..e1d99b95c4ec 100644
--- a/Documentation/devicetree/bindings/net/micrel.txt
+++ b/Documentation/devicetree/bindings/net/micrel.txt
@@ -16,3 +16,9 @@ Optional properties:
 	      KSZ8051: register 0x1f, bits 5..4
 
               See the respective PHY datasheet for the mode values.
+
+ - clocks, clock-names: contains clocks according to the common clock bindings.
+
+              supported clocks:
+	      - KSZ8021, KSZ8031: "rmii-ref": The RMII refence input clock. Used
+		to determine the XI input clock.
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 011dbda2b2f1..492435fce1d4 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -26,6 +26,7 @@
 #include <linux/phy.h>
 #include <linux/micrel_phy.h>
 #include <linux/of.h>
+#include <linux/clk.h>
 
 /* Operation Mode Strap Override */
 #define MII_KSZPHY_OMSO				0x16
@@ -72,9 +73,12 @@ static int ksz_config_flags(struct phy_device *phydev)
 {
 	int regval;
 
-	if (phydev->dev_flags & MICREL_PHY_50MHZ_CLK) {
+	if (phydev->dev_flags & (MICREL_PHY_50MHZ_CLK | MICREL_PHY_25MHZ_CLK)) {
 		regval = phy_read(phydev, MII_KSZPHY_CTRL);
-		regval |= KSZ8051_RMII_50MHZ_CLK;
+		if (phydev->dev_flags & MICREL_PHY_50MHZ_CLK)
+			regval |= KSZ8051_RMII_50MHZ_CLK;
+		else
+			regval &= ~KSZ8051_RMII_50MHZ_CLK;
 		return phy_write(phydev, MII_KSZPHY_CTRL, regval);
 	}
 	return 0;
@@ -440,6 +444,27 @@ ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
 {
 }
 
+static int ksz8021_probe(struct phy_device *phydev)
+{
+	struct clk *clk;
+
+	clk = devm_clk_get(&phydev->dev, "rmii-ref");
+	if (!IS_ERR(clk)) {
+		unsigned long rate = clk_get_rate(clk);
+
+		if (rate > 24500000 && rate < 25500000) {
+			phydev->dev_flags |= MICREL_PHY_25MHZ_CLK;
+		} else if (rate > 49500000 && rate < 50500000) {
+			phydev->dev_flags |= MICREL_PHY_50MHZ_CLK;
+		} else {
+			dev_err(&phydev->dev, "Clock rate out of range: %ld\n", rate);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static struct phy_driver ksphy_driver[] = {
 {
 	.phy_id		= PHY_ID_KS8737,
@@ -462,6 +487,7 @@ static struct phy_driver ksphy_driver[] = {
 	.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
 			   SUPPORTED_Asym_Pause),
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
+	.probe		= ksz8021_probe,
 	.config_init	= ksz8021_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
@@ -477,6 +503,7 @@ static struct phy_driver ksphy_driver[] = {
 	.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
 			   SUPPORTED_Asym_Pause),
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
+	.probe		= ksz8021_probe,
 	.config_init	= ksz8021_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 2e5b194b9b19..53d33dee70e1 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -37,6 +37,7 @@
 
 /* struct phy_device dev_flags definitions */
 #define MICREL_PHY_50MHZ_CLK	0x00000001
+#define MICREL_PHY_25MHZ_CLK	0x00000002
 
 #define MICREL_KSZ9021_EXTREG_CTRL	0xB
 #define MICREL_KSZ9021_EXTREG_DATA_WRITE	0xC
-- 
cgit v1.2.3


From 810bb172671aec17cf85cc748120cf73c17af372 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 12 Oct 2014 12:45:37 -0400
Subject: take dname_external() into fs/dcache.c

never used outside and it's too low-level for legitimate uses outside
of fs/dcache.c anyway

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 5 +++++
 include/linux/dcache.h | 5 -----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index 8221faae0bef..d5a23fd0da90 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -264,6 +264,11 @@ static void __d_free_external(struct rcu_head *head)
 	kmem_cache_free(dentry_cache, dentry); 
 }
 
+static inline int dname_external(const struct dentry *dentry)
+{
+	return dentry->d_name.name != dentry->d_iname;
+}
+
 static void dentry_free(struct dentry *dentry)
 {
 	if (unlikely(dname_external(dentry))) {
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 81b03150f39a..27a7f00bc89e 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -226,11 +226,6 @@ struct dentry_operations {
 
 extern seqlock_t rename_lock;
 
-static inline int dname_external(const struct dentry *dentry)
-{
-	return dentry->d_name.name != dentry->d_iname;
-}
-
 /*
  * These are the low-level FS interfaces to the dcache..
  */
-- 
cgit v1.2.3


From 7b600f2abb36909e70963cc7c744c15983500bee Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 12 Oct 2014 13:31:58 -0400
Subject: don't need that forward declaration of struct nameidata in dcache.h
 anymore

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/dcache.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 27a7f00bc89e..b2a2a08523bf 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -11,7 +11,6 @@
 #include <linux/rcupdate.h>
 #include <linux/lockref.h>
 
-struct nameidata;
 struct path;
 struct vfsmount;
 
-- 
cgit v1.2.3


From dfda0df3426483cf5fc7441f23f318edbabecb03 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Wed, 6 Aug 2014 16:26:21 +1000
Subject: drm/mst: rework payload table allocation to conform better.

The old code has problems with the Dell MST monitors due to some
assumptions I made that weren't true.

I initially thought the Virtual Channel Payload IDs had to be in
the DPCD table in ascending order, however it appears that assumption
is bogus.

The old code also assumed it was possible to insert a member
into the table and it would move other members up, like it does
when you remove table entries, however reality has shown this
isn't true.

So the new code allocates VCPIs separate from entries in the payload
tracking table, and when we remove an entry from the DPCD table,
I shuffle the tracking payload entries around in the struct.

This appears to make VT switch more robust (still not perfect)
with an MST enabled Dell monitor.

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_dp_mst_topology.c | 77 ++++++++++++++++++++++++++---------
 include/drm/drm_dp_mst_helper.h       |  2 +
 2 files changed, 59 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index b3adf1445020..070f913d2dba 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -682,7 +682,7 @@ static int build_allocate_payload(struct drm_dp_sideband_msg_tx *msg, int port_n
 static int drm_dp_mst_assign_payload_id(struct drm_dp_mst_topology_mgr *mgr,
 					struct drm_dp_vcpi *vcpi)
 {
-	int ret;
+	int ret, vcpi_ret;
 
 	mutex_lock(&mgr->payload_lock);
 	ret = find_first_zero_bit(&mgr->payload_mask, mgr->max_payloads + 1);
@@ -692,8 +692,16 @@ static int drm_dp_mst_assign_payload_id(struct drm_dp_mst_topology_mgr *mgr,
 		goto out_unlock;
 	}
 
+	vcpi_ret = find_first_zero_bit(&mgr->vcpi_mask, mgr->max_payloads + 1);
+	if (vcpi_ret > mgr->max_payloads) {
+		ret = -EINVAL;
+		DRM_DEBUG_KMS("out of vcpi ids %d\n", ret);
+		goto out_unlock;
+	}
+
 	set_bit(ret, &mgr->payload_mask);
-	vcpi->vcpi = ret;
+	set_bit(vcpi_ret, &mgr->vcpi_mask);
+	vcpi->vcpi = vcpi_ret + 1;
 	mgr->proposed_vcpis[ret - 1] = vcpi;
 out_unlock:
 	mutex_unlock(&mgr->payload_lock);
@@ -701,15 +709,23 @@ out_unlock:
 }
 
 static void drm_dp_mst_put_payload_id(struct drm_dp_mst_topology_mgr *mgr,
-				      int id)
+				      int vcpi)
 {
-	if (id == 0)
+	int i;
+	if (vcpi == 0)
 		return;
 
 	mutex_lock(&mgr->payload_lock);
-	DRM_DEBUG_KMS("putting payload %d\n", id);
-	clear_bit(id, &mgr->payload_mask);
-	mgr->proposed_vcpis[id - 1] = NULL;
+	DRM_DEBUG_KMS("putting payload %d\n", vcpi);
+	clear_bit(vcpi - 1, &mgr->vcpi_mask);
+
+	for (i = 0; i < mgr->max_payloads; i++) {
+		if (mgr->proposed_vcpis[i])
+			if (mgr->proposed_vcpis[i]->vcpi == vcpi) {
+				mgr->proposed_vcpis[i] = NULL;
+				clear_bit(i + 1, &mgr->payload_mask);
+			}
+	}
 	mutex_unlock(&mgr->payload_lock);
 }
 
@@ -1563,7 +1579,7 @@ static int drm_dp_destroy_payload_step1(struct drm_dp_mst_topology_mgr *mgr,
 	}
 
 	drm_dp_dpcd_write_payload(mgr, id, payload);
-	payload->payload_state = 0;
+	payload->payload_state = DP_PAYLOAD_DELETE_LOCAL;
 	return 0;
 }
 
@@ -1590,7 +1606,7 @@ static int drm_dp_destroy_payload_step2(struct drm_dp_mst_topology_mgr *mgr,
  */
 int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 {
-	int i;
+	int i, j;
 	int cur_slots = 1;
 	struct drm_dp_payload req_payload;
 	struct drm_dp_mst_port *port;
@@ -1607,26 +1623,46 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 			port = NULL;
 			req_payload.num_slots = 0;
 		}
+
+		if (mgr->payloads[i].start_slot != req_payload.start_slot) {
+			mgr->payloads[i].start_slot = req_payload.start_slot;
+		}
 		/* work out what is required to happen with this payload */
-		if (mgr->payloads[i].start_slot != req_payload.start_slot ||
-		    mgr->payloads[i].num_slots != req_payload.num_slots) {
+		if (mgr->payloads[i].num_slots != req_payload.num_slots) {
 
 			/* need to push an update for this payload */
 			if (req_payload.num_slots) {
-				drm_dp_create_payload_step1(mgr, i + 1, &req_payload);
+				drm_dp_create_payload_step1(mgr, mgr->proposed_vcpis[i]->vcpi, &req_payload);
 				mgr->payloads[i].num_slots = req_payload.num_slots;
 			} else if (mgr->payloads[i].num_slots) {
 				mgr->payloads[i].num_slots = 0;
-				drm_dp_destroy_payload_step1(mgr, port, i + 1, &mgr->payloads[i]);
+				drm_dp_destroy_payload_step1(mgr, port, port->vcpi.vcpi, &mgr->payloads[i]);
 				req_payload.payload_state = mgr->payloads[i].payload_state;
-			} else
-				req_payload.payload_state = 0;
-
-			mgr->payloads[i].start_slot = req_payload.start_slot;
+				mgr->payloads[i].start_slot = 0;
+			}
 			mgr->payloads[i].payload_state = req_payload.payload_state;
 		}
 		cur_slots += req_payload.num_slots;
 	}
+
+	for (i = 0; i < mgr->max_payloads; i++) {
+		if (mgr->payloads[i].payload_state == DP_PAYLOAD_DELETE_LOCAL) {
+			DRM_DEBUG_KMS("removing payload %d\n", i);
+			for (j = i; j < mgr->max_payloads - 1; j++) {
+				memcpy(&mgr->payloads[j], &mgr->payloads[j + 1], sizeof(struct drm_dp_payload));
+				mgr->proposed_vcpis[j] = mgr->proposed_vcpis[j + 1];
+				if (mgr->proposed_vcpis[j] && mgr->proposed_vcpis[j]->num_slots) {
+					set_bit(j + 1, &mgr->payload_mask);
+				} else {
+					clear_bit(j + 1, &mgr->payload_mask);
+				}
+			}
+			memset(&mgr->payloads[mgr->max_payloads - 1], 0, sizeof(struct drm_dp_payload));
+			mgr->proposed_vcpis[mgr->max_payloads - 1] = NULL;
+			clear_bit(mgr->max_payloads, &mgr->payload_mask);
+
+		}
+	}
 	mutex_unlock(&mgr->payload_lock);
 
 	return 0;
@@ -1657,9 +1693,9 @@ int drm_dp_update_payload_part2(struct drm_dp_mst_topology_mgr *mgr)
 
 		DRM_DEBUG_KMS("payload %d %d\n", i, mgr->payloads[i].payload_state);
 		if (mgr->payloads[i].payload_state == DP_PAYLOAD_LOCAL) {
-			ret = drm_dp_create_payload_step2(mgr, port, i + 1, &mgr->payloads[i]);
+			ret = drm_dp_create_payload_step2(mgr, port, mgr->proposed_vcpis[i]->vcpi, &mgr->payloads[i]);
 		} else if (mgr->payloads[i].payload_state == DP_PAYLOAD_DELETE_LOCAL) {
-			ret = drm_dp_destroy_payload_step2(mgr, i + 1, &mgr->payloads[i]);
+			ret = drm_dp_destroy_payload_step2(mgr, mgr->proposed_vcpis[i]->vcpi, &mgr->payloads[i]);
 		}
 		if (ret) {
 			mutex_unlock(&mgr->payload_lock);
@@ -1861,6 +1897,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 		memset(mgr->payloads, 0, mgr->max_payloads * sizeof(struct drm_dp_payload));
 		mgr->payload_mask = 0;
 		set_bit(0, &mgr->payload_mask);
+		mgr->vcpi_mask = 0;
 	}
 
 out_unlock:
@@ -2475,7 +2512,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 	mutex_unlock(&mgr->lock);
 
 	mutex_lock(&mgr->payload_lock);
-	seq_printf(m, "vcpi: %lx\n", mgr->payload_mask);
+	seq_printf(m, "vcpi: %lx %lx\n", mgr->payload_mask, mgr->vcpi_mask);
 
 	for (i = 0; i < mgr->max_payloads; i++) {
 		if (mgr->proposed_vcpis[i]) {
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index 9b446ada2532..338fc1053835 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -388,6 +388,7 @@ struct drm_dp_payload {
 	int payload_state;
 	int start_slot;
 	int num_slots;
+	int vcpi;
 };
 
 /**
@@ -454,6 +455,7 @@ struct drm_dp_mst_topology_mgr {
 	struct drm_dp_vcpi **proposed_vcpis;
 	struct drm_dp_payload *payloads;
 	unsigned long payload_mask;
+	unsigned long vcpi_mask;
 
 	wait_queue_head_t tx_waitq;
 	struct work_struct work;
-- 
cgit v1.2.3


From 71458cfc782eafe4b27656e078d379a34e472adf Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Mon, 13 Oct 2014 15:51:05 -0700
Subject: kernel: add support for gcc 5

We're missing include/linux/compiler-gcc5.h which is required now
because gcc branched off to v5 in trunk.

Just copy the relevant bits out of include/linux/compiler-gcc4.h,
no new code is added as of now.

This fixes a build error when using gcc 5.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler-gcc5.h | 66 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)
 create mode 100644 include/linux/compiler-gcc5.h

(limited to 'include')

diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h
new file mode 100644
index 000000000000..cdd1cc202d51
--- /dev/null
+++ b/include/linux/compiler-gcc5.h
@@ -0,0 +1,66 @@
+#ifndef __LINUX_COMPILER_H
+#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead."
+#endif
+
+#define __used				__attribute__((__used__))
+#define __must_check			__attribute__((warn_unused_result))
+#define __compiler_offsetof(a, b)	__builtin_offsetof(a, b)
+
+/* Mark functions as cold. gcc will assume any path leading to a call
+   to them will be unlikely.  This means a lot of manual unlikely()s
+   are unnecessary now for any paths leading to the usual suspects
+   like BUG(), printk(), panic() etc. [but let's keep them for now for
+   older compilers]
+
+   Early snapshots of gcc 4.3 don't support this and we can't detect this
+   in the preprocessor, but we can live with this because they're unreleased.
+   Maketime probing would be overkill here.
+
+   gcc also has a __attribute__((__hot__)) to move hot functions into
+   a special section, but I don't see any sense in this right now in
+   the kernel context */
+#define __cold			__attribute__((__cold__))
+
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+#ifndef __CHECKER__
+# define __compiletime_warning(message) __attribute__((warning(message)))
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif /* __CHECKER__ */
+
+/*
+ * Mark a position in code as unreachable.  This can be used to
+ * suppress control flow warnings after asm blocks that transfer
+ * control elsewhere.
+ *
+ * Early snapshots of gcc 4.5 don't support this and we can't detect
+ * this in the preprocessor, but we can live with this because they're
+ * unreleased.  Really, we need to have autoconf for the kernel.
+ */
+#define unreachable() __builtin_unreachable()
+
+/* Mark a function definition as prohibited from being cloned. */
+#define __noclone	__attribute__((__noclone__))
+
+/*
+ * Tell the optimizer that something else uses this function or variable.
+ */
+#define __visible __attribute__((externally_visible))
+
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ *   http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
+
+#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+#define __HAVE_BUILTIN_BSWAP32__
+#define __HAVE_BUILTIN_BSWAP64__
+#define __HAVE_BUILTIN_BSWAP16__
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
-- 
cgit v1.2.3


From de9e14eebf33a60712a52a0bc6e08c043c0aba53 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Mon, 13 Oct 2014 15:51:09 -0700
Subject: drivers: dma-contiguous: add initialization from device tree

Add a function to create CMA region from previously reserved memory and
add support for handling 'shared-dma-pool' reserved-memory device tree
nodes.

Based on previous code provided by Josh Cartwright <joshc@codeaurora.org>

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Laura Abbott <lauraa@codeaurora.org>
Cc: Josh Cartwright <joshc@codeaurora.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/dma-contiguous.c | 66 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/cma.h           |  3 ++
 mm/cma.c                      | 62 ++++++++++++++++++++++++++++++++--------
 3 files changed, 120 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 6606abdf880c..473ff4892401 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -211,3 +211,69 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 {
 	return cma_release(dev_get_cma_area(dev), pages, count);
 }
+
+/*
+ * Support for reserved memory regions defined in device tree
+ */
+#ifdef CONFIG_OF_RESERVED_MEM
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+static void rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
+{
+	dev_set_cma_area(dev, rmem->priv);
+}
+
+static void rmem_cma_device_release(struct reserved_mem *rmem,
+				    struct device *dev)
+{
+	dev_set_cma_area(dev, NULL);
+}
+
+static const struct reserved_mem_ops rmem_cma_ops = {
+	.device_init	= rmem_cma_device_init,
+	.device_release = rmem_cma_device_release,
+};
+
+static int __init rmem_cma_setup(struct reserved_mem *rmem)
+{
+	phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+	phys_addr_t mask = align - 1;
+	unsigned long node = rmem->fdt_node;
+	struct cma *cma;
+	int err;
+
+	if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
+	    of_get_flat_dt_prop(node, "no-map", NULL))
+		return -EINVAL;
+
+	if ((rmem->base & mask) || (rmem->size & mask)) {
+		pr_err("Reserved memory: incorrect alignment of CMA region\n");
+		return -EINVAL;
+	}
+
+	err = cma_init_reserved_mem(rmem->base, rmem->size, 0, &cma);
+	if (err) {
+		pr_err("Reserved memory: unable to setup CMA region\n");
+		return err;
+	}
+	/* Architecture specific contiguous memory fixup. */
+	dma_contiguous_early_fixup(rmem->base, rmem->size);
+
+	if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
+		dma_contiguous_set_default(cma);
+
+	rmem->ops = &rmem_cma_ops;
+	rmem->priv = cma;
+
+	pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n",
+		&rmem->base, (unsigned long)rmem->size / SZ_1M);
+
+	return 0;
+}
+RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup);
+#endif
diff --git a/include/linux/cma.h b/include/linux/cma.h
index 371b93042520..0430ed05d3b9 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -22,6 +22,9 @@ extern int __init cma_declare_contiguous(phys_addr_t size,
 			phys_addr_t base, phys_addr_t limit,
 			phys_addr_t alignment, unsigned int order_per_bit,
 			bool fixed, struct cma **res_cma);
+extern int cma_init_reserved_mem(phys_addr_t size,
+					phys_addr_t base, int order_per_bit,
+					struct cma **res_cma);
 extern struct page *cma_alloc(struct cma *cma, int count, unsigned int align);
 extern bool cma_release(struct cma *cma, struct page *pages, int count);
 #endif
diff --git a/mm/cma.c b/mm/cma.c
index a951a3b3ed36..963bc4add9af 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -142,6 +142,54 @@ static int __init cma_init_reserved_areas(void)
 }
 core_initcall(cma_init_reserved_areas);
 
+/**
+ * cma_init_reserved_mem() - create custom contiguous area from reserved memory
+ * @base: Base address of the reserved area
+ * @size: Size of the reserved area (in bytes),
+ * @order_per_bit: Order of pages represented by one bit on bitmap.
+ * @res_cma: Pointer to store the created cma region.
+ *
+ * This function creates custom contiguous area from already reserved memory.
+ */
+int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
+				 int order_per_bit, struct cma **res_cma)
+{
+	struct cma *cma;
+	phys_addr_t alignment;
+
+	/* Sanity checks */
+	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
+		pr_err("Not enough slots for CMA reserved regions!\n");
+		return -ENOSPC;
+	}
+
+	if (!size || !memblock_is_region_reserved(base, size))
+		return -EINVAL;
+
+	/* ensure minimal alignment requied by mm core */
+	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+
+	/* alignment should be aligned with order_per_bit */
+	if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit))
+		return -EINVAL;
+
+	if (ALIGN(base, alignment) != base || ALIGN(size, alignment) != size)
+		return -EINVAL;
+
+	/*
+	 * Each reserved area must be initialised later, when more kernel
+	 * subsystems (like slab allocator) are available.
+	 */
+	cma = &cma_areas[cma_area_count];
+	cma->base_pfn = PFN_DOWN(base);
+	cma->count = size >> PAGE_SHIFT;
+	cma->order_per_bit = order_per_bit;
+	*res_cma = cma;
+	cma_area_count++;
+
+	return 0;
+}
+
 /**
  * cma_declare_contiguous() - reserve custom contiguous area
  * @base: Base address of the reserved area optional, use 0 for any
@@ -165,7 +213,6 @@ int __init cma_declare_contiguous(phys_addr_t base,
 			phys_addr_t alignment, unsigned int order_per_bit,
 			bool fixed, struct cma **res_cma)
 {
-	struct cma *cma;
 	phys_addr_t memblock_end = memblock_end_of_DRAM();
 	phys_addr_t highmem_start = __pa(high_memory);
 	int ret = 0;
@@ -237,16 +284,9 @@ int __init cma_declare_contiguous(phys_addr_t base,
 		}
 	}
 
-	/*
-	 * Each reserved area must be initialised later, when more kernel
-	 * subsystems (like slab allocator) are available.
-	 */
-	cma = &cma_areas[cma_area_count];
-	cma->base_pfn = PFN_DOWN(base);
-	cma->count = size >> PAGE_SHIFT;
-	cma->order_per_bit = order_per_bit;
-	*res_cma = cma;
-	cma_area_count++;
+	ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma);
+	if (ret)
+		goto err;
 
 	pr_info("Reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
 		(unsigned long)base);
-- 
cgit v1.2.3


From 8b21d9ca17ff8ed0dbf650f4162ee2d59bb5a881 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.m@jp.panasonic.com>
Date: Mon, 13 Oct 2014 15:51:30 -0700
Subject: list: include linux/kernel.h

linux/list.h uses container_of, therefore it depends on linux/kernel.h.

Signed-off-by: Masahiro Yamada <yamada.m@jp.panasonic.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/list.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/list.h b/include/linux/list.h
index cbbb96fcead9..f33f831eb3c8 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -5,6 +5,7 @@
 #include <linux/stddef.h>
 #include <linux/poison.h>
 #include <linux/const.h>
+#include <linux/kernel.h>
 
 /*
  * Simple doubly linked list implementation.
-- 
cgit v1.2.3


From 6de8ab68bc30da75116209d818c75497bdaed09d Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Mon, 13 Oct 2014 15:51:36 -0700
Subject: lib: remove prio_heap

The prio_heap code is unused since commit 889ed9ceaa97 ("cgroup: remove
css_scan_tasks()").  It should be compiled out to shrink the binary
kernel size which can be done via introducing CONFIG_PRIO_HEAD or by
removing the code.

We can simply recover the code from git when needed, so it would be
better to remove it IMO.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Francesco Fusco <ffusco@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: George Spelvin <linux@horizon.com>
Cc: Mark Salter <msalter@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/prio_heap.h | 58 ---------------------------------------
 lib/Makefile              |  2 +-
 lib/prio_heap.c           | 70 -----------------------------------------------
 3 files changed, 1 insertion(+), 129 deletions(-)
 delete mode 100644 include/linux/prio_heap.h
 delete mode 100644 lib/prio_heap.c

(limited to 'include')

diff --git a/include/linux/prio_heap.h b/include/linux/prio_heap.h
deleted file mode 100644
index 08094350f26a..000000000000
--- a/include/linux/prio_heap.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef _LINUX_PRIO_HEAP_H
-#define _LINUX_PRIO_HEAP_H
-
-/*
- * Simple insertion-only static-sized priority heap containing
- * pointers, based on CLR, chapter 7
- */
-
-#include <linux/gfp.h>
-
-/**
- * struct ptr_heap - simple static-sized priority heap
- * @ptrs - pointer to data area
- * @max - max number of elements that can be stored in @ptrs
- * @size - current number of valid elements in @ptrs (in the range 0..@size-1
- * @gt: comparison operator, which should implement "greater than"
- */
-struct ptr_heap {
-	void **ptrs;
-	int max;
-	int size;
-	int (*gt)(void *, void *);
-};
-
-/**
- * heap_init - initialize an empty heap with a given memory size
- * @heap: the heap structure to be initialized
- * @size: amount of memory to use in bytes
- * @gfp_mask: mask to pass to kmalloc()
- * @gt: comparison operator, which should implement "greater than"
- */
-extern int heap_init(struct ptr_heap *heap, size_t size, gfp_t gfp_mask,
-		     int (*gt)(void *, void *));
-
-/**
- * heap_free - release a heap's storage
- * @heap: the heap structure whose data should be released
- */
-void heap_free(struct ptr_heap *heap);
-
-/**
- * heap_insert - insert a value into the heap and return any overflowed value
- * @heap: the heap to be operated on
- * @p: the pointer to be inserted
- *
- * Attempts to insert the given value into the priority heap. If the
- * heap is full prior to the insertion, then the resulting heap will
- * consist of the smallest @max elements of the original heap and the
- * new element; the greatest element will be removed from the heap and
- * returned. Note that the returned element will be the new element
- * (i.e. no change to the heap) if the new element is greater than all
- * elements currently in the heap.
- */
-extern void *heap_insert(struct ptr_heap *heap, void *p);
-
-
-
-#endif /* _LINUX_PRIO_HEAP_H */
diff --git a/lib/Makefile b/lib/Makefile
index d6b4bc496408..eb95e0fdcca5 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -11,7 +11,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o timerqueue.o\
 	 idr.o int_sqrt.o extable.o \
 	 sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
-	 proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
+	 proportions.o flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o
 
diff --git a/lib/prio_heap.c b/lib/prio_heap.c
deleted file mode 100644
index a7af6f85eca8..000000000000
--- a/lib/prio_heap.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Simple insertion-only static-sized priority heap containing
- * pointers, based on CLR, chapter 7
- */
-
-#include <linux/slab.h>
-#include <linux/prio_heap.h>
-
-int heap_init(struct ptr_heap *heap, size_t size, gfp_t gfp_mask,
-	      int (*gt)(void *, void *))
-{
-	heap->ptrs = kmalloc(size, gfp_mask);
-	if (!heap->ptrs)
-		return -ENOMEM;
-	heap->size = 0;
-	heap->max = size / sizeof(void *);
-	heap->gt = gt;
-	return 0;
-}
-
-void heap_free(struct ptr_heap *heap)
-{
-	kfree(heap->ptrs);
-}
-
-void *heap_insert(struct ptr_heap *heap, void *p)
-{
-	void *res;
-	void **ptrs = heap->ptrs;
-	int pos;
-
-	if (heap->size < heap->max) {
-		/* Heap insertion */
-		pos = heap->size++;
-		while (pos > 0 && heap->gt(p, ptrs[(pos-1)/2])) {
-			ptrs[pos] = ptrs[(pos-1)/2];
-			pos = (pos-1)/2;
-		}
-		ptrs[pos] = p;
-		return NULL;
-	}
-
-	/* The heap is full, so something will have to be dropped */
-
-	/* If the new pointer is greater than the current max, drop it */
-	if (heap->gt(p, ptrs[0]))
-		return p;
-
-	/* Replace the current max and heapify */
-	res = ptrs[0];
-	ptrs[0] = p;
-	pos = 0;
-
-	while (1) {
-		int left = 2 * pos + 1;
-		int right = 2 * pos + 2;
-		int largest = pos;
-		if (left < heap->size && heap->gt(ptrs[left], p))
-			largest = left;
-		if (right < heap->size && heap->gt(ptrs[right], ptrs[largest]))
-			largest = right;
-		if (largest == pos)
-			break;
-		/* Push p down the heap one level and bump one up */
-		ptrs[pos] = ptrs[largest];
-		ptrs[largest] = p;
-		pos = largest;
-	}
-	return res;
-}
-- 
cgit v1.2.3


From 1c3bea0e71892ef9100c01d3799cdae8cac273ef Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 13 Oct 2014 15:53:33 -0700
Subject: signal: use BUILD_BUG() instead of _NSIG_WORDS_is_unsupported_size()

Kill _NSIG_WORDS_is_unsupported_size(), use BUILD_BUG() instead.  This
simplifies the code, avoids the nested-externs warnings, and this way we
do not defer the problem to linker.

Also, fix the indentation in _SIG_SET_BINOP() and _SIG_SET_OP().

Note: this patch assumes that the code like "if (0) BUILD_BUG();" is
valid.  If not (say __compiletime_error() is not defined and thus
__compiletime_error_fallback() uses a negative array) we should fix
BUILD_BUG() and/or BUILD_BUG_ON_MSG().  This code should be fine by
definition, this is the documented purpose of BUILD_BUG().

[sfr@canb.auug.org.au: fix powerpc build failures]
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/signal.h | 29 +++++++++++++----------------
 1 file changed, 13 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/signal.h b/include/linux/signal.h
index 750196fcc0a5..ab1e0392b5ac 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -2,6 +2,7 @@
 #define _LINUX_SIGNAL_H
 
 #include <linux/list.h>
+#include <linux/bug.h>
 #include <uapi/linux/signal.h>
 
 struct task_struct;
@@ -67,7 +68,6 @@ static inline int sigismember(sigset_t *set, int _sig)
 
 static inline int sigisemptyset(sigset_t *set)
 {
-	extern void _NSIG_WORDS_is_unsupported_size(void);
 	switch (_NSIG_WORDS) {
 	case 4:
 		return (set->sig[3] | set->sig[2] |
@@ -77,7 +77,7 @@ static inline int sigisemptyset(sigset_t *set)
 	case 1:
 		return set->sig[0] == 0;
 	default:
-		_NSIG_WORDS_is_unsupported_size();
+		BUILD_BUG();
 		return 0;
 	}
 }
@@ -90,24 +90,23 @@ static inline int sigisemptyset(sigset_t *set)
 #define _SIG_SET_BINOP(name, op)					\
 static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \
 {									\
-	extern void _NSIG_WORDS_is_unsupported_size(void);		\
 	unsigned long a0, a1, a2, a3, b0, b1, b2, b3;			\
 									\
 	switch (_NSIG_WORDS) {						\
-	    case 4:							\
+	case 4:								\
 		a3 = a->sig[3]; a2 = a->sig[2];				\
 		b3 = b->sig[3]; b2 = b->sig[2];				\
 		r->sig[3] = op(a3, b3);					\
 		r->sig[2] = op(a2, b2);					\
-	    case 2:							\
+	case 2:								\
 		a1 = a->sig[1]; b1 = b->sig[1];				\
 		r->sig[1] = op(a1, b1);					\
-	    case 1:							\
+	case 1:								\
 		a0 = a->sig[0]; b0 = b->sig[0];				\
 		r->sig[0] = op(a0, b0);					\
 		break;							\
-	    default:							\
-		_NSIG_WORDS_is_unsupported_size();			\
+	default:							\
+		BUILD_BUG();						\
 	}								\
 }
 
@@ -128,16 +127,14 @@ _SIG_SET_BINOP(sigandnsets, _sig_andn)
 #define _SIG_SET_OP(name, op)						\
 static inline void name(sigset_t *set)					\
 {									\
-	extern void _NSIG_WORDS_is_unsupported_size(void);		\
-									\
 	switch (_NSIG_WORDS) {						\
-	    case 4: set->sig[3] = op(set->sig[3]);			\
-		    set->sig[2] = op(set->sig[2]);			\
-	    case 2: set->sig[1] = op(set->sig[1]);			\
-	    case 1: set->sig[0] = op(set->sig[0]);			\
+	case 4:	set->sig[3] = op(set->sig[3]);				\
+		set->sig[2] = op(set->sig[2]);				\
+	case 2:	set->sig[1] = op(set->sig[1]);				\
+	case 1:	set->sig[0] = op(set->sig[0]);				\
 		    break;						\
-	    default:							\
-		_NSIG_WORDS_is_unsupported_size();			\
+	default:							\
+		BUILD_BUG();						\
 	}								\
 }
 
-- 
cgit v1.2.3


From 669280a152ce5144321c0e511498877383f34393 Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Mon, 13 Oct 2014 15:53:40 -0700
Subject: kexec: take the segment adding out of locate_mem_hole functions

In locate_mem_hole functions, a memory hole is located and added as
kexec_segment.  But from the name of locate_mem_hole, it should only take
responsibility of searching a available memory hole to contain data of a
specified size.

So in this patch add a new field 'mem' into kexec_buf, then take that
kexec segment adding code out of locate_mem_hole_top_down and
locate_mem_hole_bottom_up.  This make clear of the functionality of
locate_mem_hole just like it declars to do.  And by this
locate_mem_hole_callback chould be used later if anyone want to locate a
memory hole for other use.

Meanwhile Vivek suggested opening code function __kexec_add_segment(),
that way we have to retreive ksegment pointer once and it is easy to read.
 So just do it in this patch and remove __kexec_add_segment() since no one
use it anymore.

Signed-off-by: Baoquan He <bhe@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kexec.h |  1 +
 kernel/kexec.c        | 29 ++++++++---------------------
 2 files changed, 9 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 4b2a0e11cc5b..9d957b7ae095 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -178,6 +178,7 @@ struct kexec_buf {
 	struct kimage *image;
 	char *buffer;
 	unsigned long bufsz;
+	unsigned long mem;
 	unsigned long memsz;
 	unsigned long buf_align;
 	unsigned long buf_min;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 2bee072268d9..63bc3cdfb629 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -2016,22 +2016,6 @@ static int __init crash_save_vmcoreinfo_init(void)
 subsys_initcall(crash_save_vmcoreinfo_init);
 
 #ifdef CONFIG_KEXEC_FILE
-static int __kexec_add_segment(struct kimage *image, char *buf,
-			       unsigned long bufsz, unsigned long mem,
-			       unsigned long memsz)
-{
-	struct kexec_segment *ksegment;
-
-	ksegment = &image->segment[image->nr_segments];
-	ksegment->kbuf = buf;
-	ksegment->bufsz = bufsz;
-	ksegment->mem = mem;
-	ksegment->memsz = memsz;
-	image->nr_segments++;
-
-	return 0;
-}
-
 static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
 				    struct kexec_buf *kbuf)
 {
@@ -2064,8 +2048,7 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
 	} while (1);
 
 	/* If we are here, we found a suitable memory range */
-	__kexec_add_segment(image, kbuf->buffer, kbuf->bufsz, temp_start,
-			    kbuf->memsz);
+	kbuf->mem = temp_start;
 
 	/* Success, stop navigating through remaining System RAM ranges */
 	return 1;
@@ -2099,8 +2082,7 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
 	} while (1);
 
 	/* If we are here, we found a suitable memory range */
-	__kexec_add_segment(image, kbuf->buffer, kbuf->bufsz, temp_start,
-			    kbuf->memsz);
+	kbuf->mem = temp_start;
 
 	/* Success, stop navigating through remaining System RAM ranges */
 	return 1;
@@ -2187,7 +2169,12 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	}
 
 	/* Found a suitable memory range */
-	ksegment = &image->segment[image->nr_segments - 1];
+	ksegment = &image->segment[image->nr_segments];
+	ksegment->kbuf = kbuf->buffer;
+	ksegment->bufsz = kbuf->bufsz;
+	ksegment->mem = kbuf->mem;
+	ksegment->memsz = kbuf->memsz;
+	image->nr_segments++;
 	*load_addr = ksegment->mem;
 	return 0;
 }
-- 
cgit v1.2.3


From a841b65921a959c759da6b5c8d5dc21966b4cf86 Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Mon, 13 Oct 2014 15:53:48 -0700
Subject: rbtree: add comment to rb_insert_augmented()

The comment is copied from Documentation/rbtree.txt, but this comment is
so important that it should also be in the code.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/rbtree_augmented.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index fea49b5da12a..378c5ee75f78 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -43,6 +43,16 @@ struct rb_augment_callbacks {
 
 extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+/*
+ * Fixup the rbtree and update the augmented information when rebalancing.
+ *
+ * On insertion, the user must update the augmented information on the path
+ * leading to the inserted node, then call rb_link_node() as usual and
+ * rb_augment_inserted() instead of the usual rb_insert_color() call.
+ * If rb_augment_inserted() rebalances the rbtree, it will callback into
+ * a user provided function to update the augmented information on the
+ * affected subtrees.
+ */
 static inline void
 rb_insert_augmented(struct rb_node *node, struct rb_root *root,
 		    const struct rb_augment_callbacks *augment)
-- 
cgit v1.2.3


From 67cf13ceed89e2c1a967719e98624a20c48dfb5a Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Mon, 13 Oct 2014 15:54:03 -0700
Subject: x86: optimize resource lookups for ioremap

We have a large university system in the UK that is experiencing very long
delays modprobing the driver for a specific I/O device.  The delay is from
8-10 minutes per device and there are 31 devices in the system.  This 4 to
5 hour delay in starting up those I/O devices is very much a burden on the
customer.

There are two causes for requiring a restart/reload of the drivers.  First
is periodic preventive maintenance (PM) and the second is if any of the
devices experience a fatal error.  Both of these trigger this excessively
long delay in bringing the system back up to full capability.

The problem was tracked down to a very slow IOREMAP operation and the
excessively long ioresource lookup to insure that the user is not
attempting to ioremap RAM.  These patches provide a speed up to that
function.

The modprobe time appears to be affected quite a bit by previous activity
on the ioresource list, which I suspect is due to cache preloading.  While
the overall improvement is impacted by other overhead of starting the
devices, this drastically improves the modprobe time.

Also our system is considerably smaller so the percentages gained will not
be the same.  Best case improvement with the modprobe on our 20 device
smallish system was from 'real 5m51.913s' to 'real 0m18.275s'.

This patch (of 2):

Since the ioremap operation is verifying that the specified address range
is NOT RAM, it will search the entire ioresource list if the condition is
true.  To make matters worse, it does this one 4k page at a time.  For a
128M BAR region this is 32 passes to determine the entire region does not
contain any RAM addresses.

This patch provides another resource lookup function, region_is_ram, that
searches for the entire region specified, verifying that it is completely
contained within the resource region.  If it is found, then it is checked
to be RAM or not, within a single pass.

The return result reflects if it was found or not (-1), and whether it is
RAM (1) or not (0).  This allows the caller to fallback to the previous
page by page search if it was not found.

[akpm@linux-foundation.org: fix spellos and typos in comment]
Signed-off-by: Mike Travis <travis@sgi.com>
Acked-by: Alex Thorlton <athorlton@sgi.com>
Reviewed-by: Cliff Wickman <cpw@sgi.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  1 +
 kernel/resource.c  | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fa0d74e06428..4cd45cb95e6d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -347,6 +347,7 @@ static inline int put_page_unless_one(struct page *page)
 }
 
 extern int page_is_ram(unsigned long pfn);
+extern int region_is_ram(resource_size_t phys_addr, unsigned long size);
 
 /* Support for virtually mapped pages */
 struct page *vmalloc_to_page(const void *addr);
diff --git a/kernel/resource.c b/kernel/resource.c
index 46322019ab7d..0bcebffc4e77 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -491,6 +491,42 @@ int __weak page_is_ram(unsigned long pfn)
 }
 EXPORT_SYMBOL_GPL(page_is_ram);
 
+/*
+ * Search for a resouce entry that fully contains the specified region.
+ * If found, return 1 if it is RAM, 0 if not.
+ * If not found, or region is not fully contained, return -1
+ *
+ * Used by the ioremap functions to ensure the user is not remapping RAM and is
+ * a vast speed up over walking through the resource table page by page.
+ */
+int region_is_ram(resource_size_t start, unsigned long size)
+{
+	struct resource *p;
+	resource_size_t end = start + size - 1;
+	int flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	const char *name = "System RAM";
+	int ret = -1;
+
+	read_lock(&resource_lock);
+	for (p = iomem_resource.child; p ; p = p->sibling) {
+		if (end < p->start)
+			continue;
+
+		if (p->start <= start && end <= p->end) {
+			/* resource fully contains region */
+			if ((p->flags != flags) || strcmp(p->name, name))
+				ret = 0;
+			else
+				ret = 1;
+			break;
+		}
+		if (p->end < start)
+			break;	/* not found */
+	}
+	read_unlock(&resource_lock);
+	return ret;
+}
+
 void __weak arch_remove_reservations(struct resource *avail)
 {
 }
-- 
cgit v1.2.3


From b0bfb63118612e3614cf77b115c00f895a42c96a Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Mon, 13 Oct 2014 15:54:27 -0700
Subject: lib: string: Make all calls to strnicmp into calls to strncasecmp

The previous patch made strnicmp into a wrapper for strncasecmp.

This patch makes all in-tree users of strnicmp call strncasecmp
directly, while still making sure that the strnicmp symbol can be used
by out-of-tree modules.  It should be considered a temporary hack until
all in-tree callers have been converted.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/string.h | 2 +-
 lib/string.c           | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/string.h b/include/linux/string.h
index d36977e029af..e6edfe51575a 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -41,7 +41,7 @@ extern int strcmp(const char *,const char *);
 extern int strncmp(const char *,const char *,__kernel_size_t);
 #endif
 #ifndef __HAVE_ARCH_STRNICMP
-extern int strnicmp(const char *, const char *, __kernel_size_t);
+#define strnicmp strncasecmp
 #endif
 #ifndef __HAVE_ARCH_STRCASECMP
 extern int strcasecmp(const char *s1, const char *s2);
diff --git a/lib/string.c b/lib/string.c
index 3181e267a033..2fc20aa06f84 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -59,6 +59,7 @@ int strncasecmp(const char *s1, const char *s2, size_t len)
 EXPORT_SYMBOL(strncasecmp);
 #endif
 #ifndef __HAVE_ARCH_STRNICMP
+#undef strnicmp
 int strnicmp(const char *s1, const char *s2, size_t len)
 {
 	return strncasecmp(s1, s2, len);
-- 
cgit v1.2.3


From 3db2e9cdc085144e243495137273e2318c53a82f Mon Sep 17 00:00:00 2001
From: Daniel Walter <dwalter@google.com>
Date: Mon, 13 Oct 2014 15:55:09 -0700
Subject: include/linux: remove strict_strto* definitions

Remove obsolete and unused strict_strto* functions

Signed-off-by: Daniel Walter <dwalter@google.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 35c8ffb0136f..40728cf1c452 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -376,10 +376,6 @@ extern unsigned long simple_strtoul(const char *,char **,unsigned int);
 extern long simple_strtol(const char *,char **,unsigned int);
 extern unsigned long long simple_strtoull(const char *,char **,unsigned int);
 extern long long simple_strtoll(const char *,char **,unsigned int);
-#define strict_strtoul	kstrtoul
-#define strict_strtol	kstrtol
-#define strict_strtoull	kstrtoull
-#define strict_strtoll	kstrtoll
 
 extern int num_to_str(char *buf, int size, unsigned long long num);
 
-- 
cgit v1.2.3


From d295634e965ecacdb44c6760b3ca4eae08812715 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 13 Oct 2014 15:55:11 -0700
Subject: lib / string_helpers: move documentation to c-file

The introduced function string_escape_mem() is a kind of opposite to
string_unescape.  We have several users of such functionality each of
them created custom implementation.  The series contains clean up of
test suite, adding new call, and switching few users to use it via %*pE
specifier.

Test suite covers all of existing and most of potential use cases.

This patch (of 11):

The documentation of API belongs to c-file.  This patch moves it
accordingly.

There is no functional change.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: "John W . Linville" <linville@tuxdriver.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/string_helpers.h | 34 ----------------------------------
 lib/string_helpers.c           | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index 3eeee9672a4a..5a30f2a86239 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -20,40 +20,6 @@ int string_get_size(u64 size, enum string_size_units units,
 #define UNESCAPE_ANY		\
 	(UNESCAPE_SPACE | UNESCAPE_OCTAL | UNESCAPE_HEX | UNESCAPE_SPECIAL)
 
-/**
- * string_unescape - unquote characters in the given string
- * @src:	source buffer (escaped)
- * @dst:	destination buffer (unescaped)
- * @size:	size of the destination buffer (0 to unlimit)
- * @flags:	combination of the flags (bitwise OR):
- *	%UNESCAPE_SPACE:
- *		'\f' - form feed
- *		'\n' - new line
- *		'\r' - carriage return
- *		'\t' - horizontal tab
- *		'\v' - vertical tab
- *	%UNESCAPE_OCTAL:
- *		'\NNN' - byte with octal value NNN (1 to 3 digits)
- *	%UNESCAPE_HEX:
- *		'\xHH' - byte with hexadecimal value HH (1 to 2 digits)
- *	%UNESCAPE_SPECIAL:
- *		'\"' - double quote
- *		'\\' - backslash
- *		'\a' - alert (BEL)
- *		'\e' - escape
- *	%UNESCAPE_ANY:
- *		all previous together
- *
- * Returns amount of characters processed to the destination buffer excluding
- * trailing '\0'.
- *
- * Because the size of the output will be the same as or less than the size of
- * the input, the transformation may be performed in place.
- *
- * Caller must provide valid source and destination pointers. Be aware that
- * destination buffer will always be NULL-terminated. Source string must be
- * NULL-terminated as well.
- */
 int string_unescape(char *src, char *dst, size_t size, unsigned int flags);
 
 static inline int string_unescape_inplace(char *buf, unsigned int flags)
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 29033f319aea..74ec60469640 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -168,6 +168,44 @@ static bool unescape_special(char **src, char **dst)
 	return true;
 }
 
+/**
+ * string_unescape - unquote characters in the given string
+ * @src:	source buffer (escaped)
+ * @dst:	destination buffer (unescaped)
+ * @size:	size of the destination buffer (0 to unlimit)
+ * @flags:	combination of the flags (bitwise OR):
+ *	%UNESCAPE_SPACE:
+ *		'\f' - form feed
+ *		'\n' - new line
+ *		'\r' - carriage return
+ *		'\t' - horizontal tab
+ *		'\v' - vertical tab
+ *	%UNESCAPE_OCTAL:
+ *		'\NNN' - byte with octal value NNN (1 to 3 digits)
+ *	%UNESCAPE_HEX:
+ *		'\xHH' - byte with hexadecimal value HH (1 to 2 digits)
+ *	%UNESCAPE_SPECIAL:
+ *		'\"' - double quote
+ *		'\\' - backslash
+ *		'\a' - alert (BEL)
+ *		'\e' - escape
+ *	%UNESCAPE_ANY:
+ *		all previous together
+ *
+ * Description:
+ * The function unquotes characters in the given string.
+ *
+ * Because the size of the output will be the same as or less than the size of
+ * the input, the transformation may be performed in place.
+ *
+ * Caller must provide valid source and destination pointers. Be aware that
+ * destination buffer will always be NULL-terminated. Source string must be
+ * NULL-terminated as well.
+ *
+ * Return:
+ * The amount of the characters processed to the destination buffer excluding
+ * trailing '\0' is returned.
+ */
 int string_unescape(char *src, char *dst, size_t size, unsigned int flags)
 {
 	char *out = dst;
-- 
cgit v1.2.3


From c8250381c8272a9828fdd353171727b154fbd296 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 13 Oct 2014 15:55:16 -0700
Subject: lib / string_helpers: introduce string_escape_mem()

This is almost the opposite function to string_unescape().  Nevertheless
it handles \0 and could be used for any byte buffer.

The documentation is supplied together with the function prototype.

The test cases covers most of the scenarios and would be expanded later
on.

[akpm@linux-foundation.org: avoid 1k stack consumption]
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: "John W . Linville" <linville@tuxdriver.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Joe Perches <joe@perches.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/string_helpers.h |  31 +++++
 lib/string_helpers.c           | 274 +++++++++++++++++++++++++++++++++++++++++
 lib/test-string_helpers.c      | 240 +++++++++++++++++++++++++++++++++++-
 3 files changed, 541 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index 5a30f2a86239..6eb567ac56bc 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -37,4 +37,35 @@ static inline int string_unescape_any_inplace(char *buf)
 	return string_unescape_any(buf, buf, 0);
 }
 
+#define ESCAPE_SPACE		0x01
+#define ESCAPE_SPECIAL		0x02
+#define ESCAPE_NULL		0x04
+#define ESCAPE_OCTAL		0x08
+#define ESCAPE_ANY		\
+	(ESCAPE_SPACE | ESCAPE_OCTAL | ESCAPE_SPECIAL | ESCAPE_NULL)
+#define ESCAPE_NP		0x10
+#define ESCAPE_ANY_NP		(ESCAPE_ANY | ESCAPE_NP)
+#define ESCAPE_HEX		0x20
+
+int string_escape_mem(const char *src, size_t isz, char **dst, size_t osz,
+		unsigned int flags, const char *esc);
+
+static inline int string_escape_mem_any_np(const char *src, size_t isz,
+		char **dst, size_t osz, const char *esc)
+{
+	return string_escape_mem(src, isz, dst, osz, ESCAPE_ANY_NP, esc);
+}
+
+static inline int string_escape_str(const char *src, char **dst, size_t sz,
+		unsigned int flags, const char *esc)
+{
+	return string_escape_mem(src, strlen(src), dst, sz, flags, esc);
+}
+
+static inline int string_escape_str_any_np(const char *src, char **dst,
+		size_t sz, const char *esc)
+{
+	return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, esc);
+}
+
 #endif
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 74ec60469640..58b78ba57439 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -8,6 +8,8 @@
 #include <linux/math64.h>
 #include <linux/export.h>
 #include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/string.h>
 #include <linux/string_helpers.h>
 
 /**
@@ -240,3 +242,275 @@ int string_unescape(char *src, char *dst, size_t size, unsigned int flags)
 	return out - dst;
 }
 EXPORT_SYMBOL(string_unescape);
+
+static int escape_passthrough(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+
+	if (*osz < 1)
+		return -ENOMEM;
+
+	*out++ = c;
+
+	*dst = out;
+	*osz -= 1;
+
+	return 1;
+}
+
+static int escape_space(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+	unsigned char to;
+
+	if (*osz < 2)
+		return -ENOMEM;
+
+	switch (c) {
+	case '\n':
+		to = 'n';
+		break;
+	case '\r':
+		to = 'r';
+		break;
+	case '\t':
+		to = 't';
+		break;
+	case '\v':
+		to = 'v';
+		break;
+	case '\f':
+		to = 'f';
+		break;
+	default:
+		return 0;
+	}
+
+	*out++ = '\\';
+	*out++ = to;
+
+	*dst = out;
+	*osz -= 2;
+
+	return 1;
+}
+
+static int escape_special(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+	unsigned char to;
+
+	if (*osz < 2)
+		return -ENOMEM;
+
+	switch (c) {
+	case '\\':
+		to = '\\';
+		break;
+	case '\a':
+		to = 'a';
+		break;
+	case '\e':
+		to = 'e';
+		break;
+	default:
+		return 0;
+	}
+
+	*out++ = '\\';
+	*out++ = to;
+
+	*dst = out;
+	*osz -= 2;
+
+	return 1;
+}
+
+static int escape_null(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+
+	if (*osz < 2)
+		return -ENOMEM;
+
+	if (c)
+		return 0;
+
+	*out++ = '\\';
+	*out++ = '0';
+
+	*dst = out;
+	*osz -= 2;
+
+	return 1;
+}
+
+static int escape_octal(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+
+	if (*osz < 4)
+		return -ENOMEM;
+
+	*out++ = '\\';
+	*out++ = ((c >> 6) & 0x07) + '0';
+	*out++ = ((c >> 3) & 0x07) + '0';
+	*out++ = ((c >> 0) & 0x07) + '0';
+
+	*dst = out;
+	*osz -= 4;
+
+	return 1;
+}
+
+static int escape_hex(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+
+	if (*osz < 4)
+		return -ENOMEM;
+
+	*out++ = '\\';
+	*out++ = 'x';
+	*out++ = hex_asc_hi(c);
+	*out++ = hex_asc_lo(c);
+
+	*dst = out;
+	*osz -= 4;
+
+	return 1;
+}
+
+/**
+ * string_escape_mem - quote characters in the given memory buffer
+ * @src:	source buffer (unescaped)
+ * @isz:	source buffer size
+ * @dst:	destination buffer (escaped)
+ * @osz:	destination buffer size
+ * @flags:	combination of the flags (bitwise OR):
+ *	%ESCAPE_SPACE:
+ *		'\f' - form feed
+ *		'\n' - new line
+ *		'\r' - carriage return
+ *		'\t' - horizontal tab
+ *		'\v' - vertical tab
+ *	%ESCAPE_SPECIAL:
+ *		'\\' - backslash
+ *		'\a' - alert (BEL)
+ *		'\e' - escape
+ *	%ESCAPE_NULL:
+ *		'\0' - null
+ *	%ESCAPE_OCTAL:
+ *		'\NNN' - byte with octal value NNN (3 digits)
+ *	%ESCAPE_ANY:
+ *		all previous together
+ *	%ESCAPE_NP:
+ *		escape only non-printable characters (checked by isprint)
+ *	%ESCAPE_ANY_NP:
+ *		all previous together
+ *	%ESCAPE_HEX:
+ *		'\xHH' - byte with hexadecimal value HH (2 digits)
+ * @esc:	NULL-terminated string of characters any of which, if found in
+ *		the source, has to be escaped
+ *
+ * Description:
+ * The process of escaping byte buffer includes several parts. They are applied
+ * in the following sequence.
+ *	1. The character is matched to the printable class, if asked, and in
+ *	   case of match it passes through to the output.
+ *	2. The character is not matched to the one from @esc string and thus
+ *	   must go as is to the output.
+ *	3. The character is checked if it falls into the class given by @flags.
+ *	   %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any
+ *	   character. Note that they actually can't go together, otherwise
+ *	   %ESCAPE_HEX will be ignored.
+ *
+ * Caller must provide valid source and destination pointers. Be aware that
+ * destination buffer will not be NULL-terminated, thus caller have to append
+ * it if needs.
+ *
+ * Return:
+ * The amount of the characters processed to the destination buffer, or
+ * %-ENOMEM if the size of buffer is not enough to put an escaped character is
+ * returned.
+ *
+ * Even in the case of error @dst pointer will be updated to point to the byte
+ * after the last processed character.
+ */
+int string_escape_mem(const char *src, size_t isz, char **dst, size_t osz,
+		      unsigned int flags, const char *esc)
+{
+	char *out = *dst, *p = out;
+	bool is_dict = esc && *esc;
+	int ret = 0;
+
+	while (isz--) {
+		unsigned char c = *src++;
+
+		/*
+		 * Apply rules in the following sequence:
+		 *	- the character is printable, when @flags has
+		 *	  %ESCAPE_NP bit set
+		 *	- the @esc string is supplied and does not contain a
+		 *	  character under question
+		 *	- the character doesn't fall into a class of symbols
+		 *	  defined by given @flags
+		 * In these cases we just pass through a character to the
+		 * output buffer.
+		 */
+		if ((flags & ESCAPE_NP && isprint(c)) ||
+		    (is_dict && !strchr(esc, c))) {
+			/* do nothing */
+		} else {
+			if (flags & ESCAPE_SPACE) {
+				ret = escape_space(c, &p, &osz);
+				if (ret < 0)
+					break;
+				if (ret > 0)
+					continue;
+			}
+
+			if (flags & ESCAPE_SPECIAL) {
+				ret = escape_special(c, &p, &osz);
+				if (ret < 0)
+					break;
+				if (ret > 0)
+					continue;
+			}
+
+			if (flags & ESCAPE_NULL) {
+				ret = escape_null(c, &p, &osz);
+				if (ret < 0)
+					break;
+				if (ret > 0)
+					continue;
+			}
+
+			/* ESCAPE_OCTAL and ESCAPE_HEX always go last */
+			if (flags & ESCAPE_OCTAL) {
+				ret = escape_octal(c, &p, &osz);
+				if (ret < 0)
+					break;
+				continue;
+			}
+			if (flags & ESCAPE_HEX) {
+				ret = escape_hex(c, &p, &osz);
+				if (ret < 0)
+					break;
+				continue;
+			}
+		}
+
+		ret = escape_passthrough(c, &p, &osz);
+		if (ret < 0)
+			break;
+	}
+
+	*dst = p;
+
+	if (ret < 0)
+		return ret;
+
+	return p - out;
+}
+EXPORT_SYMBOL(string_escape_mem);
diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c
index ac44c9245dcf..ab0d30e1e18f 100644
--- a/lib/test-string_helpers.c
+++ b/lib/test-string_helpers.c
@@ -5,6 +5,7 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/string.h>
@@ -62,10 +63,14 @@ static const struct test_string strings[] __initconst = {
 static void __init test_string_unescape(const char *name, unsigned int flags,
 					bool inplace)
 {
-	char in[256];
-	char out_test[256];
-	char out_real[256];
-	int i, p = 0, q_test = 0, q_real = sizeof(out_real);
+	int q_real = 256;
+	char *in = kmalloc(q_real, GFP_KERNEL);
+	char *out_test = kmalloc(q_real, GFP_KERNEL);
+	char *out_real = kmalloc(q_real, GFP_KERNEL);
+	int i, p = 0, q_test = 0;
+
+	if (!in || !out_test || !out_real)
+		goto out;
 
 	for (i = 0; i < ARRAY_SIZE(strings); i++) {
 		const char *s = strings[i].in;
@@ -100,6 +105,223 @@ static void __init test_string_unescape(const char *name, unsigned int flags,
 
 	test_string_check_buf(name, flags, in, p - 1, out_real, q_real,
 			      out_test, q_test);
+out:
+	kfree(out_real);
+	kfree(out_test);
+	kfree(in);
+}
+
+struct test_string_1 {
+	const char *out;
+	unsigned int flags;
+};
+
+#define	TEST_STRING_2_MAX_S1		32
+struct test_string_2 {
+	const char *in;
+	struct test_string_1 s1[TEST_STRING_2_MAX_S1];
+};
+
+#define	TEST_STRING_2_DICT_0		NULL
+static const struct test_string_2 escape0[] __initconst = {{
+	.in = "\f\\ \n\r\t\v",
+	.s1 = {{
+		.out = "\\f\\ \\n\\r\\t\\v",
+		.flags = ESCAPE_SPACE,
+	},{
+		.out = "\\f\\134\\040\\n\\r\\t\\v",
+		.flags = ESCAPE_SPACE | ESCAPE_OCTAL,
+	},{
+		.out = "\\f\\x5c\\x20\\n\\r\\t\\v",
+		.flags = ESCAPE_SPACE | ESCAPE_HEX,
+	},{
+		/* terminator */
+	}},
+},{
+	.in = "\\h\\\"\a\e\\",
+	.s1 = {{
+		.out = "\\\\h\\\\\"\\a\\e\\\\",
+		.flags = ESCAPE_SPECIAL,
+	},{
+		.out = "\\\\\\150\\\\\\042\\a\\e\\\\",
+		.flags = ESCAPE_SPECIAL | ESCAPE_OCTAL,
+	},{
+		.out = "\\\\\\x68\\\\\\x22\\a\\e\\\\",
+		.flags = ESCAPE_SPECIAL | ESCAPE_HEX,
+	},{
+		/* terminator */
+	}},
+},{
+	.in = "\eb \\C\007\"\x90\r]",
+	.s1 = {{
+		.out = "\eb \\C\007\"\x90\\r]",
+		.flags = ESCAPE_SPACE,
+	},{
+		.out = "\\eb \\\\C\\a\"\x90\r]",
+		.flags = ESCAPE_SPECIAL,
+	},{
+		.out = "\\eb \\\\C\\a\"\x90\\r]",
+		.flags = ESCAPE_SPACE | ESCAPE_SPECIAL,
+	},{
+		.out = "\\033\\142\\040\\134\\103\\007\\042\\220\\015\\135",
+		.flags = ESCAPE_OCTAL,
+	},{
+		.out = "\\033\\142\\040\\134\\103\\007\\042\\220\\r\\135",
+		.flags = ESCAPE_SPACE | ESCAPE_OCTAL,
+	},{
+		.out = "\\e\\142\\040\\\\\\103\\a\\042\\220\\015\\135",
+		.flags = ESCAPE_SPECIAL | ESCAPE_OCTAL,
+	},{
+		.out = "\\e\\142\\040\\\\\\103\\a\\042\\220\\r\\135",
+		.flags = ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_OCTAL,
+	},{
+		.out = "\eb \\C\007\"\x90\r]",
+		.flags = ESCAPE_NP,
+	},{
+		.out = "\eb \\C\007\"\x90\\r]",
+		.flags = ESCAPE_SPACE | ESCAPE_NP,
+	},{
+		.out = "\\eb \\C\\a\"\x90\r]",
+		.flags = ESCAPE_SPECIAL | ESCAPE_NP,
+	},{
+		.out = "\\eb \\C\\a\"\x90\\r]",
+		.flags = ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_NP,
+	},{
+		.out = "\\033b \\C\\007\"\\220\\015]",
+		.flags = ESCAPE_OCTAL | ESCAPE_NP,
+	},{
+		.out = "\\033b \\C\\007\"\\220\\r]",
+		.flags = ESCAPE_SPACE | ESCAPE_OCTAL | ESCAPE_NP,
+	},{
+		.out = "\\eb \\C\\a\"\\220\\r]",
+		.flags = ESCAPE_SPECIAL | ESCAPE_SPACE | ESCAPE_OCTAL |
+			 ESCAPE_NP,
+	},{
+		.out = "\\x1bb \\C\\x07\"\\x90\\x0d]",
+		.flags = ESCAPE_NP | ESCAPE_HEX,
+	},{
+		/* terminator */
+	}},
+},{
+	/* terminator */
+}};
+
+#define	TEST_STRING_2_DICT_1		"b\\ \t\r"
+static const struct test_string_2 escape1[] __initconst = {{
+	.in = "\f\\ \n\r\t\v",
+	.s1 = {{
+		.out = "\f\\134\\040\n\\015\\011\v",
+		.flags = ESCAPE_OCTAL,
+	},{
+		.out = "\f\\x5c\\x20\n\\x0d\\x09\v",
+		.flags = ESCAPE_HEX,
+	},{
+		/* terminator */
+	}},
+},{
+	.in = "\\h\\\"\a\e\\",
+	.s1 = {{
+		.out = "\\134h\\134\"\a\e\\134",
+		.flags = ESCAPE_OCTAL,
+	},{
+		/* terminator */
+	}},
+},{
+	.in = "\eb \\C\007\"\x90\r]",
+	.s1 = {{
+		.out = "\e\\142\\040\\134C\007\"\x90\\015]",
+		.flags = ESCAPE_OCTAL,
+	},{
+		/* terminator */
+	}},
+},{
+	/* terminator */
+}};
+
+static __init const char *test_string_find_match(const struct test_string_2 *s2,
+						 unsigned int flags)
+{
+	const struct test_string_1 *s1 = s2->s1;
+	unsigned int i;
+
+	if (!flags)
+		return s2->in;
+
+	/* Test cases are NULL-aware */
+	flags &= ~ESCAPE_NULL;
+
+	/* ESCAPE_OCTAL has a higher priority */
+	if (flags & ESCAPE_OCTAL)
+		flags &= ~ESCAPE_HEX;
+
+	for (i = 0; i < TEST_STRING_2_MAX_S1 && s1->out; i++, s1++)
+		if (s1->flags == flags)
+			return s1->out;
+	return NULL;
+}
+
+static __init void test_string_escape(const char *name,
+				      const struct test_string_2 *s2,
+				      unsigned int flags, const char *esc)
+{
+	int q_real = 512;
+	char *out_test = kmalloc(q_real, GFP_KERNEL);
+	char *out_real = kmalloc(q_real, GFP_KERNEL);
+	char *in = kmalloc(256, GFP_KERNEL);
+	char *buf = out_real;
+	int p = 0, q_test = 0;
+
+	if (!out_test || !out_real || !in)
+		goto out;
+
+	for (; s2->in; s2++) {
+		const char *out;
+		int len;
+
+		/* NULL injection */
+		if (flags & ESCAPE_NULL) {
+			in[p++] = '\0';
+			out_test[q_test++] = '\\';
+			out_test[q_test++] = '0';
+		}
+
+		/* Don't try strings that have no output */
+		out = test_string_find_match(s2, flags);
+		if (!out)
+			continue;
+
+		/* Copy string to in buffer */
+		len = strlen(s2->in);
+		memcpy(&in[p], s2->in, len);
+		p += len;
+
+		/* Copy expected result for given flags */
+		len = strlen(out);
+		memcpy(&out_test[q_test], out, len);
+		q_test += len;
+	}
+
+	q_real = string_escape_mem(in, p, &buf, q_real, flags, esc);
+
+	test_string_check_buf(name, flags, in, p, out_real, q_real, out_test,
+			      q_test);
+out:
+	kfree(in);
+	kfree(out_real);
+	kfree(out_test);
+}
+
+static __init void test_string_escape_nomem(void)
+{
+	char *in = "\eb \\C\007\"\x90\r]";
+	char out[64], *buf = out;
+	int rc = -ENOMEM, ret;
+
+	ret = string_escape_str_any_np(in, &buf, strlen(in), NULL);
+	if (ret == rc)
+		return;
+
+	pr_err("Test 'escape nomem' failed: got %d instead of %d\n", ret, rc);
 }
 
 static int __init test_string_helpers_init(void)
@@ -112,6 +334,16 @@ static int __init test_string_helpers_init(void)
 	test_string_unescape("unescape inplace",
 			     get_random_int() % (UNESCAPE_ANY + 1), true);
 
+	/* Without dictionary */
+	for (i = 0; i < (ESCAPE_ANY_NP | ESCAPE_HEX) + 1; i++)
+		test_string_escape("escape 0", escape0, i, TEST_STRING_2_DICT_0);
+
+	/* With dictionary */
+	for (i = 0; i < (ESCAPE_ANY_NP | ESCAPE_HEX) + 1; i++)
+		test_string_escape("escape 1", escape1, i, TEST_STRING_2_DICT_1);
+
+	test_string_escape_nomem();
+
 	return -EINVAL;
 }
 module_init(test_string_helpers_init);
-- 
cgit v1.2.3


From 5df1415aee48e1d20328238d3077e39793e83232 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 13 Oct 2014 15:55:27 -0700
Subject: lib80211: remove unused print_ssid()

In kernel we have %*pE specifier to print an escaped buffer.  All users
now switched to that approach.

This fixes a bug as well.  The current implementation wrongly prints
octal numbers: only two first digits are used in case when 3 are
required and the rest of the string ends up cut off.

Additionally by default the \f, \v, \a, and \e are escaped to their
alphabetic representation.  It's safe to do since it is currently used
for messaging only.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: "John W . Linville" <linville@tuxdriver.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/net/lib80211.h  |  5 -----
 net/wireless/lib80211.c | 32 --------------------------------
 2 files changed, 37 deletions(-)

(limited to 'include')

diff --git a/include/net/lib80211.h b/include/net/lib80211.h
index be95b9262801..aab0f427edb5 100644
--- a/include/net/lib80211.h
+++ b/include/net/lib80211.h
@@ -32,11 +32,6 @@
 #include <linux/timer.h>
 #include <linux/seq_file.h>
 
-/* print_ssid() is intended to be used in debug (and possibly error)
- * messages. It should never be used for passing ssid to user space. */
-const char *print_ssid(char *buf, const char *ssid, u8 ssid_len);
-#define DECLARE_SSID_BUF(var) char var[IEEE80211_MAX_SSID_LEN * 4 + 1] __maybe_unused
-
 #define NUM_WEP_KEYS	4
 
 enum {
diff --git a/net/wireless/lib80211.c b/net/wireless/lib80211.c
index a55c27b75ee5..459611577d3d 100644
--- a/net/wireless/lib80211.c
+++ b/net/wireless/lib80211.c
@@ -46,38 +46,6 @@ static void lib80211_crypt_deinit_entries(struct lib80211_crypt_info *info,
 static void lib80211_crypt_quiescing(struct lib80211_crypt_info *info);
 static void lib80211_crypt_deinit_handler(unsigned long data);
 
-const char *print_ssid(char *buf, const char *ssid, u8 ssid_len)
-{
-	const char *s = ssid;
-	char *d = buf;
-
-	ssid_len = min_t(u8, ssid_len, IEEE80211_MAX_SSID_LEN);
-	while (ssid_len--) {
-		if (isprint(*s)) {
-			*d++ = *s++;
-			continue;
-		}
-
-		*d++ = '\\';
-		if (*s == '\0')
-			*d++ = '0';
-		else if (*s == '\n')
-			*d++ = 'n';
-		else if (*s == '\r')
-			*d++ = 'r';
-		else if (*s == '\t')
-			*d++ = 't';
-		else if (*s == '\\')
-			*d++ = '\\';
-		else
-			d += snprintf(d, 3, "%03o", *s);
-		s++;
-	}
-	*d = '\0';
-	return buf;
-}
-EXPORT_SYMBOL(print_ssid);
-
 int lib80211_crypt_info_init(struct lib80211_crypt_info *info, char *name,
 				spinlock_t *lock)
 {
-- 
cgit v1.2.3


From 6e7458a6f074c71e74cda31c483114e65ea0f570 Mon Sep 17 00:00:00 2001
From: Ulrich Obergfell <uobergfe@redhat.com>
Date: Mon, 13 Oct 2014 15:55:35 -0700
Subject: kernel/watchdog.c: control hard lockup detection default

In some cases we don't want hard lockup detection enabled by default.
An example is when running as a guest.  Introduce

  watchdog_enable_hardlockup_detector(bool)

allowing those cases to disable hard lockup detection.  This must be
executed early by the boot processor from e.g.  smp_prepare_boot_cpu, in
order to allow kernel command line arguments to override it, as well as
to avoid hard lockup detection being enabled before we've had a chance
to indicate that it's unwanted.  In summary,

  initial boot:					default=enabled
  smp_prepare_boot_cpu
    watchdog_enable_hardlockup_detector(false):	default=disabled
  cmdline has 'nmi_watchdog=1':			default=enabled

The running kernel still has the ability to enable/disable at any time
with /proc/sys/kernel/nmi_watchdog us usual.  However even when the
default has been overridden /proc/sys/kernel/nmi_watchdog will initially
show '1'.  To truly turn it on one must disable/enable it, i.e.

  echo 0 > /proc/sys/kernel/nmi_watchdog
  echo 1 > /proc/sys/kernel/nmi_watchdog

This patch will be immediately useful for KVM with the next patch of this
series.  Other hypervisor guest types may find it useful as well.

[akpm@linux-foundation.org: fix build]
[dzickus@redhat.com: fix compile issues on sparc]
Signed-off-by: Ulrich Obergfell <uobergfe@redhat.com>
Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/nmi.h | 13 +++++++++++++
 kernel/watchdog.c   | 50 ++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 61 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 1d2a6ab6b8bb..9b2022ab4d85 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -24,6 +24,19 @@ static inline void touch_nmi_watchdog(void)
 }
 #endif
 
+#if defined(CONFIG_HARDLOCKUP_DETECTOR)
+extern void watchdog_enable_hardlockup_detector(bool val);
+extern bool watchdog_hardlockup_detector_is_enabled(void);
+#else
+static inline void watchdog_enable_hardlockup_detector(bool val)
+{
+}
+static inline bool watchdog_hardlockup_detector_is_enabled(void)
+{
+	return true;
+}
+#endif
+
 /*
  * Create trigger_all_cpu_backtrace() out of the arch-provided
  * base function. Return whether such support was available,
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index ff7fd80bef99..49e9537f3673 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -59,6 +59,25 @@ static unsigned long soft_lockup_nmi_warn;
 static int hardlockup_panic =
 			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
 
+static bool hardlockup_detector_enabled = true;
+/*
+ * We may not want to enable hard lockup detection by default in all cases,
+ * for example when running the kernel as a guest on a hypervisor. In these
+ * cases this function can be called to disable hard lockup detection. This
+ * function should only be executed once by the boot processor before the
+ * kernel command line parameters are parsed, because otherwise it is not
+ * possible to override this in hardlockup_panic_setup().
+ */
+void watchdog_enable_hardlockup_detector(bool val)
+{
+	hardlockup_detector_enabled = val;
+}
+
+bool watchdog_hardlockup_detector_is_enabled(void)
+{
+	return hardlockup_detector_enabled;
+}
+
 static int __init hardlockup_panic_setup(char *str)
 {
 	if (!strncmp(str, "panic", 5))
@@ -67,6 +86,14 @@ static int __init hardlockup_panic_setup(char *str)
 		hardlockup_panic = 0;
 	else if (!strncmp(str, "0", 1))
 		watchdog_user_enabled = 0;
+	else if (!strncmp(str, "1", 1) || !strncmp(str, "2", 1)) {
+		/*
+		 * Setting 'nmi_watchdog=1' or 'nmi_watchdog=2' (legacy option)
+		 * has the same effect.
+		 */
+		watchdog_user_enabled = 1;
+		watchdog_enable_hardlockup_detector(true);
+	}
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
@@ -465,6 +492,15 @@ static int watchdog_nmi_enable(unsigned int cpu)
 	struct perf_event_attr *wd_attr;
 	struct perf_event *event = per_cpu(watchdog_ev, cpu);
 
+	/*
+	 * Some kernels need to default hard lockup detection to
+	 * 'disabled', for example a guest on a hypervisor.
+	 */
+	if (!watchdog_hardlockup_detector_is_enabled()) {
+		event = ERR_PTR(-ENOENT);
+		goto handle_err;
+	}
+
 	/* is it already setup and enabled? */
 	if (event && event->state > PERF_EVENT_STATE_OFF)
 		goto out;
@@ -479,6 +515,7 @@ static int watchdog_nmi_enable(unsigned int cpu)
 	/* Try to register using hardware perf events */
 	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
 
+handle_err:
 	/* save cpu0 error for future comparision */
 	if (cpu == 0 && IS_ERR(event))
 		cpu0_err = PTR_ERR(event);
@@ -624,11 +661,13 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old_thresh, old_enabled;
+	bool old_hardlockup;
 	static DEFINE_MUTEX(watchdog_proc_mutex);
 
 	mutex_lock(&watchdog_proc_mutex);
 	old_thresh = ACCESS_ONCE(watchdog_thresh);
 	old_enabled = ACCESS_ONCE(watchdog_user_enabled);
+	old_hardlockup = watchdog_hardlockup_detector_is_enabled();
 
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (err || !write)
@@ -640,15 +679,22 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 	 * disabled. The 'watchdog_running' variable check in
 	 * watchdog_*_all_cpus() function takes care of this.
 	 */
-	if (watchdog_user_enabled && watchdog_thresh)
+	if (watchdog_user_enabled && watchdog_thresh) {
+		/*
+		 * Prevent a change in watchdog_thresh accidentally overriding
+		 * the enablement of the hardlockup detector.
+		 */
+		if (watchdog_user_enabled != old_enabled)
+			watchdog_enable_hardlockup_detector(true);
 		err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh);
-	else
+	} else
 		watchdog_disable_all_cpus();
 
 	/* Restore old values on failure */
 	if (err) {
 		watchdog_thresh = old_thresh;
 		watchdog_user_enabled = old_enabled;
+		watchdog_enable_hardlockup_detector(old_hardlockup);
 	}
 out:
 	mutex_unlock(&watchdog_proc_mutex);
-- 
cgit v1.2.3


From 63a12d9d01831208a47f5c0fbbf93f503d1fb162 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 13 Oct 2014 15:55:44 -0700
Subject: kernel/param: consolidate __{start,stop}___param[] in
 <linux/moduleparam.h>

Consolidate the various external const and non-const declarations of
__start___param[] and __stop___param in <linux/moduleparam.h>.  This
requires making a few struct kernel_param pointers in kernel/params.c
const.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/moduleparam.h | 2 ++
 init/main.c                 | 2 --
 kernel/params.c             | 7 +++----
 3 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index b43f4752304e..1c9effa25e26 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -78,6 +78,8 @@ struct kernel_param {
 	};
 };
 
+extern const struct kernel_param __start___param[], __stop___param[];
+
 /* Special one for strings we want to copy into */
 struct kparam_string {
 	unsigned int maxlen;
diff --git a/init/main.c b/init/main.c
index 89ec862da2d4..800a0daede7e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -501,7 +501,6 @@ asmlinkage __visible void __init start_kernel(void)
 {
 	char *command_line;
 	char *after_dashes;
-	extern const struct kernel_param __start___param[], __stop___param[];
 
 	/*
 	 * Need to run as early as possible, to initialize the
@@ -844,7 +843,6 @@ static char *initcall_level_names[] __initdata = {
 
 static void __init do_initcall_level(int level)
 {
-	extern const struct kernel_param __start___param[], __stop___param[];
 	initcall_t *fn;
 
 	strcpy(initcall_command_line, saved_command_line);
diff --git a/kernel/params.c b/kernel/params.c
index 041b5899d5e2..db97b791390f 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -19,6 +19,7 @@
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/slab.h>
@@ -513,8 +514,6 @@ EXPORT_SYMBOL(param_ops_string);
 #define to_module_attr(n) container_of(n, struct module_attribute, attr)
 #define to_module_kobject(n) container_of(n, struct module_kobject, kobj)
 
-extern struct kernel_param __start___param[], __stop___param[];
-
 struct param_attribute
 {
 	struct module_attribute mattr;
@@ -774,7 +773,7 @@ static struct module_kobject * __init locate_module_kobject(const char *name)
 }
 
 static void __init kernel_add_sysfs_param(const char *name,
-					  struct kernel_param *kparam,
+					  const struct kernel_param *kparam,
 					  unsigned int name_skip)
 {
 	struct module_kobject *mk;
@@ -809,7 +808,7 @@ static void __init kernel_add_sysfs_param(const char *name,
  */
 static void __init param_sysfs_builtin(void)
 {
-	struct kernel_param *kp;
+	const struct kernel_param *kp;
 	unsigned int name_len;
 	char modname[MODULE_NAME_LEN];
 
-- 
cgit v1.2.3


From 64e455079e1bd7787cc47be30b7f601ce682a5f6 Mon Sep 17 00:00:00 2001
From: Peter Feiner <pfeiner@google.com>
Date: Mon, 13 Oct 2014 15:55:46 -0700
Subject: mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY
 cleared

For VMAs that don't want write notifications, PTEs created for read faults
have their write bit set.  If the read fault happens after VM_SOFTDIRTY is
cleared, then the PTE's softdirty bit will remain clear after subsequent
writes.

Here's a simple code snippet to demonstrate the bug:

  char* m = mmap(NULL, getpagesize(), PROT_READ | PROT_WRITE,
                 MAP_ANONYMOUS | MAP_SHARED, -1, 0);
  system("echo 4 > /proc/$PPID/clear_refs"); /* clear VM_SOFTDIRTY */
  assert(*m == '\0');     /* new PTE allows write access */
  assert(!soft_dirty(x));
  *m = 'x';               /* should dirty the page */
  assert(soft_dirty(x));  /* fails */

With this patch, write notifications are enabled when VM_SOFTDIRTY is
cleared.  Furthermore, to avoid unnecessary faults, write notifications
are disabled when VM_SOFTDIRTY is set.

As a side effect of enabling and disabling write notifications with
care, this patch fixes a bug in mprotect where vm_page_prot bits set by
drivers were zapped on mprotect.  An analogous bug was fixed in mmap by
commit c9d0bf241451 ("mm: uncached vma support with writenotify").

Signed-off-by: Peter Feiner <pfeiner@google.com>
Reported-by: Peter Feiner <pfeiner@google.com>
Suggested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Jamie Liu <jamieliu@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c            | 19 +++++++++++++-----
 include/asm-generic/pgtable.h | 14 ++++++++++++++
 include/linux/mm.h            |  5 +++++
 mm/memory.c                   |  3 ++-
 mm/mmap.c                     | 45 +++++++++++++++++++++++++++----------------
 mm/mprotect.c                 | 20 +++++--------------
 6 files changed, 68 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index b7a7dc963a35..4e0388cffe3d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -827,8 +827,21 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			.private = &cp,
 		};
 		down_read(&mm->mmap_sem);
-		if (type == CLEAR_REFS_SOFT_DIRTY)
+		if (type == CLEAR_REFS_SOFT_DIRTY) {
+			for (vma = mm->mmap; vma; vma = vma->vm_next) {
+				if (!(vma->vm_flags & VM_SOFTDIRTY))
+					continue;
+				up_read(&mm->mmap_sem);
+				down_write(&mm->mmap_sem);
+				for (vma = mm->mmap; vma; vma = vma->vm_next) {
+					vma->vm_flags &= ~VM_SOFTDIRTY;
+					vma_set_page_prot(vma);
+				}
+				downgrade_write(&mm->mmap_sem);
+				break;
+			}
 			mmu_notifier_invalidate_range_start(mm, 0, -1);
+		}
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			cp.vma = vma;
 			if (is_vm_hugetlb_page(vma))
@@ -848,10 +861,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				continue;
 			if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
 				continue;
-			if (type == CLEAR_REFS_SOFT_DIRTY) {
-				if (vma->vm_flags & VM_SOFTDIRTY)
-					vma->vm_flags &= ~VM_SOFTDIRTY;
-			}
 			walk_page_range(vma->vm_start, vma->vm_end,
 					&clear_refs_walk);
 		}
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 081ff8826bf6..752e30d63904 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -253,6 +253,20 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #define pgprot_device pgprot_noncached
 #endif
 
+#ifndef pgprot_modify
+#define pgprot_modify pgprot_modify
+static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+{
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
+		newprot = pgprot_noncached(newprot);
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
+		newprot = pgprot_writecombine(newprot);
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
+		newprot = pgprot_device(newprot);
+	return newprot;
+}
+#endif
+
 /*
  * When walking page tables, get the address of the next boundary,
  * or the end address of the range if that comes earlier.  Although no
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4cd45cb95e6d..02d11ee7f19d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1974,11 +1974,16 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
 
 #ifdef CONFIG_MMU
 pgprot_t vm_get_page_prot(unsigned long vm_flags);
+void vma_set_page_prot(struct vm_area_struct *vma);
 #else
 static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
 {
 	return __pgprot(0);
 }
+static inline void vma_set_page_prot(struct vm_area_struct *vma)
+{
+	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+}
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/mm/memory.c b/mm/memory.c
index e229970e4223..1cc6bfbd872e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2053,7 +2053,8 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	old_page = vm_normal_page(vma, address, orig_pte);
 	if (!old_page) {
 		/*
-		 * VM_MIXEDMAP !pfn_valid() case
+		 * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
+		 * VM_PFNMAP VMA.
 		 *
 		 * We should not cow pages in a shared writeable mapping.
 		 * Just mark the pages writable as we can't do any dirty
diff --git a/mm/mmap.c b/mm/mmap.c
index 93d28c7e5420..7f855206e7fb 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -89,6 +89,25 @@ pgprot_t vm_get_page_prot(unsigned long vm_flags)
 }
 EXPORT_SYMBOL(vm_get_page_prot);
 
+static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
+{
+	return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
+}
+
+/* Update vma->vm_page_prot to reflect vma->vm_flags. */
+void vma_set_page_prot(struct vm_area_struct *vma)
+{
+	unsigned long vm_flags = vma->vm_flags;
+
+	vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
+	if (vma_wants_writenotify(vma)) {
+		vm_flags &= ~VM_SHARED;
+		vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot,
+						     vm_flags);
+	}
+}
+
+
 int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;  /* heuristic overcommit */
 int sysctl_overcommit_ratio __read_mostly = 50;	/* default is 50% */
 unsigned long sysctl_overcommit_kbytes __read_mostly;
@@ -1475,11 +1494,16 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
 	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
 		return 1;
 
-	/* The open routine did something to the protections already? */
+	/* The open routine did something to the protections that pgprot_modify
+	 * won't preserve? */
 	if (pgprot_val(vma->vm_page_prot) !=
-	    pgprot_val(vm_get_page_prot(vm_flags)))
+	    pgprot_val(vm_pgprot_modify(vma->vm_page_prot, vm_flags)))
 		return 0;
 
+	/* Do we need to track softdirty? */
+	if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY))
+		return 1;
+
 	/* Specialty mapping? */
 	if (vm_flags & VM_PFNMAP)
 		return 0;
@@ -1615,21 +1639,6 @@ munmap_back:
 			goto free_vma;
 	}
 
-	if (vma_wants_writenotify(vma)) {
-		pgprot_t pprot = vma->vm_page_prot;
-
-		/* Can vma->vm_page_prot have changed??
-		 *
-		 * Answer: Yes, drivers may have changed it in their
-		 *         f_op->mmap method.
-		 *
-		 * Ensures that vmas marked as uncached stay that way.
-		 */
-		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
-		if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
-			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	}
-
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	/* Once vma denies write, undo our temporary denial count */
 	if (file) {
@@ -1663,6 +1672,8 @@ out:
 	 */
 	vma->vm_flags |= VM_SOFTDIRTY;
 
+	vma_set_page_prot(vma);
+
 	return addr;
 
 unmap_and_free_vma:
diff --git a/mm/mprotect.c b/mm/mprotect.c
index c43d557941f8..ace93454ce8e 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -29,13 +29,6 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
-#ifndef pgprot_modify
-static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
-{
-	return newprot;
-}
-#endif
-
 /*
  * For a prot_numa update we only hold mmap_sem for read so there is a
  * potential race with faulting where a pmd was temporarily none. This
@@ -93,7 +86,9 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				 * Avoid taking write faults for pages we
 				 * know to be dirty.
 				 */
-				if (dirty_accountable && pte_dirty(ptent))
+				if (dirty_accountable && pte_dirty(ptent) &&
+				    (pte_soft_dirty(ptent) ||
+				     !(vma->vm_flags & VM_SOFTDIRTY)))
 					ptent = pte_mkwrite(ptent);
 				ptep_modify_prot_commit(mm, addr, pte, ptent);
 				updated = true;
@@ -320,13 +315,8 @@ success:
 	 * held in write mode.
 	 */
 	vma->vm_flags = newflags;
-	vma->vm_page_prot = pgprot_modify(vma->vm_page_prot,
-					  vm_get_page_prot(newflags));
-
-	if (vma_wants_writenotify(vma)) {
-		vma->vm_page_prot = vm_get_page_prot(newflags & ~VM_SHARED);
-		dirty_accountable = 1;
-	}
+	dirty_accountable = vma_wants_writenotify(vma);
+	vma_set_page_prot(vma);
 
 	change_protection(vma, start, end, vma->vm_page_prot,
 			  dirty_accountable, 0);
-- 
cgit v1.2.3


From 2cbbca5e7c38d0c776497f586688464f8cfb1583 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Tue, 30 Sep 2014 16:02:19 +1000
Subject: md: discard PRINT_RAID_DEBUG ioctl

All the interesting information printed by this ioctl
is provided in /proc/mdstat and/or sysfs.
So it isn't needed and isn't used and would be best if it didn't
exist.

Signed-off-by: NeilBrown <neilb@suse.de>
---
 drivers/md/md.c                | 138 -----------------------------------------
 include/uapi/linux/raid/md_u.h |   1 -
 2 files changed, 139 deletions(-)

(limited to 'include')

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9c33f052c848..fdd2d3fe1c6c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -66,8 +66,6 @@ static void autostart_arrays(int part);
 static LIST_HEAD(pers_list);
 static DEFINE_SPINLOCK(pers_lock);
 
-static void md_print_devices(void);
-
 static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
 static struct workqueue_struct *md_wq;
 static struct workqueue_struct *md_misc_wq;
@@ -2171,136 +2169,6 @@ static void export_array(struct mddev *mddev)
 	mddev->major_version = 0;
 }
 
-static void print_desc(mdp_disk_t *desc)
-{
-	printk(" DISK<N:%d,(%d,%d),R:%d,S:%d>\n", desc->number,
-		desc->major,desc->minor,desc->raid_disk,desc->state);
-}
-
-static void print_sb_90(mdp_super_t *sb)
-{
-	int i;
-
-	printk(KERN_INFO
-		"md:  SB: (V:%d.%d.%d) ID:<%08x.%08x.%08x.%08x> CT:%08x\n",
-		sb->major_version, sb->minor_version, sb->patch_version,
-		sb->set_uuid0, sb->set_uuid1, sb->set_uuid2, sb->set_uuid3,
-		sb->ctime);
-	printk(KERN_INFO "md:     L%d S%08d ND:%d RD:%d md%d LO:%d CS:%d\n",
-		sb->level, sb->size, sb->nr_disks, sb->raid_disks,
-		sb->md_minor, sb->layout, sb->chunk_size);
-	printk(KERN_INFO "md:     UT:%08x ST:%d AD:%d WD:%d"
-		" FD:%d SD:%d CSUM:%08x E:%08lx\n",
-		sb->utime, sb->state, sb->active_disks, sb->working_disks,
-		sb->failed_disks, sb->spare_disks,
-		sb->sb_csum, (unsigned long)sb->events_lo);
-
-	printk(KERN_INFO);
-	for (i = 0; i < MD_SB_DISKS; i++) {
-		mdp_disk_t *desc;
-
-		desc = sb->disks + i;
-		if (desc->number || desc->major || desc->minor ||
-		    desc->raid_disk || (desc->state && (desc->state != 4))) {
-			printk("     D %2d: ", i);
-			print_desc(desc);
-		}
-	}
-	printk(KERN_INFO "md:     THIS: ");
-	print_desc(&sb->this_disk);
-}
-
-static void print_sb_1(struct mdp_superblock_1 *sb)
-{
-	__u8 *uuid;
-
-	uuid = sb->set_uuid;
-	printk(KERN_INFO
-	       "md:  SB: (V:%u) (F:0x%08x) Array-ID:<%pU>\n"
-	       "md:    Name: \"%s\" CT:%llu\n",
-		le32_to_cpu(sb->major_version),
-		le32_to_cpu(sb->feature_map),
-		uuid,
-		sb->set_name,
-		(unsigned long long)le64_to_cpu(sb->ctime)
-		       & MD_SUPERBLOCK_1_TIME_SEC_MASK);
-
-	uuid = sb->device_uuid;
-	printk(KERN_INFO
-	       "md:       L%u SZ%llu RD:%u LO:%u CS:%u DO:%llu DS:%llu SO:%llu"
-			" RO:%llu\n"
-	       "md:     Dev:%08x UUID: %pU\n"
-	       "md:       (F:0x%08x) UT:%llu Events:%llu ResyncOffset:%llu CSUM:0x%08x\n"
-	       "md:         (MaxDev:%u) \n",
-		le32_to_cpu(sb->level),
-		(unsigned long long)le64_to_cpu(sb->size),
-		le32_to_cpu(sb->raid_disks),
-		le32_to_cpu(sb->layout),
-		le32_to_cpu(sb->chunksize),
-		(unsigned long long)le64_to_cpu(sb->data_offset),
-		(unsigned long long)le64_to_cpu(sb->data_size),
-		(unsigned long long)le64_to_cpu(sb->super_offset),
-		(unsigned long long)le64_to_cpu(sb->recovery_offset),
-		le32_to_cpu(sb->dev_number),
-		uuid,
-		sb->devflags,
-		(unsigned long long)le64_to_cpu(sb->utime) & MD_SUPERBLOCK_1_TIME_SEC_MASK,
-		(unsigned long long)le64_to_cpu(sb->events),
-		(unsigned long long)le64_to_cpu(sb->resync_offset),
-		le32_to_cpu(sb->sb_csum),
-		le32_to_cpu(sb->max_dev)
-		);
-}
-
-static void print_rdev(struct md_rdev *rdev, int major_version)
-{
-	char b[BDEVNAME_SIZE];
-	printk(KERN_INFO "md: rdev %s, Sect:%08llu F:%d S:%d DN:%u\n",
-	       bdevname(rdev->bdev, b), (unsigned long long)rdev->sectors,
-	       test_bit(Faulty, &rdev->flags), test_bit(In_sync, &rdev->flags),
-	       rdev->desc_nr);
-	if (rdev->sb_loaded) {
-		printk(KERN_INFO "md: rdev superblock (MJ:%d):\n", major_version);
-		switch (major_version) {
-		case 0:
-			print_sb_90(page_address(rdev->sb_page));
-			break;
-		case 1:
-			print_sb_1(page_address(rdev->sb_page));
-			break;
-		}
-	} else
-		printk(KERN_INFO "md: no rdev superblock!\n");
-}
-
-static void md_print_devices(void)
-{
-	struct list_head *tmp;
-	struct md_rdev *rdev;
-	struct mddev *mddev;
-	char b[BDEVNAME_SIZE];
-
-	printk("\n");
-	printk("md:	**********************************\n");
-	printk("md:	* <COMPLETE RAID STATE PRINTOUT> *\n");
-	printk("md:	**********************************\n");
-	for_each_mddev(mddev, tmp) {
-
-		if (mddev->bitmap)
-			bitmap_print_sb(mddev->bitmap);
-		else
-			printk("%s: ", mdname(mddev));
-		rdev_for_each(rdev, mddev)
-			printk("<%s>", bdevname(rdev->bdev,b));
-		printk("\n");
-
-		rdev_for_each(rdev, mddev)
-			print_rdev(rdev, mddev->major_version);
-	}
-	printk("md:	**********************************\n");
-	printk("\n");
-}
-
 static void sync_sbs(struct mddev *mddev, int nospares)
 {
 	/* Update each superblock (in-memory image), but
@@ -6285,7 +6153,6 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 	case GET_DISK_INFO:
 	case HOT_ADD_DISK:
 	case HOT_REMOVE_DISK:
-	case PRINT_RAID_DEBUG:
 	case RAID_AUTORUN:
 	case RAID_VERSION:
 	case RESTART_ARRAY_RW:
@@ -6331,11 +6198,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 		err = get_version(argp);
 		goto out;
 
-	case PRINT_RAID_DEBUG:
-		err = 0;
-		md_print_devices();
-		goto out;
-
 #ifndef MODULE
 	case RAID_AUTORUN:
 		err = 0;
diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h
index 4133e744e4e6..74e7c60c4716 100644
--- a/include/uapi/linux/raid/md_u.h
+++ b/include/uapi/linux/raid/md_u.h
@@ -39,7 +39,6 @@
 #define RAID_VERSION		_IOR (MD_MAJOR, 0x10, mdu_version_t)
 #define GET_ARRAY_INFO		_IOR (MD_MAJOR, 0x11, mdu_array_info_t)
 #define GET_DISK_INFO		_IOR (MD_MAJOR, 0x12, mdu_disk_info_t)
-#define PRINT_RAID_DEBUG	_IO (MD_MAJOR, 0x13)
 #define RAID_AUTORUN		_IO (MD_MAJOR, 0x14)
 #define GET_BITMAP_FILE		_IOR (MD_MAJOR, 0x15, mdu_bitmap_file_t)
 
-- 
cgit v1.2.3


From a0a77af14117e388d43b2385d5ecc800e2d6eee9 Mon Sep 17 00:00:00 2001
From: Behan Webster <behanw@converseincode.com>
Date: Mon, 8 Sep 2014 00:05:09 -0500
Subject: crypto: LLVMLinux: Add macro to remove use of VLAIS in crypto code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a macro which replaces the use of a Variable Length Array In Struct (VLAIS)
with a C99 compliant equivalent. This macro instead allocates the appropriate
amount of memory using an char array.

The new code can be compiled with both gcc and clang.

struct shash_desc contains a flexible array member member ctx declared with
CRYPTO_MINALIGN_ATTR, so sizeof(struct shash_desc) aligns the beginning
of the array declared after struct shash_desc with long long.

No trailing padding is required because it is not a struct type that can
be used in an array.

The CRYPTO_MINALIGN_ATTR is required so that desc is aligned with long long
as would be the case for a struct containing a member with
CRYPTO_MINALIGN_ATTR.

If you want to get to the ctx at the end of the shash_desc as before you can do
so using shash_desc_ctx(shash)

Signed-off-by: Behan Webster <behanw@converseincode.com>
Reviewed-by: Mark Charlebois <charlebm@gmail.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Michał Mirosław <mirqus@gmail.com>
---
 include/crypto/hash.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index a39195539601..74b13ec1ebd4 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -58,6 +58,11 @@ struct shash_desc {
 	void *__ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
+#define SHASH_DESC_ON_STACK(shash, ctx)				  \
+	char __##shash##_desc[sizeof(struct shash_desc) +	  \
+		crypto_shash_descsize(ctx)] CRYPTO_MINALIGN_ATTR; \
+	struct shash_desc *shash = (struct shash_desc *)__##shash##_desc
+
 struct shash_alg {
 	int (*init)(struct shash_desc *desc);
 	int (*update)(struct shash_desc *desc, const u8 *data,
-- 
cgit v1.2.3


From e19a8a0ad2d255316830ead05b59c5a704434cbb Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Tue, 14 Oct 2014 09:00:44 -0600
Subject: block: Remove REQ_KERNEL

REQ_KERNEL is no longer used. Remove it and drop the redundant uio
argument to nfs_file_direct_{read,write}.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 fs/nfs/direct.c           | 12 +++++-------
 fs/nfs/file.c             |  4 ++--
 include/linux/blk_types.h |  2 --
 include/linux/fs.h        |  2 --
 include/linux/nfs_fs.h    |  4 ++--
 5 files changed, 9 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 65ef6e00deee..891f7dd8cbd6 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -222,11 +222,9 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t
 #else
 	VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
 
-	if (rw == READ || rw == KERNEL_READ)
-		return nfs_file_direct_read(iocb, iter, pos,
-				rw == READ ? true : false);
-	return nfs_file_direct_write(iocb, iter, pos,
-				rw == WRITE ? true : false);
+	if (rw == READ)
+		return nfs_file_direct_read(iocb, iter, pos);
+	return nfs_file_direct_write(iocb, iter, pos);
 #endif /* CONFIG_NFS_SWAP */
 }
 
@@ -512,7 +510,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
  * cache.
  */
 ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
-				loff_t pos, bool uio)
+				loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
@@ -893,7 +891,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
  * is no atomic O_APPEND write facility in the NFS protocol.
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
-				loff_t pos, bool uio)
+				loff_t pos)
 {
 	ssize_t result = -EINVAL;
 	struct file *file = iocb->ki_filp;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 524dd80d1898..3b42cb86218e 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -171,7 +171,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 	ssize_t result;
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_read(iocb, to, iocb->ki_pos, true);
+		return nfs_file_direct_read(iocb, to, iocb->ki_pos);
 
 	dprintk("NFS: read(%pD2, %zu@%lu)\n",
 		iocb->ki_filp,
@@ -648,7 +648,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 		return result;
 
 	if (file->f_flags & O_DIRECT)
-		return nfs_file_direct_write(iocb, from, pos, true);
+		return nfs_file_direct_write(iocb, from, pos);
 
 	dprintk("NFS: write(%pD2, %zu@%Ld)\n",
 		file, count, (long long) pos);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 38bc008e4503..445d59231bc4 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -187,7 +187,6 @@ enum rq_flag_bits {
 	__REQ_FLUSH_SEQ,	/* request for flush sequence */
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
-	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_PM,		/* runtime pm request */
 	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_MQ_INFLIGHT,	/* track inflight for MQ */
@@ -241,7 +240,6 @@ enum rq_flag_bits {
 #define REQ_IO_STAT		(1ULL << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1ULL << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1ULL << __REQ_SECURE)
-#define REQ_KERNEL		(1ULL << __REQ_KERNEL)
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 94187721ad41..9b5bc1cacb8e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -192,8 +192,6 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define READ			0
 #define WRITE			RW_MASK
 #define READA			RWA_MASK
-#define KERNEL_READ		(READ|REQ_KERNEL)
-#define KERNEL_WRITE		(WRITE|REQ_KERNEL)
 
 #define READ_SYNC		(READ | REQ_SYNC)
 #define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 5180a7ededec..e6e1c4e0d7f3 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -464,10 +464,10 @@ extern int nfs3_removexattr (struct dentry *, const char *name);
 extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t);
 extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
 			struct iov_iter *iter,
-			loff_t pos, bool uio);
+			loff_t pos);
 extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
 			struct iov_iter *iter,
-			loff_t pos, bool uio);
+			loff_t pos);
 
 /*
  * linux/fs/nfs/dir.c
-- 
cgit v1.2.3


From 9de7922bc709eee2f609cd01d98aaedc4cf5ea74 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Thu, 9 Oct 2014 22:55:31 +0200
Subject: net: sctp: fix skb_over_panic when receiving malformed ASCONF chunks

Commit 6f4c618ddb0 ("SCTP : Add paramters validity check for
ASCONF chunk") added basic verification of ASCONF chunks, however,
it is still possible to remotely crash a server by sending a
special crafted ASCONF chunk, even up to pre 2.6.12 kernels:

skb_over_panic: text:ffffffffa01ea1c3 len:31056 put:30768
 head:ffff88011bd81800 data:ffff88011bd81800 tail:0x7950
 end:0x440 dev:<NULL>
 ------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:129!
[...]
Call Trace:
 <IRQ>
 [<ffffffff8144fb1c>] skb_put+0x5c/0x70
 [<ffffffffa01ea1c3>] sctp_addto_chunk+0x63/0xd0 [sctp]
 [<ffffffffa01eadaf>] sctp_process_asconf+0x1af/0x540 [sctp]
 [<ffffffff8152d025>] ? _read_unlock_bh+0x15/0x20
 [<ffffffffa01e0038>] sctp_sf_do_asconf+0x168/0x240 [sctp]
 [<ffffffffa01e3751>] sctp_do_sm+0x71/0x1210 [sctp]
 [<ffffffff8147645d>] ? fib_rules_lookup+0xad/0xf0
 [<ffffffffa01e6b22>] ? sctp_cmp_addr_exact+0x32/0x40 [sctp]
 [<ffffffffa01e8393>] sctp_assoc_bh_rcv+0xd3/0x180 [sctp]
 [<ffffffffa01ee986>] sctp_inq_push+0x56/0x80 [sctp]
 [<ffffffffa01fcc42>] sctp_rcv+0x982/0xa10 [sctp]
 [<ffffffffa01d5123>] ? ipt_local_in_hook+0x23/0x28 [iptable_filter]
 [<ffffffff8148bdc9>] ? nf_iterate+0x69/0xb0
 [<ffffffff81496d10>] ? ip_local_deliver_finish+0x0/0x2d0
 [<ffffffff8148bf86>] ? nf_hook_slow+0x76/0x120
 [<ffffffff81496d10>] ? ip_local_deliver_finish+0x0/0x2d0
 [<ffffffff81496ded>] ip_local_deliver_finish+0xdd/0x2d0
 [<ffffffff81497078>] ip_local_deliver+0x98/0xa0
 [<ffffffff8149653d>] ip_rcv_finish+0x12d/0x440
 [<ffffffff81496ac5>] ip_rcv+0x275/0x350
 [<ffffffff8145c88b>] __netif_receive_skb+0x4ab/0x750
 [<ffffffff81460588>] netif_receive_skb+0x58/0x60

This can be triggered e.g., through a simple scripted nmap
connection scan injecting the chunk after the handshake, for
example, ...

  -------------- INIT[ASCONF; ASCONF_ACK] ------------->
  <----------- INIT-ACK[ASCONF; ASCONF_ACK] ------------
  -------------------- COOKIE-ECHO -------------------->
  <-------------------- COOKIE-ACK ---------------------
  ------------------ ASCONF; UNKNOWN ------------------>

... where ASCONF chunk of length 280 contains 2 parameters ...

  1) Add IP address parameter (param length: 16)
  2) Add/del IP address parameter (param length: 255)

... followed by an UNKNOWN chunk of e.g. 4 bytes. Here, the
Address Parameter in the ASCONF chunk is even missing, too.
This is just an example and similarly-crafted ASCONF chunks
could be used just as well.

The ASCONF chunk passes through sctp_verify_asconf() as all
parameters passed sanity checks, and after walking, we ended
up successfully at the chunk end boundary, and thus may invoke
sctp_process_asconf(). Parameter walking is done with
WORD_ROUND() to take padding into account.

In sctp_process_asconf()'s TLV processing, we may fail in
sctp_process_asconf_param() e.g., due to removal of the IP
address that is also the source address of the packet containing
the ASCONF chunk, and thus we need to add all TLVs after the
failure to our ASCONF response to remote via helper function
sctp_add_asconf_response(), which basically invokes a
sctp_addto_chunk() adding the error parameters to the given
skb.

When walking to the next parameter this time, we proceed
with ...

  length = ntohs(asconf_param->param_hdr.length);
  asconf_param = (void *)asconf_param + length;

... instead of the WORD_ROUND()'ed length, thus resulting here
in an off-by-one that leads to reading the follow-up garbage
parameter length of 12336, and thus throwing an skb_over_panic
for the reply when trying to sctp_addto_chunk() next time,
which implicitly calls the skb_put() with that length.

Fix it by using sctp_walk_params() [ which is also used in
INIT parameter processing ] macro in the verification *and*
in ASCONF processing: it will make sure we don't spill over,
that we walk parameters WORD_ROUND()'ed. Moreover, we're being
more defensive and guard against unknown parameter types and
missized addresses.

Joint work with Vlad Yasevich.

Fixes: b896b82be4ae ("[SCTP] ADDIP: Support for processing incoming ASCONF_ACK chunks.")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Vlad Yasevich <vyasevich@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sm.h    |  6 +--
 net/sctp/sm_make_chunk.c | 99 +++++++++++++++++++++++++++---------------------
 net/sctp/sm_statefuns.c  | 18 +--------
 3 files changed, 60 insertions(+), 63 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 7f4eeb340a54..72a31db47ded 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -248,9 +248,9 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *,
 					      int, __be16);
 struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc,
 					     union sctp_addr *addr);
-int sctp_verify_asconf(const struct sctp_association *asoc,
-		       struct sctp_paramhdr *param_hdr, void *chunk_end,
-		       struct sctp_paramhdr **errp);
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+			struct sctp_chunk *chunk, bool addr_param_needed,
+			struct sctp_paramhdr **errp);
 struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 				       struct sctp_chunk *asconf);
 int sctp_process_asconf_ack(struct sctp_association *asoc,
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index ae0e616a7ca5..ab734be8cb20 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -3110,50 +3110,63 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
 	return SCTP_ERROR_NO_ERROR;
 }
 
-/* Verify the ASCONF packet before we process it.  */
-int sctp_verify_asconf(const struct sctp_association *asoc,
-		       struct sctp_paramhdr *param_hdr, void *chunk_end,
-		       struct sctp_paramhdr **errp) {
-	sctp_addip_param_t *asconf_param;
+/* Verify the ASCONF packet before we process it. */
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+			struct sctp_chunk *chunk, bool addr_param_needed,
+			struct sctp_paramhdr **errp)
+{
+	sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr;
 	union sctp_params param;
-	int length, plen;
-
-	param.v = (sctp_paramhdr_t *) param_hdr;
-	while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) {
-		length = ntohs(param.p->length);
-		*errp = param.p;
+	bool addr_param_seen = false;
 
-		if (param.v > chunk_end - length ||
-		    length < sizeof(sctp_paramhdr_t))
-			return 0;
+	sctp_walk_params(param, addip, addip_hdr.params) {
+		size_t length = ntohs(param.p->length);
 
+		*errp = param.p;
 		switch (param.p->type) {
+		case SCTP_PARAM_ERR_CAUSE:
+			break;
+		case SCTP_PARAM_IPV4_ADDRESS:
+			if (length != sizeof(sctp_ipv4addr_param_t))
+				return false;
+			addr_param_seen = true;
+			break;
+		case SCTP_PARAM_IPV6_ADDRESS:
+			if (length != sizeof(sctp_ipv6addr_param_t))
+				return false;
+			addr_param_seen = true;
+			break;
 		case SCTP_PARAM_ADD_IP:
 		case SCTP_PARAM_DEL_IP:
 		case SCTP_PARAM_SET_PRIMARY:
-			asconf_param = (sctp_addip_param_t *)param.v;
-			plen = ntohs(asconf_param->param_hdr.length);
-			if (plen < sizeof(sctp_addip_param_t) +
-			    sizeof(sctp_paramhdr_t))
-				return 0;
+			/* In ASCONF chunks, these need to be first. */
+			if (addr_param_needed && !addr_param_seen)
+				return false;
+			length = ntohs(param.addip->param_hdr.length);
+			if (length < sizeof(sctp_addip_param_t) +
+				     sizeof(sctp_paramhdr_t))
+				return false;
 			break;
 		case SCTP_PARAM_SUCCESS_REPORT:
 		case SCTP_PARAM_ADAPTATION_LAYER_IND:
 			if (length != sizeof(sctp_addip_param_t))
-				return 0;
-
+				return false;
 			break;
 		default:
-			break;
+			/* This is unkown to us, reject! */
+			return false;
 		}
-
-		param.v += WORD_ROUND(length);
 	}
 
-	if (param.v != chunk_end)
-		return 0;
+	/* Remaining sanity checks. */
+	if (addr_param_needed && !addr_param_seen)
+		return false;
+	if (!addr_param_needed && addr_param_seen)
+		return false;
+	if (param.v != chunk->chunk_end)
+		return false;
 
-	return 1;
+	return true;
 }
 
 /* Process an incoming ASCONF chunk with the next expected serial no. and
@@ -3162,16 +3175,17 @@ int sctp_verify_asconf(const struct sctp_association *asoc,
 struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 				       struct sctp_chunk *asconf)
 {
+	sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr;
+	bool all_param_pass = true;
+	union sctp_params param;
 	sctp_addiphdr_t		*hdr;
 	union sctp_addr_param	*addr_param;
 	sctp_addip_param_t	*asconf_param;
 	struct sctp_chunk	*asconf_ack;
-
 	__be16	err_code;
 	int	length = 0;
 	int	chunk_len;
 	__u32	serial;
-	int	all_param_pass = 1;
 
 	chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t);
 	hdr = (sctp_addiphdr_t *)asconf->skb->data;
@@ -3199,9 +3213,14 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 		goto done;
 
 	/* Process the TLVs contained within the ASCONF chunk. */
-	while (chunk_len > 0) {
+	sctp_walk_params(param, addip, addip_hdr.params) {
+		/* Skip preceeding address parameters. */
+		if (param.p->type == SCTP_PARAM_IPV4_ADDRESS ||
+		    param.p->type == SCTP_PARAM_IPV6_ADDRESS)
+			continue;
+
 		err_code = sctp_process_asconf_param(asoc, asconf,
-						     asconf_param);
+						     param.addip);
 		/* ADDIP 4.1 A7)
 		 * If an error response is received for a TLV parameter,
 		 * all TLVs with no response before the failed TLV are
@@ -3209,28 +3228,20 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 		 * the failed response are considered unsuccessful unless
 		 * a specific success indication is present for the parameter.
 		 */
-		if (SCTP_ERROR_NO_ERROR != err_code)
-			all_param_pass = 0;
-
+		if (err_code != SCTP_ERROR_NO_ERROR)
+			all_param_pass = false;
 		if (!all_param_pass)
-			sctp_add_asconf_response(asconf_ack,
-						 asconf_param->crr_id, err_code,
-						 asconf_param);
+			sctp_add_asconf_response(asconf_ack, param.addip->crr_id,
+						 err_code, param.addip);
 
 		/* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add
 		 * an IP address sends an 'Out of Resource' in its response, it
 		 * MUST also fail any subsequent add or delete requests bundled
 		 * in the ASCONF.
 		 */
-		if (SCTP_ERROR_RSRC_LOW == err_code)
+		if (err_code == SCTP_ERROR_RSRC_LOW)
 			goto done;
-
-		/* Move to the next ASCONF param. */
-		length = ntohs(asconf_param->param_hdr.length);
-		asconf_param = (void *)asconf_param + length;
-		chunk_len -= length;
 	}
-
 done:
 	asoc->peer.addip_serial++;
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c8f606324134..bdea3dfbad31 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3591,9 +3591,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net,
 	struct sctp_chunk	*asconf_ack = NULL;
 	struct sctp_paramhdr	*err_param = NULL;
 	sctp_addiphdr_t		*hdr;
-	union sctp_addr_param	*addr_param;
 	__u32			serial;
-	int			length;
 
 	if (!sctp_vtag_verify(chunk, asoc)) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG,
@@ -3618,17 +3616,8 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net,
 	hdr = (sctp_addiphdr_t *)chunk->skb->data;
 	serial = ntohl(hdr->serial);
 
-	addr_param = (union sctp_addr_param *)hdr->params;
-	length = ntohs(addr_param->p.length);
-	if (length < sizeof(sctp_paramhdr_t))
-		return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
-			   (void *)addr_param, commands);
-
 	/* Verify the ASCONF chunk before processing it. */
-	if (!sctp_verify_asconf(asoc,
-			    (sctp_paramhdr_t *)((void *)addr_param + length),
-			    (void *)chunk->chunk_end,
-			    &err_param))
+	if (!sctp_verify_asconf(asoc, chunk, true, &err_param))
 		return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
 						  (void *)err_param, commands);
 
@@ -3745,10 +3734,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net,
 	rcvd_serial = ntohl(addip_hdr->serial);
 
 	/* Verify the ASCONF-ACK chunk before processing it. */
-	if (!sctp_verify_asconf(asoc,
-	    (sctp_paramhdr_t *)addip_hdr->params,
-	    (void *)asconf_ack->chunk_end,
-	    &err_param))
+	if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param))
 		return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
 			   (void *)err_param, commands);
 
-- 
cgit v1.2.3


From b69040d8e39f20d5215a03502a8e8b4c6ab78395 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Thu, 9 Oct 2014 22:55:32 +0200
Subject: net: sctp: fix panic on duplicate ASCONF chunks

When receiving a e.g. semi-good formed connection scan in the
form of ...

  -------------- INIT[ASCONF; ASCONF_ACK] ------------->
  <----------- INIT-ACK[ASCONF; ASCONF_ACK] ------------
  -------------------- COOKIE-ECHO -------------------->
  <-------------------- COOKIE-ACK ---------------------
  ---------------- ASCONF_a; ASCONF_b ----------------->

... where ASCONF_a equals ASCONF_b chunk (at least both serials
need to be equal), we panic an SCTP server!

The problem is that good-formed ASCONF chunks that we reply with
ASCONF_ACK chunks are cached per serial. Thus, when we receive a
same ASCONF chunk twice (e.g. through a lost ASCONF_ACK), we do
not need to process them again on the server side (that was the
idea, also proposed in the RFC). Instead, we know it was cached
and we just resend the cached chunk instead. So far, so good.

Where things get nasty is in SCTP's side effect interpreter, that
is, sctp_cmd_interpreter():

While incoming ASCONF_a (chunk = event_arg) is being marked
!end_of_packet and !singleton, and we have an association context,
we do not flush the outqueue the first time after processing the
ASCONF_ACK singleton chunk via SCTP_CMD_REPLY. Instead, we keep it
queued up, although we set local_cork to 1. Commit 2e3216cd54b1
changed the precedence, so that as long as we get bundled, incoming
chunks we try possible bundling on outgoing queue as well. Before
this commit, we would just flush the output queue.

Now, while ASCONF_a's ASCONF_ACK sits in the corked outq, we
continue to process the same ASCONF_b chunk from the packet. As
we have cached the previous ASCONF_ACK, we find it, grab it and
do another SCTP_CMD_REPLY command on it. So, effectively, we rip
the chunk->list pointers and requeue the same ASCONF_ACK chunk
another time. Since we process ASCONF_b, it's correctly marked
with end_of_packet and we enforce an uncork, and thus flush, thus
crashing the kernel.

Fix it by testing if the ASCONF_ACK is currently pending and if
that is the case, do not requeue it. When flushing the output
queue we may relink the chunk for preparing an outgoing packet,
but eventually unlink it when it's copied into the skb right
before transmission.

Joint work with Vlad Yasevich.

Fixes: 2e3216cd54b1 ("sctp: Follow security requirement of responding with 1 packet")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 5 +++++
 net/sctp/associola.c    | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 9fbd856e6713..856f01cb51dd 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -426,6 +426,11 @@ static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_associat
 	asoc->pmtu_pending = 0;
 }
 
+static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk)
+{
+	return !list_empty(&chunk->list);
+}
+
 /* Walk through a list of TLV parameters.  Don't trust the
  * individual parameter lengths and instead depend on
  * the chunk length to indicate when to stop.  Make sure
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index a88b8524846e..f791edd64d6c 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1668,6 +1668,8 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
 	 * ack chunk whose serial number matches that of the request.
 	 */
 	list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) {
+		if (sctp_chunk_pending(ack))
+			continue;
 		if (ack->subh.addip_hdr->serial == serial) {
 			sctp_chunk_hold(ack);
 			return ack;
-- 
cgit v1.2.3


From 31eff81e94472ddb7549509bf4b6e93e1f6f7dc9 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Fri, 10 Oct 2014 23:10:47 +0200
Subject: skbuff: fix ftrace handling in skb_unshare

If the skb is not dropped afterwards we should run consume_skb instead
kfree_skb. Inside of function skb_unshare we do always a kfree_skb,
doesn't depend if skb_copy failed or was successful.

This patch switch this behaviour like skb_share_check, if allocation of
sk_buff failed we use kfree_skb otherwise consume_skb.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3ab0749d6875..a59d9343c25b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1203,7 +1203,12 @@ static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
 	might_sleep_if(pri & __GFP_WAIT);
 	if (skb_cloned(skb)) {
 		struct sk_buff *nskb = skb_copy(skb, pri);
-		kfree_skb(skb);	/* Free our shared copy */
+
+		/* Free our shared copy */
+		if (likely(nskb))
+			consume_skb(skb);
+		else
+			kfree_skb(skb);
 		skb = nskb;
 	}
 	return skb;
-- 
cgit v1.2.3


From 02ea80741a25435123e8a5ca40cac6a0bcf0c9f1 Mon Sep 17 00:00:00 2001
From: Li RongQing <roy.qing.li@gmail.com>
Date: Sat, 11 Oct 2014 13:03:34 +0800
Subject: ipv6: remove aca_lock spinlock from struct ifacaddr6

no user uses this lock.

Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/if_inet6.h | 1 -
 net/ipv6/anycast.c     | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 55a8d4056cc9..98e5f9578f86 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -146,7 +146,6 @@ struct ifacaddr6 {
 	struct ifacaddr6	*aca_next;
 	int			aca_users;
 	atomic_t		aca_refcnt;
-	spinlock_t		aca_lock;
 	unsigned long		aca_cstamp;
 	unsigned long		aca_tstamp;
 };
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index f5e319a8d4e2..baf2742d1ec4 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -235,7 +235,6 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
 	/* aca_tstamp should be updated upon changes */
 	aca->aca_cstamp = aca->aca_tstamp = jiffies;
 	atomic_set(&aca->aca_refcnt, 1);
-	spin_lock_init(&aca->aca_lock);
 
 	return aca;
 }
-- 
cgit v1.2.3


From 9ea8aa8d5087529210553114b7bc4bf4374ace8f Mon Sep 17 00:00:00 2001
From: Tilman Schmidt <tilman@imap.cc>
Date: Sat, 11 Oct 2014 13:46:30 +0200
Subject: isdn/capi: correct capi20_manufacturer argument type mismatch

Function capi20_manufacturer() is declared with unsigned int cmd
argument but called with unsigned long.
Fix by correcting the function prototype since the actual argument
is part of the user visible API.

Spotted with Coverity.

Signed-off-by: Tilman Schmidt <tilman@imap.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/capi/kcapi.c  | 4 ++--
 include/linux/kernelcapi.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index c123709acf82..823f6985b260 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -1184,7 +1184,7 @@ static int old_capi_manufacturer(unsigned int cmd, void __user *data)
  * Return value: CAPI result code
  */
 
-int capi20_manufacturer(unsigned int cmd, void __user *data)
+int capi20_manufacturer(unsigned long cmd, void __user *data)
 {
 	struct capi_ctr *ctr;
 	int retval;
@@ -1259,7 +1259,7 @@ int capi20_manufacturer(unsigned int cmd, void __user *data)
 	}
 
 	default:
-		printk(KERN_ERR "kcapi: manufacturer command %d unknown.\n",
+		printk(KERN_ERR "kcapi: manufacturer command %lu unknown.\n",
 		       cmd);
 		break;
 
diff --git a/include/linux/kernelcapi.h b/include/linux/kernelcapi.h
index 9be37da93680..e985ba679c4a 100644
--- a/include/linux/kernelcapi.h
+++ b/include/linux/kernelcapi.h
@@ -41,7 +41,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 buf[CAPI_MANUFACTURER_LEN]);
 u16 capi20_get_version(u32 contr, struct capi_version *verp);
 u16 capi20_get_serial(u32 contr, u8 serial[CAPI_SERIAL_LEN]);
 u16 capi20_get_profile(u32 contr, struct capi_profile *profp);
-int capi20_manufacturer(unsigned int cmd, void __user *data);
+int capi20_manufacturer(unsigned long cmd, void __user *data);
 
 #define CAPICTR_UP			0
 #define CAPICTR_DOWN			1
-- 
cgit v1.2.3


From e4339d28f640a7c0d92903bcf389a2dfa281270d Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zyan@redhat.com>
Date: Tue, 16 Sep 2014 17:50:45 +0800
Subject: libceph: reference counting pagelist

this allow pagelist to present data that may be sent multiple times.

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
---
 fs/ceph/mds_client.c          | 1 -
 include/linux/ceph/pagelist.h | 5 ++++-
 net/ceph/messenger.c          | 4 +---
 net/ceph/pagelist.c           | 7 +++++--
 4 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 5474feb77743..b4430ce1b3f6 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2865,7 +2865,6 @@ fail:
 	mutex_unlock(&session->s_mutex);
 fail_nomsg:
 	ceph_pagelist_release(pagelist);
-	kfree(pagelist);
 fail_nopagelist:
 	pr_err("error %d preparing reconnect for mds%d\n", err, mds);
 	return;
diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h
index 9660d6b0a35d..5f871d84ddce 100644
--- a/include/linux/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -2,6 +2,7 @@
 #define __FS_CEPH_PAGELIST_H
 
 #include <linux/list.h>
+#include <linux/atomic.h>
 
 struct ceph_pagelist {
 	struct list_head head;
@@ -10,6 +11,7 @@ struct ceph_pagelist {
 	size_t room;
 	struct list_head free_list;
 	size_t num_pages_free;
+	atomic_t refcnt;
 };
 
 struct ceph_pagelist_cursor {
@@ -26,9 +28,10 @@ static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
 	pl->room = 0;
 	INIT_LIST_HEAD(&pl->free_list);
 	pl->num_pages_free = 0;
+	atomic_set(&pl->refcnt, 1);
 }
 
-extern int ceph_pagelist_release(struct ceph_pagelist *pl);
+extern void ceph_pagelist_release(struct ceph_pagelist *pl);
 
 extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l);
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index e7d94113f2d6..9764c771cfb1 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -3071,10 +3071,8 @@ static void ceph_msg_data_destroy(struct ceph_msg_data *data)
 		return;
 
 	WARN_ON(!list_empty(&data->links));
-	if (data->type == CEPH_MSG_DATA_PAGELIST) {
+	if (data->type == CEPH_MSG_DATA_PAGELIST)
 		ceph_pagelist_release(data->pagelist);
-		kfree(data->pagelist);
-	}
 	kmem_cache_free(ceph_msg_data_cache, data);
 }
 
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
index 92866bebb65f..c7c220a736e5 100644
--- a/net/ceph/pagelist.c
+++ b/net/ceph/pagelist.c
@@ -1,5 +1,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/ceph/pagelist.h>
@@ -13,8 +14,10 @@ static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
 	}
 }
 
-int ceph_pagelist_release(struct ceph_pagelist *pl)
+void ceph_pagelist_release(struct ceph_pagelist *pl)
 {
+	if (!atomic_dec_and_test(&pl->refcnt))
+		return;
 	ceph_pagelist_unmap_tail(pl);
 	while (!list_empty(&pl->head)) {
 		struct page *page = list_first_entry(&pl->head, struct page,
@@ -23,7 +26,7 @@ int ceph_pagelist_release(struct ceph_pagelist *pl)
 		__free_page(page);
 	}
 	ceph_pagelist_free_reserve(pl);
-	return 0;
+	kfree(pl);
 }
 EXPORT_SYMBOL(ceph_pagelist_release);
 
-- 
cgit v1.2.3


From eb179d3975c804ad98eaa403425eb6e48cfd3cc2 Mon Sep 17 00:00:00 2001
From: Fabian Frederick <fabf@skynet.be>
Date: Tue, 30 Sep 2014 22:07:50 +0200
Subject: libceph: remove redundant declaration

ceph_release_page_vector was defined twice in libceph.h

Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
---
 include/linux/ceph/libceph.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 279b0afac1c1..07bc359b88ac 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -211,7 +211,6 @@ extern struct page **ceph_get_direct_page_vector(const void __user *data,
 						 bool write_page);
 extern void ceph_put_page_vector(struct page **pages, int num_pages,
 				 bool dirty);
-extern void ceph_release_page_vector(struct page **pages, int num_pages);
 extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
 extern int ceph_copy_user_to_page_vector(struct page **pages,
 					 const void __user *data,
-- 
cgit v1.2.3


From 70b5bfa360aea4157b45c2863746ca67896c6ef1 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@redhat.com>
Date: Thu, 2 Oct 2014 17:22:29 +0400
Subject: libceph: sync osd op definitions in rados.h

Bring in missing osd ops and strings, use macros to eliminate multiple
points of maintenance.

Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
---
 include/linux/ceph/rados.h | 225 ++++++++++++++++++++++++++-------------------
 net/ceph/ceph_strings.c    |  75 +--------------
 net/ceph/osd_client.c      |  65 +------------
 3 files changed, 137 insertions(+), 228 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index f20e0d8a2155..2f822dca1046 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -172,6 +172,7 @@ extern const char *ceph_osd_state_name(int s);
 #define CEPH_OSD_OP_MODE_WR    0x2000
 #define CEPH_OSD_OP_MODE_RMW   0x3000
 #define CEPH_OSD_OP_MODE_SUB   0x4000
+#define CEPH_OSD_OP_MODE_CACHE 0x8000
 
 #define CEPH_OSD_OP_TYPE       0x0f00
 #define CEPH_OSD_OP_TYPE_LOCK  0x0100
@@ -181,103 +182,135 @@ extern const char *ceph_osd_state_name(int s);
 #define CEPH_OSD_OP_TYPE_PG    0x0500
 #define CEPH_OSD_OP_TYPE_MULTI 0x0600 /* multiobject */
 
+#define __CEPH_OSD_OP1(mode, nr) \
+	(CEPH_OSD_OP_MODE_##mode | (nr))
+
+#define __CEPH_OSD_OP(mode, type, nr) \
+	(CEPH_OSD_OP_MODE_##mode | CEPH_OSD_OP_TYPE_##type | (nr))
+
+#define __CEPH_FORALL_OSD_OPS(f)					    \
+	/** data **/							    \
+	/* read */							    \
+	f(READ,		__CEPH_OSD_OP(RD, DATA, 1),	"read")		    \
+	f(STAT,		__CEPH_OSD_OP(RD, DATA, 2),	"stat")		    \
+	f(MAPEXT,	__CEPH_OSD_OP(RD, DATA, 3),	"mapext")	    \
+									    \
+	/* fancy read */						    \
+	f(MASKTRUNC,	__CEPH_OSD_OP(RD, DATA, 4),	"masktrunc")	    \
+	f(SPARSE_READ,	__CEPH_OSD_OP(RD, DATA, 5),	"sparse-read")	    \
+									    \
+	f(NOTIFY,	__CEPH_OSD_OP(RD, DATA, 6),	"notify")	    \
+	f(NOTIFY_ACK,	__CEPH_OSD_OP(RD, DATA, 7),	"notify-ack")	    \
+									    \
+	/* versioning */						    \
+	f(ASSERT_VER,	__CEPH_OSD_OP(RD, DATA, 8),	"assert-version")   \
+									    \
+	f(LIST_WATCHERS, __CEPH_OSD_OP(RD, DATA, 9),	"list-watchers")    \
+									    \
+	f(LIST_SNAPS,	__CEPH_OSD_OP(RD, DATA, 10),	"list-snaps")	    \
+									    \
+	/* sync */							    \
+	f(SYNC_READ,	__CEPH_OSD_OP(RD, DATA, 11),	"sync_read")	    \
+									    \
+	/* write */							    \
+	f(WRITE,	__CEPH_OSD_OP(WR, DATA, 1),	"write")	    \
+	f(WRITEFULL,	__CEPH_OSD_OP(WR, DATA, 2),	"writefull")	    \
+	f(TRUNCATE,	__CEPH_OSD_OP(WR, DATA, 3),	"truncate")	    \
+	f(ZERO,		__CEPH_OSD_OP(WR, DATA, 4),	"zero")		    \
+	f(DELETE,	__CEPH_OSD_OP(WR, DATA, 5),	"delete")	    \
+									    \
+	/* fancy write */						    \
+	f(APPEND,	__CEPH_OSD_OP(WR, DATA, 6),	"append")	    \
+	f(STARTSYNC,	__CEPH_OSD_OP(WR, DATA, 7),	"startsync")	    \
+	f(SETTRUNC,	__CEPH_OSD_OP(WR, DATA, 8),	"settrunc")	    \
+	f(TRIMTRUNC,	__CEPH_OSD_OP(WR, DATA, 9),	"trimtrunc")	    \
+									    \
+	f(TMAPUP,	__CEPH_OSD_OP(RMW, DATA, 10),	"tmapup")	    \
+	f(TMAPPUT,	__CEPH_OSD_OP(WR, DATA, 11),	"tmapput")	    \
+	f(TMAPGET,	__CEPH_OSD_OP(RD, DATA, 12),	"tmapget")	    \
+									    \
+	f(CREATE,	__CEPH_OSD_OP(WR, DATA, 13),	"create")	    \
+	f(ROLLBACK,	__CEPH_OSD_OP(WR, DATA, 14),	"rollback")	    \
+									    \
+	f(WATCH,	__CEPH_OSD_OP(WR, DATA, 15),	"watch")	    \
+									    \
+	/* omap */							    \
+	f(OMAPGETKEYS,	__CEPH_OSD_OP(RD, DATA, 17),	"omap-get-keys")    \
+	f(OMAPGETVALS,	__CEPH_OSD_OP(RD, DATA, 18),	"omap-get-vals")    \
+	f(OMAPGETHEADER, __CEPH_OSD_OP(RD, DATA, 19),	"omap-get-header")  \
+	f(OMAPGETVALSBYKEYS, __CEPH_OSD_OP(RD, DATA, 20), "omap-get-vals-by-keys") \
+	f(OMAPSETVALS,	__CEPH_OSD_OP(WR, DATA, 21),	"omap-set-vals")    \
+	f(OMAPSETHEADER, __CEPH_OSD_OP(WR, DATA, 22),	"omap-set-header")  \
+	f(OMAPCLEAR,	__CEPH_OSD_OP(WR, DATA, 23),	"omap-clear")	    \
+	f(OMAPRMKEYS,	__CEPH_OSD_OP(WR, DATA, 24),	"omap-rm-keys")	    \
+	f(OMAP_CMP,	__CEPH_OSD_OP(RD, DATA, 25),	"omap-cmp")	    \
+									    \
+	/* tiering */							    \
+	f(COPY_FROM,	__CEPH_OSD_OP(WR, DATA, 26),	"copy-from")	    \
+	f(COPY_GET_CLASSIC, __CEPH_OSD_OP(RD, DATA, 27), "copy-get-classic") \
+	f(UNDIRTY,	__CEPH_OSD_OP(WR, DATA, 28),	"undirty")	    \
+	f(ISDIRTY,	__CEPH_OSD_OP(RD, DATA, 29),	"isdirty")	    \
+	f(COPY_GET,	__CEPH_OSD_OP(RD, DATA, 30),	"copy-get")	    \
+	f(CACHE_FLUSH,	__CEPH_OSD_OP(CACHE, DATA, 31),	"cache-flush")	    \
+	f(CACHE_EVICT,	__CEPH_OSD_OP(CACHE, DATA, 32),	"cache-evict")	    \
+	f(CACHE_TRY_FLUSH, __CEPH_OSD_OP(CACHE, DATA, 33), "cache-try-flush") \
+									    \
+	/* convert tmap to omap */					    \
+	f(TMAP2OMAP,	__CEPH_OSD_OP(RMW, DATA, 34),	"tmap2omap")	    \
+									    \
+	/* hints */							    \
+	f(SETALLOCHINT,	__CEPH_OSD_OP(WR, DATA, 35),	"set-alloc-hint")   \
+									    \
+	/** multi **/							    \
+	f(CLONERANGE,	__CEPH_OSD_OP(WR, MULTI, 1),	"clonerange")	    \
+	f(ASSERT_SRC_VERSION, __CEPH_OSD_OP(RD, MULTI, 2), "assert-src-version") \
+	f(SRC_CMPXATTR,	__CEPH_OSD_OP(RD, MULTI, 3),	"src-cmpxattr")	    \
+									    \
+	/** attrs **/							    \
+	/* read */							    \
+	f(GETXATTR,	__CEPH_OSD_OP(RD, ATTR, 1),	"getxattr")	    \
+	f(GETXATTRS,	__CEPH_OSD_OP(RD, ATTR, 2),	"getxattrs")	    \
+	f(CMPXATTR,	__CEPH_OSD_OP(RD, ATTR, 3),	"cmpxattr")	    \
+									    \
+	/* write */							    \
+	f(SETXATTR,	__CEPH_OSD_OP(WR, ATTR, 1),	"setxattr")	    \
+	f(SETXATTRS,	__CEPH_OSD_OP(WR, ATTR, 2),	"setxattrs")	    \
+	f(RESETXATTRS,	__CEPH_OSD_OP(WR, ATTR, 3),	"resetxattrs")	    \
+	f(RMXATTR,	__CEPH_OSD_OP(WR, ATTR, 4),	"rmxattr")	    \
+									    \
+	/** subop **/							    \
+	f(PULL,		__CEPH_OSD_OP1(SUB, 1),		"pull")		    \
+	f(PUSH,		__CEPH_OSD_OP1(SUB, 2),		"push")		    \
+	f(BALANCEREADS,	__CEPH_OSD_OP1(SUB, 3),		"balance-reads")    \
+	f(UNBALANCEREADS, __CEPH_OSD_OP1(SUB, 4),	"unbalance-reads")  \
+	f(SCRUB,	__CEPH_OSD_OP1(SUB, 5),		"scrub")	    \
+	f(SCRUB_RESERVE, __CEPH_OSD_OP1(SUB, 6),	"scrub-reserve")    \
+	f(SCRUB_UNRESERVE, __CEPH_OSD_OP1(SUB, 7),	"scrub-unreserve")  \
+	f(SCRUB_STOP,	__CEPH_OSD_OP1(SUB, 8),		"scrub-stop")	    \
+	f(SCRUB_MAP,	__CEPH_OSD_OP1(SUB, 9),		"scrub-map")	    \
+									    \
+	/** lock **/							    \
+	f(WRLOCK,	__CEPH_OSD_OP(WR, LOCK, 1),	"wrlock")	    \
+	f(WRUNLOCK,	__CEPH_OSD_OP(WR, LOCK, 2),	"wrunlock")	    \
+	f(RDLOCK,	__CEPH_OSD_OP(WR, LOCK, 3),	"rdlock")	    \
+	f(RDUNLOCK,	__CEPH_OSD_OP(WR, LOCK, 4),	"rdunlock")	    \
+	f(UPLOCK,	__CEPH_OSD_OP(WR, LOCK, 5),	"uplock")	    \
+	f(DNLOCK,	__CEPH_OSD_OP(WR, LOCK, 6),	"dnlock")	    \
+									    \
+	/** exec **/							    \
+	/* note: the RD bit here is wrong; see special-case below in helper */ \
+	f(CALL,		__CEPH_OSD_OP(RD, EXEC, 1),	"call")		    \
+									    \
+	/** pg **/							    \
+	f(PGLS,		__CEPH_OSD_OP(RD, PG, 1),	"pgls")		    \
+	f(PGLS_FILTER,	__CEPH_OSD_OP(RD, PG, 2),	"pgls-filter")	    \
+	f(PG_HITSET_LS,	__CEPH_OSD_OP(RD, PG, 3),	"pg-hitset-ls")	    \
+	f(PG_HITSET_GET, __CEPH_OSD_OP(RD, PG, 4),	"pg-hitset-get")
+
 enum {
-	/** data **/
-	/* read */
-	CEPH_OSD_OP_READ      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1,
-	CEPH_OSD_OP_STAT      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2,
-	CEPH_OSD_OP_MAPEXT    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 3,
-
-	/* fancy read */
-	CEPH_OSD_OP_MASKTRUNC   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4,
-	CEPH_OSD_OP_SPARSE_READ = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 5,
-
-	CEPH_OSD_OP_NOTIFY    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 6,
-	CEPH_OSD_OP_NOTIFY_ACK = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 7,
-
-	/* versioning */
-	CEPH_OSD_OP_ASSERT_VER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 8,
-
-	/* write */
-	CEPH_OSD_OP_WRITE     = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1,
-	CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2,
-	CEPH_OSD_OP_TRUNCATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3,
-	CEPH_OSD_OP_ZERO      = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4,
-	CEPH_OSD_OP_DELETE    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5,
-
-	/* fancy write */
-	CEPH_OSD_OP_APPEND    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6,
-	CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7,
-	CEPH_OSD_OP_SETTRUNC  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8,
-	CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9,
-
-	CEPH_OSD_OP_TMAPUP  = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10,
-	CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11,
-	CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12,
-
-	CEPH_OSD_OP_CREATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13,
-	CEPH_OSD_OP_ROLLBACK= CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 14,
-
-	CEPH_OSD_OP_WATCH   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 15,
-
-	/* omap */
-	CEPH_OSD_OP_OMAPGETKEYS   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 17,
-	CEPH_OSD_OP_OMAPGETVALS   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 18,
-	CEPH_OSD_OP_OMAPGETHEADER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 19,
-	CEPH_OSD_OP_OMAPGETVALSBYKEYS  =
-	  CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 20,
-	CEPH_OSD_OP_OMAPSETVALS   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 21,
-	CEPH_OSD_OP_OMAPSETHEADER = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 22,
-	CEPH_OSD_OP_OMAPCLEAR     = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 23,
-	CEPH_OSD_OP_OMAPRMKEYS    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 24,
-	CEPH_OSD_OP_OMAP_CMP      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 25,
-
-	/* hints */
-	CEPH_OSD_OP_SETALLOCHINT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 35,
-
-	/** multi **/
-	CEPH_OSD_OP_CLONERANGE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_MULTI | 1,
-	CEPH_OSD_OP_ASSERT_SRC_VERSION = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 2,
-	CEPH_OSD_OP_SRC_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 3,
-
-	/** attrs **/
-	/* read */
-	CEPH_OSD_OP_GETXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1,
-	CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2,
-	CEPH_OSD_OP_CMPXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 3,
-
-	/* write */
-	CEPH_OSD_OP_SETXATTR  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1,
-	CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2,
-	CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3,
-	CEPH_OSD_OP_RMXATTR   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4,
-
-	/** subop **/
-	CEPH_OSD_OP_PULL            = CEPH_OSD_OP_MODE_SUB | 1,
-	CEPH_OSD_OP_PUSH            = CEPH_OSD_OP_MODE_SUB | 2,
-	CEPH_OSD_OP_BALANCEREADS    = CEPH_OSD_OP_MODE_SUB | 3,
-	CEPH_OSD_OP_UNBALANCEREADS  = CEPH_OSD_OP_MODE_SUB | 4,
-	CEPH_OSD_OP_SCRUB           = CEPH_OSD_OP_MODE_SUB | 5,
-	CEPH_OSD_OP_SCRUB_RESERVE   = CEPH_OSD_OP_MODE_SUB | 6,
-	CEPH_OSD_OP_SCRUB_UNRESERVE = CEPH_OSD_OP_MODE_SUB | 7,
-	CEPH_OSD_OP_SCRUB_STOP      = CEPH_OSD_OP_MODE_SUB | 8,
-	CEPH_OSD_OP_SCRUB_MAP     = CEPH_OSD_OP_MODE_SUB | 9,
-
-	/** lock **/
-	CEPH_OSD_OP_WRLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1,
-	CEPH_OSD_OP_WRUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2,
-	CEPH_OSD_OP_RDLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3,
-	CEPH_OSD_OP_RDUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4,
-	CEPH_OSD_OP_UPLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5,
-	CEPH_OSD_OP_DNLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6,
-
-	/** exec **/
-	/* note: the RD bit here is wrong; see special-case below in helper */
-	CEPH_OSD_OP_CALL    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1,
-
-	/** pg **/
-	CEPH_OSD_OP_PGLS      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1,
-	CEPH_OSD_OP_PGLS_FILTER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 2,
+#define GENERATE_ENUM_ENTRY(op, opcode, str)	CEPH_OSD_OP_##op = (opcode),
+__CEPH_FORALL_OSD_OPS(GENERATE_ENUM_ENTRY)
+#undef GENERATE_ENUM_ENTRY
 };
 
 static inline int ceph_osd_op_type_lock(int op)
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
index 1348df96fe15..30560202f57b 100644
--- a/net/ceph/ceph_strings.c
+++ b/net/ceph/ceph_strings.c
@@ -19,77 +19,12 @@ const char *ceph_entity_type_name(int type)
 const char *ceph_osd_op_name(int op)
 {
 	switch (op) {
-	case CEPH_OSD_OP_READ: return "read";
-	case CEPH_OSD_OP_STAT: return "stat";
-	case CEPH_OSD_OP_MAPEXT: return "mapext";
-	case CEPH_OSD_OP_SPARSE_READ: return "sparse-read";
-	case CEPH_OSD_OP_NOTIFY: return "notify";
-	case CEPH_OSD_OP_NOTIFY_ACK: return "notify-ack";
-	case CEPH_OSD_OP_ASSERT_VER: return "assert-version";
-
-	case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
-
-	case CEPH_OSD_OP_CREATE: return "create";
-	case CEPH_OSD_OP_WRITE: return "write";
-	case CEPH_OSD_OP_DELETE: return "delete";
-	case CEPH_OSD_OP_TRUNCATE: return "truncate";
-	case CEPH_OSD_OP_ZERO: return "zero";
-	case CEPH_OSD_OP_WRITEFULL: return "writefull";
-	case CEPH_OSD_OP_ROLLBACK: return "rollback";
-
-	case CEPH_OSD_OP_APPEND: return "append";
-	case CEPH_OSD_OP_STARTSYNC: return "startsync";
-	case CEPH_OSD_OP_SETTRUNC: return "settrunc";
-	case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
-
-	case CEPH_OSD_OP_TMAPUP: return "tmapup";
-	case CEPH_OSD_OP_TMAPGET: return "tmapget";
-	case CEPH_OSD_OP_TMAPPUT: return "tmapput";
-	case CEPH_OSD_OP_WATCH: return "watch";
-
-	case CEPH_OSD_OP_CLONERANGE: return "clonerange";
-	case CEPH_OSD_OP_ASSERT_SRC_VERSION: return "assert-src-version";
-	case CEPH_OSD_OP_SRC_CMPXATTR: return "src-cmpxattr";
-
-	case CEPH_OSD_OP_GETXATTR: return "getxattr";
-	case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
-	case CEPH_OSD_OP_SETXATTR: return "setxattr";
-	case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
-	case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
-	case CEPH_OSD_OP_RMXATTR: return "rmxattr";
-	case CEPH_OSD_OP_CMPXATTR: return "cmpxattr";
-
-	case CEPH_OSD_OP_PULL: return "pull";
-	case CEPH_OSD_OP_PUSH: return "push";
-	case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
-	case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
-	case CEPH_OSD_OP_SCRUB: return "scrub";
-	case CEPH_OSD_OP_SCRUB_RESERVE: return "scrub-reserve";
-	case CEPH_OSD_OP_SCRUB_UNRESERVE: return "scrub-unreserve";
-	case CEPH_OSD_OP_SCRUB_STOP: return "scrub-stop";
-	case CEPH_OSD_OP_SCRUB_MAP: return "scrub-map";
-
-	case CEPH_OSD_OP_WRLOCK: return "wrlock";
-	case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
-	case CEPH_OSD_OP_RDLOCK: return "rdlock";
-	case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
-	case CEPH_OSD_OP_UPLOCK: return "uplock";
-	case CEPH_OSD_OP_DNLOCK: return "dnlock";
-
-	case CEPH_OSD_OP_CALL: return "call";
-
-	case CEPH_OSD_OP_PGLS: return "pgls";
-	case CEPH_OSD_OP_PGLS_FILTER: return "pgls-filter";
-	case CEPH_OSD_OP_OMAPGETKEYS: return "omap-get-keys";
-	case CEPH_OSD_OP_OMAPGETVALS: return "omap-get-vals";
-	case CEPH_OSD_OP_OMAPGETHEADER: return "omap-get-header";
-	case CEPH_OSD_OP_OMAPGETVALSBYKEYS: return "omap-get-vals-by-keys";
-	case CEPH_OSD_OP_OMAPSETVALS: return "omap-set-vals";
-	case CEPH_OSD_OP_OMAPSETHEADER: return "omap-set-header";
-	case CEPH_OSD_OP_OMAPCLEAR: return "omap-clear";
-	case CEPH_OSD_OP_OMAPRMKEYS: return "omap-rm-keys";
+#define GENERATE_CASE(op, opcode, str)	case CEPH_OSD_OP_##op: return (str);
+__CEPH_FORALL_OSD_OPS(GENERATE_CASE)
+#undef GENERATE_CASE
+	default:
+		return "???";
 	}
-	return "???";
 }
 
 const char *ceph_osd_state_name(int s)
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index a528ea34253a..f3fc54eac09d 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -431,68 +431,9 @@ EXPORT_SYMBOL(ceph_osdc_alloc_request);
 static bool osd_req_opcode_valid(u16 opcode)
 {
 	switch (opcode) {
-	case CEPH_OSD_OP_READ:
-	case CEPH_OSD_OP_STAT:
-	case CEPH_OSD_OP_MAPEXT:
-	case CEPH_OSD_OP_MASKTRUNC:
-	case CEPH_OSD_OP_SPARSE_READ:
-	case CEPH_OSD_OP_NOTIFY:
-	case CEPH_OSD_OP_NOTIFY_ACK:
-	case CEPH_OSD_OP_ASSERT_VER:
-	case CEPH_OSD_OP_WRITE:
-	case CEPH_OSD_OP_WRITEFULL:
-	case CEPH_OSD_OP_TRUNCATE:
-	case CEPH_OSD_OP_ZERO:
-	case CEPH_OSD_OP_DELETE:
-	case CEPH_OSD_OP_APPEND:
-	case CEPH_OSD_OP_STARTSYNC:
-	case CEPH_OSD_OP_SETTRUNC:
-	case CEPH_OSD_OP_TRIMTRUNC:
-	case CEPH_OSD_OP_TMAPUP:
-	case CEPH_OSD_OP_TMAPPUT:
-	case CEPH_OSD_OP_TMAPGET:
-	case CEPH_OSD_OP_CREATE:
-	case CEPH_OSD_OP_ROLLBACK:
-	case CEPH_OSD_OP_WATCH:
-	case CEPH_OSD_OP_OMAPGETKEYS:
-	case CEPH_OSD_OP_OMAPGETVALS:
-	case CEPH_OSD_OP_OMAPGETHEADER:
-	case CEPH_OSD_OP_OMAPGETVALSBYKEYS:
-	case CEPH_OSD_OP_OMAPSETVALS:
-	case CEPH_OSD_OP_OMAPSETHEADER:
-	case CEPH_OSD_OP_OMAPCLEAR:
-	case CEPH_OSD_OP_OMAPRMKEYS:
-	case CEPH_OSD_OP_OMAP_CMP:
-	case CEPH_OSD_OP_SETALLOCHINT:
-	case CEPH_OSD_OP_CLONERANGE:
-	case CEPH_OSD_OP_ASSERT_SRC_VERSION:
-	case CEPH_OSD_OP_SRC_CMPXATTR:
-	case CEPH_OSD_OP_GETXATTR:
-	case CEPH_OSD_OP_GETXATTRS:
-	case CEPH_OSD_OP_CMPXATTR:
-	case CEPH_OSD_OP_SETXATTR:
-	case CEPH_OSD_OP_SETXATTRS:
-	case CEPH_OSD_OP_RESETXATTRS:
-	case CEPH_OSD_OP_RMXATTR:
-	case CEPH_OSD_OP_PULL:
-	case CEPH_OSD_OP_PUSH:
-	case CEPH_OSD_OP_BALANCEREADS:
-	case CEPH_OSD_OP_UNBALANCEREADS:
-	case CEPH_OSD_OP_SCRUB:
-	case CEPH_OSD_OP_SCRUB_RESERVE:
-	case CEPH_OSD_OP_SCRUB_UNRESERVE:
-	case CEPH_OSD_OP_SCRUB_STOP:
-	case CEPH_OSD_OP_SCRUB_MAP:
-	case CEPH_OSD_OP_WRLOCK:
-	case CEPH_OSD_OP_WRUNLOCK:
-	case CEPH_OSD_OP_RDLOCK:
-	case CEPH_OSD_OP_RDUNLOCK:
-	case CEPH_OSD_OP_UPLOCK:
-	case CEPH_OSD_OP_DNLOCK:
-	case CEPH_OSD_OP_CALL:
-	case CEPH_OSD_OP_PGLS:
-	case CEPH_OSD_OP_PGLS_FILTER:
-		return true;
+#define GENERATE_CASE(op, opcode, str)	case CEPH_OSD_OP_##op: return true;
+__CEPH_FORALL_OSD_OPS(GENERATE_CASE)
+#undef GENERATE_CASE
 	default:
 		return false;
 	}
-- 
cgit v1.2.3


From c15952dc18d8a293d976ac6c06d44d9d98023b45 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Tue, 14 Oct 2014 02:08:54 -0700
Subject: net: filter: move common defines into bpf_common.h

userspace programs that use eBPF instruction macros need to include two files:
uapi/linux/filter.h and uapi/linux/bpf.h
Move common macro definitions that are shared between classic BPF and eBPF
into uapi/linux/bpf_common.h, so that user app can include only one bpf.h file

Cc: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/Kbuild       |  1 +
 include/uapi/linux/bpf.h        |  1 +
 include/uapi/linux/bpf_common.h | 55 ++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/filter.h     | 56 +----------------------------------------
 4 files changed, 58 insertions(+), 55 deletions(-)
 create mode 100644 include/uapi/linux/bpf_common.h

(limited to 'include')

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 70e150ebc6c9..1115d68b150f 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -68,6 +68,7 @@ header-y += binfmts.h
 header-y += blkpg.h
 header-y += blktrace_api.h
 header-y += bpf.h
+header-y += bpf_common.h
 header-y += bpqether.h
 header-y += bsg.h
 header-y += btrfs.h
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 31b0ac208a52..d18316f9e9c4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -8,6 +8,7 @@
 #define _UAPI__LINUX_BPF_H__
 
 #include <linux/types.h>
+#include <linux/bpf_common.h>
 
 /* Extended instruction set based on top of classic BPF */
 
diff --git a/include/uapi/linux/bpf_common.h b/include/uapi/linux/bpf_common.h
new file mode 100644
index 000000000000..a5c220e0828f
--- /dev/null
+++ b/include/uapi/linux/bpf_common.h
@@ -0,0 +1,55 @@
+#ifndef _UAPI__LINUX_BPF_COMMON_H__
+#define _UAPI__LINUX_BPF_COMMON_H__
+
+/* Instruction classes */
+#define BPF_CLASS(code) ((code) & 0x07)
+#define		BPF_LD		0x00
+#define		BPF_LDX		0x01
+#define		BPF_ST		0x02
+#define		BPF_STX		0x03
+#define		BPF_ALU		0x04
+#define		BPF_JMP		0x05
+#define		BPF_RET		0x06
+#define		BPF_MISC        0x07
+
+/* ld/ldx fields */
+#define BPF_SIZE(code)  ((code) & 0x18)
+#define		BPF_W		0x00
+#define		BPF_H		0x08
+#define		BPF_B		0x10
+#define BPF_MODE(code)  ((code) & 0xe0)
+#define		BPF_IMM		0x00
+#define		BPF_ABS		0x20
+#define		BPF_IND		0x40
+#define		BPF_MEM		0x60
+#define		BPF_LEN		0x80
+#define		BPF_MSH		0xa0
+
+/* alu/jmp fields */
+#define BPF_OP(code)    ((code) & 0xf0)
+#define		BPF_ADD		0x00
+#define		BPF_SUB		0x10
+#define		BPF_MUL		0x20
+#define		BPF_DIV		0x30
+#define		BPF_OR		0x40
+#define		BPF_AND		0x50
+#define		BPF_LSH		0x60
+#define		BPF_RSH		0x70
+#define		BPF_NEG		0x80
+#define		BPF_MOD		0x90
+#define		BPF_XOR		0xa0
+
+#define		BPF_JA		0x00
+#define		BPF_JEQ		0x10
+#define		BPF_JGT		0x20
+#define		BPF_JGE		0x30
+#define		BPF_JSET        0x40
+#define BPF_SRC(code)   ((code) & 0x08)
+#define		BPF_K		0x00
+#define		BPF_X		0x08
+
+#ifndef BPF_MAXINSNS
+#define BPF_MAXINSNS 4096
+#endif
+
+#endif /* _UAPI__LINUX_BPF_COMMON_H__ */
diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h
index 253b4d42cf2b..47785d5ecf17 100644
--- a/include/uapi/linux/filter.h
+++ b/include/uapi/linux/filter.h
@@ -7,7 +7,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-
+#include <linux/bpf_common.h>
 
 /*
  * Current version of the filter code architecture.
@@ -32,56 +32,6 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 	struct sock_filter __user *filter;
 };
 
-/*
- * Instruction classes
- */
-
-#define BPF_CLASS(code) ((code) & 0x07)
-#define         BPF_LD          0x00
-#define         BPF_LDX         0x01
-#define         BPF_ST          0x02
-#define         BPF_STX         0x03
-#define         BPF_ALU         0x04
-#define         BPF_JMP         0x05
-#define         BPF_RET         0x06
-#define         BPF_MISC        0x07
-
-/* ld/ldx fields */
-#define BPF_SIZE(code)  ((code) & 0x18)
-#define         BPF_W           0x00
-#define         BPF_H           0x08
-#define         BPF_B           0x10
-#define BPF_MODE(code)  ((code) & 0xe0)
-#define         BPF_IMM         0x00
-#define         BPF_ABS         0x20
-#define         BPF_IND         0x40
-#define         BPF_MEM         0x60
-#define         BPF_LEN         0x80
-#define         BPF_MSH         0xa0
-
-/* alu/jmp fields */
-#define BPF_OP(code)    ((code) & 0xf0)
-#define         BPF_ADD         0x00
-#define         BPF_SUB         0x10
-#define         BPF_MUL         0x20
-#define         BPF_DIV         0x30
-#define         BPF_OR          0x40
-#define         BPF_AND         0x50
-#define         BPF_LSH         0x60
-#define         BPF_RSH         0x70
-#define         BPF_NEG         0x80
-#define		BPF_MOD		0x90
-#define		BPF_XOR		0xa0
-
-#define         BPF_JA          0x00
-#define         BPF_JEQ         0x10
-#define         BPF_JGT         0x20
-#define         BPF_JGE         0x30
-#define         BPF_JSET        0x40
-#define BPF_SRC(code)   ((code) & 0x08)
-#define         BPF_K           0x00
-#define         BPF_X           0x08
-
 /* ret - BPF_K and BPF_X also apply */
 #define BPF_RVAL(code)  ((code) & 0x18)
 #define         BPF_A           0x10
@@ -91,10 +41,6 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 #define         BPF_TAX         0x00
 #define         BPF_TXA         0x80
 
-#ifndef BPF_MAXINSNS
-#define BPF_MAXINSNS 4096
-#endif
-
 /*
  * Macros for filter block array initializers.
  */
-- 
cgit v1.2.3


From db404b13617fe0cdb415da55762203d456837912 Mon Sep 17 00:00:00 2001
From: Mark Rustad <mark.d.rustad@intel.com>
Date: Tue, 14 Oct 2014 06:28:38 -0700
Subject: genl_magic: Resolve logical-op warnings

Resolve "logical 'and' applied to non-boolean constant" warnings"
that appear in W=2 builds by adding !! to a bit test.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/genl_magic_func.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index c0894dd8827b..667c31101b8b 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -178,12 +178,12 @@ static int s_name ## _from_attrs_for_change(struct s_name *s,		\
 #define __assign(attr_nr, attr_flag, name, nla_type, type, assignment...)	\
 		nla = ntb[attr_nr];						\
 		if (nla) {						\
-			if (exclude_invariants && ((attr_flag) & DRBD_F_INVARIANT)) {		\
+			if (exclude_invariants && !!((attr_flag) & DRBD_F_INVARIANT)) {		\
 				pr_info("<< must not change invariant attr: %s\n", #name);	\
 				return -EEXIST;				\
 			}						\
 			assignment;					\
-		} else if (exclude_invariants && ((attr_flag) & DRBD_F_INVARIANT)) {		\
+		} else if (exclude_invariants && !!((attr_flag) & DRBD_F_INVARIANT)) {		\
 			/* attribute missing from payload, */		\
 			/* which was expected */			\
 		} else if ((attr_flag) & DRBD_F_REQUIRED) {		\
-- 
cgit v1.2.3


From 016c98c6fe0c914d12e2e242b2bccde6d6dea54b Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 14 Oct 2014 10:40:34 +1030
Subject: virtio: unify config_changed handling

Replace duplicated code in all transports with a single wrapper in
virtio.c.

The only functional change is in virtio_mmio.c: if a buggy device sends
us an interrupt before driver is set, we previously returned IRQ_NONE,
now we return IRQ_HANDLED.

As this must not happen in practice, this does not look like a big deal.

See also commit 3fff0179e33cd7d0a688dab65700c46ad089e934
	virtio-pci: do not oops on config change if driver not loaded.
for the original motivation behind the driver check.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/misc/mic/card/mic_virtio.c | 6 +-----
 drivers/s390/kvm/kvm_virtio.c      | 9 +--------
 drivers/s390/kvm/virtio_ccw.c      | 6 +-----
 drivers/virtio/virtio.c            | 9 +++++++++
 drivers/virtio/virtio_mmio.c       | 7 ++-----
 drivers/virtio/virtio_pci.c        | 6 +-----
 include/linux/virtio.h             | 2 ++
 7 files changed, 17 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/mic/card/mic_virtio.c b/drivers/misc/mic/card/mic_virtio.c
index f14b60080c21..e64794730e21 100644
--- a/drivers/misc/mic/card/mic_virtio.c
+++ b/drivers/misc/mic/card/mic_virtio.c
@@ -462,16 +462,12 @@ static void mic_handle_config_change(struct mic_device_desc __iomem *d,
 	struct mic_device_ctrl __iomem *dc
 		= (void __iomem *)d + mic_aligned_desc_size(d);
 	struct mic_vdev *mvdev = (struct mic_vdev *)ioread64(&dc->vdev);
-	struct virtio_driver *drv;
 
 	if (ioread8(&dc->config_change) != MIC_VIRTIO_PARAM_CONFIG_CHANGED)
 		return;
 
 	dev_dbg(mdrv->dev, "%s %d\n", __func__, __LINE__);
-	drv = container_of(mvdev->vdev.dev.driver,
-				struct virtio_driver, driver);
-	if (drv->config_changed)
-		drv->config_changed(&mvdev->vdev);
+	virtio_config_changed(&mvdev->vdev);
 	iowrite8(1, &dc->guest_ack);
 }
 
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index a1349653c6d9..643129070c51 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -406,15 +406,8 @@ static void kvm_extint_handler(struct ext_code ext_code,
 
 	switch (param) {
 	case VIRTIO_PARAM_CONFIG_CHANGED:
-	{
-		struct virtio_driver *drv;
-		drv = container_of(vq->vdev->dev.driver,
-				   struct virtio_driver, driver);
-		if (drv->config_changed)
-			drv->config_changed(vq->vdev);
-
+		virtio_config_changed(vq->vdev);
 		break;
-	}
 	case VIRTIO_PARAM_DEV_ADD:
 		schedule_work(&hotplug_work);
 		break;
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index d2c0b442bce5..6cbe6ef3c889 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -940,11 +940,7 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev,
 		vring_interrupt(0, vq);
 	}
 	if (test_bit(0, &vcdev->indicators2)) {
-		drv = container_of(vcdev->vdev.dev.driver,
-				   struct virtio_driver, driver);
-
-		if (drv && drv->config_changed)
-			drv->config_changed(&vcdev->vdev);
+		virtio_config_changed(&vcdev->vdev);
 		clear_bit(0, &vcdev->indicators2);
 	}
 }
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index fed0ce198ae3..3980687401f6 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -239,6 +239,15 @@ void unregister_virtio_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(unregister_virtio_device);
 
+void virtio_config_changed(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	if (drv && drv->config_changed)
+		drv->config_changed(dev);
+}
+EXPORT_SYMBOL_GPL(virtio_config_changed);
+
 static int virtio_init(void)
 {
 	if (bus_register(&virtio_bus) != 0)
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index c600ccfd6922..ef9a1650bb80 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -234,8 +234,6 @@ static irqreturn_t vm_interrupt(int irq, void *opaque)
 {
 	struct virtio_mmio_device *vm_dev = opaque;
 	struct virtio_mmio_vq_info *info;
-	struct virtio_driver *vdrv = container_of(vm_dev->vdev.dev.driver,
-			struct virtio_driver, driver);
 	unsigned long status;
 	unsigned long flags;
 	irqreturn_t ret = IRQ_NONE;
@@ -244,9 +242,8 @@ static irqreturn_t vm_interrupt(int irq, void *opaque)
 	status = readl(vm_dev->base + VIRTIO_MMIO_INTERRUPT_STATUS);
 	writel(status, vm_dev->base + VIRTIO_MMIO_INTERRUPT_ACK);
 
-	if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)
-			&& vdrv && vdrv->config_changed) {
-		vdrv->config_changed(&vm_dev->vdev);
+	if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)) {
+		virtio_config_changed(&vm_dev->vdev);
 		ret = IRQ_HANDLED;
 	}
 
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index add40d00dcdb..f39f4e772e6a 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -211,12 +211,8 @@ static bool vp_notify(struct virtqueue *vq)
 static irqreturn_t vp_config_changed(int irq, void *opaque)
 {
 	struct virtio_pci_device *vp_dev = opaque;
-	struct virtio_driver *drv;
-	drv = container_of(vp_dev->vdev.dev.driver,
-			   struct virtio_driver, driver);
 
-	if (drv && drv->config_changed)
-		drv->config_changed(&vp_dev->vdev);
+	virtio_config_changed(&vp_dev->vdev);
 	return IRQ_HANDLED;
 }
 
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index b46671e28de2..3c19bd3189cb 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -108,6 +108,8 @@ void unregister_virtio_device(struct virtio_device *dev);
 
 void virtio_break_device(struct virtio_device *dev);
 
+void virtio_config_changed(struct virtio_device *dev);
+
 /**
  * virtio_driver - operations for a virtio I/O driver
  * @driver: underlying device driver (populate name and owner).
-- 
cgit v1.2.3


From c6716bae52f97347e25166c6270aa98693d9212c Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 14 Oct 2014 10:40:35 +1030
Subject: virtio-pci: move freeze/restore to virtio core

This is in preparation to extending config changed event handling
in core.
Wrapping these in an API also seems to make for a cleaner code.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/virtio/virtio.c     | 54 +++++++++++++++++++++++++++++++++++++++++++++
 drivers/virtio/virtio_pci.c | 54 ++-------------------------------------------
 include/linux/virtio.h      |  6 +++++
 3 files changed, 62 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 3980687401f6..8216b7311092 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -248,6 +248,60 @@ void virtio_config_changed(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(virtio_config_changed);
 
+#ifdef CONFIG_PM_SLEEP
+int virtio_device_freeze(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
+
+	if (drv && drv->freeze)
+		return drv->freeze(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_freeze);
+
+int virtio_device_restore(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up. */
+	dev->config->reset(dev);
+
+	/* Acknowledge that we've seen the device. */
+	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+	/* Maybe driver failed before freeze.
+	 * Restore the failed status, for debugging. */
+	if (dev->failed)
+		add_status(dev, VIRTIO_CONFIG_S_FAILED);
+
+	if (!drv)
+		return 0;
+
+	/* We have a driver! */
+	add_status(dev, VIRTIO_CONFIG_S_DRIVER);
+
+	dev->config->finalize_features(dev);
+
+	if (drv->restore) {
+		int ret = drv->restore(dev);
+		if (ret) {
+			add_status(dev, VIRTIO_CONFIG_S_FAILED);
+			return ret;
+		}
+	}
+
+	/* Finally, tell the device we're all set */
+	add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_restore);
+#endif
+
 static int virtio_init(void)
 {
 	if (bus_register(&virtio_bus) != 0)
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index f39f4e772e6a..d34ebfa604f3 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -57,9 +57,6 @@ struct virtio_pci_device
 	/* Vectors allocated, excluding per-vq vectors if any */
 	unsigned msix_used_vectors;
 
-	/* Status saved during hibernate/restore */
-	u8 saved_status;
-
 	/* Whether we have vector per vq */
 	bool per_vq_vectors;
 };
@@ -764,16 +761,9 @@ static int virtio_pci_freeze(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
-	struct virtio_driver *drv;
 	int ret;
 
-	drv = container_of(vp_dev->vdev.dev.driver,
-			   struct virtio_driver, driver);
-
-	ret = 0;
-	vp_dev->saved_status = vp_get_status(&vp_dev->vdev);
-	if (drv && drv->freeze)
-		ret = drv->freeze(&vp_dev->vdev);
+	ret = virtio_device_freeze(&vp_dev->vdev);
 
 	if (!ret)
 		pci_disable_device(pci_dev);
@@ -784,54 +774,14 @@ static int virtio_pci_restore(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
-	struct virtio_driver *drv;
-	unsigned status = 0;
 	int ret;
 
-	drv = container_of(vp_dev->vdev.dev.driver,
-			   struct virtio_driver, driver);
-
 	ret = pci_enable_device(pci_dev);
 	if (ret)
 		return ret;
 
 	pci_set_master(pci_dev);
-	/* We always start by resetting the device, in case a previous
-	 * driver messed it up. */
-	vp_reset(&vp_dev->vdev);
-
-	/* Acknowledge that we've seen the device. */
-	status |= VIRTIO_CONFIG_S_ACKNOWLEDGE;
-	vp_set_status(&vp_dev->vdev, status);
-
-	/* Maybe driver failed before freeze.
-	 * Restore the failed status, for debugging. */
-	status |= vp_dev->saved_status & VIRTIO_CONFIG_S_FAILED;
-	vp_set_status(&vp_dev->vdev, status);
-
-	if (!drv)
-		return 0;
-
-	/* We have a driver! */
-	status |= VIRTIO_CONFIG_S_DRIVER;
-	vp_set_status(&vp_dev->vdev, status);
-
-	vp_finalize_features(&vp_dev->vdev);
-
-	if (drv->restore) {
-		ret = drv->restore(&vp_dev->vdev);
-		if (ret) {
-			status |= VIRTIO_CONFIG_S_FAILED;
-			vp_set_status(&vp_dev->vdev, status);
-			return ret;
-		}
-	}
-
-	/* Finally, tell the device we're all set */
-	status |= VIRTIO_CONFIG_S_DRIVER_OK;
-	vp_set_status(&vp_dev->vdev, status);
-
-	return ret;
+	return virtio_device_restore(&vp_dev->vdev);
 }
 
 static const struct dev_pm_ops virtio_pci_pm_ops = {
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 3c19bd3189cb..8df7ba81e5c7 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -78,6 +78,7 @@ bool virtqueue_is_broken(struct virtqueue *vq);
 /**
  * virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
+ * @failed: saved value for CONFIG_S_FAILED bit (for restore)
  * @dev: underlying device.
  * @id: the device type identification (used to match it with a driver).
  * @config: the configuration ops for this device.
@@ -88,6 +89,7 @@ bool virtqueue_is_broken(struct virtqueue *vq);
  */
 struct virtio_device {
 	int index;
+	bool failed;
 	struct device dev;
 	struct virtio_device_id id;
 	const struct virtio_config_ops *config;
@@ -109,6 +111,10 @@ void unregister_virtio_device(struct virtio_device *dev);
 void virtio_break_device(struct virtio_device *dev);
 
 void virtio_config_changed(struct virtio_device *dev);
+#ifdef CONFIG_PM_SLEEP
+int virtio_device_freeze(struct virtio_device *dev);
+int virtio_device_restore(struct virtio_device *dev);
+#endif
 
 /**
  * virtio_driver - operations for a virtio I/O driver
-- 
cgit v1.2.3


From 22b7050a024d7deb0c9ef1e14ed73e3b1e369f24 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 15 Oct 2014 10:21:55 +1030
Subject: virtio: defer config changed notifications

Defer config changed notifications that arrive during
probe/scan/freeze/restore.

This will allow drivers to set DRIVER_OK earlier, without worrying about
racing with config change interrupts.

This change will also benefit old hypervisors (before 2009)
that send interrupts without checking DRIVER_OK: previously,
the callback could race with driver-specific initialization.

This will also help simplify drivers.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (cosmetic changes)
---
 drivers/virtio/virtio.c | 58 +++++++++++++++++++++++++++++++++++++++++--------
 include/linux/virtio.h  |  6 +++++
 2 files changed, 55 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 8216b7311092..df598dd8c5c8 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -117,6 +117,43 @@ void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
 }
 EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
 
+static void __virtio_config_changed(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	if (!dev->config_enabled)
+		dev->config_change_pending = true;
+	else if (drv && drv->config_changed)
+		drv->config_changed(dev);
+}
+
+void virtio_config_changed(struct virtio_device *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->config_lock, flags);
+	__virtio_config_changed(dev);
+	spin_unlock_irqrestore(&dev->config_lock, flags);
+}
+EXPORT_SYMBOL_GPL(virtio_config_changed);
+
+static void virtio_config_disable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_enabled = false;
+	spin_unlock_irq(&dev->config_lock);
+}
+
+static void virtio_config_enable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_enabled = true;
+	if (dev->config_change_pending)
+		__virtio_config_changed(dev);
+	dev->config_change_pending = false;
+	spin_unlock_irq(&dev->config_lock);
+}
+
 static int virtio_dev_probe(struct device *_d)
 {
 	int err, i;
@@ -153,6 +190,8 @@ static int virtio_dev_probe(struct device *_d)
 		add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
 		if (drv->scan)
 			drv->scan(dev);
+
+		virtio_config_enable(dev);
 	}
 
 	return err;
@@ -163,6 +202,8 @@ static int virtio_dev_remove(struct device *_d)
 	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 
+	virtio_config_disable(dev);
+
 	drv->remove(dev);
 
 	/* Driver should have reset device. */
@@ -211,6 +252,10 @@ int register_virtio_device(struct virtio_device *dev)
 	dev->index = err;
 	dev_set_name(&dev->dev, "virtio%u", dev->index);
 
+	spin_lock_init(&dev->config_lock);
+	dev->config_enabled = false;
+	dev->config_change_pending = false;
+
 	/* We always start by resetting the device, in case a previous
 	 * driver messed it up.  This also tests that code path a little. */
 	dev->config->reset(dev);
@@ -239,20 +284,13 @@ void unregister_virtio_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(unregister_virtio_device);
 
-void virtio_config_changed(struct virtio_device *dev)
-{
-	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
-
-	if (drv && drv->config_changed)
-		drv->config_changed(dev);
-}
-EXPORT_SYMBOL_GPL(virtio_config_changed);
-
 #ifdef CONFIG_PM_SLEEP
 int virtio_device_freeze(struct virtio_device *dev)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 
+	virtio_config_disable(dev);
+
 	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
 
 	if (drv && drv->freeze)
@@ -297,6 +335,8 @@ int virtio_device_restore(struct virtio_device *dev)
 	/* Finally, tell the device we're all set */
 	add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
 
+	virtio_config_enable(dev);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(virtio_device_restore);
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 8df7ba81e5c7..65261a7244fc 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -79,6 +79,9 @@ bool virtqueue_is_broken(struct virtqueue *vq);
  * virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
  * @failed: saved value for CONFIG_S_FAILED bit (for restore)
+ * @config_enabled: configuration change reporting enabled
+ * @config_change_pending: configuration change reported while disabled
+ * @config_lock: protects configuration change reporting
  * @dev: underlying device.
  * @id: the device type identification (used to match it with a driver).
  * @config: the configuration ops for this device.
@@ -90,6 +93,9 @@ bool virtqueue_is_broken(struct virtqueue *vq);
 struct virtio_device {
 	int index;
 	bool failed;
+	bool config_enabled;
+	bool config_change_pending;
+	spinlock_t config_lock;
 	struct device dev;
 	struct virtio_device_id id;
 	const struct virtio_config_ops *config;
-- 
cgit v1.2.3


From 3569db593081fd88bbd6df21b9b0531873f2042c Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 15 Oct 2014 10:22:30 +1030
Subject: virtio: add API to enable VQs early

virtio spec 0.9.X requires DRIVER_OK to be set before
VQs are used, but some drivers use VQs before probe
function returns.
Since DRIVER_OK is set after probe, this violates the spec.

Even though under virtio 1.0 transitional devices support this
behaviour, we want to make it possible for those early callers to become
spec compliant and eventually support non-transitional devices.

Add API for drivers to call before using VQs.

Sets DRIVER_OK internally.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/virtio_config.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index e8f8f71e843c..7f4ef66873ef 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -109,6 +109,23 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev,
 	return vq;
 }
 
+/**
+ * virtio_device_ready - enable vq use in probe function
+ * @vdev: the device
+ *
+ * Driver must call this to use vqs in the probe function.
+ *
+ * Note: vqs are enabled automatically after probe returns.
+ */
+static inline
+void virtio_device_ready(struct virtio_device *dev)
+{
+	unsigned status = dev->config->get_status(dev);
+
+	BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
+	dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK);
+}
+
 static inline
 const char *virtio_bus_name(struct virtio_device *vdev)
 {
-- 
cgit v1.2.3


From 46e8c83c83c06b90ebc000df481c2fdcee79a141 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 23 Sep 2014 17:18:10 +0300
Subject: dmaengine: dw: move private definitions to regs.h

Since we don't allow user to set registers directly through private slave
configuration we may move definitions to the regs.h because they are not used
anywhere except core.c part.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/dma/dw/regs.h                | 32 +++++++++++++++++++++++++++++---
 include/linux/platform_data/dma-dw.h | 31 -------------------------------
 2 files changed, 29 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index 00d27a9d9c27..e8f92b28ffc2 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -11,7 +11,6 @@
 
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
-#include <linux/platform_data/dma-dw.h>
 
 #define DW_DMA_MAX_NR_CHANNELS	8
 #define DW_DMA_MAX_NR_REQUESTS	16
@@ -132,6 +131,18 @@ struct dw_dma_regs {
 /* Bitfields in DWC_PARAMS */
 #define DWC_PARAMS_MBLK_EN	11		/* multi block transfer */
 
+/* bursts size */
+enum dw_dma_msize {
+	DW_DMA_MSIZE_1,
+	DW_DMA_MSIZE_4,
+	DW_DMA_MSIZE_8,
+	DW_DMA_MSIZE_16,
+	DW_DMA_MSIZE_32,
+	DW_DMA_MSIZE_64,
+	DW_DMA_MSIZE_128,
+	DW_DMA_MSIZE_256,
+};
+
 /* Bitfields in CTL_LO */
 #define DWC_CTLL_INT_EN		(1 << 0)	/* irqs enabled? */
 #define DWC_CTLL_DST_WIDTH(n)	((n)<<1)	/* bytes per element */
@@ -161,20 +172,35 @@ struct dw_dma_regs {
 #define DWC_CTLH_DONE		0x00001000
 #define DWC_CTLH_BLOCK_TS_MASK	0x00000fff
 
-/* Bitfields in CFG_LO. Platform-configurable bits are in <linux/platform_data/dma-dw.h> */
+/* Bitfields in CFG_LO */
 #define DWC_CFGL_CH_PRIOR_MASK	(0x7 << 5)	/* priority mask */
 #define DWC_CFGL_CH_PRIOR(x)	((x) << 5)	/* priority */
 #define DWC_CFGL_CH_SUSP	(1 << 8)	/* pause xfer */
 #define DWC_CFGL_FIFO_EMPTY	(1 << 9)	/* pause xfer */
 #define DWC_CFGL_HS_DST		(1 << 10)	/* handshake w/dst */
 #define DWC_CFGL_HS_SRC		(1 << 11)	/* handshake w/src */
+#define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
+#define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
+#define DWC_CFGL_LOCK_CH_XACT	(2 << 12)
+#define DWC_CFGL_LOCK_BUS_XFER	(0 << 14)	/* scope of LOCK_BUS */
+#define DWC_CFGL_LOCK_BUS_BLOCK	(1 << 14)
+#define DWC_CFGL_LOCK_BUS_XACT	(2 << 14)
+#define DWC_CFGL_LOCK_CH	(1 << 15)	/* channel lockout */
+#define DWC_CFGL_LOCK_BUS	(1 << 16)	/* busmaster lockout */
+#define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
+#define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
 #define DWC_CFGL_MAX_BURST(x)	((x) << 20)
 #define DWC_CFGL_RELOAD_SAR	(1 << 30)
 #define DWC_CFGL_RELOAD_DAR	(1 << 31)
 
-/* Bitfields in CFG_HI. Platform-configurable bits are in <linux/platform_data/dma-dw.h> */
+/* Bitfields in CFG_HI */
+#define DWC_CFGH_FCMODE		(1 << 0)
+#define DWC_CFGH_FIFO_MODE	(1 << 1)
+#define DWC_CFGH_PROTCTL(x)	((x) << 2)
 #define DWC_CFGH_DS_UPD_EN	(1 << 5)
 #define DWC_CFGH_SS_UPD_EN	(1 << 6)
+#define DWC_CFGH_SRC_PER(x)	((x) << 7)
+#define DWC_CFGH_DST_PER(x)	((x) << 11)
 
 /* Bitfields in SGR */
 #define DWC_SGR_SGI(x)		((x) << 0)
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
index bc411a1bf8e7..d0c97da66e22 100644
--- a/include/linux/platform_data/dma-dw.h
+++ b/include/linux/platform_data/dma-dw.h
@@ -56,37 +56,6 @@ struct dw_dma_platform_data {
 	unsigned char	data_width[4];
 };
 
-/* bursts size */
-enum dw_dma_msize {
-	DW_DMA_MSIZE_1,
-	DW_DMA_MSIZE_4,
-	DW_DMA_MSIZE_8,
-	DW_DMA_MSIZE_16,
-	DW_DMA_MSIZE_32,
-	DW_DMA_MSIZE_64,
-	DW_DMA_MSIZE_128,
-	DW_DMA_MSIZE_256,
-};
-
-/* Platform-configurable bits in CFG_HI */
-#define DWC_CFGH_FCMODE		(1 << 0)
-#define DWC_CFGH_FIFO_MODE	(1 << 1)
-#define DWC_CFGH_PROTCTL(x)	((x) << 2)
-#define DWC_CFGH_SRC_PER(x)	((x) << 7)
-#define DWC_CFGH_DST_PER(x)	((x) << 11)
-
-/* Platform-configurable bits in CFG_LO */
-#define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
-#define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
-#define DWC_CFGL_LOCK_CH_XACT	(2 << 12)
-#define DWC_CFGL_LOCK_BUS_XFER	(0 << 14)	/* scope of LOCK_BUS */
-#define DWC_CFGL_LOCK_BUS_BLOCK	(1 << 14)
-#define DWC_CFGL_LOCK_BUS_XACT	(2 << 14)
-#define DWC_CFGL_LOCK_CH	(1 << 15)	/* channel lockout */
-#define DWC_CFGL_LOCK_BUS	(1 << 16)	/* busmaster lockout */
-#define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
-#define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
-
 /* DMA API extensions */
 struct dw_cyclic_desc {
 	struct dw_desc	**desc;
-- 
cgit v1.2.3


From 3d588f83e4d6a5230d9094b97d38621cbaa9a972 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 23 Sep 2014 17:18:11 +0300
Subject: dmaengine: dw: split dma-dw.h to platform and private parts

The introduced include/linux/dma/dw.h is going to contain the private
extensions and structures which are shared for dw_dmac users in the kernel.
Meanwhile include/linux/platform_data/dma-dw.h keeps only platform related data
types and definitions.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/dma/dw/internal.h            |  2 ++
 include/linux/dma/dw.h               | 37 ++++++++++++++++++++++++++++++++++++
 include/linux/platform_data/dma-dw.h | 27 ++++----------------------
 sound/atmel/abdac.c                  |  4 +++-
 sound/atmel/ac97c.c                  |  1 +
 5 files changed, 47 insertions(+), 24 deletions(-)
 create mode 100644 include/linux/dma/dw.h

(limited to 'include')

diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h
index 82258a167a0e..9a886e3c31d3 100644
--- a/drivers/dma/dw/internal.h
+++ b/drivers/dma/dw/internal.h
@@ -12,6 +12,8 @@
 #define _DW_DMAC_INTERNAL_H
 
 #include <linux/device.h>
+
+#include <linux/dma/dw.h>
 #include <linux/platform_data/dma-dw.h>
 
 #include "regs.h"
diff --git a/include/linux/dma/dw.h b/include/linux/dma/dw.h
new file mode 100644
index 000000000000..24756130eadb
--- /dev/null
+++ b/include/linux/dma/dw.h
@@ -0,0 +1,37 @@
+/*
+ * Driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2007 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _DMA_DW_H
+#define _DMA_DW_H
+
+#include <linux/dmaengine.h>
+
+/* DMA API extensions */
+struct dw_desc;
+
+struct dw_cyclic_desc {
+	struct dw_desc	**desc;
+	unsigned long	periods;
+	void		(*period_callback)(void *param);
+	void		*period_callback_param;
+};
+
+struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
+		dma_addr_t buf_addr, size_t buf_len, size_t period_len,
+		enum dma_transfer_direction direction);
+void dw_dma_cyclic_free(struct dma_chan *chan);
+int dw_dma_cyclic_start(struct dma_chan *chan);
+void dw_dma_cyclic_stop(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
+
+#endif /* _DMA_DW_H */
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
index d0c97da66e22..d8155c005242 100644
--- a/include/linux/platform_data/dma-dw.h
+++ b/include/linux/platform_data/dma-dw.h
@@ -8,10 +8,10 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#ifndef DW_DMAC_H
-#define DW_DMAC_H
+#ifndef _PLATFORM_DATA_DMA_DW_H
+#define _PLATFORM_DATA_DMA_DW_H
 
-#include <linux/dmaengine.h>
+#include <linux/device.h>
 
 /**
  * struct dw_dma_slave - Controller-specific information about a slave
@@ -56,23 +56,4 @@ struct dw_dma_platform_data {
 	unsigned char	data_width[4];
 };
 
-/* DMA API extensions */
-struct dw_cyclic_desc {
-	struct dw_desc	**desc;
-	unsigned long	periods;
-	void		(*period_callback)(void *param);
-	void		*period_callback_param;
-};
-
-struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
-		dma_addr_t buf_addr, size_t buf_len, size_t period_len,
-		enum dma_transfer_direction direction);
-void dw_dma_cyclic_free(struct dma_chan *chan);
-int dw_dma_cyclic_start(struct dma_chan *chan);
-void dw_dma_cyclic_stop(struct dma_chan *chan);
-
-dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
-
-dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
-
-#endif /* DW_DMAC_H */
+#endif /* _PLATFORM_DATA_DMA_DW_H */
diff --git a/sound/atmel/abdac.c b/sound/atmel/abdac.c
index 154a7c44e38d..31061e3521d4 100644
--- a/sound/atmel/abdac.c
+++ b/sound/atmel/abdac.c
@@ -9,7 +9,6 @@
  */
 #include <linux/clk.h>
 #include <linux/bitmap.h>
-#include <linux/platform_data/dma-dw.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/init.h>
@@ -25,6 +24,9 @@
 #include <sound/pcm_params.h>
 #include <sound/atmel-abdac.h>
 
+#include <linux/platform_data/dma-dw.h>
+#include <linux/dma/dw.h>
+
 /* DAC register offsets */
 #define DAC_DATA                                0x0000
 #define DAC_CTRL                                0x0008
diff --git a/sound/atmel/ac97c.c b/sound/atmel/ac97c.c
index 1dfb35afef8f..b59427d5a697 100644
--- a/sound/atmel/ac97c.c
+++ b/sound/atmel/ac97c.c
@@ -32,6 +32,7 @@
 #include <sound/memalloc.h>
 
 #include <linux/platform_data/dma-dw.h>
+#include <linux/dma/dw.h>
 
 #include <mach/cpu.h>
 
-- 
cgit v1.2.3


From 2a52f6e49e5e400ed98a79503193d81207009647 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 23 Sep 2014 17:18:15 +0300
Subject: dmaengine: dw: export probe()/remove() and Co to users

The driver library functions can be used directly by the compound devices such
as ADSP or serial driver where DesignWare DMA IP is privately attached to the
main hardware.

Instead of creating a new platform device leaf they may call dw_dma_probe()
with given struct dw_dma_chip directly and make sure that the main device is
DMA capable.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/dma/dw/internal.h | 29 +++--------------------------
 include/linux/dma/dw.h    | 27 +++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h
index c55c3e0bf1fe..41439732ff6b 100644
--- a/drivers/dma/dw/internal.h
+++ b/drivers/dma/dw/internal.h
@@ -8,39 +8,16 @@
  * published by the Free Software Foundation.
  */
 
-#ifndef _DW_DMAC_INTERNAL_H
-#define _DW_DMAC_INTERNAL_H
-
-#include <linux/device.h>
+#ifndef _DMA_DW_INTERNAL_H
+#define _DMA_DW_INTERNAL_H
 
 #include <linux/dma/dw.h>
-#include <linux/platform_data/dma-dw.h>
 
 #include "regs.h"
 
-/**
- * struct dw_dma_chip - representation of DesignWare DMA controller hardware
- * @dev:		struct device of the DMA controller
- * @irq:		irq line
- * @regs:		memory mapped I/O space
- * @clk:		hclk clock
- * @dw:			struct dw_dma that is filed by dw_dma_probe()
- */
-struct dw_dma_chip {
-	struct device	*dev;
-	int		irq;
-	void __iomem	*regs;
-	struct clk	*clk;
-	struct dw_dma	*dw;
-};
-
-/* Export to the platform drivers */
-int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata);
-int dw_dma_remove(struct dw_dma_chip *chip);
-
 int dw_dma_disable(struct dw_dma_chip *chip);
 int dw_dma_enable(struct dw_dma_chip *chip);
 
 extern bool dw_dma_filter(struct dma_chan *chan, void *param);
 
-#endif /* _DW_DMAC_INTERNAL_H */
+#endif /* _DMA_DW_INTERNAL_H */
diff --git a/include/linux/dma/dw.h b/include/linux/dma/dw.h
index 24756130eadb..71456442ebe3 100644
--- a/include/linux/dma/dw.h
+++ b/include/linux/dma/dw.h
@@ -3,6 +3,7 @@
  *
  * Copyright (C) 2007 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
+ * Copyright (C) 2014 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -11,8 +12,34 @@
 #ifndef _DMA_DW_H
 #define _DMA_DW_H
 
+#include <linux/clk.h>
+#include <linux/device.h>
 #include <linux/dmaengine.h>
 
+#include <linux/platform_data/dma-dw.h>
+
+struct dw_dma;
+
+/**
+ * struct dw_dma_chip - representation of DesignWare DMA controller hardware
+ * @dev:		struct device of the DMA controller
+ * @irq:		irq line
+ * @regs:		memory mapped I/O space
+ * @clk:		hclk clock
+ * @dw:			struct dw_dma that is filed by dw_dma_probe()
+ */
+struct dw_dma_chip {
+	struct device	*dev;
+	int		irq;
+	void __iomem	*regs;
+	struct clk	*clk;
+	struct dw_dma	*dw;
+};
+
+/* Export to the platform drivers */
+int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata);
+int dw_dma_remove(struct dw_dma_chip *chip);
+
 /* DMA API extensions */
 struct dw_desc;
 
-- 
cgit v1.2.3


From b65612a868768cd0431084ccf376d0946c12132d Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Sat, 11 Oct 2014 21:16:43 +0530
Subject: dmaengine: add dmaengine_prep_dma_sg() helper

This was only prep API which didnt have an helper

Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 include/linux/dmaengine.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 1f9e642c66ad..7e6b3a281da8 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -755,6 +755,16 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma(
 	return chan->device->device_prep_interleaved_dma(chan, xt, flags);
 }
 
+static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg(
+		struct dma_chan *chan,
+		struct scatterlist *dst_sg, unsigned int dst_nents,
+		struct scatterlist *src_sg, unsigned int src_nents,
+		unsigned long flags)
+{
+	return chan->device->device_prep_dma_sg(chan, dst_sg, dst_nents,
+			src_sg, src_nents, flags);
+}
+
 static inline int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 {
 	if (!chan || !caps)
-- 
cgit v1.2.3


From 0a5642be03293f73706961a7649ac1d12bd0be59 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Sat, 11 Oct 2014 21:16:44 +0530
Subject: dmaengine: freescale: add and export fsl_dma_external_start()

The freescale driver uses custom device control FSLDMA_EXTERNAL_START to
put the controller in external start mode.
Since we are planning to deprecate the device control, move this to exported
API. Subsequent patches will remove the FSLDMA_EXTERNAL_START

Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/dma/fsldma.c   | 16 +++++++++++++++-
 include/linux/fsldma.h | 13 +++++++++++++
 2 files changed, 28 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/fsldma.h

(limited to 'include')

diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index d5d6885ab341..0cded86f946c 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -36,7 +36,7 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
-
+#include <linux/fsldma.h>
 #include "dmaengine.h"
 #include "fsldma.h"
 
@@ -367,6 +367,20 @@ static void fsl_chan_toggle_ext_start(struct fsldma_chan *chan, int enable)
 		chan->feature &= ~FSL_DMA_CHAN_START_EXT;
 }
 
+int fsl_dma_external_start(struct dma_chan *dchan, int enable)
+{
+	struct fsldma_chan *chan;
+
+	if (!dchan)
+		return -EINVAL;
+
+	chan = to_fsl_chan(dchan);
+
+	fsl_chan_toggle_ext_start(chan, enable);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fsl_dma_external_start);
+
 static void append_ld_queue(struct fsldma_chan *chan, struct fsl_desc_sw *desc)
 {
 	struct fsl_desc_sw *tail = to_fsl_desc(chan->ld_pending.prev);
diff --git a/include/linux/fsldma.h b/include/linux/fsldma.h
new file mode 100644
index 000000000000..b213c02963c9
--- /dev/null
+++ b/include/linux/fsldma.h
@@ -0,0 +1,13 @@
+/*
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef FSL_DMA_H
+#define FSL_DMA_H
+/* fsl dma API for enxternal start */
+int fsl_dma_external_start(struct dma_chan *dchan, int enable);
+
+#endif
-- 
cgit v1.2.3


From b80719b6bd083130c112cb4d3e5329a164eef4c3 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Sat, 11 Oct 2014 21:16:48 +0530
Subject: dmaengine: remove FSLDMA_EXTERNAL_START

as users have been converted, so no need of this custom method

Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 include/linux/dmaengine.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 7e6b3a281da8..f8e5a9ea461a 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -199,15 +199,12 @@ enum dma_ctrl_flags {
  * configuration data in statically from the platform). An additional
  * argument of struct dma_slave_config must be passed in with this
  * command.
- * @FSLDMA_EXTERNAL_START: this command will put the Freescale DMA controller
- * into external start mode.
  */
 enum dma_ctrl_cmd {
 	DMA_TERMINATE_ALL,
 	DMA_PAUSE,
 	DMA_RESUME,
 	DMA_SLAVE_CONFIG,
-	FSLDMA_EXTERNAL_START,
 };
 
 /**
-- 
cgit v1.2.3


From 04ffcb255f22a2a988ce7393e6e72f6eb3fcb7aa Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Tue, 14 Oct 2014 15:19:06 -0700
Subject: net: Add ndo_gso_check

Add ndo_gso_check which a device can define to indicate whether is
is capable of doing GSO on a packet. This funciton would be called from
the stack to determine whether software GSO is needed to be done. A
driver should populate this function if it advertises GSO types for
which there are combinations that it wouldn't be able to handle. For
instance a device that performs UDP tunneling might only implement
support for transparent Ethernet bridging type of inner packets
or might have limitations on lengths of inner headers.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c      |  2 +-
 drivers/net/xen-netfront.c |  2 +-
 include/linux/netdevice.h  | 12 +++++++++++-
 net/core/dev.c             |  2 +-
 4 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 0c6adaaf898c..65e2892342bd 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -298,7 +298,7 @@ static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb)
 	 */
 	if (q->flags & IFF_VNET_HDR)
 		features |= vlan->tap_features;
-	if (netif_needs_gso(skb, features)) {
+	if (netif_needs_gso(dev, skb, features)) {
 		struct sk_buff *segs = __skb_gso_segment(skb, features, false);
 
 		if (IS_ERR(segs))
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index ca82f545ec2c..3c0b37574d05 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -638,7 +638,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (unlikely(!netif_carrier_ok(dev) ||
 		     (slots > 1 && !xennet_can_sg(dev)) ||
-		     netif_needs_gso(skb, netif_skb_features(skb)))) {
+		     netif_needs_gso(dev, skb, netif_skb_features(skb)))) {
 		spin_unlock_irqrestore(&queue->tx_lock, flags);
 		goto drop;
 	}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 838407aea705..74fd5d37f15a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -998,6 +998,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	Callback to use for xmit over the accelerated station. This
  *	is used in place of ndo_start_xmit on accelerated net
  *	devices.
+ * bool	(*ndo_gso_check) (struct sk_buff *skb,
+ *			  struct net_device *dev);
+ *	Called by core transmit path to determine if device is capable of
+ *	performing GSO on a packet. The device returns true if it is
+ *	able to GSO the packet, false otherwise. If the return value is
+ *	false the stack will do software GSO.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1147,6 +1153,8 @@ struct net_device_ops {
 							struct net_device *dev,
 							void *priv);
 	int			(*ndo_get_lock_subclass)(struct net_device *dev);
+	bool			(*ndo_gso_check) (struct sk_buff *skb,
+						  struct net_device *dev);
 };
 
 /**
@@ -3572,10 +3580,12 @@ static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
 	       (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
 }
 
-static inline bool netif_needs_gso(struct sk_buff *skb,
+static inline bool netif_needs_gso(struct net_device *dev, struct sk_buff *skb,
 				   netdev_features_t features)
 {
 	return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
+		(dev->netdev_ops->ndo_gso_check &&
+		 !dev->netdev_ops->ndo_gso_check(skb, dev)) ||
 		unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
 			 (skb->ip_summed != CHECKSUM_UNNECESSARY)));
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 4699dcfdc4ab..9f77a78c6b1c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2675,7 +2675,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 	if (skb->encapsulation)
 		features &= dev->hw_enc_features;
 
-	if (netif_needs_gso(skb, features)) {
+	if (netif_needs_gso(dev, skb, features)) {
 		struct sk_buff *segs;
 
 		segs = skb_gso_segment(skb, features);
-- 
cgit v1.2.3


From 2df36a5dd6792870bef48f63bfca42055ea5b79c Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Sun, 28 Sep 2014 16:04:26 +0200
Subject: arm/arm64: KVM: Fix BE accesses to GICv2 EISR and ELRSR regs

The EIRSR and ELRSR registers are 32-bit registers on GICv2, and we
store these as an array of two such registers on the vgic vcpu struct.
However, we access them as a single 64-bit value or as a bitmap pointer
in the generic vgic code, which breaks BE support.

Instead, store them as u64 values on the vgic structure and do the
word-swapping in the assembly code, which already handles the byte order
for BE systems.

Tested-by: Victor Kamensky <victor.kamensky@linaro.org>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 arch/arm/kvm/interrupts_head.S  |  7 +++++++
 arch/arm64/kvm/vgic-v2-switch.S | 12 ++++++++----
 include/kvm/arm_vgic.h          |  4 ++--
 virt/kvm/arm/vgic-v2.c          | 24 +++---------------------
 virt/kvm/arm/vgic.c             | 18 ++++++++++++++++--
 5 files changed, 36 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 98c8c5b9a87f..14d488388480 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -433,10 +433,17 @@ ARM_BE8(rev	r10, r10	)
 	str	r3, [r11, #VGIC_V2_CPU_HCR]
 	str	r4, [r11, #VGIC_V2_CPU_VMCR]
 	str	r5, [r11, #VGIC_V2_CPU_MISR]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	str	r6, [r11, #(VGIC_V2_CPU_EISR + 4)]
+	str	r7, [r11, #VGIC_V2_CPU_EISR]
+	str	r8, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
+	str	r9, [r11, #VGIC_V2_CPU_ELRSR]
+#else
 	str	r6, [r11, #VGIC_V2_CPU_EISR]
 	str	r7, [r11, #(VGIC_V2_CPU_EISR + 4)]
 	str	r8, [r11, #VGIC_V2_CPU_ELRSR]
 	str	r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
+#endif
 	str	r10, [r11, #VGIC_V2_CPU_APR]
 
 	/* Clear GICH_HCR */
diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S
index ae211772f991..f002fe1c3700 100644
--- a/arch/arm64/kvm/vgic-v2-switch.S
+++ b/arch/arm64/kvm/vgic-v2-switch.S
@@ -67,10 +67,14 @@ CPU_BE(	rev	w11, w11 )
 	str	w4, [x3, #VGIC_V2_CPU_HCR]
 	str	w5, [x3, #VGIC_V2_CPU_VMCR]
 	str	w6, [x3, #VGIC_V2_CPU_MISR]
-	str	w7, [x3, #VGIC_V2_CPU_EISR]
-	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)]
-	str	w9, [x3, #VGIC_V2_CPU_ELRSR]
-	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)]
+CPU_LE(	str	w7, [x3, #VGIC_V2_CPU_EISR] )
+CPU_LE(	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)] )
+CPU_LE(	str	w9, [x3, #VGIC_V2_CPU_ELRSR] )
+CPU_LE(	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
+CPU_BE(	str	w7, [x3, #(VGIC_V2_CPU_EISR + 4)] )
+CPU_BE(	str	w8, [x3, #VGIC_V2_CPU_EISR] )
+CPU_BE(	str	w9, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
+CPU_BE(	str	w10, [x3, #VGIC_V2_CPU_ELRSR] )
 	str	w11, [x3, #VGIC_V2_CPU_APR]
 
 	/* Clear GICH_HCR */
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index ec559d3264cc..206dcc3b3f7a 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -219,8 +219,8 @@ struct vgic_v2_cpu_if {
 	u32		vgic_hcr;
 	u32		vgic_vmcr;
 	u32		vgic_misr;	/* Saved only */
-	u32		vgic_eisr[2];	/* Saved only */
-	u32		vgic_elrsr[2];	/* Saved only */
+	u64		vgic_eisr;	/* Saved only */
+	u64		vgic_elrsr;	/* Saved only */
 	u32		vgic_apr;
 	u32		vgic_lr[VGIC_V2_MAX_LRS];
 };
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index 01124ef3690a..2935405ad22f 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -71,35 +71,17 @@ static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
 				  struct vgic_lr lr_desc)
 {
 	if (!(lr_desc.state & LR_STATE_MASK))
-		set_bit(lr, (unsigned long *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr);
+		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr);
 }
 
 static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
 {
-	u64 val;
-
-#if BITS_PER_LONG == 64
-	val  = vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[1];
-	val <<= 32;
-	val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[0];
-#else
-	val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr;
-#endif
-	return val;
+	return vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr;
 }
 
 static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu)
 {
-	u64 val;
-
-#if BITS_PER_LONG == 64
-	val  = vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[1];
-	val <<= 32;
-	val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[0];
-#else
-	val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
-#endif
-	return val;
+	return vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
 }
 
 static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 382fb5a88b9c..3aaca49de325 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -145,6 +145,20 @@ static void vgic_free_bitmap(struct vgic_bitmap *b)
 	b->shared = NULL;
 }
 
+/*
+ * Call this function to convert a u64 value to an unsigned long * bitmask
+ * in a way that works on both 32-bit and 64-bit LE and BE platforms.
+ *
+ * Warning: Calling this function may modify *val.
+ */
+static unsigned long *u64_to_bitmask(u64 *val)
+{
+#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 32
+	*val = (*val >> 32) | (*val << 32);
+#endif
+	return (unsigned long *)val;
+}
+
 static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
 				int cpuid, u32 offset)
 {
@@ -1442,7 +1456,7 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 		 * active bit.
 		 */
 		u64 eisr = vgic_get_eisr(vcpu);
-		unsigned long *eisr_ptr = (unsigned long *)&eisr;
+		unsigned long *eisr_ptr = u64_to_bitmask(&eisr);
 		int lr;
 
 		for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
@@ -1505,7 +1519,7 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 
 	level_pending = vgic_process_maintenance(vcpu);
 	elrsr = vgic_get_elrsr(vcpu);
-	elrsr_ptr = (unsigned long *)&elrsr;
+	elrsr_ptr = u64_to_bitmask(&elrsr);
 
 	/* Clear mappings for empty LRs */
 	for_each_set_bit(lr, elrsr_ptr, vgic->nr_lr) {
-- 
cgit v1.2.3


From 2c6ba4b15b5ef38213b6c42ce09e9398f78cef9f Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 16 Oct 2014 15:47:51 +0200
Subject: netlink: fix description of portid

Avoid confusion between pid and portid.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 6c1076275aaa..7b903e1bdbbb 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -431,7 +431,7 @@ static inline int nlmsg_report(const struct nlmsghdr *nlh)
 /**
  * nlmsg_put - Add a new netlink message to an skb
  * @skb: socket buffer to store message in
- * @portid: netlink process id
+ * @portid: netlink PORTID of requesting application
  * @seq: sequence number of message
  * @type: message type
  * @payload: length of message payload
-- 
cgit v1.2.3


From e25f866fbc8a4bf387b5dbe8e25aa5b07e55c74f Mon Sep 17 00:00:00 2001
From: Cong Wang <cwang@twopensource.com>
Date: Wed, 15 Oct 2014 14:33:21 -0700
Subject: ipv4: share tcp_v4_save_options() with cookie_v4_check()

cookie_v4_check() allocates ip_options_rcu in the same way
with tcp_v4_save_options(), we can just make it a helper function.

Cc: Krzysztof Kolasa <kkolasa@winsoft.pl>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 20 ++++++++++++++++++++
 net/ipv4/syncookies.c | 10 +---------
 net/ipv4/tcp_ipv4.c   | 20 --------------------
 3 files changed, 21 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 74efeda994b3..869637a7caf7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1666,4 +1666,24 @@ int tcpv4_offload_init(void);
 void tcp_v4_init(void);
 void tcp_init(void);
 
+/*
+ * Save and compile IPv4 options, return a pointer to it
+ */
+static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
+{
+	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
+	struct ip_options_rcu *dopt = NULL;
+
+	if (opt && opt->optlen) {
+		int opt_size = sizeof(*dopt) + opt->optlen;
+
+		dopt = kmalloc(opt_size, GFP_ATOMIC);
+		if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) {
+			kfree(dopt);
+			dopt = NULL;
+		}
+	}
+	return dopt;
+}
+
 #endif	/* _TCP_H */
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 7e7401cdb9d7..c68d0a1a468e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -317,15 +317,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
-	if (opt && opt->optlen) {
-		int opt_size = sizeof(struct ip_options_rcu) + opt->optlen;
-
-		ireq->opt = kmalloc(opt_size, GFP_ATOMIC);
-		if (ireq->opt != NULL && __ip_options_echo(&ireq->opt->opt, skb, opt)) {
-			kfree(ireq->opt);
-			ireq->opt = NULL;
-		}
-	}
+	ireq->opt = tcp_v4_save_options(skb);
 
 	if (security_inet_conn_request(sk, skb, req)) {
 		reqsk_free(req);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 552e87e3c269..6a2a7d659a7a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -880,26 +880,6 @@ bool tcp_syn_flood_action(struct sock *sk,
 }
 EXPORT_SYMBOL(tcp_syn_flood_action);
 
-/*
- * Save and compile IPv4 options into the request_sock if needed.
- */
-static struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
-{
-	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
-	struct ip_options_rcu *dopt = NULL;
-
-	if (opt && opt->optlen) {
-		int opt_size = sizeof(*dopt) + opt->optlen;
-
-		dopt = kmalloc(opt_size, GFP_ATOMIC);
-		if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) {
-			kfree(dopt);
-			dopt = NULL;
-		}
-	}
-	return dopt;
-}
-
 #ifdef CONFIG_TCP_MD5SIG
 /*
  * RFC2385 MD5 checksumming requires a mapping of
-- 
cgit v1.2.3


From 461b74c391c4ec9c766794e158508c357d8952e6 Mon Sep 17 00:00:00 2001
From: Cong Wang <cwang@twopensource.com>
Date: Wed, 15 Oct 2014 14:33:22 -0700
Subject: ipv4: clean up cookie_v4_check()

We can retrieve opt from skb, no need to pass it as a parameter.
And opt should always be non-NULL, no need to check.

Cc: Krzysztof Kolasa <kkolasa@winsoft.pl>
Cc: Eric Dumazet <edumazet@google.com>
Tested-by: Krzysztof Kolasa <kkolasa@winsoft.pl>
Signed-off-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 5 ++---
 net/ipv4/syncookies.c | 6 +++---
 net/ipv4/tcp_ipv4.c   | 2 +-
 3 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 869637a7caf7..3a4bbbfdcf8d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -468,8 +468,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
 /* From syncookies.c */
 int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
 		      u32 cookie);
-struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
-			     struct ip_options *opt);
+struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
 #ifdef CONFIG_SYN_COOKIES
 
 /* Syncookies use a monotonic timer which increments every 60 seconds.
@@ -1674,7 +1673,7 @@ static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
 	const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	struct ip_options_rcu *dopt = NULL;
 
-	if (opt && opt->optlen) {
+	if (opt->optlen) {
 		int opt_size = sizeof(*dopt) + opt->optlen;
 
 		dopt = kmalloc(opt_size, GFP_ATOMIC);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index c68d0a1a468e..d346303fac77 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -255,9 +255,9 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt,
 }
 EXPORT_SYMBOL(cookie_check_timestamp);
 
-struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
-			     struct ip_options *opt)
+struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 {
+	struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	struct tcp_options_received tcp_opt;
 	struct inet_request_sock *ireq;
 	struct tcp_request_sock *treq;
@@ -336,7 +336,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
 			   inet_sk_flowi_flags(sk),
-			   (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
+			   opt->srr ? opt->faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, th->source, th->dest);
 	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(sock_net(sk), &fl4);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6a2a7d659a7a..94d1a7757ff7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1408,7 +1408,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_SYN_COOKIES
 	if (!th->syn)
-		sk = cookie_v4_check(sk, skb, &TCP_SKB_CB(skb)->header.h4.opt);
+		sk = cookie_v4_check(sk, skb);
 #endif
 	return sk;
 }
-- 
cgit v1.2.3


From 870c3151382c980590d4d609babf3b0243e7db93 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 17 Oct 2014 09:17:20 -0700
Subject: ipv6: introduce tcp_v6_iif()

Commit 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line
misses") added a regression for SO_BINDTODEVICE on IPv6.

This is because we still use inet6_iif() which expects that IP6 control
block is still at the beginning of skb->cb[]

This patch adds tcp_v6_iif() helper and uses it where necessary.

Because __inet6_lookup_skb() is used by TCP and DCCP, we add an iif
parameter to it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet6_hashtables.h |  5 +++--
 include/net/tcp.h              |  9 +++++++++
 net/dccp/ipv6.c                |  3 ++-
 net/ipv6/syncookies.c          |  2 +-
 net/ipv6/tcp_ipv6.c            | 26 +++++++++++++++-----------
 5 files changed, 30 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index ae0613544308..d1d272843b3b 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -80,7 +80,8 @@ static inline struct sock *__inet6_lookup(struct net *net,
 static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      struct sk_buff *skb,
 					      const __be16 sport,
-					      const __be16 dport)
+					      const __be16 dport,
+					      int iif)
 {
 	struct sock *sk = skb_steal_sock(skb);
 
@@ -90,7 +91,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 	return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
 			      &ipv6_hdr(skb)->saddr, sport,
 			      &ipv6_hdr(skb)->daddr, ntohs(dport),
-			      inet6_iif(skb));
+			      iif);
 }
 
 struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3a4bbbfdcf8d..c9766f89deba 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -729,6 +729,15 @@ struct tcp_skb_cb {
 
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
 
+
+/* This is the variant of inet6_iif() that must be used by TCP,
+ * as TCP moves IP6CB into a different location in skb->cb[]
+ */
+static inline int tcp_v6_iif(const struct sk_buff *skb)
+{
+	return TCP_SKB_CB(skb)->header.h6.iif;
+}
+
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
  */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index ad2acfe1ca61..6bcaa33cd804 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -757,7 +757,8 @@ static int dccp_v6_rcv(struct sk_buff *skb)
 	/* Step 2:
 	 *	Look up flow ID in table and get corresponding socket */
 	sk = __inet6_lookup_skb(&dccp_hashinfo, skb,
-			        dh->dccph_sport, dh->dccph_dport);
+			        dh->dccph_sport, dh->dccph_dport,
+				inet6_iif(skb));
 	/*
 	 * Step 2:
 	 *	If no socket ...
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 9a2838e93cc5..2a86a0f00f2b 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -214,7 +214,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		ireq->ir_iif = inet6_iif(skb);
+		ireq->ir_iif = tcp_v6_iif(skb);
 
 	ireq->ir_mark = inet_request_mark(sk, skb);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index cf2e45ab2fa4..831495529b82 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -424,6 +424,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (sock_owned_by_user(sk))
 			goto out;
 
+		/* Note : We use inet6_iif() here, not tcp_v6_iif() */
 		req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
 					   &hdr->saddr, inet6_iif(skb));
 		if (!req)
@@ -738,7 +739,7 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		ireq->ir_iif = inet6_iif(skb);
+		ireq->ir_iif = tcp_v6_iif(skb);
 
 	if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
 	    (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
@@ -860,7 +861,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 
 	fl6.flowi6_proto = IPPROTO_TCP;
 	if (rt6_need_strict(&fl6.daddr) && !oif)
-		fl6.flowi6_oif = inet6_iif(skb);
+		fl6.flowi6_oif = tcp_v6_iif(skb);
 	else
 		fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
@@ -918,7 +919,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 		sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev),
 					   &tcp_hashinfo, &ipv6h->saddr,
 					   th->source, &ipv6h->daddr,
-					   ntohs(th->source), inet6_iif(skb));
+					   ntohs(th->source), tcp_v6_iif(skb));
 		if (!sk1)
 			return;
 
@@ -1000,13 +1001,14 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb)
 	/* Find possible connection requests. */
 	req = inet6_csk_search_req(sk, &prev, th->source,
 				   &ipv6_hdr(skb)->saddr,
-				   &ipv6_hdr(skb)->daddr, inet6_iif(skb));
+				   &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb));
 	if (req)
 		return tcp_check_req(sk, skb, req, prev, false);
 
 	nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo,
-			&ipv6_hdr(skb)->saddr, th->source,
-			&ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb));
+					 &ipv6_hdr(skb)->saddr, th->source,
+					 &ipv6_hdr(skb)->daddr, ntohs(th->dest),
+					 tcp_v6_iif(skb));
 
 	if (nsk) {
 		if (nsk->sk_state != TCP_TIME_WAIT) {
@@ -1090,7 +1092,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
-		newnp->mcast_oif   = inet6_iif(skb);
+		newnp->mcast_oif   = tcp_v6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
 		newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
 		if (np->repflow)
@@ -1174,7 +1176,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 			skb_set_owner_r(newnp->pktoptions, newsk);
 	}
 	newnp->opt	  = NULL;
-	newnp->mcast_oif  = inet6_iif(skb);
+	newnp->mcast_oif  = tcp_v6_iif(skb);
 	newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
 	newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
 	if (np->repflow)
@@ -1360,7 +1362,7 @@ ipv6_pktoptions:
 	if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt &&
 	    !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
 		if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo)
-			np->mcast_oif = inet6_iif(opt_skb);
+			np->mcast_oif = tcp_v6_iif(opt_skb);
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
 			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
 		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
@@ -1427,7 +1429,8 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
 	TCP_SKB_CB(skb)->sacked = 0;
 
-	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
+	sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest,
+				tcp_v6_iif(skb));
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1514,7 +1517,7 @@ do_time_wait:
 		sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo,
 					    &ipv6_hdr(skb)->saddr, th->source,
 					    &ipv6_hdr(skb)->daddr,
-					    ntohs(th->dest), inet6_iif(skb));
+					    ntohs(th->dest), tcp_v6_iif(skb));
 		if (sk2 != NULL) {
 			struct inet_timewait_sock *tw = inet_twsk(sk);
 			inet_twsk_deschedule(tw, &tcp_death_row);
@@ -1553,6 +1556,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
 	if (th->doff < sizeof(struct tcphdr) / 4)
 		return;
 
+	/* Note : We use inet6_iif() here, not tcp_v6_iif() */
 	sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
 					&hdr->saddr, th->source,
 					&hdr->daddr, ntohs(th->dest),
-- 
cgit v1.2.3


From a28205437b41a2c1333c1599ce1e8f09af7b00d6 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 17 Oct 2014 16:02:13 -0700
Subject: net: dsa: add includes for ethtool and phy_fixed definitions

net/dsa/slave.c uses functions and structures declared in phy_fixed.h
but does not explicitely include it, while dsa.h needs structure
declarations for 'struct ethtool_wolinfo' and 'struct ethtool_eee', fix
those by including the correct header files.

Fixes: ec9436baedb6 ("net: dsa: allow drivers to do link adjustment")
Fixes: ce31b31c68e7 ("net: dsa: allow updating fixed PHY link information")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 1 +
 net/dsa/slave.c   | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 58ad8c6492db..b76559293535 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -18,6 +18,7 @@
 #include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/phy_fixed.h>
+#include <linux/ethtool.h>
 
 enum dsa_tag_protocol {
 	DSA_TAG_PROTO_NONE = 0,
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 8030489d9cbe..a851e9f14118 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -11,6 +11,7 @@
 #include <linux/list.h>
 #include <linux/etherdevice.h>
 #include <linux/phy.h>
+#include <linux/phy_fixed.h>
 #include <linux/of_net.h>
 #include <linux/of_mdio.h>
 #include "dsa_priv.h"
-- 
cgit v1.2.3


From 815afe1785da727ee48cd8e63ac4a3ec6c7459b3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 18 Oct 2014 08:34:37 -0700
Subject: tcp: fix build error if IPv6 is not enabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

$ make M=net/ipv4
  CC      net/ipv4/route.o
In file included from net/ipv4/route.c:102:0:
include/net/tcp.h: In function ‘tcp_v6_iif’:
include/net/tcp.h:738:32: error: ‘union <anonymous>’ has no member named ‘h6’
  return TCP_SKB_CB(skb)->header.h6.iif;

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 870c3151382c ("ipv6: introduce tcp_v6_iif()")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index c9766f89deba..4062b4f0d121 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -730,6 +730,7 @@ struct tcp_skb_cb {
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
 
 
+#if IS_ENABLED(CONFIG_IPV6)
 /* This is the variant of inet6_iif() that must be used by TCP,
  * as TCP moves IP6CB into a different location in skb->cb[]
  */
@@ -737,6 +738,7 @@ static inline int tcp_v6_iif(const struct sk_buff *skb)
 {
 	return TCP_SKB_CB(skb)->header.h6.iif;
 }
+#endif
 
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
-- 
cgit v1.2.3